diff options
Diffstat (limited to 'lib')
253 files changed, 10376 insertions, 7297 deletions
diff --git a/lib/.gitignore b/lib/.gitignore index 54596b634ecb..101a4aa92fb5 100644 --- a/lib/.gitignore +++ b/lib/.gitignore @@ -5,5 +5,3 @@ /gen_crc32table /gen_crc64table /oid_registry_data.c -/test_fortify.log -/test_fortify/*.log diff --git a/lib/842/842.h b/lib/842/842.h index 7b1f581a2907..f9e8a5dd790f 100644 --- a/lib/842/842.h +++ b/lib/842/842.h @@ -78,7 +78,7 @@ #include <linux/kernel.h> #include <linux/bitops.h> #include <linux/crc32.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/sw842.h> diff --git a/lib/Kconfig b/lib/Kconfig index d33a268bc256..dccb61b7d698 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -40,6 +40,18 @@ config PACKING When in doubt, say N. +config PACKING_KUNIT_TEST + tristate "KUnit tests for packing library" if !KUNIT_ALL_TESTS + depends on PACKING && KUNIT + default KUNIT_ALL_TESTS + help + This builds KUnit tests for the packing library. + + For more information on KUnit and unit tests in general, + please refer to the KUnit documentation in Documentation/dev-tools/kunit/. + + When in doubt, say N. + config BITREVERSE tristate @@ -144,13 +156,18 @@ config CRC16 config CRC_T10DIF tristate "CRC calculation for the T10 Data Integrity Field" - select CRYPTO - select CRYPTO_CRCT10DIF help This option is only needed if a module that's not in the kernel tree needs to calculate CRC checks for use with the SCSI data integrity subsystem. +config ARCH_HAS_CRC_T10DIF + bool + +config CRC_T10DIF_ARCH + tristate + default CRC_T10DIF if ARCH_HAS_CRC_T10DIF && CRC_OPTIMIZATIONS + config CRC64_ROCKSOFT tristate "CRC calculation for the Rocksoft model CRC64" select CRC64 @@ -178,61 +195,12 @@ config CRC32 the kernel tree does. Such modules that use library CRC32/CRC32c functions require M here. -config CRC32_SELFTEST - tristate "CRC32 perform self test on init" - depends on CRC32 - help - This option enables the CRC32 library functions to perform a - self test on initialization. The self test computes crc32_le - and crc32_be over byte strings with random alignment and length - and computes the total elapsed time and number of bytes processed. - -choice - prompt "CRC32 implementation" - depends on CRC32 - default CRC32_SLICEBY8 - help - This option allows a kernel builder to override the default choice - of CRC32 algorithm. Choose the default ("slice by 8") unless you - know that you need one of the others. - -config CRC32_SLICEBY8 - bool "Slice by 8 bytes" - help - Calculate checksum 8 bytes at a time with a clever slicing algorithm. - This is the fastest algorithm, but comes with a 8KiB lookup table. - Most modern processors have enough cache to hold this table without - thrashing the cache. - - This is the default implementation choice. Choose this one unless - you have a good reason not to. - -config CRC32_SLICEBY4 - bool "Slice by 4 bytes" - help - Calculate checksum 4 bytes at a time with a clever slicing algorithm. - This is a bit slower than slice by 8, but has a smaller 4KiB lookup - table. - - Only choose this option if you know what you are doing. - -config CRC32_SARWATE - bool "Sarwate's Algorithm (one byte at a time)" - help - Calculate checksum a byte at a time using Sarwate's algorithm. This - is not particularly fast, but has a small 256 byte lookup table. - - Only choose this option if you know what you are doing. - -config CRC32_BIT - bool "Classic Algorithm (one bit at a time)" - help - Calculate checksum one bit at a time. This is VERY slow, but has - no lookup table. This is provided as a debugging option. - - Only choose this option if you are debugging crc32. +config ARCH_HAS_CRC32 + bool -endchoice +config CRC32_ARCH + tristate + default CRC32 if ARCH_HAS_CRC32 && CRC_OPTIMIZATIONS config CRC64 tristate "CRC64 functions" @@ -260,14 +228,10 @@ config CRC7 config LIBCRC32C tristate "CRC32c (Castagnoli, et al) Cyclic Redundancy-Check" - select CRYPTO - select CRYPTO_CRC32C + select CRC32 help - This option is provided for the case where no in-kernel-tree - modules require CRC32c functions, but a module built outside the - kernel tree does. Such modules that use library CRC32c functions - require M here. See Castagnoli93. - Module will be libcrc32c. + This option just selects CRC32 and is provided for compatibility + purposes until the users are updated to select CRC32 directly. config CRC8 tristate "CRC8 function" @@ -276,6 +240,17 @@ config CRC8 when they need to do cyclic redundancy check according CRC8 algorithm. Module will be called crc8. +config CRC_OPTIMIZATIONS + bool "Enable optimized CRC implementations" if EXPERT + default y + help + Disabling this option reduces code size slightly by disabling the + architecture-optimized implementations of any CRC variants that are + enabled. CRC checksumming performance may get much slower. + + Keep this enabled unless you're really trying to minimize the size of + the kernel. + config XXHASH tristate @@ -539,13 +514,7 @@ config CPUMASK_OFFSTACK stack overflow. config FORCE_NR_CPUS - bool "Set number of CPUs at compile time" - depends on SMP && EXPERT && !COMPILE_TEST - help - Say Yes if you have NR_CPUS set to an actual number of possible - CPUs in your system, not to a default value. This forces the core - code to rely on compile-time value and optimize kernel routines - better. + def_bool !SMP config CPU_RMAP bool @@ -629,6 +598,7 @@ config SIGNATURE config DIMLIB tristate + depends on NET help Dynamic Interrupt Moderation library. Implements an algorithm for dynamically changing CQ moderation values @@ -782,3 +752,9 @@ config POLYNOMIAL config FIRMWARE_TABLE bool + +config UNION_FIND + bool + +config MIN_HEAP + bool diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 8bba448c819b..1af972a92d06 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -97,7 +97,7 @@ config BOOT_PRINTK_DELAY using "boot_delay=N". It is likely that you would also need to use "lpj=M" to preset - the "loops per jiffie" value. + the "loops per jiffy" value. See a previous boot log for the "lpj" value to use for your system, and then set "lpj=M" before setting "boot_delay=N". NOTE: Using this option may adversely affect SMP systems. @@ -379,13 +379,15 @@ config DEBUG_INFO_BTF depends on !DEBUG_INFO_SPLIT && !DEBUG_INFO_REDUCED depends on !GCC_PLUGIN_RANDSTRUCT || COMPILE_TEST depends on BPF_SYSCALL - depends on !DEBUG_INFO_DWARF5 || PAHOLE_VERSION >= 121 + depends on PAHOLE_VERSION >= 116 + depends on DEBUG_INFO_DWARF4 || PAHOLE_VERSION >= 121 # pahole uses elfutils, which does not have support for Hexagon relocations depends on !HEXAGON help Generate deduplicated BTF type information from DWARF debug info. - Turning this on expects presence of pahole tool, which will convert - DWARF type info into equivalent deduplicated BTF type info. + Turning this on requires pahole v1.16 or later (v1.21 or later to + support DWARF 5), which will convert DWARF type info into equivalent + deduplicated BTF type info. config PAHOLE_HAS_SPLIT_BTF def_bool PAHOLE_VERSION >= 119 @@ -431,7 +433,7 @@ config GDB_SCRIPTS build directory. If you load vmlinux into gdb, the helper scripts will be automatically imported by gdb as well, and additional functions are available to analyze a Linux kernel - instance. See Documentation/dev-tools/gdb-kernel-debugging.rst + instance. See Documentation/process/debugging/gdb-kernel-debugging.rst for further details. endif # DEBUG_INFO @@ -571,6 +573,21 @@ config VMLINUX_MAP pieces of code get eliminated with CONFIG_LD_DEAD_CODE_DATA_ELIMINATION. +config BUILTIN_MODULE_RANGES + bool "Generate address range information for builtin modules" + depends on !LTO + depends on VMLINUX_MAP + help + When modules are built into the kernel, there will be no module name + associated with its symbols in /proc/kallsyms. Tracers may want to + identify symbols by module name and symbol name regardless of whether + the module is configured as loadable or not. + + This option generates modules.builtin.ranges in the build tree with + offset ranges (per ELF section) for the module(s) they belong to. + It also records an anchor symbol to determine the load address of the + section. + config DEBUG_FORCE_WEAK_PER_CPU bool "Force weak per-cpu definitions" depends on DEBUG_KERNEL @@ -969,6 +986,38 @@ config DEBUG_STACKOVERFLOW If in doubt, say "N". +config CODE_TAGGING + bool + select KALLSYMS + +config MEM_ALLOC_PROFILING + bool "Enable memory allocation profiling" + default n + depends on MMU + depends on PROC_FS + depends on !DEBUG_FORCE_WEAK_PER_CPU + select CODE_TAGGING + select PAGE_EXTENSION + select SLAB_OBJ_EXT + help + Track allocation source code and record total allocation size + initiated at that code location. The mechanism can be used to track + memory leaks with a low performance and memory impact. + +config MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT + bool "Enable memory allocation profiling by default" + default y + depends on MEM_ALLOC_PROFILING + +config MEM_ALLOC_PROFILING_DEBUG + bool "Memory allocation profiler debugging" + default n + depends on MEM_ALLOC_PROFILING + select MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT + help + Adds warnings with helpful error messages for memory allocation + profiling. + source "lib/Kconfig.kasan" source "lib/Kconfig.kfence" source "lib/Kconfig.kmsan" @@ -1012,7 +1061,9 @@ config PANIC_TIMEOUT Set the timeout value (in seconds) until a reboot occurs when the kernel panics. If n = 0, then we wait forever. A timeout value n > 0 will wait n seconds before rebooting, while a timeout - value n < 0 will reboot immediately. + value n < 0 will reboot immediately. This setting can be overridden + with the kernel command line option panic=, and from userspace via + /proc/sys/kernel/panic. config LOCKUP_DETECTOR bool @@ -1278,19 +1329,6 @@ config SCHEDSTATS endmenu -config DEBUG_TIMEKEEPING - bool "Enable extra timekeeping sanity checking" - help - This option will enable additional timekeeping sanity checks - which may be helpful when diagnosing issues where timekeeping - problems are suspected. - - This may include checks in the timekeeping hotpaths, so this - option may have a (very small) performance impact to some - workloads. - - If unsure, say N. - config DEBUG_PREEMPT bool "Debug preemptible kernel" depends on DEBUG_KERNEL && PREEMPTION && TRACE_IRQFLAGS_SUPPORT @@ -1359,22 +1397,14 @@ config PROVE_LOCKING For more details, see Documentation/locking/lockdep-design.rst. config PROVE_RAW_LOCK_NESTING - bool "Enable raw_spinlock - spinlock nesting checks" + bool "Enable raw_spinlock - spinlock nesting checks" if !ARCH_SUPPORTS_RT depends on PROVE_LOCKING - default n + default y if ARCH_SUPPORTS_RT help Enable the raw_spinlock vs. spinlock nesting checks which ensure that the lock nesting rules for PREEMPT_RT enabled kernels are not violated. - NOTE: There are known nesting problems. So if you enable this - option expect lockdep splats until these problems have been fully - addressed which is work in progress. This config switch allows to - identify and analyze these problems. It will be removed and the - check permanently enabled once the main issues have been fixed. - - If unsure, select N. - config LOCK_STAT bool "Lock usage statistics" depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT @@ -1472,41 +1502,41 @@ config LOCKDEP_SMALL bool config LOCKDEP_BITS - int "Bitsize for MAX_LOCKDEP_ENTRIES" + int "Size for MAX_LOCKDEP_ENTRIES (as Nth power of 2)" depends on LOCKDEP && !LOCKDEP_SMALL - range 10 30 + range 10 24 default 15 help Try increasing this value if you hit "BUG: MAX_LOCKDEP_ENTRIES too low!" message. config LOCKDEP_CHAINS_BITS - int "Bitsize for MAX_LOCKDEP_CHAINS" + int "Size for MAX_LOCKDEP_CHAINS (as Nth power of 2)" depends on LOCKDEP && !LOCKDEP_SMALL - range 10 30 + range 10 21 default 16 help Try increasing this value if you hit "BUG: MAX_LOCKDEP_CHAINS too low!" message. config LOCKDEP_STACK_TRACE_BITS - int "Bitsize for MAX_STACK_TRACE_ENTRIES" + int "Size for MAX_STACK_TRACE_ENTRIES (as Nth power of 2)" depends on LOCKDEP && !LOCKDEP_SMALL - range 10 30 + range 10 26 default 19 help Try increasing this value if you hit "BUG: MAX_STACK_TRACE_ENTRIES too low!" message. config LOCKDEP_STACK_TRACE_HASH_BITS - int "Bitsize for STACK_TRACE_HASH_SIZE" + int "Size for STACK_TRACE_HASH_SIZE (as Nth power of 2)" depends on LOCKDEP && !LOCKDEP_SMALL - range 10 30 + range 10 26 default 14 help Try increasing this value if you need large STACK_TRACE_HASH_SIZE. config LOCKDEP_CIRCULAR_QUEUE_BITS - int "Bitsize for elements in circular_queue struct" + int "Size for elements in circular_queue struct (as Nth power of 2)" depends on LOCKDEP - range 10 30 + range 10 26 default 12 help Try increasing this value if you hit "lockdep bfs error:-1" warning due to __cq_enqueue() failure. @@ -1581,6 +1611,7 @@ config SCF_TORTURE_TEST config CSD_LOCK_WAIT_DEBUG bool "Debugging for csd_lock_wait(), called from smp_call_function*()" depends on DEBUG_KERNEL + depends on SMP depends on 64BIT default n help @@ -1854,7 +1885,7 @@ config STRICT_DEVMEM bool "Filter access to /dev/mem" depends on MMU && DEVMEM depends on ARCH_HAS_DEVMEM_IS_ALLOWED || GENERIC_LIB_DEVMEM_IS_ALLOWED - default y if PPC || X86 || ARM64 + default y if PPC || X86 || ARM64 || S390 help If this option is disabled, you allow userspace (root) access to all of memory, including kernel and userspace memory. Accidental @@ -2064,6 +2095,16 @@ config FAIL_SUNRPC Provide fault-injection capability for SunRPC and its consumers. +config FAIL_SKB_REALLOC + bool "Fault-injection capability forcing skb to reallocate" + depends on FAULT_INJECTION_DEBUG_FS + help + Provide fault-injection capability that forces the skb to be + reallocated, catching possible invalid pointers to the skb. + + For more information, check + Documentation/dev-tools/fault-injection/fault-injection.rst + config FAULT_INJECTION_CONFIGFS bool "Configfs interface for fault-injection capabilities" depends on FAULT_INJECTION @@ -2140,6 +2181,14 @@ config KCOV_IRQ_AREA_SIZE soft interrupts. This specifies the size of those areas in the number of unsigned long words. +config KCOV_SELFTEST + bool "Perform short selftests on boot" + depends on KCOV + help + Run short KCOV coverage collection selftests on boot. + On test failure, causes the kernel to panic. Recommended to be + enabled, ensuring critical functionality works as intended. + menuconfig RUNTIME_TESTING_MENU bool "Runtime Testing" default y @@ -2247,6 +2296,16 @@ config TEST_DIV64 If unsure, say N. +config TEST_MULDIV64 + tristate "mul_u64_u64_div_u64() test" + depends on DEBUG_KERNEL || m + help + Enable this to turn on 'mul_u64_u64_div_u64()' function test. + This test is executed only once during system boot (so affects + only boot time), or at module load time. + + If unsure, say N. + config TEST_IOV_ITER tristate "Test iov_iter operation" if !KUNIT_ALL_TESTS depends on KUNIT @@ -2419,6 +2478,17 @@ config TEST_RHASHTABLE config TEST_IDA tristate "Perform selftest on IDA functions" +config TEST_MISC_MINOR + tristate "Basic misc minor Kunit test" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + help + Kunit test for the misc minor. + It tests misc minor functions for dynamic and misc dynamic minor. + This include misc_xxx functions + + If unsure, say N. + config TEST_PARMAN tristate "Perform selftest on priority array manager" depends on PARMAN @@ -2451,7 +2521,6 @@ config TEST_LKM config TEST_BITOPS tristate "Test module for compilation of bitops operations" - depends on m help This builds the "test_bitops" module that is much like the TEST_LKM module except that it does a basic exercise of the @@ -2475,18 +2544,6 @@ config TEST_VMALLOC If unsure, say N. -config TEST_USER_COPY - tristate "Test user/kernel boundary protections" - depends on m - help - This builds the "test_user_copy" module that runs sanity checks - on the copy_to/from_user infrastructure, making sure basic - user/kernel boundary testing is working. If it fails to load, - a regression has been detected in the user/kernel memory boundary - protections. - - If unsure, say N. - config TEST_BPF tristate "Test BPF filter functionality" depends on m && NET @@ -2573,6 +2630,23 @@ config CHECKSUM_KUNIT If unsure, say N. +config UTIL_MACROS_KUNIT + tristate "KUnit test util_macros.h functions at runtime" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + help + Enable this option to test the util_macros.h function at boot. + + KUnit tests run during boot and output the results to the debug log + in TAP format (http://testanything.org/). Only useful for kernel devs + running the KUnit test harness, and not intended for inclusion into a + production build. + + For more information on KUnit and unit tests in general please refer + to the KUnit documentation in Documentation/dev-tools/kunit/. + + If unsure, say N. + config HASH_KUNIT_TEST tristate "KUnit Test for integer hash functions" if !KUNIT_ALL_TESTS depends on KUNIT @@ -2596,6 +2670,7 @@ config RESOURCE_KUNIT_TEST tristate "KUnit test for resource API" if !KUNIT_ALL_TESTS depends on KUNIT default KUNIT_ALL_TESTS + select GET_FREE_REGION help This builds the resource API unit test. Tests the logic of API provided by resource.c and ioport.h. @@ -2773,6 +2848,26 @@ config HW_BREAKPOINT_KUNIT_TEST If unsure, say N. +config CRC_KUNIT_TEST + tristate "KUnit tests for CRC functions" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + select CRC16 + select CRC_T10DIF + select CRC32 + select CRC64 + help + Unit tests for the CRC library functions. + + This is intended to help people writing architecture-specific + optimized versions. If unsure, say N. + +config CRC_BENCHMARK + bool "Benchmark for the CRC functions" + depends on CRC_KUNIT_TEST + help + Include benchmarks in the KUnit test suite for the CRC functions. + config SIPHASH_KUNIT_TEST tristate "Perform selftest on siphash functions" if !KUNIT_ALL_TESTS depends on KUNIT @@ -2784,6 +2879,15 @@ config SIPHASH_KUNIT_TEST This is intended to help people writing architecture-specific optimized versions. If unsure, say N. +config USERCOPY_KUNIT_TEST + tristate "KUnit Test for user/kernel boundary protections" + depends on KUNIT + default KUNIT_ALL_TESTS + help + This builds the "usercopy_kunit" module that runs sanity checks + on the copy_to/from_user infrastructure, making sure basic + user/kernel boundary testing is working. + config TEST_UDELAY tristate "udelay test driver" help @@ -2837,6 +2941,141 @@ config TEST_KMOD If unsure, say N. +config TEST_RUNTIME + bool + +config TEST_RUNTIME_MODULE + bool + +config TEST_KALLSYMS + tristate "module kallsyms find_symbol() test" + depends on m + select TEST_RUNTIME + select TEST_RUNTIME_MODULE + select TEST_KALLSYMS_A + select TEST_KALLSYMS_B + select TEST_KALLSYMS_C + select TEST_KALLSYMS_D + help + This allows us to stress test find_symbol() through the kallsyms + used to place symbols on the kernel ELF kallsyms and modules kallsyms + where we place kernel symbols such as exported symbols. + + We have four test modules: + + A: has KALLSYSMS_NUMSYMS exported symbols + B: uses one of A's symbols + C: adds KALLSYMS_SCALE_FACTOR * KALLSYSMS_NUMSYMS exported + D: adds 2 * the symbols than C + + We stress test find_symbol() through two means: + + 1) Upon load of B it will trigger simplify_symbols() to look for the + one symbol it uses from the module A with tons of symbols. This is an + indirect way for us to have B call resolve_symbol_wait() upon module + load. This will eventually call find_symbol() which will eventually + try to find the symbols used with find_exported_symbol_in_section(). + find_exported_symbol_in_section() uses bsearch() so a binary search + for each symbol. Binary search will at worst be O(log(n)) so the + larger TEST_MODULE_KALLSYSMS the worse the search. + + 2) The selftests should load C first, before B. Upon B's load towards + the end right before we call module B's init routine we get + complete_formation() called on the module. That will first check + for duplicate symbols with the call to verify_exported_symbols(). + That is when we'll force iteration on module C's insane symbol list. + Since it has 10 * KALLSYMS_NUMSYMS it means we can first test + just loading B without C. The amount of time it takes to load C Vs + B can give us an idea of the impact growth of the symbol space and + give us projection. Module A only uses one symbol from B so to allow + this scaling in module C to be proportional, if it used more symbols + then the first test would be doing more and increasing just the + search space would be slightly different. The last module, module D + will just increase the search space by twice the number of symbols in + C so to allow for full projects. + + tools/testing/selftests/module/find_symbol.sh + + The current defaults will incur a build delay of about 7 minutes + on an x86_64 with only 8 cores. Enable this only if you want to + stress test find_symbol() with thousands of symbols. At the same + time this is also useful to test building modules with thousands of + symbols, and if BTF is enabled this also stress tests adding BTF + information for each module. Currently enabling many more symbols + will segfault the build system. + + If unsure, say N. + +if TEST_KALLSYMS + +config TEST_KALLSYMS_A + tristate + depends on m + +config TEST_KALLSYMS_B + tristate + depends on m + +config TEST_KALLSYMS_C + tristate + depends on m + +config TEST_KALLSYMS_D + tristate + depends on m + +choice + prompt "Kallsym test range" + default TEST_KALLSYMS_LARGE + help + Selecting something other than "Fast" will enable tests which slow + down the build and may crash your build. + +config TEST_KALLSYMS_FAST + bool "Fast builds" + help + You won't really be testing kallsysms, so this just helps fast builds + when allmodconfig is used.. + +config TEST_KALLSYMS_LARGE + bool "Enable testing kallsyms with large exports" + help + This will enable larger number of symbols. This will slow down + your build considerably. + +config TEST_KALLSYMS_MAX + bool "Known kallsysms limits" + help + This will enable exports to the point we know we'll start crashing + builds. + +endchoice + +config TEST_KALLSYMS_NUMSYMS + int "test kallsyms number of symbols" + range 2 10000 + default 2 if TEST_KALLSYMS_FAST + default 100 if TEST_KALLSYMS_LARGE + default 10000 if TEST_KALLSYMS_MAX + help + The number of symbols to create on TEST_KALLSYMS_A, only one of which + module TEST_KALLSYMS_B will use. This also will be used + for how many symbols TEST_KALLSYMS_C will have, scaled up by + TEST_KALLSYMS_SCALE_FACTOR. Note that setting this to 10,000 will + trigger a segfault today, don't use anything close to it unless + you are aware that this should not be used for automated build tests. + +config TEST_KALLSYMS_SCALE_FACTOR + int "test kallsyms scale factor" + default 8 + help + How many more unusued symbols will TEST_KALLSYSMS_C have than + TEST_KALLSYMS_A. If 8, then module C will have 8 * syms + than module A. Then TEST_KALLSYMS_D will have double the amount + of symbols than C so to allow projections. + +endif # TEST_KALLSYMS + config TEST_DEBUG_VIRTUAL tristate "Test CONFIG_DEBUG_VIRTUAL feature" depends on DEBUG_VIRTUAL @@ -2895,7 +3134,7 @@ config TEST_FREE_PAGES config TEST_FPU tristate "Test floating point operations in kernel space" - depends on X86 && !KCOV_INSTRUMENT_ALL + depends on ARCH_HAS_KERNEL_FPU_SUPPORT && !KCOV_INSTRUMENT_ALL help Enable this option to add /sys/kernel/debug/selftest_helpers/test_fpu which will trigger a sequence of floating point operations. This is used @@ -2927,6 +3166,37 @@ config TEST_OBJPOOL If unsure, say N. +config INT_POW_TEST + tristate "Integer exponentiation (int_pow) test" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + help + This option enables the KUnit test suite for the int_pow function, + which performs integer exponentiation. The test suite is designed to + verify that the implementation of int_pow correctly computes the power + of a given base raised to a given exponent. + + Enabling this option will include tests that check various scenarios + and edge cases to ensure the accuracy and reliability of the exponentiation + function. + + If unsure, say N + +config INT_SQRT_KUNIT_TEST + tristate "Integer square root test" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + help + This option enables the KUnit test suite for the int_sqrt() function, + which performs square root calculation. The test suite checks + various scenarios, including edge cases, to ensure correctness. + + Enabling this option will include tests that check various scenarios + and edge cases to ensure the accuracy and reliability of the square root + function. + + If unsure, say N + endif # RUNTIME_TESTING_MENU config ARCH_USE_MEMTEST @@ -2994,7 +3264,7 @@ config RUST_BUILD_ASSERT_ALLOW bool "Allow unoptimized build-time assertions" depends on RUST help - Controls how are `build_error!