From eedb0b12d091a21909b5e84d9f3e5e649305bd12 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 Jan 2021 14:53:22 +0100 Subject: dma-mapping: add a dma_mmap_pages helper Add a helper to map memory allocated using dma_alloc_pages into a user address space, similar to the dma_alloc_attrs function for coherent allocations. Signed-off-by: Christoph Hellwig Reviewed-by: Tomasz Figa Tested-by: Ricardo Ribalda --- kernel/dma/mapping.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'kernel') diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index b6a633679933..9ce86c77651c 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -517,6 +517,19 @@ void dma_free_pages(struct device *dev, size_t size, struct page *page, } EXPORT_SYMBOL_GPL(dma_free_pages); +int dma_mmap_pages(struct device *dev, struct vm_area_struct *vma, + size_t size, struct page *page) +{ + unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; + + if (vma->vm_pgoff >= count || vma_pages(vma) > count - vma->vm_pgoff) + return -ENXIO; + return remap_pfn_range(vma, vma->vm_start, + page_to_pfn(page) + vma->vm_pgoff, + vma_pages(vma) << PAGE_SHIFT, vma->vm_page_prot); +} +EXPORT_SYMBOL_GPL(dma_mmap_pages); + int dma_supported(struct device *dev, u64 mask) { const struct dma_map_ops *ops = get_dma_ops(dev); -- cgit v1.2.3-71-gd317 From 198c50e2ccff5c78ddbe0cb01593ac32458deb69 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Feb 2021 18:12:02 +0100 Subject: dma-mapping: refactor dma_{alloc,free}_pages Factour out internal versions without the dma_debug calls in preparation for callers that will need different dma_debug calls. Note that this changes the dma_debug calls to get the not page aligned size values, but as long as alloc and free agree on one variant we are fine. Signed-off-by: Christoph Hellwig Reviewed-by: Tomasz Figa Tested-by: Ricardo Ribalda --- kernel/dma/mapping.c | 29 +++++++++++++++++++---------- 1 file changed, 19 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 9ce86c77651c..07f964ebcda1 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -477,11 +477,10 @@ void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, } EXPORT_SYMBOL(dma_free_attrs); -struct page *dma_alloc_pages(struct device *dev, size_t size, +static struct page *__dma_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp) { const struct dma_map_ops *ops = get_dma_ops(dev); - struct page *page; if (WARN_ON_ONCE(!dev->coherent_dma_mask)) return NULL; @@ -490,31 +489,41 @@ struct page *dma_alloc_pages(struct device *dev, size_t size, size = PAGE_ALIGN(size); if (dma_alloc_direct(dev, ops)) - page = dma_direct_alloc_pages(dev, size, dma_handle, dir, gfp); - else if (ops->alloc_pages) - page = ops->alloc_pages(dev, size, dma_handle, dir, gfp); - else + return dma_direct_alloc_pages(dev, size, dma_handle, dir, gfp); + if (!ops->alloc_pages) return NULL; + return ops->alloc_pages(dev, size, dma_handle, dir, gfp); +} - debug_dma_map_page(dev, page, 0, size, dir, *dma_handle); +struct page *dma_alloc_pages(struct device *dev, size_t size, + dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp) +{ + struct page *page = __dma_alloc_pages(dev, size, dma_handle, dir, gfp); + if (page) + debug_dma_map_page(dev, page, 0, size, dir, *dma_handle); return page; } EXPORT_SYMBOL_GPL(dma_alloc_pages); -void dma_free_pages(struct device *dev, size_t size, struct page *page, +static void __dma_free_pages(struct device *dev, size_t size, struct page *page, dma_addr_t dma_handle, enum dma_data_direction dir) { const struct dma_map_ops *ops = get_dma_ops(dev); size = PAGE_ALIGN(size); - debug_dma_unmap_page(dev, dma_handle, size, dir); - if (dma_alloc_direct(dev, ops)) dma_direct_free_pages(dev, size, page, dma_handle, dir); else if (ops->free_pages) ops->free_pages(dev, size, page, dma_handle, dir); } + +void dma_free_pages(struct device *dev, size_t size, struct page *page, + dma_addr_t dma_handle, enum dma_data_direction dir) +{ + debug_dma_unmap_page(dev, dma_handle, size, dir); + __dma_free_pages(dev, size, page, dma_handle, dir); +} EXPORT_SYMBOL_GPL(dma_free_pages); int dma_mmap_pages(struct device *dev, struct vm_area_struct *vma, -- cgit v1.2.3-71-gd317 From 7d5b5738d1514e9dd8ed452660e2a4d25beb9483 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 Jan 2021 14:54:18 +0100 Subject: dma-mapping: add a dma_alloc_noncontiguous API Add a new API that returns a potentiall virtually non-contigous sg_table and a DMA address. This API is only properly implemented for dma-iommu and will simply return a contigious chunk as a fallback. The intent is that drivers can use this API if either: - no kernel mapping or only temporary kernel mappings are required. That is as a better replacement for DMA_ATTR_NO_KERNEL_MAPPING - a kernel mapping is required for cached and DMA mapped pages, but the driver also needs the pages to e.g. map them to userspace. In that sense it is a replacement for some aspects of the recently removed and never fully implemented DMA_ATTR_NON_CONSISTENT Signed-off-by: Christoph Hellwig Reviewed-by: Tomasz Figa Tested-by: Ricardo Ribalda --- Documentation/core-api/dma-api.rst | 78 +++++++++++++++++++++++++++ include/linux/dma-map-ops.h | 19 +++++++ include/linux/dma-mapping.h | 32 +++++++++++ kernel/dma/mapping.c | 106 +++++++++++++++++++++++++++++++++++++ 4 files changed, 235 insertions(+) (limited to 'kernel') diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst index 157a474ae544..00a1d4fa3f9e 100644 --- a/Documentation/core-api/dma-api.rst +++ b/Documentation/core-api/dma-api.rst @@ -594,6 +594,84 @@ dev, size, dma_handle and dir must all be the same as those passed into dma_alloc_noncoherent(). cpu_addr must be the virtual address returned by dma_alloc_noncoherent(). +:: + + struct sg_table * + dma_alloc_noncontiguous(struct device *dev, size_t size, + enum dma_data_direction dir, gfp_t gfp, + unsigned long attrs); + +This routine allocates bytes of non-coherent and possibly non-contiguous +memory. It returns a pointer to struct sg_table that describes the allocated +and DMA mapped memory, or NULL if the allocation failed. The resulting memory +can be used for struct page mapped into a scatterlist are suitable for. + +The return sg_table is guaranteed to have 1 single DMA mapped segment as +indicated by sgt->nents, but it might have multiple CPU side segments as +indicated by sgt->orig_nents. + +The dir parameter specified if data is read and/or written by the device, +see dma_map_single() for details. + +The gfp parameter allows the caller to specify the ``GFP_`` flags (see +kmalloc()) for the allocation, but rejects flags used to specify a memory +zone such as GFP_DMA or GFP_HIGHMEM. + +The attrs argument must be either 0 or DMA_ATTR_ALLOC_SINGLE_PAGES. + +Before giving the memory to the device, dma_sync_sgtable_for_device() needs +to be called, and before reading memory written by the device, +dma_sync_sgtable_for_cpu(), just like for streaming DMA mappings that are +reused. + +:: + + void + dma_free_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt, + enum dma_data_direction dir) + +Free memory previously allocated using dma_alloc_noncontiguous(). dev, size, +and dir must all be the same as those passed into dma_alloc_noncontiguous(). +sgt must be the pointer returned by dma_alloc_noncontiguous(). + +:: + + void * + dma_vmap_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt) + +Return a contiguous kernel mapping for an allocation returned from +dma_alloc_noncontiguous(). dev and size must be the same as those passed into +dma_alloc_noncontiguous(). sgt must be the pointer returned by +dma_alloc_noncontiguous(). + +Once a non-contiguous allocation is mapped using this function, the +flush_kernel_vmap_range() and invalidate_kernel_vmap_range() APIs must be used +to manage the coherency between the kernel mapping, the device and user space +mappings (if any). + +:: + + void + dma_vunmap_noncontiguous(struct device *dev, void *vaddr) + +Unmap a kernel mapping returned by dma_vmap_noncontiguous(). dev must be the +same the one passed into dma_alloc_noncontiguous(). vaddr must be the pointer +returned by dma_vmap_noncontiguous(). + + +:: + + int + dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma, + size_t size, struct sg_table *sgt) + +Map an allocation returned from dma_alloc_noncontiguous() into a user address +space. dev and size must be the same as those passed into +dma_alloc_noncontiguous(). sgt must be the pointer returned by +dma_alloc_noncontiguous(). + :: int diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 51872e736e7b..0d53a96a3d64 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -22,6 +22,11 @@ struct dma_map_ops { gfp_t gfp); void (*free_pages)(struct device *dev, size_t size, struct page *vaddr, dma_addr_t dma_handle, enum dma_data_direction dir); + struct sg_table *(*alloc_noncontiguous)(struct device *dev, size_t size, + enum dma_data_direction dir, gfp_t gfp, + unsigned long attrs); + void (*free_noncontiguous)(struct device *dev, size_t size, + struct sg_table *sgt, enum dma_data_direction dir); int (*mmap)(struct device *, struct vm_area_struct *, void *, dma_addr_t, size_t, unsigned long attrs); @@ -198,6 +203,20 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma, } #endif /* CONFIG_DMA_DECLARE_COHERENT */ +/* + * This is the actual return value from the ->alloc_noncontiguous method. + * The users of the DMA API should only care about the sg_table, but to make + * the DMA-API internal vmaping and freeing easier we stash away the page + * array as well (except for the fallback case). This can go away any time, + * e.g. when a vmap-variant that takes a scatterlist comes along. + */ +struct dma_sgt_handle { + struct sg_table sgt; + struct page **pages; +}; +#define sgt_handle(sgt) \ + container_of((sgt), struct dma_sgt_handle, sgt) + int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 2b8dce756e1f..954847f9a3e0 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -144,6 +144,15 @@ u64 dma_get_required_mask(struct device *dev); size_t dma_max_mapping_size(struct device *dev); bool dma_need_sync(struct device *dev, dma_addr_t dma_addr); unsigned long dma_get_merge_boundary(struct device *dev); +struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size, + enum dma_data_direction dir, gfp_t gfp, unsigned long attrs); +void dma_free_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt, enum dma_data_direction dir); +void *dma_vmap_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt); +void dma_vunmap_noncontiguous(struct device *dev, void *vaddr); +int dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma, + size_t size, struct sg_table *sgt); #else /* CONFIG_HAS_DMA */ static inline dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, size_t offset, size_t size, @@ -257,6 +266,29 @@ static inline unsigned long dma_get_merge_boundary(struct device *dev) { return 0; } +static inline struct sg_table *dma_alloc_noncontiguous(struct device *dev, + size_t size, enum dma_data_direction dir, gfp_t gfp, + unsigned long attrs) +{ + return NULL; +} +static inline void dma_free_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt, enum dma_data_direction dir) +{ +} +static inline void *dma_vmap_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt) +{ + return NULL; +} +static inline void dma_vunmap_noncontiguous(struct device *dev, void *vaddr) +{ +} +static inline int dma_mmap_noncontiguous(struct device *dev, + struct vm_area_struct *vma, size_t size, struct sg_table *sgt) +{ + return -EINVAL; +} #endif /* CONFIG_HAS_DMA */ struct page *dma_alloc_pages(struct device *dev, size_t size, diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 07f964ebcda1..2b06a809d0b9 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -539,6 +539,112 @@ int dma_mmap_pages(struct device *dev, struct vm_area_struct *vma, } EXPORT_SYMBOL_GPL(dma_mmap_pages); +static struct sg_table *alloc_single_sgt(struct device *dev, size_t size, + enum dma_data_direction dir, gfp_t gfp) +{ + struct sg_table *sgt; + struct page *page; + + sgt = kmalloc(sizeof(*sgt), gfp); + if (!sgt) + return NULL; + if (sg_alloc_table(sgt, 1, gfp)) + goto out_free_sgt; + page = __dma_alloc_pages(dev, size, &sgt->sgl->dma_address, dir, gfp); + if (!page) + goto out_free_table; + sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0); + sg_dma_len(sgt->sgl) = sgt->sgl->length; + return sgt; +out_free_table: + sg_free_table(sgt); +out_free_sgt: + kfree(sgt); + return NULL; +} + +struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size, + enum dma_data_direction dir, gfp_t gfp, unsigned long attrs) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + struct sg_table *sgt; + + if (WARN_ON_ONCE(attrs & ~DMA_ATTR_ALLOC_SINGLE_PAGES)) + return NULL; + + if (ops && ops->alloc_noncontiguous) + sgt = ops->alloc_noncontiguous(dev, size, dir, gfp, attrs); + else + sgt = alloc_single_sgt(dev, size, dir, gfp); + + if (sgt) { + sgt->nents = 1; + debug_dma_map_sg(dev, sgt->sgl, sgt->orig_nents, 1, dir); + } + return sgt; +} +EXPORT_SYMBOL_GPL(dma_alloc_noncontiguous); + +static void free_single_sgt(struct device *dev, size_t size, + struct sg_table *sgt, enum dma_data_direction dir) +{ + __dma_free_pages(dev, size, sg_page(sgt->sgl), sgt->sgl->dma_address, + dir); + sg_free_table(sgt); + kfree(sgt); +} + +void dma_free_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt, enum dma_data_direction dir) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + debug_dma_unmap_sg(dev, sgt->sgl, sgt->orig_nents, dir); + if (ops && ops->free_noncontiguous) + ops->free_noncontiguous(dev, size, sgt, dir); + else + free_single_sgt(dev, size, sgt, dir); +} +EXPORT_SYMBOL_GPL(dma_free_noncontiguous); + +void *dma_vmap_noncontiguous(struct device *dev, size_t size, + struct sg_table *sgt) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; + + if (ops && ops->alloc_noncontiguous) + return vmap(sgt_handle(sgt)->pages, count, VM_MAP, PAGE_KERNEL); + return page_address(sg_page(sgt->sgl)); +} +EXPORT_SYMBOL_GPL(dma_vmap_noncontiguous); + +void dma_vunmap_noncontiguous(struct device *dev, void *vaddr) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (ops && ops->alloc_noncontiguous) + vunmap(vaddr); +} +EXPORT_SYMBOL_GPL(dma_vunmap_noncontiguous); + +int dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma, + size_t size, struct sg_table *sgt) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (ops && ops->alloc_noncontiguous) { + unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; + + if (vma->vm_pgoff >= count || + vma_pages(vma) > count - vma->vm_pgoff) + return -ENXIO; + return vm_map_pages(vma, sgt_handle(sgt)->pages, count); + } + return dma_mmap_pages(dev, vma, size, sg_page(sgt->sgl)); +} +EXPORT_SYMBOL_GPL(dma_mmap_noncontiguous); + int dma_supported(struct device *dev, u64 mask) { const struct dma_map_ops *ops = get_dma_ops(dev); -- cgit v1.2.3-71-gd317 From 2973073a80b46daebc352c31d09d95d16cf6876e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Mar 2021 08:44:24 +0100 Subject: swiotlb: remove the alloc_size parameter to swiotlb_tbl_unmap_single Now that swiotlb remembers the allocation size there is no need to pass it back to swiotlb_tbl_unmap_single. Signed-off-by: Christoph Hellwig Signed-off-by: Konrad Rzeszutek Wilk --- drivers/iommu/dma-iommu.c | 11 +++-------- drivers/xen/swiotlb-xen.c | 4 ++-- include/linux/swiotlb.h | 1 - kernel/dma/direct.h | 2 +- kernel/dma/swiotlb.c | 45 +++++++++++++++++++++++---------------------- 5 files changed, 29 insertions(+), 34 deletions(-) (limited to 'kernel') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index af765c813cc8..9149597410e2 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -499,8 +499,6 @@ static void __iommu_dma_unmap_swiotlb(struct device *dev, dma_addr_t dma_addr, unsigned long attrs) { struct iommu_domain *domain = iommu_get_dma_domain(dev); - struct iommu_dma_cookie *cookie = domain->iova_cookie; - struct iova_domain *iovad = &cookie->iovad; phys_addr_t phys; phys = iommu_iova_to_phys(domain, dma_addr); @@ -510,8 +508,7 @@ static void __iommu_dma_unmap_swiotlb(struct device *dev, dma_addr_t dma_addr, __iommu_dma_unmap(dev, dma_addr, size); if (unlikely(is_swiotlb_buffer(phys))) - swiotlb_tbl_unmap_single(dev, phys, size, - iova_align(iovad, size), dir, attrs); + swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); } static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys, @@ -581,10 +578,8 @@ static dma_addr_t __iommu_dma_map_swiotlb(struct device *dev, phys_addr_t phys, } iova = __iommu_dma_map(dev, phys, aligned_size, prot, dma_mask); - if ((iova == DMA_MAPPING_ERROR) && is_swiotlb_buffer(phys)) - swiotlb_tbl_unmap_single(dev, phys, org_size, - aligned_size, dir, attrs); - + if (iova == DMA_MAPPING_ERROR && is_swiotlb_buffer(phys)) + swiotlb_tbl_unmap_single(dev, phys, org_size, dir, attrs); return iova; } diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 2b385c1b4a99..d47f1b311caa 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -406,7 +406,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, * Ensure that the address returned is DMA'ble */ if (unlikely(!dma_capable(dev, dev_addr, size, true))) { - swiotlb_tbl_unmap_single(dev, map, size, size, dir, + swiotlb_tbl_unmap_single(dev, map, size, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC); return DMA_MAPPING_ERROR; } @@ -445,7 +445,7 @@ static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, /* NOTE: We use dev_addr here, not paddr! */ if (is_xen_swiotlb_buffer(hwdev, dev_addr)) - swiotlb_tbl_unmap_single(hwdev, paddr, size, size, dir, attrs); + swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs); } static void diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 5857a937c637..59f421d041ed 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -57,7 +57,6 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, extern void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, size_t mapping_size, - size_t alloc_size, enum dma_data_direction dir, unsigned long attrs); diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h index b98615578737..e1bf721591c0 100644 --- a/kernel/dma/direct.h +++ b/kernel/dma/direct.h @@ -114,6 +114,6 @@ static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, dma_direct_sync_single_for_cpu(dev, addr, size, dir); if (unlikely(is_swiotlb_buffer(phys))) - swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs); + swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); } #endif /* _KERNEL_DMA_DIRECT_H */ diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index c10e855a03bc..03aa614565e4 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -102,7 +102,7 @@ static phys_addr_t *io_tlb_orig_addr; /* * The mapped buffer's size should be validated during a sync operation. */ -static size_t *io_tlb_orig_size; +static size_t *io_tlb_alloc_size; /* * Protect the above data structures in the map and unmap calls @@ -253,15 +253,15 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) __func__, alloc_size, PAGE_SIZE); alloc_size = PAGE_ALIGN(io_tlb_nslabs * sizeof(size_t)); - io_tlb_orig_size = memblock_alloc(alloc_size, PAGE_SIZE); - if (!io_tlb_orig_size) + io_tlb_alloc_size = memblock_alloc(alloc_size, PAGE_SIZE); + if (!io_tlb_alloc_size) panic("%s: Failed to allocate %zu bytes align=0x%lx\n", __func__, alloc_size, PAGE_SIZE); for (i = 0; i < io_tlb_nslabs; i++) { io_tlb_list[i] = IO_TLB_SEGSIZE - io_tlb_offset(i); io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; - io_tlb_orig_size[i] = 0; + io_tlb_alloc_size[i] = 0; } io_tlb_index = 0; no_iotlb_memory = false; @@ -393,18 +393,18 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) if (!io_tlb_orig_addr) goto cleanup4; - io_tlb_orig_size = (size_t *) + io_tlb_alloc_size = (size_t *) __get_free_pages(GFP_KERNEL, get_order(io_tlb_nslabs * sizeof(size_t))); - if (!io_tlb_orig_size) + if (!io_tlb_alloc_size) goto cleanup5; for (i = 0; i < io_tlb_nslabs; i++) { io_tlb_list[i] = IO_TLB_SEGSIZE - io_tlb_offset(i); io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; - io_tlb_orig_size[i] = 0; + io_tlb_alloc_size[i] = 0; } io_tlb_index = 0; no_iotlb_memory = false; @@ -436,7 +436,7 @@ void __init swiotlb_exit(void) return; if (late_alloc) { - free_pages((unsigned long)io_tlb_orig_size, + free_pages((unsigned long)io_tlb_alloc_size, get_order(io_tlb_nslabs * sizeof(size_t))); free_pages((unsigned long)io_tlb_orig_addr, get_order(io_tlb_nslabs * sizeof(phys_addr_t))); @@ -447,7 +447,7 @@ void __init swiotlb_exit(void) } else { memblock_free_late(__pa(io_tlb_orig_addr), PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t))); - memblock_free_late(__pa(io_tlb_orig_size), + memblock_free_late(__pa(io_tlb_alloc_size), PAGE_ALIGN(io_tlb_nslabs * sizeof(size_t))); memblock_free_late(__pa(io_tlb_list), PAGE_ALIGN(io_tlb_nslabs * sizeof(int))); @@ -639,7 +639,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, */ for (i = 0; i < nr_slots(alloc_size + offset); i++) { io_tlb_orig_addr[index + i] = slot_addr(orig_addr, i); - io_tlb_orig_size[index+i] = alloc_size - (i << IO_TLB_SHIFT); + io_tlb_alloc_size[index+i] = alloc_size - (i << IO_TLB_SHIFT); } tlb_addr = slot_addr(io_tlb_start, index) + offset; if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && @@ -648,14 +648,14 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, return tlb_addr; } -static void validate_sync_size_and_truncate(struct device *hwdev, size_t orig_size, size_t *size) +static void validate_sync_size_and_truncate(struct device *hwdev, size_t alloc_size, size_t *size) { - if (*size > orig_size) { + if (*size > alloc_size) { /* Warn and truncate mapping_size */ dev_WARN_ONCE(hwdev, 1, "Attempt for buffer overflow. Original size: %zu. Mapping size: %zu.\n", - orig_size, *size); - *size = orig_size; + alloc_size, *size); + *size = alloc_size; } } @@ -663,16 +663,17 @@ static void validate_sync_size_and_truncate(struct device *hwdev, size_t orig_si * tlb_addr is the physical address of the bounce buffer to unmap. */ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, - size_t mapping_size, size_t alloc_size, - enum dma_data_direction dir, unsigned long attrs) + size_t mapping_size, enum dma_data_direction dir, + unsigned long attrs) { unsigned long flags; unsigned int offset = swiotlb_align_offset(hwdev, tlb_addr); - int i, count, nslots = nr_slots(alloc_size + offset); int index = (tlb_addr - offset - io_tlb_start) >> IO_TLB_SHIFT; phys_addr_t orig_addr = io_tlb_orig_addr[index]; + size_t alloc_size = io_tlb_alloc_size[index]; + int i, count, nslots = nr_slots(alloc_size + offset); - validate_sync_size_and_truncate(hwdev, io_tlb_orig_size[index], &mapping_size); + validate_sync_size_and_truncate(hwdev, alloc_size, &mapping_size); /* * First, sync the memory before unmapping the entry @@ -701,7 +702,7 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, for (i = index + nslots - 1; i >= index; i--) { io_tlb_list[i] = ++count; io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; - io_tlb_orig_size[i] = 0; + io_tlb_alloc_size[i] = 0; } /* @@ -721,13 +722,13 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, enum dma_sync_target target) { int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT; - size_t orig_size = io_tlb_orig_size[index]; + size_t alloc_size = io_tlb_alloc_size[index]; phys_addr_t orig_addr = io_tlb_orig_addr[index]; if (orig_addr == INVALID_PHYS_ADDR) return; - validate_sync_size_and_truncate(hwdev, orig_size, &size); + validate_sync_size_and_truncate(hwdev, alloc_size, &size); switch (target) { case SYNC_FOR_CPU: @@ -770,7 +771,7 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size, /* Ensure that the address returned is DMA'ble */ dma_addr = phys_to_dma_unencrypted(dev, swiotlb_addr); if (unlikely(!dma_capable(dev, dma_addr, size, true))) { - swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, size, dir, + swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC); dev_WARN_ONCE(dev, 1, "swiotlb addr %pad+%zu overflow (mask %llx, bus limit %llx).\n", -- cgit v1.2.3-71-gd317 From 2bdba622c351259317b0294c6e9fe243b2404316 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Mar 2021 08:44:25 +0100 Subject: swiotlb: move orig addr and size validation into swiotlb_bounce Move the code to find and validate the original buffer address and size from the callers into swiotlb_bounce. This means a tiny bit of extra work in the swiotlb_map path, but avoids code duplication and a leads to a better code structure. Signed-off-by: Christoph Hellwig Signed-off-by: Konrad Rzeszutek Wilk --- kernel/dma/swiotlb.c | 59 ++++++++++++++++++++-------------------------------- 1 file changed, 23 insertions(+), 36 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 03aa614565e4..a431c6b64e82 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -460,12 +460,25 @@ void __init swiotlb_exit(void) /* * Bounce: copy the swiotlb buffer from or back to the original dma location */ -static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr, - size_t size, enum dma_data_direction dir) +static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size, + enum dma_data_direction dir) { + int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT; + size_t alloc_size = io_tlb_alloc_size[index]; + phys_addr_t orig_addr = io_tlb_orig_addr[index]; unsigned long pfn = PFN_DOWN(orig_addr); unsigned char *vaddr = phys_to_virt(tlb_addr); + if (orig_addr == INVALID_PHYS_ADDR) + return; + + if (size > alloc_size) { + dev_WARN_ONCE(dev, 1, + "Buffer overflow detected. Allocation size: %zu. Mapping size: %zu.\n", + alloc_size, size); + size = alloc_size; + } + if (PageHighMem(pfn_to_page(pfn))) { /* The buffer does not have a mapping. Map it in and copy */ unsigned int offset = orig_addr & ~PAGE_MASK; @@ -644,21 +657,10 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, tlb_addr = slot_addr(io_tlb_start, index) + offset; if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) - swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_TO_DEVICE); + swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_TO_DEVICE); return tlb_addr; } -static void validate_sync_size_and_truncate(struct device *hwdev, size_t alloc_size, size_t *size) -{ - if (*size > alloc_size) { - /* Warn and truncate mapping_size */ - dev_WARN_ONCE(hwdev, 1, - "Attempt for buffer overflow. Original size: %zu. Mapping size: %zu.\n", - alloc_size, *size); - *size = alloc_size; - } -} - /* * tlb_addr is the physical address of the bounce buffer to unmap. */ @@ -669,19 +671,15 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, unsigned long flags; unsigned int offset = swiotlb_align_offset(hwdev, tlb_addr); int index = (tlb_addr - offset - io_tlb_start) >> IO_TLB_SHIFT; - phys_addr_t orig_addr = io_tlb_orig_addr[index]; - size_t alloc_size = io_tlb_alloc_size[index]; - int i, count, nslots = nr_slots(alloc_size + offset); - - validate_sync_size_and_truncate(hwdev, alloc_size, &mapping_size); + int nslots = nr_slots(io_tlb_alloc_size[index] + offset); + int count, i; /* * First, sync the memory before unmapping the entry */ - if (orig_addr != INVALID_PHYS_ADDR && - !(attrs & DMA_ATTR_SKIP_CPU_SYNC) && - ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL))) - swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_FROM_DEVICE); + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && + (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) + swiotlb_bounce(hwdev, tlb_addr, mapping_size, DMA_FROM_DEVICE); /* * Return the buffer to the free list by setting the corresponding @@ -721,27 +719,16 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, size_t size, enum dma_data_direction dir, enum dma_sync_target target) { - int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT; - size_t alloc_size = io_tlb_alloc_size[index]; - phys_addr_t orig_addr = io_tlb_orig_addr[index]; - - if (orig_addr == INVALID_PHYS_ADDR) - return; - - validate_sync_size_and_truncate(hwdev, alloc_size, &size); - switch (target) { case SYNC_FOR_CPU: if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) - swiotlb_bounce(orig_addr, tlb_addr, - size, DMA_FROM_DEVICE); + swiotlb_bounce(hwdev, tlb_addr, size, DMA_FROM_DEVICE); else BUG_ON(dir != DMA_TO_DEVICE); break; case SYNC_FOR_DEVICE: if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) - swiotlb_bounce(orig_addr, tlb_addr, - size, DMA_TO_DEVICE); + swiotlb_bounce(hwdev, tlb_addr, size, DMA_TO_DEVICE); else BUG_ON(dir != DMA_FROM_DEVICE); break; -- cgit v1.2.3-71-gd317 From 80808d273a3f075196d1a26463f65d4c9d2891c8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Mar 2021 08:44:26 +0100 Subject: swiotlb: split swiotlb_tbl_sync_single Split swiotlb_tbl_sync_single into two separate funtions for the to device and to cpu synchronization. Signed-off-by: Christoph Hellwig Signed-off-by: Konrad Rzeszutek Wilk --- drivers/iommu/dma-iommu.c | 12 ++++++------ drivers/xen/swiotlb-xen.c | 4 ++-- include/linux/swiotlb.h | 17 ++++------------- kernel/dma/direct.c | 8 ++++---- kernel/dma/direct.h | 4 ++-- kernel/dma/swiotlb.c | 34 +++++++++++++++------------------- 6 files changed, 33 insertions(+), 46 deletions(-) (limited to 'kernel') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 9149597410e2..3087d9fa6065 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -750,7 +750,7 @@ static void iommu_dma_sync_single_for_cpu(struct device *dev, arch_sync_dma_for_cpu(phys, size, dir); if (is_swiotlb_buffer(phys)) - swiotlb_tbl_sync_single(dev, phys, size, dir, SYNC_FOR_CPU); + swiotlb_sync_single_for_cpu(dev, phys, size, dir); } static void iommu_dma_sync_single_for_device(struct device *dev, @@ -763,7 +763,7 @@ static void iommu_dma_sync_single_for_device(struct device *dev, phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle); if (is_swiotlb_buffer(phys)) - swiotlb_tbl_sync_single(dev, phys, size, dir, SYNC_FOR_DEVICE); + swiotlb_sync_single_for_device(dev, phys, size, dir); if (!dev_is_dma_coherent(dev)) arch_sync_dma_for_device(phys, size, dir); @@ -784,8 +784,8 @@ static void iommu_dma_sync_sg_for_cpu(struct device *dev, arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir); if (is_swiotlb_buffer(sg_phys(sg))) - swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length, - dir, SYNC_FOR_CPU); + swiotlb_sync_single_for_cpu(dev, sg_phys(sg), + sg->length, dir); } } @@ -801,8 +801,8 @@ static void iommu_dma_sync_sg_for_device(struct device *dev, for_each_sg(sgl, sg, nelems, i) { if (is_swiotlb_buffer(sg_phys(sg))) - swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length, - dir, SYNC_FOR_DEVICE); + swiotlb_sync_single_for_device(dev, sg_phys(sg), + sg->length, dir); if (!dev_is_dma_coherent(dev)) arch_sync_dma_for_device(sg_phys(sg), sg->length, dir); diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index d47f1b311caa..4e8a4e14942a 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -462,7 +462,7 @@ xen_swiotlb_sync_single_for_cpu(struct device *dev, dma_addr_t dma_addr, } if (is_xen_swiotlb_buffer(dev, dma_addr)) - swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU); + swiotlb_sync_single_for_cpu(dev, paddr, size, dir); } static void @@ -472,7 +472,7 @@ xen_swiotlb_sync_single_for_device(struct device *dev, dma_addr_t dma_addr, phys_addr_t paddr = xen_dma_to_phys(dev, dma_addr); if (is_xen_swiotlb_buffer(dev, dma_addr)) - swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE); + swiotlb_sync_single_for_device(dev, paddr, size, dir); if (!dev_is_dma_coherent(dev)) { if (pfn_valid(PFN_DOWN(dma_to_phys(dev, dma_addr)))) diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 59f421d041ed..0696bdc8072e 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -42,14 +42,6 @@ extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); extern int swiotlb_late_init_with_default_size(size_t default_size); extern void __init swiotlb_update_mem_attributes(void); -/* - * Enumeration for sync targets - */ -enum dma_sync_target { - SYNC_FOR_CPU = 0, - SYNC_FOR_DEVICE = 1, -}; - phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, size_t mapping_size, size_t alloc_size, enum dma_data_direction dir, unsigned long attrs); @@ -60,11 +52,10 @@ extern void swiotlb_tbl_unmap_single(struct device *hwdev, enum dma_data_direction dir, unsigned long attrs); -extern void swiotlb_tbl_sync_single(struct device *hwdev, - phys_addr_t tlb_addr, - size_t size, enum dma_data_direction dir, - enum dma_sync_target target); - +void swiotlb_sync_single_for_device(struct device *dev, phys_addr_t tlb_addr, + size_t size, enum dma_data_direction dir); +void swiotlb_sync_single_for_cpu(struct device *dev, phys_addr_t tlb_addr, + size_t size, enum dma_data_direction dir); dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys, size_t size, enum dma_data_direction dir, unsigned long attrs); diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 002268262c9a..f737e3347059 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -344,8 +344,8 @@ void dma_direct_sync_sg_for_device(struct device *dev, phys_addr_t paddr = dma_to_phys(dev, sg_dma_address(sg)); if (unlikely(is_swiotlb_buffer(paddr))) - swiotlb_tbl_sync_single(dev, paddr, sg->length, - dir, SYNC_FOR_DEVICE); + swiotlb_sync_single_for_device(dev, paddr, sg->length, + dir); if (!dev_is_dma_coherent(dev)) arch_sync_dma_for_device(paddr, sg->length, @@ -370,8 +370,8 @@ void dma_direct_sync_sg_for_cpu(struct device *dev, arch_sync_dma_for_cpu(paddr, sg->length, dir); if (unlikely(is_swiotlb_buffer(paddr))) - swiotlb_tbl_sync_single(dev, paddr, sg->length, dir, - SYNC_FOR_CPU); + swiotlb_sync_single_for_cpu(dev, paddr, sg->length, + dir); if (dir == DMA_FROM_DEVICE) arch_dma_mark_clean(paddr, sg->length); diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h index e1bf721591c0..50afc05b6f1d 100644 --- a/kernel/dma/direct.h +++ b/kernel/dma/direct.h @@ -57,7 +57,7 @@ static inline void dma_direct_sync_single_for_device(struct device *dev, phys_addr_t paddr = dma_to_phys(dev, addr); if (unlikely(is_swiotlb_buffer(paddr))) - swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE); + swiotlb_sync_single_for_device(dev, paddr, size, dir); if (!dev_is_dma_coherent(dev)) arch_sync_dma_for_device(paddr, size, dir); @@ -74,7 +74,7 @@ static inline void dma_direct_sync_single_for_cpu(struct device *dev, } if (unlikely(is_swiotlb_buffer(paddr))) - swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU); + swiotlb_sync_single_for_cpu(dev, paddr, size, dir); if (dir == DMA_FROM_DEVICE) arch_dma_mark_clean(paddr, size); diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index a431c6b64e82..5fe8781be6f2 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -715,26 +715,22 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, spin_unlock_irqrestore(&io_tlb_lock, flags); } -void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, - size_t size, enum dma_data_direction dir, - enum dma_sync_target target) +void swiotlb_sync_single_for_device(struct device *dev, phys_addr_t tlb_addr, + size_t size, enum dma_data_direction dir) { - switch (target) { - case SYNC_FOR_CPU: - if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) - swiotlb_bounce(hwdev, tlb_addr, size, DMA_FROM_DEVICE); - else - BUG_ON(dir != DMA_TO_DEVICE); - break; - case SYNC_FOR_DEVICE: - if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) - swiotlb_bounce(hwdev, tlb_addr, size, DMA_TO_DEVICE); - else - BUG_ON(dir != DMA_FROM_DEVICE); - break; - default: - BUG(); - } + if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) + swiotlb_bounce(dev, tlb_addr, size, DMA_TO_DEVICE); + else + BUG_ON(dir != DMA_FROM_DEVICE); +} + +void swiotlb_sync_single_for_cpu(struct device *dev, phys_addr_t tlb_addr, + size_t size, enum dma_data_direction dir) +{ + if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) + swiotlb_bounce(dev, tlb_addr, size, DMA_FROM_DEVICE); + else + BUG_ON(dir != DMA_TO_DEVICE); } /* -- cgit v1.2.3-71-gd317 From 5d0538b2b884f7fd239f6ab3b667148dc57123f1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Mar 2021 08:44:31 +0100 Subject: swiotlb: lift the double initialization protection from xen-swiotlb Lift the double initialization protection from xen-swiotlb to the core code to avoid exposing too many swiotlb internals. Also upgrade the check to a warning as it should not happen. Signed-off-by: Christoph Hellwig Signed-off-by: Konrad Rzeszutek Wilk --- drivers/xen/swiotlb-xen.c | 7 ------- kernel/dma/swiotlb.c | 8 ++++++++ 2 files changed, 8 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 1a31ddf71397..060eeb056486 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -172,12 +172,6 @@ retry: bytes = nslabs << IO_TLB_SHIFT; order = get_order(bytes); - /* - * IO TLB memory already allocated. Just use it. - */ - if (io_tlb_start != 0) - goto end; - /* * Get IO TLB memory from any location. */ @@ -232,7 +226,6 @@ retry: } else rc = swiotlb_late_init_with_tbl(start, nslabs); -end: if (!rc) swiotlb_set_max_segment(PAGE_SIZE); diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 5fe8781be6f2..35e24f0ff8b2 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -229,6 +229,10 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) unsigned long i, bytes; size_t alloc_size; + /* protect against double initialization */ + if (WARN_ON_ONCE(io_tlb_start)) + return -ENOMEM; + bytes = nslabs << IO_TLB_SHIFT; io_tlb_nslabs = nslabs; @@ -367,6 +371,10 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) { unsigned long i, bytes; + /* protect against double initialization */ + if (WARN_ON_ONCE(io_tlb_start)) + return -ENOMEM; + bytes = nslabs << IO_TLB_SHIFT; io_tlb_nslabs = nslabs; -- cgit v1.2.3-71-gd317 From e20044f7e9ae2b5395ca3ae9bd0907fdf43357a7 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 16 Mar 2021 12:41:01 -0400 Subject: ring-buffer: Separate out internal use of ring_buffer_event_time_stamp() The exported use of ring_buffer_event_time_stamp() is going to become different than how it is used internally. Move the internal logic out into a static function called rb_event_time_stamp(), and have the internal callers call that instead. Link: https://lkml.kernel.org/r/20210316164113.257790481@goodmis.org Reviewed-by: Tom Zanussi Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 41 +++++++++++++++++++++++------------------ 1 file changed, 23 insertions(+), 18 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 68744c51517e..941ac2021b97 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -287,6 +287,17 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data); #define TS_MASK ((1ULL << TS_SHIFT) - 1) #define TS_DELTA_TEST (~TS_MASK) +static u64 rb_event_time_stamp(struct ring_buffer_event *event) +{ + u64 ts; + + ts = event->array[0]; + ts <<= TS_SHIFT; + ts += event->time_delta; + + return ts; +} + /** * ring_buffer_event_time_stamp - return the event's extended timestamp * @event: the event to get the timestamp of @@ -299,13 +310,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data); */ u64 ring_buffer_event_time_stamp(struct ring_buffer_event *event) { - u64 ts; - - ts = event->array[0]; - ts <<= TS_SHIFT; - ts += event->time_delta; - - return ts; + return rb_event_time_stamp(event); } /* Flag when events were overwritten */ @@ -2766,7 +2771,7 @@ static u64 rb_time_delta(struct ring_buffer_event *event) return 0; case RINGBUF_TYPE_TIME_EXTEND: - return ring_buffer_event_time_stamp(event); + return rb_event_time_stamp(event); case RINGBUF_TYPE_TIME_STAMP: return 0; @@ -3212,13 +3217,13 @@ static void dump_buffer_page(struct buffer_data_page *bpage, switch (event->type_len) { case RINGBUF_TYPE_TIME_EXTEND: - delta = ring_buffer_event_time_stamp(event); + delta = rb_event_time_stamp(event); ts += delta; pr_warn(" [%lld] delta:%lld TIME EXTEND\n", ts, delta); break; case RINGBUF_TYPE_TIME_STAMP: - delta = ring_buffer_event_time_stamp(event); + delta = rb_event_time_stamp(event); ts = delta; pr_warn(" [%lld] absolute:%lld TIME STAMP\n", ts, delta); break; @@ -3289,12 +3294,12 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer, switch (event->type_len) { case RINGBUF_TYPE_TIME_EXTEND: - delta = ring_buffer_event_time_stamp(event); + delta = rb_event_time_stamp(event); ts += delta; break; case RINGBUF_TYPE_TIME_STAMP: - delta = ring_buffer_event_time_stamp(event); + delta = rb_event_time_stamp(event); ts = delta; break; @@ -4256,12 +4261,12 @@ rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer, return; case RINGBUF_TYPE_TIME_EXTEND: - delta = ring_buffer_event_time_stamp(event); + delta = rb_event_time_stamp(event); cpu_buffer->read_stamp += delta; return; case RINGBUF_TYPE_TIME_STAMP: - delta = ring_buffer_event_time_stamp(event); + delta = rb_event_time_stamp(event); cpu_buffer->read_stamp = delta; return; @@ -4286,12 +4291,12 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *iter, return; case RINGBUF_TYPE_TIME_EXTEND: - delta = ring_buffer_event_time_stamp(event); + delta = rb_event_time_stamp(event); iter->read_stamp += delta; return; case RINGBUF_TYPE_TIME_STAMP: - delta = ring_buffer_event_time_stamp(event); + delta = rb_event_time_stamp(event); iter->read_stamp = delta; return; @@ -4544,7 +4549,7 @@ rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts, case RINGBUF_TYPE_TIME_STAMP: if (ts) { - *ts = ring_buffer_event_time_stamp(event); + *ts = rb_event_time_stamp(event); ring_buffer_normalize_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu, ts); } @@ -4635,7 +4640,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) case RINGBUF_TYPE_TIME_STAMP: if (ts) { - *ts = ring_buffer_event_time_stamp(event); + *ts = rb_event_time_stamp(event); ring_buffer_normalize_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu, ts); } -- cgit v1.2.3-71-gd317 From 8672e4948d0c44272cc05f8ff563dbf6b6c1289f Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 16 Mar 2021 12:41:02 -0400 Subject: ring-buffer: Add a event_stamp to cpu_buffer for each level of nesting Add a place to save the current event time stamp for each level of nesting. This will be used to retrieve the time stamp of the current event before it is committed. Link: https://lkml.kernel.org/r/20210316164113.399089673@goodmis.org Reviewed-by: Tom Zanussi Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 941ac2021b97..470d97169081 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -492,6 +492,8 @@ struct rb_time_struct { #endif typedef struct rb_time_struct rb_time_t; +#define MAX_NEST 5 + /* * head_page == tail_page && head == tail then buffer is empty. */ @@ -529,6 +531,7 @@ struct ring_buffer_per_cpu { unsigned long read_bytes; rb_time_t write_stamp; rb_time_t before_stamp; + u64 event_stamp[MAX_NEST]; u64 read_stamp; /* ring buffer pages to update, > 0 to add, < 0 to remove */ long nr_pages_to_update; @@ -2715,6 +2718,10 @@ rb_update_event(struct ring_buffer_per_cpu *cpu_buffer, { unsigned length = info->length; u64 delta = info->delta; + unsigned int nest = local_read(&cpu_buffer->committing) - 1; + + if (nest < MAX_NEST) + cpu_buffer->event_stamp[nest] = info->ts; /* * If we need to add a timestamp, then we @@ -3456,7 +3463,6 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, info->after, ts)) { /* Nothing came after this event between C and E */ info->delta = ts - info->after; - info->ts = ts; } else { /* * Interrupted between C and E: @@ -3468,6 +3474,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, */ info->delta = 0; } + info->ts = ts; info->add_timestamp &= ~RB_ADD_STAMP_FORCE; } @@ -5026,6 +5033,8 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) rb_time_set(&cpu_buffer->write_stamp, 0); rb_time_set(&cpu_buffer->before_stamp, 0); + memset(cpu_buffer->event_stamp, 0, sizeof(cpu_buffer->event_stamp)); + cpu_buffer->lost_events = 0; cpu_buffer->last_overrun = 0; -- cgit v1.2.3-71-gd317 From b47e330231acbf4506b049643145cc64268a1940 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 16 Mar 2021 12:41:03 -0400 Subject: tracing: Pass buffer of event to trigger operations The ring_buffer_event_time_stamp() is going to be updated to extract the time stamp for the event without needing it to be set to have absolute values for all events. But to do so, it needs the buffer that the event is on as the buffer saves information for the event before it is committed to the buffer. If the trace buffer is disabled, a temporary buffer is used, and there's no access to this buffer from the current histogram triggers, even though it is passed to the trace event code. Pass the buffer that the event is on all the way down to the histogram triggers. Link: https://lkml.kernel.org/r/20210316164113.542448131@goodmis.org Reviewed-by: Tom Zanussi Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 5 +- kernel/trace/trace.c | 2 +- kernel/trace/trace.h | 4 +- kernel/trace/trace_events_hist.c | 92 ++++++++++++++++++++++++------------- kernel/trace/trace_events_trigger.c | 45 +++++++++++------- 5 files changed, 95 insertions(+), 53 deletions(-) (limited to 'kernel') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 28e7af1406f2..8cba64ce23a4 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -640,7 +640,8 @@ enum event_trigger_type { extern int filter_match_preds(struct event_filter *filter, void *rec); extern enum event_trigger_type -event_triggers_call(struct trace_event_file *file, void *rec, +event_triggers_call(struct trace_event_file *file, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event); extern void event_triggers_post_call(struct trace_event_file *file, @@ -664,7 +665,7 @@ trace_trigger_soft_disabled(struct trace_event_file *file) if (!