From 543c37cb165049c3be24a0d4733e67caa2b33eef Mon Sep 17 00:00:00 2001 From: Emese Revfy Date: Tue, 24 May 2016 00:11:37 +0200 Subject: Add sancov plugin The sancov gcc plugin inserts a __sanitizer_cov_trace_pc() call at the start of basic blocks. This plugin is a helper plugin for the kcov feature. It supports all gcc versions with plugin support (from gcc-4.5 on). It is based on the gcc commit "Add fuzzing coverage support" by Dmitry Vyukov (https://gcc.gnu.org/viewcvs/gcc?limit_changes=0&view=revision&revision=231296). Signed-off-by: Emese Revfy Acked-by: Kees Cook Signed-off-by: Michal Marek --- lib/Kconfig.debug | 2 ++ 1 file changed, 2 insertions(+) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 77d7d034bac3..b7827dca3fec 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -708,6 +708,8 @@ config KCOV bool "Code coverage for fuzzing" depends on ARCH_HAS_KCOV select DEBUG_FS + select GCC_PLUGINS + select GCC_PLUGIN_SANCOV help KCOV exposes kernel code coverage information in a form suitable for coverage-guided fuzzing (randomized testing). -- cgit v1.2.3 From a519167e753e6a89476115375b65a7eb6ec485b3 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Sat, 11 Jun 2016 09:09:28 -0700 Subject: gcc-plugins: disable under COMPILE_TEST Since adding the gcc plugin development headers is required for the gcc plugin support, we should ease into this new kernel build dependency more slowly. For now, disable the gcc plugins under COMPILE_TEST so that all*config builds will skip it. Signed-off-by: Kees Cook Signed-off-by: Michal Marek --- lib/Kconfig.debug | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index b7827dca3fec..7936e5e4da9d 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -708,8 +708,8 @@ config KCOV bool "Code coverage for fuzzing" depends on ARCH_HAS_KCOV select DEBUG_FS - select GCC_PLUGINS - select GCC_PLUGIN_SANCOV + select GCC_PLUGINS if !COMPILE_TEST + select GCC_PLUGIN_SANCOV if !COMPILE_TEST help KCOV exposes kernel code coverage information in a form suitable for coverage-guided fuzzing (randomized testing). -- cgit v1.2.3 From 4816c9406430d0d3d4fa58a212a7a869d429b315 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 28 Jul 2016 13:29:17 +0800 Subject: lib/mpi: Fix SG miter leak In mpi_read_raw_from_sgl we may leak the SG miter resouces after reading the leading zeroes. This patch fixes this by stopping the iteration once the leading zeroes have been read. Fixes: 127827b9c295 ("lib/mpi: Do not do sg_virt") Reported-by: Nicolai Stange Tested-by: Nicolai Stange Signed-off-by: Herbert Xu --- lib/mpi/mpicoder.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'lib') diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c index c6272ae2015e..5a0f75a3bf01 100644 --- a/lib/mpi/mpicoder.c +++ b/lib/mpi/mpicoder.c @@ -363,6 +363,9 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes) lzeros = 0; } + miter.consumed = lzeros; + sg_miter_stop(&miter); + nbytes -= lzeros; nbits = nbytes * 8; if (nbits > MAX_EXTERN_MPI_BITS) { @@ -390,7 +393,10 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes) z = BYTES_PER_MPI_LIMB - nbytes % BYTES_PER_MPI_LIMB; z %= BYTES_PER_MPI_LIMB; - for (;;) { + while (sg_miter_next(&miter)) { + buff = miter.addr; + len = miter.length; + for (x = 0; x < len; x++) { a <<= 8; a |= *buff++; @@ -400,12 +406,6 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes) } } z += x; - - if (!sg_miter_next(&miter)) - break; - - buff = miter.addr; - len = miter.length; } return val; -- cgit v1.2.3 From 05eb6e7263185a6bb0de9501ccf2addc52429414 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Tue, 2 Aug 2016 14:03:01 -0700 Subject: radix-tree: account nodes to memcg only if explicitly requested Radix trees may be used not only for storing page cache pages, so unconditionally accounting radix tree nodes to the current memory cgroup is bad: if a radix tree node is used for storing data shared among different cgroups we risk pinning dead memory cgroups forever. So let's only account radix tree nodes if it was explicitly requested by passing __GFP_ACCOUNT to INIT_RADIX_TREE. Currently, we only want to account page cache entries, so mark mapping->page_tree so. Fixes: 58e698af4c63 ("radix-tree: account radix_tree_node to memory cgroup") Link: http://lkml.kernel.org/r/1470057188-7864-1-git-send-email-vdavydov@virtuozzo.com Signed-off-by: Vladimir Davydov Acked-by: Johannes Weiner Acked-by: Michal Hocko Cc: [4.6+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/radix-tree.