` and `build_assert!` handled during build. + Controls how `build_error!` and `build_assert!` are handled during the build. If calls to them exist in the binary, it may indicate a violated invariant or that the optimizer failed to verify the invariant during compilation. diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index 98016e137b7f..f82889a830fa 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -195,13 +195,6 @@ config KASAN_KUNIT_TEST For more information on KUnit and unit tests in general, please refer to the KUnit documentation in Documentation/dev-tools/kunit/. -config KASAN_MODULE_TEST - tristate "KUnit-incompatible tests of KASAN bug detection capabilities" - depends on m && KASAN && !KASAN_HW_TAGS - help - A part of the KASAN test suite that is not integrated with KUnit. - Incompatible with Hardware Tag-Based KASAN. - config KASAN_EXTRA_INFO bool "Record and report more information" depends on KASAN diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb index b5c0e6576749..8336b1a489a3 100644 --- a/lib/Kconfig.kgdb +++ b/lib/Kconfig.kgdb @@ -19,7 +19,7 @@ menuconfig KGDB CONFIG_FRAME_POINTER to aid in producing more reliable stack backtraces in the external debugger. Documentation of kernel debugger is available at http://kgdb.sourceforge.net - as well as in Documentation/dev-tools/kgdb.rst. If + as well as in Documentation/process/debugging/kgdb.rst. If unsure, say N. if KGDB @@ -122,6 +122,7 @@ config KDB_DEFAULT_ENABLE config KDB_KEYBOARD bool "KGDB_KDB: keyboard as input device" depends on VT && KGDB_KDB && !PARISC + depends on HAS_IOPORT default n help KDB can use a PS/2 type keyboard for an input device diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan index e81e1ac4a919..1d4aa7a83b3a 100644 --- a/lib/Kconfig.ubsan +++ b/lib/Kconfig.ubsan @@ -4,6 +4,7 @@ config ARCH_HAS_UBSAN menuconfig UBSAN bool "Undefined behaviour sanity checker" + depends on ARCH_HAS_UBSAN help This option enables the Undefined Behaviour sanity checker. Compile-time instrumentation is used to detect various undefined @@ -28,8 +29,8 @@ config UBSAN_TRAP Also note that selecting Y will cause your kernel to Oops with an "illegal instruction" error with no further details - when a UBSAN violation occurs. (Except on arm64, which will - report which Sanitizer failed.) This may make it hard to + when a UBSAN violation occurs. (Except on arm64 and x86, which + will report which Sanitizer failed.) This may make it hard to determine whether an Oops was caused by UBSAN or to figure out the details of a UBSAN violation. It makes the kernel log output less useful for bug reports. diff --git a/lib/Makefile b/lib/Makefile index ed8dbf4436dd..d5cfc7afbbb8 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -14,6 +14,7 @@ KCOV_INSTRUMENT_list_debug.o := n KCOV_INSTRUMENT_debugobjects.o := n KCOV_INSTRUMENT_dynamic_debug.o := n KCOV_INSTRUMENT_fault-inject.o := n +KCOV_INSTRUMENT_find_bit.o := n # string.o implements standard library functions like memset/memcpy etc. # Use -ffreestanding to ensure that the compiler does not try to "optimize" @@ -34,10 +35,12 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ earlycpio.o seq_buf.o siphash.o dec_and_lock.o \ nmi_backtrace.o win_minmax.o memcat_p.o \ - buildid.o objpool.o + buildid.o objpool.o iomem_copy.o +lib-$(CONFIG_UNION_FIND) += union_find.o lib-$(CONFIG_PRINTK) += dump_stack.o lib-$(CONFIG_SMP) += cpumask.o +lib-$(CONFIG_MIN_HEAP) += min_heap.o lib-y += kobject.o klist.o obj-y += lockref.o @@ -78,7 +81,6 @@ obj-$(CONFIG_TEST_LKM) += test_module.o obj-$(CONFIG_TEST_VMALLOC) += test_vmalloc.o obj-$(CONFIG_TEST_RHASHTABLE) += test_rhashtable.o obj-$(CONFIG_TEST_SORT) += test_sort.o -obj-$(CONFIG_TEST_USER_COPY) += test_user_copy.o obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_keys.o obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_key_base.o obj-$(CONFIG_TEST_DYNAMIC_DEBUG) += test_dynamic_debug.o @@ -96,6 +98,7 @@ obj-$(CONFIG_TEST_XARRAY) += test_xarray.o obj-$(CONFIG_TEST_MAPLE_TREE) += test_maple_tree.o obj-$(CONFIG_TEST_PARMAN) += test_parman.o obj-$(CONFIG_TEST_KMOD) += test_kmod.o +obj-$(CONFIG_TEST_RUNTIME) += tests/ obj-$(CONFIG_TEST_DEBUG_VIRTUAL) += test_debug_virtual.o obj-$(CONFIG_TEST_MEMCAT_P) += test_memcat_p.o obj-$(CONFIG_TEST_OBJAGG) += test_objagg.o @@ -110,30 +113,10 @@ CFLAGS_test_fprobe.o += $(CC_FLAGS_FTRACE) obj-$(CONFIG_FPROBE_SANITY_TEST) += test_fprobe.o obj-$(CONFIG_TEST_OBJPOOL) += test_objpool.o -# -# CFLAGS for compiling floating point code inside the kernel. x86/Makefile turns -# off the generation of FPU/SSE* instructions for kernel proper but FPU_FLAGS -# get appended last to CFLAGS and thus override those previous compiler options. -# -FPU_CFLAGS := -msse -msse2 -ifdef CONFIG_CC_IS_GCC -# Stack alignment mismatch, proceed with caution. -# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 -# (8B stack alignment). -# See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383 -# -# The "-msse" in the first argument is there so that the -# -mpreferred-stack-boundary=3 build error: -# -# -mpreferred-stack-boundary=3 is not between 4 and 12 -# -# can be triggered. Otherwise gcc doesn't complain. -FPU_CFLAGS += -mhard-float -FPU_CFLAGS += $(call cc-option,-msse -mpreferred-stack-boundary=3,-mpreferred-stack-boundary=4) -endif - obj-$(CONFIG_TEST_FPU) += test_fpu.o -CFLAGS_test_fpu.o += $(FPU_CFLAGS) +test_fpu-y := test_fpu_glue.o test_fpu_impl.o +CFLAGS_test_fpu_impl.o += $(CC_FLAGS_FPU) +CFLAGS_REMOVE_test_fpu_impl.o += $(CC_FLAGS_NO_FPU) # Some KUnit files (hooks.o) need to be built-in even when KUnit is a module, # so we can't just use obj-$(CONFIG_KUNIT). @@ -174,16 +157,15 @@ obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o obj-$(CONFIG_BITREVERSE) += bitrev.o obj-$(CONFIG_LINEAR_RANGES) += linear_ranges.o obj-$(CONFIG_PACKING) += packing.o +obj-$(CONFIG_PACKING_KUNIT_TEST) += packing_test.o obj-$(CONFIG_CRC_CCITT) += crc-ccitt.o obj-$(CONFIG_CRC16) += crc16.o obj-$(CONFIG_CRC_T10DIF)+= crc-t10dif.o obj-$(CONFIG_CRC_ITU_T) += crc-itu-t.o obj-$(CONFIG_CRC32) += crc32.o obj-$(CONFIG_CRC64) += crc64.o -obj-$(CONFIG_CRC32_SELFTEST) += crc32test.o obj-$(CONFIG_CRC4) += crc4.o obj-$(CONFIG_CRC7) += crc7.o -obj-$(CONFIG_LIBCRC32C) += libcrc32c.o obj-$(CONFIG_CRC8) += crc8.o obj-$(CONFIG_CRC64_ROCKSOFT) += crc64-rocksoft.o obj-$(CONFIG_XXHASH) += xxhash.o @@ -233,6 +215,9 @@ obj-$(CONFIG_OF_RECONFIG_NOTIFIER_ERROR_INJECT) += \ of-reconfig-notifier-error-inject.o obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o +obj-$(CONFIG_CODE_TAGGING) += codetag.o +obj-$(CONFIG_MEM_ALLOC_PROFILING) += alloc_tag.o + lib-$(CONFIG_GENERIC_BUG) += bug.o obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o @@ -353,7 +338,7 @@ $(obj)/oid_registry_data.c: $(srctree)/include/linux/oid_registry.h \ $(call cmd,build_OID_registry) quiet_cmd_build_OID_registry = GEN $@ - cmd_build_OID_registry = perl $(srctree)/$(src)/build_OID_registry $< $@ + cmd_build_OID_registry = perl $(src)/build_OID_registry $< $@ clean-files += oid_registry_data.c @@ -387,6 +372,7 @@ obj-$(CONFIG_PLDMFW) += pldmfw/ CFLAGS_bitfield_kunit.o := $(DISABLE_STRUCTLEAK_PLUGIN) obj-$(CONFIG_BITFIELD_KUNIT) += bitfield_kunit.o obj-$(CONFIG_CHECKSUM_KUNIT) += checksum_kunit.o +obj-$(CONFIG_UTIL_MACROS_KUNIT) += util_macros_kunit.o obj-$(CONFIG_LIST_KUNIT_TEST) += list-test.o obj-$(CONFIG_HASHTABLE_KUNIT_TEST) += hashtable_test.o obj-$(CONFIG_LINEAR_RANGES_TEST) += test_linear_ranges.o @@ -404,42 +390,12 @@ CFLAGS_fortify_kunit.o += $(call cc-disable-warning, stringop-overread) CFLAGS_fortify_kunit.o += $(call cc-disable-warning, stringop-truncation) CFLAGS_fortify_kunit.o += $(DISABLE_STRUCTLEAK_PLUGIN) obj-$(CONFIG_FORTIFY_KUNIT_TEST) += fortify_kunit.o +obj-$(CONFIG_CRC_KUNIT_TEST) += crc_kunit.o obj-$(CONFIG_SIPHASH_KUNIT_TEST) += siphash_kunit.o +obj-$(CONFIG_USERCOPY_KUNIT_TEST) += usercopy_kunit.o obj-$(CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED) += devmem_is_allowed.o obj-$(CONFIG_FIRMWARE_TABLE) += fw_table.o -# FORTIFY_SOURCE compile-time behavior tests -TEST_FORTIFY_SRCS = $(wildcard $(srctree)/$(src)/test_fortify/*-*.c) -TEST_FORTIFY_LOGS = $(patsubst $(srctree)/$(src)/%.c, %.log, $(TEST_FORTIFY_SRCS)) -TEST_FORTIFY_LOG = test_fortify.log - -quiet_cmd_test_fortify = TEST $@ - cmd_test_fortify = $(CONFIG_SHELL) $(srctree)/scripts/test_fortify.sh \ - $< $@ "$(NM)" $(CC) $(c_flags) \ - $(call cc-disable-warning,fortify-source) \ - -DKBUILD_EXTRA_WARN1 - -targets += $(TEST_FORTIFY_LOGS) -clean-files += $(TEST_FORTIFY_LOGS) -clean-files += $(addsuffix .o, $(TEST_FORTIFY_LOGS)) -$(obj)/test_fortify/%.log: $(src)/test_fortify/%.c \ - $(src)/test_fortify/test_fortify.h \ - $(srctree)/include/linux/fortify-string.h \ - $(srctree)/scripts/test_fortify.sh \ - FORCE - $(call if_changed,test_fortify) - -quiet_cmd_gen_fortify_log = GEN $@ - cmd_gen_fortify_log = cat </dev/null $(filter-out FORCE,$^) 2>/dev/null > $@ || true - -targets += $(TEST_FORTIFY_LOG) -clean-files += $(TEST_FORTIFY_LOG) -$(obj)/$(TEST_FORTIFY_LOG): $(addprefix $(obj)/, $(TEST_FORTIFY_LOGS)) FORCE - $(call if_changed,gen_fortify_log) - -# Fake dependency to trigger the fortify tests. -ifeq ($(CONFIG_FORTIFY_SOURCE),y) -$(obj)/string.o: $(obj)/$(TEST_FORTIFY_LOG) -endif +subdir-$(CONFIG_FORTIFY_SOURCE) += test_fortify diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c new file mode 100644 index 000000000000..19b45617bdcf --- /dev/null +++ b/lib/alloc_tag.c @@ -0,0 +1,771 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/alloc_tag.h> +#include <linux/execmem.h> +#include <linux/fs.h> +#include <linux/gfp.h> +#include <linux/kallsyms.h> +#include <linux/module.h> +#include <linux/page_ext.h> +#include <linux/proc_fs.h> +#include <linux/seq_buf.h> +#include <linux/seq_file.h> +#include <linux/vmalloc.h> + +#define ALLOCINFO_FILE_NAME "allocinfo" +#define MODULE_ALLOC_TAG_VMAP_SIZE (100000UL * sizeof(struct alloc_tag)) +#define SECTION_START(NAME) (CODETAG_SECTION_START_PREFIX NAME) +#define SECTION_STOP(NAME) (CODETAG_SECTION_STOP_PREFIX NAME) + +#ifdef CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT +static bool mem_profiling_support = true; +#else +static bool mem_profiling_support; +#endif + +static struct codetag_type *alloc_tag_cttype; + +DEFINE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag); +EXPORT_SYMBOL(_shared_alloc_tag); + +DEFINE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT, + mem_alloc_profiling_key); +EXPORT_SYMBOL(mem_alloc_profiling_key); + +DEFINE_STATIC_KEY_FALSE(mem_profiling_compressed); + +struct alloc_tag_kernel_section kernel_tags = { NULL, 0 }; +unsigned long alloc_tag_ref_mask; +int alloc_tag_ref_offs; + +struct allocinfo_private { + struct codetag_iterator iter; + bool print_header; +}; + +static void *allocinfo_start(struct seq_file *m, loff_t *pos) +{ + struct allocinfo_private *priv; + struct codetag *ct; + loff_t node = *pos; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + m->private = priv; + if (!priv) + return NULL; + + priv->print_header = (node == 0); + codetag_lock_module_list(alloc_tag_cttype, true); + priv->iter = codetag_get_ct_iter(alloc_tag_cttype); + while ((ct = codetag_next_ct(&priv->iter)) != NULL && node) + node--; + + return ct ? priv : NULL; +} + +static void *allocinfo_next(struct seq_file *m, void *arg, loff_t *pos) +{ + struct allocinfo_private *priv = (struct allocinfo_private *)arg; + struct codetag *ct = codetag_next_ct(&priv->iter); + + (*pos)++; + if (!ct) + return NULL; + + return priv; +} + +static void allocinfo_stop(struct seq_file *m, void *arg) +{ + struct allocinfo_private *priv = (struct allocinfo_private *)m->private; + + if (priv) { + codetag_lock_module_list(alloc_tag_cttype, false); + kfree(priv); + } +} + +static void print_allocinfo_header(struct seq_buf *buf) +{ + /* Output format version, so we can change it. */ + seq_buf_printf(buf, "allocinfo - version: 1.0\n"); + seq_buf_printf(buf, "# <size> <calls> <tag info>\n"); +} + +static void alloc_tag_to_text(struct seq_buf *out, struct codetag *ct) +{ + struct alloc_tag *tag = ct_to_alloc_tag(ct); + struct alloc_tag_counters counter = alloc_tag_read(tag); + s64 bytes = counter.bytes; + + seq_buf_printf(out, "%12lli %8llu ", bytes, counter.calls); + codetag_to_text(out, ct); + seq_buf_putc(out, ' '); + seq_buf_putc(out, '\n'); +} + +static int allocinfo_show(struct seq_file *m, void *arg) +{ + struct allocinfo_private *priv = (struct allocinfo_private *)arg; + char *bufp; + size_t n = seq_get_buf(m, &bufp); + struct seq_buf buf; + + seq_buf_init(&buf, bufp, n); + if (priv->print_header) { + print_allocinfo_header(&buf); + priv->print_header = false; + } + alloc_tag_to_text(&buf, priv->iter.ct); + seq_commit(m, seq_buf_used(&buf)); + return 0; +} + +static const struct seq_operations allocinfo_seq_op = { + .start = allocinfo_start, + .next = allocinfo_next, + .stop = allocinfo_stop, + .show = allocinfo_show, +}; + +size_t alloc_tag_top_users(struct codetag_bytes *tags, size_t count, bool can_sleep) +{ + struct codetag_iterator iter; + struct codetag *ct; + struct codetag_bytes n; + unsigned int i, nr = 0; + + if (can_sleep) + codetag_lock_module_list(alloc_tag_cttype, true); + else if (!codetag_trylock_module_list(alloc_tag_cttype)) + return 0; + + iter = codetag_get_ct_iter(alloc_tag_cttype); + while ((ct = codetag_next_ct(&iter))) { + struct alloc_tag_counters counter = alloc_tag_read(ct_to_alloc_tag(ct)); + + n.ct = ct; + n.bytes = counter.bytes; + + for (i = 0; i < nr; i++) + if (n.bytes > tags[i].bytes) + break; + + if (i < count) { + nr -= nr == count; + memmove(&tags[i + 1], + &tags[i], + sizeof(tags[0]) * (nr - i)); + nr++; + tags[i] = n; + } + } + + codetag_lock_module_list(alloc_tag_cttype, false); + + return nr; +} + +void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) +{ + int i; + struct alloc_tag *tag; + unsigned int nr_pages = 1 << new_order; + + if (!mem_alloc_profiling_enabled()) + return; + + tag = pgalloc_tag_get(&folio->page); + if (!tag) + return; + + for (i = nr_pages; i < (1 << old_order); i += nr_pages) { + union pgtag_ref_handle handle; + union codetag_ref ref; + + if (get_page_tag_ref(folio_page(folio, i), &ref, &handle)) { + /* Set new reference to point to the original tag */ + alloc_tag_ref_set(&ref, tag); + update_page_tag_ref(handle, &ref); + put_page_tag_ref(handle); + } + } +} + +void pgalloc_tag_swap(struct folio *new, struct folio *old) +{ + union pgtag_ref_handle handle_old, handle_new; + union codetag_ref ref_old, ref_new; + struct alloc_tag *tag_old, *tag_new; + + if (!mem_alloc_profiling_enabled()) + return; + + tag_old = pgalloc_tag_get(&old->page); + if (!tag_old) + return; + tag_new = pgalloc_tag_get(&new->page); + if (!tag_new) + return; + + if (!get_page_tag_ref(&old->page, &ref_old, &handle_old)) + return; + if (!get_page_tag_ref(&new->page, &ref_new, &handle_new)) { + put_page_tag_ref(handle_old); + return; + } + + /* + * Clear tag references to avoid debug warning when using + * __alloc_tag_ref_set() with non-empty reference. + */ + set_codetag_empty(&ref_old); + set_codetag_empty(&ref_new); + + /* swap tags */ + __alloc_tag_ref_set(&ref_old, tag_new); + update_page_tag_ref(handle_old, &ref_old); + __alloc_tag_ref_set(&ref_new, tag_old); + update_page_tag_ref(handle_new, &ref_new); + + put_page_tag_ref(handle_old); + put_page_tag_ref(handle_new); +} + +static void shutdown_mem_profiling(bool remove_file) +{ + if (mem_alloc_profiling_enabled()) + static_branch_disable(&mem_alloc_profiling_key); + + if (!mem_profiling_support) + return; + + if (remove_file) + remove_proc_entry(ALLOCINFO_FILE_NAME, NULL); + mem_profiling_support = false; +} + +static void __init procfs_init(void) +{ + if (!mem_profiling_support) + return; + + if (!proc_create_seq(ALLOCINFO_FILE_NAME, 0400, NULL, &allocinfo_seq_op)) { + pr_err("Failed to create %s file\n", ALLOCINFO_FILE_NAME); + shutdown_mem_profiling(false); + } +} + +void __init alloc_tag_sec_init(void) +{ + struct alloc_tag *last_codetag; + + if (!mem_profiling_support) + return; + + if (!static_key_enabled(&mem_profiling_compressed)) + return; + + kernel_tags.first_tag = (struct alloc_tag *)kallsyms_lookup_name( + SECTION_START(ALLOC_TAG_SECTION_NAME)); + last_codetag = (struct alloc_tag *)kallsyms_lookup_name( + SECTION_STOP(ALLOC_TAG_SECTION_NAME)); + kernel_tags.count = last_codetag - kernel_tags.first_tag; + + /* Check if kernel tags fit into page flags */ + if (kernel_tags.count > (1UL << NR_UNUSED_PAGEFLAG_BITS)) { + shutdown_mem_profiling(false); /* allocinfo file does not exist yet */ + pr_err("%lu allocation tags cannot be references using %d available page flag bits. Memory allocation profiling is disabled!\n", + kernel_tags.count, NR_UNUSED_PAGEFLAG_BITS); + return; + } + + alloc_tag_ref_offs = (LRU_REFS_PGOFF - NR_UNUSED_PAGEFLAG_BITS); + alloc_tag_ref_mask = ((1UL << NR_UNUSED_PAGEFLAG_BITS) - 1); + pr_debug("Memory allocation profiling compression is using %d page flag bits!\n", + NR_UNUSED_PAGEFLAG_BITS); +} + +#ifdef CONFIG_MODULES + +static struct maple_tree mod_area_mt = MTREE_INIT(mod_area_mt, MT_FLAGS_ALLOC_RANGE); +static struct vm_struct *vm_module_tags; +/* A dummy object used to indicate an unloaded module */ +static struct module unloaded_mod; +/* A dummy object used to indicate a module prepended area */ +static struct module prepend_mod; + +struct alloc_tag_module_section module_tags; + +static inline unsigned long alloc_tag_align(unsigned long val) +{ + if (!static_key_enabled(&mem_profiling_compressed)) { + /* No alignment requirements when we are not indexing the tags */ + return val; + } + + if (val % sizeof(struct alloc_tag) == 0) + return val; + return ((val / sizeof(struct alloc_tag)) + 1) * sizeof(struct alloc_tag); +} + +static bool ensure_alignment(unsigned long align, unsigned int *prepend) +{ + if (!static_key_enabled(&mem_profiling_compressed)) { + /* No alignment requirements when we are not indexing the tags */ + return true; + } + + /* + * If alloc_tag size is not a multiple of required alignment, tag + * indexing does not work. + */ + if (!IS_ALIGNED(sizeof(struct alloc_tag), align)) + return false; + + /* Ensure prepend consumes multiple of alloc_tag-sized blocks */ + if (*prepend) + *prepend = alloc_tag_align(*prepend); + + return true; +} + +static inline bool tags_addressable(void) +{ + unsigned long tag_idx_count; + + if (!static_key_enabled(&mem_profiling_compressed)) + return true; /* with page_ext tags are always addressable */ + + tag_idx_count = CODETAG_ID_FIRST + kernel_tags.count + + module_tags.size / sizeof(struct alloc_tag); + + return tag_idx_count < (1UL << NR_UNUSED_PAGEFLAG_BITS); +} + +static bool needs_section_mem(struct module *mod, unsigned long size) +{ + if (!mem_profiling_support) + return false; + + return size >= sizeof(struct alloc_tag); +} + +static struct alloc_tag *find_used_tag(struct alloc_tag *from, struct alloc_tag *to) +{ + while (from <= to) { + struct alloc_tag_counters counter; + + counter = alloc_tag_read(from); + if (counter.bytes) + return from; + from++; + } + + return NULL; +} + +/* Called with mod_area_mt locked */ +static void clean_unused_module_areas_locked(void) +{ + MA_STATE(mas, &mod_area_mt, 0, module_tags.size); + struct module *val; + + mas_for_each(&mas, val, module_tags.size) { + if (val != &unloaded_mod) + continue; + + /* Release area if all tags are unused */ + if (!find_used_tag((struct alloc_tag *)(module_tags.start_addr + mas.index), + (struct alloc_tag *)(module_tags.start_addr + mas.last))) + mas_erase(&mas); + } +} + +/* Called with mod_area_mt locked */ +static bool find_aligned_area(struct ma_state *mas, unsigned long section_size, + unsigned long size, unsigned int prepend, unsigned long align) +{ + bool cleanup_done = false; + +repeat: + /* Try finding exact size and hope the start is aligned */ + if (!mas_empty_area(mas, 0, section_size - 1, prepend + size)) { + if (IS_ALIGNED(mas->index + prepend, align)) + return true; + + /* Try finding larger area to align later */ + mas_reset(mas); + if (!mas_empty_area(mas, 0, section_size - 1, + size + prepend + align - 1)) + return true; + } + + /* No free area, try cleanup stale data and repeat the search once */ + if (!cleanup_done) { + clean_unused_module_areas_locked(); + cleanup_done = true; + mas_reset(mas); + goto repeat; + } + + return false; +} + +static int vm_module_tags_populate(void) +{ + unsigned long phys_end = ALIGN_DOWN(module_tags.start_addr, PAGE_SIZE) + + (vm_module_tags->nr_pages << PAGE_SHIFT); + unsigned long new_end = module_tags.start_addr + module_tags.size; + + if (phys_end < new_end) { + struct page **next_page = vm_module_tags->pages + vm_module_tags->nr_pages; + unsigned long old_shadow_end = ALIGN(phys_end, MODULE_ALIGN); + unsigned long new_shadow_end = ALIGN(new_end, MODULE_ALIGN); + unsigned long more_pages; + unsigned long nr; + + more_pages = ALIGN(new_end - phys_end, PAGE_SIZE) >> PAGE_SHIFT; + nr = alloc_pages_bulk_node(GFP_KERNEL | __GFP_NOWARN, + NUMA_NO_NODE, more_pages, next_page); + if (nr < more_pages || + vmap_pages_range(phys_end, phys_end + (nr << PAGE_SHIFT), PAGE_KERNEL, + next_page, PAGE_SHIFT) < 0) { + /* Clean up and error out */ + for (int i = 0; i < nr; i++) + __free_page(next_page[i]); + return -ENOMEM; + } + + vm_module_tags->nr_pages += nr; + + /* + * Kasan allocates 1 byte of shadow for every 8 bytes of data. + * When kasan_alloc_module_shadow allocates shadow memory, + * its unit of allocation is a page. + * Therefore, here we need to align to MODULE_ALIGN. + */ + if (old_shadow_end < new_shadow_end) + kasan_alloc_module_shadow((void *)old_shadow_end, + new_shadow_end - old_shadow_end, + GFP_KERNEL); + } + + /* + * Mark the pages as accessible, now that they are mapped. + * With hardware tag-based KASAN, marking is skipped for + * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc(). + */ + kasan_unpoison_vmalloc((void *)module_tags.start_addr, + new_end - module_tags.start_addr, + KASAN_VMALLOC_PROT_NORMAL); + + return 0; +} + +static void *reserve_module_tags(struct module *mod, unsigned long size, + unsigned int prepend, unsigned long align) +{ + unsigned long section_size = module_tags.end_addr - module_tags.start_addr; + MA_STATE(mas, &mod_area_mt, 0, section_size - 1); + unsigned long offset; + void *ret = NULL; + + /* If no tags return error */ + if (size < sizeof(struct alloc_tag)) + return ERR_PTR(-EINVAL); + + /* + * align is always power of 2, so we can use IS_ALIGNED and ALIGN. + * align 0 or 1 means no alignment, to simplify set to 1. + */ + if (!align) + align = 1; + + if (!ensure_alignment(align, &prepend)) { + shutdown_mem_profiling(true); + pr_err("%s: alignment %lu is incompatible with allocation tag indexing. Memory allocation profiling is disabled!\n", + mod->name, align); + return ERR_PTR(-EINVAL); + } + + mas_lock(&mas); + if (!find_aligned_area(&mas, section_size, size, prepend, align)) { + ret = ERR_PTR(-ENOMEM); + goto unlock; + } + + /* Mark found area as reserved */ + offset = mas.index; + offset += prepend; + offset = ALIGN(offset, align); + if (offset != mas.index) { + unsigned long pad_start = mas.index; + + mas.last = offset - 1; + mas_store(&mas, &prepend_mod); + if (mas_is_err(&mas)) { + ret = ERR_PTR(xa_err(mas.node)); + goto unlock; + } + mas.index = offset; + mas.last = offset + size - 1; + mas_store(&mas, mod); + if (mas_is_err(&mas)) { + mas.index = pad_start; + mas_erase(&mas); + ret = ERR_PTR(xa_err(mas.node)); + } + } else { + mas.last = offset + size - 1; + mas_store(&mas, mod); + if (mas_is_err(&mas)) + ret = ERR_PTR(xa_err(mas.node)); + } +unlock: + mas_unlock(&mas); + + if (IS_ERR(ret)) + return ret; + + if (module_tags.size < offset + size) { + int grow_res; + + module_tags.size = offset + size; + if (mem_alloc_profiling_enabled() && !tags_addressable()) { + shutdown_mem_profiling(true); + pr_warn("With module %s there are too many tags to fit in %d page flag bits. Memory allocation profiling is disabled!