(eflags & EVENT_FILE_FL_TRIGGER_COND)) { if (eflags & EVENT_FILE_FL_TRIGGER_MODE) - event_triggers_call(file, NULL, NULL); + event_triggers_call(file, NULL, NULL, NULL); if (eflags & EVENT_FILE_FL_SOFT_DISABLED) return true; if (eflags & EVENT_FILE_FL_PID_FILTER) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index eccb4e1187cc..f979220238a5 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6763,7 +6763,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, if (tr->trace_marker_file && !list_empty(&tr->trace_marker_file->triggers)) { /* do not add \n before testing triggers, but add \0 */ entry->buf[cnt] = '\0'; - tt = event_triggers_call(tr->trace_marker_file, entry, event); + tt = event_triggers_call(tr->trace_marker_file, buffer, entry, event); } if (entry->buf[cnt - 1] != '\n') { diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index a6446c03cfbc..798773178d7e 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1329,7 +1329,7 @@ __event_trigger_test_discard(struct trace_event_file *file, unsigned long eflags = file->flags; if (eflags & EVENT_FILE_FL_TRIGGER_COND) - *tt = event_triggers_call(file, entry, event); + *tt = event_triggers_call(file, buffer, entry, event); if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags) || (unlikely(file->flags & EVENT_FILE_FL_FILTERED) && @@ -1626,7 +1626,7 @@ extern int register_trigger_hist_enable_disable_cmds(void); */ struct event_trigger_ops { void (*func)(struct event_trigger_data *data, - void *rec, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *rbe); int (*init)(struct event_trigger_ops *ops, struct event_trigger_data *data); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 39ebe1826fc3..6978aa3ee4c5 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -81,6 +81,7 @@ struct hist_field; typedef u64 (*hist_field_fn_t) (struct hist_field *field, struct tracing_map_elt *elt, + struct trace_buffer *buffer, struct ring_buffer_event *rbe, void *event); @@ -153,6 +154,7 @@ struct hist_field { static u64 hist_field_none(struct hist_field *field, struct tracing_map_elt *elt, + struct trace_buffer *buffer, struct ring_buffer_event *rbe, void *event) { @@ -161,6 +163,7 @@ static u64 hist_field_none(struct hist_field *field, static u64 hist_field_counter(struct hist_field *field, struct tracing_map_elt *elt, + struct trace_buffer *buffer, struct ring_buffer_event *rbe, void *event) { @@ -169,6 +172,7 @@ static u64 hist_field_counter(struct hist_field *field, static u64 hist_field_string(struct hist_field *hist_field, struct tracing_map_elt *elt, + struct trace_buffer *buffer, struct ring_buffer_event *rbe, void *event) { @@ -179,6 +183,7 @@ static u64 hist_field_string(struct hist_field *hist_field, static u64 hist_field_dynstring(struct hist_field *hist_field, struct tracing_map_elt *elt, + struct trace_buffer *buffer, struct ring_buffer_event *rbe, void *event) { @@ -191,6 +196,7 @@ static u64 hist_field_dynstring(struct hist_field *hist_field, static u64 hist_field_pstring(struct hist_field *hist_field, struct tracing_map_elt *elt, + struct trace_buffer *buffer, struct ring_buffer_event *rbe, void *event) { @@ -201,52 +207,56 @@ static u64 hist_field_pstring(struct hist_field *hist_field, static u64 hist_field_log2(struct hist_field *hist_field, struct tracing_map_elt *elt, + struct trace_buffer *buffer, struct ring_buffer_event *rbe, void *event) { struct hist_field *operand = hist_field->operands[0]; - u64 val = operand->fn(operand, elt, rbe, event); + u64 val = operand->fn(operand, elt, buffer, rbe, event); return (u64) ilog2(roundup_pow_of_two(val)); } static u64 hist_field_plus(struct hist_field *hist_field, struct tracing_map_elt *elt, + struct trace_buffer *buffer, struct ring_buffer_event *rbe, void *event) { struct hist_field *operand1 = hist_field->operands[0]; struct hist_field *operand2 = hist_field->operands[1]; - u64 val1 = operand1->fn(operand1, elt, rbe, event); - u64 val2 = operand2->fn(operand2, elt, rbe, event); + u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event); + u64 val2 = operand2->fn(operand2, elt, buffer, rbe, event); return val1 + val2; } static u64 hist_field_minus(struct hist_field *hist_field, struct tracing_map_elt *elt, + struct trace_buffer *buffer, struct ring_buffer_event *rbe, void *event) { struct hist_field *operand1 = hist_field->operands[0]; struct hist_field *operand2 = hist_field->operands[1]; - u64 val1 = operand1->fn(operand1, elt, rbe, event); - u64 val2 = operand2->fn(operand2, elt, rbe, event); + u64 val1 = operand1->fn(operand1, elt, buffer, rbe, event); + u64 val2 = operand2->fn(operand2, elt, buffer, rbe, event); return val1 - val2; } static u64 hist_field_unary_minus(struct hist_field *hist_field, struct tracing_map_elt *elt, + struct trace_buffer *buffer, struct ring_buffer_event *rbe, void *event) { struct hist_field *operand = hist_field->operands[0]; - s64 sval = (s64)operand->fn(operand, elt, rbe, event); + s64 sval = (s64)operand->fn(operand, elt, buffer, rbe, event); u64 val = (u64)-sval; return val; @@ -255,6 +265,7 @@ static u64 hist_field_unary_minus(struct hist_field *hist_field, #define DEFINE_HIST_FIELD_FN(type) \ static u64 hist_field_##type(struct hist_field *hist_field, \ struct tracing_map_elt *elt, \ + struct trace_buffer *buffer, \ struct ring_buffer_event *rbe, \ void *event) \ { \ @@ -380,7 +391,8 @@ struct hist_trigger_data { struct action_data; typedef void (*action_fn_t) (struct hist_trigger_data *hist_data, - struct tracing_map_elt *elt, void *rec, + struct tracing_map_elt *elt, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *rbe, void *key, struct action_data *data, u64 *var_ref_vals); @@ -608,7 +620,8 @@ static inline void trace_synth(struct synth_event *event, u64 *var_ref_vals, } static void action_trace(struct hist_trigger_data *hist_data, - struct tracing_map_elt *elt, void *rec, + struct tracing_map_elt *elt, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *rbe, void *key, struct action_data *data, u64 *var_ref_vals) { @@ -624,6 +637,7 @@ struct hist_var_data { static u64 hist_field_timestamp(struct hist_field *hist_field, struct tracing_map_elt *elt, + struct trace_buffer *buffer, struct ring_buffer_event *rbe, void *event) { @@ -640,6 +654,7 @@ static u64 hist_field_timestamp(struct hist_field *hist_field, static u64 hist_field_cpu(struct hist_field *hist_field, struct tracing_map_elt *elt, + struct trace_buffer *buffer, struct ring_buffer_event *rbe, void *event) { @@ -1020,6 +1035,7 @@ static struct hist_field *find_event_var(struct hist_trigger_data *hist_data, static u64 hist_field_var_ref(struct hist_field *hist_field, struct tracing_map_elt *elt, + struct trace_buffer *buffer, struct ring_buffer_event *rbe, void *event) { @@ -2561,6 +2577,7 @@ find_target_event_var(struct hist_trigger_data *hist_data, } static inline void __update_field_vars(struct tracing_map_elt *elt, + struct trace_buffer *buffer, struct ring_buffer_event *rbe, void *rec, struct field_var **field_vars, @@ -2576,7 +2593,7 @@ static inline void __update_field_vars(struct tracing_map_elt *elt, struct hist_field *var = field_var->var; struct hist_field *val = field_var->val; - var_val = val->fn(val, elt, rbe, rec); + var_val = val->fn(val, elt, buffer, rbe, rec); var_idx = var->var.idx; if (val->flags & HIST_FIELD_FL_STRING) { @@ -2592,19 +2609,21 @@ static inline void __update_field_vars(struct tracing_map_elt *elt, static void update_field_vars(struct hist_trigger_data *hist_data, struct tracing_map_elt *elt, + struct trace_buffer *buffer, struct ring_buffer_event *rbe, void *rec) { - __update_field_vars(elt, rbe, rec, hist_data->field_vars, + __update_field_vars(elt, buffer, rbe, rec, hist_data->field_vars, hist_data->n_field_vars, 0); } static void save_track_data_vars(struct hist_trigger_data *hist_data, - struct tracing_map_elt *elt, void *rec, + struct tracing_map_elt *elt, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *rbe, void *key, struct action_data *data, u64 *var_ref_vals) { - __update_field_vars(elt, rbe, rec, hist_data->save_vars, + __update_field_vars(elt, buffer, rbe, rec, hist_data->save_vars, hist_data->n_save_vars, hist_data->n_field_var_str); } @@ -2780,12 +2799,14 @@ static void save_track_val(struct hist_trigger_data *hist_data, } static void save_track_data(struct hist_trigger_data *hist_data, - struct tracing_map_elt *elt, void *rec, + struct tracing_map_elt *elt, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *rbe, void *key, struct action_data *data, u64 *var_ref_vals) { if (data->track_data.save_data) - data->track_data.save_data(hist_data, elt, rec, rbe, key, data, var_ref_vals); + data->track_data.save_data(hist_data, elt, buffer, rec, rbe, + key, data, var_ref_vals); } static bool check_track_val(struct tracing_map_elt *elt, @@ -2836,7 +2857,8 @@ static bool cond_snapshot_update(struct trace_array *tr, void *cond_data) } static void save_track_data_snapshot(struct hist_trigger_data *hist_data, - struct tracing_map_elt *elt, void *rec, + struct tracing_map_elt *elt, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *rbe, void *key, struct action_data *data, u64 *var_ref_vals) @@ -2905,7 +2927,8 @@ static bool cond_snapshot_update(struct trace_array *tr, void *cond_data) return false; } static void save_track_data_snapshot(struct hist_trigger_data *hist_data, - struct tracing_map_elt *elt, void *rec, + struct tracing_map_elt *elt, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *rbe, void *key, struct action_data *data, u64 *var_ref_vals) {} @@ -2947,7 +2970,8 @@ static void track_data_print(struct seq_file *m, } static void ontrack_action(struct hist_trigger_data *hist_data, - struct tracing_map_elt *elt, void *rec, + struct tracing_map_elt *elt, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *rbe, void *key, struct action_data *data, u64 *var_ref_vals) { @@ -2955,7 +2979,8 @@ static void ontrack_action(struct hist_trigger_data *hist_data, if (check_track_val(elt, data, var_val)) { save_track_val(hist_data, elt, data, var_val); - save_track_data(hist_data, elt, rec, rbe, key, data, var_ref_vals); + save_track_data(hist_data, elt, buffer, rec, rbe, + key, data, var_ref_vals); } } @@ -4400,7 +4425,8 @@ create_hist_data(unsigned int map_bits, } static void hist_trigger_elt_update(struct hist_trigger_data *hist_data, - struct tracing_map_elt *elt, void *rec, + struct tracing_map_elt *elt, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *rbe, u64 *var_ref_vals) { @@ -4414,7 +4440,7 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data, for_each_hist_val_field(i, hist_data) { hist_field = hist_data->fields[i]; - hist_val = hist_field->fn(hist_field, elt, rbe, rec); + hist_val = hist_field->fn(hist_field, elt, buffer, rbe, rec); if (hist_field->flags & HIST_FIELD_FL_VAR) { var_idx = hist_field->var.idx; @@ -4442,13 +4468,13 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data, for_each_hist_key_field(i, hist_data) { hist_field = hist_data->fields[i]; if (hist_field->flags & HIST_FIELD_FL_VAR) { - hist_val = hist_field->fn(hist_field, elt, rbe, rec); + hist_val = hist_field->fn(hist_field, elt, buffer, rbe, rec); var_idx = hist_field->var.idx; tracing_map_set_var(elt, var_idx, hist_val); } } - update_field_vars(hist_data, elt, rbe, rec); + update_field_vars(hist_data, elt, buffer, rbe, rec); } static inline void add_to_key(char *compound_key, void *key, @@ -4478,7 +4504,8 @@ static inline void add_to_key(char *compound_key, void *key, static void hist_trigger_actions(struct hist_trigger_data *hist_data, - struct tracing_map_elt *elt, void *rec, + struct tracing_map_elt *elt, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *rbe, void *key, u64 *var_ref_vals) { @@ -4487,11 +4514,12 @@ hist_trigger_actions(struct hist_trigger_data *hist_data, for (i = 0; i < hist_data->n_actions; i++) { data = hist_data->actions[i]; - data->fn(hist_data, elt, rec, rbe, key, data, var_ref_vals); + data->fn(hist_data, elt, buffer, rec, rbe, key, data, var_ref_vals); } } -static void event_hist_trigger(struct event_trigger_data *data, void *rec, +static void event_hist_trigger(struct event_trigger_data *data, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *rbe) { struct hist_trigger_data *hist_data = data->private_data; @@ -4516,7 +4544,7 @@ static void event_hist_trigger(struct event_trigger_data *data, void *rec, HIST_STACKTRACE_SKIP); key = entries; } else { - field_contents = key_field->fn(key_field, elt, rbe, rec); + field_contents = key_field->fn(key_field, elt, buffer, rbe, rec); if (key_field->flags & HIST_FIELD_FL_STRING) { key = (void *)(unsigned long)field_contents; use_compound_key = true; @@ -4539,10 +4567,10 @@ static void event_hist_trigger(struct event_trigger_data *data, void *rec, if (!elt) return; - hist_trigger_elt_update(hist_data, elt, rec, rbe, var_ref_vals); + hist_trigger_elt_update(hist_data, elt, buffer, rec, rbe, var_ref_vals); if (resolve_var_refs(hist_data, key, var_ref_vals, true)) - hist_trigger_actions(hist_data, elt, rec, rbe, key, var_ref_vals); + hist_trigger_actions(hist_data, elt, buffer, rec, rbe, key, var_ref_vals); } static void hist_trigger_stacktrace_print(struct seq_file *m, @@ -5812,7 +5840,8 @@ __init int register_trigger_hist_cmd(void) } static void -hist_enable_trigger(struct event_trigger_data *data, void *rec, +hist_enable_trigger(struct event_trigger_data *data, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { struct enable_trigger_data *enable_data = data->private_data; @@ -5830,7 +5859,8 @@ hist_enable_trigger(struct event_trigger_data *data, void *rec, } static void -hist_enable_count_trigger(struct event_trigger_data *data, void *rec, +hist_enable_count_trigger(struct event_trigger_data *data, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { if (!data->count) @@ -5839,7 +5869,7 @@ hist_enable_count_trigger(struct event_trigger_data *data, void *rec, if (data->count != -1) (data->count)--; - hist_enable_trigger(data, rec, event); + hist_enable_trigger(data, buffer, rec, event); } static struct event_trigger_ops hist_enable_trigger_ops = { diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index f725802160c0..b8bfa8505b7b 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -53,7 +53,8 @@ void trigger_data_free(struct event_trigger_data *data) * any trigger that should be deferred, ETT_NONE if nothing to defer. */ enum event_trigger_type -event_triggers_call(struct trace_event_file *file, void *rec, +event_triggers_call(struct trace_event_file *file, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { struct event_trigger_data *data; @@ -67,7 +68,7 @@ event_triggers_call(struct trace_event_file *file, void *rec, if (data->paused) continue; if (!rec) { - data->ops->func(data, rec, event); + data->ops->func(data, buffer, rec, event); continue; } filter = rcu_dereference_sched(data->filter); @@ -77,7 +78,7 @@ event_triggers_call(struct trace_event_file *file, void *rec, tt |= data->cmd_ops->trigger_type; continue; } - data->ops->func(data, rec, event); + data->ops->func(data, buffer, rec, event); } return tt; } @@ -105,7 +106,7 @@ event_triggers_post_call(struct trace_event_file *file, if (data->paused) continue; if (data->cmd_ops->trigger_type & tt) - data->ops->func(data, NULL, NULL); + data->ops->func(data, NULL, NULL, NULL); } } EXPORT_SYMBOL_GPL(event_triggers_post_call); @@ -937,7 +938,8 @@ get_named_trigger_data(struct event_trigger_data *data) } static void -traceon_trigger(struct event_trigger_data *data, void *rec, +traceon_trigger(struct event_trigger_data *data, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { if (tracing_is_on()) @@ -947,7 +949,8 @@ traceon_trigger(struct event_trigger_data *data, void *rec, } static void -traceon_count_trigger(struct event_trigger_data *data, void *rec, +traceon_count_trigger(struct event_trigger_data *data, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { if (tracing_is_on()) @@ -963,7 +966,8 @@ traceon_count_trigger(struct event_trigger_data *data, void *rec, } static void -traceoff_trigger(struct event_trigger_data *data, void *rec, +traceoff_trigger(struct event_trigger_data *data, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { if (!tracing_is_on()) @@ -973,7 +977,8 @@ traceoff_trigger(struct event_trigger_data *data, void *rec, } static void -traceoff_count_trigger(struct event_trigger_data *data, void *rec, +traceoff_count_trigger(struct event_trigger_data *data, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { if (!tracing_is_on()) @@ -1071,7 +1076,8 @@ static struct event_command trigger_traceoff_cmd = { #ifdef CONFIG_TRACER_SNAPSHOT static void -snapshot_trigger(struct event_trigger_data *data, void *rec, +snapshot_trigger(struct event_trigger_data *data, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { struct trace_event_file *file = data->private_data; @@ -1083,7 +1089,8 @@ snapshot_trigger(struct event_trigger_data *data, void *rec, } static void -snapshot_count_trigger(struct event_trigger_data *data, void *rec, +snapshot_count_trigger(struct event_trigger_data *data, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { if (!data->count) @@ -1092,7 +1099,7 @@ snapshot_count_trigger(struct event_trigger_data *data, void *rec, if (data->count != -1) (data->count)--; - snapshot_trigger(data, rec, event); + snapshot_trigger(data, buffer, rec, event); } static int @@ -1176,14 +1183,16 @@ static __init int register_trigger_snapshot_cmd(void) { return 0; } #endif static void -stacktrace_trigger(struct event_trigger_data *data, void *rec, +stacktrace_trigger(struct event_trigger_data *data, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { trace_dump_stack(STACK_SKIP); } static void -stacktrace_count_trigger(struct event_trigger_data *data, void *rec, +stacktrace_count_trigger(struct event_trigger_data *data, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { if (!data->count) @@ -1192,7 +1201,7 @@ stacktrace_count_trigger(struct event_trigger_data *data, void *rec, if (data->count != -1) (data->count)--; - stacktrace_trigger(data, rec, event); + stacktrace_trigger(data, buffer, rec, event); } static int @@ -1254,7 +1263,8 @@ static __init void unregister_trigger_traceon_traceoff_cmds(void) } static void -event_enable_trigger(struct event_trigger_data *data, void *rec, +event_enable_trigger(struct event_trigger_data *data, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { struct enable_trigger_data *enable_data = data->private_data; @@ -1266,7 +1276,8 @@ event_enable_trigger(struct event_trigger_data *data, void *rec, } static void -event_enable_count_trigger(struct event_trigger_data *data, void *rec, +event_enable_count_trigger(struct event_trigger_data *data, + struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { struct enable_trigger_data *enable_data = data->private_data; @@ -1281,7 +1292,7 @@ event_enable_count_trigger(struct event_trigger_data *data, void *rec, if (data->count != -1) (data->count)--; - event_enable_trigger(data, rec, event); + event_enable_trigger(data, buffer, rec, event); } int event_enable_trigger_print(struct seq_file *m, -- cgit v1.2.3-71-gd317 From efe6196a6bc5bbc84b856316c4687fd24566a95c Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 16 Mar 2021 12:41:04 -0400 Subject: ring-buffer: Allow ring_buffer_event_time_stamp() to return time stamp of all events Currently, ring_buffer_event_time_stamp() only returns an accurate time stamp of the event if it has an absolute extended time stamp attached to it. To make it more robust, use the event_stamp() in case the event does not have an absolute value attached to it. This will allow ring_buffer_event_time_stamp() to be used in more cases than just histograms, and it will also allow histograms to not require including absolute values all the time. Link: https://lkml.kernel.org/r/20210316164113.704830885@goodmis.org Reviewed-by: Tom Zanussi Signed-off-by: Steven Rostedt (VMware) --- include/linux/ring_buffer.h | 3 +- kernel/trace/ring_buffer.c | 60 ++++++++++++++++++++++++++++++---------- kernel/trace/trace_events_hist.c | 2 +- 3 files changed, 48 insertions(+), 17 deletions(-) (limited to 'kernel') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 136ea0997e6d..057b7ed4fe24 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -61,7 +61,8 @@ enum ring_buffer_type { unsigned ring_buffer_event_length(struct ring_buffer_event *event); void *ring_buffer_event_data(struct ring_buffer_event *event); -u64 ring_buffer_event_time_stamp(struct ring_buffer_event *event); +u64 ring_buffer_event_time_stamp(struct trace_buffer *buffer, + struct ring_buffer_event *event); /* * ring_buffer_discard_commit will remove an event that has not diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 470d97169081..8fa2a84f714f 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -298,21 +298,6 @@ static u64 rb_event_time_stamp(struct ring_buffer_event *event) return ts; } -/** - * ring_buffer_event_time_stamp - return the event's extended timestamp - * @event: the event to get the timestamp of - * - * Returns the extended timestamp associated with a data event. - * An extended time_stamp is a 64-bit timestamp represented - * internally in a special way that makes the best use of space - * contained within a ring buffer event. This function decodes - * it and maps it to a straight u64 value. - */ -u64 ring_buffer_event_time_stamp(struct ring_buffer_event *event) -{ - return rb_event_time_stamp(event); -} - /* Flag when events were overwritten */ #define RB_MISSED_EVENTS (1 << 31) /* Missed count stored at end */ @@ -757,6 +742,51 @@ static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set) } #endif +static inline u64 rb_time_stamp(struct trace_buffer *buffer); + +/** + * ring_buffer_event_time_stamp - return the event's current time stamp + * @buffer: The buffer that the event is on + * @event: the event to get the time stamp of + * + * Note, this must be called after @event is reserved, and before it is + * committed to the ring buffer. And must be called from the same + * context where the event was reserved (normal, softirq, irq, etc). + * + * Returns the time stamp associated with the current event. + * If the event has an extended time stamp, then that is used as + * the time stamp to return. + * In the highly unlikely case that the event was nested more than + * the max nesting, then the write_stamp of the buffer is returned, + * otherwise current time is returned, but that really neither of + * the last two cases should ever happen. + */ +u64 ring_buffer_event_time_stamp(struct trace_buffer *buffer, + struct ring_buffer_event *event) +{ + struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[smp_processor_id()]; + unsigned int nest; + u64 ts; + + /* If the event includes an absolute time, then just use that */ + if (event->type_len == RINGBUF_TYPE_TIME_STAMP) + return rb_event_time_stamp(event); + + /* Read the current saved nesting level time stamp */ + nest = local_read(&cpu_buffer->committing) - 1; + if (likely(nest < MAX_NEST)) + return cpu_buffer->event_stamp[nest]; + + WARN_ON_ONCE(1); + + /* Can only fail on 32 bit */ + if (!rb_time_read(&cpu_buffer->write_stamp, &ts)) + /* Screw it, just read the current time */ + ts = rb_time_stamp(cpu_buffer->buffer); + + return ts; +} + /** * ring_buffer_nr_pages - get the number of buffer pages in the ring buffer * @buffer: The ring_buffer to get the number of pages from diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 6978aa3ee4c5..45986cb4637e 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -644,7 +644,7 @@ static u64 hist_field_timestamp(struct hist_field *hist_field, struct hist_trigger_data *hist_data = hist_field->hist_data; struct trace_array *tr = hist_data->event_file->tr; - u64 ts = ring_buffer_event_time_stamp(rbe); + u64 ts = ring_buffer_event_time_stamp(buffer, rbe); if (hist_data->attrs->ts_in_usecs && trace_clock_in_ns(tr)) ts = ns2usecs(ts); -- cgit v1.2.3-71-gd317 From b94bc80df64823e676b506f8de7dcf6a688d681e Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 16 Mar 2021 12:41:05 -0400 Subject: tracing: Use a no_filter_buffering_ref to stop using the filter buffer Currently, the trace histograms relies on it using absolute time stamps to trigger the tracing to not use the temp buffer if filters are set. That's because the histograms need the full timestamp that is saved in the ring buffer. That is no longer the case, as the ring_buffer_event_time_stamp() can now return the time stamp for all events without all triggering a full absolute time stamp. Now that the absolute time stamp is an unrelated dependency to not using the filters. There's nothing about having absolute timestamps to keep from using the filter buffer. Instead, change the interface to explicitly state to disable filter buffering that the histogram logic can use. Link: https://lkml.kernel.org/r/20210316164113.847886563@goodmis.org Reviewed-by: Tom Zanussi Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 28 ++++++++++++---------------- kernel/trace/trace.h | 4 ++-- kernel/trace/trace_events_hist.c | 6 +++--- 3 files changed, 17 insertions(+), 21 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f979220238a5..b15436ff85e8 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2737,12 +2737,13 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb, unsigned int trace_ctx) { struct ring_buffer_event *entry; + struct trace_array *tr = trace_file->tr; int val; - *current_rb = trace_file->tr->array_buffer.buffer; + *current_rb = tr->array_buffer.buffer; - if (!ring_buffer_time_stamp_abs(*current_rb) && (trace_file->flags & - (EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED)) && + if (!tr->no_filter_buffering_ref && + (trace_file->flags & (EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED)) && (entry = this_cpu_read(trace_buffered_event))) { /* Try to use the per cpu buffer first */ val = this_cpu_inc_return(trace_buffered_event_cnt); @@ -6971,31 +6972,26 @@ static int tracing_time_stamp_mode_open(struct inode *inode, struct file *file) return ret; } -int tracing_set_time_stamp_abs(struct trace_array *tr, bool abs) +/* + * Set or disable using the per CPU trace_buffer_event when possible. + */ +int tracing_set_filter_buffering(struct trace_array *tr, bool set) { int ret = 0; mutex_lock(&trace_types_lock); - if (abs && tr->time_stamp_abs_ref++) + if (set && tr->no_filter_buffering_ref++) goto out; - if (!abs) { - if (WARN_ON_ONCE(!tr->time_stamp_abs_ref)) { + if (!set) { + if (WARN_ON_ONCE(!tr->no_filter_buffering_ref)) { ret = -EINVAL; goto out; } - if (--tr->time_stamp_abs_ref) - goto out; + --tr->no_filter_buffering_ref; } - - ring_buffer_set_time_stamp_abs(tr->array_buffer.buffer, abs); - -#ifdef CONFIG_TRACER_MAX_TRACE - if (tr->max_buffer.buffer) - ring_buffer_set_time_stamp_abs(tr->max_buffer.buffer, abs); -#endif out: mutex_unlock(&trace_types_lock); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 798773178d7e..f2a7a72825c7 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -352,7 +352,7 @@ struct trace_array { /* function tracing enabled */ int function_enabled; #endif - int time_stamp_abs_ref; + int no_filter_buffering_ref; struct list_head hist_vars; #ifdef CONFIG_TRACER_SNAPSHOT struct cond_snapshot *cond_snapshot; @@ -372,7 +372,7 @@ extern int tracing_check_open_get_tr(struct trace_array *tr); extern struct trace_array *trace_array_find(const char *instance); extern struct trace_array *trace_array_find_get(const char *instance); -extern int tracing_set_time_stamp_abs(struct trace_array *tr, bool abs); +extern int tracing_set_filter_buffering(struct trace_array *tr, bool set); extern int tracing_set_clock(struct trace_array *tr, const char *clockstr); extern bool trace_clock_in_ns(struct trace_array *tr); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 45986cb4637e..c1abd63f1d6c 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -5484,7 +5484,7 @@ static int hist_register_trigger(char *glob, struct event_trigger_ops *ops, goto out; } - tracing_set_time_stamp_abs(file->tr, true); + tracing_set_filter_buffering(file->tr, true); } if (named_data) @@ -5592,7 +5592,7 @@ static void hist_unregister_trigger(char *glob, struct event_trigger_ops *ops, if (hist_data->enable_timestamps) { if (!hist_data->remove || unregistered) - tracing_set_time_stamp_abs(file->tr, false); + tracing_set_filter_buffering(file->tr, false); } } @@ -5639,7 +5639,7 @@ static void hist_unreg_all(struct trace_event_file *file) update_cond_flag(file); if (hist_data->enable_timestamps) - tracing_set_time_stamp_abs(file->tr, false); + tracing_set_filter_buffering(file->tr, false); if (test->ops->free) test->ops->free(test->ops, test); } -- cgit v1.2.3-71-gd317 From a948c69d6fb1ba749a958a8a87d4eecdda28989d Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 16 Mar 2021 12:41:06 -0400 Subject: ring-buffer: Add verifier for using ring_buffer_event_time_stamp() The ring_buffer_event_time_stamp() must be only called by an event that has not been committed yet, and is on the buffer that is passed in. This was used to help debug converting the histogram logic over to using the new time stamp code, and was proven to be very useful. Add a verifier that can check that this is the case, and extra WARN_ONs to catch unexpected use cases. Link: https://lkml.kernel.org/r/20210316164113.987294354@goodmis.org Reviewed-by: Tom Zanussi Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 56 ++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 52 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 8fa2a84f714f..1c61a8cd7b99 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -742,6 +742,48 @@ static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set) } #endif +/* + * Enable this to make sure that the event passed to + * ring_buffer_event_time_stamp() is not committed and also + * is on the buffer that it passed in. + */ +//#define RB_VERIFY_EVENT +#ifdef RB_VERIFY_EVENT +static struct list_head *rb_list_head(struct list_head *list); +static void verify_event(struct ring_buffer_per_cpu *cpu_buffer, + void *event) +{ + struct buffer_page *page = cpu_buffer->commit_page; + struct buffer_page *tail_page = READ_ONCE(cpu_buffer->tail_page); + struct list_head *next; + long commit, write; + unsigned long addr = (unsigned long)event; + bool done = false; + int stop = 0; + + /* Make sure the event exists and is not committed yet */ + do { + if (page == tail_page || WARN_ON_ONCE(stop++ > 100)) + done = true; + commit = local_read(&page->page->commit); + write = local_read(&page->write); + if (addr >= (unsigned long)&page->page->data[commit] && + addr < (unsigned long)&page->page->data[write]) + return; + + next = rb_list_head(page->list.next); + page = list_entry(next, struct buffer_page, list); + } while (!done); + WARN_ON_ONCE(1); +} +#else +static inline void verify_event(struct ring_buffer_per_cpu *cpu_buffer, + void *event) +{ +} +#endif + + static inline u64 rb_time_stamp(struct trace_buffer *buffer); /** @@ -772,13 +814,19 @@ u64 ring_buffer_event_time_stamp(struct trace_buffer *buffer, if (event->type_len == RINGBUF_TYPE_TIME_STAMP) return rb_event_time_stamp(event); + nest = local_read(&cpu_buffer->committing); + verify_event(cpu_buffer, event); + if (WARN_ON_ONCE(!nest)) + goto fail; + /* Read the current saved nesting level time stamp */ - nest = local_read(&cpu_buffer->committing) - 1; - if (likely(nest < MAX_NEST)) + if (likely(--nest < MAX_NEST)) return cpu_buffer->event_stamp[nest]; - WARN_ON_ONCE(1); + /* Shouldn't happen, warn if it does */ + WARN_ONCE(1, "nest (%d) greater than max", nest); + fail: /* Can only fail on 32 bit */ if (!rb_time_read(&cpu_buffer->write_stamp, &ts)) /* Screw it, just read the current time */ @@ -2750,7 +2798,7 @@ rb_update_event(struct ring_buffer_per_cpu *cpu_buffer, u64 delta = info->delta; unsigned int nest = local_read(&cpu_buffer->committing) - 1; - if (nest < MAX_NEST) + if (!WARN_ON_ONCE(nest >= MAX_NEST)) cpu_buffer->event_stamp[nest] = info->ts; /* -- cgit v1.2.3-71-gd317 From d8279bfc5e9598682f657606d3830ab65932cfe4 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 16 Mar 2021 12:41:07 -0400 Subject: tracing: Add tracing_event_time_stamp() API Add a tracing_event_time_stamp() API that checks if the event passed in is not on the ring buffer but a pointer to the per CPU trace_buffered_event which does not have its time stamp set yet. If it is a pointer to the trace_buffered_event, then just return the current time stamp that the ring buffer would produce. Otherwise, return the time stamp from the event. Link: https://lkml.kernel.org/r/20210316164114.131996180@goodmis.org Reviewed-by: Tom Zanussi Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 8 ++++++++ kernel/trace/trace.h | 1 + 2 files changed, 9 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index b15436ff85e8..90ae3140756e 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6972,6 +6972,14 @@ static int tracing_time_stamp_mode_open(struct inode *inode, struct file *file) return ret; } +u64 tracing_event_time_stamp(struct trace_buffer *buffer, struct ring_buffer_event *rbe) +{ + if (rbe == this_cpu_read(trace_buffered_event)) + return ring_buffer_time_stamp(buffer, smp_processor_id()); + + return ring_buffer_event_time_stamp(buffer, rbe); +} + /* * Set or disable using the per CPU trace_buffer_event when possible. */ diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index f2a7a72825c7..0d8f54f49a3a 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -372,6 +372,7 @@ extern int tracing_check_open_get_tr(struct trace_array *tr); extern struct trace_array *trace_array_find(const char *instance); extern struct trace_array *trace_array_find_get(const char *instance); +extern u64 tracing_event_time_stamp(struct trace_buffer *buffer, struct ring_buffer_event *rbe); extern int tracing_set_filter_buffering(struct trace_array *tr, bool set); extern int tracing_set_clock(struct trace_array *tr, const char *clockstr); -- cgit v1.2.3-71-gd317 From 5013f454a352cce8e62162976026a9c472595e42 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 25 Feb 2021 16:51:23 -0500 Subject: tracing: Add check of trace event print fmts for dereferencing pointers Trace events record data into the ring buffer at the time of the event. The trace event has a printf logic to display the recorded data at a much later time when the user reads the trace file. This makes using dereferencing pointers unsafe if the dereferenced pointer points to the original source. The safe way to handle this is to create an array within the trace event and copy the source into the array. Then the dereference pointer may point to that array. As this is a easy mistake to make, a check is added to examine all trace event print fmts to make sure that they are safe to use. This only checks the various %p* dereferenced pointers like %pB, %pR, etc. It does not handle dereferencing of strings, as there are some use cases that are OK to dereference the source. That will be dealt with differently. Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events.c | 210 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 210 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index a3563afd412d..f58106eaf8cb 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -217,6 +217,214 @@ int trace_event_get_offsets(struct trace_event_call *call) return tail->offset + tail->size; } +/* + * Check if the referenced field is an array and return true, + * as arrays are OK to dereference. + */ +static bool test_field(const char *fmt, struct trace_event_call *call) +{ + struct trace_event_fields *field = call->class->fields_array; + const char *array_descriptor; + const char *p = fmt; + int len; + + if (!(len = str_has_prefix(fmt, "REC->"))) + return false; + fmt += len; + for (p = fmt; *p; p++) { + if (!isalnum(*p) && *p != '_') + break; + } + len = p - fmt; + + for (; field->type; field++) { + if (strncmp(field->name, fmt, len) || + field->name[len]) + continue; + array_descriptor = strchr(field->type, '['); + /* This is an array and is OK to dereference. */ + return array_descriptor != NULL; + } + return false; +} + +/* + * Examine the print fmt of the event looking for unsafe dereference + * pointers using %p* that could be recorded in the trace event and + * much later referenced after the pointer was freed. Dereferencing + * pointers are OK, if it is dereferenced into the event itself. + */ +static void test_event_printk(struct trace_event_call *call) +{ + u64 dereference_flags = 0; + bool first = true; + const char *fmt, *c, *r, *a; + int parens = 0; + char in_quote = 0; + int start_arg = 0; + int arg = 0; + int i; + + fmt = call->print_fmt; + + if (!fmt) + return; + + for (i = 0; fmt[i]; i++) { + switch (fmt[i]) { + case '\\': + i++; + if (!fmt[i]) + return; + continue; + case '"': + case '\'': + /* + * The print fmt starts with a string that + * is processed first to find %p* usage, + * then after the first string, the print fmt + * contains arguments that are used to check + * if the dereferenced %p* usage is safe. + */ + if (first) { + if (fmt[i] == '\'') + continue; + if (in_quote) { + arg = 0; + first = false; + /* + * If there was no %p* uses + * the fmt is OK. + */ + if (!dereference_flags) + return; + } + } + if (in_quote) { + if (in_quote == fmt[i]) + in_quote = 0; + } else { + in_quote = fmt[i]; + } + continue; + case '%': + if (!first || !in_quote) + continue; + i++; + if (!fmt[i]) + return; + switch (fmt[i]) { + case '%': + continue; + case 'p': + /* Find dereferencing fields */ + switch (fmt[i + 1]) { + case 'B': case 'R': case 'r': + case 'b': case 'M': case 'm': + case 'I': case 'i': case 'E': + case 'U': case 'V': case 'N': + case 'a': case 'd': case 'D': + case 'g': case 't': case 'C': + case 'O': case 'f': + if (WARN_ONCE(arg == 63, + "Too many args for event: %s", + trace_event_name(call))) + return; + dereference_flags |= 1ULL << arg; + } + break; + default: + { + bool star = false; + int j; + + /* Increment arg if %*s exists. */ + for (j = 0; fmt[i + j]; j++) { + if (isdigit(fmt[i + j]) || + fmt[i + j] == '.') + continue; + if (fmt[i + j] == '*') { + star = true; + continue; + } + if ((fmt[i + j] == 's') && star) + arg++; + break; + } + break; + } /* default */ + + } /* switch */ + arg++; + continue; + case '(': + if (in_quote) + continue; + parens++; + continue; + case ')': + if (in_quote) + continue; + parens--; + if (WARN_ONCE(parens < 0, + "Paren mismatch for event: %s\narg='%s'\n%*s", + trace_event_name(call), + fmt + start_arg, + (i - start_arg) + 5, "^")) + return; + continue; + case ',': + if (in_quote || parens) + continue; + i++; + while (isspace(fmt[i])) + i++; + start_arg = i; + if (!(dereference_flags & (1ULL << arg))) + goto next_arg; + + /* Find the REC-> in the argument */ + c = strchr(fmt + i, ','); + r = strstr(fmt + i, "REC->"); + if (r && (!c || r < c)) { + /* + * Addresses of events on the buffer, + * or an array on the buffer is + * OK to dereference. + * There's ways to fool this, but + * this is to catch common mistakes, + * not malicious code. + */ + a = strchr(fmt + i, '&'); + if ((a && (a < r)) || test_field(r, call)) + dereference_flags &= ~(1ULL << arg); + } + next_arg: + i--; + arg++; + } + } + + /* + * If you triggered the below warning, the trace event reported + * uses an unsafe dereference pointer %p*. As the data stored + * at the trace event time may no longer exist when the trace + * event is printed, dereferencing to the original source is + * unsafe. The source of the dereference must be copied into the + * event itself, and the dereference must access the copy instead. + */ + if (WARN_ON_ONCE(dereference_flags)) { + arg = 1; + while (!(dereference_flags & 1)) { + dereference_flags >>= 1; + arg++; + } + pr_warn("event %s has unsafe dereference of argument %d\n", + trace_event_name(call), arg); + pr_warn("print_fmt: %s\n", fmt); + } +} + int trace_event_raw_init(struct trace_event_call *call) { int id; @@ -225,6 +433,8 @@ int trace_event_raw_init(struct trace_event_call *call) if (!id) return -ENODEV; + test_event_printk(call); + return 0; } EXPORT_SYMBOL_GPL(trace_event_raw_init); -- cgit v1.2.3-71-gd317 From 9a6944fee68e25084130386c608c5ac8db487581 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 25 Feb 2021 22:00:57 -0500 Subject: tracing: Add a verifier to check string pointers for trace events It is a common mistake for someone writing a trace event to save a pointer to a string in the TP_fast_assign() and then display that string pointer in the TP_printk() with %s. The problem is that those two events may happen a long time apart, where the source of the string may no longer exist. The proper way to handle displaying any string that is not guaranteed to be in the kernel core rodata section, is to copy it into the ring buffer via the __string(), __assign_str() and __get_str() helper macros. Add a check at run time while displaying the TP_printk() of events to make sure that every %s referenced is safe to dereference, and if it is not, trigger a warning and only show the address of the pointer, and the dereferenced string if it can be safely retrieved with a strncpy_from_kernel_nofault() call. In order to not have to copy the parsing of vsnprintf() formats, or even exporting its code, the verifier relies on vsnprintf() being able to modify the va_list that is passed to it, and it remains modified after it is called. This is the case for some architectures like x86_64, but other architectures like x86_32 pass the va_list to vsnprintf() as a value not a reference, and the verifier can not use it to parse the non string arguments. Thus, at boot up, it is checked if vsnprintf() modifies the passed in va_list or not, and a static branch will disable the verifier if it's not compatible. Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 200 ++++++++++++++++++++++++++++++++++++++++++++ kernel/trace/trace.h | 3 + kernel/trace/trace_output.c | 2 +- kernel/trace/trace_printk.c | 11 +++ 4 files changed, 215 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 90ae3140756e..e32f5a49f1cf 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3558,6 +3558,204 @@ static char *trace_iter_expand_format(struct trace_iterator *iter) return tmp; } +/* Returns true if the string is safe to dereference from an event */ +static bool trace_safe_str(struct trace_iterator *iter, const char *str) +{ + unsigned long addr = (unsigned long)str; + struct trace_event *trace_event; + struct trace_event_call *event; + + /* OK if part of the event data */ + if ((addr >= (unsigned long)iter->ent) && + (addr < (unsigned long)iter->ent + iter->ent_size)) + return true; + + /* OK if part of the temp seq buffer */ + if ((addr >= (unsigned long)iter->tmp_seq.buffer) && + (addr < (unsigned long)iter->tmp_seq.buffer + PAGE_SIZE)) + return true; + + /* Core rodata can not be freed */ + if (is_kernel_rodata(addr)) + return true; + + if (trace_is_tracepoint_string(str)) + return true; + + /* + * Now this could be a module event, referencing core module + * data, which is OK. + */ + if (!iter->ent) + return false; + + trace_event = ftrace_find_event(iter->ent->type); + if (!trace_event) + return false; + + event = container_of(trace_event, struct trace_event_call, event); + if (!event->mod) + return false; + + /* Would rather have rodata, but this will suffice */ + if (within_module_core(addr, event->mod)) + return true; + + return false; +} + +static const char *show_buffer(struct trace_seq *s) +{ + struct seq_buf *seq = &s->seq; + + seq_buf_terminate(seq); + + return seq->buffer; +} + +static DEFINE_STATIC_KEY_FALSE(trace_no_verify); + +static int test_can_verify_check(const char *fmt, ...) +{ + char buf[16]; + va_list ap; + int ret; + + /* + * The verifier is dependent on vsnprintf() modifies the va_list + * passed to it, where it is sent as a reference. Some architectures + * (like x86_32) passes it by value, which means that vsnprintf() + * does not modify the va_list passed to it, and the verifier + * would then need to be able to understand all the values that + * vsnprintf can use. If it is passed by value, then the verifier + * is disabled. + */ + va_start(ap, fmt); + vsnprintf(buf, 16, "%d", ap); + ret = va_arg(ap, int); + va_end(ap); + + return ret; +} + +static void test_can_verify(void) +{ + if (!test_can_verify_check("%d %d", 0, 1)) { + pr_info("trace event string verifier disabled\n"); + static_branch_inc(&trace_no_verify); + } +} + +/** + * trace_check_vprintf - Check dereferenced strings while writing to the seq buffer + * @iter: The iterator that holds the seq buffer and the event being printed + * @fmt: The format used to print the event + * @ap: The va_list holding the data to print from @fmt. + * + * This writes the data into the @iter->seq buffer using the data from + * @fmt and @ap. If the format has a %s, then the source of the string + * is examined to make sure it is safe to print, otherwise it will + * warn and print "[UNSAFE MEMORY]" in place of the dereferenced string + * pointer. + */ +void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, + va_list ap) +{ + const char *p = fmt; + const char *str; + int i, j; + + if (WARN_ON_ONCE(!fmt)) + return; + + if (static_branch_unlikely(&trace_no_verify)) + goto print; + + /* Don't bother checking when doing a ftrace_dump() */ + if (iter->fmt == static_fmt_buf) + goto print; + + while (*p) { + j = 0; + + /* We only care about %s and variants */ + for (i = 0; p[i]; i++) { + if (i + 1 >= iter->fmt_size) { + /* + * If we can't expand the copy buffer, + * just print it. + */ + if (!trace_iter_expand_format(iter)) + goto print; + } + + if (p[i] == '\\' && p[i+1]) { + i++; + continue; + } + if (p[i] == '%') { + /* Need to test cases like %08.*s */ + for (j = 1; p[i+j]; j++) { + if (isdigit(p[i+j]) || + p[i+j] == '*' || + p[i+j] == '.') + continue; + break; + } + if (p[i+j] == 's') + break; + } + j = 0; + } + /* If no %s found then just print normally */ + if (!p[i]) + break; + + /* Copy up to the %s, and print that */ + strncpy(iter->fmt, p, i); + iter->fmt[i] = '\0'; + trace_seq_vprintf(&iter->seq, iter->fmt, ap); + + /* The ap now points to the string data of the %s */ + str = va_arg(ap, const char *); + + /* + * If you hit this warning, it is likely that the + * trace event in question used %s on a string that + * was saved at the time of the event, but may not be + * around when the trace is read. Use __string(), + * __assign_str() and __get_str() helpers in the TRACE_EVENT() + * instead. See samples/trace_events/trace-events-sample.h + * for reference. + */ + if (WARN_ONCE(!trace_safe_str(iter, str), + "fmt: '%s' current_buffer: '%s'", + fmt, show_buffer(&iter->seq))) { + int ret; + + /* Try to safely read the string */ + ret = strncpy_from_kernel_nofault(iter->fmt, str, + iter->fmt_size); + if (ret < 0) + trace_seq_printf(&iter->seq, "(0x%px)", str); + else + trace_seq_printf(&iter->seq, "(0x%px:%s)", + str, iter->fmt); + str = "[UNSAFE-MEMORY]"; + strcpy(iter->fmt, "%s"); + } else { + strncpy(iter->fmt, p + i, j + 1); + iter->fmt[j+1] = '\0'; + } + trace_seq_printf(&iter->seq, iter->fmt, str); + + p += i + j + 1; + } + print: + if (*p) + trace_seq_vprintf(&iter->seq, p, ap); +} + const char *trace_event_format(struct trace_iterator *iter, const char *fmt) { const char *p, *new_fmt; @@ -9675,6 +9873,8 @@ __init static int tracer_alloc_buffers(void) register_snapshot_cmd(); + test_can_verify(); + return 0; out_free_savedcmd: diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 0d8f54f49a3a..2952bd92bc62 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -582,7 +582,10 @@ struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, void trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer, struct ring_buffer_event *event); +bool trace_is_tracepoint_string(const char *str); const char *trace_event_format(struct trace_iterator *iter, const char *fmt); +void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, + va_list ap); int trace_empty(struct trace_iterator *iter); diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 61255bad7e01..a0146e1fffdf 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -317,7 +317,7 @@ void trace_event_printf(struct trace_iterator *iter, const char *fmt, ...) va_list ap; va_start(ap, fmt); - trace_seq_vprintf(&iter->seq, trace_event_format(iter, fmt), ap); + trace_check_vprintf(iter, trace_event_format(iter, fmt), ap); va_end(ap); } EXPORT_SYMBOL(trace_event_printf); diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index ff32476df072..4b320fe7df70 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -251,6 +251,17 @@ int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap) } EXPORT_SYMBOL_GPL(__ftrace_vprintk); +bool trace_is_tracepoint_string(const char *str) +{ + const char **ptr = __start___tracepoint_str; + + for (ptr = __start___tracepoint_str; ptr < __stop___tracepoint_str; ptr++) { + if (str == *ptr) + return true; + } + return false; +} + static const char **find_next(void *v, loff_t *pos) { const char **fmt = v; -- cgit v1.2.3-71-gd317 From 73f620951b2b594bdc38722c0d647c3b3312af7a Mon Sep 17 00:00:00 2001 From: Claire Chang Date: Thu, 18 Mar 2021 17:14:22 +0100 Subject: swiotlb: move global variables into a new io_tlb_mem structure Added a new struct, io_tlb_mem, as the IO TLB memory pool descriptor and moved relevant global variables into that struct. This will be useful later to allow for restricted DMA pool. Signed-off-by: Claire Chang [hch: rebased] Signed-off-by: Christoph Hellwig Signed-off-by: Konrad Rzeszutek Wilk --- drivers/xen/swiotlb-xen.c | 2 +- include/linux/swiotlb.h | 43 +++++- kernel/dma/swiotlb.c | 354 +++++++++++++++++++++------------------------- 3 files changed, 206 insertions(+), 193 deletions(-) (limited to 'kernel') diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 4ecfce2c6f72..5329ad54a5f3 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -548,7 +548,7 @@ xen_swiotlb_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, static int xen_swiotlb_dma_supported(struct device *hwdev, u64 mask) { - return xen_phys_to_dma(hwdev, io_tlb_end - 1) <= mask; + return xen_phys_to_dma(hwdev, io_tlb_default_mem.end - 1) <= mask; } const struct dma_map_ops xen_swiotlb_dma_ops = { diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 0696bdc8072e..5ec5378b17c3 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -6,6 +6,7 @@ #include #include #include +#include struct device; struct page; @@ -61,11 +62,49 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys, #ifdef CONFIG_SWIOTLB extern enum swiotlb_force swiotlb_force; -extern phys_addr_t io_tlb_start, io_tlb_end; + +/** + * struct io_tlb_mem - IO TLB Memory Pool Descriptor + * + * @start: The start address of the swiotlb memory pool. Used to do a quick + * range check to see if the memory was in fact allocated by this + * API. + * @end: The end address of the swiotlb memory pool. Used to do a quick + * range check to see if the memory was in fact allocated by this + * API. + * @nslabs: The number of IO TLB blocks (in groups of 64) between @start and + * @end. This is command line adjustable via setup_io_tlb_npages. + * @used: The number of used IO TLB block. + * @list: The free list describing the number of free entries available + * from each index. + * @index: The index to start searching in the next round. + * @orig_addr: The original address corresponding to a mapped entry. + * @alloc_size: Size of the allocated buffer. + * @lock: The lock to protect the above data structures in the map and + * unmap calls. + * @debugfs: The dentry to debugfs. + * @late_alloc: %true if allocated using the page allocator + */ +struct io_tlb_mem { + phys_addr_t start; + phys_addr_t end; + unsigned long nslabs; + unsigned long used; + unsigned int *list; + unsigned int index; + phys_addr_t *orig_addr; + size_t *alloc_size; + spinlock_t lock; + struct dentry *debugfs; + bool late_alloc; +}; +extern struct io_tlb_mem io_tlb_default_mem; static inline bool is_swiotlb_buffer(phys_addr_t paddr) { - return paddr >= io_tlb_start && paddr < io_tlb_end; + struct io_tlb_mem *mem = &io_tlb_default_mem; + + return paddr >= mem->start && paddr < mem->end; } void __init swiotlb_exit(void); diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 35e24f0ff8b2..d9c097f0f78c 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -59,32 +59,11 @@ */ #define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT) -enum swiotlb_force swiotlb_force; - -/* - * Used to do a quick range check in swiotlb_tbl_unmap_single and - * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this - * API. - */ -phys_addr_t io_tlb_start, io_tlb_end; - -/* - * The number of IO TLB blocks (in groups of 64) between io_tlb_start and - * io_tlb_end. This is command line adjustable via setup_io_tlb_npages. - */ -static unsigned long io_tlb_nslabs; +#define INVALID_PHYS_ADDR (~(phys_addr_t)0) -/* - * The number of used IO TLB block - */ -static unsigned long io_tlb_used; +enum swiotlb_force swiotlb_force; -/* - * This is a free list describing the number of free entries available from - * each index - */ -static unsigned int *io_tlb_list; -static unsigned int io_tlb_index; +struct io_tlb_mem io_tlb_default_mem; /* * Max segment that we can provide which (if pages are contingous) will @@ -92,32 +71,15 @@ static unsigned int io_tlb_index; */ static unsigned int max_segment; -/* - * We need to save away the original address corresponding to a mapped entry - * for the sync operations. - */ -#define INVALID_PHYS_ADDR (~(phys_addr_t)0) -static phys_addr_t *io_tlb_orig_addr; - -/* - * The mapped buffer's size should be validated during a sync operation. - */ -static size_t *io_tlb_alloc_size; - -/* - * Protect the above data structures in the map and unmap calls - */ -static DEFINE_SPINLOCK(io_tlb_lock); - -static int late_alloc; - static int __init setup_io_tlb_npages(char *str) { + struct io_tlb_mem *mem = &io_tlb_default_mem; + if (isdigit(*str)) { - io_tlb_nslabs = simple_strtoul(str, &str, 0); + mem->nslabs = simple_strtoul(str, &str, 0); /* avoid tail segment of size < IO_TLB_SEGSIZE */ - io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); + mem->nslabs = ALIGN(mem->nslabs, IO_TLB_SEGSIZE); } if (*str == ',') ++str; @@ -125,7 +87,7 @@ setup_io_tlb_npages(char *str) swiotlb_force = SWIOTLB_FORCE; } else if (!strcmp(str, "noforce")) { swiotlb_force = SWIOTLB_NO_FORCE; - io_tlb_nslabs = 1; + mem->nslabs = 1; } return 0; @@ -136,7 +98,7 @@ static bool no_iotlb_memory; unsigned long swiotlb_nr_tbl(void) { - return unlikely(no_iotlb_memory) ? 0 : io_tlb_nslabs; + return unlikely(no_iotlb_memory) ? 0 : io_tlb_default_mem.nslabs; } EXPORT_SYMBOL_GPL(swiotlb_nr_tbl); @@ -158,13 +120,14 @@ unsigned long swiotlb_size_or_default(void) { unsigned long size; - size = io_tlb_nslabs << IO_TLB_SHIFT; + size = io_tlb_default_mem.nslabs << IO_TLB_SHIFT; return size ? size : (IO_TLB_DEFAULT_SIZE); } void __init swiotlb_adjust_size(unsigned long new_size) { + struct io_tlb_mem *mem = &io_tlb_default_mem; unsigned long size; /* @@ -172,10 +135,10 @@ void __init swiotlb_adjust_size(unsigned long new_size) * architectures such as those supporting memory encryption to * adjust/expand SWIOTLB size for their use. */ - if (!io_tlb_nslabs) { + if (!mem->nslabs) { size = ALIGN(new_size, IO_TLB_SIZE); - io_tlb_nslabs = size >> IO_TLB_SHIFT; - io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); + mem->nslabs = size >> IO_TLB_SHIFT; + mem->nslabs = ALIGN(mem->nslabs, IO_TLB_SEGSIZE); pr_info("SWIOTLB bounce buffer size adjusted to %luMB", size >> 20); } @@ -183,14 +146,15 @@ void __init swiotlb_adjust_size(unsigned long new_size) void swiotlb_print_info(void) { - unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT; + struct io_tlb_mem *mem = &io_tlb_default_mem; + unsigned long bytes = mem->nslabs << IO_TLB_SHIFT; if (no_iotlb_memory) { pr_warn("No low mem\n"); return; } - pr_info("mapped [mem %pa-%pa] (%luMB)\n", &io_tlb_start, &io_tlb_end, + pr_info("mapped [mem %pa-%pa] (%luMB)\n", &mem->start, &mem->end, bytes >> 20); } @@ -212,68 +176,71 @@ static inline unsigned long nr_slots(u64 val) */ void __init swiotlb_update_mem_attributes(void) { + struct io_tlb_mem *mem = &io_tlb_default_mem; void *vaddr; unsigned long bytes; - if (no_iotlb_memory || late_alloc) + if (no_iotlb_memory || mem->late_alloc) return; - vaddr = phys_to_virt(io_tlb_start); - bytes = PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT); + vaddr = phys_to_virt(mem->start); + bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT); set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT); memset(vaddr, 0, bytes); } int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) { + struct io_tlb_mem *mem = &io_tlb_default_mem; unsigned long i, bytes; size_t alloc_size; /* protect against double initialization */ - if (WARN_ON_ONCE(io_tlb_start)) + if (WARN_ON_ONCE(mem->start)) return -ENOMEM; bytes = nslabs << IO_TLB_SHIFT; - io_tlb_nslabs = nslabs; - io_tlb_start = __pa(tlb); - io_tlb_end = io_tlb_start + bytes; + mem->nslabs = nslabs; + mem->start = __pa(tlb); + mem->end = mem->start + bytes; + mem->index = 0; + spin_lock_init(&mem->lock); /* * Allocate and initialize the free list array. This array is used * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE - * between io_tlb_start and io_tlb_end. + * between mem->start and mem->end. */ - alloc_size = PAGE_ALIGN(io_tlb_nslabs * sizeof(int)); - io_tlb_list = memblock_alloc(alloc_size, PAGE_SIZE); - if (!io_tlb_list) + alloc_size = PAGE_ALIGN(mem->nslabs * sizeof(int)); + mem->list = memblock_alloc(alloc_size, PAGE_SIZE); + if (!mem->list) panic("%s: Failed to allocate %zu bytes align=0x%lx\n", __func__, alloc_size, PAGE_SIZE); - alloc_size = PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)); - io_tlb_orig_addr = memblock_alloc(alloc_size, PAGE_SIZE); - if (!io_tlb_orig_addr) + alloc_size = PAGE_ALIGN(mem->nslabs * sizeof(phys_addr_t)); + mem->orig_addr = memblock_alloc(alloc_size, PAGE_SIZE); + if (!mem->orig_addr) panic("%s: Failed to allocate %zu bytes align=0x%lx\n", __func__, alloc_size, PAGE_SIZE); - alloc_size = PAGE_ALIGN(io_tlb_nslabs * sizeof(size_t)); - io_tlb_alloc_size = memblock_alloc(alloc_size, PAGE_SIZE); - if (!io_tlb_alloc_size) + alloc_size = PAGE_ALIGN(mem->nslabs * sizeof(size_t)); + mem->alloc_size = memblock_alloc(alloc_size, PAGE_SIZE); + if (mem->alloc_size) panic("%s: Failed to allocate %zu bytes align=0x%lx\n", __func__, alloc_size, PAGE_SIZE); - for (i = 0; i < io_tlb_nslabs; i++) { - io_tlb_list[i] = IO_TLB_SEGSIZE - io_tlb_offset(i); - io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; - io_tlb_alloc_size[i] = 0; + for (i = 0; i < mem->nslabs; i++) { + mem->list[i] = IO_TLB_SEGSIZE - io_tlb_offset(i); + mem->orig_addr[i] = INVALID_PHYS_ADDR; + mem->alloc_size[i] = 0; } - io_tlb_index = 0; no_iotlb_memory = false; if (verbose) swiotlb_print_info(); - swiotlb_set_max_segment(io_tlb_nslabs << IO_TLB_SHIFT); + swiotlb_set_max_segment(mem->nslabs << IO_TLB_SHIFT); return 0; } @@ -284,26 +251,27 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) void __init swiotlb_init(int verbose) { + struct io_tlb_mem *mem = &io_tlb_default_mem; size_t default_size = IO_TLB_DEFAULT_SIZE; unsigned char *vstart; unsigned long bytes; - if (!io_tlb_nslabs) { - io_tlb_nslabs = (default_size >> IO_TLB_SHIFT); - io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); + if (!mem->nslabs) { + mem->nslabs = (default_size >> IO_TLB_SHIFT); + mem->nslabs = ALIGN(mem->nslabs, IO_TLB_SEGSIZE); } - bytes = io_tlb_nslabs << IO_TLB_SHIFT; + bytes = mem->nslabs << IO_TLB_SHIFT; /* Get IO TLB memory from the low pages */ vstart = memblock_alloc_low(PAGE_ALIGN(bytes), PAGE_SIZE); - if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose)) + if (vstart && !swiotlb_init_with_tbl(vstart, mem->nslabs, verbose)) return; - if (io_tlb_start) { - memblock_free_early(io_tlb_start, - PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); - io_tlb_start = 0; + if (mem->start) { + memblock_free_early(mem->start, + PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT)); + mem->start = 0; } pr_warn("Cannot allocate buffer"); no_iotlb_memory = true; @@ -317,22 +285,23 @@ swiotlb_init(int verbose) int swiotlb_late_init_with_default_size(size_t default_size) { - unsigned long bytes, req_nslabs = io_tlb_nslabs; + struct io_tlb_mem *mem = &io_tlb_default_mem; + unsigned long bytes, req_nslabs = mem->nslabs; unsigned char *vstart = NULL; unsigned int order; int rc = 0; - if (!io_tlb_nslabs) { - io_tlb_nslabs = (default_size >> IO_TLB_SHIFT); - io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); + if (!mem->nslabs) { + mem->nslabs = (default_size >> IO_TLB_SHIFT); + mem->nslabs = ALIGN(mem->nslabs, IO_TLB_SEGSIZE); } /* * Get IO TLB memory from the low pages */ - order = get_order(io_tlb_nslabs << IO_TLB_SHIFT); - io_tlb_nslabs = SLABS_PER_PAGE << order; - bytes = io_tlb_nslabs << IO_TLB_SHIFT; + order = get_order(mem->nslabs << IO_TLB_SHIFT); + mem->nslabs = SLABS_PER_PAGE << order; + bytes = mem->nslabs << IO_TLB_SHIFT; while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) { vstart = (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, @@ -343,15 +312,15 @@ swiotlb_late_init_with_default_size(size_t default_size) } if (!vstart) { - io_tlb_nslabs = req_nslabs; + mem->nslabs = req_nslabs; return -ENOMEM; } if (order != get_order(bytes)) { pr_warn("only able to allocate %ld MB\n", (PAGE_SIZE << order) >> 20); - io_tlb_nslabs = SLABS_PER_PAGE << order; + mem->nslabs = SLABS_PER_PAGE << order; } - rc = swiotlb_late_init_with_tbl(vstart, io_tlb_nslabs); + rc = swiotlb_late_init_with_tbl(vstart, mem->nslabs); if (rc) free_pages((unsigned long)vstart, order); @@ -360,26 +329,32 @@ swiotlb_late_init_with_default_size(size_t default_size) static void swiotlb_cleanup(void) { - io_tlb_end = 0; - io_tlb_start = 0; - io_tlb_nslabs = 0; + struct io_tlb_mem *mem = &io_tlb_default_mem; + + mem->end = 0; + mem->start = 0; + mem->nslabs = 0; max_segment = 0; } int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) { + struct io_tlb_mem *mem = &io_tlb_default_mem; unsigned long i, bytes; /* protect against double initialization */ - if (WARN_ON_ONCE(io_tlb_start)) + if (WARN_ON_ONCE(mem->start)) return -ENOMEM; bytes = nslabs << IO_TLB_SHIFT; - io_tlb_nslabs = nslabs; - io_tlb_start = virt_to_phys(tlb); - io_tlb_end = io_tlb_start + bytes; + mem->nslabs = nslabs; + mem->start = virt_to_phys(tlb); + mem->end = mem->start + bytes; + mem->index = 0; + mem->late_alloc = 1; + spin_lock_init(&mem->lock); set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT); memset(tlb, 0, bytes); @@ -387,52 +362,45 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) /* * Allocate and initialize the free list array. This array is used * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE - * between io_tlb_start and io_tlb_end. + * between mem->start and mem->end. */ - io_tlb_list = (unsigned int *)__get_free_pages(GFP_KERNEL, - get_order(io_tlb_nslabs * sizeof(int))); - if (!io_tlb_list) + mem->list = (unsigned int *)__get_free_pages(GFP_KERNEL, + get_order(mem->nslabs * sizeof(int))); + if (!mem->list) goto cleanup3; - io_tlb_orig_addr = (phys_addr_t *) + mem->orig_addr = (phys_addr_t *) __get_free_pages(GFP_KERNEL, - get_order(io_tlb_nslabs * + get_order(mem->nslabs * sizeof(phys_addr_t))); - if (!io_tlb_orig_addr) + if (!mem->orig_addr) goto cleanup4; - io_tlb_alloc_size = (size_t *) + mem->alloc_size = (size_t *) __get_free_pages(GFP_KERNEL, - get_order(io_tlb_nslabs * + get_order(mem->nslabs * sizeof(size_t))); - if (!io_tlb_alloc_size) + if (!mem->alloc_size) goto cleanup5; - - for (i = 0; i < io_tlb_nslabs; i++) { - io_tlb_list[i] = IO_TLB_SEGSIZE - io_tlb_offset(i); - io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; - io_tlb_alloc_size[i] = 0; + for (i = 0; i < mem->nslabs; i++) { + mem->list[i] = IO_TLB_SEGSIZE - io_tlb_offset(i); + mem->orig_addr[i] = INVALID_PHYS_ADDR; + mem->alloc_size[i] = 0; } - io_tlb_index = 0; no_iotlb_memory = false; swiotlb_print_info(); - - late_alloc = 1; - - swiotlb_set_max_segment(io_tlb_nslabs << IO_TLB_SHIFT); - + swiotlb_set_max_segment(mem->nslabs << IO_TLB_SHIFT); return 0; cleanup5: - free_pages((unsigned long)io_tlb_orig_addr, get_order(io_tlb_nslabs * - sizeof(phys_addr_t))); - + free_pages((unsigned long)mem->orig_addr, + get_order(mem->nslabs * sizeof(phys_addr_t))); cleanup4: - free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs * - sizeof(int))); - io_tlb_list = NULL; + free_pages((unsigned long)mem->list, + get_order(mem->nslabs * sizeof(int))); + mem->list = NULL; cleanup3: swiotlb_cleanup(); return -ENOMEM; @@ -440,27 +408,29 @@ cleanup3: void __init swiotlb_exit(void) { - if (!io_tlb_orig_addr) + struct io_tlb_mem *mem = &io_tlb_default_mem; + + if (!mem->orig_addr) return; - if (late_alloc) { - free_pages((unsigned long)io_tlb_alloc_size, - get_order(io_tlb_nslabs * sizeof(size_t))); - free_pages((unsigned long)io_tlb_orig_addr, - get_order(io_tlb_nslabs * sizeof(phys_addr_t))); - free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs * - sizeof(int))); - free_pages((unsigned long)phys_to_virt(io_tlb_start), - get_order(io_tlb_nslabs << IO_TLB_SHIFT)); + if (mem->late_alloc) { + free_pages((unsigned long)mem->alloc_size, + get_order(mem->nslabs * sizeof(size_t))); + free_pages((unsigned long)mem->orig_addr, + get_order(mem->nslabs * sizeof(phys_addr_t))); + free_pages((unsigned long)mem->list, + get_order(mem->nslabs * sizeof(int))); + free_pages((unsigned long)phys_to_virt(mem->start), + get_order(mem->nslabs << IO_TLB_SHIFT)); } else { - memblock_free_late(__pa(io_tlb_orig_addr), - PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t))); - memblock_free_late(__pa(io_tlb_alloc_size), - PAGE_ALIGN(io_tlb_nslabs * sizeof(size_t))); - memblock_free_late(__pa(io_tlb_list), - PAGE_ALIGN(io_tlb_nslabs * sizeof(int))); - memblock_free_late(io_tlb_start, - PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + memblock_free_late(__pa(mem->alloc_size), + PAGE_ALIGN(mem->nslabs * sizeof(size_t))); + memblock_free_late(__pa(mem->orig_addr), + PAGE_ALIGN(mem->nslabs * sizeof(phys_addr_t))); + memblock_free_late(__pa(mem->list), + PAGE_ALIGN(mem->nslabs * sizeof(int))); + memblock_free_late(mem->start, + PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT)); } swiotlb_cleanup(); } @@ -471,9 +441,10 @@ void __init swiotlb_exit(void) static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size, enum dma_data_direction dir) { - int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT; - size_t alloc_size = io_tlb_alloc_size[index]; - phys_addr_t orig_addr = io_tlb_orig_addr[index]; + struct io_tlb_mem *mem = &io_tlb_default_mem; + int index = (tlb_addr - mem->start) >> IO_TLB_SHIFT; + phys_addr_t orig_addr = mem->orig_addr[index]; + size_t alloc_size = mem->alloc_size[index]; unsigned long pfn = PFN_DOWN(orig_addr); unsigned char *vaddr = phys_to_virt(tlb_addr); @@ -538,9 +509,9 @@ static inline unsigned long get_max_slots(unsigned long boundary_mask) return nr_slots(boundary_mask + 1); } -static unsigned int wrap_index(unsigned int index) +static unsigned int wrap_index(struct io_tlb_mem *mem, unsigned int index) { - if (index >= io_tlb_nslabs) + if (index >= mem->nslabs) return 0; return index; } @@ -552,9 +523,10 @@ static unsigned int wrap_index(unsigned int index) static int find_slots(struct device *dev, phys_addr_t orig_addr, size_t alloc_size) { + struct io_tlb_mem *mem = &io_tlb_default_mem; unsigned long boundary_mask = dma_get_seg_boundary(dev); dma_addr_t tbl_dma_addr = - phys_to_dma_unencrypted(dev, io_tlb_start) & boundary_mask; + phys_to_dma_unencrypted(dev, mem->start) & boundary_mask; unsigned long max_slots = get_max_slots(boundary_mask); unsigned int iotlb_align_mask = dma_get_min_align_mask(dev) & ~(IO_TLB_SIZE - 1); @@ -573,15 +545,15 @@ static int find_slots(struct device *dev, phys_addr_t orig_addr, if (alloc_size >= PAGE_SIZE) stride = max(stride, stride << (PAGE_SHIFT - IO_TLB_SHIFT)); - spin_lock_irqsave(&io_tlb_lock, flags); - if (unlikely(nslots > io_tlb_nslabs - io_tlb_used)) + spin_lock_irqsave(&mem->lock, flags); + if (unlikely(nslots > mem->nslabs - mem->used)) goto not_found; - index = wrap = wrap_index(ALIGN(io_tlb_index, stride)); + index = wrap = wrap_index(mem, ALIGN(mem->index, stride)); do { if ((slot_addr(tbl_dma_addr, index) & iotlb_align_mask) != (orig_addr & iotlb_align_mask)) { - index = wrap_index(index + 1); + index = wrap_index(mem, index + 1); continue; } @@ -593,34 +565,34 @@ static int find_slots(struct device *dev, phys_addr_t orig_addr, if (!iommu_is_span_boundary(index, nslots, nr_slots(tbl_dma_addr), max_slots)) { - if (io_tlb_list[index] >= nslots) + if (mem->list[index] >= nslots) goto found; } - index = wrap_index(index + stride); + index = wrap_index(mem, index + stride); } while (index != wrap); not_found: - spin_unlock_irqrestore(&io_tlb_lock, flags); + spin_unlock_irqrestore(&mem->lock, flags); return -1; found: for (i = index; i < index + nslots; i++) - io_tlb_list[i] = 0; + mem->list[i] = 0; for (i = index - 1; io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && - io_tlb_list[i]; i--) - io_tlb_list[i] = ++count; + mem->list[i]; i--) + mem->list[i] = ++count; /* * Update the indices to avoid searching in the next round. */ - if (index + nslots < io_tlb_nslabs) - io_tlb_index = index + nslots; + if (index + nslots < mem->nslabs) + mem->index = index + nslots; else - io_tlb_index = 0; - io_tlb_used += nslots; + mem->index = 0; + mem->used += nslots; - spin_unlock_irqrestore(&io_tlb_lock, flags); + spin_unlock_irqrestore(&mem->lock, flags); return index; } @@ -628,6 +600,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, size_t mapping_size, size_t alloc_size, enum dma_data_direction dir, unsigned long attrs) { + struct io_tlb_mem *mem = &io_tlb_default_mem; unsigned int offset = swiotlb_align_offset(dev, orig_addr); unsigned int index, i; phys_addr_t tlb_addr; @@ -649,7 +622,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, if (!(attrs & DMA_ATTR_NO_WARN)) dev_warn_ratelimited(dev, "swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n", - alloc_size, io_tlb_nslabs, io_tlb_used); + alloc_size, mem->nslabs, mem->used); return (phys_addr_t)DMA_MAPPING_ERROR; } @@ -659,10 +632,10 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, * needed. */ for (i = 0; i < nr_slots(alloc_size + offset); i++) { - io_tlb_orig_addr[index + i] = slot_addr(orig_addr, i); - io_tlb_alloc_size[index+i] = alloc_size - (i << IO_TLB_SHIFT); + mem->orig_addr[index + i] = slot_addr(orig_addr, i); + mem->alloc_size[index + i] = alloc_size - (i << IO_TLB_SHIFT); } - tlb_addr = slot_addr(io_tlb_start, index) + offset; + tlb_addr = slot_addr(mem->start, index) + offset; if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_TO_DEVICE); @@ -676,10 +649,11 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, size_t mapping_size, enum dma_data_direction dir, unsigned long attrs) { + struct io_tlb_mem *mem = &io_tlb_default_mem; unsigned long flags; unsigned int offset = swiotlb_align_offset(hwdev, tlb_addr); - int index = (tlb_addr - offset - io_tlb_start) >> IO_TLB_SHIFT; - int nslots = nr_slots(io_tlb_alloc_size[index] + offset); + int index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT; + int nslots = nr_slots(mem->alloc_size[index] + offset); int count, i; /* @@ -695,9 +669,9 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, * While returning the entries to the free list, we merge the entries * with slots below and above the pool being returned. */ - spin_lock_irqsave(&io_tlb_lock, flags); + spin_lock_irqsave(&mem->lock, flags); if (index + nslots < ALIGN(index + 1, IO_TLB_SEGSIZE)) - count = io_tlb_list[index + nslots]; + count = mem->list[index + nslots]; else count = 0; @@ -706,9 +680,9 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, * superceeding slots */ for (i = index + nslots - 1; i >= index; i--) { - io_tlb_list[i] = ++count; - io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; - io_tlb_alloc_size[i] = 0; + mem->list[i] = ++count; + mem->orig_addr[i] = INVALID_PHYS_ADDR; + mem->alloc_size[i] = 0; } /* @@ -716,11 +690,11 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, * available (non zero) */ for (i = index - 1; - io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && io_tlb_list[i]; + io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && mem->list[i]; i--) - io_tlb_list[i] = ++count; - io_tlb_used -= nslots; - spin_unlock_irqrestore(&io_tlb_lock, flags); + mem->list[i] = ++count; + mem->used -= nslots; + spin_unlock_irqrestore(&mem->lock, flags); } void swiotlb_sync_single_for_device(struct device *dev, phys_addr_t tlb_addr, @@ -783,21 +757,21 @@ size_t swiotlb_max_mapping_size(struct device *dev) bool is_swiotlb_active(void) { /* - * When SWIOTLB is initialized, even if io_tlb_start points to physical - * address zero, io_tlb_end surely doesn't. + * When SWIOTLB is initialized, even if mem->start points to physical + * address zero, mem->end surely doesn't. */ - return io_tlb_end != 0; + return io_tlb_default_mem.end != 0; } #ifdef CONFIG_DEBUG_FS static int __init swiotlb_create_debugfs(void) { - struct dentry *root; + struct io_tlb_mem *mem = &io_tlb_default_mem; - root = debugfs_create_dir("swiotlb", NULL); - debugfs_create_ulong("io_tlb_nslabs", 0400, root, &io_tlb_nslabs); - debugfs_create_ulong("io_tlb_used", 0400, root, &io_tlb_used); + mem->debugfs = debugfs_create_dir("swiotlb", NULL); + debugfs_create_ulong("io_tlb_nslabs", 0400, mem->debugfs, &mem->nslabs); + debugfs_create_ulong("io_tlb_used", 0400, mem->debugfs, &mem->used); return 0; } -- cgit v1.2.3-71-gd317 From 2d29960af0bee8cc6731b9bd3964850c9e7a6840 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 18 Mar 2021 17:14:23 +0100 Subject: swiotlb: dynamically allocate io_tlb_default_mem Instead of allocating ->list and ->orig_addr separately just do one dynamic allocation for the actual io_tlb_mem structure. This simplifies a lot of the initialization code, and also allows to just check io_tlb_default_mem to see if swiotlb is in use. Signed-off-by: Christoph Hellwig Signed-off-by: Konrad Rzeszutek Wilk --- drivers/xen/swiotlb-xen.c | 22 ++-- include/linux/swiotlb.h | 18 +-- kernel/dma/swiotlb.c | 306 +++++++++++++++------------------------------- 3 files changed, 117 insertions(+), 229 deletions(-) (limited to 'kernel') diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 5329ad54a5f3..4c89afc0df62 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -158,17 +158,14 @@ static const char *xen_swiotlb_error(enum xen_swiotlb_err err) int __ref xen_swiotlb_init(void) { enum xen_swiotlb_err m_ret = XEN_SWIOTLB_UNKNOWN; - unsigned long nslabs, bytes, order; - unsigned int repeat = 3; + unsigned long bytes = swiotlb_size_or_default(); + unsigned long nslabs = bytes >> IO_TLB_SHIFT; + unsigned int order, repeat = 3; int rc = -ENOMEM; char *start; - nslabs = swiotlb_nr_tbl(); - if (!nslabs) - nslabs = DEFAULT_NSLABS; retry: m_ret = XEN_SWIOTLB_ENOMEM; - bytes = nslabs << IO_TLB_SHIFT; order = get_order(bytes); /* @@ -221,19 +218,16 @@ error: #ifdef CONFIG_X86 void __init xen_swiotlb_init_early(void) { - unsigned long nslabs, bytes; + unsigned long bytes = swiotlb_size_or_default(); + unsigned long nslabs = bytes >> IO_TLB_SHIFT; unsigned int repeat = 3; char *start; int rc; - nslabs = swiotlb_nr_tbl(); - if (!nslabs) - nslabs = DEFAULT_NSLABS; retry: /* * Get IO TLB memory from any location. */ - bytes = nslabs << IO_TLB_SHIFT; start = memblock_alloc(PAGE_ALIGN(bytes), PAGE_SIZE); if (!start) panic("%s: Failed to allocate %lu bytes align=0x%lx\n", @@ -248,8 +242,8 @@ retry: if (repeat--) { /* Min is 2MB */ nslabs = max(1024UL, (nslabs >> 1)); - pr_info("Lowering to %luMB\n", - (nslabs << IO_TLB_SHIFT) >> 20); + bytes = nslabs << IO_TLB_SHIFT; + pr_info("Lowering to %luMB\n", bytes >> 20); goto retry; } panic("%s (rc:%d)", xen_swiotlb_error(XEN_SWIOTLB_EFIXUP), rc); @@ -548,7 +542,7 @@ xen_swiotlb_sync_sg_for_device(struct device *dev, struct scatterlist *sgl, static int xen_swiotlb_dma_supported(struct device *hwdev, u64 mask) { - return xen_phys_to_dma(hwdev, io_tlb_default_mem.end - 1) <= mask; + return xen_phys_to_dma(hwdev, io_tlb_default_mem->end - 1) <= mask; } const struct dma_map_ops xen_swiotlb_dma_ops = { diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 5ec5378b17c3..63f7a63f61d0 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -90,28 +90,30 @@ struct io_tlb_mem { phys_addr_t end; unsigned long nslabs; unsigned long used; - unsigned int *list; unsigned int index; - phys_addr_t *orig_addr; - size_t *alloc_size; spinlock_t lock; struct dentry *debugfs; bool late_alloc; + struct io_tlb_slot { + phys_addr_t orig_addr; + size_t alloc_size; + unsigned int list; + } slots[]; }; -extern struct io_tlb_mem io_tlb_default_mem; +extern struct io_tlb_mem *io_tlb_default_mem; static inline bool is_swiotlb_buffer(phys_addr_t paddr) { - struct io_tlb_mem *mem = &io_tlb_default_mem; + struct io_tlb_mem *mem = io_tlb_default_mem; - return paddr >= mem->start && paddr < mem->end; + return mem && paddr >= mem->start && paddr < mem->end; } void __init swiotlb_exit(void); unsigned int swiotlb_max_segment(void); size_t swiotlb_max_mapping_size(struct device *dev); bool is_swiotlb_active(void); -void __init swiotlb_adjust_size(unsigned long new_size); +void __init swiotlb_adjust_size(unsigned long size); #else #define swiotlb_force SWIOTLB_NO_FORCE static inline bool is_swiotlb_buffer(phys_addr_t paddr) @@ -135,7 +137,7 @@ static inline bool is_swiotlb_active(void) return false; } -static inline void swiotlb_adjust_size(unsigned long new_size) +static inline void swiotlb_adjust_size(unsigned long size) { } #endif /* CONFIG_SWIOTLB */ diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index d9c097f0f78c..13de669a9b46 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -63,7 +63,7 @@ enum swiotlb_force swiotlb_force; -struct io_tlb_mem io_tlb_default_mem; +struct io_tlb_mem *io_tlb_default_mem; /* * Max segment that we can provide which (if pages are contingous) will @@ -71,15 +71,15 @@ struct io_tlb_mem io_tlb_default_mem; */ static unsigned int max_segment; +static unsigned long default_nslabs = IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT; + static int __init setup_io_tlb_npages(char *str) { - struct io_tlb_mem *mem = &io_tlb_default_mem; - if (isdigit(*str)) { - mem->nslabs = simple_strtoul(str, &str, 0); /* avoid tail segment of size < IO_TLB_SEGSIZE */ - mem->nslabs = ALIGN(mem->nslabs, IO_TLB_SEGSIZE); + default_nslabs = + ALIGN(simple_strtoul(str, &str, 0), IO_TLB_SEGSIZE); } if (*str == ',') ++str; @@ -87,24 +87,22 @@ setup_io_tlb_npages(char *str) swiotlb_force = SWIOTLB_FORCE; } else if (!strcmp(str, "noforce")) { swiotlb_force = SWIOTLB_NO_FORCE; - mem->nslabs = 1; + default_nslabs = 1; } return 0; } early_param("swiotlb", setup_io_tlb_npages); -static bool no_iotlb_memory; - unsigned long swiotlb_nr_tbl(void) { - return unlikely(no_iotlb_memory) ? 0 : io_tlb_default_mem.nslabs; + return io_tlb_default_mem ? io_tlb_default_mem->nslabs : 0; } EXPORT_SYMBOL_GPL(swiotlb_nr_tbl); unsigned int swiotlb_max_segment(void) { - return unlikely(no_iotlb_memory) ? 0 : max_segment; + return io_tlb_default_mem ? max_segment : 0; } EXPORT_SYMBOL_GPL(swiotlb_max_segment); @@ -118,44 +116,32 @@ void swiotlb_set_max_segment(unsigned int val) unsigned long swiotlb_size_or_default(void) { - unsigned long size; - - size = io_tlb_default_mem.nslabs << IO_TLB_SHIFT; - - return size ? size : (IO_TLB_DEFAULT_SIZE); + return default_nslabs << IO_TLB_SHIFT; } -void __init swiotlb_adjust_size(unsigned long new_size) +void __init swiotlb_adjust_size(unsigned long size) { - struct io_tlb_mem *mem = &io_tlb_default_mem; - unsigned long size; - /* * If swiotlb parameter has not been specified, give a chance to * architectures such as those supporting memory encryption to * adjust/expand SWIOTLB size for their use. */ - if (!mem->nslabs) { - size = ALIGN(new_size, IO_TLB_SIZE); - mem->nslabs = size >> IO_TLB_SHIFT; - mem->nslabs = ALIGN(mem->nslabs, IO_TLB_SEGSIZE); - - pr_info("SWIOTLB bounce buffer size adjusted to %luMB", size >> 20); - } + size = ALIGN(size, IO_TLB_SIZE); + default_nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE); + pr_info("SWIOTLB bounce buffer size adjusted to %luMB", size >> 20); } void swiotlb_print_info(void) { - struct io_tlb_mem *mem = &io_tlb_default_mem; - unsigned long bytes = mem->nslabs << IO_TLB_SHIFT; + struct io_tlb_mem *mem = io_tlb_default_mem; - if (no_iotlb_memory) { + if (!mem) { pr_warn("No low mem\n"); return; } pr_info("mapped [mem %pa-%pa] (%luMB)\n", &mem->start, &mem->end, - bytes >> 20); + (mem->nslabs << IO_TLB_SHIFT) >> 20); } static inline unsigned long io_tlb_offset(unsigned long val) @@ -176,13 +162,12 @@ static inline unsigned long nr_slots(u64 val) */ void __init swiotlb_update_mem_attributes(void) { - struct io_tlb_mem *mem = &io_tlb_default_mem; + struct io_tlb_mem *mem = io_tlb_default_mem; void *vaddr; unsigned long bytes; - if (no_iotlb_memory || mem->late_alloc) + if (!mem || mem->late_alloc) return; - vaddr = phys_to_virt(mem->start); bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT); set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT); @@ -191,55 +176,33 @@ void __init swiotlb_update_mem_attributes(void) int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) { - struct io_tlb_mem *mem = &io_tlb_default_mem; - unsigned long i, bytes; + unsigned long bytes = nslabs << IO_TLB_SHIFT, i; + struct io_tlb_mem *mem; size_t alloc_size; /* protect against double initialization */ - if (WARN_ON_ONCE(mem->start)) + if (WARN_ON_ONCE(io_tlb_default_mem)) return -ENOMEM; - bytes = nslabs << IO_TLB_SHIFT; - + alloc_size = PAGE_ALIGN(struct_size(mem, slots, nslabs)); + mem = memblock_alloc(alloc_size, PAGE_SIZE); + if (!mem) + panic("%s: Failed to allocate %zu bytes align=0x%lx\n", + __func__, alloc_size, PAGE_SIZE); mem->nslabs = nslabs; mem->start = __pa(tlb); mem->end = mem->start + bytes; mem->index = 0; spin_lock_init(&mem->lock); - - /* - * Allocate and initialize the free list array. This array is used - * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE - * between mem->start and mem->end. - */ - alloc_size = PAGE_ALIGN(mem->nslabs * sizeof(int)); - mem->list = memblock_alloc(alloc_size, PAGE_SIZE); - if (!mem->list) - panic("%s: Failed to allocate %zu bytes align=0x%lx\n", - __func__, alloc_size, PAGE_SIZE); - - alloc_size = PAGE_ALIGN(mem->nslabs * sizeof(phys_addr_t)); - mem->orig_addr = memblock_alloc(alloc_size, PAGE_SIZE); - if (!mem->orig_addr) - panic("%s: Failed to allocate %zu bytes align=0x%lx\n", - __func__, alloc_size, PAGE_SIZE); - - alloc_size = PAGE_ALIGN(mem->nslabs * sizeof(size_t)); - mem->alloc_size = memblock_alloc(alloc_size, PAGE_SIZE); - if (mem->alloc_size) - panic("%s: Failed to allocate %zu bytes align=0x%lx\n", - __func__, alloc_size, PAGE_SIZE); - for (i = 0; i < mem->nslabs; i++) { - mem->list[i] = IO_TLB_SEGSIZE - io_tlb_offset(i); - mem->orig_addr[i] = INVALID_PHYS_ADDR; - mem->alloc_size[i] = 0; + mem->slots[i].list = IO_TLB_SEGSIZE - io_tlb_offset(i); + mem->slots[i].orig_addr = INVALID_PHYS_ADDR; + mem->slots[i].alloc_size = 0; } - no_iotlb_memory = false; + io_tlb_default_mem = mem; if (verbose) swiotlb_print_info(); - swiotlb_set_max_segment(mem->nslabs << IO_TLB_SHIFT); return 0; } @@ -251,30 +214,21 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) void __init swiotlb_init(int verbose) { - struct io_tlb_mem *mem = &io_tlb_default_mem; - size_t default_size = IO_TLB_DEFAULT_SIZE; - unsigned char *vstart; - unsigned long bytes; - - if (!mem->nslabs) { - mem->nslabs = (default_size >> IO_TLB_SHIFT); - mem->nslabs = ALIGN(mem->nslabs, IO_TLB_SEGSIZE); - } - - bytes = mem->nslabs << IO_TLB_SHIFT; + size_t bytes = PAGE_ALIGN(default_nslabs << IO_TLB_SHIFT); + void *tlb; /* Get IO TLB memory from the low pages */ - vstart = memblock_alloc_low(PAGE_ALIGN(bytes), PAGE_SIZE); - if (vstart && !swiotlb_init_with_tbl(vstart, mem->nslabs, verbose)) - return; - - if (mem->start) { - memblock_free_early(mem->start, - PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT)); - mem->start = 0; - } + tlb = memblock_alloc_low(bytes, PAGE_SIZE); + if (!tlb) + goto fail; + if (swiotlb_init_with_tbl(tlb, default_nslabs, verbose)) + goto fail_free_mem; + return; + +fail_free_mem: + memblock_free_early(__pa(tlb), bytes); +fail: pr_warn("Cannot allocate buffer"); - no_iotlb_memory = true; } /* @@ -285,23 +239,19 @@ swiotlb_init(int verbose) int swiotlb_late_init_with_default_size(size_t default_size) { - struct io_tlb_mem *mem = &io_tlb_default_mem; - unsigned long bytes, req_nslabs = mem->nslabs; + unsigned long nslabs = + ALIGN(default_size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE); + unsigned long bytes; unsigned char *vstart = NULL; unsigned int order; int rc = 0; - if (!mem->nslabs) { - mem->nslabs = (default_size >> IO_TLB_SHIFT); - mem->nslabs = ALIGN(mem->nslabs, IO_TLB_SEGSIZE); - } - /* * Get IO TLB memory from the low pages */ - order = get_order(mem->nslabs << IO_TLB_SHIFT); - mem->nslabs = SLABS_PER_PAGE << order; - bytes = mem->nslabs << IO_TLB_SHIFT; + order = get_order(nslabs << IO_TLB_SHIFT); + nslabs = SLABS_PER_PAGE << order; + bytes = nslabs << IO_TLB_SHIFT; while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) { vstart = (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, @@ -311,43 +261,35 @@ swiotlb_late_init_with_default_size(size_t default_size) order--; } - if (!vstart) { - mem->nslabs = req_nslabs; + if (!vstart) return -ENOMEM; - } + if (order != get_order(bytes)) { pr_warn("only able to allocate %ld MB\n", (PAGE_SIZE << order) >> 20); - mem->nslabs = SLABS_PER_PAGE << order; + nslabs = SLABS_PER_PAGE << order; } - rc = swiotlb_late_init_with_tbl(vstart, mem->nslabs); + rc = swiotlb_late_init_with_tbl(vstart, nslabs); if (rc) free_pages((unsigned long)vstart, order); return rc; } -static void swiotlb_cleanup(void) -{ - struct io_tlb_mem *mem = &io_tlb_default_mem; - - mem->end = 0; - mem->start = 0; - mem->nslabs = 0; - max_segment = 0; -} - int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) { - struct io_tlb_mem *mem = &io_tlb_default_mem; - unsigned long i, bytes; + unsigned long bytes = nslabs << IO_TLB_SHIFT, i; + struct io_tlb_mem *mem; /* protect against double initialization */ - if (WARN_ON_ONCE(mem->start)) + if (WARN_ON_ONCE(io_tlb_default_mem)) return -ENOMEM; - bytes = nslabs << IO_TLB_SHIFT; + mem = (void *)__get_free_pages(GFP_KERNEL, + get_order(struct_size(mem, slots, nslabs))); + if (!mem) + return -ENOMEM; mem->nslabs = nslabs; mem->start = virt_to_phys(tlb); @@ -355,84 +297,35 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) mem->index = 0; mem->late_alloc = 1; spin_lock_init(&mem->lock); + for (i = 0; i < mem->nslabs; i++) { + mem->slots[i].list = IO_TLB_SEGSIZE - io_tlb_offset(i); + mem->slots[i].orig_addr = INVALID_PHYS_ADDR; + mem->slots[i].alloc_size = 0; + } set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT); memset(tlb, 0, bytes); - /* - * Allocate and initialize the free list array. This array is used - * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE - * between mem->start and mem->end. - */ - mem->list = (unsigned int *)__get_free_pages(GFP_KERNEL, - get_order(mem->nslabs * sizeof(int))); - if (!mem->list) - goto cleanup3; - - mem->orig_addr = (phys_addr_t *) - __get_free_pages(GFP_KERNEL, - get_order(mem->nslabs * - sizeof(phys_addr_t))); - if (!mem->orig_addr) - goto cleanup4; - - mem->alloc_size = (size_t *) - __get_free_pages(GFP_KERNEL, - get_order(mem->nslabs * - sizeof(size_t))); - if (!mem->alloc_size) - goto cleanup5; - - for (i = 0; i < mem->nslabs; i++) { - mem->list[i] = IO_TLB_SEGSIZE - io_tlb_offset(i); - mem->orig_addr[i] = INVALID_PHYS_ADDR; - mem->alloc_size[i] = 0; - } - no_iotlb_memory = false; - + io_tlb_default_mem = mem; swiotlb_print_info(); swiotlb_set_max_segment(mem->nslabs << IO_TLB_SHIFT); return 0; - -cleanup5: - free_pages((unsigned long)mem->orig_addr, - get_order(mem->nslabs * sizeof(phys_addr_t))); -cleanup4: - free_pages((unsigned long)mem->list, - get_order(mem->nslabs * sizeof(int))); - mem->list = NULL; -cleanup3: - swiotlb_cleanup(); - return -ENOMEM; } void __init swiotlb_exit(void) { - struct io_tlb_mem *mem = &io_tlb_default_mem; + struct io_tlb_mem *mem = io_tlb_default_mem; + size_t size; - if (!mem->orig_addr) + if (!mem) return; - if (mem->late_alloc) { - free_pages((unsigned long)mem->alloc_size, - get_order(mem->nslabs * sizeof(size_t))); - free_pages((unsigned long)mem->orig_addr, - get_order(mem->nslabs * sizeof(phys_addr_t))); - free_pages((unsigned long)mem->list, - get_order(mem->nslabs * sizeof(int))); - free_pages((unsigned long)phys_to_virt(mem->start), - get_order(mem->nslabs << IO_TLB_SHIFT)); - } else { - memblock_free_late(__pa(mem->alloc_size), - PAGE_ALIGN(mem->nslabs * sizeof(size_t))); - memblock_free_late(__pa(mem->orig_addr), - PAGE_ALIGN(mem->nslabs * sizeof(phys_addr_t))); - memblock_free_late(__pa(mem->list), - PAGE_ALIGN(mem->nslabs * sizeof(int))); - memblock_free_late(mem->start, - PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT)); - } - swiotlb_cleanup(); + size = struct_size(mem, slots, mem->nslabs); + if (mem->late_alloc) + free_pages((unsigned long)mem, get_order(size)); + else + memblock_free_late(__pa(mem), PAGE_ALIGN(size)); + io_tlb_default_mem = NULL; } /* @@ -441,10 +334,10 @@ void __init swiotlb_exit(void) static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size, enum dma_data_direction dir) { - struct io_tlb_mem *mem = &io_tlb_default_mem; + struct io_tlb_mem *mem = io_tlb_default_mem; int index = (tlb_addr - mem->start) >> IO_TLB_SHIFT; - phys_addr_t orig_addr = mem->orig_addr[index]; - size_t alloc_size = mem->alloc_size[index]; + phys_addr_t orig_addr = mem->slots[index].orig_addr; + size_t alloc_size = mem->slots[index].alloc_size; unsigned long pfn = PFN_DOWN(orig_addr); unsigned char *vaddr = phys_to_virt(tlb_addr); @@ -523,7 +416,7 @@ static unsigned int wrap_index(struct io_tlb_mem *mem, unsigned int index) static int find_slots(struct device *dev, phys_addr_t orig_addr, size_t alloc_size) { - struct io_tlb_mem *mem = &io_tlb_default_mem; + struct io_tlb_mem *mem = io_tlb_default_mem; unsigned long boundary_mask = dma_get_seg_boundary(dev); dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(dev, mem->start) & boundary_mask; @@ -565,7 +458,7 @@ static int find_slots(struct device *dev, phys_addr_t orig_addr, if (!iommu_is_span_boundary(index, nslots, nr_slots(tbl_dma_addr), max_slots)) { - if (mem->list[index] >= nslots) + if (mem->slots[index].list >= nslots) goto found; } index = wrap_index(mem, index + stride); @@ -577,11 +470,11 @@ not_found: found: for (i = index; i < index + nslots; i++) - mem->list[i] = 0; + mem->slots[i].list = 0; for (i = index - 1; io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && - mem->list[i]; i--) - mem->list[i] = ++count; + mem->slots[i].list; i--) + mem->slots[i].list = ++count; /* * Update the indices to avoid searching in the next round. @@ -600,12 +493,12 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, size_t mapping_size, size_t alloc_size, enum dma_data_direction dir, unsigned long attrs) { - struct io_tlb_mem *mem = &io_tlb_default_mem; + struct io_tlb_mem *mem = io_tlb_default_mem; unsigned int offset = swiotlb_align_offset(dev, orig_addr); unsigned int index, i; phys_addr_t tlb_addr; - if (no_iotlb_memory) + if (!mem) panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer"); if (mem_encrypt_active()) @@ -632,8 +525,9 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, * needed. */ for (i = 0; i < nr_slots(alloc_size + offset); i++) { - mem->orig_addr[index + i] = slot_addr(orig_addr, i); - mem->alloc_size[index + i] = alloc_size - (i << IO_TLB_SHIFT); + mem->slots[index + i].orig_addr = slot_addr(orig_addr, i); + mem->slots[index + i].alloc_size = + alloc_size - (i << IO_TLB_SHIFT); } tlb_addr = slot_addr(mem->start, index) + offset; if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && @@ -649,11 +543,11 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, size_t mapping_size, enum dma_data_direction dir, unsigned long attrs) { - struct io_tlb_mem *mem = &io_tlb_default_mem; + struct io_tlb_mem *mem = io_tlb_default_mem; unsigned long flags; unsigned int offset = swiotlb_align_offset(hwdev, tlb_addr); int index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT; - int nslots = nr_slots(mem->alloc_size[index] + offset); + int nslots = nr_slots(mem->slots[index].alloc_size + offset); int count, i; /* @@ -671,7 +565,7 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, */ spin_lock_irqsave(&mem->lock, flags); if (index + nslots < ALIGN(index + 1, IO_TLB_SEGSIZE)) - count = mem->list[index + nslots]; + count = mem->slots[index + nslots].list; else count = 0; @@ -680,9 +574,9 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, * superceeding slots */ for (i = index + nslots - 1; i >= index; i--) { - mem->list[i] = ++count; - mem->orig_addr[i] = INVALID_PHYS_ADDR; - mem->alloc_size[i] = 0; + mem->slots[i].list = ++count; + mem->slots[i].orig_addr = INVALID_PHYS_ADDR; + mem->slots[i].alloc_size = 0; } /* @@ -690,9 +584,9 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, * available (non zero) */ for (i = index - 1; - io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && mem->list[i]; + io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && mem->slots[i].list; i--) - mem->list[i] = ++count; + mem->slots[i].list = ++count; mem->used -= nslots; spin_unlock_irqrestore(&mem->lock, flags); } @@ -756,19 +650,17 @@ size_t swiotlb_max_mapping_size(struct device *dev) bool is_swiotlb_active(void) { - /* - * When SWIOTLB is initialized, even if mem->start points to physical - * address zero, mem->end surely doesn't. - */ - return io_tlb_default_mem.end != 0; + return io_tlb_default_mem != NULL; } #ifdef CONFIG_DEBUG_FS static int __init swiotlb_create_debugfs(void) { - struct io_tlb_mem *mem = &io_tlb_default_mem; + struct io_tlb_mem *mem = io_tlb_default_mem; + if (!mem) + return 0; mem->debugfs = debugfs_create_dir("swiotlb", NULL); debugfs_create_ulong("io_tlb_nslabs", 0400, mem->debugfs, &mem->nslabs); debugfs_create_ulong("io_tlb_used", 0400, mem->debugfs, &mem->used); -- cgit v1.2.3-71-gd317 From 2cbc2776efe4faed0e17c48ae076aa03a0fcc61f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 18 Mar 2021 17:14:24 +0100 Subject: swiotlb: remove swiotlb_nr_tbl All callers just use it to check if swiotlb is active at all, for which they can just use is_swiotlb_active. In the longer run drivers need to stop using is_swiotlb_active as well, but let's do the simple step first. Signed-off-by: Christoph Hellwig Signed-off-by: Konrad Rzeszutek Wilk --- drivers/gpu/drm/i915/gem/i915_gem_internal.c | 2 +- drivers/gpu/drm/nouveau/nouveau_ttm.c | 2 +- drivers/pci/xen-pcifront.c | 2 +- include/linux/swiotlb.h | 1 - kernel/dma/swiotlb.c | 7 +------ 5 files changed, 4 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c index ad22f42541bd..a9d65fc8aa0e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c @@ -42,7 +42,7 @@ static int i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj) max_order = MAX_ORDER; #ifdef CONFIG_SWIOTLB - if (swiotlb_nr_tbl()) { + if (is_swiotlb_active()) { unsigned int max_segment; max_segment = swiotlb_max_segment(); diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c index a37bc3d7b38b..9662522aa066 100644 --- a/drivers/gpu/drm/nouveau/nouveau_ttm.c +++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c @@ -321,7 +321,7 @@ nouveau_ttm_init(struct nouveau_drm *drm) } #if IS_ENABLED(CONFIG_SWIOTLB) && IS_ENABLED(CONFIG_X86) - need_swiotlb = !!swiotlb_nr_tbl(); + need_swiotlb = is_swiotlb_active(); #endif ret = ttm_bo_device_init(&drm->ttm.bdev, &nouveau_bo_driver, diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index 2d7502648219..b7a8f3a1921f 100644 --- a/drivers/pci/xen-pcifront.c +++ b/drivers/pci/xen-pcifront.c @@ -693,7 +693,7 @@ static int pcifront_connect_and_init_dma(struct pcifront_device *pdev) spin_unlock(&pcifront_dev_lock); - if (!err && !swiotlb_nr_tbl()) { + if (!err && !is_swiotlb_active()) { err = pci_xen_swiotlb_init_late(); if (err) dev_err(&pdev->xdev->dev, "Could not setup SWIOTLB!\n"); diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 63f7a63f61d0..216854a5e513 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -37,7 +37,6 @@ enum swiotlb_force { extern void swiotlb_init(int verbose); int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose); -extern unsigned long swiotlb_nr_tbl(void); unsigned long swiotlb_size_or_default(void); extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); extern int swiotlb_late_init_with_default_size(size_t default_size); diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 13de669a9b46..539c76beb52e 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -94,12 +94,6 @@ setup_io_tlb_npages(char *str) } early_param("swiotlb", setup_io_tlb_npages); -unsigned long swiotlb_nr_tbl(void) -{ - return io_tlb_default_mem ? io_tlb_default_mem->nslabs : 0; -} -EXPORT_SYMBOL_GPL(swiotlb_nr_tbl); - unsigned int swiotlb_max_segment(void) { return io_tlb_default_mem ? max_segment : 0; @@ -652,6 +646,7 @@ bool is_swiotlb_active(void) { return io_tlb_default_mem != NULL; } +EXPORT_SYMBOL_GPL(is_swiotlb_active); #ifdef CONFIG_DEBUG_FS -- cgit v1.2.3-71-gd317 From f2cc020d7876de7583feb52ec939a32419cf9468 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 23 Mar 2021 18:49:35 +0100 Subject: tracing: Fix various typos in comments Fix ~59 single-word typos in the tracing code comments, and fix the grammar in a handful of places. Link: https://lore.kernel.org/r/20210322224546.GA1981273@gmail.com Link: https://lkml.kernel.org/r/20210323174935.GA4176821@gmail.com Reviewed-by: Randy Dunlap Signed-off-by: Ingo Molnar Signed-off-by: Steven Rostedt (VMware) --- arch/microblaze/include/asm/ftrace.h | 2 +- arch/nds32/kernel/ftrace.c | 2 +- arch/powerpc/include/asm/ftrace.h | 4 ++-- arch/sh/kernel/ftrace.c | 2 +- arch/sparc/include/asm/ftrace.h | 2 +- fs/tracefs/inode.c | 2 +- include/linux/ftrace.h | 4 ++-- include/linux/trace_events.h | 2 +- include/linux/tracepoint.h | 2 +- include/trace/events/io_uring.h | 2 +- include/trace/events/rcu.h | 2 +- include/trace/events/sched.h | 2 +- include/trace/events/timer.h | 2 +- kernel/trace/bpf_trace.c | 5 +++-- kernel/trace/fgraph.c | 4 ++-- kernel/trace/ftrace.c | 8 ++++---- kernel/trace/ring_buffer.c | 2 +- kernel/trace/synth_event_gen_test.c | 2 +- kernel/trace/trace.c | 18 +++++++++--------- kernel/trace/trace.h | 4 ++-- kernel/trace/trace_event_perf.c | 2 +- kernel/trace/trace_events.c | 4 ++-- kernel/trace/trace_events_filter.c | 4 ++-- kernel/trace/trace_events_synth.c | 2 +- kernel/trace/trace_functions_graph.c | 2 +- kernel/trace/trace_hwlat.c | 4 ++-- kernel/trace/trace_kprobe.c | 2 +- kernel/trace/trace_probe.c | 6 +++--- kernel/trace/trace_probe.h | 2 +- kernel/trace/trace_probe_tmpl.h | 2 +- kernel/trace/trace_selftest.c | 4 ++-- kernel/trace/trace_seq.c | 12 ++++++------ 32 files changed, 60 insertions(+), 59 deletions(-) (limited to 'kernel') diff --git a/arch/microblaze/include/asm/ftrace.h b/arch/microblaze/include/asm/ftrace.h index 5db7f4489f05..6a92bed37794 100644 --- a/arch/microblaze/include/asm/ftrace.h +++ b/arch/microblaze/include/asm/ftrace.h @@ -13,7 +13,7 @@ extern void ftrace_call_graph(void); #endif #ifdef CONFIG_DYNAMIC_FTRACE -/* reloction of mcount call site is the same as the address */ +/* relocation of mcount call site is the same as the address */ static inline unsigned long ftrace_call_adjust(unsigned long addr) { return addr; diff --git a/arch/nds32/kernel/ftrace.c b/arch/nds32/kernel/ftrace.c index 414f8a780cc3..0e23e3a8df6b 100644 --- a/arch/nds32/kernel/ftrace.c +++ b/arch/nds32/kernel/ftrace.c @@ -236,7 +236,7 @@ void __naked return_to_handler(void) "bal ftrace_return_to_handler\n\t" "move $lp, $r0 \n\t" - /* restore state nedded by the ABI */ + /* restore state needed by the ABI */ "lmw.bim $r0,[$sp],$r1,#0x0 \n\t"); } diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h index bc76970b6ee5..debe8c4f7062 100644 --- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -12,7 +12,7 @@ #ifdef __ASSEMBLY__ -/* Based off of objdump optput from glibc */ +/* Based off of objdump output from glibc */ #define MCOUNT_SAVE_FRAME \ stwu r1,-48(r1); \ @@ -52,7 +52,7 @@ extern void _mcount(void); static inline unsigned long ftrace_call_adjust(unsigned long addr) { - /* reloction of mcount call site is the same as the address */ + /* relocation of mcount call site is the same as the address */ return addr; } diff --git a/arch/sh/kernel/ftrace.c b/arch/sh/kernel/ftrace.c index 0646c5961846..295c43315bbe 100644 --- a/arch/sh/kernel/ftrace.c +++ b/arch/sh/kernel/ftrace.c @@ -67,7 +67,7 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) * Modifying code must take extra care. On an SMP machine, if * the code being modified is also being executed on another CPU * that CPU will have undefined results and possibly take a GPF. - * We use kstop_machine to stop other CPUS from exectuing code. + * We use kstop_machine to stop other CPUS from executing code. * But this does not stop NMIs from happening. We still need * to protect against that. We separate out the modification of * the code to take care of this. diff --git a/arch/sparc/include/asm/ftrace.h b/arch/sparc/include/asm/ftrace.h index d3aa1a524431..e284394cb3aa 100644 --- a/arch/sparc/include/asm/ftrace.h +++ b/arch/sparc/include/asm/ftrace.h @@ -17,7 +17,7 @@ void _mcount(void); #endif #ifdef CONFIG_DYNAMIC_FTRACE -/* reloction of mcount call site is the same as the address */ +/* relocation of mcount call site is the same as the address */ static inline unsigned long ftrace_call_adjust(unsigned long addr) { return addr; diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 4b83cbded559..1261e8b41edb 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -477,7 +477,7 @@ struct dentry *tracefs_create_dir(const char *name, struct dentry *parent) * * The instances directory is special as it allows for mkdir and rmdir to * to be done by userspace. When a mkdir or rmdir is performed, the inode - * locks are released and the methhods passed in (@mkdir and @rmdir) are + * locks are released and the methods passed in (@mkdir and @rmdir) are * called without locks and with the name of the directory being created * within the instances directory. * diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 86e5028bfa20..a69f363b61bf 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -33,7 +33,7 @@ /* * If the arch's mcount caller does not support all of ftrace's * features, then it must call an indirect function that - * does. Or at least does enough to prevent any unwelcomed side effects. + * does. Or at least does enough to prevent any unwelcome side effects. */ #if !ARCH_SUPPORTS_FTRACE_OPS # define FTRACE_FORCE_LIST_FUNC 1 @@ -389,7 +389,7 @@ DECLARE_PER_CPU(int, disable_stack_tracer); */ static inline void stack_tracer_disable(void) { - /* Preemption or interupts must be disabled */ + /* Preemption or interrupts must be disabled */ if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) WARN_ON_ONCE(!preempt_count() || !irqs_disabled()); this_cpu_inc(disable_stack_tracer); diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 8cba64ce23a4..36e27c1f42e0 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -206,7 +206,7 @@ static inline unsigned int tracing_gen_ctx_dec(void) trace_ctx = tracing_gen_ctx(); /* - * Subtract one from the preeption counter if preemption is enabled, + * Subtract one from the preemption counter if preemption is enabled, * see trace_event_buffer_reserve()for details. */ if (IS_ENABLED(CONFIG_PREEMPTION)) diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 9cfb099da58f..13f65420f188 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -465,7 +465,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * * * * The declared 'local variable' is called '__entry' * * - * * __field(pid_t, prev_prid) is equivalent to a standard declariton: + * * __field(pid_t, prev_prid) is equivalent to a standard declaration: * * * * pid_t prev_pid; * * diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 9f0d3b7d56b0..ba78a5602cd1 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -49,7 +49,7 @@ TRACE_EVENT(io_uring_create, ); /** - * io_uring_register - called after a buffer/file/eventfd was succesfully + * io_uring_register - called after a buffer/file/eventfd was successfully * registered for a ring * * @ctx: pointer to a ring context structure diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 5fc29400e1a2..97177c10bf64 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -48,7 +48,7 @@ TRACE_EVENT(rcu_utilization, * RCU flavor, the grace-period number, and a string identifying the * grace-period-related event as follows: * - * "AccReadyCB": CPU acclerates new callbacks to RCU_NEXT_READY_TAIL. + * "AccReadyCB": CPU accelerates new callbacks to RCU_NEXT_READY_TAIL. * "AccWaitCB": CPU accelerates new callbacks to RCU_WAIT_TAIL. * "newreq": Request a new grace period. * "start": Start a grace period. diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index cbe3e152d24c..1eca2305ca42 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -174,7 +174,7 @@ DEFINE_EVENT(sched_wakeup_template, sched_waking, TP_ARGS(p)); /* - * Tracepoint called when the task is actually woken; p->state == TASK_RUNNNG. + * Tracepoint called when the task is actually woken; p->state == TASK_RUNNING. * It is not always called from the waking context. */ DEFINE_EVENT(sched_wakeup_template, sched_wakeup, diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 19abb6c3eb73..6ad031c71be7 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -119,7 +119,7 @@ TRACE_EVENT(timer_expire_entry, * When used in combination with the timer_expire_entry tracepoint we can * determine the runtime of the timer callback function. * - * NOTE: Do NOT derefernce timer in TP_fast_assign. The pointer might + * NOTE: Do NOT dereference timer in TP_fast_assign. The pointer might * be invalid. We solely track the pointer. */ DEFINE_EVENT(timer_class, timer_expire_exit, diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index b0c45d923f0f..49f7ddb36149 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -658,7 +658,7 @@ BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size, /* fmt[i] != 0 && fmt[last] == 0, so we can access fmt[i + 1] */ i++; - /* skip optional "[0 +-][num]" width formating field */ + /* skip optional "[0 +-][num]" width formatting field */ while (fmt[i] == '0' || fmt[i] == '+' || fmt[i] == '-' || fmt[i] == ' ') i++; @@ -748,7 +748,8 @@ BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size, fmt_cnt++; } - /* Maximumly we can have MAX_SEQ_PRINTF_VARARGS parameter, just give + /* + * The maximum we can have is MAX_SEQ_PRINTF_VARARGS parameters, so just give * all of them to seq_printf(). */ seq_printf(m, fmt, params[0], params[1], params[2], params[3], diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 29a6ebeebc9e..b8a0d1d564fb 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -42,7 +42,7 @@ bool ftrace_graph_is_dead(void) } /** - * ftrace_graph_stop - set to permanently disable function graph tracincg + * ftrace_graph_stop - set to permanently disable function graph tracing * * In case of an error int function graph tracing, this is called * to try to keep function graph tracing from causing any more harm. @@ -117,7 +117,7 @@ int function_graph_enter(unsigned long ret, unsigned long func, /* * Skip graph tracing if the return location is served by direct trampoline, - * since call sequence and return addresses is unpredicatable anymore. + * since call sequence and return addresses are unpredictable anyway. * Ex: BPF trampoline may call original function and may skip frame * depending on type of BPF programs attached. */ diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 4d8e35575549..eb7d677cb466 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1045,7 +1045,7 @@ struct ftrace_ops global_ops = { }; /* - * Used by the stack undwinder to know about dynamic ftrace trampolines. + * Used by the stack unwinder to know about dynamic ftrace trampolines. */ struct ftrace_ops *ftrace_ops_trampoline(unsigned long addr) { @@ -3000,7 +3000,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command) * When the kernel is preemptive, tasks can be preempted * while on a ftrace trampoline. Just scheduling a task on * a CPU is not good enough to flush them. Calling - * synchornize_rcu_tasks() will wait for those tasks to + * synchronize_rcu_tasks() will wait for those tasks to * execute and either schedule voluntarily or enter user space. */ if (IS_ENABLED(CONFIG_PREEMPTION)) @@ -5373,7 +5373,7 @@ EXPORT_SYMBOL_GPL(modify_ftrace_direct); * @reset - non zero to reset all filters before applying this filter. * * Filters denote which functions should be enabled when tracing is enabled - * If @ip is NULL, it failes to update filter. + * If @ip is NULL, it fails to update filter. */ int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip, int remove, int reset) @@ -6325,7 +6325,7 @@ clear_mod_from_hash(struct ftrace_page *pg, struct ftrace_hash *hash) } } -/* Clear any records from hashs */ +/* Clear any records from hashes */ static void clear_mod_from_hashes(struct ftrace_page *pg) { struct trace_array *tr; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 1c61a8cd7b99..f4216df58e31 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3154,7 +3154,7 @@ rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) * is called before preempt_count() is updated, since the check will * be on the NORMAL bit, the TRANSITION bit will then be set. If an * NMI then comes in, it will set the NMI bit, but when the NMI code - * does the trace_recursive_unlock() it will clear the TRANSTION bit + * does the trace_recursive_unlock() it will clear the TRANSITION bit * and leave the NMI bit set. But this is fine, because the interrupt * code that set the TRANSITION bit will then clear the NMI bit when it * calls trace_recursive_unlock(). If another NMI comes in, it will diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c index a4b4bbf8c3bf..0b15e975d2c2 100644 --- a/kernel/trace/synth_event_gen_test.c +++ b/kernel/trace/synth_event_gen_test.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Test module for in-kernel sythetic event creation and generation. + * Test module for in-kernel synthetic event creation and generation. * * Copyright (C) 2019 Tom Zanussi */ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index e32f5a49f1cf..c8e54b674d3e 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -514,7 +514,7 @@ void trace_free_pid_list(struct trace_pid_list *pid_list) * @filtered_pids: The list of pids to check * @search_pid: The PID to find in @filtered_pids * - * Returns true if @search_pid is fonud in @filtered_pids, and false otherwis. + * Returns true if @search_pid is found in @filtered_pids, and false otherwise. */ bool trace_find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid) @@ -545,7 +545,7 @@ trace_ignore_this_task(struct trace_pid_list *filtered_pids, struct task_struct *task) { /* - * If filterd_no_pids is not empty, and the task's pid is listed + * If filtered_no_pids is not empty, and the task's pid is listed * in filtered_no_pids, then return true. * Otherwise, if filtered_pids is empty, that means we can * trace all tasks. If it has content, then only trace pids @@ -612,7 +612,7 @@ void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos) (*pos)++; - /* pid already is +1 of the actual prevous bit */ + /* pid already is +1 of the actual previous bit */ pid = find_next_bit(pid_list->pids, pid_list->pid_max, pid); /* Return pid + 1 to allow zero to be represented */ @@ -834,7 +834,7 @@ DEFINE_MUTEX(trace_types_lock); * The content of events may become garbage if we allow other process consumes * these events concurrently: * A) the page of the consumed events may become a normal page - * (not reader page) in ring buffer, and this page will be rewrited + * (not reader page) in ring buffer, and this page will be rewritten * by events producer. * B) The page of the consumed events may become a page for splice_read, * and this page will be returned to system. @@ -1520,7 +1520,7 @@ unsigned long nsecs_to_usecs(unsigned long nsecs) #undef C #define C(a, b) b -/* These must match the bit postions in trace_iterator_flags */ +/* These must match the bit positions in trace_iterator_flags */ static const char *trace_options[] = { TRACE_FLAGS NULL @@ -3368,7 +3368,7 @@ int trace_array_vprintk(struct trace_array *tr, * buffer (use trace_printk() for that), as writing into the top level * buffer should only have events that can be individually disabled. * trace_printk() is only used for debugging a kernel, and should not - * be ever encorporated in normal use. + * be ever incorporated in normal use. * * trace_array_printk() can be used, as it will not add noise to the * top level tracing buffer. @@ -7533,11 +7533,11 @@ static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr) * @cmd: The tracing command that caused the error * @str: The string to position the caret at within @cmd * - * Finds the position of the first occurence of @str within @cmd. The + * Finds the position of the first occurrence of @str within @cmd. The * return value can be passed to tracing_log_err() for caret placement * within @cmd. * - * Returns the index within @cmd of the first occurence of @str or 0 + * Returns the index within @cmd of the first occurrence of @str or 0 * if @str was not found. */ unsigned int err_pos(char *cmd, const char *str) @@ -9320,7 +9320,7 @@ int tracing_init_dentry(void) * As there may still be users that expect the tracing * files to exist in debugfs/tracing, we must automount * the tracefs file system there, so older tools still - * work with the newer kerenl. + * work with the newer kernel. */ tr->dir = debugfs_create_automount("tracing", NULL, trace_automount, NULL); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 2952bd92bc62..5506424eae2a 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1347,7 +1347,7 @@ __event_trigger_test_discard(struct trace_event_file *file, /** * event_trigger_unlock_commit - handle triggers and finish event commit - * @file: The file pointer assoctiated to the event + * @file: The file pointer associated with the event * @buffer: The ring buffer that the event is being written to * @event: The event meta data in the ring buffer * @entry: The event itself @@ -1374,7 +1374,7 @@ event_trigger_unlock_commit(struct trace_event_file *file, /** * event_trigger_unlock_commit_regs - handle triggers and finish event commit - * @file: The file pointer assoctiated to the event + * @file: The file pointer associated with the event * @buffer: The ring buffer that the event is being written to * @event: The event meta data in the ring buffer * @entry: The event itself diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 288ad2c274fb..03be4435d103 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -16,7 +16,7 @@ static char __percpu *perf_trace_buf[PERF_NR_CONTEXTS]; /* * Force it to be aligned to unsigned long to avoid misaligned accesses - * suprises + * surprises */ typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)]) perf_trace_t; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index f58106eaf8cb..80e96989770e 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2646,7 +2646,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len) } /* - * Since calls are grouped by systems, the likelyhood that the + * Since calls are grouped by systems, the likelihood that the * next call in the iteration belongs to the same system as the * previous call is high. As an optimization, we skip searching * for a map[] that matches the call's system if the last call @@ -2706,7 +2706,7 @@ __trace_add_new_event(struct trace_event_call *call, struct trace_array *tr) } /* - * Just create a decriptor for early init. A descriptor is required + * Just create a descriptor for early init. A descriptor is required * for enabling events at boot. We want to enable events before * the filesystem is initialized. */ diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index e91259f6a722..9730acf3c03e 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -296,7 +296,7 @@ enum { * and "FALSE" the program entry after that, we are now done with the first * pass. * - * Making the above "a || b && c" have a progam of: + * Making the above "a || b && c" have a program of: * prog[0] = { "a", 1, 2 } * prog[1] = { "b", 0, 2 } * prog[2] = { "c", 0, 3 } @@ -390,7 +390,7 @@ enum { * F: return FALSE * * As "r = a; if (!r) goto n5;" is obviously the same as - * "if (!a) goto n5;" without doing anything we can interperate the + * "if (!a) goto n5;" without doing anything we can interpret the * program as: * n1: if (!a) goto n5; * n2: if (!b) goto n5; diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index 8d71e6c83f10..2ac75eb6aa86 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -1385,7 +1385,7 @@ static int destroy_synth_event(struct synth_event *se) /** * synth_event_delete - Delete a synthetic event - * @event_name: The name of the new sythetic event + * @event_name: The name of the new synthetic event * * Delete a synthetic event that was created with synth_event_create(). * diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 0aa6e6faa943..0de6837722da 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -764,7 +764,7 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s, * - we are inside irq code * - we just entered irq code * - * retunns 0 if + * returns 0 if * - funcgraph-interrupts option is set * - we are not inside irq code */ diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index 34dc1a712dcb..632ef88131a9 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -83,7 +83,7 @@ struct hwlat_sample { u64 nmi_total_ts; /* Total time spent in NMIs */ struct timespec64 timestamp; /* wall time */ int nmi_count; /* # NMIs during this sample */ - int count; /* # of iteratons over threash */ + int count; /* # of iterations over thresh */ }; /* keep the global state somewhere. */ @@ -389,7 +389,7 @@ static int start_kthread(struct trace_array *tr) } /** - * stop_kthread - Inform the hardware latency samping/detector kthread to stop + * stop_kthread - Inform the hardware latency sampling/detector kthread to stop * * This kicks the running hardware latency sampling/detector kernel thread and * tells it to stop sampling now. Use this on unload and at system shutdown. diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 6fe770d86dc3..ea6178cb5e33 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1748,7 +1748,7 @@ kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs) if (trace_probe_test_flag(&tk->tp, TP_FLAG_PROFILE)) kretprobe_perf_func(tk, ri, regs); #endif - return 0; /* We don't tweek kernel, so just return 0 */ + return 0; /* We don't tweak kernel, so just return 0 */ } NOKPROBE_SYMBOL(kretprobe_dispatcher); diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index ec589a4612df..15413ad7cef2 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -168,7 +168,7 @@ void __trace_probe_log_err(int offset, int err_type) if (!trace_probe_log.argv) return; - /* Recalcurate the length and allocate buffer */ + /* Recalculate the length and allocate buffer */ for (i = 0; i < trace_probe_log.argc; i++) { if (i == trace_probe_log.index) pos = len; @@ -182,7 +182,7 @@ void __trace_probe_log_err(int offset, int err_type) /** * Set the error position is next to the last arg + space. * Note that len includes the terminal null and the cursor - * appaers at pos + 1. + * appears at pos + 1. */ pos = len; offset = 0; @@ -592,7 +592,7 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size, } /* - * Since $comm and immediate string can not be dereferred, + * Since $comm and immediate string can not be dereferenced, * we can find those by strcmp. */ if (strcmp(arg, "$comm") == 0 || strncmp(arg, "\\\"", 2) == 0) { diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 7ce4027089ee..227d518e5ba5 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -134,7 +134,7 @@ struct fetch_type { size_t size; /* Byte size of type */ int is_signed; /* Signed flag */ print_type_func_t print; /* Print functions */ - const char *fmt; /* Fromat string */ + const char *fmt; /* Format string */ const char *fmttype; /* Name in format file */ }; diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h index e5282828f4a6..f003c5d02a3a 100644 --- a/kernel/trace/trace_probe_tmpl.h +++ b/kernel/trace/trace_probe_tmpl.h @@ -167,7 +167,7 @@ array: return code->op == FETCH_OP_END ? ret : -EILSEQ; } -/* Sum up total data length for dynamic arraies (strings) */ +/* Sum up total data length for dynamic arrays (strings) */ static nokprobe_inline int __get_data_size(struct trace_probe *tp, struct pt_regs *regs) { diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 73ef12092250..adf7ef194005 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -878,7 +878,7 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr) int ret; /* - * Now that the big kernel lock is no longer preemptable, + * Now that the big kernel lock is no longer preemptible, * and this is called with the BKL held, it will always * fail. If preemption is already disabled, simply * pass the test. When the BKL is removed, or becomes @@ -940,7 +940,7 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array * int ret; /* - * Now that the big kernel lock is no longer preemptable, + * Now that the big kernel lock is no longer preemptible, * and this is called with the BKL held, it will always * fail. If preemption is already disabled, simply * pass the test. When the BKL is removed, or becomes diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c index 1d84fcc78e3e..9c90b3a7dce2 100644 --- a/kernel/trace/trace_seq.c +++ b/kernel/trace/trace_seq.c @@ -16,7 +16,7 @@ * The buffer size is currently PAGE_SIZE, although it may become dynamic * in the future. * - * A write to the buffer will either succed or fail. That is, unlike + * A write to the buffer will either succeed or fail. That is, unlike * sprintf() there will not be a partial write (well it may write into * the buffer but it wont update the pointers). This allows users to * try to write something into the trace_seq buffer and if it fails @@ -73,7 +73,7 @@ int trace_print_seq(struct seq_file *m, struct trace_seq *s) * @fmt: printf format string * * The tracer may use either sequence operations or its own - * copy to user routines. To simplify formating of a trace + * copy to user routines. To simplify formatting of a trace * trace_seq_printf() is used to store strings into a special * buffer (@s). Then the output may be either used by * the sequencer or pulled into another buffer. @@ -133,7 +133,7 @@ EXPORT_SYMBOL_GPL(trace_seq_bitmask); * @fmt: printf format string * * The tracer may use either sequence operations or its own - * copy to user routines. To simplify formating of a trace + * copy to user routines. To simplify formatting of a trace * trace_seq_printf is used to store strings into a special * buffer (@s). Then the output may be either used by * the sequencer or pulled into another buffer. @@ -226,7 +226,7 @@ EXPORT_SYMBOL_GPL(trace_seq_puts); * @c: simple character to record * * The tracer may use either the sequence operations or its own - * copy to user routines. This function records a simple charater + * copy to user routines. This function records a simple character * into a special buffer (@s) for later retrieval by a sequencer * or other mechanism. */ @@ -348,7 +348,7 @@ int trace_seq_path(struct trace_seq *s, const struct path *path) EXPORT_SYMBOL_GPL(trace_seq_path); /** - * trace_seq_to_user - copy the squence buffer to user space + * trace_seq_to_user - copy the sequence buffer to user space * @s: trace sequence descriptor * @ubuf: The userspace memory location to copy to * @cnt: The amount to copy @@ -363,7 +363,7 @@ EXPORT_SYMBOL_GPL(trace_seq_path); * * On failure it returns -EBUSY if all of the content in the * sequence has been already read, which includes nothing in the - * sequenc (@s->len == @s->readpos). + * sequence (@s->len == @s->readpos). * * Returns -EFAULT if the copy to userspace fails. */ -- cgit v1.2.3-71-gd317 From 4613bdcc122e9e60e0763c5851337470d25d7e40 Mon Sep 17 00:00:00 2001 From: Bhaskar Chowdhury Date: Wed, 17 Mar 2021 15:24:01 +0530 Subject: kernel: trace: Mundane typo fixes in the file trace_events_filter.c s/callin/calling/ Link: https://lkml.kernel.org/r/20210317095401.1854544-1-unixbhaskar@gmail.com Acked-by: Randy Dunlap Signed-off-by: Bhaskar Chowdhury [ Other fixes already done by Ingo Molnar ] Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_filter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 9730acf3c03e..49de3e21e9bc 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -256,7 +256,7 @@ enum { * is "&&" we don't call update_preds(). Instead continue to "c". As the * next token after "c" is not "&&" but the end of input, we first process the * "&&" by calling update_preds() for the "&&" then we process the "||" by - * callin updates_preds() with the values for processing "||". + * calling updates_preds() with the values for processing "||". * * What does that mean? What update_preds() does is to first save the "target" * of the program entry indexed by the current program entry's "target" -- cgit v1.2.3-71-gd317 From 30c3d39f7f78f3b232f6a6f6357a545cbe23cc16 Mon Sep 17 00:00:00 2001 From: Qiujun Huang Date: Thu, 25 Mar 2021 16:37:52 +0000 Subject: tracing: A minor cleanup for create_system_filter() The first two parameters should be reduced to one, as @tr is simply @dir->tr. Link: https://lkml.kernel.org/r/20210324205642.65e03248@oasis.local.home Link: https://lkml.kernel.org/r/20210325163752.128407-1-hqjagain@gmail.com Suggested-by: Steven Rostedt (VMware) Signed-off-by: Qiujun Huang Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_filter.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 49de3e21e9bc..c2dd697cc9c0 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1750,7 +1750,6 @@ int create_event_filter(struct trace_array *tr, * and always remembers @filter_str. */ static int create_system_filter(struct trace_subsystem_dir *dir, - struct trace_array *tr, char *filter_str, struct event_filter **filterp) { struct filter_parse_error *pe = NULL; @@ -1758,13 +1757,13 @@ static int create_system_filter(struct trace_subsystem_dir *dir, err = create_filter_start(filter_str, true, &pe, filterp); if (!err) { - err = process_system_preds(dir, tr, pe, filter_str); + err = process_system_preds(dir, dir->tr, pe, filter_str); if (!err) { /* System filters just show a default message */ kfree((*filterp)->filter_string); (*filterp)->filter_string = NULL; } else { - append_filter_err(tr, pe, *filterp); + append_filter_err(dir->tr, pe, *filterp); } } create_filter_finish(pe); @@ -1852,7 +1851,7 @@ int apply_subsystem_event_filter(struct trace_subsystem_dir *dir, goto out_unlock; } - err = create_system_filter(dir, tr, filter_string, &filter); + err = create_system_filter(dir, filter_string, &filter); if (filter) { /* * No event actually uses the system filter -- cgit v1.2.3-71-gd317 From 70193038a6ec9bbf10990a126432b0cbf56aa339 Mon Sep 17 00:00:00 2001 From: Qiujun Huang Date: Thu, 25 Mar 2021 16:19:10 +0000 Subject: tracing: Update create_system_filter() kernel-doc comment commit f306cc82a93d ("tracing: Update event filters for multibuffer") added the parameter @tr for create_system_filter(). commit bb9ef1cb7d86 ("tracing: Change apply_subsystem_event_filter() paths to check file->system == dir") changed the parameter from @system to @dir. Link: https://lkml.kernel.org/r/20210325161911.123452-1-hqjagain@gmail.com Signed-off-by: Qiujun Huang Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_filter.