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 61b8fb529cef..1b7bf7314141 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -277,10 +277,11 @@ radix_tree_node_alloc(struct radix_tree_root *root) /* * Even if the caller has preloaded, try to allocate from the - * cache first for the new node to get accounted. + * cache first for the new node to get accounted to the memory + * cgroup. */ ret = kmem_cache_alloc(radix_tree_node_cachep, - gfp_mask | __GFP_ACCOUNT | __GFP_NOWARN); + gfp_mask | __GFP_NOWARN); if (ret) goto out; @@ -303,8 +304,7 @@ radix_tree_node_alloc(struct radix_tree_root *root) kmemleak_update_trace(ret); goto out; } - ret = kmem_cache_alloc(radix_tree_node_cachep, - gfp_mask | __GFP_ACCOUNT); + ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); out: BUG_ON(radix_tree_is_internal_node(ret)); return ret; @@ -351,6 +351,12 @@ static int __radix_tree_preload(gfp_t gfp_mask, int nr) struct radix_tree_node *node; int ret = -ENOMEM; + /* + * Nodes preloaded by one cgroup can be be used by another cgroup, so + * they should never be accounted to any particular memory cgroup. + */ + gfp_mask &= ~__GFP_ACCOUNT; + preempt_disable(); rtp = this_cpu_ptr(&radix_tree_preloads); while (rtp->nr < nr) { -- cgit v1.2.3 From 901d805c33fc4c029fc6b2d94ee5fb7d30278045 Mon Sep 17 00:00:00 2001 From: Nicolas Iooss Date: Tue, 2 Aug 2016 14:03:10 -0700 Subject: UBSAN: fix typo in format string handle_object_size_mismatch() used %pk to format a kernel pointer with pr_err(). This seemed to be a misspelling for %pK, but using this to format a kernel pointer does not make much sence here. Therefore use %p instead, like in handle_missaligned_access(). Link: http://lkml.kernel.org/r/20160730083010.11569-1-nicolas.iooss_linux@m4x.org Signed-off-by: Nicolas Iooss Acked-by: Andrey Ryabinin Cc: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/ubsan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/ubsan.c b/lib/ubsan.c index 8799ae5e2e42..fb0409df1bcf 100644 --- a/lib/ubsan.c +++ b/lib/ubsan.c @@ -308,7 +308,7 @@ static void handle_object_size_mismatch(struct type_mismatch_data *data, return; ubsan_prologue(&data->location, &flags); - pr_err("%s address %pk with insufficient space\n", + pr_err("%s address %p with insufficient space\n", type_check_kinds[data->type_check_kind], (void *) ptr); pr_err("for an object of type %s\n", data->type->type_name); -- cgit v1.2.3 From 6b1d174b0c27b5de421eda55c2731f32b6bd9852 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 2 Aug 2016 14:04:04 -0700 Subject: ratelimit: extend to print suppressed messages on release MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Extend the ratelimiting facility to print the amount of suppressed lines when it is being released. This use case is aimed at short-termed, burst-like users for which we want to output the suppressed lines stats only once, after it has been disposed of. For an example, see /dev/kmsg usage in a follow-on patch. Also, change the printk() line we issue on release to not use "callbacks" as it is misleading: we're not suppressing callbacks but printk() calls. This has been separated from a previous patch by Linus. Link: http://lkml.kernel.org/r/20160716061745.15795-2-bp@alien8.de Signed-off-by: Borislav Petkov Cc: Dave Young Cc: Franck Bui Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Uwe Kleine-König Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/ratelimit.