\n", + mod->name, NR_UNUSED_PAGEFLAG_BITS); + } + + grow_res = vm_module_tags_populate(); + if (grow_res) { + shutdown_mem_profiling(true); + pr_err("Failed to allocate memory for allocation tags in the module %s. Memory allocation profiling is disabled!\n", + mod->name); + return ERR_PTR(grow_res); + } + } + + return (struct alloc_tag *)(module_tags.start_addr + offset); +} + +static void release_module_tags(struct module *mod, bool used) +{ + MA_STATE(mas, &mod_area_mt, module_tags.size, module_tags.size); + struct alloc_tag *tag; + struct module *val; + + mas_lock(&mas); + mas_for_each_rev(&mas, val, 0) + if (val == mod) + break; + + if (!val) /* module not found */ + goto out; + + if (!used) + goto release_area; + + /* Find out if the area is used */ + tag = find_used_tag((struct alloc_tag *)(module_tags.start_addr + mas.index), + (struct alloc_tag *)(module_tags.start_addr + mas.last)); + if (tag) { + struct alloc_tag_counters counter = alloc_tag_read(tag); + + pr_info("%s:%u module %s func:%s has %llu allocated at module unload\n", + tag->ct.filename, tag->ct.lineno, tag->ct.modname, + tag->ct.function, counter.bytes); + } else { + used = false; + } +release_area: + mas_store(&mas, used ? &unloaded_mod : NULL); + val = mas_prev_range(&mas, 0); + if (val == &prepend_mod) + mas_store(&mas, NULL); +out: + mas_unlock(&mas); +} + +static void replace_module(struct module *mod, struct module *new_mod) +{ + MA_STATE(mas, &mod_area_mt, 0, module_tags.size); + struct module *val; + + mas_lock(&mas); + mas_for_each(&mas, val, module_tags.size) { + if (val != mod) + continue; + + mas_store_gfp(&mas, new_mod, GFP_KERNEL); + break; + } + mas_unlock(&mas); +} + +static int __init alloc_mod_tags_mem(void) +{ + /* Map space to copy allocation tags */ + vm_module_tags = execmem_vmap(MODULE_ALLOC_TAG_VMAP_SIZE); + if (!vm_module_tags) { + pr_err("Failed to map %lu bytes for module allocation tags\n", + MODULE_ALLOC_TAG_VMAP_SIZE); + module_tags.start_addr = 0; + return -ENOMEM; + } + + vm_module_tags->pages = kmalloc_array(get_vm_area_size(vm_module_tags) >> PAGE_SHIFT, + sizeof(struct page *), GFP_KERNEL | __GFP_ZERO); + if (!vm_module_tags->pages) { + free_vm_area(vm_module_tags); + return -ENOMEM; + } + + module_tags.start_addr = (unsigned long)vm_module_tags->addr; + module_tags.end_addr = module_tags.start_addr + MODULE_ALLOC_TAG_VMAP_SIZE; + /* Ensure the base is alloc_tag aligned when required for indexing */ + module_tags.start_addr = alloc_tag_align(module_tags.start_addr); + + return 0; +} + +static void __init free_mod_tags_mem(void) +{ + int i; + + module_tags.start_addr = 0; + for (i = 0; i < vm_module_tags->nr_pages; i++) + __free_page(vm_module_tags->pages[i]); + kfree(vm_module_tags->pages); + free_vm_area(vm_module_tags); +} + +#else /* CONFIG_MODULES */ + +static inline int alloc_mod_tags_mem(void) { return 0; } +static inline void free_mod_tags_mem(void) {} + +#endif /* CONFIG_MODULES */ + +/* See: Documentation/mm/allocation-profiling.rst */ +static int __init setup_early_mem_profiling(char *str) +{ + bool compressed = false; + bool enable; + + if (!str || !str[0]) + return -EINVAL; + + if (!strncmp(str, "never", 5)) { + enable = false; + mem_profiling_support = false; + pr_info("Memory allocation profiling is disabled!\n"); + } else { + char *token = strsep(&str, ","); + + if (kstrtobool(token, &enable)) + return -EINVAL; + + if (str) { + + if (strcmp(str, "compressed")) + return -EINVAL; + + compressed = true; + } + mem_profiling_support = true; + pr_info("Memory allocation profiling is enabled %s compression and is turned %s!\n", + compressed ? "with" : "without", enable ? "on" : "off"); + } + + if (enable != mem_alloc_profiling_enabled()) { + if (enable) + static_branch_enable(&mem_alloc_profiling_key); + else + static_branch_disable(&mem_alloc_profiling_key); + } + if (compressed != static_key_enabled(&mem_profiling_compressed)) { + if (compressed) + static_branch_enable(&mem_profiling_compressed); + else + static_branch_disable(&mem_profiling_compressed); + } + + return 0; +} +early_param("sysctl.vm.mem_profiling", setup_early_mem_profiling); + +static __init bool need_page_alloc_tagging(void) +{ + if (static_key_enabled(&mem_profiling_compressed)) + return false; + + return mem_profiling_support; +} + +static __init void init_page_alloc_tagging(void) +{ +} + +struct page_ext_operations page_alloc_tagging_ops = { + .size = sizeof(union codetag_ref), + .need = need_page_alloc_tagging, + .init = init_page_alloc_tagging, +}; +EXPORT_SYMBOL(page_alloc_tagging_ops); + +#ifdef CONFIG_SYSCTL +static struct ctl_table memory_allocation_profiling_sysctls[] = { + { + .procname = "mem_profiling", + .data = &mem_alloc_profiling_key, +#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG + .mode = 0444, +#else + .mode = 0644, +#endif + .proc_handler = proc_do_static_key, + }, +}; + +static void __init sysctl_init(void) +{ + if (!mem_profiling_support) + memory_allocation_profiling_sysctls[0].mode = 0444; + + register_sysctl_init("vm", memory_allocation_profiling_sysctls); +} +#else /* CONFIG_SYSCTL */ +static inline void sysctl_init(void) {} +#endif /* CONFIG_SYSCTL */ + +static int __init alloc_tag_init(void) +{ + const struct codetag_type_desc desc = { + .section = ALLOC_TAG_SECTION_NAME, + .tag_size = sizeof(struct alloc_tag), +#ifdef CONFIG_MODULES + .needs_section_mem = needs_section_mem, + .alloc_section_mem = reserve_module_tags, + .free_section_mem = release_module_tags, + .module_replaced = replace_module, +#endif + }; + int res; + + res = alloc_mod_tags_mem(); + if (res) + return res; + + alloc_tag_cttype = codetag_register_type(&desc); + if (IS_ERR(alloc_tag_cttype)) { + free_mod_tags_mem(); + return PTR_ERR(alloc_tag_cttype); + } + + sysctl_init(); + procfs_init(); + + return 0; +} +module_init(alloc_tag_init); diff --git a/lib/asn1_encoder.c b/lib/asn1_encoder.c index 0fd3c454a468..92f35aae13b1 100644 --- a/lib/asn1_encoder.c +++ b/lib/asn1_encoder.c @@ -449,4 +449,5 @@ asn1_encode_boolean(unsigned char *data, const unsigned char *end_data, } EXPORT_SYMBOL_GPL(asn1_encode_boolean); +MODULE_DESCRIPTION("Simple encoder primitives for ASN.1 BER/DER/CER"); MODULE_LICENSE("GPL"); diff --git a/lib/atomic64.c b/lib/atomic64.c index caf895789a1e..1a72bba36d24 100644 --- a/lib/atomic64.c +++ b/lib/atomic64.c @@ -25,15 +25,15 @@ * Ensure each lock is in a separate cacheline. */ static union { - raw_spinlock_t lock; + arch_spinlock_t lock; char pad[L1_CACHE_BYTES]; } atomic64_lock[NR_LOCKS] __cacheline_aligned_in_smp = { [0 ... (NR_LOCKS - 1)] = { - .lock = __RAW_SPIN_LOCK_UNLOCKED(atomic64_lock.lock), + .lock = __ARCH_SPIN_LOCK_UNLOCKED, }, }; -static inline raw_spinlock_t *lock_addr(const atomic64_t *v) +static inline arch_spinlock_t *lock_addr(const atomic64_t *v) { unsigned long addr = (unsigned long) v; @@ -45,12 +45,14 @@ static inline raw_spinlock_t *lock_addr(const atomic64_t *v) s64 generic_atomic64_read(const atomic64_t *v) { unsigned long flags; - raw_spinlock_t *lock = lock_addr(v); + arch_spinlock_t *lock = lock_addr(v); s64 val; - raw_spin_lock_irqsave(lock, flags); + local_irq_save(flags); + arch_spin_lock(lock); val = v->counter; - raw_spin_unlock_irqrestore(lock, flags); + arch_spin_unlock(lock); + local_irq_restore(flags); return val; } EXPORT_SYMBOL(generic_atomic64_read); @@ -58,11 +60,13 @@ EXPORT_SYMBOL(generic_atomic64_read); void generic_atomic64_set(atomic64_t *v, s64 i) { unsigned long flags; - raw_spinlock_t *lock = lock_addr(v); + arch_spinlock_t *lock = lock_addr(v); - raw_spin_lock_irqsave(lock, flags); + local_irq_save(flags); + arch_spin_lock(lock); v->counter = i; - raw_spin_unlock_irqrestore(lock, flags); + arch_spin_unlock(lock); + local_irq_restore(flags); } EXPORT_SYMBOL(generic_atomic64_set); @@ -70,11 +74,13 @@ EXPORT_SYMBOL(generic_atomic64_set); void generic_atomic64_##op(s64 a, atomic64_t *v) \ { \ unsigned long flags; \ - raw_spinlock_t *lock = lock_addr(v); \ + arch_spinlock_t *lock = lock_addr(v); \ \ - raw_spin_lock_irqsave(lock, flags); \ + local_irq_save(flags); \ + arch_spin_lock(lock); \ v->counter c_op a; \ - raw_spin_unlock_irqrestore(lock, flags); \ + arch_spin_unlock(lock); \ + local_irq_restore(flags); \ } \ EXPORT_SYMBOL(generic_atomic64_##op); @@ -82,12 +88,14 @@ EXPORT_SYMBOL(generic_atomic64_##op); s64 generic_atomic64_##op##_return(s64 a, atomic64_t *v) \ { \ unsigned long flags; \ - raw_spinlock_t *lock = lock_addr(v); \ + arch_spinlock_t *lock = lock_addr(v); \ s64 val; \ \ - raw_spin_lock_irqsave(lock, flags); \ + local_irq_save(flags); \ + arch_spin_lock(lock); \ val = (v->counter c_op a); \ - raw_spin_unlock_irqrestore(lock, flags); \ + arch_spin_unlock(lock); \ + local_irq_restore(flags); \ return val; \ } \ EXPORT_SYMBOL(generic_atomic64_##op##_return); @@ -96,13 +104,15 @@ EXPORT_SYMBOL(generic_atomic64_##op##_return); s64 generic_atomic64_fetch_##op(s64 a, atomic64_t *v) \ { \ unsigned long flags; \ - raw_spinlock_t *lock = lock_addr(v); \ + arch_spinlock_t *lock = lock_addr(v); \ s64 val; \ \ - raw_spin_lock_irqsave(lock, flags); \ + local_irq_save(flags); \ + arch_spin_lock(lock); \ val = v->counter; \ v->counter c_op a; \ - raw_spin_unlock_irqrestore(lock, flags); \ + arch_spin_unlock(lock); \ + local_irq_restore(flags); \ return val; \ } \ EXPORT_SYMBOL(generic_atomic64_fetch_##op); @@ -131,14 +141,16 @@ ATOMIC64_OPS(xor, ^=) s64 generic_atomic64_dec_if_positive(atomic64_t *v) { unsigned long flags; - raw_spinlock_t *lock = lock_addr(v); + arch_spinlock_t *lock = lock_addr(v); s64 val; - raw_spin_lock_irqsave(lock, flags); + local_irq_save(flags); + arch_spin_lock(lock); val = v->counter - 1; if (val >= 0) v->counter = val; - raw_spin_unlock_irqrestore(lock, flags); + arch_spin_unlock(lock); + local_irq_restore(flags); return val; } EXPORT_SYMBOL(generic_atomic64_dec_if_positive); @@ -146,14 +158,16 @@ EXPORT_SYMBOL(generic_atomic64_dec_if_positive); s64 generic_atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n) { unsigned long flags; - raw_spinlock_t *lock = lock_addr(v); + arch_spinlock_t *lock = lock_addr(v); s64 val; - raw_spin_lock_irqsave(lock, flags); + local_irq_save(flags); + arch_spin_lock(lock); val = v->counter; if (val == o) v->counter = n; - raw_spin_unlock_irqrestore(lock, flags); + arch_spin_unlock(lock); + local_irq_restore(flags); return val; } EXPORT_SYMBOL(generic_atomic64_cmpxchg); @@ -161,13 +175,15 @@ EXPORT_SYMBOL(generic_atomic64_cmpxchg); s64 generic_atomic64_xchg(atomic64_t *v, s64 new) { unsigned long flags; - raw_spinlock_t *lock = lock_addr(v); + arch_spinlock_t *lock = lock_addr(v); s64 val; - raw_spin_lock_irqsave(lock, flags); + local_irq_save(flags); + arch_spin_lock(lock); val = v->counter; v->counter = new; - raw_spin_unlock_irqrestore(lock, flags); + arch_spin_unlock(lock); + local_irq_restore(flags); return val; } EXPORT_SYMBOL(generic_atomic64_xchg); @@ -175,14 +191,16 @@ EXPORT_SYMBOL(generic_atomic64_xchg); s64 generic_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { unsigned long flags; - raw_spinlock_t *lock = lock_addr(v); + arch_spinlock_t *lock = lock_addr(v); s64 val; - raw_spin_lock_irqsave(lock, flags); + local_irq_save(flags); + arch_spin_lock(lock); val = v->counter; if (val != u) v->counter += a; - raw_spin_unlock_irqrestore(lock, flags); + arch_spin_unlock(lock); + local_irq_restore(flags); return val; } diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c index d9d170238165..759ea1783cc5 100644 --- a/lib/atomic64_test.c +++ b/lib/atomic64_test.c @@ -273,4 +273,5 @@ static __exit void test_atomics_exit(void) {} module_init(test_atomics_init); module_exit(test_atomics_exit); +MODULE_DESCRIPTION("Testsuite for atomic64_t functions"); MODULE_LICENSE("GPL"); diff --git a/lib/bcd.c b/lib/bcd.c index 7e4750b6e801..c5e79ba9cd7b 100644 --- a/lib/bcd.c +++ b/lib/bcd.c @@ -10,6 +10,8 @@ EXPORT_SYMBOL(_bcd2bin); unsigned char _bin2bcd(unsigned val) { - return ((val / 10) << 4) + val % 10; + const unsigned int t = (val * 103) >> 10; + + return (t << 4) | (val - t * 10); } EXPORT_SYMBOL(_bin2bcd); diff --git a/lib/bch.c b/lib/bch.c index 5f71fd76eca8..1c0cb07cdfeb 100644 --- a/lib/bch.c +++ b/lib/bch.c @@ -479,11 +479,8 @@ static int solve_linear_system(struct bch_control *bch, unsigned int *rows, /* find suitable row for elimination */ for (r = p; r < m; r++) { if (rows[r] & mask) { - if (r != p) { - tmp = rows[r]; - rows[r] = rows[p]; - rows[p] = tmp; - } + if (r != p) + swap(rows[r], rows[p]); rem = r+1; break; } @@ -799,21 +796,14 @@ static void gf_poly_div(struct bch_control *bch, struct gf_poly *a, static struct gf_poly *gf_poly_gcd(struct bch_control *bch, struct gf_poly *a, struct gf_poly *b) { - struct gf_poly *tmp; - dbg("gcd(%s,%s)=", gf_poly_str(a), gf_poly_str(b)); - if (a->deg < b->deg) { - tmp = b; - b = a; - a = tmp; - } + if (a->deg < b->deg) + swap(a, b); while (b->deg > 0) { gf_poly_mod(bch, a, b, NULL); - tmp = b; - b = a; - a = tmp; + swap(a, b); } dbg("%s\n", gf_poly_str(a)); diff --git a/lib/bitfield_kunit.c b/lib/bitfield_kunit.c index 1473d8b4bf0f..5ccd86f61896 100644 --- a/lib/bitfield_kunit.c +++ b/lib/bitfield_kunit.c @@ -151,4 +151,5 @@ static struct kunit_suite bitfields_test_suite = { kunit_test_suites(&bitfields_test_suite); MODULE_AUTHOR("Johannes Berg <johannes@sipsolutions.net>"); +MODULE_DESCRIPTION("Test cases for bitfield helpers"); MODULE_LICENSE("GPL"); diff --git a/lib/bootconfig.c b/lib/bootconfig.c index 97f8911ea339..81f29c29f47b 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -4,8 +4,16 @@ * Masami Hiramatsu <mhiramat@kernel.org> */ -#ifdef __KERNEL__ +/* + * NOTE: This is only for tools/bootconfig, because tools/bootconfig will + * run the parser sanity test. + * This does NOT mean lib/bootconfig.c is available in the user space. + * However, if you change this file, please make sure the tools/bootconfig + * has no issue on building and running. + */ #include <linux/bootconfig.h> + +#ifdef __KERNEL__ #include <linux/bug.h> #include <linux/ctype.h> #include <linux/errno.h> @@ -24,16 +32,6 @@ const char * __init xbc_get_embedded_bootconfig(size_t *size) return (*size) ? embedded_bootconfig_data : NULL; } #endif - -#else /* !__KERNEL__ */ -/* - * NOTE: This is only for tools/bootconfig, because tools/bootconfig will - * run the parser sanity test. - * This does NOT mean lib/bootconfig.c is available in the user space. - * However, if you change this file, please make sure the tools/bootconfig - * has no issue on building and running. - */ -#include <linux/bootconfig.h> #endif /* diff --git a/lib/btree.c b/lib/btree.c index 49420cae3a83..bb81d3393ac5 100644 --- a/lib/btree.c +++ b/lib/btree.c @@ -43,7 +43,6 @@ #include <linux/slab.h> #include <linux/module.h> -#define MAX(a, b) ((a) > (b) ? (a) : (b)) #define NODESIZE MAX(L1_CACHE_BYTES, 128) struct btree_geo { diff --git a/lib/build_OID_registry b/lib/build_OID_registry index d7fc32ea8ac2..8267e8d71338 100755 --- a/lib/build_OID_registry +++ b/lib/build_OID_registry @@ -8,6 +8,7 @@ # use strict; +use Cwd qw(abs_path); my @names = (); my @oids = (); @@ -17,6 +18,8 @@ if ($#ARGV != 1) { exit(2); } +my $abs_srctree = abs_path($ENV{'srctree'}); + # # Open the file to read from # @@ -35,7 +38,9 @@ close IN_FILE || die; # open C_FILE, ">$ARGV[1]" or die; print C_FILE "/*\n"; -print C_FILE " * Automatically generated by ", $0, ". Do not edit\n"; +my $scriptname = $0; +$scriptname =~ s#^\Q$abs_srctree/\E##; +print C_FILE " * Automatically generated by ", $scriptname, ". Do not edit\n"; print C_FILE " */\n"; # diff --git a/lib/buildid.c b/lib/buildid.c index 898301b49eb6..c4b0f376fb34 100644 --- a/lib/buildid.c +++ b/lib/buildid.c @@ -5,143 +5,310 @@ #include <linux/elf.h> #include <linux/kernel.h> #include <linux/pagemap.h> +#include <linux/secretmem.h> #define BUILD_ID 3 +#define MAX_PHDR_CNT 256 + +struct freader { + void *buf; + u32 buf_sz; + int err; + union { + struct { + struct file *file; + struct folio *folio; + void *addr; + loff_t folio_off; + bool may_fault; + }; + struct { + const char *data; + u64 data_sz; + }; + }; +}; + +static void freader_init_from_file(struct freader *r, void *buf, u32 buf_sz, + struct file *file, bool may_fault) +{ + memset(r, 0, sizeof(*r)); + r->buf = buf; + r->buf_sz = buf_sz; + r->file = file; + r->may_fault = may_fault; +} + +static void freader_init_from_mem(struct freader *r, const char *data, u64 data_sz) +{ + memset(r, 0, sizeof(*r)); + r->data = data; + r->data_sz = data_sz; +} + +static void freader_put_folio(struct freader *r) +{ + if (!r->folio) + return; + kunmap_local(r->addr); + folio_put(r->folio); + r->folio = NULL; +} + +static int freader_get_folio(struct freader *r, loff_t file_off) +{ + /* check if we can just reuse current folio */ + if (r->folio && file_off >= r->folio_off && + file_off < r->folio_off + folio_size(r->folio)) + return 0; + + freader_put_folio(r); + + /* reject secretmem folios created with memfd_secret() */ + if (secretmem_mapping(r->file->f_mapping)) + return -EFAULT; + + r->folio = filemap_get_folio(r->file->f_mapping, file_off >> PAGE_SHIFT); + + /* if sleeping is allowed, wait for the page, if necessary */ + if (r->may_fault && (IS_ERR(r->folio) || !folio_test_uptodate(r->folio))) { + filemap_invalidate_lock_shared(r->file->f_mapping); + r->folio = read_cache_folio(r->file->f_mapping, file_off >> PAGE_SHIFT, + NULL, r->file); + filemap_invalidate_unlock_shared(r->file->f_mapping); + } + + if (IS_ERR(r->folio) || !folio_test_uptodate(r->folio)) { + if (!IS_ERR(r->folio)) + folio_put(r->folio); + r->folio = NULL; + return -EFAULT; + } + + r->folio_off = folio_pos(r->folio); + r->addr = kmap_local_folio(r->folio, 0); + + return 0; +} + +static const void *freader_fetch(struct freader *r, loff_t file_off, size_t sz) +{ + size_t folio_sz; + + /* provided internal temporary buffer should be sized correctly */ + if (WARN_ON(r->buf && sz > r->buf_sz)) { + r->err = -E2BIG; + return NULL; + } + + if (unlikely(file_off + sz < file_off)) { + r->err = -EOVERFLOW; + return NULL; + } + + /* working with memory buffer is much more straightforward */ + if (!r->buf) { + if (file_off + sz > r->data_sz) { + r->err = -ERANGE; + return NULL; + } + return r->data + file_off; + } + + /* fetch or reuse folio for given file offset */ + r->err = freader_get_folio(r, file_off); + if (r->err) + return NULL; + + /* if requested data is crossing folio boundaries, we have to copy + * everything into our local buffer to keep a simple linear memory + * access interface + */ + folio_sz = folio_size(r->folio); + if (file_off + sz > r->folio_off + folio_sz) { + int part_sz = r->folio_off + folio_sz - file_off; + + /* copy the part that resides in the current folio */ + memcpy(r->buf, r->addr + (file_off - r->folio_off), part_sz); + + /* fetch next folio */ + r->err = freader_get_folio(r, r->folio_off + folio_sz); + if (r->err) + return NULL; + + /* copy the rest of requested data */ + memcpy(r->buf + part_sz, r->addr, sz - part_sz); + + return r->buf; + } + + /* if data fits in a single folio, just return direct pointer */ + return r->addr + (file_off - r->folio_off); +} + +static void freader_cleanup(struct freader *r) +{ + if (!r->buf) + return; /* non-file-backed mode */ + + freader_put_folio(r); +} + /* * Parse build id from the note segment. This logic can be shared between * 32-bit and 64-bit system, because Elf32_Nhdr and Elf64_Nhdr are * identical. */ -static int parse_build_id_buf(unsigned char *build_id, - __u32 *size, - const void *note_start, - Elf32_Word note_size) +static int parse_build_id(struct freader *r, unsigned char *build_id, __u32 *size, + loff_t note_off, Elf32_Word note_size) { - Elf32_Word note_offs = 0, new_offs; + const char note_name[] = "GNU"; + const size_t note_name_sz = sizeof(note_name); + u32 build_id_off, new_off, note_end, name_sz, desc_sz; + const Elf32_Nhdr *nhdr; + const char *data; + + if (check_add_overflow(note_off, note_size, ¬e_end)) + return -EINVAL; - while (note_offs + sizeof(Elf32_Nhdr) < note_size) { - Elf32_Nhdr *nhdr = (Elf32_Nhdr *)(note_start + note_offs); + while (note_end - note_off > sizeof(Elf32_Nhdr) + note_name_sz) { + nhdr = freader_fetch(r, note_off, sizeof(Elf32_Nhdr) + note_name_sz); + if (!nhdr) + return r->err; + + name_sz = READ_ONCE(nhdr->n_namesz); + desc_sz = READ_ONCE(nhdr->n_descsz); + + new_off = note_off + sizeof(Elf32_Nhdr); + if (check_add_overflow(new_off, ALIGN(name_sz, 4), &new_off) || + check_add_overflow(new_off, ALIGN(desc_sz, 4), &new_off) || + new_off > note_end) + break; if (nhdr->n_type == BUILD_ID && - nhdr->n_namesz == sizeof("GNU") && - !strcmp((char *)(nhdr + 1), "GNU") && - nhdr->n_descsz > 0 && - nhdr->n_descsz <= BUILD_ID_SIZE_MAX) { - memcpy(build_id, - note_start + note_offs + - ALIGN(sizeof("GNU"), 4) + sizeof(Elf32_Nhdr), - nhdr->n_descsz); - memset(build_id + nhdr->n_descsz, 0, - BUILD_ID_SIZE_MAX - nhdr->n_descsz); + name_sz == note_name_sz && + memcmp(nhdr + 1, note_name, note_name_sz) == 0 && + desc_sz > 0 && desc_sz <= BUILD_ID_SIZE_MAX) { + build_id_off = note_off + sizeof(Elf32_Nhdr) + ALIGN(note_name_sz, 4); + + /* freader_fetch() will invalidate nhdr pointer */ + data = freader_fetch(r, build_id_off, desc_sz); + if (!data) + return r->err; + + memcpy(build_id, data, desc_sz); + memset(build_id + desc_sz, 0, BUILD_ID_SIZE_MAX - desc_sz); if (size) - *size = nhdr->n_descsz; + *size = desc_sz; return 0; } - new_offs = note_offs + sizeof(Elf32_Nhdr) + - ALIGN(nhdr->n_namesz, 4) + ALIGN(nhdr->n_descsz, 4); - if (new_offs <= note_offs) /* overflow */ - break; - note_offs = new_offs; + + note_off = new_off; } return -EINVAL; } -static inline int parse_build_id(const void *page_addr, - unsigned char *build_id, - __u32 *size, - const void *note_start, - Elf32_Word note_size) +/* Parse build ID from 32-bit ELF */ +static int get_build_id_32(struct freader *r, unsigned char *build_id, __u32 *size) { - /* check for overflow */ - if (note_start < page_addr || note_start + note_size < note_start) - return -EINVAL; + const Elf32_Ehdr *ehdr; + const Elf32_Phdr *phdr; + __u32 phnum, phoff, i; - /* only supports note that fits in the first page */ - if (note_start + note_size > page_addr + PAGE_SIZE) - return -EINVAL; + ehdr = freader_fetch(r, 0, sizeof(Elf32_Ehdr)); + if (!ehdr) + return r->err; - return parse_build_id_buf(build_id, size, note_start, note_size); -} + /* subsequent freader_fetch() calls invalidate pointers, so remember locally */ + phnum = READ_ONCE(ehdr->e_phnum); + phoff = READ_ONCE(ehdr->e_phoff); -/* Parse build ID from 32-bit ELF */ -static int get_build_id_32(const void *page_addr, unsigned char *build_id, - __u32 *size) -{ - Elf32_Ehdr *ehdr = (Elf32_Ehdr *)page_addr; - Elf32_Phdr *phdr; - int i; + /* set upper bound on amount of segments (phdrs) we iterate */ + if (phnum > MAX_PHDR_CNT) + phnum = MAX_PHDR_CNT; - /* only supports phdr that fits in one page */ - if (ehdr->e_phnum > - (PAGE_SIZE - sizeof(Elf32_Ehdr)) / sizeof(Elf32_Phdr)) + /* check that phoff is not large enough to cause an overflow */ + if (phoff + phnum * sizeof(Elf32_Phdr) < phoff) return -EINVAL; - phdr = (Elf32_Phdr *)(page_addr + sizeof(Elf32_Ehdr)); + for (i = 0; i < phnum; ++i) { + phdr = freader_fetch(r, phoff + i * sizeof(Elf32_Phdr), sizeof(Elf32_Phdr)); + if (!phdr) + return r->err; - for (i = 0; i < ehdr->e_phnum; ++i) { - if (phdr[i].p_type == PT_NOTE && - !parse_build_id(page_addr, build_id, size, - page_addr + phdr[i].p_offset, - phdr[i].p_filesz)) + if (phdr->p_type == PT_NOTE && + !parse_build_id(r, build_id, size, READ_ONCE(phdr->p_offset), + READ_ONCE(phdr->p_filesz))) return 0; } return -EINVAL; } /* Parse build ID from 64-bit ELF */ -static int get_build_id_64(const void *page_addr, unsigned char *build_id, - __u32 *size) +static int get_build_id_64(struct freader *r, unsigned char *build_id, __u32 *size) { - Elf64_Ehdr *ehdr = (Elf64_Ehdr *)page_addr; - Elf64_Phdr *phdr; - int i; + const Elf64_Ehdr *ehdr; + const Elf64_Phdr *phdr; + __u32 phnum, i; + __u64 phoff; + + ehdr = freader_fetch(r, 