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index c2dd697cc9c0..c9124038b140 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1693,6 +1693,7 @@ static void create_filter_finish(struct filter_parse_error *pe) /** * create_filter - create a filter for a trace_event_call + * @tr: the trace array associated with these events * @call: trace_event_call to create a filter for * @filter_str: filter string * @set_str: remember @filter_str and enable detailed error in filter @@ -1741,8 +1742,8 @@ int create_event_filter(struct trace_array *tr, } /** - * create_system_filter - create a filter for an event_subsystem - * @system: event_subsystem to create a filter for + * create_system_filter - create a filter for an event subsystem + * @dir: the descriptor for the subsystem directory * @filter_str: filter string * @filterp: out param for created filter (always updated on return) * -- cgit v1.2.3-71-gd317 From 67196fea0fcef92b25608882f62f3985bc59f1fe Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 9 Mar 2021 11:37:31 +0200 Subject: irqdomain: Introduce irq_domain_create_simple() API Linus Walleij pointed out that ird_domain_add_simple() gained additional functionality and can't be anymore replaced with a simple conditional. In preparation to upgrade GPIO library to use fwnode, introduce irq_domain_create_simple() API which is functional equivalent to the existing irq_domain_add_simple(), but takes a pointer to the struct fwnode_handle as a parameter. While at it, amend documentation to mention irq_domain_create_*() functions where it makes sense. Signed-off-by: Andy Shevchenko Acked-by: Marc Zyngier Signed-off-by: Bartosz Golaszewski --- Documentation/core-api/irq/irq-domain.rst | 22 ++++++++++++---------- include/linux/irqdomain.h | 19 ++++++++++++++----- kernel/irq/irqdomain.c | 20 ++++++++++---------- 3 files changed, 36 insertions(+), 25 deletions(-) (limited to 'kernel') diff --git a/Documentation/core-api/irq/irq-domain.rst b/Documentation/core-api/irq/irq-domain.rst index a77c24c27f7b..8214e215a8bf 100644 --- a/Documentation/core-api/irq/irq-domain.rst +++ b/Documentation/core-api/irq/irq-domain.rst @@ -42,10 +42,10 @@ irq_domain usage ================ An interrupt controller driver creates and registers an irq_domain by -calling one of the irq_domain_add_*() functions (each mapping method -has a different allocator function, more on that later). The function -will return a pointer to the irq_domain on success. The caller must -provide the allocator function with an irq_domain_ops structure. +calling one of the irq_domain_add_*() or irq_domain_create_*() functions +(each mapping method has a different allocator function, more on that later). +The function will return a pointer to the irq_domain on success. The caller +must provide the allocator function with an irq_domain_ops structure. In most cases, the irq_domain will begin empty without any mappings between hwirq and IRQ numbers. Mappings are added to the irq_domain @@ -147,6 +147,7 @@ Legacy irq_domain_add_simple() irq_domain_add_legacy() irq_domain_add_legacy_isa() + irq_domain_create_simple() irq_domain_create_legacy() The Legacy mapping is a special case for drivers that already have a @@ -169,13 +170,13 @@ supported. For example, ISA controllers would use the legacy map for mapping Linux IRQs 0-15 so that existing ISA drivers get the correct IRQ numbers. -Most users of legacy mappings should use irq_domain_add_simple() which -will use a legacy domain only if an IRQ range is supplied by the -system and will otherwise use a linear domain mapping. The semantics -of this call are such that if an IRQ range is specified then +Most users of legacy mappings should use irq_domain_add_simple() or +irq_domain_create_simple() which will use a legacy domain only if an IRQ range +is supplied by the system and will otherwise use a linear domain mapping. +The semantics of this call are such that if an IRQ range is specified then descriptors will be allocated on-the-fly for it, and if no range is -specified it will fall through to irq_domain_add_linear() which means -*no* irq descriptors will be allocated. +specified it will fall through to irq_domain_add_linear() or +irq_domain_create_linear() which means *no* irq descriptors will be allocated. A typical use case for simple domains is where an irqchip provider is supporting both dynamic and static IRQ assignments. @@ -186,6 +187,7 @@ that the driver using the simple domain call irq_create_mapping() before any irq_find_mapping() since the latter will actually work for the static IRQ assignment case. +irq_domain_add_simple() and irq_domain_create_simple() as well as irq_domain_add_legacy() and irq_domain_create_legacy() are functionally equivalent, except for the first argument is different - the former accepts an Open Firmware specific 'struct device_node', while the latter diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 33cacc8af26d..1ad8d5328715 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -256,11 +256,11 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, irq_hw_number_t hwirq_max, int direct_max, const struct irq_domain_ops *ops, void *host_data); -struct irq_domain *irq_domain_add_simple(struct device_node *of_node, - unsigned int size, - unsigned int first_irq, - const struct irq_domain_ops *ops, - void *host_data); +struct irq_domain *irq_domain_create_simple(struct fwnode_handle *fwnode, + unsigned int size, + unsigned int first_irq, + const struct irq_domain_ops *ops, + void *host_data); struct irq_domain *irq_domain_add_legacy(struct device_node *of_node, unsigned int size, unsigned int first_irq, @@ -325,6 +325,15 @@ static inline struct irq_domain *irq_find_host(struct device_node *node) return d; } +static inline struct irq_domain *irq_domain_add_simple(struct device_node *of_node, + unsigned int size, + unsigned int first_irq, + const struct irq_domain_ops *ops, + void *host_data) +{ + return irq_domain_create_simple(of_node_to_fwnode(of_node), size, first_irq, ops, host_data); +} + /** * irq_domain_add_linear() - Allocate and register a linear revmap irq_domain. * @of_node: pointer to interrupt controller's device tree node. diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index d10ab1d689d5..2681dc43813c 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -295,8 +295,8 @@ void irq_domain_update_bus_token(struct irq_domain *domain, EXPORT_SYMBOL_GPL(irq_domain_update_bus_token); /** - * irq_domain_add_simple() - Register an irq_domain and optionally map a range of irqs - * @of_node: pointer to interrupt controller's device tree node. + * irq_domain_create_simple() - Register an irq_domain and optionally map a range of irqs + * @fwnode: firmware node for the interrupt controller * @size: total number of irqs in mapping * @first_irq: first number of irq block assigned to the domain, * pass zero to assign irqs on-the-fly. If first_irq is non-zero, then @@ -312,15 +312,15 @@ EXPORT_SYMBOL_GPL(irq_domain_update_bus_token); * irqs get mapped dynamically on the fly. However, if the controller requires * static virq assignments (non-DT boot) then it will set that up correctly. */ -struct irq_domain *irq_domain_add_simple(struct device_node *of_node, - unsigned int size, - unsigned int first_irq, - const struct irq_domain_ops *ops, - void *host_data) +struct irq_domain *irq_domain_create_simple(struct fwnode_handle *fwnode, + unsigned int size, + unsigned int first_irq, + const struct irq_domain_ops *ops, + void *host_data) { struct irq_domain *domain; - domain = __irq_domain_add(of_node_to_fwnode(of_node), size, size, 0, ops, host_data); + domain = __irq_domain_add(fwnode, size, size, 0, ops, host_data); if (!domain) return NULL; @@ -328,7 +328,7 @@ struct irq_domain *irq_domain_add_simple(struct device_node *of_node, if (IS_ENABLED(CONFIG_SPARSE_IRQ)) { /* attempt to allocated irq_descs */ int rc = irq_alloc_descs(first_irq, first_irq, size, - of_node_to_nid(of_node)); + of_node_to_nid(to_of_node(fwnode))); if (rc < 0) pr_info("Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n", first_irq); @@ -338,7 +338,7 @@ struct irq_domain *irq_domain_add_simple(struct device_node *of_node, return domain; } -EXPORT_SYMBOL_GPL(irq_domain_add_simple); +EXPORT_SYMBOL_GPL(irq_domain_create_simple); /** * irq_domain_add_legacy() - Allocate and register a legacy revmap irq_domain. -- cgit v1.2.3-71-gd317 From f3ef7202ef7c705d640d1aeec3b286a641ac9186 Mon Sep 17 00:00:00 2001 From: "Yordan Karadzhov (VMware)" Date: Mon, 29 Mar 2021 16:03:31 +0300 Subject: tracing: Remove unused argument from "ring_buffer_time_stamp() The "cpu" parameter is not being used by the function. Link: https://lkml.kernel.org/r/20210329130331.199402-1-y.karadz@gmail.com Signed-off-by: Yordan Karadzhov (VMware) Signed-off-by: Steven Rostedt (VMware) --- include/linux/ring_buffer.h | 2 +- kernel/trace/ring_buffer.c | 2 +- kernel/trace/trace.c | 8 ++++---- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 057b7ed4fe24..dac53fd3afea 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -181,7 +181,7 @@ unsigned long ring_buffer_commit_overrun_cpu(struct trace_buffer *buffer, int cp unsigned long ring_buffer_dropped_events_cpu(struct trace_buffer *buffer, int cpu); unsigned long ring_buffer_read_events_cpu(struct trace_buffer *buffer, int cpu); -u64 ring_buffer_time_stamp(struct trace_buffer *buffer, int cpu); +u64 ring_buffer_time_stamp(struct trace_buffer *buffer); void ring_buffer_normalize_time_stamp(struct trace_buffer *buffer, int cpu, u64 *ts); void ring_buffer_set_clock(struct trace_buffer *buffer, diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index f4216df58e31..2c0ee6484990 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1080,7 +1080,7 @@ static inline u64 rb_time_stamp(struct trace_buffer *buffer) return ts << DEBUG_SHIFT; } -u64 ring_buffer_time_stamp(struct trace_buffer *buffer, int cpu) +u64 ring_buffer_time_stamp(struct trace_buffer *buffer) { u64 time; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 3834de91fb97..507a30bf26e4 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -771,7 +771,7 @@ static u64 buffer_ftrace_now(struct array_buffer *buf, int cpu) if (!buf->buffer) return trace_clock_local(); - ts = ring_buffer_time_stamp(buf->buffer, cpu); + ts = ring_buffer_time_stamp(buf->buffer); ring_buffer_normalize_time_stamp(buf->buffer, cpu, &ts); return ts; @@ -7174,7 +7174,7 @@ static int tracing_time_stamp_mode_open(struct inode *inode, struct file *file) u64 tracing_event_time_stamp(struct trace_buffer *buffer, struct ring_buffer_event *rbe) { if (rbe == this_cpu_read(trace_buffered_event)) - return ring_buffer_time_stamp(buffer, smp_processor_id()); + return ring_buffer_time_stamp(buffer); return ring_buffer_event_time_stamp(buffer, rbe); } @@ -8088,7 +8088,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf, trace_seq_printf(s, "oldest event ts: %5llu.%06lu\n", t, usec_rem); - t = ns2usecs(ring_buffer_time_stamp(trace_buf->buffer, cpu)); + t = ns2usecs(ring_buffer_time_stamp(trace_buf->buffer)); usec_rem = do_div(t, USEC_PER_SEC); trace_seq_printf(s, "now ts: %5llu.%06lu\n", t, usec_rem); } else { @@ -8097,7 +8097,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf, ring_buffer_oldest_event_ts(trace_buf->buffer, cpu)); trace_seq_printf(s, "now ts: %llu\n", - ring_buffer_time_stamp(trace_buf->buffer, cpu)); + ring_buffer_time_stamp(trace_buf->buffer)); } cnt = ring_buffer_dropped_events_cpu(trace_buf->buffer, cpu); -- cgit v1.2.3-71-gd317 From 2726bf3ff2520dba61fafc90a055640f7ad54e05 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 22 Mar 2021 18:53:49 -0700 Subject: swiotlb: Make SWIOTLB_NO_FORCE perform no allocation When SWIOTLB_NO_FORCE is used, there should really be no allocations of default_nslabs to occur since we are not going to use those slabs. If a platform was somehow setting swiotlb_no_force and a later call to swiotlb_init() was to be made we would still be proceeding with allocating the default SWIOTLB size (64MB), whereas if swiotlb=noforce was set on the kernel command line we would have only allocated 2KB. This would be inconsistent and the point of initializing default_nslabs to 1, was intended to allocate the minimum amount of memory possible, so simply remove that minimal allocation period. Signed-off-by: Florian Fainelli Reviewed-by: Christoph Hellwig Signed-off-by: Konrad Rzeszutek Wilk --- kernel/dma/swiotlb.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 539c76beb52e..0a5b6f7e75bc 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -83,12 +83,10 @@ setup_io_tlb_npages(char *str) } if (*str == ',') ++str; - if (!strcmp(str, "force")) { + if (!strcmp(str, "force")) swiotlb_force = SWIOTLB_FORCE; - } else if (!strcmp(str, "noforce")) { + else if (!strcmp(str, "noforce")) swiotlb_force = SWIOTLB_NO_FORCE; - default_nslabs = 1; - } return 0; } @@ -174,6 +172,9 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) struct io_tlb_mem *mem; size_t alloc_size; + if (swiotlb_force == SWIOTLB_NO_FORCE) + return 0; + /* protect against double initialization */ if (WARN_ON_ONCE(io_tlb_default_mem)) return -ENOMEM; @@ -211,6 +212,9 @@ swiotlb_init(int verbose) size_t bytes = PAGE_ALIGN(default_nslabs << IO_TLB_SHIFT); void *tlb; + if (swiotlb_force == SWIOTLB_NO_FORCE) + return; + /* Get IO TLB memory from the low pages */ tlb = memblock_alloc_low(bytes, PAGE_SIZE); if (!tlb) @@ -240,6 +244,9 @@ swiotlb_late_init_with_default_size(size_t default_size) unsigned int order; int rc = 0; + if (swiotlb_force == SWIOTLB_NO_FORCE) + return 0; + /* * Get IO TLB memory from the low pages */ @@ -276,6 +283,9 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) unsigned long bytes = nslabs << IO_TLB_SHIFT, i; struct io_tlb_mem *mem; + if (swiotlb_force == SWIOTLB_NO_FORCE) + return 0; + /* protect against double initialization */ if (WARN_ON_ONCE(io_tlb_default_mem)) return -ENOMEM; -- cgit v1.2.3-71-gd317 From db42523b4f3e83ff86b53cdda219a9767c8b047f Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 1 Apr 2021 16:14:17 -0400 Subject: ftrace: Store the order of pages allocated in ftrace_page Instead of saving the size of the records field of the ftrace_page, store the order it uses to allocate the pages, as that is what is needed to know in order to free the pages. This simplifies the code. Link: https://lore.kernel.org/lkml/CAHk-=whyMxheOqXAORt9a7JK9gc9eHTgCJ55Pgs4p=X3RrQubQ@mail.gmail.com/ Signed-off-by: Linus Torvalds [ change log written by Steven Rostedt ] Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 35 +++++++++++++++++------------------ 1 file changed, 17 insertions(+), 18 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 22ecaaa13baa..f7bef5a9ada9 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1090,7 +1090,7 @@ struct ftrace_page { struct ftrace_page *next; struct dyn_ftrace *records; int index; - int size; + int order; }; #define ENTRY_SIZE sizeof(struct dyn_ftrace) @@ -3181,7 +3181,7 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count) ftrace_number_of_groups++; cnt = (PAGE_SIZE << order) / ENTRY_SIZE; - pg->size = cnt; + pg->order = order; if (cnt > count) cnt = count; @@ -3194,7 +3194,6 @@ ftrace_allocate_pages(unsigned long num_to_init) { struct ftrace_page *start_pg; struct ftrace_page *pg; - int order; int cnt; if (!num_to_init) @@ -3230,13 +3229,13 @@ ftrace_allocate_pages(unsigned long num_to_init) free_pages: pg = start_pg; while (pg) { - order = get_count_order(pg->size / ENTRIES_PER_PAGE); - if (order >= 0) - free_pages((unsigned long)pg->records, order); + if (pg->records) { + free_pages((unsigned long)pg->records, pg->order); + ftrace_number_of_pages -= 1 << pg->order; + } start_pg = pg->next; kfree(pg); pg = start_pg; - ftrace_number_of_pages -= 1 << order; ftrace_number_of_groups--; } pr_info("ftrace: FAILED to allocate memory for functions\n"); @@ -6188,6 +6187,7 @@ static int ftrace_process_locs(struct module *mod, p = start; pg = start_pg; while (p < end) { + unsigned long end_offset; addr = ftrace_call_adjust(*p++); /* * Some architecture linkers will pad between @@ -6198,7 +6198,8 @@ static int ftrace_process_locs(struct module *mod, if (!addr) continue; - if (pg->index == pg->size) { + end_offset = (pg->index+1) * sizeof(pg->records[0]); + if (end_offset > PAGE_SIZE << pg->order) { /* We should have allocated enough */ if (WARN_ON(!pg->next)) break; @@ -6367,7 +6368,6 @@ void ftrace_release_mod(struct module *mod) struct ftrace_page **last_pg; struct ftrace_page *tmp_page = NULL; struct ftrace_page *pg; - int order; mutex_lock(&ftrace_lock); @@ -6418,12 +6418,12 @@ void ftrace_release_mod(struct module *mod) /* Needs to be called outside of ftrace_lock */ clear_mod_from_hashes(pg); - order = get_count_order(pg->size / ENTRIES_PER_PAGE); - if (order >= 0) - free_pages((unsigned long)pg->records, order); + if (pg->records) { + free_pages((unsigned long)pg->records, pg->order); + ftrace_number_of_pages -= 1 << pg->order; + } tmp_page = pg->next; kfree(pg); - ftrace_number_of_pages -= 1 << order; ftrace_number_of_groups--; } } @@ -6741,7 +6741,6 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr) struct ftrace_mod_map *mod_map = NULL; struct ftrace_init_func *func, *func_next; struct list_head clear_hash; - int order; INIT_LIST_HEAD(&clear_hash); @@ -6779,10 +6778,10 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr) ftrace_update_tot_cnt--; if (!pg->index) { *last_pg = pg->next; - order = get_count_order(pg->size / ENTRIES_PER_PAGE); - if (order >= 0) - free_pages((unsigned long)pg->records, order); - ftrace_number_of_pages -= 1 << order; + if (pg->records) { + free_pages((unsigned long)pg->records, pg->order); + ftrace_number_of_pages -= 1 << pg->order; + } ftrace_number_of_groups--; kfree(pg); pg = container_of(last_pg, struct ftrace_page, next); -- cgit v1.2.3-71-gd317 From ceaaa12904df07d07ea8975abbf04c4d60e46956 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 1 Apr 2021 16:40:32 -0400 Subject: ftrace: Simplify the calculation of page number for ftrace_page->records some more Commit b40c6eabfcd40 ("ftrace: Simplify the calculation of page number for ftrace_page->records") simplified the calculation of the number of pages needed for each page group without having any empty pages, but it can be simplified even further. Link: https://lore.kernel.org/lkml/CAHk-=wjt9b7kxQ2J=aDNKbR1QBMB3Hiqb_hYcZbKsxGRSEb+gQ@mail.gmail.com/ Suggested-by: Linus Torvalds Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f7bef5a9ada9..057e962ca5ce 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3156,15 +3156,9 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count) if (WARN_ON(!count)) return -EINVAL; + /* We want to fill as much as possible, with no empty pages */ pages = DIV_ROUND_UP(count, ENTRIES_PER_PAGE); - order = get_count_order(pages); - - /* - * We want to fill as much as possible. No more than a page - * may be empty. - */ - if (!is_power_of_2(pages)) - order--; + order = fls(pages) - 1; again: pg->records = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, order); -- cgit v1.2.3-71-gd317 From 42e4eefb089f12ea900062ecdcc7ca10c3423a05 Mon Sep 17 00:00:00 2001 From: Hao Fang Date: Tue, 30 Mar 2021 14:33:48 +0800 Subject: dma-mapping: benchmark: use the correct HiSilicon copyright s/Hisilicon/HiSilicon/g. It should use capital S, according to https://www.hisilicon.com/en/terms-of-use. Signed-off-by: Hao Fang Acked-by: Barry Song Signed-off-by: Christoph Hellwig --- kernel/dma/map_benchmark.c | 2 +- tools/testing/selftests/dma/dma_map_benchmark.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c index e0e64f8b0739..00d6549a5495 100644 --- a/kernel/dma/map_benchmark.c +++ b/kernel/dma/map_benchmark.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2020 Hisilicon Limited. + * Copyright (C) 2020 HiSilicon Limited. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/tools/testing/selftests/dma/dma_map_benchmark.c b/tools/testing/selftests/dma/dma_map_benchmark.c index fb23ce9617ea..b492bed0936d 100644 --- a/tools/testing/selftests/dma/dma_map_benchmark.c +++ b/tools/testing/selftests/dma/dma_map_benchmark.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2020 Hisilicon Limited. + * Copyright (C) 2020 HiSilicon Limited. */ #include -- cgit v1.2.3-71-gd317 From ca947482b0b30443e6da1f0f5ba7244e34a4f65a Mon Sep 17 00:00:00 2001 From: Xiang Chen Date: Thu, 18 Mar 2021 17:29:30 +0800 Subject: dma-mapping: benchmark: Add support for multi-pages map/unmap Currently it only support one page map/unmap once a time for dma-map benchmark, but there are some other scenaries which need to support for multi-page map/unmap: for those multi-pages interfaces such as dma_alloc_coherent() and dma_map_sg(), the time spent on multi-pages map/unmap is not the time of a single page * npages (not linear) as it may use block description instead of page description when it is satified with the size such as 2M/1G, and also it can send a single TLB invalidation command to invalidate multi-pages instead of multi-times when RIL is enabled (which will short the time of unmap). So it is necessary to add support for multi-pages map/unmap. Add a parameter "-g" to support multi-pages map/unmap. Signed-off-by: Xiang Chen Acked-by: Barry Song Signed-off-by: Christoph Hellwig --- kernel/dma/map_benchmark.c | 21 ++++++++++++++------- tools/testing/selftests/dma/dma_map_benchmark.c | 20 ++++++++++++++++---- 2 files changed, 30 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c index 00d6549a5495..9b9af1bd6be3 100644 --- a/kernel/dma/map_benchmark.c +++ b/kernel/dma/map_benchmark.c @@ -38,7 +38,8 @@ struct map_benchmark { __u32 dma_bits; /* DMA addressing capability */ __u32 dma_dir; /* DMA data direction */ __u32 dma_trans_ns; /* time for DMA transmission in ns */ - __u8 expansion[80]; /* For future use */ + __u32 granule; /* how many PAGE_SIZE will do map/unmap once a time */ + __u8 expansion[76]; /* For future use */ }; struct map_benchmark_data { @@ -58,9 +59,11 @@ static int map_benchmark_thread(void *data) void *buf; dma_addr_t dma_addr; struct map_benchmark_data *map = data; + int npages = map->bparam.granule; + u64 size = npages * PAGE_SIZE; int ret = 0; - buf = (void *)__get_free_page(GFP_KERNEL); + buf = alloc_pages_exact(size, GFP_KERNEL); if (!buf) return -ENOMEM; @@ -76,10 +79,10 @@ static int map_benchmark_thread(void *data) * 66 means evertything goes well! 66 is lucky. */ if (map->dir != DMA_FROM_DEVICE) - memset(buf, 0x66, PAGE_SIZE); + memset(buf, 0x66, size); map_stime = ktime_get(); - dma_addr = dma_map_single(map->dev, buf, PAGE_SIZE, map->dir); + dma_addr = dma_map_single(map->dev, buf, size, map->dir); if (unlikely(dma_mapping_error(map->dev, dma_addr))) { pr_err("dma_map_single failed on %s\n", dev_name(map->dev)); @@ -93,7 +96,7 @@ static int map_benchmark_thread(void *data) ndelay(map->bparam.dma_trans_ns); unmap_stime = ktime_get(); - dma_unmap_single(map->dev, dma_addr, PAGE_SIZE, map->dir); + dma_unmap_single(map->dev, dma_addr, size, map->dir); unmap_etime = ktime_get(); unmap_delta = ktime_sub(unmap_etime, unmap_stime); @@ -112,7 +115,7 @@ static int map_benchmark_thread(void *data) } out: - free_page((unsigned long)buf); + free_pages_exact(buf, size); return ret; } @@ -203,7 +206,6 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd, struct map_benchmark_data *map = file->private_data; void __user *argp = (void __user *)arg; u64 old_dma_mask; - int ret; if (copy_from_user(&map->bparam, argp, sizeof(map->bparam))) @@ -234,6 +236,11 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd, return -EINVAL; } + if (map->bparam.granule < 1 || map->bparam.granule > 1024) { + pr_err("invalid granule size\n"); + return -EINVAL; + } + switch (map->bparam.dma_dir) { case DMA_MAP_BIDIRECTIONAL: map->dir = DMA_BIDIRECTIONAL; diff --git a/tools/testing/selftests/dma/dma_map_benchmark.c b/tools/testing/selftests/dma/dma_map_benchmark.c index b492bed0936d..485dff51bad2 100644 --- a/tools/testing/selftests/dma/dma_map_benchmark.c +++ b/tools/testing/selftests/dma/dma_map_benchmark.c @@ -40,7 +40,8 @@ struct map_benchmark { __u32 dma_bits; /* DMA addressing capability */ __u32 dma_dir; /* DMA data direction */ __u32 dma_trans_ns; /* time for DMA transmission in ns */ - __u8 expansion[80]; /* For future use */ + __u32 granule; /* how many PAGE_SIZE will do map/unmap once a time */ + __u8 expansion[76]; /* For future use */ }; int main(int argc, char **argv) @@ -51,11 +52,13 @@ int main(int argc, char **argv) int threads = 1, seconds = 20, node = -1; /* default dma mask 32bit, bidirectional DMA */ int bits = 32, xdelay = 0, dir = DMA_MAP_BIDIRECTIONAL; + /* default granule 1 PAGESIZE */ + int granule = 1; int cmd = DMA_MAP_BENCHMARK; char *p; - while ((opt = getopt(argc, argv, "t:s:n:b:d:x:")) != -1) { + while ((opt = getopt(argc, argv, "t:s:n:b:d:x:g:")) != -1) { switch (opt) { case 't': threads = atoi(optarg); @@ -75,6 +78,9 @@ int main(int argc, char **argv) case 'x': xdelay = atoi(optarg); break; + case 'g': + granule = atoi(optarg); + break; default: return -1; } @@ -110,6 +116,11 @@ int main(int argc, char **argv) exit(1); } + if (granule < 1 || granule > 1024) { + fprintf(stderr, "invalid granule size\n"); + exit(1); + } + fd = open("/sys/kernel/debug/dma_map_benchmark", O_RDWR); if (fd == -1) { perror("open"); @@ -123,14 +134,15 @@ int main(int argc, char **argv) map.dma_bits = bits; map.dma_dir = dir; map.dma_trans_ns = xdelay; + map.granule = granule; if (ioctl(fd, cmd, &map)) { perror("ioctl"); exit(1); } - printf("dma mapping benchmark: threads:%d seconds:%d node:%d dir:%s\n", - threads, seconds, node, dir[directions]); + printf("dma mapping benchmark: threads:%d seconds:%d node:%d dir:%s granule: %d\n", + threads, seconds, node, dir[directions], granule); printf("average map latency(us):%.1f standard deviation:%.1f\n", map.avg_map_100ns/10.0, map.map_stddev/10.0); printf("average unmap latency(us):%.1f standard deviation:%.1f\n", -- cgit v1.2.3-71-gd317 From eaa7a897206ac5bfa7da3f647686209ada1984d0 Mon Sep 17 00:00:00 2001 From: "Yordan Karadzhov (VMware)" Date: Thu, 15 Apr 2021 21:18:49 +0300 Subject: tracing: Define static void trace_print_time() The part of the code that prints the time of the trace record in "int trace_print_context()" gets extracted in a static function. This is done as a preparation for a following patch, in which we will define a new ftrace event called "func_repeats". The new static method, defined here, will be used by this new event to print the time of the last repeat of a function that is consecutively called number of times. Link: https://lkml.kernel.org/r/20210415181854.147448-2-y.karadz@gmail.com Signed-off-by: Yordan Karadzhov (VMware) Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_output.c | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index a0146e1fffdf..333233d45596 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -587,13 +587,26 @@ lat_print_timestamp(struct trace_iterator *iter, u64 next_ts) return !trace_seq_has_overflowed(s); } +static void trace_print_time(struct trace_seq *s, struct trace_iterator *iter, + unsigned long long ts) +{ + unsigned long secs, usec_rem; + unsigned long long t; + + if (iter->iter_flags & TRACE_FILE_TIME_IN_NS) { + t = ns2usecs(ts); + usec_rem = do_div(t, USEC_PER_SEC); + secs = (unsigned long)t; + trace_seq_printf(s, " %5lu.%06lu", secs, usec_rem); + } else + trace_seq_printf(s, " %12llu", ts); +} + int trace_print_context(struct trace_iterator *iter) { struct trace_array *tr = iter->tr; struct trace_seq *s = &iter->seq; struct trace_entry *entry = iter->ent; - unsigned long long t; - unsigned long secs, usec_rem; char comm[TASK_COMM_LEN]; trace_find_cmdline(entry->pid, comm); @@ -614,13 +627,8 @@ int trace_print_context(struct trace_iterator *iter) if (tr->trace_flags & TRACE_ITER_IRQ_INFO) trace_print_lat_fmt(s, entry); - if (iter->iter_flags & TRACE_FILE_TIME_IN_NS) { - t = ns2usecs(iter->ts); - usec_rem = do_div(t, USEC_PER_SEC); - secs = (unsigned long)t; - trace_seq_printf(s, " %5lu.%06lu: ", secs, usec_rem); - } else - trace_seq_printf(s, " %12llu: ", iter->ts); + trace_print_time(s, iter, iter->ts); + trace_seq_puts(s, ": "); return !trace_seq_has_overflowed(s); } -- cgit v1.2.3-71-gd317 From f689e4f280b69cd7341743c2ecacd1b13528a0d8 Mon Sep 17 00:00:00 2001 From: "Yordan Karadzhov (VMware)" Date: Thu, 15 Apr 2021 21:18:50 +0300 Subject: tracing: Define new ftrace event "func_repeats" The event aims to consolidate the function tracing record in the cases when a single function is called number of times consecutively. while (cond) do_func(); This may happen in various scenarios (busy waiting for example). The new ftrace event can be used to show repeated function events with a single event and save space on the ring buffer Link: https://lkml.kernel.org/r/20210415181854.147448-3-y.karadz@gmail.com Signed-off-by: Yordan Karadzhov (VMware) Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.h | 3 +++ kernel/trace/trace_entries.h | 22 ++++++++++++++++++++ kernel/trace/trace_output.c | 48 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 73 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 5506424eae2a..6a5b4c2a0fa7 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -45,6 +45,7 @@ enum trace_type { TRACE_BPUTS, TRACE_HWLAT, TRACE_RAW_DATA, + TRACE_FUNC_REPEATS, __TRACE_LAST_TYPE, }; @@ -442,6 +443,8 @@ extern void __ftrace_bad_type(void); TRACE_GRAPH_ENT); \ IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry, \ TRACE_GRAPH_RET); \ + IF_ASSIGN(var, ent, struct func_repeats_entry, \ + TRACE_FUNC_REPEATS); \ __ftrace_bad_type(); \ } while (0) diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index 4547ac59da61..251c819cf0c5 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -338,3 +338,25 @@ FTRACE_ENTRY(hwlat, hwlat_entry, __entry->nmi_total_ts, __entry->nmi_count) ); + +#define FUNC_REPEATS_GET_DELTA_TS(entry) \ + (((u64)(entry)->top_delta_ts << 32) | (entry)->bottom_delta_ts) \ + +FTRACE_ENTRY(func_repeats, func_repeats_entry, + + TRACE_FUNC_REPEATS, + + F_STRUCT( + __field( unsigned long, ip ) + __field( unsigned long, parent_ip ) + __field( u16 , count ) + __field( u16 , top_delta_ts ) + __field( u32 , bottom_delta_ts ) + ), + + F_printk(" %ps <-%ps\t(repeats:%u delta: -%llu)", + (void *)__entry->ip, + (void *)__entry->parent_ip, + __entry->count, + FUNC_REPEATS_GET_DELTA_TS(__entry)) +); diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 333233d45596..3037f0c88f90 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -1381,6 +1381,53 @@ static struct trace_event trace_raw_data_event = { .funcs = &trace_raw_data_funcs, }; +static enum print_line_t +trace_func_repeats_raw(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct func_repeats_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + trace_seq_printf(s, "%lu %lu %u %llu\n", + field->ip, + field->parent_ip, + field->count, + FUNC_REPEATS_GET_DELTA_TS(field)); + + return trace_handle_return(s); +} + +static enum print_line_t +trace_func_repeats_print(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct func_repeats_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + seq_print_ip_sym(s, field->ip, flags); + trace_seq_puts(s, " <-"); + seq_print_ip_sym(s, field->parent_ip, flags); + trace_seq_printf(s, " (repeats: %u, last_ts:", field->count); + trace_print_time(s, iter, + iter->ts - FUNC_REPEATS_GET_DELTA_TS(field)); + trace_seq_puts(s, ")\n"); + + return trace_handle_return(s); +} + +static struct trace_event_functions trace_func_repeats_funcs = { + .trace = trace_func_repeats_print, + .raw = trace_func_repeats_raw, +}; + +static struct trace_event trace_func_repeats_event = { + .type = TRACE_FUNC_REPEATS, + .funcs = &trace_func_repeats_funcs, +}; static struct trace_event *events[] __initdata = { &trace_fn_event, @@ -1393,6 +1440,7 @@ static struct trace_event *events[] __initdata = { &trace_print_event, &trace_hwlat_event, &trace_raw_data_event, + &trace_func_repeats_event, NULL }; -- cgit v1.2.3-71-gd317 From 20344c54d1c7ab7428e312bbe9b0097750875002 Mon Sep 17 00:00:00 2001 From: "Yordan Karadzhov (VMware)" Date: Thu, 15 Apr 2021 21:18:51 +0300 Subject: tracing: Add "last_func_repeats" to struct trace_array The field is used to keep track of the consecutive (on the same CPU) calls of a single function. This information is needed in order to consolidate the function tracing record in the cases when a single function is called number of times. Link: https://lkml.kernel.org/r/20210415181854.147448-4-y.karadz@gmail.com Signed-off-by: Yordan Karadzhov (VMware) Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 1 + kernel/trace/trace.h | 12 ++++++++++++ 2 files changed, 13 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 507a30bf26e4..82833be07c1e 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -9104,6 +9104,7 @@ static int __remove_instance(struct trace_array *tr) ftrace_clear_pids(tr); ftrace_destroy_function_files(tr); tracefs_remove(tr->dir); + free_percpu(tr->last_func_repeats); free_trace_buffers(tr); for (i = 0; i < tr->nr_topts; i++) { diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 6a5b4c2a0fa7..a4f1b66049fd 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -262,6 +262,17 @@ struct cond_snapshot { cond_update_fn_t update; }; +/* + * struct trace_func_repeats - used to keep track of the consecutive + * (on the same CPU) calls of a single function. + */ +struct trace_func_repeats { + unsigned long ip; + unsigned long parent_ip; + unsigned long count; + u64 ts_last_call; +}; + /* * The trace array - an array of per-CPU trace arrays. This is the * highest level data structure that individual tracers deal with. @@ -358,6 +369,7 @@ struct trace_array { #ifdef CONFIG_TRACER_SNAPSHOT struct cond_snapshot *cond_snapshot; #endif + struct trace_func_repeats __percpu *last_func_repeats; }; enum { -- cgit v1.2.3-71-gd317 From c658797f1a70561205a224be0c8be64977ed64e8 Mon Sep 17 00:00:00 2001 From: "Yordan Karadzhov (VMware)" Date: Thu, 15 Apr 2021 21:18:52 +0300 Subject: tracing: Add method for recording "func_repeats" events This patch only provides the implementation of the method. Later we will used it in a combination with a new option for function tracing. Link: https://lkml.kernel.org/r/20210415181854.147448-5-y.karadz@gmail.com Signed-off-by: Yordan Karadzhov (VMware) Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 34 ++++++++++++++++++++++++++++++++++ kernel/trace/trace.h | 4 ++++ 2 files changed, 38 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 82833be07c1e..66a4ad93b5e9 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3117,6 +3117,40 @@ static void ftrace_trace_userstack(struct trace_array *tr, #endif /* CONFIG_STACKTRACE */ +static inline void +func_repeats_set_delta_ts(struct func_repeats_entry *entry, + unsigned long long delta) +{ + entry->bottom_delta_ts = delta & U32_MAX; + entry->top_delta_ts = (delta >> 32); +} + +void trace_last_func_repeats(struct trace_array *tr, + struct trace_func_repeats *last_info, + unsigned int trace_ctx) +{ + struct trace_buffer *buffer = tr->array_buffer.buffer; + struct func_repeats_entry *entry; + struct ring_buffer_event *event; + u64 delta; + + event = __trace_buffer_lock_reserve(buffer, TRACE_FUNC_REPEATS, + sizeof(*entry), trace_ctx); + if (!event) + return; + + delta = ring_buffer_event_time_stamp(buffer, event) - + last_info->ts_last_call; + + entry = ring_buffer_event_data(event); + entry->ip = last_info->ip; + entry->parent_ip = last_info->parent_ip; + entry->count = last_info->count; + func_repeats_set_delta_ts(entry, delta); + + __buffer_unlock_commit(buffer, event); +} + /* created for use with alloc_percpu */ struct trace_buffer_struct { int nesting; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index a4f1b66049fd..cd80d046c7a5 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -695,6 +695,10 @@ static inline void __trace_stack(struct trace_array *tr, unsigned int trace_ctx, } #endif /* CONFIG_STACKTRACE */ +void trace_last_func_repeats(struct trace_array *tr, + struct trace_func_repeats *last_info, + unsigned int trace_ctx); + extern u64 ftrace_now(int cpu); extern void trace_find_cmdline(int pid, char comm[]); -- cgit v1.2.3-71-gd317 From 4994891ebbb89b18903637dc1c8f27b42cb8b8b2 Mon Sep 17 00:00:00 2001 From: "Yordan Karadzhov (VMware)" Date: Thu, 15 Apr 2021 21:18:53 +0300 Subject: tracing: Unify the logic for function tracing options Currently the logic for dealing with the options for function tracing has two different implementations. One is used when we set the flags (in "static int func_set_flag()") and another used when we initialize the tracer (in "static int function_trace_init()"). Those two implementations are meant to do essentially the same thing and they are both not very convenient for adding new options. In this patch we add a helper function that provides a single implementation of the logic for dealing with the options and we make it such that new options can be easily added. Link: https://lkml.kernel.org/r/20210415181854.147448-6-y.karadz@gmail.com Signed-off-by: Yordan Karadzhov (VMware) Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_functions.c | 65 ++++++++++++++++++++++++------------------ 1 file changed, 38 insertions(+), 27 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index f93723ca66bc..f37f73a9b1b8 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -31,9 +31,12 @@ static struct tracer_flags func_flags; /* Our option */ enum { + TRACE_FUNC_NO_OPTS = 0x0, /* No flags set. */ TRACE_FUNC_OPT_STACK = 0x1, }; +#define TRACE_FUNC_OPT_MASK (TRACE_FUNC_OPT_STACK) + int ftrace_allocate_ftrace_ops(struct trace_array *tr) { struct ftrace_ops *ops; @@ -86,6 +89,18 @@ void ftrace_destroy_function_files(struct trace_array *tr) ftrace_free_ftrace_ops(tr); } +static ftrace_func_t select_trace_function(u32 flags_val) +{ + switch (flags_val & TRACE_FUNC_OPT_MASK) { + case TRACE_FUNC_NO_OPTS: + return function_trace_call; + case TRACE_FUNC_OPT_STACK: + return function_stack_trace_call; + default: + return NULL; + } +} + static int function_trace_init(struct trace_array *tr) { ftrace_func_t func; @@ -97,12 +112,9 @@ static int function_trace_init(struct trace_array *tr) if (!tr->ops) return -ENOMEM; - /* Currently only the global instance can do stack tracing */ - if (tr->flags & TRACE_ARRAY_FL_GLOBAL && - func_flags.val & TRACE_FUNC_OPT_STACK) - func = function_stack_trace_call; - else - func = function_trace_call; + func = select_trace_function(func_flags.val); + if (!func) + return -EINVAL; ftrace_init_array_ops(tr, func); @@ -213,7 +225,7 @@ static struct tracer_opt func_opts[] = { }; static struct tracer_flags func_flags = { - .val = 0, /* By default: all flags disabled */ + .val = TRACE_FUNC_NO_OPTS, /* By default: all flags disabled */ .opts = func_opts }; @@ -235,30 +247,29 @@ static struct tracer function_trace; static int func_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { - switch (bit) { - case TRACE_FUNC_OPT_STACK: - /* do nothing if already set */ - if (!!set == !!(func_flags.val & TRACE_FUNC_OPT_STACK)) - break; - - /* We can change this flag when not running. */ - if (tr->current_trace != &function_trace) - break; + ftrace_func_t func; + u32 new_flags; - unregister_ftrace_function(tr->ops); + /* Do nothing if already set. */ + if (!!set == !!(func_flags.val & bit)) + return 0; - if (set) { - tr->ops->func = function_stack_trace_call; - register_ftrace_function(tr->ops); - } else { - tr->ops->func = function_trace_call; - register_ftrace_function(tr->ops); - } + /* We can change this flag only when not running. */ + if (tr->current_trace != &function_trace) + return 0; - break; - default: + new_flags = (func_flags.val & ~bit) | (set ? bit : 0); + func = select_trace_function(new_flags); + if (!func) return -EINVAL; - } + + /* Check if there's anything to change. */ + if (tr->ops->func == func) + return 0; + + unregister_ftrace_function(tr->ops); + tr->ops->func = func; + register_ftrace_function(tr->ops); return 0; } -- cgit v1.2.3-71-gd317 From 22db095d57b51ff71aaa8ddba515180399f54334 Mon Sep 17 00:00:00 2001 From: "Yordan Karadzhov (VMware)" Date: Thu, 15 Apr 2021 21:18:54 +0300 Subject: tracing: Add "func_no_repeats" option for function tracing If the option is activated the function tracing record gets consolidated in the cases when a single function is called number of times consecutively. Instead of having an identical record for each call of the function we will record only the first call following by event showing the number of repeats. Link: https://lkml.kernel.org/r/20210415181854.147448-7-y.karadz@gmail.com Signed-off-by: Yordan Karadzhov (VMware) Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_functions.c | 162 ++++++++++++++++++++++++++++++++++++++++- 1 file changed, 159 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index f37f73a9b1b8..1f0e63f5d1f9 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -27,15 +27,27 @@ function_trace_call(unsigned long ip, unsigned long parent_ip, static void function_stack_trace_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs); +static void +function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs); +static void +function_stack_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, + struct ftrace_regs *fregs); static struct tracer_flags func_flags; /* Our option */ enum { - TRACE_FUNC_NO_OPTS = 0x0, /* No flags set. */ - TRACE_FUNC_OPT_STACK = 0x1, + + TRACE_FUNC_NO_OPTS = 0x0, /* No flags set. */ + TRACE_FUNC_OPT_STACK = 0x1, + TRACE_FUNC_OPT_NO_REPEATS = 0x2, + + /* Update this to next highest bit. */ + TRACE_FUNC_OPT_HIGHEST_BIT = 0x4 }; -#define TRACE_FUNC_OPT_MASK (TRACE_FUNC_OPT_STACK) +#define TRACE_FUNC_OPT_MASK (TRACE_FUNC_OPT_HIGHEST_BIT - 1) int ftrace_allocate_ftrace_ops(struct trace_array *tr) { @@ -96,11 +108,27 @@ static ftrace_func_t select_trace_function(u32 flags_val) return function_trace_call; case TRACE_FUNC_OPT_STACK: return function_stack_trace_call; + case TRACE_FUNC_OPT_NO_REPEATS: + return function_no_repeats_trace_call; + case TRACE_FUNC_OPT_STACK | TRACE_FUNC_OPT_NO_REPEATS: + return function_stack_no_repeats_trace_call; default: return NULL; } } +static bool handle_func_repeats(struct trace_array *tr, u32 flags_val) +{ + if (!tr->last_func_repeats && + (flags_val & TRACE_FUNC_OPT_NO_REPEATS)) { + tr->last_func_repeats = alloc_percpu(struct trace_func_repeats); + if (!tr->last_func_repeats) + return false; + } + + return true; +} + static int function_trace_init(struct trace_array *tr) { ftrace_func_t func; @@ -116,6 +144,9 @@ static int function_trace_init(struct trace_array *tr) if (!func) return -EINVAL; + if (!handle_func_repeats(tr, func_flags.val)) + return -ENOMEM; + ftrace_init_array_ops(tr, func); tr->array_buffer.cpu = raw_smp_processor_id(); @@ -217,10 +248,132 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip, local_irq_restore(flags); } +static inline bool is_repeat_check(struct trace_array *tr, + struct trace_func_repeats *last_info, + unsigned long ip, unsigned long parent_ip) +{ + if (last_info->ip == ip && + last_info->parent_ip == parent_ip && + last_info->count < U16_MAX) { + last_info->ts_last_call = + ring_buffer_time_stamp(tr->array_buffer.buffer); + last_info->count++; + return true; + } + + return false; +} + +static inline void process_repeats(struct trace_array *tr, + unsigned long ip, unsigned long parent_ip, + struct trace_func_repeats *last_info, + unsigned int trace_ctx) +{ + if (last_info->count) { + trace_last_func_repeats(tr, last_info, trace_ctx); + last_info->count = 0; + } + + last_info->ip = ip; + last_info->parent_ip = parent_ip; +} + +static void +function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, + struct ftrace_regs *fregs) +{ + struct trace_func_repeats *last_info; + struct trace_array *tr = op->private; + struct trace_array_cpu *data; + unsigned int trace_ctx; + unsigned long flags; + int bit; + int cpu; + + if (unlikely(!tr->function_enabled)) + return; + + bit = ftrace_test_recursion_trylock(ip, parent_ip); + if (bit < 0) + return; + + preempt_disable_notrace(); + + cpu = smp_processor_id(); + data = per_cpu_ptr(tr->array_buffer.data, cpu); + if (atomic_read(&data->disabled)) + goto out; + + /* + * An interrupt may happen at any place here. But as far as I can see, + * the only damage that this can cause is to mess up the repetition + * counter without valuable data being lost. + * TODO: think about a solution that is better than just hoping to be + * lucky. + */ + last_info = per_cpu_ptr(tr->last_func_repeats, cpu); + if (is_repeat_check(tr, last_info, ip, parent_ip)) + goto out; + + local_save_flags(flags); + trace_ctx = tracing_gen_ctx_flags(flags); + process_repeats(tr, ip, parent_ip, last_info, trace_ctx); + + trace_function(tr, ip, parent_ip, trace_ctx); + +out: + ftrace_test_recursion_unlock(bit); + preempt_enable_notrace(); +} + +static void +function_stack_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, + struct ftrace_regs *fregs) +{ + struct trace_func_repeats *last_info; + struct trace_array *tr = op->private; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu; + unsigned int trace_ctx; + + if (unlikely(!tr->function_enabled)) + return; + + /* + * Need to use raw, since this must be called before the + * recursive protection is performed. + */ + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = per_cpu_ptr(tr->array_buffer.data, cpu); + disabled = atomic_inc_return(&data->disabled); + + if (likely(disabled == 1)) { + last_info = per_cpu_ptr(tr->last_func_repeats, cpu); + if (is_repeat_check(tr, last_info, ip, parent_ip)) + goto out; + + trace_ctx = tracing_gen_ctx_flags(flags); + process_repeats(tr, ip, parent_ip, last_info, trace_ctx); + + trace_function(tr, ip, parent_ip, trace_ctx); + __trace_stack(tr, trace_ctx, STACK_SKIP); + } + + out: + atomic_dec(&data->disabled); + local_irq_restore(flags); +} + static struct tracer_opt func_opts[] = { #ifdef CONFIG_STACKTRACE { TRACER_OPT(func_stack_trace, TRACE_FUNC_OPT_STACK) }, #endif + { TRACER_OPT(func-no-repeats, TRACE_FUNC_OPT_NO_REPEATS) }, { } /* Always set a last empty entry */ }; @@ -267,6 +420,9 @@ func_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) if (tr->ops->func == func) return 0; + if (!handle_func_repeats(tr, new_flags)) + return -ENOMEM; + unregister_ftrace_function(tr->ops); tr->ops->func = func; register_ftrace_function(tr->ops); -- cgit v1.2.3-71-gd317 From e1db6338d6fa0d409e45cf20ab5aeaca704f68e7 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 15 Apr 2021 16:34:26 -0400 Subject: ftrace: Reuse the output of the function tracer for func_repeats The func_repeats event shows the output of the function tracer followed by a count of the number of repeats the previous function had made, as well as the timestamp of the last function that was repeated. The printing of the function should be the same as is for the function it is displaying. Reuse the code in trace_fn_trace() by making a helper function print_fn_trace() and use it for trace_func_repeats_print(). Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_output.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 3037f0c88f90..d0368a569bfa 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -845,6 +845,17 @@ enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags, return trace_handle_return(&iter->seq); } +static void print_fn_trace(struct trace_seq *s, unsigned long ip, + unsigned long parent_ip, int flags) +{ + seq_print_ip_sym(s, ip, flags); + + if ((flags & TRACE_ITER_PRINT_PARENT) && parent_ip) { + trace_seq_puts(s, " <-"); + seq_print_ip_sym(s, parent_ip, flags); + } +} + /* TRACE_FN */ static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags, struct trace_event *event) @@ -854,13 +865,7 @@ static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags, trace_assign_type(field, iter->ent); - seq_print_ip_sym(s, field->ip, flags); - - if ((flags & TRACE_ITER_PRINT_PARENT) && field->parent_ip) { - trace_seq_puts(s, " <-"); - seq_print_ip_sym(s, field->parent_ip, flags); - } - + print_fn_trace(s, field->ip, field->parent_ip, flags); trace_seq_putc(s, '\n'); return trace_handle_return(s); @@ -1408,9 +1413,7 @@ trace_func_repeats_print(struct trace_iterator *iter, int flags, trace_assign_type(field, iter->ent); - seq_print_ip_sym(s, field->ip, flags); - trace_seq_puts(s, " <-"); - seq_print_ip_sym(s, field->parent_ip, flags); + print_fn_trace(s, field->ip, field->parent_ip, flags); trace_seq_printf(s, " (repeats: %u, last_ts:", field->count); trace_print_time(s, iter, iter->ts - FUNC_REPEATS_GET_DELTA_TS(field)); -- cgit v1.2.3-71-gd317 From 42eb0d54c08a0331d6d295420f602237968d792b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 25 Mar 2021 09:22:09 +0100 Subject: fs: split receive_fd_replace from __receive_fd receive_fd_replace shares almost no code with the general case, so split it out. Also remove the "Bump the sock usage counts" comment from both copies, as that is now what __receive_sock actually does. [AV: ... and make the only user of receive_fd_replace() choose between it and receive_fd() according to what userland had passed to it in flags] Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/file.c | 39 +++++++++++++++++++-------------------- include/linux/file.h | 11 ++++------- kernel/seccomp.c | 17 ++++++++++++----- 3 files changed, 35 insertions(+), 32 deletions(-) (limited to 'kernel') diff --git a/fs/file.c b/fs/file.c index f3a4bac2cbe9..d8ccb95a7f41 100644 --- a/fs/file.c +++ b/fs/file.c @@ -1068,8 +1068,6 @@ out_unlock: /** * __receive_fd() - Install received file into file descriptor table - * - * @fd: fd to install into (if negative, a new fd will be allocated) * @file: struct file that was received from another process * @ufd: __user pointer to write new fd number to * @o_flags: the O_* flags to apply to the new fd entry @@ -1083,7 +1081,7 @@ out_unlock: * * Returns newly install fd or -ve on error. */ -int __receive_fd(int fd, struct file *file, int __user *ufd, unsigned int o_flags) +int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags) { int new_fd; int error; @@ -1092,32 +1090,33 @@ int __receive_fd(int fd, struct file *file, int __user *ufd, unsigned int o_flag if (error) return error; - if (fd < 0) { - new_fd = get_unused_fd_flags(o_flags); - if (new_fd < 0) - return new_fd; - } else { - new_fd = fd; - } + new_fd = get_unused_fd_flags(o_flags); + if (new_fd < 0) + return new_fd; if (ufd) { error = put_user(new_fd, ufd); if (error) { - if (fd < 0) - put_unused_fd(new_fd); + put_unused_fd(new_fd); return error; } } - if (fd < 0) { - fd_install(new_fd, get_file(file)); - } else { - error = replace_fd(new_fd, file, o_flags); - if (error) - return error; - } + fd_install(new_fd, get_file(file)); + __receive_sock(file); + return new_fd; +} - /* Bump the sock usage counts, if any. */ +int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags) +{ + int error; + + error = security_file_receive(file); + if (error) + return error; + error = replace_fd(new_fd, file, o_flags); + if (error) + return error; __receive_sock(file); return new_fd; } diff --git a/include/linux/file.h b/include/linux/file.h index 225982792fa2..2de2e4613d7b 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -92,23 +92,20 @@ extern void put_unused_fd(unsigned int fd); extern void fd_install(unsigned int fd, struct file *file); -extern int __receive_fd(int fd, struct file *file, int __user *ufd, +extern int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags); static inline int receive_fd_user(struct file *file, int __user *ufd, unsigned int o_flags) { if (ufd == NULL) return -EFAULT; - return __receive_fd(-1, file, ufd, o_flags); + return __receive_fd(file, ufd, o_flags); } static inline int receive_fd(struct file *file, unsigned int o_flags) { - return __receive_fd(-1, file, NULL, o_flags); -} -static inline int receive_fd_replace(int fd, struct file *file, unsigned int o_flags) -{ - return __receive_fd(fd, file, NULL, o_flags); + return __receive_fd(file, NULL, o_flags); } +int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags); extern void flush_delayed_fput(void); extern void __fput_sync(struct file *); diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 1d60fc2c9987..4fe19cecaa94 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -119,8 +119,11 @@ struct seccomp_kaddfd { int fd; unsigned int flags; - /* To only be set on reply */ - int ret; + union { + bool setfd; + /* To only be set on reply */ + int ret; + }; struct completion completion; struct list_head list; }; @@ -1069,7 +1072,11 @@ static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd) * that it has been handled. */ list_del_init(&addfd->list); - addfd->ret = receive_fd_replace(addfd->fd, addfd->file, addfd->flags); + if (!addfd->setfd) + addfd->ret = receive_fd(addfd->file, addfd->flags); + else + addfd->ret = receive_fd_replace(addfd->fd, addfd->file, + addfd->flags); complete(&addfd->completion); } @@ -1583,8 +1590,8 @@ static long seccomp_notify_addfd(struct seccomp_filter *filter, return -EBADF; kaddfd.flags = addfd.newfd_flags; - kaddfd.fd = (addfd.flags & SECCOMP_ADDFD_FLAG_SETFD) ? - addfd.newfd : -1; + kaddfd.setfd = addfd.flags & SECCOMP_ADDFD_FLAG_SETFD; + kaddfd.fd = addfd.newfd; init_completion(&kaddfd.completion); ret = mutex_lock_interruptible(&filter->notify_lock); -- cgit v1.2.3-71-gd317 From 95b079d8215b83b37fa59341fda92fcb9392f14a Mon Sep 17 00:00:00 2001 From: Claire Chang Date: Thu, 22 Apr 2021 16:14:53 +0800 Subject: swiotlb: Fix the type of index Fix the type of index from unsigned int to int since find_slots() might return -1. Fixes: 26a7e094783d ("swiotlb: refactor swiotlb_tbl_map_single") Reviewed-by: Christoph Hellwig Signed-off-by: Claire Chang Signed-off-by: Konrad Rzeszutek Wilk --- kernel/dma/swiotlb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 0a5b6f7e75bc..8635a57f88e9 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -499,7 +499,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, { struct io_tlb_mem *mem = io_tlb_default_mem; unsigned int offset = swiotlb_align_offset(dev, orig_addr); - unsigned int index, i; + unsigned int i; + int index; phys_addr_t tlb_addr; if (!mem) -- cgit v1.2.3-71-gd317 From 785e3c0a3a870e72dc530856136ab4c8dd207128 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 27 Apr 2021 11:32:07 -0400 Subject: tracing: Map all PIDs to command lines The default max PID is set by PID_MAX_DEFAULT, and the tracing infrastructure uses this number to map PIDs to the comm names of the tasks, such output of the trace can show names from the recorded PIDs in the ring buffer. This mapping is also exported to user space via the "saved_cmdlines" file in the tracefs directory. But currently the mapping expects the PIDs to be less than PID_MAX_DEFAULT, which is the default maximum and not the real maximum. Recently, systemd will increases the maximum value of a PID on the system, and when tasks are traced that have a PID higher than PID_MAX_DEFAULT, its comm is not recorded. This leads to the entire trace to have "<...>" as the comm name, which is pretty useless. Instead, keep the array mapping the size of PID_MAX_DEFAULT, but instead of just mapping the index to the comm, map a mask of the PID (PID_MAX_DEFAULT - 1) to the comm, and find the full PID from the map_cmdline_to_pid array (that already exists). This bug goes back to the beginning of ftrace, but hasn't been an issue until user space started increasing the maximum value of PIDs. Link: https://lkml.kernel.org/r/20210427113207.3c601884@gandalf.local.home Cc: stable@vger.kernel.org Fixes: bc0c38d139ec7 ("ftrace: latency tracer infrastructure") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace.c | 41 +++++++++++++++-------------------------- 1 file changed, 15 insertions(+), 26 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 66a4ad93b5e9..e28d08905124 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2390,14 +2390,13 @@ static void tracing_stop_tr(struct trace_array *tr) static int trace_save_cmdline(struct task_struct *tsk) { - unsigned pid, idx; + unsigned tpid, idx; /* treat recording of idle task as a success */ if (!tsk->pid) return 1; - if (unlikely(tsk->pid > PID_MAX_DEFAULT)) - return 0; + tpid = tsk->pid & (PID_MAX_DEFAULT - 1); /* * It's not the end of the world if we don't get @@ -2408,26 +2407,15 @@ static int trace_save_cmdline(struct task_struct *tsk) if (!arch_spin_trylock(&trace_cmdline_lock)) return 0; - idx = savedcmd->map_pid_to_cmdline[tsk->pid]; + idx = savedcmd->map_pid_to_cmdline[tpid]; if (idx == NO_CMDLINE_MAP) { idx = (savedcmd->cmdline_idx + 1) % savedcmd->cmdline_num; - /* - * Check whether the cmdline buffer at idx has a pid - * mapped. We are going to overwrite that entry so we - * need to clear the map_pid_to_cmdline. Otherwise we - * would read the new comm for the old pid. - */ - pid = savedcmd->map_cmdline_to_pid[idx]; - if (pid != NO_CMDLINE_MAP) - savedcmd->map_pid_to_cmdline[pid] = NO_CMDLINE_MAP; - - savedcmd->map_cmdline_to_pid[idx] = tsk->pid; - savedcmd->map_pid_to_cmdline[tsk->pid] = idx; - + savedcmd->map_pid_to_cmdline[tpid] = idx; savedcmd->cmdline_idx = idx; } + savedcmd->map_cmdline_to_pid[idx] = tsk->pid; set_cmdline(idx, tsk->comm); arch_spin_unlock(&trace_cmdline_lock); @@ -2438,6 +2426,7 @@ static int trace_save_cmdline(struct task_struct *tsk) static void __trace_find_cmdline(int pid, char comm[]) { unsigned map; + int tpid; if (!pid) { strcpy(comm, ""); @@ -2449,16 +2438,16 @@ static void __trace_find_cmdline(int pid, char comm[]) return; } - if (pid > PID_MAX_DEFAULT) { - strcpy(comm, "<...>"); - return; + tpid = pid & (PID_MAX_DEFAULT - 1); + map = savedcmd->map_pid_to_cmdline[tpid]; + if (map != NO_CMDLINE_MAP) { + tpid = savedcmd->map_cmdline_to_pid[map]; + if (tpid == pid) { + strlcpy(comm, get_saved_cmdlines(map), TASK_COMM_LEN); + return; + } } - - map = savedcmd->map_pid_to_cmdline[pid]; - if (map != NO_CMDLINE_MAP) - strlcpy(comm, get_saved_cmdlines(map), TASK_COMM_LEN); - else - strcpy(comm, "<...>"); + strcpy(comm, "<...>"); } void trace_find_cmdline(int pid, char comm[]) -- cgit v1.2.3-71-gd317 From dfc06b389a4f54e78c03abecd5b42ab6ea8d492a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 29 Apr 2021 08:28:59 +0200 Subject: swiotlb: don't override user specified size in swiotlb_adjust_size If the user already specified a swiotlb size on the command line, swiotlb_adjust_size should not overwrite it. Fixes: 2cbc2776efe4 ("swiotlb: remove swiotlb_nr_tbl") Reported-by: Tom Lendacky Tested-by: Tom Lendacky Signed-off-by: Christoph Hellwig Signed-off-by: Konrad Rzeszutek Wilk --- kernel/dma/swiotlb.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 8635a57f88e9..8ca7d505d61c 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -118,6 +118,8 @@ void __init swiotlb_adjust_size(unsigned long size) * architectures such as those supporting memory encryption to * adjust/expand SWIOTLB size for their use. */ + if (default_nslabs != IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT) + return; size = ALIGN(size, IO_TLB_SIZE); default_nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE); pr_info("SWIOTLB bounce buffer size adjusted to %luMB", size >> 20); -- cgit v1.2.3-71-gd317 From aafe104aa9096827a429bc1358f8260ee565b7cc Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 30 Apr 2021 12:17:58 -0400 Subject: tracing: Restructure trace_clock_global() to never block It was reported that a fix to the ring buffer recursion detection would cause a hung machine when performing suspend / resume testing. The following backtrace was extracted from debugging that case: Call Trace: trace_clock_global+0x91/0xa0 __rb_reserve_next+0x237/0x460 ring_buffer_lock_reserve+0x12a/0x3f0 trace_buffer_lock_reserve+0x10/0x50 __trace_graph_return+0x1f/0x80 trace_graph_return+0xb7/0xf0 ? trace_clock_global+0x91/0xa0 ftrace_return_to_handler+0x8b/0xf0 ? pv_hash+0xa0/0xa0 return_to_handler+0x15/0x30 ? ftrace_graph_caller+0xa0/0xa0 ? trace_clock_global+0x91/0xa0 ? __rb_reserve_next+0x237/0x460 ? ring_buffer_lock_reserve+0x12a/0x3f0 ? trace_event_buffer_lock_reserve+0x3c/0x120 ? trace_event_buffer_reserve+0x6b/0xc0 ? trace_event_raw_event_device_pm_callback_start+0x125/0x2d0 ? dpm_run_callback+0x3b/0xc0 ? pm_ops_is_empty+0x50/0x50 ? platform_get_irq_byname_optional+0x90/0x90 ? trace_device_pm_callback_start+0x82/0xd0 ? dpm_run_callback+0x49/0xc0 With the following RIP: RIP: 0010:native_queued_spin_lock_slowpath+0x69/0x200 Since the fix to the recursion detection would allow a single recursion to happen while tracing, this lead to the trace_clock_global() taking a spin lock and then trying to take it again: ring_buffer_lock_reserve() { trace_clock_global() { arch_spin_lock() { queued_spin_lock_slowpath() { /* lock taken */ (something else gets traced by function graph tracer) ring_buffer_lock_reserve() { trace_clock_global() { arch_spin_lock() { queued_spin_lock_slowpath() { /* DEAD LOCK! */ Tracing should *never* block, as it can lead to strange lockups like the above. Restructure the trace_clock_global() code to instead of simply taking a lock to update the recorded "prev_time" simply use it, as two events happening on two different CPUs that calls this at the same time, really doesn't matter which one goes first. Use a trylock to grab the lock for updating the prev_time, and if it fails, simply try again the next time. If it failed to be taken, that means something else is already updating it. Link: https://lkml.kernel.org/r/20210430121758.650b6e8a@gandalf.local.home Cc: stable@vger.kernel.org Tested-by: Konstantin Kharlamov Tested-by: Todd Brandt Fixes: b02414c8f045 ("ring-buffer: Fix recursion protection transitions between interrupt context") # started showing the problem Fixes: 14131f2f98ac3 ("tracing: implement trace_clock_*() APIs") # where the bug happened Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=212761 Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_clock.c | 44 ++++++++++++++++++++++++++++++-------------- 1 file changed, 30 insertions(+), 14 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c index aaf6793ededa..c1637f90c8a3 100644 --- a/kernel/trace/trace_clock.c +++ b/kernel/trace/trace_clock.c @@ -95,33 +95,49 @@ u64 notrace trace_clock_global(void) { unsigned long flags; int this_cpu; - u64 now; + u64 now, prev_time; raw_local_irq_save(flags); this_cpu = raw_smp_processor_id(); - now = sched_clock_cpu(this_cpu); + /* - * If in an NMI context then dont risk lockups and return the - * cpu_clock() time: + * The global clock "guarantees" that the events are ordered + * between CPUs. But if two events on two different CPUS call + * trace_clock_global at roughly the same time, it really does + * not matter which one gets the earlier time. Just make sure + * that the same CPU will always show a monotonic clock. + * + * Use a read memory barrier to get the latest written + * time that was recorded. */ - if (unlikely(in_nmi())) - goto out; + smp_rmb(); + prev_time = READ_ONCE(trace_clock_struct.prev_time); + now = sched_clock_cpu(this_cpu); - arch_spin_lock(&trace_clock_struct.lock); + /* Make sure that now is always greater than prev_time */ + if ((s64)(now - prev_time) < 0) + now = prev_time + 1; /* - * TODO: if this happens often then maybe we should reset - * my_scd->clock to prev_time+1, to make sure - * we start ticking with the local clock from now on? + * If in an NMI context then dont risk lockups and simply return + * the current time. */ - if ((s64)(now - trace_clock_struct.prev_time) < 0) - now = trace_clock_struct.prev_time + 1; + if (unlikely(in_nmi())) + goto out; - trace_clock_struct.prev_time = now; + /* Tracing can cause strange recursion, always use a try lock */ + if (arch_spin_trylock(&trace_clock_struct.lock)) { + /* Reread prev_time in case it was already updated */ + prev_time = READ_ONCE(trace_clock_struct.prev_time); + if ((s64)(now - prev_time) < 0) + now = prev_time + 1; - arch_spin_unlock(&trace_clock_struct.lock); + trace_clock_struct.prev_time = now; + /* The unlock acts as the wmb for the above rmb */ + arch_spin_unlock(&trace_clock_struct.lock); + } out: raw_local_irq_restore(flags); -- cgit v1.2.3-71-gd317 From 8c9af478c06bb1ab1422f90d8ecbc53defd44bc3 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Wed, 5 May 2021 10:38:24 -0400 Subject: ftrace: Handle commands when closing set_ftrace_filter file # echo switch_mm:traceoff > /sys/kernel/tracing/set_ftrace_filter will cause switch_mm to stop tracing by the traceoff command. # echo -n switch_mm:traceoff > /sys/kernel/tracing/set_ftrace_filter does nothing. The reason is that the parsing in the write function only processes commands if it finished parsing (there is white space written after the command). That's to handle: write(fd, "switch_mm:", 10); write(fd, "traceoff", 8); cases, where the command is broken over multiple writes. The problem is if the file descriptor is closed, then the write call is not processed, and the command needs to be processed in the release code. The release code can handle matching of functions, but does not handle commands. Cc: stable@vger.kernel.org Fixes: eda1e32855656 ("tracing: handle broken names in ftrace filter") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 057e962ca5ce..c57508445faa 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5591,7 +5591,10 @@ int ftrace_regex_release(struct inode *inode, struct file *file) parser = &iter->parser; if (trace_parser_loaded(parser)) { - ftrace_match_records(iter->hash, parser->buffer, parser->idx); + int enable = !(iter->flags & FTRACE_ITER_NOTRACE); + + ftrace_process_regex(iter, parser->buffer, + parser->idx, enable); } trace_parser_put(parser); -- cgit v1.2.3-71-gd317 From ef4984384172e93cc95e0e8cd102536d67e8a787 Mon Sep 17 00:00:00 2001 From: Pintu Kumar Date: Tue, 4 May 2021 18:36:48 -0700 Subject: mm/compaction: remove unused variable sysctl_compact_memory The sysctl_compact_memory is mostly unused in mm/compaction.c It just acts as a place holder for sysctl to store .data. But the .data itself is not needed here. So we can get ride of this variable completely and make .data as NULL. This will also eliminate the extern declaration from header file. No functionality is broken or changed this way. Link: https://lkml.kernel.org/r/1614852224-14671-1-git-send-email-pintu@codeaurora.org Signed-off-by: Pintu Kumar Signed-off-by: Pintu Agarwal Reviewed-by: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 1 - kernel/sysctl.c | 2 +- mm/compaction.c | 3 --- 3 files changed, 1 insertion(+), 5 deletions(-) (limited to 'kernel') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index ed4070ed41ef..4221888bdcd6 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -81,7 +81,6 @@ static inline unsigned long compact_gap(unsigned int order) } #ifdef CONFIG_COMPACTION -extern int sysctl_compact_memory; extern unsigned int sysctl_compaction_proactiveness; extern int sysctl_compaction_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index f91d327273c1..14edf84cc571 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2830,7 +2830,7 @@ static struct ctl_table vm_table[] = { #ifdef CONFIG_COMPACTION { .procname = "compact_memory", - .data = &sysctl_compact_memory, + .data = NULL, .maxlen = sizeof(int), .mode = 0200, .proc_handler = sysctl_compaction_handler, diff --git a/mm/compaction.c b/mm/compaction.c index 335862f1661c..027eb794e747 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -2692,9 +2692,6 @@ static void compact_nodes(void) compact_node(nid); } -/* The written value is actually unused, all memory is compacted */ -int sysctl_compact_memory; - /* * Tunable for proactive compaction. It determines how * aggressively the kernel should compact memory in the -- cgit v1.2.3-71-gd317 From 8ba9d40b6b2bf62377fd6fce25e9997e42b0317a Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 6 May 2021 18:02:36 -0700 Subject: kernel/async.c: fix pr_debug statement An async_func_t returns void - any errors encountered it has to stash somewhere for consumers to discover later. Link: https://lkml.kernel.org/r/20210226124355.2503524-1-linux@rasmusvillemoes.dk Signed-off-by: Rasmus Villemoes Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/async.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/async.c b/kernel/async.c index 33258e6e20f8..45a867b8644a 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -124,7 +124,7 @@ static void async_run_entry_fn(struct work_struct *work) if (initcall_debug && system_state < SYSTEM_RUNNING) { rettime = ktime_get(); delta = ktime_sub(rettime, calltime); - pr_debug("initcall %lli_%pS returned 0 after %lld usecs\n", + pr_debug("initcall %lli_%pS returned after %lld usecs\n", (long long)entry->cookie, entry->func, (long long)ktime_to_ns(delta) >> 10); -- cgit v1.2.3-71-gd317 From 32c93976ac2ee7ecb4b09cc032efe1445d37bd7e Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 6 May 2021 18:02:39 -0700 Subject: kernel/cred.c: make init_groups static init_groups is declared in both cred.h and init_task.h, but it is not actually referenced anywhere outside of cred.c where it is defined. So make it static and remove the declarations. Link: https://lkml.kernel.org/r/20210310220102.2484201-1-linux@rasmusvillemoes.dk Signed-off-by: Rasmus Villemoes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cred.h | 1 - include/linux/init_task.h | 1 - kernel/cred.c | 2 +- 3 files changed, 1 insertion(+), 3 deletions(-) (limited to 'kernel') diff --git a/include/linux/cred.h b/include/linux/cred.h index ac0e5f97d7d8..14971322e1a0 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -53,7 +53,6 @@ do { \ groups_free(group_info); \ } while (0) -extern struct group_info init_groups; #ifdef CONFIG_MULTIUSER extern struct group_info *groups_alloc(int); extern void groups_free(struct group_info *); diff --git a/include/linux/init_task.h b/include/linux/init_task.h index b2412b4d4c20..40fc5813cf93 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -25,7 +25,6 @@ extern struct files_struct init_files; extern struct fs_struct init_fs; extern struct nsproxy init_nsproxy; -extern struct group_info init_groups; extern struct cred init_cred; #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE diff --git a/kernel/cred.c b/kernel/cred.c index 421b1149c651..e1d274cd741b 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -33,7 +33,7 @@ do { \ static struct kmem_cache *cred_jar; /* init to 2 - one for init_task, one to ensure it is never freed */ -struct group_info init_groups = { .usage = ATOMIC_INIT(2) }; +static struct group_info init_groups = { .usage = ATOMIC_INIT(2) }; /* * The initial credentials for the initial task -- cgit v1.2.3-71-gd317 From 5449162ac001a926ad8884882b071601df5edb44 Mon Sep 17 00:00:00 2001 From: Jim Newsome Date: Thu, 6 May 2021 18:04:22 -0700 Subject: do_wait: make PIDTYPE_PID case O(1) instead of O(n) Add a special-case when waiting on a pid (via waitpid, waitid, wait4, etc) to avoid doing an O(n) scan of children and tracees, and instead do an O(1) lookup. This improves performance when waiting on a pid from a thread group with many children and/or tracees. Time to fork and then call waitpid on the child, from a task that already has N children [1]: N | Before | After -----|---------|------ 1 | 74 us | 74 us 20 | 72 us | 75 us 100 | 83 us | 77 us 500 | 99 us | 74 us 1000 | 179 us | 75 us 5000 | 804 us | 79 us 8000 | 1268 us | 78 us [1]: https://lkml.org/lkml/2021/3/12/1567 This can make a substantial performance improvement for applications with a thread that has many children or tracees and frequently needs to wait on them. Tools that use ptrace to intercept syscalls for a large number of processes are likely to fall into this category. In particular this patch was developed while building a ptrace-based second generation of the Shadow emulator [2], for which it allows us to avoid quadratic scaling (without having to use a workaround that introduces a ~40% performance penalty) [3]. Other examples of tools that fall into this category which this patch may help include User Mode Linux [4] and DetTrace [5]. [2]: https://shadow.github.io/ [3]: https://github.com/shadow/shadow/issues/1134#issuecomment-798992292 [4]: https://en.wikipedia.org/wiki/User-mode_Linux [5]: https://github.com/dettrace/dettrace Link: https://lkml.kernel.org/r/20210314231544.9379-1-jnewsome@torproject.org Signed-off-by: James Newsome Reviewed-by: Oleg Nesterov Cc: "Eric W . Biederman" Cc: Christian Brauner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 67 ++++++++++++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 57 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/kernel/exit.c b/kernel/exit.c index 0596526ed9ea..fd1c04193e18 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1440,9 +1440,48 @@ void __wake_up_parent(struct task_struct *p, struct task_struct *parent) TASK_INTERRUPTIBLE, p); } +static bool is_effectively_child(struct wait_opts *wo, bool ptrace, + struct task_struct *target) +{ + struct task_struct *parent = + !ptrace ? target->real_parent : target->parent; + + return current == parent || (!(wo->wo_flags & __WNOTHREAD) && + same_thread_group(current, parent)); +} + +/* + * Optimization for waiting on PIDTYPE_PID. No need to iterate through child + * and tracee lists to find the target task. + */ +static int do_wait_pid(struct wait_opts *wo) +{ + bool ptrace; + struct task_struct *target; + int retval; + + ptrace = false; + target = pid_task(wo->wo_pid, PIDTYPE_TGID); + if (target && is_effectively_child(wo, ptrace, target)) { + retval = wait_consider_task(wo, ptrace, target); + if (retval) + return retval; + } + + ptrace = true; + target = pid_task(wo->wo_pid, PIDTYPE_PID); + if (target && target->ptrace && + is_effectively_child(wo, ptrace, target)) { + retval = wait_consider_task(wo, ptrace, target); + if (retval) + return retval; + } + + return 0; +} + static long do_wait(struct wait_opts *wo) { - struct task_struct *tsk; int retval; trace_sched_process_wait(wo->wo_pid); @@ -1464,19 +1503,27 @@ repeat: set_current_state(TASK_INTERRUPTIBLE); read_lock(&tasklist_lock); - tsk = current; - do { - retval = do_wait_thread(wo, tsk); - if (retval) - goto end; - retval = ptrace_do_wait(wo, tsk); + if (wo->wo_type == PIDTYPE_PID) { + retval = do_wait_pid(wo); if (retval) goto end; + } else { + struct task_struct *tsk = current; + + do { + retval = do_wait_thread(wo, tsk); + if (retval) + goto end; - if (wo->wo_flags & __WNOTHREAD) - break; - } while_each_thread(current, tsk); + retval = ptrace_do_wait(wo, tsk); + if (retval) + goto end; + + if (wo->wo_flags & __WNOTHREAD) + break; + } while_each_thread(current, tsk); + } read_unlock(&tasklist_lock); notask: -- cgit v1.2.3-71-gd317 From a6895399380ab58d9efd0a0bec2fcb98d77e20bd Mon Sep 17 00:00:00 2001 From: Rolf Eike Beer Date: Thu, 6 May 2021 18:04:25 -0700 Subject: kernel/fork.c: simplify copy_mm() All this can happen without a single goto. Link: https://lkml.kernel.org/r/2072685.XptgVkyDqn@devpool47 Signed-off-by: Rolf Eike Beer Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 15 ++++----------- 1 file changed, 4 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 771e0ea90499..784f7ca7c17e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1396,7 +1396,6 @@ fail_nomem: static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) { struct mm_struct *mm, *oldmm; - int retval; tsk->min_flt = tsk->maj_flt = 0; tsk->nvcsw = tsk->nivcsw = 0; @@ -1423,21 +1422,15 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) if (clone_flags & CLONE_VM) { mmget(oldmm); mm = oldmm; - goto good_mm; + } else { + mm = dup_mm(tsk, current->mm); + if (!mm) + return -ENOMEM; } - retval = -ENOMEM; - mm = dup_mm(tsk, current->mm); - if (!mm) - goto fail_nomem; - -good_mm: tsk->mm = mm; tsk->active_mm = mm; return 0; - -fail_nomem: - return retval; } static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) -- cgit v1.2.3-71-gd317 From a8ca6b1388a91c79dad257a7cc0bc14c009312fe Mon Sep 17 00:00:00 2001 From: Xiaofeng Cao Date: Thu, 6 May 2021 18:04:28 -0700 Subject: kernel/fork.c: fix typos change 'ancestoral' to 'ancestral' change 'reuseable' to 'reusable' delete 'do' grammatically Link: https://lkml.kernel.org/r/20210317082031.11692-1-caoxiaofeng@yulong.com Signed-off-by: Xiaofeng Cao Reviewed-by: Christian Brauner Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 784f7ca7c17e..dc06afd725cb 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1145,7 +1145,7 @@ void mmput_async(struct mm_struct *mm) * invocations: in mmput() nobody alive left, in execve task is single * threaded. sys_prctl(PR_SET_MM_MAP/EXE_FILE) also needs to set the * mm->exe_file, but does so without using set_mm_exe_file() in order - * to do avoid the need for any locks. + * to avoid the need for any locks. */ void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { @@ -1736,7 +1736,7 @@ static int pidfd_release(struct inode *inode, struct file *file) * /proc//status where Pid and NSpid are always shown relative to * the pid namespace of the procfs instance. The difference becomes * obvious when sending around a pidfd between pid namespaces from a - * different branch of the tree, i.e. where no ancestoral relation is + * different branch of the tree, i.e. where no ancestral relation is * present between the pid namespaces: * - create two new pid namespaces ns1 and ns2 in the initial pid * namespace (also take care to create new mount namespaces in the @@ -2728,8 +2728,8 @@ static bool clone3_args_valid(struct kernel_clone_args *kargs) return false; /* - * - make the CLONE_DETACHED bit reuseable for clone3 - * - make the CSIGNAL bits reuseable for clone3 + * - make the CLONE_DETACHED bit reusable for clone3 + * - make the CSIGNAL bits reusable for clone3 */ if (kargs->flags & (CLONE_DETACHED | CSIGNAL)) return false; -- cgit v1.2.3-71-gd317 From a119b4e5186c283ee13850b65004de6d746a81be Mon Sep 17 00:00:00 2001 From: Joe LeVeque Date: Thu, 6 May 2021 18:04:35 -0700 Subject: kexec: Add kexec reboot string The purpose is to notify the kernel module for fast reboot. Upstream a patch from the SONiC network operating system [1]. [1]: https://github.com/Azure/sonic-linux-kernel/pull/46 Link: https://lkml.kernel.org/r/20210304124626.13927-1-pmenzel@molgen.mpg.de Signed-off-by: Joe LeVeque Signed-off-by: Paul Menzel Acked-by: Baoquan He Cc: Guohan Lu Cc: Joe LeVeque Cc: Paul Menzel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/kexec_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index a0b6780740c8..f04d04d1b855 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -1165,7 +1165,7 @@ int kernel_kexec(void) #endif { kexec_in_progress = true; - kernel_restart_prepare(NULL); + kernel_restart_prepare("kexec reboot"); migrate_to_reboot_cpu(); /* -- cgit v1.2.3-71-gd317 From 31d82c2c787d5cf65fedd35ebbc0c1bd95c1a679 Mon Sep 17 00:00:00 2001 From: Jia-Ju Bai Date: Thu, 6 May 2021 18:04:38 -0700 Subject: kernel: kexec_file: fix error return code of kexec_calculate_store_digests() When vzalloc() returns NULL to sha_regions, no error return code of kexec_calculate_store_digests() is assigned. To fix this bug, ret is assigned with -ENOMEM in this case. Link: https://lkml.kernel.org/r/20210309083904.24321-1-baijiaju1990@gmail.com Fixes: a43cac0d9dc2 ("kexec: split kexec_file syscall code to kexec_file.c") Signed-off-by: Jia-Ju Bai Reported-by: TOTE Robot Acked-by: Baoquan He Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/kexec_file.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 5c3447cf7ad5..33400ff051a8 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -740,8 +740,10 @@ static int kexec_calculate_store_digests(struct kimage *image) sha_region_sz = KEXEC_SEGMENT_MAX * sizeof(struct kexec_sha_region); sha_regions = vzalloc(sha_region_sz); - if (!sha_regions) + if (!sha_regions) { + ret = -ENOMEM; goto out_free_desc; + } desc->tfm = tfm; -- cgit v1.2.3-71-gd317 From b2075dbb15d7ae952aeb01331198f4dc45a7e46a Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Thu, 6 May 2021 18:04:41 -0700 Subject: kexec: dump kmessage before machine_kexec kmsg_dump(KMSG_DUMP_SHUTDOWN) is called before machine_restart(), machine_halt(), and machine_power_off(). The only one that is missing is machine_kexec(). The dmesg output that it contains can be used to study the shutdown performance of both kernel and systemd during kexec reboot. Here is example of dmesg data collected after kexec: root@dplat-cp22:~# cat /sys/fs/pstore/dmesg-ramoops-0 | tail ... [ 70.914592] psci: CPU3 killed (polled 0 ms) [ 70.915705] CPU4: shutdown [ 70.916643] psci: CPU4 killed (polled 4 ms) [ 70.917715] CPU5: shutdown [ 70.918725] psci: CPU5 killed (polled 0 ms) [ 70.919704] CPU6: shutdown [ 70.920726] psci: CPU6 killed (polled 4 ms) [ 70.921642] CPU7: shutdown [ 70.922650] psci: CPU7 killed (polled 0 ms) Link: https://lkml.kernel.org/r/20210319192326.146000-2-pasha.tatashin@soleen.com Signed-off-by: Pavel Tatashin Reviewed-by: Kees Cook Reviewed-by: Petr Mladek Reviewed-by: Bhupesh Sharma Acked-by: Baoquan He Reviewed-by: Tyler Hicks Cc: James Morris Cc: Sasha Levin Cc: Eric W. Biederman Cc: Anton Vorontsov Cc: Colin Cross Cc: Tony Luck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/kexec_core.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index f04d04d1b855..f099baee3578 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include @@ -1179,6 +1180,7 @@ int kernel_kexec(void) machine_shutdown(); } + kmsg_dump(KMSG_DUMP_SHUTDOWN); machine_kexec(kexec_image); #ifdef CONFIG_KEXEC_JUMP -- cgit v1.2.3-71-gd317 From 7a1d55b987dfcbddecdb67eecc76fe555d4348ba Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 6 May 2021 18:04:45 -0700 Subject: gcov: combine common code There's a lot of duplicated code between gcc and clang implementations, move it over to fs.c to simplify the code, there's no reason to believe that for small data like this one would not just implement the simple convert_to_gcda() function. Link: https://lkml.kernel.org/r/20210315235453.e3fbb86e99a0.I08a3ee6dbe47ea3e8024956083f162884a958e40@changeid Signed-off-by: Johannes Berg Acked-by: Peter Oberparleiter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/gcov/base.c | 49 +++++++++++++++ kernel/gcov/clang.c | 167 +------------------------------------------------- kernel/gcov/fs.c | 116 +++++++++++++++++++++++++++++++++++ kernel/gcov/gcc_4_7.c | 167 +------------------------------------------------- kernel/gcov/gcov.h | 14 ++--- 5 files changed, 171 insertions(+), 342 deletions(-) (limited to 'kernel') diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c index 0ffe9f194080..073a3738c5e6 100644 --- a/kernel/gcov/base.c +++ b/kernel/gcov/base.c @@ -49,6 +49,55 @@ void gcov_enable_events(void) mutex_unlock(&gcov_lock); } +/** + * store_gcov_u32 - store 32 bit number in gcov format to buffer + * @buffer: target buffer or NULL + * @off: offset into the buffer + * @v: value to be stored + * + * Number format defined by gcc: numbers are recorded in the 32 bit + * unsigned binary form of the endianness of the machine generating the + * file. Returns the number of bytes stored. If @buffer is %NULL, doesn't + * store anything. + */ +size_t store_gcov_u32(void *buffer, size_t off, u32 v) +{ + u32 *data; + + if (buffer) { + data = buffer + off; + *data = v; + } + + return sizeof(*data); +} + +/** + * store_gcov_u64 - store 64 bit number in gcov format to buffer + * @buffer: target buffer or NULL + * @off: offset into the buffer + * @v: value to be stored + * + * Number format defined by gcc: numbers are recorded in the 32 bit + * unsigned binary form of the endianness of the machine generating the + * file. 64 bit numbers are stored as two 32 bit numbers, the low part + * first. Returns the number of bytes stored. If @buffer is %NULL, doesn't store + * anything. + */ +size_t store_gcov_u64(void *buffer, size_t off, u64 v) +{ + u32 *data; + + if (buffer) { + data = buffer + off; + + data[0] = (v & 0xffffffffUL); + data[1] = (v >> 32); + } + + return sizeof(*data) * 2; +} + #ifdef CONFIG_MODULES /* Update list and generate events when modules are unloaded. */ static int gcov_module_notifier(struct notifier_block *nb, unsigned long event, diff --git a/kernel/gcov/clang.c b/kernel/gcov/clang.c index c466c7fbdece..1741c65b4fb2 100644 --- a/kernel/gcov/clang.c +++ b/kernel/gcov/clang.c @@ -48,7 +48,6 @@ #include #include #include -#include #include #include #include "gcov.h" @@ -449,71 +448,6 @@ void gcov_info_free(struct gcov_info *info) } #endif -#define ITER_STRIDE PAGE_SIZE - -/** - * struct gcov_iterator - specifies current file position in logical records - * @info: associated profiling data - * @buffer: buffer containing file data - * @size: size of buffer - * @pos: current position in file - */ -struct gcov_iterator { - struct gcov_info *info; - void *buffer; - size_t size; - loff_t pos; -}; - -/** - * store_gcov_u32 - store 32 bit number in gcov format to buffer - * @buffer: target buffer or NULL - * @off: offset into the buffer - * @v: value to be stored - * - * Number format defined by gcc: numbers are recorded in the 32 bit - * unsigned binary form of the endianness of the machine generating the - * file. Returns the number of bytes stored. If @buffer is %NULL, doesn't - * store anything. - */ -static size_t store_gcov_u32(void *buffer, size_t off, u32 v) -{ - u32 *data; - - if (buffer) { - data = buffer + off; - *data = v; - } - - return sizeof(*data); -} - -/** - * store_gcov_u64 - store 64 bit number in gcov format to buffer - * @buffer: target buffer or NULL - * @off: offset into the buffer - * @v: value to be stored - * - * Number format defined by gcc: numbers are recorded in the 32 bit - * unsigned binary form of the endianness of the machine generating the - * file. 64 bit numbers are stored as two 32 bit numbers, the low part - * first. Returns the number of bytes stored. If @buffer is %NULL, doesn't store - * anything. - */ -static size_t store_gcov_u64(void *buffer, size_t off, u64 v) -{ - u32 *data; - - if (buffer) { - data = buffer + off; - - data[0] = (v & 0xffffffffUL); - data[1] = (v >> 32); - } - - return sizeof(*data) * 2; -} - /** * convert_to_gcda - convert profiling data set to gcda file format * @buffer: the buffer to store file data or %NULL if no data should be stored @@ -521,7 +455,7 @@ static size_t store_gcov_u64(void *buffer, size_t off, u64 v) * * Returns the number of bytes that were/would have been stored into the buffer. */ -static size_t convert_to_gcda(char *buffer, struct gcov_info *info) +size_t convert_to_gcda(char *buffer, struct gcov_info *info) { struct gcov_fn_info *fi_ptr; size_t pos = 0; @@ -558,102 +492,3 @@ static size_t convert_to_gcda(char *buffer, struct gcov_info *info) return pos; } - -/** - * gcov_iter_new - allocate and initialize profiling data iterator - * @info: profiling data set to be iterated - * - * Return file iterator on success, %NULL otherwise. - */ -struct gcov_iterator *gcov_iter_new(struct gcov_info *info) -{ - struct gcov_iterator *iter; - - iter = kzalloc(sizeof(struct gcov_iterator), GFP_KERNEL); - if (!iter) - goto err_free; - - iter->info = info; - /* Dry-run to get the actual buffer size. */ - iter->size = convert_to_gcda(NULL, info); - iter->buffer = vmalloc(iter->size); - if (!iter->buffer) - goto err_free; - - convert_to_gcda(iter->buffer, info); - - return iter; - -err_free: - kfree(iter); - return NULL; -} - - -/** - * gcov_iter_get_info - return profiling data set for given file iterator - * @iter: file iterator - */ -void gcov_iter_free(struct gcov_iterator *iter) -{ - vfree(iter->buffer); - kfree(iter); -} - -/** - * gcov_iter_get_info - return profiling data set for given file iterator - * @iter: file iterator - */ -struct gcov_info *gcov_iter_get_info(struct gcov_iterator *iter) -{ - return iter->info; -} - -/** - * gcov_iter_start - reset file iterator to starting position - * @iter: file iterator - */ -void gcov_iter_start(struct gcov_iterator *iter) -{ - iter->pos = 0; -} - -/** - * gcov_iter_next - advance file iterator to next logical record - * @iter: file iterator - * - * Return zero if new position is valid, non-zero if iterator has reached end. - */ -int gcov_iter_next(struct gcov_iterator *iter) -{ - if (iter->pos < iter->size) - iter->pos += ITER_STRIDE; - - if (iter->pos >= iter->size) - return -EINVAL; - - return 0; -} - -/** - * gcov_iter_write - write data for current pos to seq_file - * @iter: file iterator - * @seq: seq_file handle - * - * Return zero on success, non-zero otherwise. - */ -int gcov_iter_write(struct gcov_iterator *iter, struct seq_file *seq) -{ - size_t len; - - if (iter->pos >= iter->size) - return -EINVAL; - - len = ITER_STRIDE; - if (iter->pos + len > iter->size) - len = iter->size - iter->pos; - - seq_write(seq, iter->buffer + iter->pos, len); - - return 0; -} diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c index 82babf5aa077..2d29e1d1225d 100644 --- a/kernel/gcov/fs.c +++ b/kernel/gcov/fs.c @@ -26,6 +26,7 @@ #include #include #include +#include #include "gcov.h" /** @@ -85,6 +86,121 @@ static int __init gcov_persist_setup(char *str) } __setup("gcov_persist=", gcov_persist_setup); +#define ITER_STRIDE PAGE_SIZE + +/** + * struct gcov_iterator - specifies current file position in logical records + * @info: associated profiling data + * @buffer: buffer containing file data + * @size: size of buffer + * @pos: current position in file + */ +struct gcov_iterator { + struct gcov_info *info; + void *buffer; + size_t size; + loff_t pos; +}; + +/** + * gcov_iter_new - allocate and initialize profiling data iterator + * @info: profiling data set to be iterated + * + * Return file iterator on success, %NULL otherwise. + */ +static struct gcov_iterator *gcov_iter_new(struct gcov_info *info) +{ + struct gcov_iterator *iter; + + iter = kzalloc(sizeof(struct gcov_iterator), GFP_KERNEL); + if (!iter) + goto err_free; + + iter->info = info; + /* Dry-run to get the actual buffer size. */ + iter->size = convert_to_gcda(NULL, info); + iter->buffer = vmalloc(iter->size); + if (!iter->buffer) + goto err_free; + + convert_to_gcda(iter->buffer, info); + + return iter; + +err_free: + kfree(iter); + return NULL; +} + + +/** + * gcov_iter_free - free iterator data + * @iter: file iterator + */ +static void gcov_iter_free(struct gcov_iterator *iter) +{ + vfree(iter->buffer); + kfree(iter); +} + +/** + * gcov_iter_get_info - return profiling data set for given file iterator + * @iter: file iterator + */ +static struct gcov_info *gcov_iter_get_info(struct gcov_iterator *iter) +{ + return iter->info; +} + +/** + * gcov_iter_start - reset file iterator to starting position + * @iter: file iterator + */ +static void gcov_iter_start(struct gcov_iterator *iter) +{ + iter->pos = 0; +} + +/** + * gcov_iter_next - advance file iterator to next logical record + * @iter: file iterator + * + * Return zero if new position is valid, non-zero if iterator has reached end. + */ +static int gcov_iter_next(struct gcov_iterator *iter) +{ + if (iter->pos < iter->size) + iter->pos += ITER_STRIDE; + + if (iter->pos >= iter->size) + return -EINVAL; + + return 0; +} + +/** + * gcov_iter_write - write data for current pos to seq_file + * @iter: file iterator + * @seq: seq_file handle + * + * Return zero on success, non-zero otherwise. + */ +static int gcov_iter_write(struct gcov_iterator *iter, struct seq_file *seq) +{ + size_t len; + + if (iter->pos >= iter->size) + return -EINVAL; + + len = ITER_STRIDE; + if (iter->pos + len > iter->size) + len = iter->size - iter->pos; + + seq_write(seq, iter->buffer + iter->pos, len); + + return 0; +} + /* * seq_file.start() implementation for gcov data files. Note that the * gcov_iterator interface is designed to be more restrictive than seq_file diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c index c53408a00d0b..1251f2434e90 100644 --- a/kernel/gcov/gcc_4_7.c +++ b/kernel/gcov/gcc_4_7.