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/ratelimit.c b/lib/ratelimit.c index 2c5de86460c5..08f8043cac61 100644 --- a/lib/ratelimit.c +++ b/lib/ratelimit.c @@ -46,12 +46,14 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func) rs->begin = jiffies; if (time_is_before_jiffies(rs->begin + rs->interval)) { - if (rs->missed) - printk(KERN_WARNING "%s: %d callbacks suppressed\n", - func, rs->missed); + if (rs->missed) { + if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) { + pr_warn("%s: %d callbacks suppressed\n", func, rs->missed); + rs->missed = 0; + } + } rs->begin = jiffies; rs->printed = 0; - rs->missed = 0; } if (rs->burst && rs->burst > rs->printed) { rs->printed++; -- cgit v1.2.3 From f003a1f182bb821f13775338a4bf8711830f927a Mon Sep 17 00:00:00 2001 From: Sebastian Ott Date: Tue, 2 Aug 2016 14:04:13 -0700 Subject: lib/iommu-helper: skip to next segment When a large enough area in the iommu bitmap is found but would span a boundary we continue the search starting from the next bit position. For large allocations this can lead to several useless invocations of bitmap_find_next_zero_area() and iommu_is_span_boundary(). Continue the search from the start of the next segment (which is the next bit position such that we'll not cross the same segment boundary again). Link: http://lkml.kernel.org/r/alpine.LFD.2.20.1606081910070.3211@schleppi Signed-off-by: Sebastian Ott Reviewed-by: Gerald Schaefer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/iommu-helper.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/iommu-helper.c b/lib/iommu-helper.c index c27e269210c4..a816f3a80625 100644 --- a/lib/iommu-helper.c +++ b/lib/iommu-helper.c @@ -29,8 +29,7 @@ again: index = bitmap_find_next_zero_area(map, size, start, nr, align_mask); if (index < size) { if (iommu_is_span_boundary(index, nr, shift, boundary_size)) { - /* we could do more effectively */ - start = index + 1; + start = ALIGN(shift + index, boundary_size) - shift; goto again; } bitmap_set(map, index, nr); -- cgit v1.2.3 From a9bfd3321713ecec86282dd2bec04212189f91f1 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 2 Aug 2016 14:04:16 -0700 Subject: crc32: use ktime_get_ns() for measurement The crc32 test function measures the elapsed time in nanoseconds, but uses 'struct timespec' for that. We want to remove timespec from the kernel for y2038 compatibility, and ktime_get_ns() also helps make the code simpler here. It is also slightly better to use monontonic time, as we are only interested in the time difference. Link: http://lkml.kernel.org/r/20160617143932.3289626-1-arnd@arndb.de Signed-off-by: Arnd Bergmann Cc: "David S . Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/crc32.c | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) (limited to 'lib') diff --git a/lib/crc32.c b/lib/crc32.c index 9a907d489d95..7fbd1a112b9d 100644 --- a/lib/crc32.c +++ b/lib/crc32.c @@ -979,7 +979,6 @@ static int __init crc32c_test(void) int i; int errors = 0; int bytes = 0; - struct timespec start, stop; u64 nsec; unsigned long flags; @@ -999,20 +998,17 @@ static int __init crc32c_test(void) local_irq_save(flags); local_irq_disable(); - getnstimeofday(&start); + nsec = ktime_get_ns(); for (i = 0; i < 100; i++) { if (test[i].crc32c_le != __crc32c_le(test[i].crc, test_buf + test[i].start, test[i].length)) errors++; } - getnstimeofday(&stop); + nsec = ktime_get_ns() - nsec; local_irq_restore(flags); local_irq_enable(); - nsec = stop.tv_nsec - start.tv_nsec + - 1000000000 * (stop.tv_sec - start.tv_sec); - pr_info("crc32c: CRC_LE_BITS = %d\n", CRC_LE_BITS); if (errors) @@ -1065,7 +1061,6 @@ static int __init crc32_test(void) int i; int errors = 0; int bytes = 0; - struct timespec start, stop; u64 nsec; unsigned long flags; @@ -1088,7 +1083,7 @@ static int __init crc32_test(void) local_irq_save(flags); local_irq_disable(); - getnstimeofday(&start); + nsec = ktime_get_ns(); for (i = 0; i < 100; i++) { if (test[i].crc_le != crc32_le(test[i].crc, test_buf + test[i].start, test[i].length)) @@ -1098,14 +1093,11 @@ static int __init crc32_test(void) test[i].start, test[i].length)) errors++; } - getnstimeofday(&stop); + nsec = ktime_get_ns() - nsec; local_irq_restore(flags); local_irq_enable(); - nsec = stop.tv_nsec - start.tv_nsec + - 1000000000 * (stop.tv_sec - start.tv_sec); - pr_info("crc32: CRC_LE_BITS = %d, CRC_BE BITS = %d\n", CRC_LE_BITS, CRC_BE_BITS); -- cgit v1.2.3 From a4691deabf284a601149a067525759939cc563b2 Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Tue, 2 Aug 2016 14:07:30 -0700 