0, sizeof(Elf64_Ehdr)); + if (!ehdr) + return r->err; + + /* subsequent freader_fetch() calls invalidate pointers, so remember locally */ + phnum = READ_ONCE(ehdr->e_phnum); + phoff = READ_ONCE(ehdr->e_phoff); + + /* set upper bound on amount of segments (phdrs) we iterate */ + if (phnum > MAX_PHDR_CNT) + phnum = MAX_PHDR_CNT; - /* only supports phdr that fits in one page */ - if (ehdr->e_phnum > - (PAGE_SIZE - sizeof(Elf64_Ehdr)) / sizeof(Elf64_Phdr)) + /* check that phoff is not large enough to cause an overflow */ + if (phoff + phnum * sizeof(Elf64_Phdr) < phoff) return -EINVAL; - phdr = (Elf64_Phdr *)(page_addr + sizeof(Elf64_Ehdr)); + for (i = 0; i < phnum; ++i) { + phdr = freader_fetch(r, phoff + i * sizeof(Elf64_Phdr), sizeof(Elf64_Phdr)); + if (!phdr) + return r->err; - for (i = 0; i < ehdr->e_phnum; ++i) { - if (phdr[i].p_type == PT_NOTE && - !parse_build_id(page_addr, build_id, size, - page_addr + phdr[i].p_offset, - phdr[i].p_filesz)) + if (phdr->p_type == PT_NOTE && + !parse_build_id(r, build_id, size, READ_ONCE(phdr->p_offset), + READ_ONCE(phdr->p_filesz))) return 0; } + return -EINVAL; } -/* - * Parse build ID of ELF file mapped to vma - * @vma: vma object - * @build_id: buffer to store build id, at least BUILD_ID_SIZE long - * @size: returns actual build id size in case of success - * - * Return: 0 on success, -EINVAL otherwise - */ -int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, - __u32 *size) +/* enough for Elf64_Ehdr, Elf64_Phdr, and all the smaller requests */ +#define MAX_FREADER_BUF_SZ 64 + +static int __build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, + __u32 *size, bool may_fault) { - Elf32_Ehdr *ehdr; - struct page *page; - void *page_addr; + const Elf32_Ehdr *ehdr; + struct freader r; + char buf[MAX_FREADER_BUF_SZ]; int ret; /* only works for page backed storage */ if (!vma->vm_file) return -EINVAL; - page = find_get_page(vma->vm_file->f_mapping, 0); - if (!page) - return -EFAULT; /* page not mapped */ + freader_init_from_file(&r, buf, sizeof(buf), vma->vm_file, may_fault); + + /* fetch first 18 bytes of ELF header for checks */ + ehdr = freader_fetch(&r, 0, offsetofend(Elf32_Ehdr, e_type)); + if (!ehdr) { + ret = r.err; + goto out; + } ret = -EINVAL; - page_addr = kmap_local_page(page); - ehdr = (Elf32_Ehdr *)page_addr; /* compare magic x7f "ELF" */ if (memcmp(ehdr->e_ident, ELFMAG, SELFMAG) != 0) @@ -152,15 +319,46 @@ int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, goto out; if (ehdr->e_ident[EI_CLASS] == ELFCLASS32) - ret = get_build_id_32(page_addr, build_id, size); + ret = get_build_id_32(&r, build_id, size); else if (ehdr->e_ident[EI_CLASS] == ELFCLASS64) - ret = get_build_id_64(page_addr, build_id, size); + ret = get_build_id_64(&r, build_id, size); out: - kunmap_local(page_addr); - put_page(page); + freader_cleanup(&r); return ret; } +/* + * Parse build ID of ELF file mapped to vma + * @vma: vma object + * @build_id: buffer to store build id, at least BUILD_ID_SIZE long + * @size: returns actual build id size in case of success + * + * Assumes no page fault can be taken, so if relevant portions of ELF file are + * not already paged in, fetching of build ID fails. + * + * Return: 0 on success; negative error, otherwise + */ +int build_id_parse_nofault(struct vm_area_struct *vma, unsigned char *build_id, __u32 *size) +{ + return __build_id_parse(vma, build_id, size, false /* !may_fault */); +} + +/* + * Parse build ID of ELF file mapped to VMA + * @vma: vma object + * @build_id: buffer to store build id, at least BUILD_ID_SIZE long + * @size: returns actual build id size in case of success + * + * Assumes faultable context and can cause page faults to bring in file data + * into page cache. + * + * Return: 0 on success; negative error, otherwise + */ +int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, __u32 *size) +{ + return __build_id_parse(vma, build_id, size, true /* may_fault */); +} + /** * build_id_parse_buf - Get build ID from a buffer * @buf: ELF note section(s) to parse @@ -171,7 +369,15 @@ out: */ int build_id_parse_buf(const void *buf, unsigned char *build_id, u32 buf_size) { - return parse_build_id_buf(build_id, NULL, buf, buf_size); + struct freader r; + int err; + + freader_init_from_mem(&r, buf, buf_size); + + err = parse_build_id(&r, build_id, NULL, 0, buf_size); + + freader_cleanup(&r); + return err; } #if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) || IS_ENABLED(CONFIG_VMCORE_INFO) @@ -182,8 +388,8 @@ unsigned char vmlinux_build_id[BUILD_ID_SIZE_MAX] __ro_after_init; */ void __init init_vmlinux_build_id(void) { - extern const void __start_notes __weak; - extern const void __stop_notes __weak; + extern const void __start_notes; + extern const void __stop_notes; unsigned int size = &__stop_notes - &__start_notes; build_id_parse_buf(&__start_notes, vmlinux_build_id, size); diff --git a/lib/checksum.c b/lib/checksum.c index 6860d6b05a17..025ba546e1ec 100644 --- a/lib/checksum.c +++ b/lib/checksum.c @@ -34,15 +34,6 @@ #include <asm/byteorder.h> #ifndef do_csum -static inline unsigned short from32to16(unsigned int x) -{ - /* add up 16-bit and 16-bit for 16+c bit */ - x = (x & 0xffff) + (x >> 16); - /* add up carry.. */ - x = (x & 0xffff) + (x >> 16); - return x; -} - static unsigned int do_csum(const unsigned char *buff, int len) { int odd; @@ -90,7 +81,7 @@ static unsigned int do_csum(const unsigned char *buff, int len) #else result += (*buff << 8); #endif - result = from32to16(result); + result = csum_from32to16(result); if (odd) result = ((result >> 8) & 0xff) | ((result & 0xff) << 8); out: diff --git a/lib/checksum_kunit.c b/lib/checksum_kunit.c index 404dba36bae3..be04aa42125c 100644 --- a/lib/checksum_kunit.c +++ b/lib/checksum_kunit.c @@ -468,12 +468,9 @@ static __wsum to_wsum(u32 x) static void assert_setup_correct(struct kunit *test) { - CHECK_EQ(sizeof(random_buf) / sizeof(random_buf[0]), MAX_LEN); - CHECK_EQ(sizeof(expected_results) / sizeof(expected_results[0]), - MAX_LEN); - CHECK_EQ(sizeof(init_sums_no_overflow) / - sizeof(init_sums_no_overflow[0]), - MAX_LEN); + CHECK_EQ(ARRAY_SIZE(random_buf), MAX_LEN); + CHECK_EQ(ARRAY_SIZE(expected_results), MAX_LEN); + CHECK_EQ(ARRAY_SIZE(init_sums_no_overflow), MAX_LEN); } /* @@ -639,4 +636,5 @@ static struct kunit_suite checksum_test_suite = { kunit_test_suites(&checksum_test_suite); MODULE_AUTHOR("Noah Goldstein <goldstein.w.n@gmail.com>"); +MODULE_DESCRIPTION("Test cases csum_* APIs"); MODULE_LICENSE("GPL"); diff --git a/lib/closure.c b/lib/closure.c index c16540552d61..2bfe7d2a0048 100644 --- a/lib/closure.c +++ b/lib/closure.c @@ -13,14 +13,25 @@ #include <linux/seq_file.h> #include <linux/sched/debug.h> -static inline void closure_put_after_sub(struct closure *cl, int flags) +static inline void closure_put_after_sub_checks(int flags) { int r = flags & CLOSURE_REMAINING_MASK; - BUG_ON(flags & CLOSURE_GUARD_MASK); - BUG_ON(!r && (flags & ~CLOSURE_DESTRUCTOR)); + if (WARN(flags & CLOSURE_GUARD_MASK, + "closure has guard bits set: %x (%u)", + flags & CLOSURE_GUARD_MASK, (unsigned) __fls(r))) + r &= ~CLOSURE_GUARD_MASK; + + WARN(!r && (flags & ~CLOSURE_DESTRUCTOR), + "closure ref hit 0 with incorrect flags set: %x (%u)", + flags & ~CLOSURE_DESTRUCTOR, (unsigned) __fls(flags)); +} + +static inline void closure_put_after_sub(struct closure *cl, int flags) +{ + closure_put_after_sub_checks(flags); - if (!r) { + if (!(flags & CLOSURE_REMAINING_MASK)) { smp_acquire__after_ctrl_dep(); cl->closure_get_happened = false; @@ -139,6 +150,78 @@ void __sched __closure_sync(struct closure *cl) } EXPORT_SYMBOL(__closure_sync); +/* + * closure_return_sync - finish running a closure, synchronously (i.e. waiting + * for outstanding get()s to finish) and returning once closure refcount is 0. + * + * Unlike closure_sync() this doesn't reinit the ref to 1; subsequent + * closure_get_not_zero() calls waill fail. + */ +void __sched closure_return_sync(struct closure *cl) +{ + struct closure_syncer s = { .task = current }; + + cl->s = &s; + set_closure_fn(cl, closure_sync_fn, NULL); + + unsigned flags = atomic_sub_return_release(1 + CLOSURE_RUNNING - CLOSURE_DESTRUCTOR, + &cl->remaining); + + closure_put_after_sub_checks(flags); + + if (unlikely(flags & CLOSURE_REMAINING_MASK)) { + while (1) { + set_current_state(TASK_UNINTERRUPTIBLE); + if (s.done) + break; + schedule(); + } + + __set_current_state(TASK_RUNNING); + } + + if (cl->parent) + closure_put(cl->parent); +} +EXPORT_SYMBOL(closure_return_sync); + +int __sched __closure_sync_timeout(struct closure *cl, unsigned long timeout) +{ + struct closure_syncer s = { .task = current }; + int ret = 0; + + cl->s = &s; + continue_at(cl, closure_sync_fn, NULL); + + while (1) { + set_current_state(TASK_UNINTERRUPTIBLE); + if (s.done) + break; + if (!timeout) { + /* + * Carefully undo the continue_at() - but only if it + * hasn't completed, i.e. the final closure_put() hasn't + * happened yet: + */ + unsigned old, new, v = atomic_read(&cl->remaining); + do { + old = v; + if (!old || (old & CLOSURE_RUNNING)) + goto success; + + new = old + CLOSURE_REMAINING_INITIALIZER; + } while ((v = atomic_cmpxchg(&cl->remaining, old, new)) != old); + ret = -ETIME; + } + + timeout = schedule_timeout(timeout); + } +success: + __set_current_state(TASK_RUNNING); + return ret; +} +EXPORT_SYMBOL(__closure_sync_timeout); + #ifdef CONFIG_DEBUG_CLOSURES static LIST_HEAD(closure_list); @@ -161,6 +244,9 @@ void closure_debug_destroy(struct closure *cl) { unsigned long flags; + if (cl->magic == CLOSURE_MAGIC_STACK) + return; + BUG_ON(cl->magic != CLOSURE_MAGIC_ALIVE); cl->magic = CLOSURE_MAGIC_DEAD; @@ -192,7 +278,7 @@ static int debug_show(struct seq_file *f, void *data) seq_printf(f, " W %pS\n", (void *) cl->waiting_on); - seq_puts(f, "\n"); + seq_putc(f, '\n'); } spin_unlock_irq(&closure_list_lock); diff --git a/lib/cmdline_kunit.c b/lib/cmdline_kunit.c index 705b82736be0..c1602f797637 100644 --- a/lib/cmdline_kunit.c +++ b/lib/cmdline_kunit.c @@ -153,4 +153,5 @@ static struct kunit_suite cmdline_test_suite = { }; kunit_test_suite(cmdline_test_suite); +MODULE_DESCRIPTION("Test cases for API provided by cmdline.c"); MODULE_LICENSE("GPL"); diff --git a/lib/codetag.c b/lib/codetag.c new file mode 100644 index 000000000000..42aadd6c1454 --- /dev/null +++ b/lib/codetag.c @@ -0,0 +1,377 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/codetag.h> +#include <linux/idr.h> +#include <linux/kallsyms.h> +#include <linux/module.h> +#include <linux/seq_buf.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> + +struct codetag_type { + struct list_head link; + unsigned int count; + struct idr mod_idr; + struct rw_semaphore mod_lock; /* protects mod_idr */ + struct codetag_type_desc desc; +}; + +struct codetag_range { + struct codetag *start; + struct codetag *stop; +}; + +struct codetag_module { + struct module *mod; + struct codetag_range range; +}; + +static DEFINE_MUTEX(codetag_lock); +static LIST_HEAD(codetag_types); + +void codetag_lock_module_list(struct codetag_type *cttype, bool lock) +{ + if (lock) + down_read(&cttype->mod_lock); + else + up_read(&cttype->mod_lock); +} + +bool codetag_trylock_module_list(struct codetag_type *cttype) +{ + return down_read_trylock(&cttype->mod_lock) != 0; +} + +struct codetag_iterator codetag_get_ct_iter(struct codetag_type *cttype) +{ + struct codetag_iterator iter = { + .cttype = cttype, + .cmod = NULL, + .mod_id = 0, + .ct = NULL, + }; + + return iter; +} + +static inline struct codetag *get_first_module_ct(struct codetag_module *cmod) +{ + return cmod->range.start < cmod->range.stop ? cmod->range.start : NULL; +} + +static inline +struct codetag *get_next_module_ct(struct codetag_iterator *iter) +{ + struct codetag *res = (struct codetag *) + ((char *)iter->ct + iter->cttype->desc.tag_size); + + return res < iter->cmod->range.stop ? res : NULL; +} + +struct codetag *codetag_next_ct(struct codetag_iterator *iter) +{ + struct codetag_type *cttype = iter->cttype; + struct codetag_module *cmod; + struct codetag *ct; + + lockdep_assert_held(&cttype->mod_lock); + + if (unlikely(idr_is_empty(&cttype->mod_idr))) + return NULL; + + ct = NULL; + while (true) { + cmod = idr_find(&cttype->mod_idr, iter->mod_id); + + /* If module was removed move to the next one */ + if (!cmod) + cmod = idr_get_next_ul(&cttype->mod_idr, + &iter->mod_id); + + /* Exit if no more modules */ + if (!cmod) + break; + + if (cmod != iter->cmod) { + iter->cmod = cmod; + ct = get_first_module_ct(cmod); + } else + ct = get_next_module_ct(iter); + + if (ct) + break; + + iter->mod_id++; + } + + iter->ct = ct; + return ct; +} + +void codetag_to_text(struct seq_buf *out, struct codetag *ct) +{ + if (ct->modname) + seq_buf_printf(out, "%s:%u [%s] func:%s", + ct->filename, ct->lineno, + ct->modname, ct->function); + else + seq_buf_printf(out, "%s:%u func:%s", + ct->filename, ct->lineno, ct->function); +} + +static inline size_t range_size(const struct codetag_type *cttype, + const struct codetag_range *range) +{ + return ((char *)range->stop - (char *)range->start) / + cttype->desc.tag_size; +} + +static void *get_symbol(struct module *mod, const char *prefix, const char *name) +{ + DECLARE_SEQ_BUF(sb, KSYM_NAME_LEN); + const char *buf; + void *ret; + + seq_buf_printf(&sb, "%s%s", prefix, name); + if (seq_buf_has_overflowed(&sb)) + return NULL; + + buf = seq_buf_str(&sb); + preempt_disable(); + ret = mod ? + (void *)find_kallsyms_symbol_value(mod, buf) : + (void *)kallsyms_lookup_name(buf); + preempt_enable(); + + return ret; +} + +static struct codetag_range get_section_range(struct module *mod, + const char *section) +{ + return (struct codetag_range) { + get_symbol(mod, CODETAG_SECTION_START_PREFIX, section), + get_symbol(mod, CODETAG_SECTION_STOP_PREFIX, section), + }; +} + +static const char *get_mod_name(__maybe_unused struct module *mod) +{ +#ifdef CONFIG_MODULES + if (mod) + return mod->name; +#endif + return "(built-in)"; +} + +static int codetag_module_init(struct codetag_type *cttype, struct module *mod) +{ + struct codetag_range range; + struct codetag_module *cmod; + int err; + + range = get_section_range(mod, cttype->desc.section); + if (!range.start || !range.stop) { + pr_warn("Failed to load code tags of type %s from the module %s\n", + cttype->desc.section, get_mod_name(mod)); + return -EINVAL; + } + + /* Ignore empty ranges */ + if (range.start == range.stop) + return 0; + + BUG_ON(range.start > range.stop); + + cmod = kmalloc(sizeof(*cmod), GFP_KERNEL); + if (unlikely(!cmod)) + return -ENOMEM; + + cmod->mod = mod; + cmod->range = range; + + down_write(&cttype->mod_lock); + err = idr_alloc(&cttype->mod_idr, cmod, 0, 0, GFP_KERNEL); + if (err >= 0) { + cttype->count += range_size(cttype, &range); + if (cttype->desc.module_load) + cttype->desc.module_load(cttype, cmod); + } + up_write(&cttype->mod_lock); + + if (err < 0) { + kfree(cmod); + return err; + } + + return 0; +} + +#ifdef CONFIG_MODULES +#define CODETAG_SECTION_PREFIX ".codetag." + +/* Some codetag types need a separate module section */ +bool codetag_needs_module_section(struct module *mod, const char *name, + unsigned long size) +{ + const char *type_name; + struct codetag_type *cttype; + bool ret = false; + + if (strncmp(name, CODETAG_SECTION_PREFIX, strlen(CODETAG_SECTION_PREFIX))) + return false; + + type_name = name + strlen(CODETAG_SECTION_PREFIX); + mutex_lock(&codetag_lock); + list_for_each_entry(cttype, &codetag_types, link) { + if (strcmp(type_name, cttype->desc.section) == 0) { + if (!cttype->desc.needs_section_mem) + break; + + down_write(&cttype->mod_lock); + ret = cttype->desc.needs_section_mem(mod, size); + up_write(&cttype->mod_lock); + break; + } + } + mutex_unlock(&codetag_lock); + + return ret; +} + +void *codetag_alloc_module_section(struct module *mod, const char *name, + unsigned long size, unsigned int prepend, + unsigned long align) +{ + const char *type_name = name + strlen(CODETAG_SECTION_PREFIX); + struct codetag_type *cttype; + void *ret = ERR_PTR(-EINVAL); + + mutex_lock(&codetag_lock); + list_for_each_entry(cttype, &codetag_types, link) { + if (strcmp(type_name, cttype->desc.section) == 0) { + if (WARN_ON(!cttype->desc.alloc_section_mem)) + break; + + down_write(&cttype->mod_lock); + ret = cttype->desc.alloc_section_mem(mod, size, prepend, align); + up_write(&cttype->mod_lock); + break; + } + } + mutex_unlock(&codetag_lock); + + return ret; +} + +void codetag_free_module_sections(struct module *mod) +{ + struct codetag_type *cttype; + + mutex_lock(&codetag_lock); + list_for_each_entry(cttype, &codetag_types, link) { + if (!cttype->desc.free_section_mem) + continue; + + down_write(&cttype->mod_lock); + cttype->desc.free_section_mem(mod, false); + up_write(&cttype->mod_lock); + } + mutex_unlock(&codetag_lock); +} + +void codetag_module_replaced(struct module *mod, struct module *new_mod) +{ + struct codetag_type *cttype; + + mutex_lock(&codetag_lock); + list_for_each_entry(cttype, &codetag_types, link) { + if (!cttype->desc.module_replaced) + continue; + + down_write(&cttype->mod_lock); + cttype->desc.module_replaced(mod, new_mod); + up_write(&cttype->mod_lock); + } + mutex_unlock(&codetag_lock); +} + +void codetag_load_module(struct module *mod) +{ + struct codetag_type *cttype; + + if (!mod) + return; + + mutex_lock(&codetag_lock); + list_for_each_entry(cttype, &codetag_types, link) + codetag_module_init(cttype, mod); + mutex_unlock(&codetag_lock); +} + +void codetag_unload_module(struct module *mod) +{ + struct codetag_type *cttype; + + if (!mod) + return; + + /* await any module's kfree_rcu() operations to complete */ + kvfree_rcu_barrier(); + + mutex_lock(&codetag_lock); + list_for_each_entry(cttype, &codetag_types, link) { + struct codetag_module *found = NULL; + struct codetag_module *cmod; + unsigned long mod_id, tmp; + + down_write(&cttype->mod_lock); + idr_for_each_entry_ul(&cttype->mod_idr, cmod, tmp, mod_id) { + if (cmod->mod && cmod->mod == mod) { + found = cmod; + break; + } + } + if (found) { + if (cttype->desc.module_unload) + cttype->desc.module_unload(cttype, cmod); + + cttype->count -= range_size(cttype, &cmod->range); + idr_remove(&cttype->mod_idr, mod_id); + kfree(cmod); + } + up_write(&cttype->mod_lock); + if (found && cttype->desc.free_section_mem) + cttype->desc.free_section_mem(mod, true); + } + mutex_unlock(&codetag_lock); +} +#endif /* CONFIG_MODULES */ + +struct codetag_type * +codetag_register_type(const struct codetag_type_desc *desc) +{ + struct codetag_type *cttype; + int err; + + BUG_ON(desc->tag_size <= 0); + + cttype = kzalloc(sizeof(*cttype), GFP_KERNEL); + if (unlikely(!cttype)) + return ERR_PTR(-ENOMEM); + + cttype->desc = *desc; + idr_init(&cttype->mod_idr); + init_rwsem(&cttype->mod_lock); + + err = codetag_module_init(cttype, NULL); + if (unlikely(err)) { + kfree(cttype); + return ERR_PTR(err); + } + + mutex_lock(&codetag_lock); + list_add_tail(&cttype->link, &codetag_types); + mutex_unlock(&codetag_lock); + + return cttype; +} diff --git a/lib/cpumask.c b/lib/cpumask.c index e77ee9d46f71..57274ba8b6d9 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -83,10 +83,7 @@ EXPORT_SYMBOL(alloc_cpumask_var_node); */ void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask) { - *mask = memblock_alloc(cpumask_size(), SMP_CACHE_BYTES); - if (!*mask) - panic("%s: Failed to allocate %u bytes\n", __func__, - cpumask_size()); + *mask = memblock_alloc_or_panic(cpumask_size(), SMP_CACHE_BYTES); } /** diff --git a/lib/cpumask_kunit.c b/lib/cpumask_kunit.c index a105e6369efc..6b62a6bdd50e 100644 --- a/lib/cpumask_kunit.c +++ b/lib/cpumask_kunit.c @@ -152,4 +152,5 @@ static struct kunit_suite test_cpumask_suite = { }; kunit_test_suite(test_cpumask_suite); +MODULE_DESCRIPTION("KUnit tests for cpumask"); MODULE_LICENSE("GPL"); diff --git a/lib/crc-t10dif.c b/lib/crc-t10dif.c index 1ed2ed487097..311c2ab829f1 100644 --- a/lib/crc-t10dif.c +++ b/lib/crc-t10dif.c @@ -9,123 +9,57 @@ #include <linux/types.h> #include <linux/module.h> #include <linux/crc-t10dif.h> -#include <linux/err.h> -#include <linux/init.h> -#include <crypto/hash.h> -#include <crypto/algapi.h> -#include <linux/static_key.h> -#include <linux/notifier.h> -static struct crypto_shash __rcu *crct10dif_tfm; -static DEFINE_STATIC_KEY_TRUE(crct10dif_fallback); -static DEFINE_MUTEX(crc_t10dif_mutex); -static struct work_struct crct10dif_rehash_work; - -static int crc_t10dif_notify(struct notifier_block *self, unsigned long val, void *data) -{ - struct crypto_alg *alg = data; - - if (val != CRYPTO_MSG_ALG_LOADED || - strcmp(alg->cra_name, CRC_T10DIF_STRING)) - return NOTIFY_DONE; - - schedule_work(&crct10dif_rehash_work); - return NOTIFY_OK; -} - -static void crc_t10dif_rehash(struct work_struct *work) -{ - struct crypto_shash *new, *old; - - mutex_lock(&crc_t10dif_mutex); - old = rcu_dereference_protected(crct10dif_tfm, - lockdep_is_held(&crc_t10dif_mutex)); - new = crypto_alloc_shash(CRC_T10DIF_STRING, 0, 0); - if (IS_ERR(new)) { - mutex_unlock(&crc_t10dif_mutex); - return; - } - rcu_assign_pointer(crct10dif_tfm, new); - mutex_unlock(&crc_t10dif_mutex); - - if (old) { - synchronize_rcu(); - crypto_free_shash(old); - } else { - static_branch_disable(&crct10dif_fallback); - } -} - -static struct notifier_block crc_t10dif_nb = { - .notifier_call = crc_t10dif_notify, +/* + * Table generated using the following polynomial: + * x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x + 1 + * gt: 0x8bb7 + */ +static const u16 t10_dif_crc_table[256] = { + 0x0000, 0x8BB7, 0x9CD9, 0x176E, 0xB205, 0x39B2, 0x2EDC, 0xA56B, + 0xEFBD, 0x640A, 0x7364, 0xF8D3, 0x5DB8, 0xD60F, 0xC161, 0x4AD6, + 0x54CD, 0xDF7A, 0xC814, 0x43A3, 0xE6C8, 0x6D7F, 0x7A11, 0xF1A6, + 0xBB70, 0x30C7, 0x27A9, 0xAC1E, 0x0975, 0x82C2, 0x95AC, 0x1E1B, + 0xA99A, 0x222D, 0x3543, 0xBEF4, 0x1B9F, 0x9028, 0x8746, 0x0CF1, + 0x4627, 0xCD90, 0xDAFE, 0x5149, 0xF422, 0x7F95, 0x68FB, 0xE34C, + 0xFD57, 0x76E0, 0x618E, 0xEA39, 0x4F52, 0xC4E5, 0xD38B, 0x583C, + 0x12EA, 0x995D, 0x8E33, 0x0584, 0xA0EF, 0x2B58, 0x3C36, 0xB781, + 0xD883, 0x5334, 0x445A, 0xCFED, 0x6A86, 0xE131, 0xF65F, 0x7DE8, + 0x373E, 0xBC89, 0xABE7, 0x2050, 0x853B, 0x0E8C, 0x19E2, 0x9255, + 0x8C4E, 0x07F9, 0x1097, 0x9B20, 0x3E4B, 0xB5FC, 0xA292, 0x2925, + 0x63F3, 0xE844, 0xFF2A, 0x749D, 0xD1F6, 0x5A41, 0x4D2F, 0xC698, + 0x7119, 0xFAAE, 0xEDC0, 0x6677, 0xC31C, 0x48AB, 0x5FC5, 0xD472, + 0x9EA4, 0x1513, 0x027D, 0x89CA, 0x2CA1, 0xA716, 0xB078, 0x3BCF, + 0x25D4, 0xAE63, 0xB90D, 0x32BA, 0x97D1, 0x1C66, 0x0B08, 0x80BF, + 0xCA69, 0x41DE, 0x56B0, 0xDD07, 0x786C, 0xF3DB, 0xE4B5, 0x6F02, + 0x3AB1, 0xB106, 0xA668, 0x2DDF, 0x88B4, 0x0303, 0x146D, 0x9FDA, + 0xD50C, 0x5EBB, 0x49D5, 0xC262, 0x6709, 0xECBE, 0xFBD0, 0x7067, + 0x6E7C, 0xE5CB, 0xF2A5, 0x7912, 0xDC79, 0x57CE, 0x40A0, 0xCB17, + 0x81C1, 0x0A76, 0x1D18, 0x96AF, 0x33C4, 0xB873, 0xAF1D, 0x24AA, + 0x932B, 0x189C, 0x0FF2, 0x8445, 0x212E, 0xAA99, 0xBDF7, 0x3640, + 0x7C96, 0xF721, 0xE04F, 0x6BF8, 0xCE93, 0x4524, 0x524A, 0xD9FD, + 0xC7E6, 0x4C51, 0x5B3F, 0xD088, 0x75E3, 0xFE54, 0xE93A, 0x628D, + 0x285B, 0xA3EC, 0xB482, 0x3F35, 0x9A5E, 0x11E9, 0x0687, 0x8D30, + 0xE232, 0x6985, 0x7EEB, 0xF55C, 0x5037, 0xDB80, 0xCCEE, 0x4759, + 0x0D8F, 0x8638, 0x9156, 0x1AE1, 0xBF8A, 0x343D, 0x2353, 0xA8E4, + 0xB6FF, 0x3D48, 0x2A26, 0xA191, 0x04FA, 0x8F4D, 0x9823, 0x1394, + 0x5942, 0xD2F5, 0xC59B, 0x4E2C, 0xEB47, 0x60F0, 0x779E, 0xFC29, + 0x4BA8, 0xC01F, 0xD771, 0x5CC6, 0xF9AD, 0x721A, 0x6574, 0xEEC3, + 0xA415, 0x2FA2, 0x38CC, 0xB37B, 0x1610, 0x9DA7, 0x8AC9, 0x017E, + 0x1F65, 0x94D2, 0x83BC, 0x080B, 0xAD60, 0x26D7, 0x31B9, 0xBA0E, + 0xF0D8, 0x7B6F, 0x6C01, 0xE7B6, 0x42DD, 0xC96A, 0xDE04, 0x55B3 }; -__u16 crc_t10dif_update(__u16 crc, const unsigned char *buffer, size_t len) -{ - struct { - struct shash_desc shash; - __u16 crc; - } desc; - int err; - - if (static_branch_unlikely(&crct10dif_fallback)) - return crc_t10dif_generic(crc, buffer, len); - - rcu_read_lock(); - desc.shash.tfm = rcu_dereference(crct10dif_tfm); - desc.crc = crc; - err = crypto_shash_update(&desc.shash, buffer, len); - rcu_read_unlock(); - - BUG_ON(err); - - return desc.crc; -} -EXPORT_SYMBOL(crc_t10dif_update); - -__u16 crc_t10dif(const unsigned char *buffer, size_t len) -{ - return crc_t10dif_update(0, buffer, len); -} -EXPORT_SYMBOL(crc_t10dif); - -static int __init crc_t10dif_mod_init(void) -{ - INIT_WORK(&crct10dif_rehash_work, crc_t10dif_rehash); - crypto_register_notifier(&crc_t10dif_nb); - crc_t10dif_rehash(&crct10dif_rehash_work); - return 