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include "gcov.h" @@ -363,71 +362,6 @@ free_info: kfree(info); } -#define ITER_STRIDE PAGE_SIZE - -/** - * struct gcov_iterator - specifies current file position in logical records - * @info: associated profiling data - * @buffer: buffer containing file data - * @size: size of buffer - * @pos: current position in file - */ -struct gcov_iterator { - struct gcov_info *info; - void *buffer; - size_t size; - loff_t pos; -}; - -/** - * store_gcov_u32 - store 32 bit number in gcov format to buffer - * @buffer: target buffer or NULL - * @off: offset into the buffer - * @v: value to be stored - * - * Number format defined by gcc: numbers are recorded in the 32 bit - * unsigned binary form of the endianness of the machine generating the - * file. Returns the number of bytes stored. If @buffer is %NULL, doesn't - * store anything. - */ -static size_t store_gcov_u32(void *buffer, size_t off, u32 v) -{ - u32 *data; - - if (buffer) { - data = buffer + off; - *data = v; - } - - return sizeof(*data); -} - -/** - * store_gcov_u64 - store 64 bit number in gcov format to buffer - * @buffer: target buffer or NULL - * @off: offset into the buffer - * @v: value to be stored - * - * Number format defined by gcc: numbers are recorded in the 32 bit - * unsigned binary form of the endianness of the machine generating the - * file. 64 bit numbers are stored as two 32 bit numbers, the low part - * first. Returns the number of bytes stored. If @buffer is %NULL, doesn't store - * anything. - */ -static size_t store_gcov_u64(void *buffer, size_t off, u64 v) -{ - u32 *data; - - if (buffer) { - data = buffer + off; - - data[0] = (v & 0xffffffffUL); - data[1] = (v >> 32); - } - - return sizeof(*data) * 2; -} - /** * convert_to_gcda - convert profiling data set to gcda file format * @buffer: the buffer to store file data or %NULL if no data should be stored @@ -435,7 +369,7 @@ static size_t store_gcov_u64(void *buffer, size_t off, u64 v) * * Returns the number of bytes that were/would have been stored into the buffer. */ -static size_t convert_to_gcda(char *buffer, struct gcov_info *info) +size_t convert_to_gcda(char *buffer, struct gcov_info *info) { struct gcov_fn_info *fi_ptr; struct gcov_ctr_info *ci_ptr; @@ -481,102 +415,3 @@ static size_t convert_to_gcda(char *buffer, struct gcov_info *info) return pos; } - -/** - * gcov_iter_new - allocate and initialize profiling data iterator - * @info: profiling data set to be iterated - * - * Return file iterator on success, %NULL otherwise. - */ -struct gcov_iterator *gcov_iter_new(struct gcov_info *info) -{ - struct gcov_iterator *iter; - - iter = kzalloc(sizeof(struct gcov_iterator), GFP_KERNEL); - if (!iter) - goto err_free; - - iter->info = info; - /* Dry-run to get the actual buffer size. */ - iter->size = convert_to_gcda(NULL, info); - iter->buffer = vmalloc(iter->size); - if (!iter->buffer) - goto err_free; - - convert_to_gcda(iter->buffer, info); - - return iter; - -err_free: - kfree(iter); - return NULL; -} - - -/** - * gcov_iter_get_info - return profiling data set for given file iterator - * @iter: file iterator - */ -void gcov_iter_free(struct gcov_iterator *iter) -{ - vfree(iter->buffer); - kfree(iter); -} - -/** - * gcov_iter_get_info - return profiling data set for given file iterator - * @iter: file iterator - */ -struct gcov_info *gcov_iter_get_info(struct gcov_iterator *iter) -{ - return iter->info; -} - -/** - * gcov_iter_start - reset file iterator to starting position - * @iter: file iterator - */ -void gcov_iter_start(struct gcov_iterator *iter) -{ - iter->pos = 0; -} - -/** - * gcov_iter_next - advance file iterator to next logical record - * @iter: file iterator - * - * Return zero if new position is valid, non-zero if iterator has reached end. - */ -int gcov_iter_next(struct gcov_iterator *iter) -{ - if (iter->pos < iter->size) - iter->pos += ITER_STRIDE; - - if (iter->pos >= iter->size) - return -EINVAL; - - return 0; -} - -/** - * gcov_iter_write - write data for current pos to seq_file - * @iter: file iterator - * @seq: seq_file handle - * - * Return zero on success, non-zero otherwise. - */ -int gcov_iter_write(struct gcov_iterator *iter, struct seq_file *seq) -{ - size_t len; - - if (iter->pos >= iter->size) - return -EINVAL; - - len = ITER_STRIDE; - if (iter->pos + len > iter->size) - len = iter->size - iter->pos; - - seq_write(seq, iter->buffer + iter->pos, len); - - return 0; -} diff --git a/kernel/gcov/gcov.h b/kernel/gcov/gcov.h index 6ab2c1808c9d..912b8ea01d33 100644 --- a/kernel/gcov/gcov.h +++ b/kernel/gcov/gcov.h @@ -48,6 +48,7 @@ struct gcov_info *gcov_info_next(struct gcov_info *info); void gcov_info_link(struct gcov_info *info); void gcov_info_unlink(struct gcov_info *prev, struct gcov_info *info); bool gcov_info_within_module(struct gcov_info *info, struct module *mod); +size_t convert_to_gcda(char *buffer, struct gcov_info *info); /* Base interface. */ enum gcov_action { @@ -58,16 +59,9 @@ enum gcov_action { void gcov_event(enum gcov_action action, struct gcov_info *info); void gcov_enable_events(void); -/* Iterator control. */ -struct seq_file; -struct gcov_iterator; - -struct gcov_iterator *gcov_iter_new(struct gcov_info *info); -void gcov_iter_free(struct gcov_iterator *iter); -void gcov_iter_start(struct gcov_iterator *iter); -int gcov_iter_next(struct gcov_iterator *iter); -int gcov_iter_write(struct gcov_iterator *iter, struct seq_file *seq); -struct gcov_info *gcov_iter_get_info(struct gcov_iterator *iter); +/* writing helpers */ +size_t store_gcov_u32(void *buffer, size_t off, u32 v); +size_t store_gcov_u64(void *buffer, size_t off, u64 v); /* gcov_info control. */ void gcov_info_reset(struct gcov_info *info); -- cgit v1.2.3-71-gd317 From 3180c44fe1baf14fc876a4cdad77ea7b51ddc387 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 6 May 2021 18:04:48 -0700 Subject: gcov: simplify buffer allocation Use just a single vmalloc() with struct_size() instead of a separate kmalloc() for the iter struct. Link: https://lkml.kernel.org/r/20210315235453.b6de4a92096e.Iac40a5166589cefbff8449e466bd1b38ea7a17af@changeid Signed-off-by: Johannes Berg Cc: Peter Oberparleiter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/gcov/fs.c | 24 +++++++++--------------- 1 file changed, 9 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c index 2d29e1d1225d..40ea81c0475b 100644 --- a/kernel/gcov/fs.c +++ b/kernel/gcov/fs.c @@ -97,9 +97,9 @@ __setup("gcov_persist=", gcov_persist_setup); */ struct gcov_iterator { struct gcov_info *info; - void *buffer; size_t size; loff_t pos; + char buffer[]; }; /** @@ -111,25 +111,20 @@ struct gcov_iterator { static struct gcov_iterator *gcov_iter_new(struct gcov_info *info) { struct gcov_iterator *iter; + size_t size; + + /* Dry-run to get the actual buffer size. */ + size = convert_to_gcda(NULL, info); - iter = kzalloc(sizeof(struct gcov_iterator), GFP_KERNEL); + iter = vmalloc(struct_size(iter, buffer, size)); if (!iter) - goto err_free; + return NULL; iter->info = info; - /* Dry-run to get the actual buffer size. */ - iter->size = convert_to_gcda(NULL, info); - iter->buffer = vmalloc(iter->size); - if (!iter->buffer) - goto err_free; - + iter->size = size; convert_to_gcda(iter->buffer, info); return iter; - -err_free: - kfree(iter); - return NULL; } @@ -139,8 +134,7 @@ err_free: */ static void gcov_iter_free(struct gcov_iterator *iter) { - vfree(iter->buffer); - kfree(iter); + vfree(iter); } /** -- cgit v1.2.3-71-gd317 From 1391efa952e8b22088f8626fc63ade26767b92d6 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 6 May 2021 18:04:51 -0700 Subject: gcov: use kvmalloc() Using vmalloc() in gcov is really quite wasteful, many of the objects allocated are really small (e.g. I've seen 24 bytes.) Use kvmalloc() to automatically pick the better of kmalloc() or vmalloc() depending on the size. [johannes.berg@intel.com: fix clang-11+ build] Link: https://lkml.kernel.org/r/20210412214210.6e1ecca9cdc5.I24459763acf0591d5e6b31c7e3a59890d802f79c@changeid Link: https://lkml.kernel.org/r/20210315235453.799e7a9d627d.I741d0db096c6f312910f7f1bcdfde0fda20801a4@changeid Signed-off-by: Johannes Berg Reviewed-by: Nick Desaulniers Tested-by: Nick Desaulniers Cc: Peter Oberparleiter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/gcov/clang.c | 12 ++++++------ kernel/gcov/fs.c | 6 +++--- kernel/gcov/gcc_4_7.c | 6 +++--- 3 files changed, 12 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/kernel/gcov/clang.c b/kernel/gcov/clang.c index 1741c65b4fb2..d43ffd0c5ddb 100644 --- a/kernel/gcov/clang.c +++ b/kernel/gcov/clang.c @@ -49,7 +49,7 @@ #include #include #include -#include +#include #include "gcov.h" typedef void (*llvm_gcov_callback)(void); @@ -333,8 +333,8 @@ void gcov_info_add(struct gcov_info *dst, struct gcov_info *src) static struct gcov_fn_info *gcov_fn_info_dup(struct gcov_fn_info *fn) { size_t cv_size; /* counter values size */ - struct gcov_fn_info *fn_dup = kmemdup(fn, sizeof(*fn), - GFP_KERNEL); + struct gcov_fn_info *fn_dup = kmemdup(fn, sizeof(*fn), GFP_KERNEL); + if (!fn_dup) return NULL; INIT_LIST_HEAD(&fn_dup->head); @@ -344,7 +344,7 @@ static struct gcov_fn_info *gcov_fn_info_dup(struct gcov_fn_info *fn) goto err_name; cv_size = fn->num_counters * sizeof(fn->counters[0]); - fn_dup->counters = vmalloc(cv_size); + fn_dup->counters = kvmalloc(cv_size, GFP_KERNEL); if (!fn_dup->counters) goto err_counters; memcpy(fn_dup->counters, fn->counters, cv_size); @@ -368,7 +368,7 @@ static struct gcov_fn_info *gcov_fn_info_dup(struct gcov_fn_info *fn) INIT_LIST_HEAD(&fn_dup->head); cv_size = fn->num_counters * sizeof(fn->counters[0]); - fn_dup->counters = vmalloc(cv_size); + fn_dup->counters = kvmalloc(cv_size, GFP_KERNEL); if (!fn_dup->counters) { kfree(fn_dup); return NULL; @@ -439,7 +439,7 @@ void gcov_info_free(struct gcov_info *info) struct gcov_fn_info *fn, *tmp; list_for_each_entry_safe(fn, tmp, &info->functions, head) { - vfree(fn->counters); + kvfree(fn->counters); list_del(&fn->head); kfree(fn); } diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c index 40ea81c0475b..5c3086cad8f9 100644 --- a/kernel/gcov/fs.c +++ b/kernel/gcov/fs.c @@ -26,7 +26,7 @@ #include #include #include -#include +#include #include "gcov.h" /** @@ -116,7 +116,7 @@ static struct gcov_iterator *gcov_iter_new(struct gcov_info *info) /* Dry-run to get the actual buffer size. */ size = convert_to_gcda(NULL, info); - iter = vmalloc(struct_size(iter, buffer, size)); + iter = kvmalloc(struct_size(iter, buffer, size), GFP_KERNEL); if (!iter) return NULL; @@ -134,7 +134,7 @@ static struct gcov_iterator *gcov_iter_new(struct gcov_info *info) */ static void gcov_iter_free(struct gcov_iterator *iter) { - vfree(iter); + kvfree(iter); } /** diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c index 1251f2434e90..460c12b7dfea 100644 --- a/kernel/gcov/gcc_4_7.c +++ b/kernel/gcov/gcc_4_7.c @@ -15,7 +15,7 @@ #include #include #include -#include +#include #include "gcov.h" #if (__GNUC__ >= 10) @@ -309,7 +309,7 @@ struct gcov_info *gcov_info_dup(struct gcov_info *info) cv_size = sizeof(gcov_type) * sci_ptr->num; - dci_ptr->values = vmalloc(cv_size); + dci_ptr->values = kvmalloc(cv_size, GFP_KERNEL); if (!dci_ptr->values) goto err_free; @@ -351,7 +351,7 @@ void gcov_info_free(struct gcov_info *info) ci_ptr = info->functions[fi_idx]->ctrs; for (ct_idx = 0; ct_idx < active; ct_idx++, ci_ptr++) - vfree(ci_ptr->values); + kvfree(ci_ptr->values); kfree(info->functions[fi_idx]); } -- cgit v1.2.3-71-gd317 From 9b472e85d098a40b84dd8b33fbf8a15ab1452025 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Thu, 6 May 2021 18:04:54 -0700 Subject: gcov: clang: drop support for clang-10 and older LLVM changed the expected function signatures for llvm_gcda_start_file() and llvm_gcda_emit_function() in the clang-11 release. Drop the older implementations and require folks to upgrade their compiler if they're interested in GCOV support. Link: https://reviews.llvm.org/rGcdd683b516d147925212724b09ec6fb792a40041 Link: https://reviews.llvm.org/rG13a633b438b6500ecad9e4f936ebadf3411d0f44 Link: https://lkml.kernel.org/r/20210312224132.3413602-3-ndesaulniers@google.com Link: https://lkml.kernel.org/r/20210413183113.2977432-1-ndesaulniers@google.com Signed-off-by: Nick Desaulniers Suggested-by: Nathan Chancellor Acked-by: Peter Oberparleiter Reviewed-by: Nathan Chancellor Reviewed-by: Fangrui Song Cc: Prasad Sodagudi Cc: Johannes Berg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/gcov/Kconfig | 1 + kernel/gcov/clang.c | 103 ---------------------------------------------------- 2 files changed, 1 insertion(+), 103 deletions(-) (limited to 'kernel') diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig index f62de2dea8a3..58f87a3092f3 100644 --- a/kernel/gcov/Kconfig +++ b/kernel/gcov/Kconfig @@ -4,6 +4,7 @@ menu "GCOV-based kernel profiling" config GCOV_KERNEL bool "Enable gcov-based kernel profiling" depends on DEBUG_FS + depends on !CC_IS_CLANG || CLANG_VERSION >= 110000 select CONSTRUCTORS default n help diff --git a/kernel/gcov/clang.c b/kernel/gcov/clang.c index d43ffd0c5ddb..cbb0bed958ab 100644 --- a/kernel/gcov/clang.c +++ b/kernel/gcov/clang.c @@ -69,16 +69,10 @@ struct gcov_fn_info { u32 ident; u32 checksum; -#if CONFIG_CLANG_VERSION < 110000 - u8 use_extra_checksum; -#endif u32 cfg_checksum; u32 num_counters; u64 *counters; -#if CONFIG_CLANG_VERSION < 110000 - const char *function_name; -#endif }; static struct gcov_info *current_info; @@ -108,16 +102,6 @@ void llvm_gcov_init(llvm_gcov_callback writeout, llvm_gcov_callback flush) } EXPORT_SYMBOL(llvm_gcov_init); -#if CONFIG_CLANG_VERSION < 110000 -void llvm_gcda_start_file(const char *orig_filename, const char version[4], - u32 checksum) -{ - current_info->filename = orig_filename; - memcpy(¤t_info->version, version, sizeof(current_info->version)); - current_info->checksum = checksum; -} -EXPORT_SYMBOL(llvm_gcda_start_file); -#else void llvm_gcda_start_file(const char *orig_filename, u32 version, u32 checksum) { current_info->filename = orig_filename; @@ -125,28 +109,7 @@ void llvm_gcda_start_file(const char *orig_filename, u32 version, u32 checksum) current_info->checksum = checksum; } EXPORT_SYMBOL(llvm_gcda_start_file); -#endif -#if CONFIG_CLANG_VERSION < 110000 -void llvm_gcda_emit_function(u32 ident, const char *function_name, - u32 func_checksum, u8 use_extra_checksum, u32 cfg_checksum) -{ - struct gcov_fn_info *info = kzalloc(sizeof(*info), GFP_KERNEL); - - if (!info) - return; - - INIT_LIST_HEAD(&info->head); - info->ident = ident; - info->checksum = func_checksum; - info->use_extra_checksum = use_extra_checksum; - info->cfg_checksum = cfg_checksum; - if (function_name) - info->function_name = kstrdup(function_name, GFP_KERNEL); - - list_add_tail(&info->head, ¤t_info->functions); -} -#else void llvm_gcda_emit_function(u32 ident, u32 func_checksum, u32 cfg_checksum) { struct gcov_fn_info *info = kzalloc(sizeof(*info), GFP_KERNEL); @@ -160,7 +123,6 @@ void llvm_gcda_emit_function(u32 ident, u32 func_checksum, u32 cfg_checksum) info->cfg_checksum = cfg_checksum; list_add_tail(&info->head, ¤t_info->functions); } -#endif EXPORT_SYMBOL(llvm_gcda_emit_function); void llvm_gcda_emit_arcs(u32 num_counters, u64 *counters) @@ -291,16 +253,8 @@ int gcov_info_is_compatible(struct gcov_info *info1, struct gcov_info *info2) !list_is_last(&fn_ptr2->head, &info2->functions)) { if (fn_ptr1->checksum != fn_ptr2->checksum) return false; -#if CONFIG_CLANG_VERSION < 110000 - if (fn_ptr1->use_extra_checksum != fn_ptr2->use_extra_checksum) - return false; - if (fn_ptr1->use_extra_checksum && - fn_ptr1->cfg_checksum != fn_ptr2->cfg_checksum) - return false; -#else if (fn_ptr1->cfg_checksum != fn_ptr2->cfg_checksum) return false; -#endif fn_ptr1 = list_next_entry(fn_ptr1, head); fn_ptr2 = list_next_entry(fn_ptr2, head); } @@ -329,35 +283,6 @@ void gcov_info_add(struct gcov_info *dst, struct gcov_info *src) } } -#if CONFIG_CLANG_VERSION < 110000 -static struct gcov_fn_info *gcov_fn_info_dup(struct gcov_fn_info *fn) -{ - size_t cv_size; /* counter values size */ - struct gcov_fn_info *fn_dup = kmemdup(fn, sizeof(*fn), GFP_KERNEL); - - if (!fn_dup) - return NULL; - INIT_LIST_HEAD(&fn_dup->head); - - fn_dup->function_name = kstrdup(fn->function_name, GFP_KERNEL); - if (!fn_dup->function_name) - goto err_name; - - cv_size = fn->num_counters * sizeof(fn->counters[0]); - fn_dup->counters = kvmalloc(cv_size, GFP_KERNEL); - if (!fn_dup->counters) - goto err_counters; - memcpy(fn_dup->counters, fn->counters, cv_size); - - return fn_dup; - -err_counters: - kfree(fn_dup->function_name); -err_name: - kfree(fn_dup); - return NULL; -} -#else static struct gcov_fn_info *gcov_fn_info_dup(struct gcov_fn_info *fn) { size_t cv_size; /* counter values size */ @@ -378,7 +303,6 @@ static struct gcov_fn_info *gcov_fn_info_dup(struct gcov_fn_info *fn) return fn_dup; } -#endif /** * gcov_info_dup - duplicate profiling data set @@ -419,21 +343,6 @@ err: * gcov_info_free - release memory for profiling data set duplicate * @info: profiling data set duplicate to free */ -#if CONFIG_CLANG_VERSION < 110000 -void gcov_info_free(struct gcov_info *info) -{ - struct gcov_fn_info *fn, *tmp; - - list_for_each_entry_safe(fn, tmp, &info->functions, head) { - kfree(fn->function_name); - vfree(fn->counters); - list_del(&fn->head); - kfree(fn); - } - kfree(info->filename); - kfree(info); -} -#else void gcov_info_free(struct gcov_info *info) { struct gcov_fn_info *fn, *tmp; @@ -446,7 +355,6 @@ void gcov_info_free(struct gcov_info *info) kfree(info->filename); kfree(info); } -#endif /** * convert_to_gcda - convert profiling data set to gcda file format @@ -469,21 +377,10 @@ size_t convert_to_gcda(char *buffer, struct gcov_info *info) u32 i; pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION); -#if CONFIG_CLANG_VERSION < 110000 - pos += store_gcov_u32(buffer, pos, - fi_ptr->use_extra_checksum ? 3 : 2); -#else pos += store_gcov_u32(buffer, pos, 3); -#endif pos += store_gcov_u32(buffer, pos, fi_ptr->ident); pos += store_gcov_u32(buffer, pos, fi_ptr->checksum); -#if CONFIG_CLANG_VERSION < 110000 - if (fi_ptr->use_extra_checksum) - pos += store_gcov_u32(buffer, pos, fi_ptr->cfg_checksum); -#else pos += store_gcov_u32(buffer, pos, fi_ptr->cfg_checksum); -#endif - pos += store_gcov_u32(buffer, pos, GCOV_TAG_COUNTER_BASE); pos += store_gcov_u32(buffer, pos, fi_ptr->num_counters * 2); for (i = 0; i < fi_ptr->num_counters; i++) -- cgit v1.2.3-71-gd317 From 97f61c8f44ec9020708b97a51188170add4f3084 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 6 May 2021 18:05:12 -0700 Subject: kernel/resource: make walk_system_ram_res() find all busy IORESOURCE_SYSTEM_RAM resources Patch series "kernel/resource: make walk_system_ram_res() and walk_mem_res() search the whole tree", v2. Playing with kdump+virtio-mem I noticed that kexec_file_load() does not consider System RAM added via dax/kmem and virtio-mem when preparing the elf header for kdump. Looking into the details, the logic used in walk_system_ram_res() and walk_mem_res() seems to be outdated. walk_system_ram_range() already does the right thing, let's change walk_system_ram_res() and walk_mem_res(), and clean up. Loading a kdump kernel via "kexec -p -s" ... will result in the kdump kernel to also dump dax/kmem and virtio-mem added System RAM now. Note: kexec-tools on x86-64 also have to be updated to consider this memory in the kexec_load() case when processing /proc/iomem. This patch (of 3): It used to be true that we can have system RAM (IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY) only on the first level in the resource tree. However, this is no longer holds for driver-managed system RAM (i.e., added via dax/kmem and virtio-mem), which gets added on lower levels, for example, inside device containers. We have two users of walk_system_ram_res(), which currently only consideres the first level: a) kernel/kexec_file.c:kexec_walk_resources() -- We properly skip IORESOURCE_SYSRAM_DRIVER_MANAGED resources via locate_mem_hole_callback(), so even after this change, we won't be placing kexec images onto dax/kmem and virtio-mem added memory. No change. b) arch/x86/kernel/crash.c:fill_up_crash_elf_data() -- we're currently not adding relevant ranges to the crash elf header, resulting in them not getting dumped via kdump. This change fixes loading a crashkernel via kexec_file_load() and including dax/kmem and virtio-mem added System RAM in the crashdump on x86-64. Note that e.g,, arm64 relies on memblock data and, therefore, always considers all added System RAM already. Let's find all IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY resources, making the function behave like walk_system_ram_range(). Link: https://lkml.kernel.org/r/20210325115326.7826-1-david@redhat.com Link: https://lkml.kernel.org/r/20210325115326.7826-2-david@redhat.com Fixes: ebf71552bb0e ("virtio-mem: Add parent resource for all added "System RAM"") Fixes: c221c0b0308f ("device-dax: "Hotplug" persistent memory for use like normal RAM") Signed-off-by: David Hildenbrand Reviewed-by: Dan Williams Acked-by: Baoquan He Cc: Greg Kroah-Hartman Cc: Dan Williams Cc: Daniel Vetter Cc: Andy Shevchenko Cc: Mauro Carvalho Chehab Cc: Dave Young Cc: Baoquan He Cc: Vivek Goyal Cc: Dave Hansen Cc: Keith Busch Cc: Michal Hocko Cc: Qian Cai Cc: Oscar Salvador Cc: Eric Biederman Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Tom Lendacky Cc: Brijesh Singh Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/resource.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/resource.c b/kernel/resource.c index 627e61b0c124..4efd6e912279 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -457,7 +457,7 @@ int walk_system_ram_res(u64 start, u64 end, void *arg, { unsigned long flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; - return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, true, + return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, false, arg, func); } -- cgit v1.2.3-71-gd317 From 3c9c797534364593b73ba6ab060a014af8934721 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 6 May 2021 18:05:16 -0700 Subject: kernel/resource: make walk_mem_res() find all busy IORESOURCE_MEM resources It used to be true that we can have system RAM (IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY) only on the first level in the resource tree. However, this is no longer holds for driver-managed system RAM (i.e., added via dax/kmem and virtio-mem), which gets added on lower levels, for example, inside device containers. IORESOURCE_SYSTEM_RAM is defined as IORESOURCE_MEM | IORESOURCE_SYSRAM and just a special type of IORESOURCE_MEM. The function walk_mem_res() only considers the first level and is used in arch/x86/mm/ioremap.c:__ioremap_check_mem() only. We currently fail to identify System RAM added by dax/kmem and virtio-mem as "IORES_MAP_SYSTEM_RAM", for example, allowing for remapping of such "normal RAM" in __ioremap_caller(). Let's find all IORESOURCE_MEM | IORESOURCE_BUSY resources, making the function behave similar to walk_system_ram_res(). Link: https://lkml.kernel.org/r/20210325115326.7826-3-david@redhat.com Fixes: ebf71552bb0e ("virtio-mem: Add parent resource for all added "System RAM"") Fixes: c221c0b0308f ("device-dax: "Hotplug" persistent memory for use like normal RAM") Signed-off-by: David Hildenbrand Reviewed-by: Dan Williams Cc: Greg Kroah-Hartman Cc: Dan Williams Cc: Daniel Vetter Cc: Andy Shevchenko Cc: Mauro Carvalho Chehab Cc: Dave Young Cc: Baoquan He Cc: Vivek Goyal Cc: Dave Hansen Cc: Keith Busch Cc: Michal Hocko Cc: Qian Cai Cc: Oscar Salvador Cc: Eric Biederman Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Tom Lendacky Cc: Brijesh Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/resource.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/resource.c b/kernel/resource.c index 4efd6e912279..16e0c7e8ed24 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -470,7 +470,7 @@ int walk_mem_res(u64 start, u64 end, void *arg, { unsigned long flags = IORESOURCE_MEM | IORESOURCE_BUSY; - return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, true, + return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, false, arg, func); } -- cgit v1.2.3-71-gd317 From 97523a4edb7b9dc2be48a24a2387fb1328b29521 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 6 May 2021 18:05:20 -0700 Subject: kernel/resource: remove first_lvl / siblings_only logic All functions that search for IORESOURCE_SYSTEM_RAM or IORESOURCE_MEM resources now properly consider the whole resource tree, not just the first level. Let's drop the unused first_lvl / siblings_only logic. Remove documentation that indicates that some functions behave differently, all consider the full resource tree now. Link: https://lkml.kernel.org/r/20210325115326.7826-4-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Dan Williams Reviewed-by: Andy Shevchenko Cc: Greg Kroah-Hartman Cc: Dan Williams Cc: Daniel Vetter Cc: Andy Shevchenko Cc: Mauro Carvalho Chehab Cc: Dave Young Cc: Baoquan He Cc: Vivek Goyal Cc: Dave Hansen Cc: Keith Busch Cc: Michal Hocko Cc: Qian Cai Cc: Oscar Salvador Cc: Eric Biederman Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Tom Lendacky Cc: Brijesh Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/resource.c | 45 ++++++++++++--------------------------------- 1 file changed, 12 insertions(+), 33 deletions(-) (limited to 'kernel') diff --git a/kernel/resource.c b/kernel/resource.c index 16e0c7e8ed24..7e00239a023a 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -64,12 +64,8 @@ static DEFINE_RWLOCK(resource_lock); static struct resource *bootmem_resource_free; static DEFINE_SPINLOCK(bootmem_resource_lock); -static struct resource *next_resource(struct resource *p, bool sibling_only) +static struct resource *next_resource(struct resource *p) { - /* Caller wants to traverse through siblings only */ - if (sibling_only) - return p->sibling; - if (p->child) return p->child; while (!p->sibling && p->parent) @@ -81,7 +77,7 @@ static void *r_next(struct seq_file *m, void *v, loff_t *pos) { struct resource *p = v; (*pos)++; - return (void *)next_resource(p, false); + return (void *)next_resource(p); } #ifdef CONFIG_PROC_FS @@ -330,14 +326,10 @@ EXPORT_SYMBOL(release_resource); * of the resource that's within [@start..@end]; if none is found, returns * -ENODEV. Returns -EINVAL for invalid parameters. * - * This function walks the whole tree and not just first level children - * unless @first_lvl is true. - * * @start: start address of the resource searched for * @end: end address of same resource * @flags: flags which the resource must have * @desc: descriptor the resource must have - * @first_lvl: walk only the first level children, if set * @res: return ptr, if resource found * * The caller must specify @start, @end, @flags, and @desc @@ -345,9 +337,8 @@ EXPORT_SYMBOL(release_resource); */ static int find_next_iomem_res(resource_size_t start, resource_size_t end, unsigned long flags, unsigned long desc, - bool first_lvl, struct resource *res) + struct resource *res) { - bool siblings_only = true; struct resource *p; if (!res) @@ -358,7 +349,7 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end, read_lock(&resource_lock); - for (p = iomem_resource.child; p; p = next_resource(p, siblings_only)) { + for (p = iomem_resource.child; p; p = next_resource(p)) { /* If we passed the resource we are looking for, stop */ if (p->start > end) { p = NULL; @@ -369,13 +360,6 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end, if (p->end < start) continue; - /* - * Now that we found a range that matches what we look for, - * check the flags and the descriptor. If we were not asked to - * use only the first level, start looking at children as well. - */ - siblings_only = first_lvl; - if ((p->flags & flags) != flags) continue; if ((desc != IORES_DESC_NONE) && (desc != p->desc)) @@ -402,14 +386,14 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end, static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end, unsigned long flags, unsigned long desc, - bool first_lvl, void *arg, + void *arg, int (*func)(struct resource *, void *)) { struct resource res; int ret = -EINVAL; while (start < end && - !find_next_iomem_res(start, end, flags, desc, first_lvl, &res)) { + !find_next_iomem_res(start, end, flags, desc, &res)) { ret = (*func)(&res, arg); if (ret) break; @@ -431,7 +415,6 @@ static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end, * @arg: function argument for the callback @func * @func: callback function that is called for each qualifying resource area * - * This walks through whole tree and not just first level children. * All the memory ranges which overlap start,end and also match flags and * desc are valid candidates. * @@ -441,7 +424,7 @@ static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end, int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, u64 end, void *arg, int (*func)(struct resource *, void *)) { - return __walk_iomem_res_desc(start, end, flags, desc, false, arg, func); + return __walk_iomem_res_desc(start, end, flags, desc, arg, func); } EXPORT_SYMBOL_GPL(walk_iomem_res_desc); @@ -457,8 +440,8 @@ int walk_system_ram_res(u64 start, u64 end, void *arg, { unsigned long flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; - return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, false, - arg, func); + return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, arg, + func); } /* @@ -470,17 +453,14 @@ int walk_mem_res(u64 start, u64 end, void *arg, { unsigned long flags = IORESOURCE_MEM | IORESOURCE_BUSY; - return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, false, - arg, func); + return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, arg, + func); } /* * This function calls the @func callback against all memory ranges of type * System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY. * It is to be used only for System RAM. - * - * This will find System RAM ranges that are children of top-level resources - * in addition to top-level System RAM resources. */ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, void *arg, int (*func)(unsigned long, unsigned long, void *)) @@ -495,8 +475,7 @@ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, end = ((u64)(start_pfn + nr_pages) << PAGE_SHIFT) - 1; flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; while (start < end && - !find_next_iomem_res(start, end, flags, IORES_DESC_NONE, - false, &res)) { + !find_next_iomem_res(start, end, flags, IORES_DESC_NONE, &res)) { pfn = PFN_UP(res.start); end_pfn = PFN_DOWN(res.end + 1); if (end_pfn > pfn) -- cgit v1.2.3-71-gd317 From d486ccb2522fc22f04f191cac99a844f92d56a7e Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Thu, 6 May 2021 18:05:24 -0700 Subject: kernel/resource: allow region_intersects users to hold resource_lock Introduce a version of region_intersects() that can be called with the resource_lock already held. This will be used in a future fix to __request_free_mem_region(). [akpm@linux-foundation.org: make __region_intersects static] Link: https://lkml.kernel.org/r/20210419070109.4780-1-apopple@nvidia.com Signed-off-by: Alistair Popple Cc: David Hildenbrand Cc: Daniel Vetter Cc: Dan Williams Cc: Greg Kroah-Hartman Cc: John Hubbard Cc: Jerome Glisse Cc: Balbir Singh Cc: Muchun Song Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/resource.c | 52 +++++++++++++++++++++++++++++++--------------------- 1 file changed, 31 insertions(+), 21 deletions(-) (limited to 'kernel') diff --git a/kernel/resource.c b/kernel/resource.c index 7e00239a023a..f4aeeda7ee28 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -502,6 +502,34 @@ int __weak page_is_ram(unsigned long pfn) } EXPORT_SYMBOL_GPL(page_is_ram); +static int __region_intersects(resource_size_t start, size_t size, + unsigned long flags, unsigned long desc) +{ + struct resource res; + int type = 0; int other = 0; + struct resource *p; + + res.start = start; + res.end = start + size - 1; + + for (p = iomem_resource.child; p ; p = p->sibling) { + bool is_type = (((p->flags & flags) == flags) && + ((desc == IORES_DESC_NONE) || + (desc == p->desc))); + + if (resource_overlaps(p, &res)) + is_type ? type++ : other++; + } + + if (type == 0) + return REGION_DISJOINT; + + if (other == 0) + return REGION_INTERSECTS; + + return REGION_MIXED; +} + /** * region_intersects() - determine intersection of region with known resources * @start: region start address @@ -525,31 +553,13 @@ EXPORT_SYMBOL_GPL(page_is_ram); int region_intersects(resource_size_t start, size_t size, unsigned long flags, unsigned long desc) { - struct resource res; - int type = 0; int other = 0; - struct resource *p; - - res.start = start; - res.end = start + size - 1; + int ret; read_lock(&resource_lock); - for (p = iomem_resource.child; p ; p = p->sibling) { - bool is_type = (((p->flags & flags) == flags) && - ((desc == IORES_DESC_NONE) || - (desc == p->desc))); - - if (resource_overlaps(p, &res)) - is_type ? type++ : other++; - } + ret = __region_intersects(start, size, flags, desc); read_unlock(&resource_lock); - if (type == 0) - return REGION_DISJOINT; - - if (other == 0) - return REGION_INTERSECTS; - - return REGION_MIXED; + return ret; } EXPORT_SYMBOL_GPL(region_intersects); -- cgit v1.2.3-71-gd317 From 63cdafe0af982e7da9ded37ccf21109a02bc6832 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Thu, 6 May 2021 18:05:27 -0700 Subject: kernel/resource: refactor __request_region to allow external locking Refactor the portion of __request_region() done whilst holding the resource_lock into a separate function to allow callers to hold the lock. Link: https://lkml.kernel.org/r/20210419070109.4780-2-apopple@nvidia.com Signed-off-by: Alistair Popple Reviewed-by: David Hildenbrand Cc: Balbir Singh Cc: Daniel Vetter Cc: Dan Williams Cc: Greg Kroah-Hartman Cc: Jerome Glisse Cc: John Hubbard Cc: Muchun Song Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/resource.c | 52 ++++++++++++++++++++++++++++++++-------------------- 1 file changed, 32 insertions(+), 20 deletions(-) (limited to 'kernel') diff --git a/kernel/resource.c b/kernel/resource.c index f4aeeda7ee28..c8e473b68f17 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1160,31 +1160,16 @@ struct address_space *iomem_get_mapping(void) return smp_load_acquire(&iomem_inode)->i_mapping; } -/** - * __request_region - create a new busy resource region - * @parent: parent resource descriptor - * @start: resource start address - * @n: resource region size - * @name: reserving caller's ID string - * @flags: IO resource flags - */ -struct resource * __request_region(struct resource *parent, +static int __request_region_locked(struct resource *res, struct resource *parent, resource_size_t start, resource_size_t n, const char *name, int flags) { DECLARE_WAITQUEUE(wait, current); - struct resource *res = alloc_resource(GFP_KERNEL); - struct resource *orig_parent = parent; - - if (!res) - return NULL; res->name = name; res->start = start; res->end = start + n - 1; - write_lock(&resource_lock); - for (;;) { struct resource *conflict; @@ -1220,13 +1205,40 @@ struct resource * __request_region(struct resource *parent, continue; } /* Uhhuh, that didn't work out.. */ - free_resource(res); - res = NULL; - break; + return -EBUSY; } + + return 0; +} + +/** + * __request_region - create a new busy resource region + * @parent: parent resource descriptor + * @start: resource start address + * @n: resource region size + * @name: reserving caller's ID string + * @flags: IO resource flags + */ +struct resource *__request_region(struct resource *parent, + resource_size_t start, resource_size_t n, + const char *name, int flags) +{ + struct resource *res = alloc_resource(GFP_KERNEL); + int ret; + + if (!res) + return NULL; + + write_lock(&resource_lock); + ret = __request_region_locked(res, parent, start, n, name, flags); write_unlock(&resource_lock); - if (res && orig_parent == &iomem_resource) + if (ret) { + free_resource(res); + return NULL; + } + + if (parent == &iomem_resource) revoke_iomem(res); return res; -- cgit v1.2.3-71-gd317 From 56fd94919b8bfdbe162f78920b4ebc72b4ce2f39 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Thu, 6 May 2021 18:05:30 -0700 Subject: kernel/resource: fix locking in request_free_mem_region request_free_mem_region() is used to find an empty range of physical addresses for hotplugging ZONE_DEVICE memory. It does this by iterating over the range of possible addresses using region_intersects() to see if the range is free before calling request_mem_region() to allocate the region. However the resource_lock is dropped between these two calls meaning by the time request_mem_region() is called in request_free_mem_region() another thread may have already reserved the requested region. This results in unexpected failures and a message in the kernel log from hitting this condition: /* * mm/hmm.c reserves physical addresses which then * become unavailable to other users. Conflicts are * not expected. Warn to aid debugging if encountered. */ if (conflict->desc == IORES_DESC_DEVICE_PRIVATE_MEMORY) { pr_warn("Unaddressable device %s %pR conflicts with %pR", conflict->name, conflict, res); These unexpected failures can be corrected by holding resource_lock across the two calls. This also requires memory allocation to be performed prior to taking the lock. Link: https://lkml.kernel.org/r/20210419070109.4780-3-apopple@nvidia.com Signed-off-by: Alistair Popple Reviewed-by: David Hildenbrand Cc: Balbir Singh Cc: Daniel Vetter Cc: Dan Williams Cc: Greg Kroah-Hartman Cc: Jerome Glisse Cc: John Hubbard Cc: Muchun Song Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/resource.c | 45 ++++++++++++++++++++++++++++++++++++++------- 1 file changed, 38 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/resource.c b/kernel/resource.c index c8e473b68f17..028a5ab18818 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1780,25 +1780,56 @@ static struct resource *__request_free_mem_region(struct device *dev, { resource_size_t end, addr; struct resource *res; + struct region_devres *dr = NULL; size = ALIGN(size, 1UL << PA_SECTION_SHIFT); end = min_t(unsigned long, base->end, (1UL << MAX_PHYSMEM_BITS) - 1); addr = end - size + 1UL; + res = alloc_resource(GFP_KERNEL); + if (!res) + return ERR_PTR(-ENOMEM); + + if (dev) { + dr = devres_alloc(devm_region_release, + sizeof(struct region_devres), GFP_KERNEL); + if (!dr) { + free_resource(res); + return ERR_PTR(-ENOMEM); + } + } + + write_lock(&resource_lock); for (; addr > size && addr >= base->start; addr -= size) { - if (region_intersects(addr, size, 0, IORES_DESC_NONE) != + if (__region_intersects(addr, size, 0, IORES_DESC_NONE) != REGION_DISJOINT) continue; - if (dev) - res = devm_request_mem_region(dev, addr, size, name); - else - res = request_mem_region(addr, size, name); - if (!res) - return ERR_PTR(-ENOMEM); + if (!