Subject: kcov: allow more fine-grained coverage instrumentation For more targeted fuzzing, it's better to disable kernel-wide instrumentation and instead enable it on a per-subsystem basis. This follows the pattern of UBSAN and allows you to compile in the kcov driver without instrumenting the whole kernel. To instrument a part of the kernel, you can use either # for a single file in the current directory KCOV_INSTRUMENT_filename.o := y or # for all the files in the current directory (excluding subdirectories) KCOV_INSTRUMENT := y or # (same as above) ccflags-y += $(CFLAGS_KCOV) or # for all the files in the current directory (including subdirectories) subdir-ccflags-y += $(CFLAGS_KCOV) Link: http://lkml.kernel.org/r/1464008380-11405-1-git-send-email-vegard.nossum@oracle.com Signed-off-by: Vegard Nossum Cc: Dmitry Vyukov Cc: Quentin Casasnovas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/Kconfig.debug | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index f07842e2d69f..cc02f282d05b 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -719,6 +719,17 @@ config KCOV For more details, see Documentation/kcov.txt. +config KCOV_INSTRUMENT_ALL + bool "Instrument all code by default" + depends on KCOV + default y if KCOV + help + If you are doing generic system call fuzzing (like e.g. syzkaller), + then you will want to instrument the whole kernel and you should + say y here. If you are doing more targeted fuzzing (like e.g. + filesystem fuzzing with AFL) then you will want to enable coverage + for more specific subsets of files, and should say n here. + config DEBUG_SHIRQ bool "Debug shared IRQ handlers" depends on DEBUG_KERNEL -- cgit v1.2.3 From 00085f1efa387a8ce100e3734920f7639c80caa3 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 3 Aug 2016 13:46:00 -0700 Subject: dma-mapping: use unsigned long for dma_attrs The dma-mapping core and the implementations do not change the DMA attributes passed by pointer. Thus the pointer can point to const data. However the attributes do not have to be a bitfield. Instead unsigned long will do fine: 1. This is just simpler. Both in terms of reading the code and setting attributes. Instead of initializing local attributes on the stack and passing pointer to it to dma_set_attr(), just set the bits. 2. It brings safeness and checking for const correctness because the attributes are passed by value. Semantic patches for this change (at least most of them): virtual patch virtual context @r@ identifier f, attrs; @@ f(..., - struct dma_attrs *attrs + unsigned long attrs , ...) { ... } @@ identifier r.f; @@ f(..., - NULL + 0 ) and // Options: --all-includes virtual patch virtual context @r@ identifier f, attrs; type t; @@ t f(..., struct dma_attrs *attrs); @@ identifier r.f; @@ f(..., - NULL + 0 ) Link: http://lkml.kernel.org/r/1468399300-5399-2-git-send-email-k.kozlowski@samsung.com Signed-off-by: Krzysztof Kozlowski Acked-by: Vineet Gupta Acked-by: Robin Murphy Acked-by: Hans-Christian Noren Egtvedt Acked-by: Mark Salter [c6x] Acked-by: Jesper Nilsson [cris] Acked-by: Daniel Vetter [drm] Reviewed-by: Bart Van Assche Acked-by: Joerg Roedel [iommu] Acked-by: Fabien Dessenne [bdisp] Reviewed-by: Marek Szyprowski [vb2-core] Acked-by: David Vrabel [xen] Acked-by: Konrad Rzeszutek Wilk [xen swiotlb] Acked-by: Joerg Roedel [iommu] Acked-by: Richard Kuo [hexagon] Acked-by: Geert Uytterhoeven [m68k] Acked-by: Gerald Schaefer [s390] Acked-by: Bjorn Andersson Acked-by: Hans-Christian Noren Egtvedt [avr32] Acked-by: Vineet Gupta [arc] Acked-by: Robin Murphy [arm64 and dma-iommu] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/dma-noop.c | 9 +++++---- lib/swiotlb.c | 13 +++++++------ 2 files changed, 12 insertions(+), 10 deletions(-) (limited to 'lib') diff --git a/lib/dma-noop.c b/lib/dma-noop.c index 72145646857e..3d766e78fbe2 100644 --- a/lib/dma-noop.c +++ b/lib/dma-noop.c @@ -10,7 +10,7 @@ static void *dma_noop_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, - struct dma_attrs *attrs) + unsigned long attrs) { void *ret; @@ -22,7 +22,7 @@ static void *dma_noop_alloc(struct device *dev, size_t size, static void