0; -} - -static void __exit crc_t10dif_mod_fini(void) -{ - crypto_unregister_notifier(&crc_t10dif_nb); - cancel_work_sync(&crct10dif_rehash_work); - crypto_free_shash(rcu_dereference_protected(crct10dif_tfm, 1)); -} - -module_init(crc_t10dif_mod_init); -module_exit(crc_t10dif_mod_fini); - -static int crc_t10dif_transform_show(char *buffer, const struct kernel_param *kp) +u16 crc_t10dif_generic(u16 crc, const u8 *p, size_t len) { - struct crypto_shash *tfm; - int len; + size_t i; - if (static_branch_unlikely(&crct10dif_fallback)) - return sprintf(buffer, "fallback\n"); + for (i = 0; i < len; i++) + crc = (crc << 8) ^ t10_dif_crc_table[(crc >> 8) ^ p[i]]; - rcu_read_lock(); - tfm = rcu_dereference(crct10dif_tfm); - len = snprintf(buffer, PAGE_SIZE, "%s\n", - crypto_shash_driver_name(tfm)); - rcu_read_unlock(); - - return len; + return crc; } +EXPORT_SYMBOL(crc_t10dif_generic); -module_param_call(transform, NULL, crc_t10dif_transform_show, NULL, 0444); - -MODULE_DESCRIPTION("T10 DIF CRC calculation (library API)"); +MODULE_DESCRIPTION("T10 DIF CRC calculation"); MODULE_LICENSE("GPL"); -MODULE_SOFTDEP("pre: crct10dif"); diff --git a/lib/crc32.c b/lib/crc32.c index 5649847d0a8d..ede6131f66fc 100644 --- a/lib/crc32.c +++ b/lib/crc32.c @@ -30,20 +30,6 @@ #include <linux/crc32poly.h> #include <linux/module.h> #include <linux/types.h> -#include <linux/sched.h> -#include "crc32defs.h" - -#if CRC_LE_BITS > 8 -# define tole(x) ((__force u32) cpu_to_le32(x)) -#else -# define tole(x) (x) -#endif - -#if CRC_BE_BITS > 8 -# define tobe(x) ((__force u32) cpu_to_be32(x)) -#else -# define tobe(x) (x) -#endif #include "crc32table.h" @@ -51,162 +37,21 @@ MODULE_AUTHOR("Matt Domsch <Matt_Domsch@dell.com>"); MODULE_DESCRIPTION("Various CRC32 calculations"); MODULE_LICENSE("GPL"); -#if CRC_LE_BITS > 8 || CRC_BE_BITS > 8 - -/* implements slicing-by-4 or slicing-by-8 algorithm */ -static inline u32 __pure -crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256]) +u32 __pure crc32_le_base(u32 crc, const u8 *p, size_t len) { -# ifdef __LITTLE_ENDIAN -# define DO_CRC(x) crc = t0[(crc ^ (x)) & 255] ^ (crc >> 8) -# define DO_CRC4 (t3[(q) & 255] ^ t2[(q >> 8) & 255] ^ \ - t1[(q >> 16) & 255] ^ t0[(q >> 24) & 255]) -# define DO_CRC8 (t7[(q) & 255] ^ t6[(q >> 8) & 255] ^ \ - t5[(q >> 16) & 255] ^ t4[(q >> 24) & 255]) -# else -# define DO_CRC(x) crc = t0[((crc >> 24) ^ (x)) & 255] ^ (crc << 8) -# define DO_CRC4 (t0[(q) & 255] ^ t1[(q >> 8) & 255] ^ \ - t2[(q >> 16) & 255] ^ t3[(q >> 24) & 255]) -# define DO_CRC8 (t4[(q) & 255] ^ t5[(q >> 8) & 255] ^ \ - t6[(q >> 16) & 255] ^ t7[(q >> 24) & 255]) -# endif - const u32 *b; - size_t rem_len; -# ifdef CONFIG_X86 - size_t i; -# endif - const u32 *t0=tab[0], *t1=tab[1], *t2=tab[2], *t3=tab[3]; -# if CRC_LE_BITS != 32 - const u32 *t4 = tab[4], *t5 = tab[5], *t6 = tab[6], *t7 = tab[7]; -# endif - u32 q; - - /* Align it */ - if (unlikely((long)buf & 3 && len)) { - do { - DO_CRC(*buf++); - } while ((--len) && ((long)buf)&3); - } - -# if CRC_LE_BITS == 32 - rem_len = len & 3; - len = len >> 2; -# else - rem_len = len & 7; - len = len >> 3; -# endif - - b = (const u32 *)buf; -# ifdef CONFIG_X86 - --b; - for (i = 0; i < len; i++) { -# else - for (--b; len; --len) { -# endif - q = crc ^ *++b; /* use pre increment for speed */ -# if CRC_LE_BITS == 32 - crc = DO_CRC4; -# else - crc = DO_CRC8; - q = *++b; - crc ^= DO_CRC4; -# endif - } - len = rem_len; - /* And the last few bytes */ - if (len) { - u8 *p = (u8 *)(b + 1) - 1; -# ifdef CONFIG_X86 - for (i = 0; i < len; i++) - DO_CRC(*++p); /* use pre increment for speed */ -# else - do { - DO_CRC(*++p); /* use pre increment for speed */ - } while (--len); -# endif - } + while (len--) + crc = (crc >> 8) ^ crc32table_le[(crc & 255) ^ *p++]; return crc; -#undef DO_CRC -#undef DO_CRC4 -#undef DO_CRC8 } -#endif - +EXPORT_SYMBOL(crc32_le_base); -/** - * crc32_le_generic() - Calculate bitwise little-endian Ethernet AUTODIN II - * CRC32/CRC32C - * @crc: seed value for computation. ~0 for Ethernet, sometimes 0 for other - * uses, or the previous crc32/crc32c value if computing incrementally. - * @p: pointer to buffer over which CRC32/CRC32C is run - * @len: length of buffer @p - * @tab: little-endian Ethernet table - * @polynomial: CRC32/CRC32c LE polynomial - */ -static inline u32 __pure crc32_le_generic(u32 crc, unsigned char const *p, - size_t len, const u32 (*tab)[256], - u32 polynomial) +u32 __pure crc32c_le_base(u32 crc, const u8 *p, size_t len) { -#if CRC_LE_BITS == 1 - int i; - while (len--) { - crc ^= *p++; - for (i = 0; i < 8; i++) - crc = (crc >> 1) ^ ((crc & 1) ? polynomial : 0); - } -# elif CRC_LE_BITS == 2 - while (len--) { - crc ^= *p++; - crc = (crc >> 2) ^ tab[0][crc & 3]; - crc = (crc >> 2) ^ tab[0][crc & 3]; - crc = (crc >> 2) ^ tab[0][crc & 3]; - crc = (crc >> 2) ^ tab[0][crc & 3]; - } -# elif CRC_LE_BITS == 4 - while (len--) { - crc ^= *p++; - crc = (crc >> 4) ^ tab[0][crc & 15]; - crc = (crc >> 4) ^ tab[0][crc & 15]; - } -# elif CRC_LE_BITS == 8 - /* aka Sarwate algorithm */ - while (len--) { - crc ^= *p++; - crc = (crc >> 8) ^ tab[0][crc & 255]; - } -# else - crc = (__force u32) __cpu_to_le32(crc); - crc = crc32_body(crc, p, len, tab); - crc = __le32_to_cpu((__force __le32)crc); -#endif + while (len--) + crc = (crc >> 8) ^ crc32ctable_le[(crc & 255) ^ *p++]; return crc; } - -#if CRC_LE_BITS == 1 -u32 __pure __weak crc32_le(u32 crc, unsigned char const *p, size_t len) -{ - return crc32_le_generic(crc, p, len, NULL, CRC32_POLY_LE); -} -u32 __pure __weak __crc32c_le(u32 crc, unsigned char const *p, size_t len) -{ - return crc32_le_generic(crc, p, len, NULL, CRC32C_POLY_LE); -} -#else -u32 __pure __weak crc32_le(u32 crc, unsigned char const *p, size_t len) -{ - return crc32_le_generic(crc, p, len, crc32table_le, CRC32_POLY_LE); -} -u32 __pure __weak __crc32c_le(u32 crc, unsigned char const *p, size_t len) -{ - return crc32_le_generic(crc, p, len, crc32ctable_le, CRC32C_POLY_LE); -} -#endif -EXPORT_SYMBOL(crc32_le); -EXPORT_SYMBOL(__crc32c_le); - -u32 __pure crc32_le_base(u32, unsigned char const *, size_t) __alias(crc32_le); -u32 __pure __crc32c_le_base(u32, unsigned char const *, size_t) __alias(__crc32c_le); -u32 __pure crc32_be_base(u32, unsigned char const *, size_t) __alias(crc32_be); +EXPORT_SYMBOL(crc32c_le_base); /* * This multiplies the polynomials x and y modulo the given modulus. @@ -281,64 +126,10 @@ u32 __attribute_const__ __crc32c_le_shift(u32 crc, size_t len) EXPORT_SYMBOL(crc32_le_shift); EXPORT_SYMBOL(__crc32c_le_shift); -/** - * crc32_be_generic() - Calculate bitwise big-endian Ethernet AUTODIN II CRC32 - * @crc: seed value for computation. ~0 for Ethernet, sometimes 0 for - * other uses, or the previous crc32 value if computing incrementally. - * @p: pointer to buffer over which CRC32 is run - * @len: length of buffer @p - * @tab: big-endian Ethernet table - * @polynomial: CRC32 BE polynomial - */ -static inline u32 __pure crc32_be_generic(u32 crc, unsigned char const *p, - size_t len, const u32 (*tab)[256], - u32 polynomial) +u32 __pure crc32_be_base(u32 crc, const u8 *p, size_t len) { -#if CRC_BE_BITS == 1 - int i; - while (len--) { - crc ^= *p++ << 24; - for (i = 0; i < 8; i++) - crc = - (crc << 1) ^ ((crc & 0x80000000) ? polynomial : - 0); - } -# elif CRC_BE_BITS == 2 - while (len--) { - crc ^= *p++ << 24; - crc = (crc << 2) ^ tab[0][crc >> 30]; - crc = (crc << 2) ^ tab[0][crc >> 30]; - crc = (crc << 2) ^ tab[0][crc >> 30]; - crc = (crc << 2) ^ tab[0][crc >> 30]; - } -# elif CRC_BE_BITS == 4 - while (len--) { - crc ^= *p++ << 24; - crc = (crc << 4) ^ tab[0][crc >> 28]; - crc = (crc << 4) ^ tab[0][crc >> 28]; - } -# elif CRC_BE_BITS == 8 - while (len--) { - crc ^= *p++ << 24; - crc = (crc << 8) ^ tab[0][crc >> 24]; - } -# else - crc = (__force u32) __cpu_to_be32(crc); - crc = crc32_body(crc, p, len, tab); - crc = __be32_to_cpu((__force __be32)crc); -# endif + while (len--) + crc = (crc << 8) ^ crc32table_be[(crc >> 24) ^ *p++]; return crc; } - -#if CRC_BE_BITS == 1 -u32 __pure __weak crc32_be(u32 crc, unsigned char const *p, size_t len) -{ - return crc32_be_generic(crc, p, len, NULL, CRC32_POLY_BE); -} -#else -u32 __pure __weak crc32_be(u32 crc, unsigned char const *p, size_t len) -{ - return crc32_be_generic(crc, p, len, crc32table_be, CRC32_POLY_BE); -} -#endif -EXPORT_SYMBOL(crc32_be); +EXPORT_SYMBOL(crc32_be_base); diff --git a/lib/crc32defs.h b/lib/crc32defs.h deleted file mode 100644 index 0c8fb5923e7e..000000000000 --- a/lib/crc32defs.h +++ /dev/null @@ -1,59 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* Try to choose an implementation variant via Kconfig */ -#ifdef CONFIG_CRC32_SLICEBY8 -# define CRC_LE_BITS 64 -# define CRC_BE_BITS 64 -#endif -#ifdef CONFIG_CRC32_SLICEBY4 -# define CRC_LE_BITS 32 -# define CRC_BE_BITS 32 -#endif -#ifdef CONFIG_CRC32_SARWATE -# define CRC_LE_BITS 8 -# define CRC_BE_BITS 8 -#endif -#ifdef CONFIG_CRC32_BIT -# define CRC_LE_BITS 1 -# define CRC_BE_BITS 1 -#endif - -/* - * How many bits at a time to use. Valid values are 1, 2, 4, 8, 32 and 64. - * For less performance-sensitive, use 4 or 8 to save table size. - * For larger systems choose same as CPU architecture as default. - * This works well on X86_64, SPARC64 systems. This may require some - * elaboration after experiments with other architectures. - */ -#ifndef CRC_LE_BITS -# ifdef CONFIG_64BIT -# define CRC_LE_BITS 64 -# else -# define CRC_LE_BITS 32 -# endif -#endif -#ifndef CRC_BE_BITS -# ifdef CONFIG_64BIT -# define CRC_BE_BITS 64 -# else -# define CRC_BE_BITS 32 -# endif -#endif - -/* - * Little-endian CRC computation. Used with serial bit streams sent - * lsbit-first. Be sure to use cpu_to_le32() to append the computed CRC. - */ -#if CRC_LE_BITS > 64 || CRC_LE_BITS < 1 || CRC_LE_BITS == 16 || \ - CRC_LE_BITS & CRC_LE_BITS-1 -# error "CRC_LE_BITS must be one of {1, 2, 4, 8, 32, 64}" -#endif - -/* - * Big-endian CRC computation. Used with serial bit streams sent - * msbit-first. Be sure to use cpu_to_be32() to append the computed CRC. - */ -#if CRC_BE_BITS > 64 || CRC_BE_BITS < 1 || CRC_BE_BITS == 16 || \ - CRC_BE_BITS & CRC_BE_BITS-1 -# error "CRC_BE_BITS must be one of {1, 2, 4, 8, 32, 64}" -#endif diff --git a/lib/crc32test.c b/lib/crc32test.c deleted file mode 100644 index 9b4af79412c4..000000000000 --- a/lib/crc32test.c +++ /dev/null @@ -1,852 +0,0 @@ -/* - * Aug 8, 2011 Bob Pearson with help from Joakim Tjernlund and George Spelvin - * cleaned up code to current version of sparse and added the slicing-by-8 - * algorithm to the closely similar existing slicing-by-4 algorithm. - * - * Oct 15, 2000 Matt Domsch <Matt_Domsch@dell.com> - * Nicer crc32 functions/docs submitted by linux@horizon.com. Thanks! - * Code was from the public domain, copyright abandoned. Code was - * subsequently included in the kernel, thus was re-licensed under the - * GNU GPL v2. - * - * Oct 12, 2000 Matt Domsch <Matt_Domsch@dell.com> - * Same crc32 function was used in 5 other places in the kernel. - * I made one version, and deleted the others. - * There are various incantations of crc32(). Some use a seed of 0 or ~0. - * Some xor at the end with ~0. The generic crc32() function takes - * seed as an argument, and doesn't xor at the end. Then individual - * users can do whatever they need. - * drivers/net/smc9194.c uses seed ~0, doesn't xor with ~0. - * fs/jffs2 uses seed 0, doesn't xor with ~0. - * fs/partitions/efi.c uses seed ~0, xor's with ~0. - * - * This source code is licensed under the GNU General Public License, - * Version 2. See the file COPYING for more details. - */ - -#include <linux/crc32.h> -#include <linux/module.h> -#include <linux/sched.h> - -#include "crc32defs.h" - -/* 4096 random bytes */ -static u8 const __aligned(8) test_buf[] __initconst = -{ - 0x5b, 0x85, 0x21, 0xcb, 0x09, 0x68, 0x7d, 0x30, - 0xc7, 0x69, 0xd7, 0x30, 0x92, 0xde, 0x59, 0xe4, - 0xc9, 0x6e, 0x8b, 0xdb, 0x98, 0x6b, 0xaa, 0x60, - 0xa8, 0xb5, 0xbc, 0x6c, 0xa9, 0xb1, 0x5b, 0x2c, - 0xea, 0xb4, 0x92, 0x6a, 0x3f, 0x79, 0x91, 0xe4, - 0xe9, 0x70, 0x51, 0x8c, 0x7f, 0x95, 0x6f, 0x1a, - 0x56, 0xa1, 0x5c, 0x27, 0x03, 0x67, 0x9f, 0x3a, - 0xe2, 0x31, 0x11, 0x29, 0x6b, 0x98, 0xfc, 0xc4, - 0x53, 0x24, 0xc5, 0x8b, 0xce, 0x47, 0xb2, 0xb9, - 0x32, 0xcb, 0xc1, 0xd0, 0x03, 0x57, 0x4e, 0xd4, - 0xe9, 0x3c, 0xa1, 0x63, 0xcf, 0x12, 0x0e, 0xca, - 0xe1, 0x13, 0xd1, 0x93, 0xa6, 0x88, 0x5c, 0x61, - 0x5b, 0xbb, 0xf0, 0x19, 0x46, 0xb4, 0xcf, 0x9e, - 0xb6, 0x6b, 0x4c, 0x3a, 0xcf, 0x60, 0xf9, 0x7a, - 0x8d, 0x07, 0x63, 0xdb, 0x40, 0xe9, 0x0b, 0x6f, - 0xad, 0x97, 0xf1, 0xed, 0xd0, 0x1e, 0x26, 0xfd, - 0xbf, 0xb7, 0xc8, 0x04, 0x94, 0xf8, 0x8b, 0x8c, - 0xf1, 0xab, 0x7a, 0xd4, 0xdd, 0xf3, 0xe8, 0x88, - 0xc3, 0xed, 0x17, 0x8a, 0x9b, 0x40, 0x0d, 0x53, - 0x62, 0x12, 0x03, 0x5f, 0x1b, 0x35, 0x32, 0x1f, - 0xb4, 0x7b, 0x93, 0x78, 0x0d, 0xdb, 0xce, 0xa4, - 0xc0, 0x47, 0xd5, 0xbf, 0x68, 0xe8, 0x5d, 0x74, - 0x8f, 0x8e, 0x75, 0x1c, 0xb2, 0x4f, 0x9a, 0x60, - 0xd1, 0xbe, 0x10, 0xf4, 0x5c, 0xa1, 0x53, 0x09, - 0xa5, 0xe0, 0x09, 0x54, 0x85, 0x5c, 0xdc, 0x07, - 0xe7, 0x21, 0x69, 0x7b, 0x8a, 0xfd, 0x90, 0xf1, - 0x22, 0xd0, 0xb4, 0x36, 0x28, 0xe6, 0xb8, 0x0f, - 0x39, 0xde, 0xc8, 0xf3, 0x86, 0x60, 0x34, 0xd2, - 0x5e, 0xdf, 0xfd, 0xcf, 0x0f, 0xa9, 0x65, 0xf0, - 0xd5, 0x4d, 0x96, 0x40, 0xe3, 0xdf, 0x3f, 0x95, - 0x5a, 0x39, 0x19, 0x93, 0xf4, 0x75, 0xce, 0x22, - 0x00, 0x1c, 0x93, 0xe2, 0x03, 0x66, 0xf4, 0x93, - 0x73, 0x86, 0x81, 0x8e, 0x29, 0x44, 0x48, 0x86, - 0x61, 0x7c, 0x48, 0xa3, 0x43, 0xd2, 0x9c, 0x8d, - 0xd4, 0x95, 0xdd, 0xe1, 0x22, 0x89, 0x3a, 0x40, - 0x4c, 0x1b, 0x8a, 0x04, 0xa8, 0x09, 0x69, 0x8b, - 0xea, 0xc6, 0x55, 0x8e, 0x57, 0xe6, 0x64, 0x35, - 0xf0, 0xc7, 0x16, 0x9f, 0x5d, 0x5e, 0x86, 0x40, - 0x46, 0xbb, 0xe5, 0x45, 0x88, 0xfe, 0xc9, 0x63, - 0x15, 0xfb, 0xf5, 0xbd, 0x71, 0x61, 0xeb, 0x7b, - 0x78, 0x70, 0x07, 0x31, 0x03, 0x9f, 0xb2, 0xc8, - 0xa7, 0xab, 0x47, 0xfd, 0xdf, 0xa0, 0x78, 0x72, - 0xa4, 0x2a, 0xe4, 0xb6, 0xba, 0xc0, 0x1e, 0x86, - 0x71, 0xe6, 0x3d, 0x18, 0x37, 0x70, 0xe6, 0xff, - 0xe0, 0xbc, 0x0b, 0x22, 0xa0, 0x1f, 0xd3, 0xed, - 0xa2, 0x55, 0x39, 0xab, 0xa8, 0x13, 0x73, 0x7c, - 0x3f, 0xb2, 0xd6, 0x19, 0xac, 0xff, 0x99, 0xed, - 0xe8, 0xe6, 0xa6, 0x22, 0xe3, 0x9c, 0xf1, 0x30, - 0xdc, 0x01, 0x0a, 0x56, 0xfa, 0xe4, 0xc9, 0x99, - 0xdd, 0xa8, 0xd8, 0xda, 0x35, 0x51, 0x73, 0xb4, - 0x40, 0x86, 0x85, 0xdb, 0x5c, 0xd5, 0x85, 0x80, - 0x14, 0x9c, 0xfd, 0x98, 0xa9, 0x82, 0xc5, 0x37, - 0xff, 0x32, 0x5d, 0xd0, 0x0b, 0xfa, 0xdc, 0x04, - 0x5e, 0x09, 0xd2, 0xca, 0x17, 0x4b, 0x1a, 0x8e, - 0x15, 0xe1, 0xcc, 0x4e, 0x52, 0x88, 0x35, 0xbd, - 0x48, 0xfe, 0x15, 0xa0, 0x91, 0xfd, 0x7e, 0x6c, - 0x0e, 0x5d, 0x79, 0x1b, 0x81, 0x79, 0xd2, 0x09, - 0x34, 0x70, 0x3d, 0x81, 0xec, 0xf6, 0x24, 0xbb, - 0xfb, 0xf1, 0x7b, 0xdf, 0x54, 0xea, 0x80, 0x9b, - 0xc7, 0x99, 0x9e, 0xbd, 0x16, 0x78, 0x12, 0x53, - 0x5e, 0x01, 0xa7, 0x4e, 0xbd, 0x67, 0xe1, 0x9b, - 0x4c, 0x0e, 0x61, 0x45, 0x97, 0xd2, 0xf0, 0x0f, - 0xfe, 0x15, 0x08, 0xb7, 0x11, 0x4c, 0xe7, 0xff, - 0x81, 0x53, 0xff, 0x91, 0x25, 0x38, 0x7e, 0x40, - 0x94, 0xe5, 0xe0, 0xad, 0xe6, 0xd9, 0x79, 0xb6, - 0x92, 0xc9, 0xfc, 0xde, 0xc3, 0x1a, 0x23, 0xbb, - 0xdd, 0xc8, 0x51, 0x0c, 0x3a, 0x72, 0xfa, 0x73, - 0x6f, 0xb7, 0xee, 0x61, 0x39, 0x03, 0x01, 0x3f, - 0x7f, 0x94, 0x2e, 0x2e, 0xba, 0x3a, 0xbb, 0xb4, - 0xfa, 0x6a, 0x17, 0xfe, 0xea, 0xef, 0x5e, 0x66, - 0x97, 0x3f, 0x32, 0x3d, 0xd7, 0x3e, 0xb1, 0xf1, - 0x6c, 0x14, 0x4c, 0xfd, 0x37, 0xd3, 0x38, 0x80, - 0xfb, 0xde, 0xa6, 0x24, 0x1e, 0xc8, 0xca, 0x7f, - 0x3a, 0x93, 0xd8, 0x8b, 0x18, 0x13, 0xb2, 0xe5, - 0xe4, 0x93, 0x05, 0x53, 0x4f, 0x84, 0x66, 0xa7, - 0x58, 0x5c, 0x7b, 0x86, 0x52, 0x6d, 0x0d, 0xce, - 0xa4, 0x30, 0x7d, 0xb6, 0x18, 0x9f, 0xeb, 0xff, - 0x22, 0xbb, 0x72, 0x29, 0xb9, 0x44, 0x0b, 0x48, - 0x1e, 0x84, 0x71, 0x81, 0xe3, 0x6d, 0x73, 0x26, - 0x92, 0xb4, 0x4d, 0x2a, 0x29, 0xb8, 0x1f, 0x72, - 0xed, 0xd0, 0xe1, 0x64, 0x77, 0xea, 0x8e, 0x88, - 0x0f, 0xef, 0x3f, 0xb1, 0x3b, 0xad, 0xf9, 0xc9, - 0x8b, 0xd0, 0xac, 0xc6, 0xcc, 0xa9, 0x40, 0xcc, - 0x76, 0xf6, 0x3b, 0x53, 0xb5, 0x88, 0xcb, 0xc8, - 0x37, 0xf1, 0xa2, 0xba, 0x23, 0x15, 0x99, 0x09, - 0xcc, 0xe7, 0x7a, 0x3b, 0x37, 0xf7, 0x58, 0xc8, - 0x46, 0x8c, 0x2b, 0x2f, 0x4e, 0x0e, 0xa6, 0x5c, - 0xea, 0x85, 0x55, 0xba, 0x02, 0x0e, 0x0e, 0x48, - 0xbc, 0xe1, 0xb1, 0x01, 0x35, 0x79, 0x13, 0x3d, - 0x1b, 0xc0, 0x53, 0x68, 0x11, 0xe7, 0x95, 0x0f, - 0x9d, 0x3f, 0x4c, 0x47, 0x7b, 0x4d, 0x1c, 0xae, - 0x50, 0x9b, 0xcb, 0xdd, 0x05, 0x8d, 0x9a, 0x97, - 0xfd, 0x8c, 0xef, 0x0c, 0x1d, 0x67, 0x73, 0xa8, - 0x28, 0x36, 0xd5, 0xb6, 0x92, 0x33, 0x40, 0x75, - 0x0b, 0x51, 0xc3, 0x64, 0xba, 0x1d, 0xc2, 0xcc, - 0xee, 0x7d, 0x54, 0x0f, 0x27, 0x69, 0xa7, 0x27, - 0x63, 0x30, 0x29, 0xd9, 0xc8, 0x84, 0xd8, 0xdf, - 0x9f, 0x68, 0x8d, 0x04, 0xca, 0xa6, 0xc5, 0xc7, - 0x7a, 0x5c, 0xc8, 0xd1, 0xcb, 0x4a, 0xec, 0xd0, - 0xd8, 0x20, 0x69, 0xc5, 0x17, 0xcd, 0x78, 0xc8, - 0x75, 0x23, 0x30, 0x69, 0xc9, 0xd4, 0xea, 0x5c, - 0x4f, 0x6b, 0x86, 0x3f, 0x8b, 0xfe, 0xee, 0x44, - 0xc9, 0x7c, 0xb7, 0xdd, 0x3e, 0xe5, 0xec, 0x54, - 0x03, 0x3e, 0xaa, 0x82, 0xc6, 0xdf, 0xb2, 0x38, - 0x0e, 0x5d, 0xb3, 0x88, 0xd9, 0xd3, 0x69, 0x5f, - 0x8f, 0x70, 0x8a, 0x7e, 0x11, 0xd9, 0x1e, 0x7b, - 0x38, 0xf1, 0x42, 0x1a, 0xc0, 0x35, 0xf5, 0xc7, - 0x36, 0x85, 0xf5, 0xf7, 0xb8, 0x7e, 0xc7, 0xef, - 0x18, 0xf1, 0x63, 0xd6, 0x7a, 0xc6, 0xc9, 0x0e, - 0x4d, 0x69, 0x4f, 0x84, 0xef, 0x26, 0x41, 0x0c, - 0xec, 0xc7, 0xe0, 0x7e, 0x3c, 0x67, 0x01, 0x4c, - 0x62, 0x1a, 0x20, 0x6f, 0xee, 0x47, 0x4d, 0xc0, - 0x99, 0x13, 0x8d, 0x91, 0x4a, 0x26, 0xd4, 0x37, - 0x28, 0x90, 0x58, 0x75, 0x66, 0x2b, 0x0a, 0xdf, - 0xda, 0xee, 0x92, 0x25, 0x90, 0x62, 0x39, 0x9e, - 0x44, 0x98, 0xad, 0xc1, 0x88, 0xed, 0xe4, 0xb4, - 0xaf, 0xf5, 0x8c, 0x9b, 0x48, 0x4d, 0x56, 0x60, - 0x97, 0x0f, 0x61, 0x59, 0x9e, 0xa6, 0x27, 0xfe, - 0xc1, 0x91, 0x15, 0x38, 0xb8, 0x0f, 0xae, 0x61, - 0x7d, 0x26, 0x13, 0x5a, 0x73, 0xff, 0x1c, 0xa3, - 0x61, 0x04, 0x58, 0x48, 0x55, 0x44, 0x11, 0xfe, - 0x15, 0xca, 0xc3, 0xbd, 0xca, 0xc5, 0xb4, 0x40, - 0x5d, 0x1b, 0x7f, 0x39, 0xb5, 0x9c, 0x35, 0xec, - 0x61, 0x15, 0x32, 0x32, 0xb8, 0x4e, 0x40, 0x9f, - 0x17, 0x1f, 0x0a, 0x4d, 0xa9, 0x91, 0xef, 0xb7, - 0xb0, 0xeb, 0xc2, 0x83, 0x9a, 0x6c, 0xd2, 0x79, - 0x43, 0x78, 0x5e, 0x2f, 0xe5, 0xdd, 0x1a, 0x3c, - 0x45, 0xab, 0x29, 0x40, 0x3a, 0x37, 0x5b, 0x6f, - 0xd7, 0xfc, 0x48, 0x64, 0x3c, 0x49, 0xfb, 0x21, - 0xbe, 0xc3, 0xff, 0x07, 0xfb, 0x17, 0xe9, 0xc9, - 0x0c, 0x4c, 0x5c, 0x15, 0x9e, 0x8e, 0x22, 0x30, - 0x0a, 0xde, 0x48, 0x7f, 0xdb, 0x0d, 0xd1, 0x2b, - 0x87, 0x38, 0x9e, 0xcc, 0x5a, 0x01, 0x16, 0xee, - 0x75, 0x49, 0x0d, 0x30, 0x01, 0x34, 0x6a, 0xb6, - 0x9a, 0x5a, 0x2a, 0xec, 0xbb, 0x48, 0xac, 0xd3, - 0x77, 0x83, 0xd8, 0x08, 0x86, 0x4f, 0x48, 0x09, - 0x29, 0x41, 0x79, 0xa1, 0x03, 0x12, 0xc4, 0xcd, - 0x90, 0x55, 0x47, 0x66, 0x74, 0x9a, 0xcc, 0x4f, - 0x35, 0x8c, 0xd6, 0x98, 0xef, 0xeb, 0x45, 0xb9, - 0x9a, 0x26, 0x2f, 0x39, 0xa5, 0x70, 0x6d, 0xfc, - 0xb4, 0x51, 0xee, 0xf4, 0x9c, 0xe7, 0x38, 0x59, - 0xad, 0xf4, 0xbc, 0x46, 0xff, 0x46, 0x8e, 0x60, - 0x9c, 0xa3, 0x60, 0x1d, 0xf8, 0x26, 0x72, 0xf5, - 0x72, 0x9d, 0x68, 0x80, 0x04, 0xf6, 0x0b, 0xa1, - 0x0a, 0xd5, 0xa7, 0x82, 0x3a, 0x3e, 0x47, 0xa8, - 0x5a, 0xde, 0x59, 0x4f, 0x7b, 0x07, 0xb3, 0xe9, - 0x24, 0x19, 0x3d, 0x34, 0x05, 0xec, 0xf1, 0xab, - 0x6e, 0x64, 0x8f, 0xd3, 0xe6, 0x41, 0x86, 0x80, - 0x70, 0xe3, 0x8d, 0x60, 0x9c, 0x34, 0x25, 0x01, - 0x07, 0x4d, 0x19, 0x41, 0x4e, 0x3d, 0x5c, 0x7e, - 0xa8, 0xf5, 0xcc, 0xd5, 0x7b, 0xe2, 0x7d, 0x3d, - 0x49, 0x86, 0x7d, 0x07, 0xb7, 0x10, 0xe3, 0x35, - 0xb8, 0x84, 0x6d, 0x76, 0xab, 0x17, 0xc6, 0x38, - 0xb4, 0xd3, 0x28, 0x57, 0xad, 0xd3, 0x88, 0x5a, - 0xda, 0xea, 0xc8, 0x94, 0xcc, 0x37, 0x19, 0xac, - 0x9c, 0x9f, 0x4b, 0x00, 0x15, 0xc0, 0xc8, 0xca, - 0x1f, 0x15, 0xaa, 0xe0, 0xdb, 0xf9, 0x2f, 0x57, - 0x1b, 0x24, 0xc7, 0x6f, 0x76, 0x29, 0xfb, 0xed, - 0x25, 0x0d, 0xc0, 0xfe, 0xbd, 0x5a, 0xbf, 0x20, - 0x08, 0x51, 0x05, 0xec, 0x71, 0xa3, 0xbf, 0xef, - 0x5e, 0x99, 0x75, 0xdb, 0x3c, 0x5f, 0x9a, 0x8c, - 0xbb, 0x19, 0x5c, 0x0e, 0x93, 0x19, 0xf8, 0x6a, - 0xbc, 0xf2, 0x12, 0x54, 0x2f, 0xcb, 0x28, 0x64, - 0x88, 0xb3, 0x92, 0x0d, 0x96, 0xd1, 0xa6, 0xe4, - 0x1f, 0xf1, 0x4d, 0xa4, 0xab, 0x1c, 0xee, 0x54, - 0xf2, 0xad, 0x29, 0x6d, 0x32, 0x37, 0xb2, 0x16, - 0x77, 0x5c, 0xdc, 0x2e, 0x54, 0xec, 0x75, 0x26, - 0xc6, 0x36, 0xd9, 0x17, 0x2c, 0xf1, 0x7a, 0xdc, - 0x4b, 0xf1, 0xe2, 0xd9, 0x95, 0xba, 0xac, 0x87, - 0xc1, 0xf3, 0x8e, 0x58, 0x08, 0xd8, 0x87, 0x60, - 0xc9, 0xee, 0x6a, 0xde, 0xa4, 0xd2, 0xfc, 0x0d, - 0xe5, 0x36, 0xc4, 0x5c, 0x52, 0xb3, 0x07, 0x54, - 0x65, 0x24, 0xc1, 0xb1, 0xd1, 0xb1, 0x53, 0x13, - 0x31, 0x79, 0x7f, 0x05, 0x76, 0xeb, 0x37, 0x59, - 0x15, 0x2b, 0xd1, 0x3f, 0xac, 0x08, 0x97, 0xeb, - 0x91, 0x98, 0xdf, 0x6c, 0x09, 0x0d, 0x04, 0x9f, - 0xdc, 0x3b, 0x0e, 0x60, 0x68, 0x47, 0x23, 0x15, - 0x16, 0xc6, 0x0b, 0x35, 0xf8, 0x77, 0xa2, 0x78, - 0x50, 0xd4, 0x64, 0x22, 0x33, 0xff, 0xfb, 0x93, - 0x71, 0x46, 0x50, 0x39, 0x1b, 0x9c, 0xea, 0x4e, - 0x8d, 0x0c, 0x37, 0xe5, 0x5c, 0x51, 0x3a, 0x31, - 0xb2, 0x85, 0x84, 0x3f, 0x41, 0xee, 0xa2, 0xc1, - 0xc6, 0x13, 0x3b, 0x54, 0x28, 0xd2, 0x18, 0x37, - 0xcc, 0x46, 0x9f, 0x6a, 0x91, 0x3d, 0x5a, 0x15, - 0x3c, 0x89, 0xa3, 0x61, 0x06, 0x7d, 0x2e, 0x78, - 0xbe, 0x7d, 0x40, 0xba, 0x2f, 0x95, 0xb1, 0x2f, - 0x87, 0x3b, 0x8a, 0xbe, 0x6a, 0xf4, 0xc2, 0x31, - 0x74, 0xee, 0x91, 0xe0, 0x23, 0xaa, 0x5d, 0x7f, - 0xdd, 0xf0, 0x44, 0x8c, 0x0b, 0x59, 0x2b, 0xfc, - 0x48, 0x3a, 0xdf, 0x07, 0x05, 0x38, 0x6c, 0xc9, - 0xeb, 0x18, 0x24, 0x68, 0x8d, 0x58, 0x98, 0xd3, - 0x31, 0xa3, 0xe4, 0x70, 0x59, 0xb1, 0x21, 0xbe, - 0x7e, 0x65, 0x7d, 0xb8, 0x04, 0xab, 0xf6, 0xe4, - 0xd7, 0xda, 0xec, 0x09, 0x8f, 0xda, 0x6d, 0x24, - 0x07, 0xcc, 0x29, 0x17, 0x05, 0x78, 0x1a, 0xc1, - 0xb1, 0xce, 0xfc, 0xaa, 0x2d, 0xe7, 0xcc, 0x85, - 0x84, 0x84, 0x03, 0x2a, 0x0c, 0x3f, 0xa9, 0xf8, - 0xfd, 0x84, 0x53, 0x59, 0x5c, 0xf0, 0xd4, 0x09, - 0xf0, 0xd2, 0x6c, 0x32, 0x03, 0xb0, 0xa0, 0x8c, - 0x52, 0xeb, 0x23, 0x91, 0x88, 0x43, 0x13, 0x46, - 0xf6, 0x1e, 0xb4, 0x1b, 0xf5, 0x8e, 0x3a, 0xb5, - 0x3d, 0x00, 0xf6, 0xe5, 0x08, 0x3d, 0x5f, 0x39, - 0xd3, 0x21, 0x69, 0xbc, 0x03, 0x22, 0x3a, 0xd2, - 0x5c, 0x84, 0xf8, 0x15, 0xc4, 0x80, 0x0b, 0xbc, - 0x29, 0x3c, 0xf3, 0x95, 0x98, 0xcd, 0x8f, 0x35, - 0xbc, 0xa5, 0x3e, 0xfc, 0xd4, 0x13, 0x9e, 0xde, - 0x4f, 0xce, 0x71, 0x9d, 0x09, 0xad, 0xf2, 0x80, - 0x6b, 0x65, 0x7f, 0x03, 0x00, 0x14, 0x7c, 0x15, - 0x85, 0x40, 0x6d, 0x70, 0xea, 0xdc, 0xb3, 0x63, - 0x35, 0x4f, 0x4d, 0xe0, 0xd9, 0xd5, 0x3c, 0x58, - 0x56, 0x23, 0x80, 0xe2, 0x36, 0xdd, 0x75, 0x1d, - 0x94, 0x11, 0x41, 0x8e, 0xe0, 0x81, 0x8e, 0xcf, - 0xe0, 0xe5, 0xf6, 0xde, 0xd1, 0xe7, 0x04, 0x12, - 0x79, 0x92, 0x2b, 0x71, 0x2a, 0x79, 0x8b, 0x7c, - 0x44, 0x79, 0x16, 0x30, 0x4e, 0xf4, 0xf6, 0x9b, - 0xb7, 0x40, 0xa3, 0x5a, 0xa7, 0x69, 0x3e, 0xc1, - 0x3a, 0x04, 0xd0, 0x88, 0xa0, 0x3b, 0xdd, 0xc6, - 0x9e, 0x7e, 0x1e, 0x1e, 0x8f, 0x44, 0xf7, 0x73, - 0x67, 0x1e, 0x1a, 0x78, 0xfa, 0x62, 0xf4, 0xa9, - 0xa8, 0xc6, 0x5b, 0xb8, 0xfa, 0x06, 0x7d, 0x5e, - 0x38, 0x1c, 0x9a, 0x39, 0xe9, 0x39, 0x98, 0x22, - 0x0b, 0xa7, 0xac, 0x0b, 0xf3, 0xbc, 0xf1, 0xeb, - 0x8c, 0x81, 0xe3, 0x48, 0x8a, 0xed, 0x42, 0xc2, - 0x38, 0xcf, 0x3e, 0xda, 0xd2, 0x89, 0x8d, 0x9c, - 0x53, 0xb5, 0x2f, 0x41, 0x01, 0x26, 0x84, 0x9c, - 0xa3, 0x56, 0xf6, 0x49, 0xc7, 0xd4, 0x9f, 0x93, - 0x1b, 0x96, 0x49, 0x5e, 0xad, 0xb3, 0x84, 0x1f, - 0x3c, 0xa4, 0xe0, 0x9b, 0xd1, 0x90, 0xbc, 0x38, - 0x6c, 0xdd, 0x95, 0x4d, 0x9d, 0xb1, 0x71, 0x57, - 0x2d, 0x34, 0xe8, 0xb8, 0x42, 0xc7, 0x99, 0x03, - 0xc7, 0x07, 0x30, 0x65, 0x91, 0x55, 0xd5, 0x90, - 0x70, 0x97, 0x37, 0x68, 0xd4, 0x11, 0xf9, 0xe8, - 0xce, 0xec, 0xdc, 0x34, 0xd5, 0xd3, 0xb7, 0xc4, - 0xb8, 0x97, 0x05, 0x92, 0xad, 0xf8, 0xe2, 0x36, - 0x64, 0x41, 0xc9, 0xc5, 0x41, 0x77, 0x52, 0xd7, - 0x2c, 0xa5, 0x24, 0x2f, 0xd9, 0x34, 0x0b, 0x47, - 0x35, 0xa7, 0x28, 0x8b, 0xc5, 0xcd, 0xe9, 0x46, - 0xac, 0x39, 0x94, 0x3c, 0x10, 0xc6, 0x29, 0x73, - 0x0e, 0x0e, 0x5d, 0xe0, 0x71, 0x03, 0x8a, 0x72, - 0x0e, 0x26, 0xb0, 0x7d, 0x84, 0xed, 0x95, 0x23, - 0x49, 0x5a, 0x45, 0x83, 0x45, 0x60, 0x11, 0x4a, - 0x46, 0x31, 0xd4, 0xd8, 0x16, 0x54, 0x98, 0x58, - 0xed, 0x6d, 0xcc, 0x5d, 0xd6, 0x50, 0x61, 0x9f, - 0x9d, 0xc5, 0x3e, 0x9d, 0x32, 0x47, 0xde, 0x96, - 0xe1, 0x5d, 0xd8, 0xf8, 0xb4, 0x69, 0x6f, 0xb9, - 0x15, 0x90, 0x57, 0x7a, 0xf6, 0xad, 0xb0, 0x5b, - 0xf5, 0xa6, 0x36, 0x94, 0xfd, 0x84, 0xce, 0x1c, - 0x0f, 0x4b, 0xd0, 0xc2, 0x5b, 0x6b, 0x56, 0xef, - 0x73, 0x93, 0x0b, 0xc3, 0xee, 0xd9, 0xcf, 0xd3, - 0xa4, 0x22, 0x58, 0xcd, 0x50, 0x6e, 0x65, 0xf4, - 0xe9, 0xb7, 