__request_region_locked(res, &iomem_resource, addr, size, + name, 0)) + break; + + if (dev) { + dr->parent = &iomem_resource; + dr->start = addr; + dr->n = size; + devres_add(dev, dr); + } + res->desc = IORES_DESC_DEVICE_PRIVATE_MEMORY; + write_unlock(&resource_lock); + + /* + * A driver is claiming this region so revoke any mappings. + */ + revoke_iomem(res); return res; } + write_unlock(&resource_lock); + + free_resource(res); + if (dr) + devres_free(dr); return ERR_PTR(-ERANGE); } -- cgit v1.2.3-71-gd317 From 07416af11dd85ca61abe60155ace37ced1233617 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 6 May 2021 18:05:36 -0700 Subject: kernel/async.c: stop guarding pr_debug() statements It's currently nigh impossible to get these pr_debug()s to print something. Being guarded by initcall_debug means one has to enable tons of other debug output during boot, and the system_state condition further means it's impossible to get them when loading modules later. Also, the compiler can't know that these global conditions do not change, so there are W=2 warnings kernel/async.c:125:9: warning: `calltime' may be used uninitialized in this function [-Wmaybe-uninitialized] kernel/async.c:300:9: warning: `starttime' may be used uninitialized in this function [-Wmaybe-uninitialized] Make it possible, for a DYNAMIC_DEBUG kernel, to get these to print their messages by booting with appropriate 'dyndbg="file async.c +p"' command line argument. For a non-DYNAMIC_DEBUG kernel, pr_debug() compiles to nothing. This does cost doing an unconditional ktime_get() for the starttime value, but the corresponding ktime_get for the end time can be elided by factoring it into a function which only gets called if the printk() arguments end up being evaluated. Link: https://lkml.kernel.org/r/20210309151723.1907838-1-linux@rasmusvillemoes.dk Signed-off-by: Rasmus Villemoes Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/async.c | 48 ++++++++++++++++++++---------------------------- 1 file changed, 20 insertions(+), 28 deletions(-) (limited to 'kernel') diff --git a/kernel/async.c b/kernel/async.c index 45a867b8644a..4b5971142922 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -78,6 +78,12 @@ static DECLARE_WAIT_QUEUE_HEAD(async_done); static atomic_t entry_count; +static long long microseconds_since(ktime_t start) +{ + ktime_t now = ktime_get(); + return ktime_to_ns(ktime_sub(now, start)) >> 10; +} + static async_cookie_t lowest_in_progress(struct async_domain *domain) { struct async_entry *first = NULL; @@ -111,24 +117,18 @@ static void async_run_entry_fn(struct work_struct *work) struct async_entry *entry = container_of(work, struct async_entry, work); unsigned long flags; - ktime_t calltime, delta, rettime; + ktime_t calltime; /* 1) run (and print duration) */ - if (initcall_debug && system_state < SYSTEM_RUNNING) { - pr_debug("calling %lli_%pS @ %i\n", - (long long)entry->cookie, - entry->func, task_pid_nr(current)); - calltime = ktime_get(); - } + pr_debug("calling %lli_%pS @ %i\n", (long long)entry->cookie, + entry->func, task_pid_nr(current)); + calltime = ktime_get(); + entry->func(entry->data, entry->cookie); - if (initcall_debug && system_state < SYSTEM_RUNNING) { - rettime = ktime_get(); - delta = ktime_sub(rettime, calltime); - pr_debug("initcall %lli_%pS returned after %lld usecs\n", - (long long)entry->cookie, - entry->func, - (long long)ktime_to_ns(delta) >> 10); - } + + pr_debug("initcall %lli_%pS returned after %lld usecs\n", + (long long)entry->cookie, entry->func, + microseconds_since(calltime)); /* 2) remove self from the pending queues */ spin_lock_irqsave(&async_lock, flags); @@ -287,23 +287,15 @@ EXPORT_SYMBOL_GPL(async_synchronize_full_domain); */ void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain *domain) { - ktime_t starttime, delta, endtime; + ktime_t starttime; - if (initcall_debug && system_state < SYSTEM_RUNNING) { - pr_debug("async_waiting @ %i\n", task_pid_nr(current)); - starttime = ktime_get(); - } + pr_debug("async_waiting @ %i\n", task_pid_nr(current)); + starttime = ktime_get(); wait_event(async_done, lowest_in_progress(domain) >= cookie); - if (initcall_debug && system_state < SYSTEM_RUNNING) { - endtime = ktime_get(); - delta = ktime_sub(endtime, starttime); - - pr_debug("async_continuing @ %i after %lli usec\n", - task_pid_nr(current), - (long long)ktime_to_ns(delta) >> 10); - } + pr_debug("async_continuing @ %i after %lli usec\n", task_pid_nr(current), + microseconds_since(starttime)); } EXPORT_SYMBOL_GPL(async_synchronize_cookie_domain); -- cgit v1.2.3-71-gd317 From a065c0faacb1e472cd4e048986407d1b177373a2 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 6 May 2021 18:05:39 -0700 Subject: kernel/async.c: remove async_unregister_domain() No callers in the tree. Link: https://lkml.kernel.org/r/20210309151723.1907838-2-linux@rasmusvillemoes.dk Signed-off-by: Rasmus Villemoes Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/async.h | 1 - kernel/async.c | 18 ------------------ 2 files changed, 19 deletions(-) (limited to 'kernel') diff --git a/include/linux/async.h b/include/linux/async.h index 0a17cd27f348..cce4ad31e8fc 100644 --- a/include/linux/async.h +++ b/include/linux/async.h @@ -112,7 +112,6 @@ async_schedule_dev_domain(async_func_t func, struct device *dev, return async_schedule_node_domain(func, dev, dev_to_node(dev), domain); } -void async_unregister_domain(struct async_domain *domain); extern void async_synchronize_full(void); extern void async_synchronize_full_domain(struct async_domain *domain); extern void async_synchronize_cookie(async_cookie_t cookie); diff --git a/kernel/async.c b/kernel/async.c index 4b5971142922..b8d7a663497f 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -245,24 +245,6 @@ void async_synchronize_full(void) } EXPORT_SYMBOL_GPL(async_synchronize_full); -/** - * async_unregister_domain - ensure no more anonymous waiters on this domain - * @domain: idle domain to flush out of any async_synchronize_full instances - * - * async_synchronize_{cookie|full}_domain() are not flushed since callers - * of these routines should know the lifetime of @domain - * - * Prefer ASYNC_DOMAIN_EXCLUSIVE() declarations over flushing - */ -void async_unregister_domain(struct async_domain *domain) -{ - spin_lock_irq(&async_lock); - WARN_ON(!domain->registered || !list_empty(&domain->pending)); - domain->registered = 0; - spin_unlock_irq(&async_lock); -} -EXPORT_SYMBOL_GPL(async_unregister_domain); - /** * async_synchronize_full_domain - synchronize all asynchronous function within a certain domain * @domain: the domain to synchronize -- cgit v1.2.3-71-gd317 From e7cb072eb988e46295512617c39d004f9e1c26f8 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 6 May 2021 18:05:42 -0700 Subject: init/initramfs.c: do unpacking asynchronously Patch series "background initramfs unpacking, and CONFIG_MODPROBE_PATH", v3. These two patches are independent, but better-together. The second is a rather trivial patch that simply allows the developer to change "/sbin/modprobe" to something else - e.g. the empty string, so that all request_module() during early boot return -ENOENT early, without even spawning a usermode helper, needlessly synchronizing with the initramfs unpacking. The first patch delegates decompressing the initramfs to a worker thread, allowing do_initcalls() in main.c to proceed to the device_ and late_ initcalls without waiting for that decompression (and populating of rootfs) to finish. Obviously, some of those later calls may rely on the initramfs being available, so I've added synchronization points in the firmware loader and usermodehelper paths - there might be other places that would need this, but so far no one has been able to think of any places I have missed. There's not much to win if most of the functionality needed during boot is only available as modules. But systems with a custom-made .config and initramfs can boot faster, partly due to utilizing more than one cpu earlier, partly by avoiding known-futile modprobe calls (which would still trigger synchronization with the initramfs unpacking, thus eliminating most of the first benefit). This patch (of 2): Most of the boot process doesn't actually need anything from the initramfs, until of course PID1 is to be executed. So instead of doing the decompressing and populating of the initramfs synchronously in populate_rootfs() itself, push that off to a worker thread. This is primarily motivated by an embedded ppc target, where unpacking even the rather modest sized initramfs takes 0.6 seconds, which is long enough that the external watchdog becomes unhappy that it doesn't get attention soon enough. By doing the initramfs decompression in a worker thread, we get to do the device_initcalls and hence start petting the watchdog much sooner. Normal desktops might benefit as well. On my mostly stock Ubuntu kernel, my initramfs is a 26M xz-compressed blob, decompressing to around 126M. That takes almost two seconds: [ 0.201454] Trying to unpack rootfs image as initramfs... [ 1.976633] Freeing initrd memory: 29416K Before this patch, these lines occur consecutively in dmesg. With this patch, the timestamps on these two lines is roughly the same as above, but with 172 lines inbetween - so more than one cpu has been kept busy doing work that would otherwise only happen after the populate_rootfs() finished. Should one of the initcalls done after rootfs_initcall time (i.e., device_ and late_ initcalls) need something from the initramfs (say, a kernel module or a firmware blob), it will simply wait for the initramfs unpacking to be done before proceeding, which should in theory make this completely safe. But if some driver pokes around in the filesystem directly and not via one of the official kernel interfaces (i.e. request_firmware*(), call_usermodehelper*) that theory may not hold - also, I certainly might have missed a spot when sprinkling wait_for_initramfs(). So there is an escape hatch in the form of an initramfs_async= command line parameter. Link: https://lkml.kernel.org/r/20210313212528.2956377-1-linux@rasmusvillemoes.dk Link: https://lkml.kernel.org/r/20210313212528.2956377-2-linux@rasmusvillemoes.dk Signed-off-by: Rasmus Villemoes Reviewed-by: Luis Chamberlain Cc: Jessica Yu Cc: Borislav Petkov Cc: Jonathan Corbet Cc: Greg Kroah-Hartman Cc: Nick Desaulniers Cc: Takashi Iwai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/kernel-parameters.txt | 12 ++++++++ drivers/base/firmware_loader/main.c | 2 ++ include/linux/initrd.h | 2 ++ init/initramfs.c | 38 ++++++++++++++++++++++++- init/main.c | 1 + kernel/umh.c | 2 ++ 6 files changed, 56 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index d93fbc1c1917..7866cc1bd4a9 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1833,6 +1833,18 @@ initcall functions. Useful for debugging built-in modules and initcalls. + initramfs_async= [KNL] + Format: + Default: 1 + This parameter controls whether the initramfs + image is unpacked asynchronously, concurrently + with devices being probed and + initialized. This should normally just work, + but as a debugging aid, one can get the + historical behaviour of the initramfs + unpacking being completed before device_ and + late_ initcalls. + initrd= [BOOT] Specify the location of the initial ramdisk initrdmem= [KNL] Specify a physical address and size from which to diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c index 78355095e00d..4fdb8219cd08 100644 --- a/drivers/base/firmware_loader/main.c +++ b/drivers/base/firmware_loader/main.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -504,6 +505,7 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv, if (!path) return -ENOMEM; + wait_for_initramfs(); for (i = 0; i < ARRAY_SIZE(fw_path); i++) { size_t file_size = 0; size_t *file_size_ptr = NULL; diff --git a/include/linux/initrd.h b/include/linux/initrd.h index 85c15717af34..1bbe9af48dc3 100644 --- a/include/linux/initrd.h +++ b/include/linux/initrd.h @@ -20,8 +20,10 @@ extern void free_initrd_mem(unsigned long, unsigned long); #ifdef CONFIG_BLK_DEV_INITRD extern void __init reserve_initrd_mem(void); +extern void wait_for_initramfs(void); #else static inline void __init reserve_initrd_mem(void) {} +static inline void wait_for_initramfs(void) {} #endif extern phys_addr_t phys_initrd_start; diff --git a/init/initramfs.c b/init/initramfs.c index d677e8e717f1..af27abc59643 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include #include #include #include @@ -541,6 +542,14 @@ static int __init keepinitrd_setup(char *__unused) __setup("keepinitrd", keepinitrd_setup); #endif +static bool __initdata initramfs_async = true; +static int __init initramfs_async_setup(char *str) +{ + strtobool(str, &initramfs_async); + return 1; +} +__setup("initramfs_async=", initramfs_async_setup); + extern char __initramfs_start[]; extern unsigned long __initramfs_size; #include @@ -658,7 +667,7 @@ static void __init populate_initrd_image(char *err) } #endif /* CONFIG_BLK_DEV_RAM */ -static int __init populate_rootfs(void) +static void __init do_populate_rootfs(void *unused, async_cookie_t cookie) { /* Load the built in initramfs */ char *err = unpack_to_rootfs(__initramfs_start, __initramfs_size); @@ -693,6 +702,33 @@ done: initrd_end = 0; flush_delayed_fput(); +} + +static ASYNC_DOMAIN_EXCLUSIVE(initramfs_domain); +static async_cookie_t initramfs_cookie; + +void wait_for_initramfs(void) +{ + if (!initramfs_cookie) { + /* + * Something before rootfs_initcall wants to access + * the filesystem/initramfs. Probably a bug. Make a + * note, avoid deadlocking the machine, and let the + * caller's access fail as it used to. + */ + pr_warn_once("wait_for_initramfs() called before rootfs_initcalls\n"); + return; + } + async_synchronize_cookie_domain(initramfs_cookie + 1, &initramfs_domain); +} +EXPORT_SYMBOL_GPL(wait_for_initramfs); + +static int __init populate_rootfs(void) +{ + initramfs_cookie = async_schedule_domain(do_populate_rootfs, NULL, + &initramfs_domain); + if (!initramfs_async) + wait_for_initramfs(); return 0; } rootfs_initcall(populate_rootfs); diff --git a/init/main.c b/init/main.c index dd11bfd10ead..11d34ccf5786 100644 --- a/init/main.c +++ b/init/main.c @@ -1561,6 +1561,7 @@ static noinline void __init kernel_init_freeable(void) kunit_run_all_tests(); + wait_for_initramfs(); console_on_rootfs(); /* diff --git a/kernel/umh.c b/kernel/umh.c index 3f646613a9d3..61f6b82c354b 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -27,6 +27,7 @@ #include #include #include +#include #include @@ -107,6 +108,7 @@ static int call_usermodehelper_exec_async(void *data) commit_creds(new); + wait_for_initramfs(); retval = kernel_execve(sub_info->path, (const char *const *)sub_info->argv, (const char *const *)sub_info->envp); -- cgit v1.2.3-71-gd317 From 17652f4240f7a501ecc13e9fdb06982569cde51f Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 6 May 2021 18:05:45 -0700 Subject: modules: add CONFIG_MODPROBE_PATH Allow the developer to specifiy the initial value of the modprobe_path[] string. This can be used to set it to the empty string initially, thus effectively disabling request_module() during early boot until userspace writes a new value via the /proc/sys/kernel/modprobe interface. [1] When building a custom kernel (often for an embedded target), it's normal to build everything into the kernel that is needed for booting, and indeed the initramfs often contains no modules at all, so every such request_module() done before userspace init has mounted the real rootfs is a waste of time. This is particularly useful when combined with the previous patch, which made the initramfs unpacking asynchronous - for that to work, it had to make any usermodehelper call wait for the unpacking to finish before attempting to invoke the userspace helper. By eliminating all such (known-to-be-futile) calls of usermodehelper, the initramfs unpacking and the {device,late}_initcalls can proceed in parallel for much longer. For a relatively slow ppc board I'm working on, the two patches combined lead to 0.2s faster boot - but more importantly, the fact that the initramfs unpacking proceeds completely in the background while devices get probed means I get to handle the gpio watchdog in time without getting reset. [1] __request_module() already has an early -ENOENT return when modprobe_path is the empty string. Link: https://lkml.kernel.org/r/20210313212528.2956377-3-linux@rasmusvillemoes.dk Signed-off-by: Rasmus Villemoes Reviewed-by: Greg Kroah-Hartman Acked-by: Jessica Yu Acked-by: Luis Chamberlain Cc: Borislav Petkov Cc: Jonathan Corbet Cc: Nick Desaulniers Cc: Takashi Iwai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/Kconfig | 12 ++++++++++++ kernel/kmod.c | 2 +- 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/init/Kconfig b/init/Kconfig index 1413413fcb9f..d83cb634c24f 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -2299,6 +2299,18 @@ config MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS If unsure, say N. +config MODPROBE_PATH + string "Path to modprobe binary" + default "/sbin/modprobe" + help + When kernel code requests a module, it does so by calling + the "modprobe" userspace utility. This option allows you to + set the path where that binary is found. This can be changed + at runtime via the sysctl file + /proc/sys/kernel/modprobe. Setting this to the empty string + removes the kernel's ability to request modules (but + userspace can still load modules explicitly). + config TRIM_UNUSED_KSYMS bool "Trim unused exported kernel symbols" if EXPERT depends on !COMPILE_TEST diff --git a/kernel/kmod.c b/kernel/kmod.c index 3cd075ce2a1e..b717134ebe17 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -58,7 +58,7 @@ static DECLARE_WAIT_QUEUE_HEAD(kmod_wq); /* modprobe_path is set via /proc/sys. */ -char modprobe_path[KMOD_PATH_LEN] = "/sbin/modprobe"; +char modprobe_path[KMOD_PATH_LEN] = CONFIG_MODPROBE_PATH; static void free_modprobe_argv(struct subprocess_info *info) { -- cgit v1.2.3-71-gd317 From bbcd53c960713507ae764bf81970651b5577b95a Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 6 May 2021 18:05:55 -0700 Subject: drivers/char: remove /dev/kmem for good Patch series "drivers/char: remove /dev/kmem for good". Exploring /dev/kmem and /dev/mem in the context of memory hot(un)plug and memory ballooning, I started questioning the existence of /dev/kmem. Comparing it with the /proc/kcore implementation, it does not seem to be able to deal with things like a) Pages unmapped from the direct mapping (e.g., to be used by secretmem) -> kern_addr_valid(). virt_addr_valid() is not sufficient. b) Special cases like gart aperture memory that is not to be touched -> mem_pfn_is_ram() Unless I am missing something, it's at least broken in some cases and might fault/crash the machine. Looks like its existence has been questioned before in 2005 and 2010 [1], after ~11 additional years, it might make sense to revive the discussion. CONFIG_DEVKMEM is only enabled in a single defconfig (on purpose or by mistake?). All distributions disable it: in Ubuntu it has been disabled for more than 10 years, in Debian since 2.6.31, in Fedora at least starting with FC3, in RHEL starting with RHEL4, in SUSE starting from 15sp2, and OpenSUSE has it disabled as well. 1) /dev/kmem was popular for rootkits [2] before it got disabled basically everywhere. Ubuntu documents [3] "There is no modern user of /dev/kmem any more beyond attackers using it to load kernel rootkits.". RHEL documents in a BZ [5] "it served no practical purpose other than to serve as a potential security problem or to enable binary module drivers to access structures/functions they shouldn't be touching" 2) /proc/kcore is a decent interface to have a controlled way to read kernel memory for debugging puposes. (will need some extensions to deal with memory offlining/unplug, memory ballooning, and poisoned pages, though) 3) It might be useful for corner case debugging [1]. KDB/KGDB might be a better fit, especially, to write random memory; harder to shoot yourself into the foot. 4) "Kernel Memory Editor" [4] hasn't seen any updates since 2000 and seems to be incompatible with 64bit [1]. For educational purposes, /proc/kcore might be used to monitor value updates -- or older kernels can be used. 5) It's broken on arm64, and therefore, completely disabled there. Looks like it's essentially unused and has been replaced by better suited interfaces for individual tasks (/proc/kcore, KDB/KGDB). Let's just remove it. [1] https://lwn.net/Articles/147901/ [2] https://www.linuxjournal.com/article/10505 [3] https://wiki.ubuntu.com/Security/Features#A.2Fdev.2Fkmem_disabled [4] https://sourceforge.net/projects/kme/ [5] https://bugzilla.redhat.com/show_bug.cgi?id=154796 Link: https://lkml.kernel.org/r/20210324102351.6932-1-david@redhat.com Link: https://lkml.kernel.org/r/20210324102351.6932-2-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Michal Hocko Acked-by: Kees Cook Cc: Linus Torvalds Cc: Greg Kroah-Hartman Cc: "Alexander A. Klimov" Cc: Alexander Viro Cc: Alexandre Belloni Cc: Andrew Lunn Cc: Andrey Zhizhikin Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Brian Cain Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Chris Zankel Cc: Corentin Labbe Cc: "David S. Miller" Cc: "Eric W. Biederman" Cc: Geert Uytterhoeven Cc: Gerald Schaefer Cc: Greentime Hu Cc: Gregory Clement Cc: Heiko Carstens Cc: Helge Deller Cc: Hillf Danton Cc: huang ying Cc: Ingo Molnar Cc: Ivan Kokshaysky Cc: "James E.J. Bottomley" Cc: James Troup Cc: Jiaxun Yang Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Kairui Song Cc: Krzysztof Kozlowski Cc: Kuninori Morimoto Cc: Liviu Dudau Cc: Lorenzo Pieralisi Cc: Luc Van Oostenryck Cc: Luis Chamberlain Cc: Matthew Wilcox Cc: Matt Turner Cc: Max Filippov Cc: Michael Ellerman Cc: Mike Rapoport Cc: Mikulas Patocka Cc: Minchan Kim Cc: Niklas Schnelle Cc: Oleksiy Avramchenko Cc: openrisc@lists.librecores.org Cc: Palmer Dabbelt Cc: Paul Mackerras Cc: "Pavel Machek (CIP)" Cc: Pavel Machek Cc: "Peter Zijlstra (Intel)" Cc: Pierre Morel Cc: Randy Dunlap Cc: Richard Henderson Cc: Rich Felker Cc: Robert Richter Cc: Rob Herring Cc: Russell King Cc: Sam Ravnborg Cc: Sebastian Andrzej Siewior Cc: Sebastian Hesselbarth Cc: sparclinux@vger.kernel.org Cc: Stafford Horne Cc: Stefan Kristiansson Cc: Steven Rostedt Cc: Sudeep Holla Cc: Theodore Dubois Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Viresh Kumar Cc: William Cohen Cc: Xiaoming Ni Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/devices.txt | 2 +- arch/arm/configs/dove_defconfig | 1 - arch/arm/configs/magician_defconfig | 1 - arch/arm/configs/moxart_defconfig | 1 - arch/arm/configs/mps2_defconfig | 1 - arch/arm/configs/mvebu_v5_defconfig | 1 - arch/arm/configs/xcep_defconfig | 1 - arch/hexagon/configs/comet_defconfig | 1 - arch/m68k/configs/amcore_defconfig | 1 - arch/openrisc/configs/or1ksim_defconfig | 1 - arch/sh/configs/edosk7705_defconfig | 1 - arch/sh/configs/se7206_defconfig | 1 - arch/sh/configs/sh2007_defconfig | 1 - arch/sh/configs/sh7724_generic_defconfig | 1 - arch/sh/configs/sh7770_generic_defconfig | 1 - arch/sh/configs/sh7785lcr_32bit_defconfig | 1 - arch/sparc/configs/sparc64_defconfig | 1 - arch/xtensa/configs/xip_kc705_defconfig | 1 - drivers/char/Kconfig | 10 -- drivers/char/mem.c | 231 ------------------------------ include/linux/fs.h | 2 +- include/linux/vmalloc.h | 2 +- kernel/configs/android-base.config | 1 - mm/ksm.c | 2 +- mm/vmalloc.c | 2 +- 25 files changed, 5 insertions(+), 264 deletions(-) (limited to 'kernel') diff --git a/Documentation/admin-guide/devices.txt b/Documentation/admin-guide/devices.txt index ef41f77cb979..9c2be821c225 100644 --- a/Documentation/admin-guide/devices.txt +++ b/Documentation/admin-guide/devices.txt @@ -4,7 +4,7 @@ 1 char Memory devices 1 = /dev/mem Physical memory access - 2 = /dev/kmem Kernel virtual memory access + 2 = /dev/kmem OBSOLETE - replaced by /proc/kcore 3 = /dev/null Null device 4 = /dev/port I/O port access 5 = /dev/zero Null byte source diff --git a/arch/arm/configs/dove_defconfig b/arch/arm/configs/dove_defconfig index e70c997d5f4c..b935162a8bba 100644 --- a/arch/arm/configs/dove_defconfig +++ b/arch/arm/configs/dove_defconfig @@ -63,7 +63,6 @@ CONFIG_INPUT_EVDEV=y # CONFIG_MOUSE_PS2 is not set # CONFIG_SERIO is not set CONFIG_LEGACY_PTY_COUNT=16 -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_RUNTIME_UARTS=2 diff --git a/arch/arm/configs/magician_defconfig b/arch/arm/configs/magician_defconfig index b4670d42f378..abde1fb23b20 100644 --- a/arch/arm/configs/magician_defconfig +++ b/arch/arm/configs/magician_defconfig @@ -72,7 +72,6 @@ CONFIG_INPUT_TOUCHSCREEN=y CONFIG_INPUT_MISC=y CONFIG_INPUT_UINPUT=m # CONFIG_SERIO is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_PXA=y # CONFIG_LEGACY_PTYS is not set # CONFIG_HW_RANDOM is not set diff --git a/arch/arm/configs/moxart_defconfig b/arch/arm/configs/moxart_defconfig index 6834e97af348..eacc089d86c5 100644 --- a/arch/arm/configs/moxart_defconfig +++ b/arch/arm/configs/moxart_defconfig @@ -79,7 +79,6 @@ CONFIG_INPUT_EVBUG=y # CONFIG_SERIO is not set # CONFIG_VT is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arm/configs/mps2_defconfig b/arch/arm/configs/mps2_defconfig index 1d923dbb9928..89f4a6ff30bd 100644 --- a/arch/arm/configs/mps2_defconfig +++ b/arch/arm/configs/mps2_defconfig @@ -69,7 +69,6 @@ CONFIG_SMSC911X=y # CONFIG_VT is not set # CONFIG_LEGACY_PTYS is not set CONFIG_SERIAL_NONSTANDARD=y -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_MPS2_UART_CONSOLE=y CONFIG_SERIAL_MPS2_UART=y # CONFIG_HW_RANDOM is not set diff --git a/arch/arm/configs/mvebu_v5_defconfig b/arch/arm/configs/mvebu_v5_defconfig index 4f16716bfc32..d57ff30dabff 100644 --- a/arch/arm/configs/mvebu_v5_defconfig +++ b/arch/arm/configs/mvebu_v5_defconfig @@ -100,7 +100,6 @@ CONFIG_INPUT_EVDEV=y CONFIG_KEYBOARD_GPIO=y # CONFIG_INPUT_MOUSE is not set CONFIG_LEGACY_PTY_COUNT=16 -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_RUNTIME_UARTS=2 diff --git a/arch/arm/configs/xcep_defconfig b/arch/arm/configs/xcep_defconfig index f1fbdfc5c8c6..4d8e7f2eaef7 100644 --- a/arch/arm/configs/xcep_defconfig +++ b/arch/arm/configs/xcep_defconfig @@ -53,7 +53,6 @@ CONFIG_NET_ETHERNET=y # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_PXA=y CONFIG_SERIAL_PXA_CONSOLE=y # CONFIG_LEGACY_PTYS is not set diff --git a/arch/hexagon/configs/comet_defconfig b/arch/hexagon/configs/comet_defconfig index f19ae2ab0aaa..c5a214716a38 100644 --- a/arch/hexagon/configs/comet_defconfig +++ b/arch/hexagon/configs/comet_defconfig @@ -34,7 +34,6 @@ CONFIG_NET_ETHERNET=y # CONFIG_SERIO is not set # CONFIG_CONSOLE_TRANSLATIONS is not set CONFIG_LEGACY_PTY_COUNT=64 -# CONFIG_DEVKMEM is not set # CONFIG_HW_RANDOM is not set CONFIG_SPI=y CONFIG_SPI_DEBUG=y diff --git a/arch/m68k/configs/amcore_defconfig b/arch/m68k/configs/amcore_defconfig index 3a84f24d41c8..6d9ed2198170 100644 --- a/arch/m68k/configs/amcore_defconfig +++ b/arch/m68k/configs/amcore_defconfig @@ -60,7 +60,6 @@ CONFIG_DM9000=y # CONFIG_VT is not set # CONFIG_UNIX98_PTYS is not set # CONFIG_DEVMEM is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_MCF=y CONFIG_SERIAL_MCF_BAUDRATE=115200 CONFIG_SERIAL_MCF_CONSOLE=y diff --git a/arch/openrisc/configs/or1ksim_defconfig b/arch/openrisc/configs/or1ksim_defconfig index 75f2da324d0e..6e1e004047c7 100644 --- a/arch/openrisc/configs/or1ksim_defconfig +++ b/arch/openrisc/configs/or1ksim_defconfig @@ -43,7 +43,6 @@ CONFIG_MICREL_PHY=y # CONFIG_SERIO is not set # CONFIG_VT is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y diff --git a/arch/sh/configs/edosk7705_defconfig b/arch/sh/configs/edosk7705_defconfig index ef7cc31997b1..9ee35269bee2 100644 --- a/arch/sh/configs/edosk7705_defconfig +++ b/arch/sh/configs/edosk7705_defconfig @@ -23,7 +23,6 @@ CONFIG_SH_PCLK_FREQ=31250000 # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set -# CONFIG_DEVKMEM is not set # CONFIG_UNIX98_PTYS is not set # CONFIG_LEGACY_PTYS is not set # CONFIG_HW_RANDOM is not set diff --git a/arch/sh/configs/se7206_defconfig b/arch/sh/configs/se7206_defconfig index 315b04a8dd2f..601d062250d1 100644 --- a/arch/sh/configs/se7206_defconfig +++ b/arch/sh/configs/se7206_defconfig @@ -71,7 +71,6 @@ CONFIG_SMC91X=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_SH_SCI=y CONFIG_SERIAL_SH_SCI_NR_UARTS=4 CONFIG_SERIAL_SH_SCI_CONSOLE=y diff --git a/arch/sh/configs/sh2007_defconfig b/arch/sh/configs/sh2007_defconfig index 99975db461d8..79f02f1c0dc8 100644 --- a/arch/sh/configs/sh2007_defconfig +++ b/arch/sh/configs/sh2007_defconfig @@ -75,7 +75,6 @@ CONFIG_INPUT_FF_MEMLESS=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set CONFIG_VT_HW_CONSOLE_BINDING=y -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_SH_SCI=y CONFIG_SERIAL_SH_SCI_CONSOLE=y # CONFIG_LEGACY_PTYS is not set diff --git a/arch/sh/configs/sh7724_generic_defconfig b/arch/sh/configs/sh7724_generic_defconfig index 2c46c0004780..cbc9389a89a8 100644 --- a/arch/sh/configs/sh7724_generic_defconfig +++ b/arch/sh/configs/sh7724_generic_defconfig @@ -18,7 +18,6 @@ CONFIG_CPU_IDLE=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_SH_SCI=y CONFIG_SERIAL_SH_SCI_NR_UARTS=6 CONFIG_SERIAL_SH_SCI_CONSOLE=y diff --git a/arch/sh/configs/sh7770_generic_defconfig b/arch/sh/configs/sh7770_generic_defconfig index 88193153e51b..ee2357deba0f 100644 --- a/arch/sh/configs/sh7770_generic_defconfig +++ b/arch/sh/configs/sh7770_generic_defconfig @@ -20,7 +20,6 @@ CONFIG_CPU_IDLE=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_SH_SCI=y CONFIG_SERIAL_SH_SCI_NR_UARTS=6 CONFIG_SERIAL_SH_SCI_CONSOLE=y diff --git a/arch/sh/configs/sh7785lcr_32bit_defconfig b/arch/sh/configs/sh7785lcr_32bit_defconfig index 9b885c14c400..5c725c75fcef 100644 --- a/arch/sh/configs/sh7785lcr_32bit_defconfig +++ b/arch/sh/configs/sh7785lcr_32bit_defconfig @@ -66,7 +66,6 @@ CONFIG_INPUT_FF_MEMLESS=m CONFIG_INPUT_EVDEV=y CONFIG_INPUT_EVBUG=m CONFIG_VT_HW_CONSOLE_BINDING=y -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_SH_SCI=y CONFIG_SERIAL_SH_SCI_NR_UARTS=6 CONFIG_SERIAL_SH_SCI_CONSOLE=y diff --git a/arch/sparc/configs/sparc64_defconfig b/arch/sparc/configs/sparc64_defconfig index 12a4fb0bd52a..18099099583e 100644 --- a/arch/sparc/configs/sparc64_defconfig +++ b/arch/sparc/configs/sparc64_defconfig @@ -122,7 +122,6 @@ CONFIG_INPUT_SPARCSPKR=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_PCIPS2=m CONFIG_SERIO_RAW=m -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_SUNSU=y CONFIG_SERIAL_SUNSU_CONSOLE=y CONFIG_SERIAL_SUNSAB=y diff --git a/arch/xtensa/configs/xip_kc705_defconfig b/arch/xtensa/configs/xip_kc705_defconfig index 4f1ff9531f6a..062148e17135 100644 --- a/arch/xtensa/configs/xip_kc705_defconfig +++ b/arch/xtensa/configs/xip_kc705_defconfig @@ -72,7 +72,6 @@ CONFIG_MARVELL_PHY=y # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set -CONFIG_DEVKMEM=y CONFIG_SERIAL_8250=y # CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set CONFIG_SERIAL_8250_CONSOLE=y diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig index d229a2d0c017..b151e0fcdeb5 100644 --- a/drivers/char/Kconfig +++ b/drivers/char/Kconfig @@ -334,16 +334,6 @@ config DEVMEM memory. When in doubt, say "Y". -config DEVKMEM - bool "/dev/kmem virtual device support" - # On arm64, VMALLOC_START < PAGE_OFFSET, which confuses kmem read/write - depends on !ARM64 - help - Say Y here if you want to support the /dev/kmem device. The - /dev/kmem device is rarely used, but can be used for certain - kind of kernel debugging operations. - When in doubt, say "N". - config NVRAM tristate "/dev/nvram support" depends on X86 || HAVE_ARCH_NVRAM_OPS diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 869b9f5e8e03..15dc54fa1d47 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -403,221 +403,6 @@ static int mmap_mem(struct file *file, struct vm_area_struct *vma) return 0; } -static int mmap_kmem(struct file *file, struct vm_area_struct *vma) -{ - unsigned long pfn; - - /* Turn a kernel-virtual address into a physical page frame */ - pfn = __pa((u64)vma->vm_pgoff << PAGE_SHIFT) >> PAGE_SHIFT; - - /* - * RED-PEN: on some architectures there is more mapped memory than - * available in mem_map which pfn_valid checks for. Perhaps should add a - * new macro here. - * - * RED-PEN: vmalloc is not supported right now. - */ - if (!pfn_valid(pfn)) - return -EIO; - - vma->vm_pgoff = pfn; - return mmap_mem(file, vma); -} - -/* - * This function reads the *virtual* memory as seen by the kernel. - */ -static ssize_t read_kmem(struct file *file, char __user *buf, - size_t count, loff_t *ppos) -{ - unsigned long p = *ppos; - ssize_t low_count, read, sz; - char *kbuf; /* k-addr because vread() takes vmlist_lock rwlock */ - int err = 0; - - read = 0; - if (p < (unsigned long) high_memory) { - low_count = count; - if (count > (unsigned long)high_memory - p) - low_count = (unsigned long)high_memory - p; - -#ifdef __ARCH_HAS_NO_PAGE_ZERO_MAPPED - /* we don't have page 0 mapped on sparc and m68k.. */ - if (p < PAGE_SIZE && low_count > 0) { - sz = size_inside_page(p, low_count); - if (clear_user(buf, sz)) - return -EFAULT; - buf += sz; - p += sz; - read += sz; - low_count -= sz; - count -= sz; - } -#endif - while (low_count > 0) { - sz = size_inside_page(p, low_count); - - /* - * On ia64 if a page has been mapped somewhere as - * uncached, then it must also be accessed uncached - * by the kernel or data corruption may occur - */ - kbuf = xlate_dev_kmem_ptr((void *)p); - if (!virt_addr_valid(kbuf)) - return -ENXIO; - - if (copy_to_user(buf, kbuf, sz)) - return -EFAULT; - buf += sz; - p += sz; - read += sz; - low_count -= sz; - count -= sz; - if (should_stop_iteration()) { - count = 0; - break; - } - } - } - - if (count > 0) { - kbuf = (char *)__get_free_page(GFP_KERNEL); - if (!kbuf) - return -ENOMEM; - while (count > 0) { - sz = size_inside_page(p, count); - if (!is_vmalloc_or_module_addr((void *)p)) { - err = -ENXIO; - break; - } - sz = vread(kbuf, (char *)p, sz); - if (!sz) - break; - if (copy_to_user(buf, kbuf, sz)) { - err = -EFAULT; - break; - } - count -= sz; - buf += sz; - read += sz; - p += sz; - if (should_stop_iteration()) - break; - } - free_page((unsigned long)kbuf); - } - *ppos = p; - return read ? read : err; -} - - -static ssize_t do_write_kmem(unsigned long p, const char __user *buf, - size_t count, loff_t *ppos) -{ - ssize_t written, sz; - unsigned long copied; - - written = 0; -#ifdef __ARCH_HAS_NO_PAGE_ZERO_MAPPED - /* we don't have page 0 mapped on sparc and m68k.. */ - if (p < PAGE_SIZE) { - sz = size_inside_page(p, count); - /* Hmm. Do something? */ - buf += sz; - p += sz; - count -= sz; - written += sz; - } -#endif - - while (count > 0) { - void *ptr; - - sz = size_inside_page(p, count); - - /* - * On ia64 if a page has been mapped somewhere as uncached, then - * it must also be accessed uncached by the kernel or data - * corruption may occur. - */ - ptr = xlate_dev_kmem_ptr((void *)p); - if (!virt_addr_valid(ptr)) - return -ENXIO; - - copied = copy_from_user(ptr, buf, sz); - if (copied) { - written += sz - copied; - if (written) - break; - return -EFAULT; - } - buf += sz; - p += sz; - count -= sz; - written += sz; - if (should_stop_iteration()) - break; - } - - *ppos += written; - return written; -} - -/* - * This function writes to the *virtual* memory as seen by the kernel. - */ -static ssize_t write_kmem(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) -{ - unsigned long p = *ppos; - ssize_t wrote = 0; - ssize_t virtr = 0; - char *kbuf; /* k-addr because vwrite() takes vmlist_lock rwlock */ - int err = 0; - - if (p < (unsigned long) high_memory) { - unsigned long to_write = min_t(unsigned long, count, - (unsigned long)high_memory - p); - wrote = do_write_kmem(p, buf, to_write, ppos); - if (wrote != to_write) - return wrote; - p += wrote; - buf += wrote; - count -= wrote; - } - - if (count > 0) { - kbuf = (char *)__get_free_page(GFP_KERNEL); - if (!kbuf) - return wrote ? wrote : -ENOMEM; - while (count > 0) { - unsigned long sz = size_inside_page(p, count); - unsigned long n; - - if (!is_vmalloc_or_module_addr((void *)p)) { - err = -ENXIO; - break; - } - n = copy_from_user(kbuf, buf, sz); - if (n) { - err = -EFAULT; - break; - } - vwrite(kbuf, (char *)p, sz); - count -= sz; - buf += sz; - virtr += sz; - p += sz; - if (should_stop_iteration()) - break; - } - free_page((unsigned long)kbuf); - } - - *ppos = p; - return virtr + wrote ? : err; -} - static ssize_t read_port(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -855,7 +640,6 @@ static int open_port(struct inode *inode, struct file *filp) #define write_zero write_null #define write_iter_zero write_iter_null #define open_mem open_port -#define open_kmem open_mem static const struct file_operations __maybe_unused mem_fops = { .llseek = memory_lseek, @@ -869,18 +653,6 @@ static const struct file_operations __maybe_unused mem_fops = { #endif }; -static const struct file_operations __maybe_unused kmem_fops = { - .llseek = memory_lseek, - .read = read_kmem, - .write = write_kmem, - .mmap = mmap_kmem, - .open = open_kmem, -#ifndef CONFIG_MMU - .get_unmapped_area = get_unmapped_area_mem, - .mmap_capabilities = memory_mmap_capabilities, -#endif -}; - static const struct file_operations null_fops = { .llseek = null_lseek, .read = read_null, @@ -924,9 +696,6 @@ static const struct memdev { } devlist[] = { #ifdef CONFIG_DEVMEM [DEVMEM_MINOR] = { "mem", 0, &mem_fops, FMODE_UNSIGNED_OFFSET }, -#endif -#ifdef CONFIG_DEVKMEM - [2] = { "kmem", 0, &kmem_fops, FMODE_UNSIGNED_OFFSET }, #endif [3] = { "null", 0666, &null_fops, 0 }, #ifdef CONFIG_DEVPORT diff --git a/include/linux/fs.h b/include/linux/fs.h index acef282b97c6..c3c88fdb9b2a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -145,7 +145,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)0x1000) -/* File is huge (eg. /dev/kmem): treat loff_t as unsigned */ +/* File is huge (eg. /dev/mem): treat loff_t as unsigned */ #define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000) /* File is opened with O_PATH; almost nothing can be done with it */ diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 394d03cc0e92..f31ba59fb1ef 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -227,7 +227,7 @@ static inline void set_vm_flush_reset_perms(void *addr) } #endif -/* for /dev/kmem */ +/* for /proc/kcore */ extern long vread(char *buf, char *addr, unsigned long count); extern long vwrite(char *buf, char *addr, unsigned long count); diff --git a/kernel/configs/android-base.config b/kernel/configs/android-base.config index d3fd428f4b92..eb701b2ac72f 100644 --- a/kernel/configs/android-base.config +++ b/kernel/configs/android-base.config @@ -1,5 +1,4 @@ # KEEP ALPHABETICALLY SORTED -# CONFIG_DEVKMEM is not set # CONFIG_DEVMEM is not set # CONFIG_FHANDLE is not set # CONFIG_INET_LRO is not set diff --git a/mm/ksm.c b/mm/ksm.c index b321a67ebaa9..b7cbcc7d4977 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -459,7 +459,7 @@ static inline bool ksm_test_exit(struct mm_struct *mm) * but taking great care only to touch a ksm page, in a VM_MERGEABLE vma, * in case the application has unmapped and remapped mm,addr meanwhile. * Could a ksm page appear anywhere else? Actually yes, in a VM_PFNMAP - * mmap of /dev/mem or /dev/kmem, where we would not want to touch it. + * mmap of /dev/mem, where we would not want to touch it. * * FAULT_FLAG/FOLL_REMOTE are because we do this outside the context * of the process that owns 'vma'. We also do not want to enforce diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 9c539f0730a5..2868692c6807 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3219,7 +3219,7 @@ static int aligned_vwrite(char *buf, char *addr, unsigned long count) * Note: In usual ops, vread() is never necessary because the caller * should know vmalloc() area is valid and can use memcpy(). * This is for routines which have to access vmalloc area without - * any information, as /dev/kmem. + * any information, as /proc/kcore. * * Return: number of bytes for which addr and buf should be increased * (same number as @count) or %0 if [addr...addr+count) doesn't -- cgit v1.2.3-71-gd317 From 48207f7d41c8bdae94d2aae11620ed76fee95d45 Mon Sep 17 00:00:00 2001 From: zhouchuangao Date: Thu, 6 May 2021 18:06:27 -0700 Subject: kernel/umh.c: fix some spelling mistakes Fix some spelling mistakes, and modify the order of the parameter comments to be consistent with the order of the parameters passed to the function. Link: https://lkml.kernel.org/r/1615636139-4076-1-git-send-email-zhouchuangao@vivo.com Signed-off-by: zhouchuangao Acked-by: Luis Chamberlain Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/umh.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/umh.c b/kernel/umh.c index 61f6b82c354b..36c123360ab8 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -338,8 +338,8 @@ static void helper_unlock(void) * @argv: arg vector for process * @envp: environment for process * @gfp_mask: gfp mask for memory allocation - * @cleanup: a cleanup function * @init: an init function + * @cleanup: a cleanup function * @data: arbitrary context sensitive data * * Returns either %NULL on allocation failure, or a subprocess_info @@ -350,7 +350,7 @@ static void helper_unlock(void) * exec. A non-zero return code causes the process to error out, exit, * and return the failure to the calling process * - * The cleanup function is just before ethe subprocess_info is about to + * The cleanup function is just before the subprocess_info is about to * be freed. This can be used for freeing the argv and envp. The * Function must be runnable in either a process context or the * context in which call_usermodehelper_exec is called. @@ -386,7 +386,7 @@ EXPORT_SYMBOL(call_usermodehelper_setup); /** * call_usermodehelper_exec - start a usermode application - * @sub_info: information about the subprocessa + * @sub_info: information about the subprocess * @wait: wait for the application to finish and return status. * when UMH_NO_WAIT don't wait at all, but you get no useful error back * when the program couldn't be exec'ed. This makes it safe to call -- cgit v1.2.3-71-gd317 From a12f4f85bc5a70ff5b74a274d3074f12e1122913 Mon Sep 17 00:00:00 2001 From: Xiaofeng Cao Date: Thu, 6 May 2021 18:06:30 -0700 Subject: kernel/user_namespace.c: fix typos change 'verifing' to 'verifying' change 'certaint' to 'certain' change 'approprpiate' to 'appropriate' Link: https://lkml.kernel.org/r/20210317100129.12440-1-caoxiaofeng@yulong.com Signed-off-by: Xiaofeng Cao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/user_namespace.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 9a4b980d695b..8d62863721b0 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -85,7 +85,7 @@ int create_user_ns(struct cred *new) /* * Verify that we can not violate the policy of which files * may be accessed that is specified by the root directory, - * by verifing that the root directory is at the root of the + * by verifying that the root directory is at the root of the * mount namespace which allows all files to be accessed. */ ret = -EPERM; @@ -1014,7 +1014,7 @@ static ssize_t map_write(struct file *file, const char __user *buf, goto out; ret = -EINVAL; } - /* Be very certaint the new map actually exists */ + /* Be very certain the new map actually exists */ if (new_map.nr_extents == 0) goto out; @@ -1169,7 +1169,7 @@ static bool new_idmap_permitted(const struct file *file, /* Allow the specified ids if we have the appropriate capability * (CAP_SETUID or CAP_SETGID) over the parent user namespace. - * And the opener of the id file also had the approprpiate capability. + * And the opener of the id file also has the appropriate capability. */ if (ns_capable(ns->parent, cap_setid) && file_ns_capable(file, ns->parent, cap_setid)) -- cgit v1.2.3-71-gd317 From f0fffaff0b8960c9a110211510269744af1f1d1e Mon Sep 17 00:00:00 2001 From: Bhaskar Chowdhury Date: Thu, 6 May 2021 18:06:33 -0700 Subject: kernel/up.c: fix typo s/condtions/conditions/ Link: https://lkml.kernel.org/r/20210317032732.3260835-1-unixbhaskar@gmail.com Signed-off-by: Bhaskar Chowdhury Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/up.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/up.c b/kernel/up.c index bf20b4a9af60..df50828cc2f0 100644 --- a/kernel/up.c +++ b/kernel/up.c @@ -38,7 +38,7 @@ EXPORT_SYMBOL(smp_call_function_single_async); /* * Preemption is disabled here to make sure the cond_func is called under the - * same condtions in UP and SMP. + * same conditions in UP and SMP. */ void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, void *info, bool wait, const struct cpumask *mask) -- cgit v1.2.3-71-gd317 From 5afe69c2ccd069112fd299b573d30d6b14528b6c Mon Sep 17 00:00:00 2001 From: Xiaofeng Cao Date: Thu, 6 May 2021 18:06:36 -0700 Subject: kernel/sys.c: fix typo change 'infite' to 'infinite' change 'concurent' to 'concurrent' change 'memvers' to 'members' change 'decendants' to 'descendants' change 'argumets' to 'arguments' Link: https://lkml.kernel.org/r/20210316112904.10661-1-cxfcosmos@gmail.com Signed-off-by: Xiaofeng Cao Acked-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sys.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/sys.c b/kernel/sys.c index 3d62c9599dc0..3a583a29815f 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1590,7 +1590,7 @@ int do_prlimit(struct task_struct *tsk, unsigned int resource, /* * RLIMIT_CPU handling. Arm the posix CPU timer if the limit is not - * infite. In case of RLIM_INFINITY the posix CPU timer code + * infinite. In case of RLIM_INFINITY the posix CPU timer code * ignores the rlimit. */ if (!retval && new_rlim && resource == RLIMIT_CPU && @@ -2029,7 +2029,7 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data } /* - * arg_lock protects concurent updates but we still need mmap_lock for + * arg_lock protects concurrent updates but we still need mmap_lock for * read to exclude races with sys_brk. */ mmap_read_lock(mm); @@ -2041,7 +2041,7 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data * output in procfs mostly, except * * - @start_brk/@brk which are used in do_brk_flags but kernel lookups - * for VMAs when updating these memvers so anything wrong written + * for VMAs when updating these members so anything wrong written * here cause kernel to swear at userspace program but won't lead * to any problem in kernel itself */ @@ -2143,7 +2143,7 @@ static int prctl_set_mm(int opt, unsigned long addr, error = -EINVAL; /* - * arg_lock protects concurent updates of arg boundaries, we need + * arg_lock protects concurrent updates of arg boundaries, we need * mmap_lock for a) concurrent sys_brk, b) finding VMA for addr * validation. */ @@ -2210,7 +2210,7 @@ static int prctl_set_mm(int opt, unsigned long addr, * If command line arguments and environment * are placed somewhere else on stack, we can * set them up here, ARG_START/END to setup - * command line argumets and ENV_START/END + * command line arguments and ENV_START/END * for environment. */ case PR_SET_MM_START_STACK: @@ -2258,8 +2258,8 @@ static int prctl_get_tid_address(struct task_struct *me, int __user * __user *ti static int propagate_has_child_subreaper(struct task_struct *p, void *data) { /* - * If task has has_child_subreaper - all its decendants - * already have these flag too and new decendants will + * If task has has_child_subreaper - all its descendants + * already have these flag too and new descendants will * inherit it on fork, skip them. * * If we've found child_reaper - skip descendants in -- cgit v1.2.3-71-gd317