dma_noop_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, - struct dma_attrs *attrs) + unsigned long attrs) { free_pages((unsigned long)cpu_addr, get_order(size)); } @@ -30,13 +30,14 @@ static void dma_noop_free(struct device *dev, size_t size, static dma_addr_t dma_noop_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { return page_to_phys(page) + offset; } static int dma_noop_map_sg(struct device *dev, struct scatterlist *sgl, int nents, - enum dma_data_direction dir, struct dma_attrs *attrs) + enum dma_data_direction dir, + unsigned long attrs) { int i; struct scatterlist *sg; diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 76f29ecba8f4..22e13a0e19d7 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -738,7 +738,7 @@ swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir, dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { phys_addr_t map, phys = page_to_phys(page) + offset; dma_addr_t dev_addr = phys_to_dma(dev, phys); @@ -807,7 +807,7 @@ static void unmap_single(struct device *hwdev, dma_addr_t dev_addr, void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { unmap_single(hwdev, dev_addr, size, dir); } @@ -877,7 +877,7 @@ EXPORT_SYMBOL(swiotlb_sync_single_for_device); */ int swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, - enum dma_data_direction dir, struct dma_attrs *attrs) + enum dma_data_direction dir, unsigned long attrs) { struct scatterlist *sg; int i; @@ -914,7 +914,7 @@ int swiotlb_map_sg(struct device *hwdev, struct scatterlist *sgl, int nelems, enum dma_data_direction dir) { - return swiotlb_map_sg_attrs(hwdev, sgl, nelems, dir, NULL); + return swiotlb_map_sg_attrs(hwdev, sgl, nelems, dir, 0); } EXPORT_SYMBOL(swiotlb_map_sg); @@ -924,7 +924,8 @@ EXPORT_SYMBOL(swiotlb_map_sg); */ void swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, - int nelems, enum dma_data_direction dir, struct dma_attrs *attrs) + int nelems, enum dma_data_direction dir, + unsigned long attrs) { struct scatterlist *sg; int i; @@ -941,7 +942,7 @@ void swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems, enum dma_data_direction dir) { - return swiotlb_unmap_sg_attrs(hwdev, sgl, nelems, dir, NULL); + return swiotlb_unmap_sg_attrs(hwdev, sgl, nelems, dir, 0); } EXPORT_SYMBOL(swiotlb_unmap_sg); -- cgit v1.2.3 From 9049fc745300c5e2236cbfc69f5e8cadb6f1f57c Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Wed, 3 Aug 2016 13:46:39 -0700 Subject: dynamic_debug: add jump label support Although dynamic debug is often only used for debug builds, sometimes its enabled for production builds as well. Minimize its impact by using jump labels. This reduces the text section by 7000+ bytes in the kernel image below. It does increase data, but this should only be referenced when changing the direction of the branches, and hence usually not in cache. text data bss dec hex filename 8194852 4879776 925696 14000324 d5a0c4 vmlinux.pre 8187337 4960224 925696 14073257 d6bda9 vmlinux.post Link: http://lkml.kernel.org/r/d165b465e8c89bc582d973758d40be44c33f018b.1467837322.git.jbaron@akamai.com Signed-off-by: Jason Baron Cc: "David S. Miller" Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Chris Metcalf Cc: Heiko Carstens Cc: Joe Perches Cc: Martin Schwidefsky Cc: Michael Ellerman Cc: Paul Mackerras Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/dynamic_debug.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'lib') diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index fe42b6ec3f0c..da796e2dc4f5 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -188,6 +188,13 @@ static int ddebug_change(const struct ddebug_query *query, newflags = (dp->flags & mask) | flags; if (newflags == dp->flags) continue; +#ifdef HAVE_JUMP_LABEL + if (dp->flags & _DPRINTK_FLAGS_PRINT) { + if (!