0x71, 0xaf, 0x4b, 0xb3, 0xb6, 0x2f, - 0x0f, 0x0e, 0x3b, 0xc9, 0x85, 0x14, 0xf5, 0x17, - 0xe8, 0x7a, 0x3a, 0xbf, 0x5f, 0x5e, 0xf8, 0x18, - 0x48, 0xa6, 0x72, 0xab, 0x06, 0x95, 0xe9, 0xc8, - 0xa7, 0xf4, 0x32, 0x44, 0x04, 0x0c, 0x84, 0x98, - 0x73, 0xe3, 0x89, 0x8d, 0x5f, 0x7e, 0x4a, 0x42, - 0x8f, 0xc5, 0x28, 0xb1, 0x82, 0xef, 0x1c, 0x97, - 0x31, 0x3b, 0x4d, 0xe0, 0x0e, 0x10, 0x10, 0x97, - 0x93, 0x49, 0x78, 0x2f, 0x0d, 0x86, 0x8b, 0xa1, - 0x53, 0xa9, 0x81, 0x20, 0x79, 0xe7, 0x07, 0x77, - 0xb6, 0xac, 0x5e, 0xd2, 0x05, 0xcd, 0xe9, 0xdb, - 0x8a, 0x94, 0x82, 0x8a, 0x23, 0xb9, 0x3d, 0x1c, - 0xa9, 0x7d, 0x72, 0x4a, 0xed, 0x33, 0xa3, 0xdb, - 0x21, 0xa7, 0x86, 0x33, 0x45, 0xa5, 0xaa, 0x56, - 0x45, 0xb5, 0x83, 0x29, 0x40, 0x47, 0x79, 0x04, - 0x6e, 0xb9, 0x95, 0xd0, 0x81, 0x77, 0x2d, 0x48, - 0x1e, 0xfe, 0xc3, 0xc2, 0x1e, 0xe5, 0xf2, 0xbe, - 0xfd, 0x3b, 0x94, 0x9f, 0xc4, 0xc4, 0x26, 0x9d, - 0xe4, 0x66, 0x1e, 0x19, 0xee, 0x6c, 0x79, 0x97, - 0x11, 0x31, 0x4b, 0x0d, 0x01, 0xcb, 0xde, 0xa8, - 0xf6, 0x6d, 0x7c, 0x39, 0x46, 0x4e, 0x7e, 0x3f, - 0x94, 0x17, 0xdf, 0xa1, 0x7d, 0xd9, 0x1c, 0x8e, - 0xbc, 0x7d, 0x33, 0x7d, 0xe3, 0x12, 0x40, 0xca, - 0xab, 0x37, 0x11, 0x46, 0xd4, 0xae, 0xef, 0x44, - 0xa2, 0xb3, 0x6a, 0x66, 0x0e, 0x0c, 0x90, 0x7f, - 0xdf, 0x5c, 0x66, 0x5f, 0xf2, 0x94, 0x9f, 0xa6, - 0x73, 0x4f, 0xeb, 0x0d, 0xad, 0xbf, 0xc0, 0x63, - 0x5c, 0xdc, 0x46, 0x51, 0xe8, 0x8e, 0x90, 0x19, - 0xa8, 0xa4, 0x3c, 0x91, 0x79, 0xfa, 0x7e, 0x58, - 0x85, 0x13, 0x55, 0xc5, 0x19, 0x82, 0x37, 0x1b, - 0x0a, 0x02, 0x1f, 0x99, 0x6b, 0x18, 0xf1, 0x28, - 0x08, 0xa2, 0x73, 0xb8, 0x0f, 0x2e, 0xcd, 0xbf, - 0xf3, 0x86, 0x7f, 0xea, 0xef, 0xd0, 0xbb, 0xa6, - 0x21, 0xdf, 0x49, 0x73, 0x51, 0xcc, 0x36, 0xd3, - 0x3e, 0xa0, 0xf8, 0x44, 0xdf, 0xd3, 0xa6, 0xbe, - 0x8a, 0xd4, 0x57, 0xdd, 0x72, 0x94, 0x61, 0x0f, - 0x82, 0xd1, 0x07, 0xb8, 0x7c, 0x18, 0x83, 0xdf, - 0x3a, 0xe5, 0x50, 0x6a, 0x82, 0x20, 0xac, 0xa9, - 0xa8, 0xff, 0xd9, 0xf3, 0x77, 0x33, 0x5a, 0x9e, - 0x7f, 0x6d, 0xfe, 0x5d, 0x33, 0x41, 0x42, 0xe7, - 0x6c, 0x19, 0xe0, 0x44, 0x8a, 0x15, 0xf6, 0x70, - 0x98, 0xb7, 0x68, 0x4d, 0xfa, 0x97, 0x39, 0xb0, - 0x8e, 0xe8, 0x84, 0x8b, 0x75, 0x30, 0xb7, 0x7d, - 0x92, 0x69, 0x20, 0x9c, 0x81, 0xfb, 0x4b, 0xf4, - 0x01, 0x50, 0xeb, 0xce, 0x0c, 0x1c, 0x6c, 0xb5, - 0x4a, 0xd7, 0x27, 0x0c, 0xce, 0xbb, 0xe5, 0x85, - 0xf0, 0xb6, 0xee, 0xd5, 0x70, 0xdd, 0x3b, 0xfc, - 0xd4, 0x99, 0xf1, 0x33, 0xdd, 0x8b, 0xc4, 0x2f, - 0xae, 0xab, 0x74, 0x96, 0x32, 0xc7, 0x4c, 0x56, - 0x3c, 0x89, 0x0f, 0x96, 0x0b, 0x42, 0xc0, 0xcb, - 0xee, 0x0f, 0x0b, 0x8c, 0xfb, 0x7e, 0x47, 0x7b, - 0x64, 0x48, 0xfd, 0xb2, 0x00, 0x80, 0x89, 0xa5, - 0x13, 0x55, 0x62, 0xfc, 0x8f, 0xe2, 0x42, 0x03, - 0xb7, 0x4e, 0x2a, 0x79, 0xb4, 0x82, 0xea, 0x23, - 0x49, 0xda, 0xaf, 0x52, 0x63, 0x1e, 0x60, 0x03, - 0x89, 0x06, 0x44, 0x46, 0x08, 0xc3, 0xc4, 0x87, - 0x70, 0x2e, 0xda, 0x94, 0xad, 0x6b, 0xe0, 0xe4, - 0xd1, 0x8a, 0x06, 0xc2, 0xa8, 0xc0, 0xa7, 0x43, - 0x3c, 0x47, 0x52, 0x0e, 0xc3, 0x77, 0x81, 0x11, - 0x67, 0x0e, 0xa0, 0x70, 0x04, 0x47, 0x29, 0x40, - 0x86, 0x0d, 0x34, 0x56, 0xa7, 0xc9, 0x35, 0x59, - 0x68, 0xdc, 0x93, 0x81, 0x70, 0xee, 0x86, 0xd9, - 0x80, 0x06, 0x40, 0x4f, 0x1a, 0x0d, 0x40, 0x30, - 0x0b, 0xcb, 0x96, 0x47, 0xc1, 0xb7, 0x52, 0xfd, - 0x56, 0xe0, 0x72, 0x4b, 0xfb, 0xbd, 0x92, 0x45, - 0x61, 0x71, 0xc2, 0x33, 0x11, 0xbf, 0x52, 0x83, - 0x79, 0x26, 0xe0, 0x49, 0x6b, 0xb7, 0x05, 0x8b, - 0xe8, 0x0e, 0x87, 0x31, 0xd7, 0x9d, 0x8a, 0xf5, - 0xc0, 0x5f, 0x2e, 0x58, 0x4a, 0xdb, 0x11, 0xb3, - 0x6c, 0x30, 0x2a, 0x46, 0x19, 0xe3, 0x27, 0x84, - 0x1f, 0x63, 0x6e, 0xf6, 0x57, 0xc7, 0xc9, 0xd8, - 0x5e, 0xba, 0xb3, 0x87, 0xd5, 0x83, 0x26, 0x34, - 0x21, 0x9e, 0x65, 0xde, 0x42, 0xd3, 0xbe, 0x7b, - 0xbc, 0x91, 0x71, 0x44, 0x4d, 0x99, 0x3b, 0x31, - 0xe5, 0x3f, 0x11, 0x4e, 0x7f, 0x13, 0x51, 0x3b, - 0xae, 0x79, 0xc9, 0xd3, 0x81, 0x8e, 0x25, 0x40, - 0x10, 0xfc, 0x07, 0x1e, 0xf9, 0x7b, 0x9a, 0x4b, - 0x6c, 0xe3, 0xb3, 0xad, 0x1a, 0x0a, 0xdd, 0x9e, - 0x59, 0x0c, 0xa2, 0xcd, 0xae, 0x48, 0x4a, 0x38, - 0x5b, 0x47, 0x41, 0x94, 0x65, 0x6b, 0xbb, 0xeb, - 0x5b, 0xe3, 0xaf, 0x07, 0x5b, 0xd4, 0x4a, 0xa2, - 0xc9, 0x5d, 0x2f, 0x64, 0x03, 0xd7, 0x3a, 0x2c, - 0x6e, 0xce, 0x76, 0x95, 0xb4, 0xb3, 0xc0, 0xf1, - 0xe2, 0x45, 0x73, 0x7a, 0x5c, 0xab, 0xc1, 0xfc, - 0x02, 0x8d, 0x81, 0x29, 0xb3, 0xac, 0x07, 0xec, - 0x40, 0x7d, 0x45, 0xd9, 0x7a, 0x59, 0xee, 0x34, - 0xf0, 0xe9, 0xd5, 0x7b, 0x96, 0xb1, 0x3d, 0x95, - 0xcc, 0x86, 0xb5, 0xb6, 0x04, 0x2d, 0xb5, 0x92, - 0x7e, 0x76, 0xf4, 0x06, 0xa9, 0xa3, 0x12, 0x0f, - 0xb1, 0xaf, 0x26, 0xba, 0x7c, 0xfc, 0x7e, 0x1c, - 0xbc, 0x2c, 0x49, 0x97, 0x53, 0x60, 0x13, 0x0b, - 0xa6, 0x61, 0x83, 0x89, 0x42, 0xd4, 0x17, 0x0c, - 0x6c, 0x26, 0x52, 0xc3, 0xb3, 0xd4, 0x67, 0xf5, - 0xe3, 0x04, 0xb7, 0xf4, 0xcb, 0x80, 0xb8, 0xcb, - 0x77, 0x56, 0x3e, 0xaa, 0x57, 0x54, 0xee, 0xb4, - 0x2c, 0x67, 0xcf, 0xf2, 0xdc, 0xbe, 0x55, 0xf9, - 0x43, 0x1f, 0x6e, 0x22, 0x97, 0x67, 0x7f, 0xc4, - 0xef, 0xb1, 0x26, 0x31, 0x1e, 0x27, 0xdf, 0x41, - 0x80, 0x47, 0x6c, 0xe2, 0xfa, 0xa9, 0x8c, 0x2a, - 0xf6, 0xf2, 0xab, 0xf0, 0x15, 0xda, 0x6c, 0xc8, - 0xfe, 0xb5, 0x23, 0xde, 0xa9, 0x05, 0x3f, 0x06, - 0x54, 0x4c, 0xcd, 0xe1, 0xab, 0xfc, 0x0e, 0x62, - 0x33, 0x31, 0x73, 0x2c, 0x76, 0xcb, 0xb4, 0x47, - 0x1e, 0x20, 0xad, 0xd8, 0xf2, 0x31, 0xdd, 0xc4, - 0x8b, 0x0c, 0x77, 0xbe, 0xe1, 0x8b, 0x26, 0x00, - 0x02, 0x58, 0xd6, 0x8d, 0xef, 0xad, 0x74, 0x67, - 0xab, 0x3f, 0xef, 0xcb, 0x6f, 0xb0, 0xcc, 0x81, - 0x44, 0x4c, 0xaf, 0xe9, 0x49, 0x4f, 0xdb, 0xa0, - 0x25, 0xa4, 0xf0, 0x89, 0xf1, 0xbe, 0xd8, 0x10, - 0xff, 0xb1, 0x3b, 0x4b, 0xfa, 0x98, 0xf5, 0x79, - 0x6d, 0x1e, 0x69, 0x4d, 0x57, 0xb1, 0xc8, 0x19, - 0x1b, 0xbd, 0x1e, 0x8c, 0x84, 0xb7, 0x7b, 0xe8, - 0xd2, 0x2d, 0x09, 0x41, 0x41, 0x37, 0x3d, 0xb1, - 0x6f, 0x26, 0x5d, 0x71, 0x16, 0x3d, 0xb7, 0x83, - 0x27, 0x2c, 0xa7, 0xb6, 0x50, 0xbd, 0x91, 0x86, - 0xab, 0x24, 0xa1, 0x38, 0xfd, 0xea, 0x71, 0x55, - 0x7e, 0x9a, 0x07, 0x77, 0x4b, 0xfa, 0x61, 0x66, - 0x20, 0x1e, 0x28, 0x95, 0x18, 0x1b, 0xa4, 0xa0, - 0xfd, 0xc0, 0x89, 0x72, 0x43, 0xd9, 0x3b, 0x49, - 0x5a, 0x3f, 0x9d, 0xbf, 0xdb, 0xb4, 0x46, 0xea, - 0x42, 0x01, 0x77, 0x23, 0x68, 0x95, 0xb6, 0x24, - 0xb3, 0xa8, 0x6c, 0x28, 0x3b, 0x11, 0x40, 0x7e, - 0x18, 0x65, 0x6d, 0xd8, 0x24, 0x42, 0x7d, 0x88, - 0xc0, 0x52, 0xd9, 0x05, 0xe4, 0x95, 0x90, 0x87, - 0x8c, 0xf4, 0xd0, 0x6b, 0xb9, 0x83, 0x99, 0x34, - 0x6d, 0xfe, 0x54, 0x40, 0x94, 0x52, 0x21, 0x4f, - 0x14, 0x25, 0xc5, 0xd6, 0x5e, 0x95, 0xdc, 0x0a, - 0x2b, 0x89, 0x20, 0x11, 0x84, 0x48, 0xd6, 0x3a, - 0xcd, 0x5c, 0x24, 0xad, 0x62, 0xe3, 0xb1, 0x93, - 0x25, 0x8d, 0xcd, 0x7e, 0xfc, 0x27, 0xa3, 0x37, - 0xfd, 0x84, 0xfc, 0x1b, 0xb2, 0xf1, 0x27, 0x38, - 0x5a, 0xb7, 0xfc, 0xf2, 0xfa, 0x95, 0x66, 0xd4, - 0xfb, 0xba, 0xa7, 0xd7, 0xa3, 0x72, 0x69, 0x48, - 0x48, 0x8c, 0xeb, 0x28, 0x89, 0xfe, 0x33, 0x65, - 0x5a, 0x36, 0x01, 0x7e, 0x06, 0x79, 0x0a, 0x09, - 0x3b, 0x74, 0x11, 0x9a, 0x6e, 0xbf, 0xd4, 0x9e, - 0x58, 0x90, 0x49, 0x4f, 0x4d, 0x08, 0xd4, 0xe5, - 0x4a, 0x09, 0x21, 0xef, 0x8b, 0xb8, 0x74, 0x3b, - 0x91, 0xdd, 0x36, 0x85, 0x60, 0x2d, 0xfa, 0xd4, - 0x45, 0x7b, 0x45, 0x53, 0xf5, 0x47, 0x87, 0x7e, - 0xa6, 0x37, 0xc8, 0x78, 0x7a, 0x68, 0x9d, 0x8d, - 0x65, 0x2c, 0x0e, 0x91, 0x5c, 0xa2, 0x60, 0xf0, - 0x8e, 0x3f, 0xe9, 0x1a, 0xcd, 0xaa, 0xe7, 0xd5, - 0x77, 0x18, 0xaf, 0xc9, 0xbc, 0x18, 0xea, 0x48, - 0x1b, 0xfb, 0x22, 0x48, 0x70, 0x16, 0x29, 0x9e, - 0x5b, 0xc1, 0x2c, 0x66, 0x23, 0xbc, 0xf0, 0x1f, - 0xef, 0xaf, 0xe4, 0xd6, 0x04, 0x19, 0x82, 0x7a, - 0x0b, 0xba, 0x4b, 0x46, 0xb1, 0x6a, 0x85, 0x5d, - 0xb4, 0x73, 0xd6, 0x21, 0xa1, 0x71, 0x60, 0x14, - 0xee, 0x0a, 0x77, 0xc4, 0x66, 0x2e, 0xf9, 0x69, - 0x30, 0xaf, 0x41, 0x0b, 0xc8, 0x83, 0x3c, 0x53, - 0x99, 0x19, 0x27, 0x46, 0xf7, 0x41, 0x6e, 0x56, - 0xdc, 0x94, 0x28, 0x67, 0x4e, 0xb7, 0x25, 0x48, - 0x8a, 0xc2, 0xe0, 0x60, 0x96, 0xcc, 0x18, 0xf4, - 0x84, 0xdd, 0xa7, 0x5e, 0x3e, 0x05, 0x0b, 0x26, - 0x26, 0xb2, 0x5c, 0x1f, 0x57, 0x1a, 0x04, 0x7e, - 0x6a, 0xe3, 0x2f, 0xb4, 0x35, 0xb6, 0x38, 0x40, - 0x40, 0xcd, 0x6f, 0x87, 0x2e, 0xef, 0xa3, 0xd7, - 0xa9, 0xc2, 0xe8, 0x0d, 0x27, 0xdf, 0x44, 0x62, - 0x99, 0xa0, 0xfc, 0xcf, 0x81, 0x78, 0xcb, 0xfe, - 0xe5, 0xa0, 0x03, 0x4e, 0x6c, 0xd7, 0xf4, 0xaf, - 0x7a, 0xbb, 0x61, 0x82, 0xfe, 0x71, 0x89, 0xb2, - 0x22, 0x7c, 0x8e, 0x83, 0x04, 0xce, 0xf6, 0x5d, - 0x84, 0x8f, 0x95, 0x6a, 0x7f, 0xad, 0xfd, 0x32, - 0x9c, 0x5e, 0xe4, 0x9c, 0x89, 0x60, 0x54, 0xaa, - 0x96, 0x72, 0xd2, 0xd7, 0x36, 0x85, 0xa9, 0x45, - 0xd2, 0x2a, 0xa1, 0x81, 0x49, 0x6f, 0x7e, 0x04, - 0xfa, 0xe2, 0xfe, 0x90, 0x26, 0x77, 0x5a, 0x33, - 0xb8, 0x04, 0x9a, 0x7a, 0xe6, 0x4c, 0x4f, 0xad, - 0x72, 0x96, 0x08, 0x28, 0x58, 0x13, 0xf8, 0xc4, - 0x1c, 0xf0, 0xc3, 0x45, 0x95, 0x49, 0x20, 0x8c, - 0x9f, 0x39, 0x70, 0xe1, 0x77, 0xfe, 0xd5, 0x4b, - 0xaf, 0x86, 0xda, 0xef, 0x22, 0x06, 0x83, 0x36, - 0x29, 0x12, 0x11, 0x40, 0xbc, 0x3b, 0x86, 0xaa, - 0xaa, 0x65, 0x60, 0xc3, 0x80, 0xca, 0xed, 0xa9, - 0xf3, 0xb0, 0x79, 0x96, 0xa2, 0x55, 0x27, 0x28, - 0x55, 0x73, 0x26, 0xa5, 0x50, 0xea, 0x92, 0x4b, - 0x3c, 0x5c, 0x82, 0x33, 0xf0, 0x01, 0x3f, 0x03, - 0xc1, 0x08, 0x05, 0xbf, 0x98, 0xf4, 0x9b, 0x6d, - 0xa5, 0xa8, 0xb4, 0x82, 0x0c, 0x06, 0xfa, 0xff, - 0x2d, 0x08, 0xf3, 0x05, 0x4f, 0x57, 0x2a, 0x39, - 0xd4, 0x83, 0x0d, 0x75, 0x51, 0xd8, 0x5b, 0x1b, - 0xd3, 0x51, 0x5a, 0x32, 0x2a, 0x9b, 0x32, 0xb2, - 0xf2, 0xa4, 0x96, 0x12, 0xf2, 0xae, 0x40, 0x34, - 0x67, 0xa8, 0xf5, 0x44, 0xd5, 0x35, 0x53, 0xfe, - 0xa3, 0x60, 0x96, 0x63, 0x0f, 0x1f, 0x6e, 0xb0, - 0x5a, 0x42, 0xa6, 0xfc, 0x51, 0x0b, 0x60, 0x27, - 0xbc, 0x06, 0x71, 0xed, 0x65, 0x5b, 0x23, 0x86, - 0x4a, 0x07, 0x3b, 0x22, 0x07, 0x46, 0xe6, 0x90, - 0x3e, 0xf3, 0x25, 0x50, 0x1b, 0x4c, 0x7f, 0x03, - 0x08, 0xa8, 0x36, 0x6b, 0x87, 0xe5, 0xe3, 0xdb, - 0x9a, 0x38, 0x83, 0xff, 0x9f, 0x1a, 0x9f, 0x57, - 0xa4, 0x2a, 0xf6, 0x37, 0xbc, 0x1a, 0xff, 0xc9, - 0x1e, 0x35, 0x0c, 0xc3, 0x7c, 0xa3, 0xb2, 0xe5, - 0xd2, 0xc6, 0xb4, 0x57, 0x47, 0xe4, 0x32, 0x16, - 0x6d, 0xa9, 0xae, 0x64, 0xe6, 0x2d, 0x8d, 0xc5, - 0x8d, 0x50, 0x8e, 0xe8, 0x1a, 0x22, 0x34, 0x2a, - 0xd9, 0xeb, 0x51, 0x90, 0x4a, 0xb1, 0x41, 0x7d, - 0x64, 0xf9, 0xb9, 0x0d, 0xf6, 0x23, 0x33, 0xb0, - 0x33, 0xf4, 0xf7, 0x3f, 0x27, 0x84, 0xc6, 0x0f, - 0x54, 0xa5, 0xc0, 0x2e, 0xec, 0x0b, 0x3a, 0x48, - 0x6e, 0x80, 0x35, 0x81, 0x43, 0x9b, 0x90, 0xb1, - 0xd0, 0x2b, 0xea, 0x21, 0xdc, 0xda, 0x5b, 0x09, - 0xf4, 0xcc, 0x10, 0xb4, 0xc7, 0xfe, 0x79, 0x51, - 0xc3, 0xc5, 0xac, 0x88, 0x74, 0x84, 0x0b, 0x4b, - 0xca, 0x79, 0x16, 0x29, 0xfb, 0x69, 0x54, 0xdf, - 0x41, 0x7e, 0xe9, 0xc7, 0x8e, 0xea, 0xa5, 0xfe, - 0xfc, 0x76, 0x0e, 0x90, 0xc4, 0x92, 0x38, 0xad, - 0x7b, 0x48, 0xe6, 0x6e, 0xf7, 0x21, 0xfd, 0x4e, - 0x93, 0x0a, 0x7b, 0x41, 0x83, 0x68, 0xfb, 0x57, - 0x51, 0x76, 0x34, 0xa9, 0x6c, 0x00, 0xaa, 0x4f, - 0x66, 0x65, 0x98, 0x4a, 0x4f, 0xa3, 0xa0, 0xef, - 0x69, 0x3f, 0xe3, 0x1c, 0x92, 0x8c, 0xfd, 0xd8, - 0xe8, 0xde, 0x7c, 0x7f, 0x3e, 0x84, 0x8e, 0x69, - 0x3c, 0xf1, 0xf2, 0x05, 0x46, 0xdc, 0x2f, 0x9d, - 0x5e, 0x6e, 0x4c, 0xfb, 0xb5, 0x99, 0x2a, 0x59, - 0x63, 0xc1, 0x34, 0xbc, 0x57, 0xc0, 0x0d, 0xb9, - 0x61, 0x25, 0xf3, 0x33, 0x23, 0x51, 0xb6, 0x0d, - 0x07, 0xa6, 0xab, 0x94, 0x4a, 0xb7, 0x2a, 0xea, - 0xee, 0xac, 0xa3, 0xc3, 0x04, 0x8b, 0x0e, 0x56, - 0xfe, 0x44, 0xa7, 0x39, 0xe2, 0xed, 0xed, 0xb4, - 0x22, 0x2b, 0xac, 0x12, 0x32, 0x28, 0x91, 0xd8, - 0xa5, 0xab, 0xff, 0x5f, 0xe0, 0x4b, 0xda, 0x78, - 0x17, 0xda, 0xf1, 0x01, 0x5b, 0xcd, 0xe2, 0x5f, - 0x50, 0x45, 0x73, 0x2b, 0xe4, 0x76, 0x77, 0xf4, - 0x64, 0x1d, 0x43, 0xfb, 0x84, 0x7a, 0xea, 0x91, - 0xae, 0xf9, 0x9e, 0xb7, 0xb4, 0xb0, 0x91, 0x5f, - 0x16, 0x35, 0x9a, 0x11, 0xb8, 0xc7, 0xc1, 0x8c, - 0xc6, 0x10, 0x8d, 0x2f, 0x63, 0x4a, 0xa7, 0x57, - 0x3a, 0x51, 0xd6, 0x32, 0x2d, 0x64, 0x72, 0xd4, - 0x66, 0xdc, 0x10, 0xa6, 0x67, 0xd6, 0x04, 0x23, - 0x9d, 0x0a, 0x11, 0x77, 0xdd, 0x37, 0x94, 0x17, - 0x3c, 0xbf, 0x8b, 0x65, 0xb0, 0x2e, 0x5e, 0x66, - 0x47, 0x64, 0xac, 0xdd, 0xf0, 0x84, 0xfd, 0x39, - 0xfa, 0x15, 0x5d, 0xef, 0xae, 0xca, 0xc1, 0x36, - 0xa7, 0x5c, 0xbf, 0xc7, 0x08, 0xc2, 0x66, 0x00, - 0x74, 0x74, 0x4e, 0x27, 0x3f, 0x55, 0x8a, 0xb7, - 0x38, 0x66, 0x83, 0x6d, 0xcf, 0x99, 0x9e, 0x60, - 0x8f, 0xdd, 0x2e, 0x62, 0x22, 0x0e, 0xef, 0x0c, - 0x98, 0xa7, 0x85, 0x74, 0x3b, 0x9d, 0xec, 0x9e, - 0xa9, 0x19, 0x72, 0xa5, 0x7f, 0x2c, 0x39, 0xb7, - 0x7d, 0xb7, 0xf1, 0x12, 0x65, 0x27, 0x4b, 0x5a, - 0xde, 0x17, 0xfe, 0xad, 0x44, 0xf3, 0x20, 0x4d, - 0xfd, 0xe4, 0x1f, 0xb5, 0x81, 0xb0, 0x36, 0x37, - 0x08, 0x6f, 0xc3, 0x0c, 0xe9, 0x85, 0x98, 0x82, - 0xa9, 0x62, 0x0c, 0xc4, 0x97, 0xc0, 0x50, 0xc8, - 0xa7, 0x3c, 0x50, 0x9f, 0x43, 0xb9, 0xcd, 0x5e, - 0x4d, 0xfa, 0x1c, 0x4b, 0x0b, 0xa9, 0x98, 0x85, - 0x38, 0x92, 0xac, 0x8d, 0xe4, 0xad, 0x9b, 0x98, - 0xab, 0xd9, 0x38, 0xac, 0x62, 0x52, 0xa3, 0x22, - 0x63, 0x0f, 0xbf, 0x95, 0x48, 0xdf, 0x69, 0xe7, - 0x8b, 0x33, 0xd5, 0xb2, 0xbd, 0x05, 0x49, 0x49, - 0x9d, 0x57, 0x73, 0x19, 0x33, 0xae, 0xfa, 0x33, - 0xf1, 0x19, 0xa8, 0x80, 0xce, 0x04, 0x9f, 0xbc, - 0x1d, 0x65, 0x82, 0x1b, 0xe5, 0x3a, 0x51, 0xc8, - 0x1c, 0x21, 0xe3, 0x5d, 0xf3, 0x7d, 0x9b, 0x2f, - 0x2c, 0x1d, 0x4a, 0x7f, 0x9b, 0x68, 0x35, 0xa3, - 0xb2, 0x50, 0xf7, 0x62, 0x79, 0xcd, 0xf4, 0x98, - 0x4f, 0xe5, 0x63, 0x7c, 0x3e, 0x45, 0x31, 0x8c, - 0x16, 0xa0, 0x12, 0xc8, 0x58, 0xce, 0x39, 0xa6, - 0xbc, 0x54, 0xdb, 0xc5, 0xe0, 0xd5, 0xba, 0xbc, - 0xb9, 0x04, 0xf4, 0x8d, 0xe8, 0x2f, 0x15, 0x9d, -}; - -/* 100 test cases */ -static struct crc_test { - u32 crc; /* random starting crc */ - u32 start; /* random 6 bit offset in buf */ - u32 length; /* random 11 bit length of test */ - u32 crc_le; /* expected crc32_le result */ - u32 crc_be; /* expected crc32_be result */ - u32 crc32c_le; /* expected crc32c_le result */ -} const test[] __initconst = -{ - {0x674bf11d, 0x00000038, 0x00000542, 0x0af6d466, 0xd8b6e4c1, 0xf6e93d6c}, - {0x35c672c6, 0x0000003a, 0x000001aa, 0xc6d3dfba, 0x28aaf3ad, 0x0fe92aca}, - {0x496da28e, 0x00000039, 0x000005af, 0xd933660f, 0x5d57e81f, 0x52e1ebb8}, - {0x09a9b90e, 0x00000027, 0x000001f8, 0xb45fe007, 0xf45fca9a, 0x0798af9a}, - {0xdc97e5a9, 0x00000025, 0x000003b6, 0xf81a3562, 0xe0126ba2, 0x18eb3152}, - {0x47c58900, 0x0000000a, 0x000000b9, 0x8e58eccf, 0xf3afc793, 0xd00d08c7}, - {0x292561e8, 0x0000000c, 0x00000403, 0xa2ba8aaf, 0x0b797aed, 0x8ba966bc}, - {0x415037f6, 0x00000003, 0x00000676, 0xa17d52e8, 0x7f0fdf35, 0x11d694a2}, - {0x3466e707, 0x00000026, 0x00000042, 0x258319be, 0x75c484a2, 0x6ab3208d}, - {0xafd1281b, 0x00000023, 0x000002ee, 0x4428eaf8, 0x06c7ad10, 0xba4603c5}, - {0xd3857b18, 0x00000028, 0x000004a2, 0x5c430821, 0xb062b7cb, 0xe6071c6f}, - {0x1d825a8f, 0x0000002b, 0x0000050b, 0xd2c45f0c, 0xd68634e0, 0x179ec30a}, - {0x5033e3bc, 0x0000000b, 0x00000078, 0xa3ea4113, 0xac6d31fb, 0x0903beb8}, - {0x94f1fb5e, 0x0000000f, 0x000003a2, 0xfbfc50b1, 0x3cfe50ed, 0x6a7cb4fa}, - {0xc9a0fe14, 0x00000009, 0x00000473, 0x5fb61894, 0x87070591, 0xdb535801}, - {0x88a034b1, 0x0000001c, 0x000005ad, 0xc1b16053, 0x46f95c67, 0x92bed597}, - {0xf0f72239, 0x00000020, 0x0000026d, 0xa6fa58f3, 0xf8c2c1dd, 0x192a3f1b}, - {0xcc20a5e3, 0x0000003b, 0x0000067a, 0x7740185a, 0x308b979a, 0xccbaec1a}, - {0xce589c95, 0x0000002b, 0x00000641, 0xd055e987, 0x40aae25b, 0x7eabae4d}, - {0x78edc885, 0x00000035, 0x000005be, 0xa39cb14b, 0x035b0d1f, 0x28c72982}, - {0x9d40a377, 0x0000003b, 0x00000038, 0x1f47ccd2, 0x197fbc9d, 0xc3cd4d18}, - {0x703d0e01, 0x0000003c, 0x000006f1, 0x88735e7c, 0xfed57c5a, 0xbca8f0e7}, - {0x776bf505, 0x0000000f, 0x000005b2, 0x5cc4fc01, 0xf32efb97, 0x713f60b3}, - {0x4a3e7854, 0x00000027, 0x000004b8, 0x8d923c82, 0x0cbfb4a2, 0xebd08fd5}, - {0x209172dd, 0x0000003b, 0x00000356, 0xb89e9c2b, 0xd7868138, 0x64406c59}, - {0x3ba4cc5b, 0x0000002f, 0x00000203, 0xe51601a9, 0x5b2a1032, 0x7421890e}, - {0xfc62f297, 0x00000000, 0x00000079, 0x71a8e1a2, 0x5d88685f, 0xe9347603}, - {0x64280b8b, 0x00000016, 0x000007ab, 0x0fa7a30c, 0xda3a455f, 0x1bef9060}, - {0x97dd724b, 0x00000033, 0x000007ad, 0x5788b2f4, 0xd7326d32, 0x34720072}, - {0x61394b52, 0x00000035, 0x00000571, 0xc66525f1, 0xcabe7fef, 0x48310f59}, - {0x29b4faff, 0x00000024, 0x0000006e, 0xca13751e, 0x993648e0, 0x783a4213}, - {0x29bfb1dc, 0x0000000b, 0x00000244, 0x436c43f7, 0x429f7a59, 0x9e8efd41}, - {0x86ae934b, 0x00000035, 0x00000104, 0x0760ec93, 0x9cf7d0f4, 0xfc3d34a5}, - {0xc4c1024e, 0x0000002e, 0x000006b1, 0x6516a3ec, 0x19321f9c, 0x17a52ae2}, - {0x3287a80a, 0x00000026, 0x00000496, 0x0b257eb1, 0x754ebd51, 0x886d935a}, - {0xa4db423e, 0x00000023, 0x0000045d, 0x9b3a66dc, 0x873e9f11, 0xeaaeaeb2}, - {0x7a1078df, 0x00000015, 0x0000014a, 0x8c2484c5, 0x6a628659, 0x8e900a4b}, - {0x6048bd5b, 0x00000006, 0x0000006a, 0x897e3559, 0xac9961af, 0xd74662b1}, - {0xd8f9ea20, 0x0000003d, 0x00000277, 0x60eb905b, 0xed2aaf99, 0xd26752ba}, - {0xea5ec3b4, 0x0000002a, 0x000004fe, 0x869965dc, 0x6c1f833b, 0x8b1fcd62}, - {0x2dfb005d, 0x00000016, 0x00000345, 0x6a3b117e, 0xf05e8521, 0xf54342fe}, - {0x5a214ade, 0x00000020, 0x000005b6, 0x467f70be, 0xcb22ccd3, 0x5b95b988}, - {0xf0ab9cca, 0x00000032, 0x00000515, 0xed223df3, 0x7f3ef01d, 0x2e1176be}, - {0x91b444f9, 0x0000002e, 0x000007f8, 0x84e9a983, 0x5676756f, 0x66120546}, - {0x1b5d2ddb, 0x0000002e, 0x0000012c, 0xba638c4c, 0x3f42047b, 0xf256a5cc}, - {0xd824d1bb, 0x0000003a, 0x000007b5, 0x6288653b, 0x3a3ebea0, 0x4af1dd69}, - {0x0470180c, 0x00000034, 0x000001f0, 0x9d5b80d6, 0x3de08195, 0x56f0a04a}, - {0xffaa3a3f, 0x00000036, 0x00000299, 0xf3a82ab8, 0x53e0c13d, 0x74f6b6b2}, - {0x6406cfeb, 0x00000023, 0x00000600, 0xa920b8e8, 0xe4e2acf4, 0x085951fd}, - {0xb24aaa38, 0x0000003e, 0x000004a1, 0x657cc328, 0x5077b2c3, 0xc65387eb}, - {0x58b2ab7c, 0x00000039, 0x000002b4, 0x3a17ee7e, 0x9dcb3643, 0x1ca9257b}, - {0x3db85970, 0x00000006, 0x000002b6, 0x95268b59, 0xb9812c10, 0xfd196d76}, - {0x857830c5, 0x00000003, 0x00000590, 0x4ef439d5, 0xf042161d, 0x5ef88339}, - {0xe1fcd978, 0x0000003e, 0x000007d8, 0xae8d8699, 0xce0a1ef5, 0x2c3714d9}, - {0xb982a768, 0x00000016, 0x000006e0, 0x62fad3df, 0x5f8a067b, 0x58576548}, - {0x1d581ce8, 0x0000001e, 0x0000058b, 0xf0f5da53, 0x26e39eee, 0xfd7c57de}, - {0x2456719b, 0x00000025, 0x00000503, 0x4296ac64, 0xd50e4c14, 0xd5fedd59}, - {0xfae6d8f2, 0x00000000, 0x0000055d, 0x057fdf2e, 0x2a31391a, 0x1cc3b17b}, - {0xcba828e3, 0x00000039, 0x000002ce, 0xe3f22351, 0x8f00877b, 0x270eed73}, - {0x13d25952, 0x0000000a, 0x0000072d, 0x76d4b4cc, 0x5eb67ec3, 0x91ecbb11}, - {0x0342be3f, 0x00000015, 0x00000599, 0xec75d9f1, 0x9d4d2826, 0x05ed8d0c}, - {0xeaa344e0, 0x00000014, 0x000004d8, 0x72a4c981, 0x2064ea06, 0x0b09ad5b}, - {0xbbb52021, 0x0000003b, 0x00000272, 0x04af99fc, 0xaf042d35, 0xf8d511fb}, - {0xb66384dc, 0x0000001d, 0x000007fc, 0xd7629116, 0x782bd801, 0x5ad832cc}, - {0x616c01b6, 0x00000022, 0x000002c8, 0x5b1dab30, 0x783ce7d2, 0x1214d196}, - {0xce2bdaad, 0x00000016, 0x0000062a, 0x932535c8, 0x3f02926d, 0x5747218a}, - {0x00fe84d7, 0x00000005, 0x00000205, 0x850e50aa, 0x753d649c, 0xde8f14de}, - {0xbebdcb4c, 0x00000006, 0x0000055d, 0xbeaa37a2, 0x2d8c9eba, 0x3563b7b9}, - {0xd8b1a02a, 0x00000010, 0x00000387, 0x5017d2fc, 0x503541a5, 0x071475d0}, - {0x3b96cad2, 0x00000036, 0x00000347, 0x1d2372ae, 0x926cd90b, 0x54c79d60}, - {0xc94c1ed7, 0x00000005, 0x0000038b, 0x9e9fdb22, 0x144a9178, 0x4c53eee6}, - {0x1aad454e, 0x00000025, 0x000002b2, 0xc3f6315c, 0x5c7a35b3, 0x10137a3c}, - {0xa4fec9a6, 0x00000000, 0x000006d6, 0x90be5080, 0xa4107605, 0xaa9d6c73}, - {0x1bbe71e2, 0x0000001f, 0x000002fd, 0x4e504c3b, 0x284ccaf1, 0xb63d23e7}, - {0x4201c7e4, 0x00000002, 0x000002b7, 0x7822e3f9, 0x0cc912a9, 0x7f53e9cf}, - {0x23fddc96, 0x00000003, 0x00000627, 0x8a385125, 0x07767e78, 0x13c1cd83}, - {0xd82ba25c, 0x00000016, 0x0000063e, 0x98e4148a, 0x283330c9, 0x49ff5867}, - {0x786f2032, 0x0000002d, 0x0000060f, 0xf201600a, 0xf561bfcd, 0x8467f211}, - {0xfebe4e1f, 0x0000002a, 0x000004f2, 0x95e51961, 0xfd80dcab, 0x3f9683b2}, - {0x1a6e0a39, 0x00000008, 0x00000672, 0x8af6c2a5, 0x78dd84cb, 0x76a3f874}, - {0x56000ab8, 0x0000000e, 0x000000e5, 0x36bacb8f, 0x22ee1f77, 0x863b702f}, - {0x4717fe0c, 0x00000000, 0x000006ec, 0x8439f342, 0x5c8e03da, 0xdc6c58ff}, - {0xd5d5d68e, 0x0000003c, 0x000003a3, 0x46fff083, 0x177d1b39, 0x0622cc95}, - {0xc25dd6c6, 0x00000024, 0x000006c0, 0x5ceb8eb4, 0x892b0d16, 0xe85605cd}, - {0xe9b11300, 0x00000023, 0x00000683, 0x07a5d59a, 0x6c6a3208, 0x31da5f06}, - {0x95cd285e, 0x00000001, 0x00000047, 0x7b3a4368, 0x0202c07e, 0xa1f2e784}, - {0xd9245a25, 0x0000001e, 0x000003a6, 0xd33c1841, 0x1936c0d5, 0xb07cc616}, - {0x103279db, 0x00000006, 0x0000039b, 0xca09b8a0, 0x77d62892, 0xbf943b6c}, - {0x1cba3172, 0x00000027, 0x000001c8, 0xcb377194, 0xebe682db, 0x2c01af1c}, - {0x8f613739, 0x0000000c, 0x000001df, 0xb4b0bc87, 0x7710bd43, 0x0fe5f56d}, - {0x1c6aa90d, 0x0000001b, 0x0000053c, 0x70559245, 0xda7894ac, 0xf8943b2d}, - {0xaabe5b93, 0x0000003d, 0x00000715, 0xcdbf42fa, 0x0c3b99e7, 0xe4d89272}, - {0xf15dd038, 0x00000006, 0x000006db, 0x6e104aea, 0x8d5967f2, 0x7c2f6bbb}, - {0x584dd49c, 0x00000020, 0x000007bc, 0x36b6cfd6, 0xad4e23b2, 0xabbf388b}, - {0x5d8c9506, 0x00000020, 0x00000470, 0x4c62378e, 0x31d92640, 0x1dca1f4e}, - {0xb80d17b0, 0x00000032, 0x00000346, 0x22a5bb88, 0x9a7ec89f, 0x5c170e23}, - {0xdaf0592e, 0x00000023, 0x000007b0, 0x3cab3f99, 0x9b1fdd99, 0xc0e9d672}, - {0x4793cc85, 0x0000000d, 0x00000706, 0xe82e04f6, 0xed3db6b7, 0xc18bdc86}, - {0x82ebf64e, 0x00000009, 0x000007c3, 0x69d590a9, 0x9efa8499, 0xa874fcdd}, - {0xb18a0319, 0x00000026, 0x000007db, 0x1cf98dcc, 0x8fa9ad6a, 0x9dc0bb48}, -}; - -#include <linux/time.h> - -static int __init crc32c_test(void) -{ - int i; - int errors = 0; - int bytes = 0; - u64 nsec; - unsigned long flags; - - /* keep static to prevent cache warming code from - * getting eliminated by the compiler */ - static u32 crc; - - /* pre-warm the cache */ - for (i = 0; i < 100; i++) { - bytes += test[i].length; - - crc ^= __crc32c_le(test[i].crc, test_buf + - test[i].start, test[i].length); - } - - /* reduce OS noise */ - local_irq_save(flags); - - 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++; - } - nsec = ktime_get_ns() - nsec; - - local_irq_restore(flags); - - pr_info("crc32c: CRC_LE_BITS = %d\n", CRC_LE_BITS); - - if (errors) - pr_warn("crc32c: %d self tests failed\n", errors); - else { - pr_info("crc32c: self tests passed, processed %d bytes in %lld nsec\n", - bytes, nsec); - } - - return 0; -} - -static int __init crc32c_combine_test(void) -{ - int i, j; - int errors = 0, runs = 0; - - for (i = 0; i < 10; i++) { - u32 crc_full; - - crc_full = __crc32c_le(test[i].crc, test_buf + test[i].start, - test[i].length); - for (j = 0; j <= test[i].length; ++j) { - u32 crc1, crc2; - u32 len1 = j, len2 = test[i].length - j; - - crc1 = __crc32c_le(test[i].crc, test_buf + - test[i].start, len1); - crc2 = __crc32c_le(0, test_buf + test[i].start + - len1, len2); - - if (!(crc_full == __crc32c_le_combine(crc1, crc2, len2) && - crc_full == test[i].crc32c_le)) - errors++; - runs++; - cond_resched(); - } - } - - if (errors) - pr_warn("crc32c_combine: %d/%d self tests failed\n", errors, runs); - else - pr_info("crc32c_combine: %d self tests passed\n", runs); - - return 0; -} - -static int __init crc32_test(void) -{ - int i; - int errors = 0; - int bytes = 0; - u64 nsec; - unsigned long flags; - - /* keep static to prevent cache warming code from - * getting eliminated by the compiler */ - static u32 crc; - - /* pre-warm the cache */ - for (i = 0; i < 100; i++) { - bytes += 2*test[i].length; - - crc ^= crc32_le(test[i].crc, test_buf + - test[i].start, test[i].length); - - crc ^= crc32_be(test[i].crc, test_buf + - test[i].start, test[i].length); - } - - /* reduce OS noise */ - local_irq_save(flags); - - 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)) - errors++; - - if (test[i].crc_be != crc32_be(test[i].crc, test_buf + - test[i].start, test[i].length)) - errors++; - } - nsec = ktime_get_ns() - nsec; - - local_irq_restore(flags); - - pr_info("crc32: CRC_LE_BITS = %d, CRC_BE BITS = %d\n", - CRC_LE_BITS, CRC_BE_BITS); - - if (errors) - pr_warn("crc32: %d self tests failed\n", errors); - else { - pr_info("crc32: self tests passed, processed %d bytes in %lld nsec\n", - bytes, nsec); - } - - return 0; -} - -static int __init crc32_combine_test(void) -{ - int i, j; - int errors = 0, runs = 0; - - for (i = 0; i < 10; i++) { - u32 crc_full; - - crc_full = crc32_le(test[i].crc, test_buf + test[i].start, - test[i].length); - for (j = 0; j <= test[i].length; ++j) { - u32 crc1, crc2; - u32 len1 = j, len2 = test[i].length - j; - - crc1 = crc32_le(test[i].crc, test_buf + - test[i].start, len1); - crc2 = crc32_le(0, test_buf + test[i].start + - len1, len2); - - if (!