(flags & _DPRINTK_FLAGS_PRINT)) + static_branch_disable(&dp->key.dd_key_true); + } else if (flags & _DPRINTK_FLAGS_PRINT) + static_branch_enable(&dp->key.dd_key_true); +#endif dp->flags = newflags; vpr_info("changed %s:%d [%s]%s =%s\n", trim_prefix(dp->filename), dp->lineno, -- cgit v1.2.3 From 1bd4403d86a1c06cb6cc9ac87664a0c9d3413d51 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 8 Aug 2016 13:02:01 -0700 Subject: unsafe_[get|put]_user: change interface to use a error target label When I initially added the unsafe_[get|put]_user() helpers in commit 5b24a7a2aa20 ("Add 'unsafe' user access functions for batched accesses"), I made the mistake of modeling the interface on our traditional __[get|put]_user() functions, which return zero on success, or -EFAULT on failure. That interface is fairly easy to use, but it's actually fairly nasty for good code generation, since it essentially forces the caller to check the error value for each access. In particular, since the error handling is already internally implemented with an exception handler, and we already use "asm goto" for various other things, we could fairly easily make the error cases just jump directly to an error label instead, and avoid the need for explicit checking after each operation. So switch the interface to pass in an error label, rather than checking the error value in the caller. Best do it now before we start growing more users (the signal handling code in particular would be a good place to use the new interface). So rather than if (unsafe_get_user(x, ptr)) ... handle error .. the interface is now unsafe_get_user(x, ptr, label); where an error during the user mode fetch will now just cause a jump to 'label' in the caller. Right now the actual _implementation_ of this all still ends up being a "if (err) goto label", and does not take advantage of any exception label tricks, but for "unsafe_put_user()" in particular it should be fairly straightforward to convert to using the exception table model. Note that "unsafe_get_user()" is much harder to convert to a clever exception table model, because current versions of gcc do not allow the use of "asm goto" (for the exception) with output values (for the actual value to be fetched). But that is hopefully not a limitation in the long term. [ Also note that it might be a good idea to switch unsafe_get_user() to actually _return_ the value it fetches from user space, but this commit only changes the error handling semantics ] Signed-off-by: Linus Torvalds --- lib/strncpy_from_user.c | 8 ++++---- lib/strnlen_user.c | 7 +++---- 2 files changed, 7 insertions(+), 8 deletions(-) (limited to 'lib') diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c index 33f655ef48cd..9c5fe8110413 100644 --- a/lib/strncpy_from_user.c +++ b/lib/strncpy_from_user.c @@ -40,8 +40,8 @@ static inline long do_strncpy_from_user(char *dst, const char __user *src, long unsigned long c, data; /* Fall back to byte-at-a-time if we get a page fault */ - if (unlikely(unsafe_get_user(c,(unsigned long __user *)(src+res)))) - break; + unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time); + *(unsigned long *)(dst+res) = c; if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); @@ -56,8 +56,7 @@ byte_at_a_time: while (max) { char c; - if (unlikely(unsafe_get_user(c,src+res))) - return -EFAULT; + unsafe_get_user(c,src+res, efault); dst[res] = c; if (!c) return res; @@ -76,6 +75,7 @@ byte_at_a_time: * Nope: we hit the address space limit, and we still had more * characters the caller would have wanted. That's an EFAULT. */ +efault: return -EFAULT; } diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c index 2625943625d7..8e105ed4df12 100644 --- a/lib/strnlen_user.c +++ b/lib/strnlen_user.c @@ -45,8 +45,7 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count, src -= align; max += align; - if (unlikely(unsafe_get_user(c,(unsigned long __user *)src))) - return 0; + unsafe_get_user(c, (unsigned long __user *)src, efault); c |= aligned_byte_mask(align); for (;;) { @@ -61,8 +60,7 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count, if (unlikely(max <= sizeof(unsigned long))) break; max -= sizeof(unsigned long); - if (unlikely(unsafe_get_user(c,(unsigned long __user *)(src+res)))) - return 0; + unsafe_get_user(c, (unsigned long __user *)(src+res), efault); } res -= align; @@ -77,6 +75,7 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count, * Nope: we hit the address space limit, and we still had more * characters the caller would have wanted. That's 0. */ +efault: return 0; } -- cgit v1.2.3