(crc_full == crc32_le_combine(crc1, crc2, len2) && - crc_full == test[i].crc_le)) - errors++; - runs++; - cond_resched(); - } - } - - if (errors) - pr_warn("crc32_combine: %d/%d self tests failed\n", errors, runs); - else - pr_info("crc32_combine: %d self tests passed\n", runs); - - return 0; -} - -static int __init crc32test_init(void) -{ - crc32_test(); - crc32c_test(); - - crc32_combine_test(); - crc32c_combine_test(); - - return 0; -} - -static void __exit crc32_exit(void) -{ -} - -module_init(crc32test_init); -module_exit(crc32_exit); - -MODULE_AUTHOR("Matt Domsch <Matt_Domsch@dell.com>"); -MODULE_DESCRIPTION("CRC32 selftest"); -MODULE_LICENSE("GPL"); diff --git a/lib/crc_kunit.c b/lib/crc_kunit.c new file mode 100644 index 000000000000..6a61d4b5fd45 --- /dev/null +++ b/lib/crc_kunit.c @@ -0,0 +1,435 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Unit tests and benchmarks for the CRC library functions + * + * Copyright 2024 Google LLC + * + * Author: Eric Biggers <ebiggers@google.com> + */ +#include <kunit/test.h> +#include <linux/crc16.h> +#include <linux/crc-t10dif.h> +#include <linux/crc32.h> +#include <linux/crc32c.h> +#include <linux/crc64.h> +#include <linux/prandom.h> +#include <linux/vmalloc.h> + +#define CRC_KUNIT_SEED 42 +#define CRC_KUNIT_MAX_LEN 16384 +#define CRC_KUNIT_NUM_TEST_ITERS 1000 + +static struct rnd_state rng; +static u8 *test_buffer; +static size_t test_buflen; + +/** + * struct crc_variant - describes a CRC variant + * @bits: Number of bits in the CRC, 1 <= @bits <= 64. + * @le: true if it's a "little endian" CRC (reversed mapping between bits and + * polynomial coefficients in each byte), false if it's a "big endian" CRC + * (natural mapping between bits and polynomial coefficients in each byte) + * @poly: The generator polynomial with the highest-order term omitted. + * Bit-reversed if @le is true. + * @func: The function to compute a CRC. The type signature uses u64 so that it + * can fit any CRC up to CRC-64. + * @combine_func: Optional function to combine two CRCs. + */ +struct crc_variant { + int bits; + bool le; + u64 poly; + u64 (*func)(u64 crc, const u8 *p, size_t len); + u64 (*combine_func)(u64 crc1, u64 crc2, size_t len2); +}; + +static u32 rand32(void) +{ + return prandom_u32_state(&rng); +} + +static u64 rand64(void) +{ + u32 n = rand32(); + + return ((u64)n << 32) | rand32(); +} + +static u64 crc_mask(const struct crc_variant *v) +{ + return (u64)-1 >> (64 - v->bits); +} + +/* Reference implementation of any CRC variant */ +static u64 crc_ref(const struct crc_variant *v, + u64 crc, const u8 *p, size_t len) +{ + size_t i, j; + + for (i = 0; i < len; i++) { + for (j = 0; j < 8; j++) { + if (v->le) { + crc ^= (p[i] >> j) & 1; + crc = (crc >> 1) ^ ((crc & 1) ? v->poly : 0); + } else { + crc ^= (u64)((p[i] >> (7 - j)) & 1) << + (v->bits - 1); + if (crc & (1ULL << (v->bits - 1))) + crc = ((crc << 1) ^ v->poly) & + crc_mask(v); + else + crc <<= 1; + } + } + } + return crc; +} + +static int crc_suite_init(struct kunit_suite *suite) +{ + /* + * Allocate the test buffer using vmalloc() with a page-aligned length + * so that it is immediately followed by a guard page. This allows + * buffer overreads to be detected, even in assembly code. + */ + test_buflen = round_up(CRC_KUNIT_MAX_LEN, PAGE_SIZE); + test_buffer = vmalloc(test_buflen); + if (!test_buffer) + return -ENOMEM; + + prandom_seed_state(&rng, CRC_KUNIT_SEED); + prandom_bytes_state(&rng, test_buffer, test_buflen); + return 0; +} + +static void crc_suite_exit(struct kunit_suite *suite) +{ + vfree(test_buffer); + test_buffer = NULL; +} + +/* Generate a random initial CRC. */ +static u64 generate_random_initial_crc(const struct crc_variant *v) +{ + switch (rand32() % 4) { + case 0: + return 0; + case 1: + return crc_mask(v); /* All 1 bits */ + default: + return rand64() & crc_mask(v); + } +} + +/* Generate a random length, preferring small lengths. */ +static size_t generate_random_length(size_t max_length) +{ + size_t len; + + switch (rand32() % 3) { + case 0: + len = rand32() % 128; + break; + case 1: + len = rand32() % 3072; + break; + default: + len = rand32(); + break; + } + return len % (max_length + 1); +} + +/* Test that v->func gives the same CRCs as a reference implementation. */ +static void crc_main_test(struct kunit *test, const struct crc_variant *v) +{ + size_t i; + + for (i = 0; i < CRC_KUNIT_NUM_TEST_ITERS; i++) { + u64 init_crc, expected_crc, actual_crc; + size_t len, offset; + bool nosimd; + + init_crc = generate_random_initial_crc(v); + len = generate_random_length(CRC_KUNIT_MAX_LEN); + + /* Generate a random offset. */ + if (rand32() % 2 == 0) { + /* Use a random alignment mod 64 */ + offset = rand32() % 64; + offset = min(offset, CRC_KUNIT_MAX_LEN - len); + } else { + /* Go up to the guard page, to catch buffer overreads */ + offset = test_buflen - len; + } + + if (rand32() % 8 == 0) + /* Refresh the data occasionally. */ + prandom_bytes_state(&rng, &test_buffer[offset], len); + + nosimd = rand32() % 8 == 0; + + /* + * Compute the CRC, and verify that it equals the CRC computed + * by a simple bit-at-a-time reference implementation. + */ + expected_crc = crc_ref(v, init_crc, &test_buffer[offset], len); + if (nosimd) + local_irq_disable(); + actual_crc = v->func(init_crc, &test_buffer[offset], len); + if (nosimd) + local_irq_enable(); + KUNIT_EXPECT_EQ_MSG(test, expected_crc, actual_crc, + "Wrong result with len=%zu offset=%zu nosimd=%d", + len, offset, nosimd); + } +} + +/* Test that CRC(concat(A, B)) == combine_CRCs(CRC(A), CRC(B), len(B)). */ +static void crc_combine_test(struct kunit *test, const struct crc_variant *v) +{ + int i; + + for (i = 0; i < 100; i++) { + u64 init_crc = generate_random_initial_crc(v); + size_t len1 = generate_random_length(CRC_KUNIT_MAX_LEN); + size_t len2 = generate_random_length(CRC_KUNIT_MAX_LEN - len1); + u64 crc1, crc2, expected_crc, actual_crc; + + prandom_bytes_state(&rng, test_buffer, len1 + len2); + crc1 = v->func(init_crc, test_buffer, len1); + crc2 = v->func(0, &test_buffer[len1], len2); + expected_crc = v->func(init_crc, test_buffer, len1 + len2); + actual_crc = v->combine_func(crc1, crc2, len2); + KUNIT_EXPECT_EQ_MSG(test, expected_crc, actual_crc, + "CRC combination gave wrong result with len1=%zu len2=%zu\n", + len1, len2); + } +} + +static void crc_test(struct kunit *test, const struct crc_variant *v) +{ + crc_main_test(test, v); + if (v->combine_func) + crc_combine_test(test, v); +} + +static __always_inline void +crc_benchmark(struct kunit *test, + u64 (*crc_func)(u64 crc, const u8 *p, size_t len)) +{ + static const size_t lens_to_test[] = { + 1, 16, 64, 127, 128, 200, 256, 511, 512, 1024, 3173, 4096, 16384, + }; + size_t len, i, j, num_iters; + /* + * Some of the CRC library functions are marked as __pure, so use + * volatile to ensure that all calls are really made as intended. + */ + volatile u64 crc = 0; + u64 t; + + if (!IS_ENABLED(CONFIG_CRC_BENCHMARK)) + kunit_skip(test, "not enabled"); + + /* warm-up */ + for (i = 0; i < 10000000; i += CRC_KUNIT_MAX_LEN) + crc = crc_func(crc, test_buffer, CRC_KUNIT_MAX_LEN); + + for (i = 0; i < ARRAY_SIZE(lens_to_test); i++) { + len = lens_to_test[i]; + KUNIT_ASSERT_LE(test, len, CRC_KUNIT_MAX_LEN); + num_iters = 10000000 / (len + 128); + preempt_disable(); + t = ktime_get_ns(); + for (j = 0; j < num_iters; j++) + crc = crc_func(crc, test_buffer, len); + t = ktime_get_ns() - t; + preempt_enable(); + kunit_info(test, "len=%zu: %llu MB/s\n", + len, div64_u64((u64)len * num_iters * 1000, t)); + } +} + +/* crc16 */ + +static u64 crc16_wrapper(u64 crc, const u8 *p, size_t len) +{ + return crc16(crc, p, len); +} + +static const struct crc_variant crc_variant_crc16 = { + .bits = 16, + .le = true, + .poly = 0xa001, + .func = crc16_wrapper, +}; + +static void crc16_test(struct kunit *test) +{ + crc_test(test, &crc_variant_crc16); +} + +static void crc16_benchmark(struct kunit *test) +{ + crc_benchmark(test, crc16_wrapper); +} + +/* crc_t10dif */ + +static u64 crc_t10dif_wrapper(u64 crc, const u8 *p, size_t len) +{ + return crc_t10dif_update(crc, p, len); +} + +static const struct crc_variant crc_variant_crc_t10dif = { + .bits = 16, + .le = false, + .poly = 0x8bb7, + .func = crc_t10dif_wrapper, +}; + +static void crc_t10dif_test(struct kunit *test) +{ + crc_test(test, &crc_variant_crc_t10dif); +} + +static void crc_t10dif_benchmark(struct kunit *test) +{ + crc_benchmark(test, crc_t10dif_wrapper); +} + +/* crc32_le */ + +static u64 crc32_le_wrapper(u64 crc, const u8 *p, size_t len) +{ + return crc32_le(crc, p, len); +} + +static u64 crc32_le_combine_wrapper(u64 crc1, u64 crc2, size_t len2) +{ + return crc32_le_combine(crc1, crc2, len2); +} + +static const struct crc_variant crc_variant_crc32_le = { + .bits = 32, + .le = true, + .poly = 0xedb88320, + .func = crc32_le_wrapper, + .combine_func = crc32_le_combine_wrapper, +}; + +static void crc32_le_test(struct kunit *test) +{ + crc_test(test, &crc_variant_crc32_le); +} + +static void crc32_le_benchmark(struct kunit *test) +{ + crc_benchmark(test, crc32_le_wrapper); +} + +/* crc32_be */ + +static u64 crc32_be_wrapper(u64 crc, const u8 *p, size_t len) +{ + return crc32_be(crc, p, len); +} + +static const struct crc_variant crc_variant_crc32_be = { + .bits = 32, + .le = false, + .poly = 0x04c11db7, + .func = crc32_be_wrapper, +}; + +static void crc32_be_test(struct kunit *test) +{ + crc_test(test, &crc_variant_crc32_be); +} + +static void crc32_be_benchmark(struct kunit *test) +{ + crc_benchmark(test, crc32_be_wrapper); +} + +/* crc32c */ + +static u64 crc32c_wrapper(u64 crc, const u8 *p, size_t len) +{ + return crc32c(crc, p, len); +} + +static u64 crc32c_combine_wrapper(u64 crc1, u64 crc2, size_t len2) +{ + return __crc32c_le_combine(crc1, crc2, len2); +} + +static const struct crc_variant crc_variant_crc32c = { + .bits = 32, + .le = true, + .poly = 0x82f63b78, + .func = crc32c_wrapper, + .combine_func = crc32c_combine_wrapper, +}; + +static void crc32c_test(struct kunit *test) +{ + crc_test(test, &crc_variant_crc32c); +} + +static void crc32c_benchmark(struct kunit *test) +{ + crc_benchmark(test, crc32c_wrapper); +} + +/* crc64_be */ + +static u64 crc64_be_wrapper(u64 crc, const u8 *p, size_t len) +{ + return crc64_be(crc, p, len); +} + +static const struct crc_variant crc_variant_crc64_be = { + .bits = 64, + .le = false, + .poly = 0x42f0e1eba9ea3693, + .func = crc64_be_wrapper, +}; + +static void crc64_be_test(struct kunit *test) +{ + crc_test(test, &crc_variant_crc64_be); +} + +static void crc64_be_benchmark(struct kunit *test) +{ + crc_benchmark(test, crc64_be_wrapper); +} + +static struct kunit_case crc_test_cases[] = { + KUNIT_CASE(crc16_test), + KUNIT_CASE(crc16_benchmark), + KUNIT_CASE(crc_t10dif_test), + KUNIT_CASE(crc_t10dif_benchmark), + KUNIT_CASE(crc32_le_test), + KUNIT_CASE(crc32_le_benchmark), + KUNIT_CASE(crc32_be_test), + KUNIT_CASE(crc32_be_benchmark), + KUNIT_CASE(crc32c_test), + KUNIT_CASE(crc32c_benchmark), + KUNIT_CASE(crc64_be_test), + KUNIT_CASE(crc64_be_benchmark), + {}, +}; + +static struct kunit_suite crc_test_suite = { + .name = "crc", + .test_cases = crc_test_cases, + .suite_init = crc_suite_init, + .suite_exit = crc_suite_exit, +}; +kunit_test_suite(crc_test_suite); + +MODULE_DESCRIPTION("Unit tests and benchmarks for the CRC library functions"); +MODULE_LICENSE("GPL"); diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile index 969baab8c805..01fac1cd05a1 100644 --- a/lib/crypto/Makefile +++ b/lib/crypto/Makefile @@ -58,3 +58,5 @@ libcurve25519-y += curve25519-selftest.o endif obj-$(CONFIG_MPILIB) += mpi/ + +obj-$(CONFIG_CRYPTO_MANAGER_EXTRA_TESTS) += simd.o diff --git a/lib/crypto/aes.c b/lib/crypto/aes.c index 827fe89922ff..eafe14d021f5 100644 --- a/lib/crypto/aes.c +++ b/lib/crypto/aes.c @@ -6,7 +6,7 @@ #include <crypto/aes.h> #include <linux/crypto.h> #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* * Emit the sbox as volatile const to prevent the compiler from doing diff --git a/lib/crypto/aesgcm.c b/lib/crypto/aesgcm.c index 6bba6473fdf3..902e49410aaf 100644 --- a/lib/crypto/aesgcm.c +++ b/lib/crypto/aesgcm.c @@ -697,7 +697,7 @@ static int __init libaesgcm_init(void) u8 tagbuf[AES_BLOCK_SIZE]; int plen = aesgcm_tv[i].plen; struct aesgcm_ctx ctx; - u8 buf[sizeof(ptext12)]; + static u8 buf[sizeof(ptext12)]; if (aesgcm_expandkey(&ctx, aesgcm_tv[i].key, aesgcm_tv[i].klen, aesgcm_tv[i].clen - plen)) { diff --git a/lib/crypto/arc4.c b/lib/crypto/arc4.c index c2020f19c652..838812d18216 100644 --- a/lib/crypto/arc4.c +++ b/lib/crypto/arc4.c @@ -71,4 +71,5 @@ void arc4_crypt(struct arc4_ctx *ctx, u8 *out, const u8 *in, unsigned int len) } EXPORT_SYMBOL(arc4_crypt); +MODULE_DESCRIPTION("ARC4 Cipher Algorithm"); MODULE_LICENSE("GPL"); diff --git a/lib/crypto/blake2s-generic.c b/lib/crypto/blake2s-generic.c index 3b6dcfdd9628..09682136b57c 100644 --- a/lib/crypto/blake2s-generic.c +++ b/lib/crypto/blake2s-generic.c @@ -14,7 +14,7 @@ #include <linux/kernel.h> #include <linux/init.h> #include <linux/bug.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> static const u8 blake2s_sigma[10][16] = { { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 }, diff --git a/lib/crypto/chacha.c b/lib/crypto/chacha.c index b748fd3d256e..3cdda3b5ee06 100644 --- a/lib/crypto/chacha.c +++ b/lib/crypto/chacha.c @@ -10,7 +10,7 @@ #include <linux/export.h> #include <linux/bitops.h> #include <linux/string.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/chacha.h> static void chacha_permute(u32 *x, int nrounds) diff --git a/lib/crypto/chacha20poly1305-selftest.c b/lib/crypto/chacha20poly1305-selftest.c index fa43deda2660..2ea61c28be4f 100644 --- a/lib/crypto/chacha20poly1305-selftest.c +++ b/lib/crypto/chacha20poly1305-selftest.c @@ -7,7 +7,7 @@ #include <crypto/chacha.h> #include <crypto/poly1305.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/bug.h> #include <linux/init.h> #include <linux/mm.h> diff --git a/lib/crypto/chacha20poly1305.c b/lib/crypto/chacha20poly1305.c index fa6a9440fc95..a839c0ac60b2 100644 --- a/lib/crypto/chacha20poly1305.c +++ b/lib/crypto/chacha20poly1305.c @@ -13,7 +13,7 @@ #include <crypto/poly1305.h> #include <crypto/scatterwalk.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/mm.h> diff --git a/lib/crypto/curve25519-fiat32.c b/lib/crypto/curve25519-fiat32.c index 2fde0ec33dbd..2e0ba634e299 100644 --- a/lib/crypto/curve25519-fiat32.c +++ b/lib/crypto/curve25519-fiat32.c @@ -10,7 +10,7 @@ * with 128-bit integer types. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/curve25519.h> #include <linux/string.h> diff --git a/lib/crypto/curve25519-hacl64.c b/lib/crypto/curve25519-hacl64.c index c40e5d913234..c4204133afb7 100644 --- a/lib/crypto/curve25519-hacl64.c +++ b/lib/crypto/curve25519-hacl64.c @@ -10,7 +10,7 @@ * integer types. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/curve25519.h> #include <linux/string.h> diff --git a/lib/crypto/des.c b/lib/crypto/des.c index ef5bb8822aba..d3423b34a8e9 100644 --- a/lib/crypto/des.c +++ b/lib/crypto/des.c @@ -17,7 +17,7 @@ #include <linux/string.h> #include <linux/types.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/des.h> #include <crypto/internal/des.h> @@ -899,4 +899,5 @@ void des3_ede_decrypt(const struct des3_ede_ctx *dctx, u8 *dst, const u8 *src) } EXPORT_SYMBOL_GPL(des3_ede_decrypt); +MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms"); MODULE_LICENSE("GPL"); diff --git a/lib/crypto/gf128mul.c b/lib/crypto/gf128mul.c index 8f8c45e0cdcf..fbe72cb3453a 100644 --- a/lib/crypto/gf128mul.c +++ b/lib/crypto/gf128mul.c @@ -225,44 +225,6 @@ void gf128mul_lle(be128 *r, const be128 *b) } EXPORT_SYMBOL(gf128mul_lle); -void gf128mul_bbe(be128 *r, const be128 *b) -{ - be128 p[8]; - int i; - - p[0] = *r; - for (i = 0; i < 7; ++i) - gf128mul_x_bbe(&p[i + 1], &p[i]); - - memset(r, 0, sizeof(*r)); - for (i = 0;;) { - u8 ch = ((u8 *)b)[i]; - - if (ch & 0x80) - be128_xor(r, r, &p[7]); - if (ch & 0x40) - be128_xor(r, r, &p[6]); - if (ch & 0x20) - be128_xor(r, r, &p[5]); - if (ch & 0x10) - be128_xor(r, r, &p[4]); - if (ch & 0x08) - be128_xor(r, r, &p[3]); - if (ch & 0x04) - be128_xor(r, r, &p[2]); - if (ch & 0x02) - be128_xor(r, r, &p[1]); - if (ch & 0x01) - be128_xor(r, r, &p[0]); - - if (++i >= 16) - break; - - gf128mul_x8_bbe(r); - } -} -EXPORT_SYMBOL(gf128mul_bbe); - /* This version uses 64k bytes of table space. A 16 byte buffer has to be multiplied by a 16 byte key value in GF(2^128). If we consider a GF(2^128) value in @@ -380,28 +342,6 @@ out: } EXPORT_SYMBOL(gf128mul_init_4k_lle); -struct gf128mul_4k *gf128mul_init_4k_bbe(const be128 *g) -{ - struct gf128mul_4k *t; - int j, k; - - t = kzalloc(sizeof(*t), GFP_KERNEL); - if (!t) - goto out; - - t->t[1] = *g; - for (j = 1; j <= 64; j <<= 1) - gf128mul_x_bbe(&t->t[j + j], &t->t[j]); - - for (j = 2; j < 256; j += j) - for (k = 1; k < j; ++k) - be128_xor(&t->t[j + k], &t->t[j], &t->t[k]); - -out: - return t; -} -EXPORT_SYMBOL(gf128mul_init_4k_bbe); - void gf128mul_4k_lle(be128 *a, const struct gf128mul_4k *t) { u8 *ap = (u8 *)a; @@ -417,20 +357,5 @@ void gf128mul_4k_lle(be128 *a, const struct gf128mul_4k *t) } EXPORT_SYMBOL(gf128mul_4k_lle); -void gf128mul_4k_bbe(be128 *a, const struct gf128mul_4k *t) -{ - u8 *ap = (u8 *)a; - be128 r[1]; - int i = 0; - - *r = t->t[ap[0]]; - while (++i < 16) { - gf128mul_x8_bbe(r); - be128_xor(r, r, &t->t[ap[i]]); - } - *a = *r; -} -EXPORT_SYMBOL(gf128mul_4k_bbe); - MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Functions for multiplying elements of GF(2^128)"); diff --git a/lib/crypto/libchacha.c b/lib/crypto/libchacha.c index dabc3accae05..cc1be0496eb9 100644 --- a/lib/crypto/libchacha.c +++ b/lib/crypto/libchacha.c @@ -32,4 +32,5 @@ void chacha_crypt_generic(u32 *state, u8 *dst, const u8 *src, } EXPORT_SYMBOL(chacha_crypt_generic); +MODULE_DESCRIPTION("ChaCha stream cipher (RFC7539)"); MODULE_LICENSE("GPL"); diff --git a/lib/crypto/memneq.c b/lib/crypto/memneq.c index 243d8677cc51..a2afd10349c9 100644 --- a/lib/crypto/memneq.c +++ b/lib/crypto/memneq.c @@ -59,7 +59,7 @@ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/algapi.h> #include <linux/module.h> diff --git a/lib/crypto/mpi/Makefile b/lib/crypto/mpi/Makefile index 6e6ef9a34fe1..9ad84079025a 100644 --- a/lib/crypto/mpi/Makefile +++ b/lib/crypto/mpi/Makefile @@ -13,14 +13,12 @@ mpi-y = \ generic_mpih-rshift.o \ generic_mpih-sub1.o \ generic_mpih-add1.o \ - ec.o \ mpicoder.o \ mpi-add.o \ mpi-bit.o \ mpi-cmp.o \ mpi-sub-ui.o \ mpi-div.o \ - mpi-inv.o \ mpi-mod.o \ mpi-mul.o \ mpih-cmp.o \ diff --git a/lib/crypto/mpi/ec.c b/lib/crypto/mpi/ec.c deleted file mode 100644 index e16dca1e23d5..000000000000 --- a/lib/crypto/mpi/ec.c +++ /dev/null @@ -1,1509 +0,0 @@ -/* ec.c - Elliptic Curve functions - * Copyright (C) 2007 Free Software Foundation, Inc. - * Copyright (C) 2013 g10 Code GmbH - * - * This file is part of Libgcrypt. - * - * Libgcrypt is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as - * published by the Free Software Foundation; either version 2.1 of - * the License, or (at your option) any later version. - * - * Libgcrypt is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#include "mpi-internal.h" -#include "longlong.h" - -#define point_init(a) mpi_point_init((a)) -#define point_free(a) mpi_point_free_parts((a)) - -#define log_error(fmt, ...) pr_err(fmt, ##__VA_ARGS__) -#define log_fatal(fmt, ...) pr_err(fmt, ##__VA_ARGS__) - -#define DIM(v) (sizeof(v)/sizeof((v)[0])) - - -/* Create a new point option. NBITS gives the size in bits of one - * coordinate; it is only used to pre-allocate some resources and - * might also be passed as 0 to use a default value. - */ -MPI_POINT mpi_point_new(unsigned int nbits) -{ - MPI_POINT p; - - (void)nbits; /* Currently not used. */ - - p = kmalloc(sizeof(*p), GFP_KERNEL); - if (p) - mpi_point_init(p); - return p; -} -EXPORT_SYMBOL_GPL(mpi_point_new); - -/* Release the point object P. P may be NULL. */ -void mpi_point_release(MPI_POINT p) -{ - if (p) { - mpi_point_free_parts(p); - kfree(p); - } -} -EXPORT_SYMBOL_GPL(mpi_point_release); - -/* Initialize the fields of a point object. gcry_mpi_point_free_parts - * may be used to release the fields. - */ -void mpi_point_init(MPI_POINT p) -{ - p->x = mpi_new(0); - p->y = mpi_new(0); - p->z = mpi_new(0); -} -EXPORT_SYMBOL_GPL(mpi_point_init); - -/* Release the parts of a point object. */ -void mpi_point_free_parts(MPI_POINT p) -{ - mpi_free(p->x); p->x = NULL; - mpi_free(p->y); p->y = NULL; - mpi_free(p->z); p->z = NULL; -} -EXPORT_SYMBOL_GPL(mpi_point_free_parts); - -/* Set the value from S into D. */ -static void point_set(MPI_POINT d, MPI_POINT s) -{ - mpi_set(d->x, s->x); - mpi_set(d->y, s->y); - mpi_set(d->z, s->z); -} - -static void point_resize(MPI_POINT p, struct mpi_ec_ctx *ctx) -{ - size_t nlimbs = ctx->p->nlimbs; - - mpi_resize(p->x, nlimbs); - p->x->nlimbs = nlimbs; - mpi_resize(p->z, nlimbs); - p->z->nlimbs = nlimbs; - - if (ctx->model != MPI_EC_MONTGOMERY) { - mpi_resize(p->y, nlimbs); - p->y->nlimbs = nlimbs; - } -} - -static void point_swap_cond(MPI_POINT d, MPI_POINT s, unsigned long swap, - struct mpi_ec_ctx *ctx) -{ - mpi_swap_cond(d->x, s->x, swap); - if (ctx->model != MPI_EC_MONTGOMERY) - mpi_swap_cond(d->y, s->y, swap); - mpi_swap_cond(d->z, s->z, swap); -} - - -/* W = W mod P. */ -static void ec_mod(MPI w, struct mpi_ec_ctx *ec) -{ - if (ec->t.p_barrett) - mpi_mod_barrett(w, w, ec->t.p_barrett); - else - mpi_mod(w, w, ec->p); -} - -static void ec_addm(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx) -{ - mpi_add(w, u, v); - ec_mod(w, ctx); -} - -static void ec_subm(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ec) -{ - mpi_sub(w, u, v); - while (w->sign) - mpi_add(w, w, ec->p); - /*ec_mod(w, ec);*/ -} - -static void ec_mulm(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx) -{ - mpi_mul(w, u, v); - ec_mod(w, ctx); -} - -/* W = 2 * U mod P. */ -static void ec_mul2(MPI w, MPI u, struct mpi_ec_ctx *ctx) -{ - mpi_lshift(w, u, 1); - ec_mod(w, ctx); -} - -static void ec_powm(MPI w, const MPI b, const MPI e, - struct mpi_ec_ctx *ctx) -{ - mpi_powm(w, b, e, ctx->p); - /* mpi_abs(w); */ -} - -/* Shortcut for - * ec_powm(B, B, mpi_const(MPI_C_TWO), ctx); - * for easier optimization. - */ -static void ec_pow2(MPI w, const MPI b, struct mpi_ec_ctx *ctx) -{ - /* Using mpi_mul is slightly faster (at least on amd64). */ - /* mpi_powm(w, b, mpi_const(MPI_C_TWO), ctx->p); */ - ec_mulm(w, b, b, ctx); -} - -/* Shortcut for - * ec_powm(B, B, mpi_const(MPI_C_THREE), ctx); - * for easier optimization. - */ -static void ec_pow3(MPI w, const MPI b, struct mpi_ec_ctx *ctx) -{ - mpi_powm(w, b, mpi_const(MPI_C_THREE), ctx->p); -} - -static void ec_invm(MPI x, MPI a, struct mpi_ec_ctx *ctx) -{ - if (!mpi_invm(x, a, ctx->p)) - log_error("ec_invm: inverse does not exist:\n"); -} - -static void mpih_set_cond(mpi_ptr_t wp, mpi_ptr_t up, - mpi_size_t usize, unsigned long set) -{ - mpi_size_t i; - mpi_limb_t mask = ((mpi_limb_t)0) - set; - mpi_limb_t x; - - for (i = 0; i < usize; i++) { - x = mask & (wp[i] ^ up[i]); - wp[i] = wp[i] ^ x; - } -} - -/* Routines for 2^255 - 19. */ - -#define LIMB_SIZE_25519 ((256+BITS_PER_MPI_LIMB-1)/BITS_PER_MPI_LIMB) - -static void ec_addm_25519(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx) -{ - mpi_ptr_t wp, up, vp; - mpi_size_t wsize = LIMB_SIZE_25519; - mpi_limb_t n[LIMB_SIZE_25519]; - mpi_limb_t borrow; - - if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize) - log_bug("addm_25519: different sizes\n"); - - memset(n, 0, sizeof(n)); - up = u->d; - vp = v->d; - wp = w->d; - - mpihelp_add_n(wp, up, vp, wsize); - borrow = mpihelp_sub_n(wp, wp, ctx->p->d, wsize); - mpih_set_cond(n, ctx->p->d, wsize, (borrow != 0UL)); - mpihelp_add_n(wp, wp, n, wsize); - wp[LIMB_SIZE_25519-1] &= ~((mpi_limb_t)1 << (255 % BITS_PER_MPI_LIMB)); -} - -static void ec_subm_25519(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx) -{ - mpi_ptr_t wp, up, vp; - mpi_size_t wsize = LIMB_SIZE_25519; - mpi_limb_t n[LIMB_SIZE_25519]; - mpi_limb_t borrow; - - if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize) - log_bug("subm_25519: different sizes\n"); - - memset(n, 0, sizeof(n)); - up = u->d; - vp = v->d; - wp = w->d; - - borrow = mpihelp_sub_n(wp, up, vp, wsize); - mpih_set_cond(n, ctx->p->d, wsize, (borrow != 0UL)); - mpihelp_add_n(wp, wp, n, wsize); - wp[LIMB_SIZE_25519-1] &= ~((mpi_limb_t)1 << (255 % BITS_PER_MPI_LIMB)); -} - -static void ec_mulm_25519(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx) -{ - mpi_ptr_t wp, up, vp; - mpi_size_t wsize = LIMB_SIZE_25519; - mpi_limb_t n[LIMB_SIZE_25519*2]; - mpi_limb_t m[LIMB_SIZE_25519+1]; - mpi_limb_t cy; - int msb; - - (void)ctx; - if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize) - log_bug("mulm_25519: different sizes\n"); - - up = u->d; - vp = v->d; - wp = w->d; - - mpihelp_mul_n(n, up, vp, wsize); - memcpy(wp, n, wsize * BYTES_PER_MPI_LIMB); - wp[LIMB_SIZE_25519-1] &= ~((mpi_limb_t)1 << (255 % BITS_PER_MPI_LIMB)); - - memcpy(m, n+LIMB_SIZE_25519-1, (wsize+1) * BYTES_PER_MPI_LIMB); - mpihelp_rshift(m, m, LIMB_SIZE_25519+1, (255 % BITS_PER_MPI_LIMB)); - - memcpy(n, m, wsize * BYTES_PER_MPI_LIMB); - cy = mpihelp_lshift(m, m, LIMB_SIZE_25519, 4); - m[LIMB_SIZE_25519] = cy; - cy = mpihelp_add_n(m, m, n, wsize); - m[LIMB_SIZE_25519] += cy; - cy = mpihelp_add_n(m, m, n, wsize); - m[LIMB_SIZE_25519] += cy; - cy = mpihelp_add_n(m, m, n, wsize); - m[LIMB_SIZE_25519] += cy; - - cy = mpihelp_add_n(wp, wp, m, wsize); - m[LIMB_SIZE_25519] += cy; - - memset(m, 0, wsize * BYTES_PER_MPI_LIMB); - msb = (wp[LIMB_SIZE_25519-1] >> (255 % BITS_PER_MPI_LIMB)); - m[0] = (m[LIMB_SIZE_25519] * 2 + msb) * 19; - wp[LIMB_SIZE_25519-1] &= ~((mpi_limb_t)1 << (255 % BITS_PER_MPI_LIMB)); - mpihelp_add_n(wp, wp, m, wsize); - - m[0] = 0; - cy = mpihelp_sub_n(wp, wp, ctx->p->d, wsize); - mpih_set_cond(m, ctx->p->d, wsize, (cy != 0UL)); - mpihelp_add_n(wp, wp, m, wsize); -} - -static void ec_mul2_25519(MPI w, MPI u, struct mpi_ec_ctx *ctx) -{ - ec_addm_25519(w, u, u, ctx); -} - -static void ec_pow2_25519(MPI w, const MPI b, struct mpi_ec_ctx *ctx) -{ - ec_mulm_25519(w, b, b, ctx); -} - -/* Routines for 2^448 - 2^224 - 1. */ - -#define LIMB_SIZE_448 ((448+BITS_PER_MPI_LIMB-1)/BITS_PER_MPI_LIMB) -#define LIMB_SIZE_HALF_448 ((LIMB_SIZE_448+1)/2) - -static void ec_addm_448(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx) -{ - mpi_ptr_t wp, up, vp; - mpi_size_t wsize = LIMB_SIZE_448; - mpi_limb_t n[LIMB_SIZE_448]; - mpi_limb_t cy; - - if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize) - log_bug("addm_448: different sizes\n"); - - memset(n, 0, sizeof(n)); - up = u->d; - vp = v->d; - wp = w->d; - - cy = mpihelp_add_n(wp, up, vp, wsize); - mpih_set_cond(n, ctx->p->d, wsize, (cy != 0UL)); - mpihelp_sub_n(wp, wp, n, wsize); -} - -static void ec_subm_448(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx) -{ - mpi_ptr_t wp, up, vp; - mpi_size_t wsize = LIMB_SIZE_448; - mpi_limb_t n[LIMB_SIZE_448]; - mpi_limb_t borrow; - - if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize) - log_bug("subm_448: different sizes\n"); - - memset(n, 0, sizeof(n)); - up = u->d; - vp = v->d; - wp = w->d; - - borrow = mpihelp_sub_n(wp, up, vp, wsize); - mpih_set_cond(n, ctx->p->d, wsize, (borrow != 0UL)); - mpihelp_add_n(wp, wp, n, wsize); -} - -static void ec_mulm_448(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx) -{ - mpi_ptr_t wp, up, vp; - mpi_size_t wsize = LIMB_SIZE_448; - mpi_limb_t n[LIMB_SIZE_448*2]; - mpi_limb_t a2[LIMB_SIZE_HALF_448]; - mpi_limb_t a3[LIMB_SIZE_HALF_448]; - mpi_limb_t b0[LIMB_SIZE_HALF_448]; - mpi_limb_t b1[LIMB_SIZE_HALF_448]; - mpi_limb_t cy; - int i; -#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2) - mpi_limb_t b1_rest, a3_rest; -#endif - - if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize) - log_bug("mulm_448: different sizes\n"); - - up = u->d; - vp = v->d; - wp = w->d; - - mpihelp_mul_n(n, up, vp, wsize); - - for (i = 0; i < (wsize + 1) / 2; i++) { - b0[i] = n[i]; - b1[i] = n[i+wsize/2]; - a2[i] = n[i+wsize]; - a3[i] = n[i+wsize+wsize/2]; - } - -#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2) - b0[LIMB_SIZE_HALF_448-1] &= ((mpi_limb_t)1UL << 32)-1; - a2[LIMB_SIZE_HALF_448-1] &= ((mpi_limb_t)1UL << 32)-1; - - b1_rest = 0; - a3_rest = 0; - - for (i = (wsize + 1) / 2 - 1; i >= 0; i--) { - mpi_limb_t b1v, a3v; - b1v = b1[i]; - a3v = a3[i]; - b1[i] = (b1_rest << 32) | (b1v >> 32); - a3[i] = (a3_rest << 32) | (a3v >> 32); - b1_rest = b1v & (((mpi_limb_t)1UL << 32)-1); - a3_rest = a3v & (((mpi_limb_t)1UL << 32)-1); - } -#endif - - cy = mpihelp_add_n(b0, b0, a2, LIMB_SIZE_HALF_448); - cy += mpihelp_add_n(b0, b0, a3, LIMB_SIZE_HALF_448); - for (i = 0; i < (wsize + 1) / 2; i++) - wp[i] = b0[i]; -#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2) - wp[LIMB_SIZE_HALF_448-1] &= (((mpi_limb_t)1UL << 32)-1); -#endif - -#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2) - cy = b0[LIMB_SIZE_HALF_448-1] >> 32; -#endif - - cy = mpihelp_add_1(b1, b1, LIMB_SIZE_HALF_448, cy); - cy += mpihelp_add_n(b1, b1, a2, LIMB_SIZE_HALF_448); - cy += mpihelp_add_n(b1, b1, a3, LIMB_SIZE_HALF_448); - cy += mpihelp_add_n(b1, b1, a3, LIMB_SIZE_HALF_448); -#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2) - b1_rest = 0; - for (i = (wsize + 1) / 2 - 1; i >= 0; i--) { - mpi_limb_t b1v = b1[i]; - b1[i] = (b1_rest << 32) | (b1v >> 32); - b1_rest = b1v & (((mpi_limb_t)1UL << 32)-1); - } - wp[LIMB_SIZE_HALF_448-1] |= (b1_rest << 32); -#endif - for (i = 0; i < wsize / 2; i++) - wp[i+(wsize + 1) / 2] = b1[i]; - -#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2) - cy = b1[LIMB_SIZE_HALF_448-1]; -#endif - - memset(n, 0, wsize * BYTES_PER_MPI_LIMB); - -#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2) - n[LIMB_SIZE_HALF_448-1] = cy << 32; -#else - n[LIMB_SIZE_HALF_448] = cy; -#endif - n[0] = cy; - mpihelp_add_n(wp, wp, n, wsize); - - memset(n, 0, wsize * BYTES_PER_MPI_LIMB); - cy = mpihelp_sub_n(wp, wp, ctx->p->d, wsize); - mpih_set_cond(n, ctx->p->d, wsize, (cy != 0UL)); - mpihelp_add_n(wp, wp, n, wsize); -} - -static void ec_mul2_448(MPI w, MPI u, struct mpi_ec_ctx *ctx) -{ - ec_addm_448(w, u, u, ctx); -} - -static void ec_pow2_448(MPI w, const MPI b, struct mpi_ec_ctx *ctx) -{ - ec_mulm_448(w, b, b, ctx); -} - -struct field_table { - const char *p; - - /* computation routines for the field. */ - void (*addm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx); - void (*subm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx); - void (*mulm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx); - void (*mul2)(MPI w, MPI u, struct mpi_ec_ctx *ctx); - void (*pow2)(MPI w, const MPI b, struct mpi_ec_ctx *ctx); -}; - -static const struct field_table field_table[] = { - { - "0x7FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFED", - ec_addm_25519, - ec_subm_25519, - ec_mulm_25519, - ec_mul2_25519, - ec_pow2_25519 - }, - { - "0xFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFE" - "FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF", - ec_addm_448, - ec_subm_448, - ec_mulm_448, - ec_mul2_448, - ec_pow2_448 - }, - { NULL, NULL, NULL, NULL, NULL, NULL }, -}; - -/* Force recomputation of all helper variables. */ -static void mpi_ec_get_reset(struct mpi_ec_ctx *ec) -{ - ec->t.valid.a_is_pminus3 = 0; - ec->t.valid.two_inv_p = 0; -} - -/* Accessor for helper variable. */ -static int ec_get_a_is_pminus3(struct mpi_ec_ctx *ec) -{ - MPI tmp; - - if (!ec->t.valid.a_is_pminus3) { - ec->t.valid.a_is_pminus3 = 1; - tmp = mpi_alloc_like(ec->p); - mpi_sub_ui(tmp, ec->p, 3); - ec->t.a_is_pminus3 = !mpi_cmp(ec->a, tmp); - mpi_free(tmp); - } - - return ec->t.a_is_pminus3; -} - -/* Accessor for helper variable. */ -static MPI ec_get_two_inv_p(struct mpi_ec_ctx *ec) -{ - if (!ec->t.valid.two_inv_p) { - ec->t.valid.two_inv_p = 1; - if (!ec->t.two_inv_p) - ec->t.two_inv_p = mpi_alloc(0); - ec_invm(ec->t.two_inv_p, mpi_const(MPI_C_TWO), ec); - } - return ec->t.two_inv_p; -} - -static const char *const curve25519_bad_points[] = { - "0x7fffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffed", - "0x0000000000000000000000000000000000000000000000000000000000000000", - "0x0000000000000000000000000000000000000000000000000000000000000001", - "0x00b8495f16056286fdb1329ceb8d09da6ac49ff1fae35616aeb8413b7c7aebe0", - "0x57119fd0dd4e22d8868e1c58c45c44045bef839c55b1d0b1248c50a3bc959c5f", - "0x7fffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffec", - "0x7fffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffee", - NULL -}; - -static const char *const curve448_bad_points[] = { - "0xfffffffffffffffffffffffffffffffffffffffffffffffffffffffe" - "ffffffffffffffffffffffffffffffffffffffffffffffffffffffff", - "0x00000000000000000000000000000000000000000000000000000000" - "00000000000000000000000000000000000000000000000000000000", - "0x00000000000000000000000000000000000000000000000000000000" - "00000000000000000000000000000000000000000000000000000001", - "0xfffffffffffffffffffffffffffffffffffffffffffffffffffffffe" - "fffffffffffffffffffffffffffffffffffffffffffffffffffffffe", - "0xffffffffffffffffffffffffffffffffffffffffffffffffffffffff" - "00000000000000000000000000000000000000000000000000000000", - NULL -}; - -static const char *const *bad_points_table[] = { - curve25519_bad_points, - curve448_bad_points, -}; - -static void mpi_ec_coefficient_normalize(MPI a, MPI p) -{ - if (a->sign) { - mpi_resize(a, p->nlimbs); - mpihelp_sub_n(a->d, p->d, a->d, p->nlimbs); - a->nlimbs = p->nlimbs; - a->sign = 0; - } -} - -/* This function initialized a context for elliptic curve based on the - * field GF(p). P is the prime specifying this field, A is the first - * coefficient. CTX is expected to be zeroized. - */ -void mpi_ec_init(struct mpi_ec_ctx *ctx, enum gcry_mpi_ec_models model, - enum ecc_dialects dialect, - int flags, MPI p, MPI a, MPI b) -{ - int i; - static int use_barrett = -1 /* TODO: 1 or -1 */; - - mpi_ec_coefficient_normalize(a, p); - mpi_ec_coefficient_normalize(b, p); - - /* Fixme: Do we want to check some constraints? e.g. a < p */ - - ctx->model = model; - ctx->dialect = dialect; - ctx->flags = flags; - if (dialect == ECC_DIALECT_ED25519) - ctx->nbits = 256; - else - ctx->nbits = mpi_get_nbits(p); - ctx->p = mpi_copy(p); - ctx->a = mpi_copy(a); - ctx->b = mpi_copy(b); - - ctx->d = NULL; - ctx->t.two_inv_p = NULL; - - ctx->t.p_barrett = use_barrett > 0 ? mpi_barrett_init(ctx->p, 0) : NULL; - - mpi_ec_get_reset(ctx); - - if (model == MPI_EC_MONTGOMERY) { - for (i = 0; i < DIM(bad_points_table); i++) { - MPI p_candidate = mpi_scanval(bad_points_table[i][0]); - int match_p = !mpi_cmp(ctx->p, p_candidate); - int j; - - mpi_free(p_candidate); - if (!match_p) - continue; - - for (j = 0; i < DIM(ctx->t.scratch) && bad_points_table[i][j]; j++) - ctx->t.scratch[j] = mpi_scanval(bad_points_table[i][j]); - } - } else { - /* Allocate scratch variables. */ - for (i = 0; i < DIM(ctx->t.scratch); i++) - ctx->t.scratch[i] = mpi_alloc_like(ctx->p); - } - - ctx->addm = ec_addm; - ctx->subm = ec_subm; - ctx->mulm = ec_mulm; - ctx->mul2 = ec_mul2; - ctx->pow2 = ec_pow2; - - for (i = 0; field_table[i].p; i++) { - MPI f_p; - - f_p = mpi_scanval(field_table[i].p); - if (!f_p) - break; - - if (!mpi_cmp(p, f_p)) { - ctx->addm = field_table[i].addm; - ctx->subm = field_table[i].subm; - ctx->mulm = field_table[i].mulm; - ctx->mul2 = field_table[i].mul2; - ctx->pow2 = field_table[i].pow2; - mpi_free(f_p); - - mpi_resize(ctx->a, ctx->p->nlimbs); - ctx->a->nlimbs = ctx->p->nlimbs; - - mpi_resize(ctx->b, ctx->p->nlimbs); - ctx->b->nlimbs = ctx->p->nlimbs; - - for (i = 0; i < DIM(ctx->t.scratch) && ctx->t.scratch[i]; i++) - ctx->t.scratch[i]->nlimbs = ctx->p->nlimbs; - - break; - } - - mpi_free(f_p); - } -} -EXPORT_SYMBOL_GPL(mpi_ec_init); - -void mpi_ec_deinit(struct mpi_ec_ctx *ctx) -{ - int i; - - mpi_barrett_free(ctx->t.p_barrett); - - /* Domain parameter. */ - mpi_free(ctx->p); - mpi_free(ctx->a); - mpi_free(ctx->b); - mpi_point_release(ctx->G); - mpi_free(ctx->n); - - /* The key. */ - mpi_point_release(ctx->Q); - mpi_free(ctx->d); - - /* Private data of ec.c. */ - mpi_free(ctx->t.two_inv_p); - - for (i = 0; i < DIM(ctx->t.scratch); i++) - mpi_free(ctx->t.scratch[i]); -} -EXPORT_SYMBOL_GPL(mpi_ec_deinit); - -/* Compute the affine coordinates from the projective coordinates in - * POINT. Set them into X and Y. If one coordinate is not required, - * X or Y may be passed as NULL. CTX is the usual context. Returns: 0 - * on success or !0 if POINT is at infinity. - */ -int mpi_ec_get_affine(MPI x, MPI y, MPI_POINT point, struct mpi_ec_ctx *ctx) -{ - if (!mpi_cmp_ui(point->z, 0)) - return -1; - - switch (ctx->model) { - case MPI_EC_WEIERSTRASS: /* Using Jacobian coordinates. */ - { - MPI z1, z2, z3; - - z1 = mpi_new(0); - z2 = mpi_new(0); - ec_invm(z1, point->z, ctx); /* z1 = z^(-1) mod p */ - ec_mulm(z2, z1, z1, ctx); /* z2 = z^(-2) mod p */ - - if (x) - ec_mulm(x, point->x, z2, ctx); - - if (y) { - z3 = mpi_new(0); - ec_mulm(z3, z2, z1, ctx); /* z3 = z^(-3) mod p */ - ec_mulm(y, point->y, z3, ctx); - mpi_free(z3); - } - - mpi_free(z2); - mpi_free(z1); - } - return 0; - - case MPI_EC_MONTGOMERY: - { - if (x) - mpi_set(x, point->x); - - if (y) { - log_fatal("%s: Getting Y-coordinate on %s is not supported\n", - "mpi_ec_get_affine", "Montgomery"); - return -1; - } - } - return 0; - - case MPI_EC_EDWARDS: - { - MPI z; - - z = mpi_new(0); - ec_invm(z, point->z, ctx); - - mpi_resize(z, ctx->p->nlimbs); - z->nlimbs = ctx->p->nlimbs; - - if (x) { - mpi_resize(x, ctx->p->nlimbs); - x->nlimbs = ctx->p->nlimbs; - ctx->mulm(x, point->x, z, ctx); - } - if (y) { - mpi_resize(y, ctx->p->nlimbs); - y->nlimbs = ctx->p->nlimbs; - ctx->mulm(y, point->y, z, ctx); - } - - mpi_free(z); - } - return 0; - - default: - return -1; - } -} -EXPORT_SYMBOL_GPL(mpi_ec_get_affine); - -/* RESULT = 2 * POINT (Weierstrass version). */ -static void dup_point_weierstrass(MPI_POINT result, - MPI_POINT point, struct mpi_ec_ctx *ctx) -{ -#define x3 (result->x) -#define y3 (result->y) -#define z3 (result->z) -#define t1 (ctx->t.scratch[0]) -#define t2 (ctx->t.scratch[1]) -#define t3 (ctx->t.scratch[2]) -#define l1 (ctx->t.scratch[3]) -#define l2 (ctx->t.scratch[4]) -#define l3 (ctx->t.scratch[5]) - - if (!mpi_cmp_ui(point->y, 0) || !mpi_cmp_ui(point->z, 0)) { - /* P_y == 0 || P_z == 0 => [1:1:0] */ - mpi_set_ui(x3, 1); - mpi_set_ui(y3, 1); - mpi_set_ui(z3, 0); - } else { - if (ec_get_a_is_pminus3(ctx)) { - /* Use the faster case. */ - /* L1 = 3(X - Z^2)(X + Z^2) */ - /* T1: used for Z^2. */ - /* T2: used for the right term. */ - ec_pow2(t1, point->z, ctx); - ec_subm(l1, point->x, t1, ctx); - ec_mulm(l1, l1, mpi_const(MPI_C_THREE), ctx); - ec_addm(t2, point->x, t1, ctx); - ec_mulm(l1, l1, t2, ctx); - } else { - /* Standard case. */ - /* L1 = 3X^2 + aZ^4 */ - /* T1: used for aZ^4. */ - ec_pow2(l1, point->x, ctx); - ec_mulm(l1, l1, mpi_const(MPI_C_THREE), ctx); - ec_powm(t1, point->z, mpi_const(MPI_C_FOUR), ctx); - ec_mulm(t1, t1, ctx->a, ctx); - ec_addm(l1, l1, t1, ctx); - } - /* Z3 = 2YZ */ - ec_mulm(z3, point->y, point->z, ctx); - ec_mul2(z3, z3, ctx); - - /* L2 = 4XY^2 */ - /* T2: used for Y2; required later. */ - ec_pow2(t2, point->y, ctx); - ec_mulm(l2, t2, point->x, ctx); - ec_mulm(l2, l2, mpi_const(MPI_C_FOUR), ctx); - - /* X3 = L1^2 - 2L2 */ - /* T1: used for L2^2. */ - ec_pow2(x3, l1, ctx); - ec_mul2(t1, l2, ctx); - ec_subm(x3, x3, t1, ctx); - - /* L3 = 8Y^4 */ - /* T2: taken from above. */ - ec_pow2(t2, t2, ctx); - ec_mulm(l3, t2, mpi_const(MPI_C_EIGHT), ctx); - - /* Y3 = L1(L2 - X3) - L3 */ - ec_subm(y3, l2, x3, ctx); - ec_mulm(y3, y3, l1, ctx); - ec_subm(y3, y3, l3, ctx); - } - -#undef x3 -#undef y3 -#undef z3 -#undef t1 -#undef t2 -#undef t3 -#undef l1 -#undef l2 -#undef l3 -} - -/* RESULT = 2 * POINT (Montgomery version). */ -static void dup_point_montgomery(MPI_POINT result, - MPI_POINT point, struct mpi_ec_ctx *ctx) -{ - (void)result; - (void)point; - (void)ctx; - log_fatal("%s: %s not yet supported\n", - "mpi_ec_dup_point", "Montgomery"); -} - -/* RESULT = 2 * POINT (Twisted Edwards version). */ -static void dup_point_edwards(MPI_POINT result, - MPI_POINT point, struct mpi_ec_ctx *ctx) -{ -#define X1 (point->x) -#define Y1 (point->y) -#define Z1 (point->z) -#define X3 (result->x) -#define Y3 (result->y) -#define Z3 (result->z) -#define B (ctx->t.scratch[0]) -#define C (ctx->t.scratch[1]) -#define D (ctx->t.scratch[2]) -#define E (ctx->t.scratch[3]) -#define F (ctx->t.scratch[4]) -#define H (ctx->t.scratch[5]) -#define J (ctx->t.scratch[6]) - - /* Compute: (X_3 : Y_3 : Z_3) = 2( X_1 : Y_1 : Z_1 ) */ - - /* B = (X_1 + Y_1)^2 */ - ctx->addm(B, X1, Y1, ctx); - ctx->pow2(B, B, ctx); - - /* C = X_1^2 */ - /* D = Y_1^2 */ - ctx->pow2(C, X1, ctx); - ctx->pow2(D, Y1, ctx); - - /* E = aC */ - if (ctx->dialect == ECC_DIALECT_ED25519) - ctx->subm(E, ctx->p, C, ctx); - else - ctx->mulm(E, ctx->a, C, ctx); - - /* F = E + D */ - ctx->addm(F, E, D, ctx); - - /* H = Z_1^2 */ - ctx->pow2(H, Z1, ctx); - - /* J = F - 2H */ - ctx->mul2(J, H, ctx); - ctx->subm(J, F, J, ctx); - - /* X_3 = (B - C - D) · J */ - ctx->subm(X3, B, C, ctx); - ctx->subm(X3, X3, D, ctx); - ctx->mulm(X3, X3, J, ctx); - - /* Y_3 = F · (E - D) */ - ctx->subm(Y3, E, D, ctx); - ctx->mulm(Y3, Y3, F, ctx); - - /* Z_3 = F · J */ - ctx->mulm(Z3, F, J, ctx); - -#undef X1 -#undef Y1 -#undef Z1 -#undef X3 -#undef Y3 -#undef Z3 -#undef B -#undef C -#undef D -#undef E -#undef F -#undef H -#undef J -} - -/* RESULT = 2 * POINT */ -static void -mpi_ec_dup_point(MPI_POINT result, MPI_POINT point, struct mpi_ec_ctx *ctx) -{ - switch (ctx->model) { - case MPI_EC_WEIERSTRASS: - dup_point_weierstrass(result, point, ctx); - break; - case MPI_EC_MONTGOMERY: - dup_point_montgomery(result, point, ctx); - break; - case MPI_EC_EDWARDS: - dup_point_edwards(result, point, ctx); - break; - } -} - -/* RESULT = P1 + P2 (Weierstrass version).*/ -static void add_points_weierstrass(MPI_POINT result, - MPI_POINT p1, MPI_POINT p2, - struct mpi_ec_ctx *ctx) -{ -#define x1 (p1->x) -#define y1 (p1->y) -#define z1 (p1->z) -#define x2 (p2->x) -#define y2 (p2->y) -#define z2 (p2->z) -#define x3 (result->x) -#define y3 (result->y) -#define z3 (result->z) -#define l1 (ctx->t.scratch[0]) -#define l2 (ctx->t.scratch[1]) -#define l3 (ctx->t.scratch[2]) -#define l4 (ctx->t.scratch[3]) -#define l5 (ctx->t.scratch[4]) -#define l6 (ctx->t.scratch[5]) -#define l7 (ctx->t.scratch[6]) -#define l8 (ctx->t.scratch[7]) -#define l9 (ctx->t.scratch[8]) -#define t1 (ctx->t.scratch[9]) -#define t2 (ctx->t.scratch[10]) - - if ((!mpi_cmp(x1, x2)) && (!mpi_cmp(y1, y2)) && (!mpi_cmp(z1, z2))) { - /* Same point; need to call the duplicate function. */ - mpi_ec_dup_point(result, p1, ctx); - } else if (!mpi_cmp_ui(z1, 0)) { - /* P1 is at infinity. */ - mpi_set(x3, p2->x); - mpi_set(y3, p2->y); - mpi_set(z3, p2->z); - } else if (!mpi_cmp_ui(z2, 0)) { - /* P2 is at infinity. */ - mpi_set(x3, p1->x); - mpi_set(y3, p1->y); - mpi_set(z3, p1->z); - } else { - int z1_is_one = !mpi_cmp_ui(z1, 1); - int z2_is_one = !mpi_cmp_ui(z2, 1); - - /* l1 = x1 z2^2 */ - /* l2 = x2 z1^2 */ - if (z2_is_one) - mpi_set(l1, x1); - else { - ec_pow2(l1, z2, ctx); - ec_mulm(l1, l1, x1, ctx); - } - if (z1_is_one) - mpi_set(l2, x2); - else { - ec_pow2(l2, z1, ctx); - ec_mulm(l2, l2, x2, ctx); - } - /* l3 = l1 - l2 */ - ec_subm(l3, l1, l2, ctx); - /* l4 = y1 z2^3 */ - ec_powm(l4, z2, mpi_const(MPI_C_THREE), ctx); - ec_mulm(l4, l4, y1, ctx); - /* l5 = y2 z1^3 */ - ec_powm(l5, z1, mpi_const(MPI_C_THREE), ctx); - ec_mulm(l5, l5, y2, ctx); - /* l6 = l4 - l5 */ - ec_subm(l6, l4, l5, ctx); - - if (!mpi_cmp_ui(l3, 0)) { - if (!mpi_cmp_ui(l6, 0)) { - /* P1 and P2 are the same - use duplicate function. */ - mpi_ec_dup_point(result, p1, ctx); - } else { - /* P1 is the inverse of P2. */ - mpi_set_ui(x3, 1); - mpi_set_ui(y3, 1); - mpi_set_ui(z3, 0); - } - } else { - /* l7 = l1 + l2 */ - ec_addm(l7, l1, l2, ctx); - /* l8 = l4 + l5 */ - ec_addm(l8, l4, l5, ctx); - /* z3 = z1 z2 l3 */ - ec_mulm(z3, z1, z2, ctx); - ec_mulm(z3, z3, l3, ctx); - /* x3 = l6^2 - l7 l3^2 */ - ec_pow2(t1, l6, ctx); - ec_pow2(t2, l3, ctx); - ec_mulm(t2, t2, l7, ctx); - ec_subm(x3, t1, t2, ctx); - /* l9 = l7 l3^2 - 2 x3 */ - ec_mul2(t1, x3, ctx); - ec_subm(l9, t2, t1, ctx); - /* y3 = (l9 l6 - l8 l3^3)/2 */ - ec_mulm(l9, l9, l6, ctx); - ec_powm(t1, l3, mpi_const(MPI_C_THREE), ctx); /* fixme: Use saved value*/ - ec_mulm(t1, t1, l8, ctx); - ec_subm(y3, l9, t1, ctx); - ec_mulm(y3, y3, ec_get_two_inv_p(ctx), ctx); - } - } - -#undef x1 -#undef y1 -#undef z1 -#undef x2 -#undef y2 -#undef z2 -#undef x3 -#undef y3 -#undef z3 -#undef l1 -#undef l2 -#undef l3 -#undef l4 -#undef l5 -#undef l6 -#undef l7 -#undef l8 -#undef l9 -#undef t1 -#undef t2 -} - -/* RESULT = P1 + P2 (Montgomery version).*/ -static void add_points_montgomery(MPI_POINT result, - MPI_POINT p1, MPI_POINT p2, - struct mpi_ec_ctx *ctx) -{ - (void)result; - (void)p1; - (void)p2; - (void)ctx; - log_fatal("%s: %s not yet supported\n", - "mpi_ec_add_points", "Montgomery"); -} - -/* RESULT = P1 + P2 (Twisted Edwards version).*/ -static void add_points_edwards(MPI_POINT result, - MPI_POINT p1, MPI_POINT p2, - struct mpi_ec_ctx *ctx) -{ -#define X1 (p1->x) -#define Y1 (p1->y) -#define Z1 (p1->z) -#define X2 (p2->x) -#define Y2 (p2->y) -#define Z2 (p2->z) -#define X3 (result->x) -#define Y3 (result->y) -#define Z3 (result->z) -#define A (ctx->t.scratch[0]) -#define B (ctx->t.scratch[1]) -#define C (ctx->t.scratch[2]) -#define D (ctx->t.scratch[3]) -#define E (ctx->t.scratch[4]) -#define F (ctx->t.scratch[5]) -#define G (ctx->t.scratch[6]) -#define tmp (ctx->t.scratch[7]) - - point_resize(result, ctx); - - /* Compute: (X_3 : Y_3 : Z_3) = (X_1 : Y_1 : Z_1) + (X_2 : Y_2 : Z_3) */ - - /* A = Z1 · Z2 */ - ctx->mulm(A, Z1, Z2, ctx); - - /* B = A^2 */ - ctx->pow2(B, A, ctx); - - /* C = X1 · X2 */ - ctx->mulm(C, X1, X2, ctx); - - /* D = Y1 · Y2 */ - ctx->mulm(D, Y1, Y2, ctx); - - /* E = d · C · D */ - ctx->mulm(E, ctx->b, C, ctx); - ctx->mulm(E, E, D, ctx); - - /* F = B - E */ - ctx->subm(F, B, E, ctx); - - /* G = B + E */ - ctx->addm(G, B, E, ctx); - - /* X_3 = A · F · ((X_1 + Y_1) · (X_2 + Y_2) - C - D) */ - ctx->addm(tmp, X1, Y1, ctx); - ctx->addm(X3, X2, Y2, ctx); - ctx->mulm(X3, X3, tmp, ctx); - ctx->subm(X3, X3, C, ctx); - ctx->subm(X3, X3, D, ctx); - ctx->mulm(X3, X3, F, ctx); - ctx->mulm(X3, X3, A, ctx); - - /* Y_3 = A · G · (D - aC) */ - if (ctx->dialect == ECC_DIALECT_ED25519) { - ctx->addm(Y3, D, C, ctx); - } else { - ctx->mulm(Y3, ctx->a, C, ctx); - ctx->subm(Y3, D, Y3, ctx); - } - ctx->mulm(Y3, Y3, G, ctx); - ctx->mulm(Y3, Y3, A, ctx); - - /* Z_3 = F · G */ - ctx->mulm(Z3, F, G, ctx); - - -#undef X1 -#undef Y1 -#undef Z1 -#undef X2 -#undef Y2 -#undef Z2 -#undef X3 -#undef Y3 -#undef Z3 -#undef A -#undef B -#undef C -#undef D -#undef E -#undef F -#undef G -#undef tmp -} - -/* Compute a step of Montgomery Ladder (only use X and Z in the point). - * Inputs: P1, P2, and x-coordinate of DIF = P1 - P1. - * Outputs: PRD = 2 * P1 and SUM = P1 + P2. - */ -static void montgomery_ladder(MPI_POINT prd, MPI_POINT sum, - MPI_POINT p1, MPI_POINT p2, MPI dif_x, - struct mpi_ec_ctx *ctx) -{ - ctx->addm(sum->x, p2->x, p2->z, ctx); - ctx->subm(p2->z, p2->x, p2->z, ctx); - ctx->addm(prd->x, p1->x, p1->z, ctx); - ctx->subm(p1->z, p1->x, p1->z, ctx); - ctx->mulm(p2->x, p1->z, sum->x, ctx); - ctx->mulm(p2->z, prd->x, p2->z, ctx); - ctx->pow2(p1->x, prd->x, ctx); - ctx->pow2(p1->z, p1->z, ctx); - ctx->addm(sum->x, p2->x, p2->z, ctx); - ctx->subm(p2->z, p2->x, p2->z, ctx); - ctx->mulm(prd->x, p1->x, p1->z, ctx); - ctx->subm(p1->z, p1->x, p1->z, ctx); - ctx->pow2(sum->x, sum->x, ctx); - ctx->pow2(sum->z, p2->z, ctx); - ctx->mulm(prd->z, p1->z, ctx->a, ctx); /* CTX->A: (a-2)/4 */ - ctx->mulm(sum->z, sum->z, dif_x, ctx); - ctx->addm(prd->z, p1->x, prd->z, ctx); - ctx->mulm(prd->z, prd->z, p1->z, ctx); -} - -/* RESULT = P1 + P2 */ -void mpi_ec_add_points(MPI_POINT result, - MPI_POINT p1, MPI_POINT p2, - struct mpi_ec_ctx *ctx) -{ - switch (ctx->model) { - case MPI_EC_WEIERSTRASS: - add_points_weierstrass(result, p1, p2, ctx); - break; - case MPI_EC_MONTGOMERY: - add_points_montgomery(result, p1, p2, ctx); - break; - case MPI_EC_EDWARDS: - add_points_edwards(result, p1, p2, ctx); - break; - } -} -EXPORT_SYMBOL_GPL(mpi_ec_add_points); - -/* Scalar point multiplication - the main function for ECC. If takes - * an integer SCALAR and a POINT as well as the usual context CTX. - * RESULT will be set to the resulting point. - */ -void mpi_ec_mul_point(MPI_POINT result, - MPI scalar, MPI_POINT point, - struct mpi_ec_ctx *ctx) -{ - MPI x1, y1, z1, k, h, yy; - unsigned int i, loops; - struct gcry_mpi_point p1, p2, p1inv; - - if (ctx->model == MPI_EC_EDWARDS) { - /* Simple left to right binary method. Algorithm 3.27 from - * {author={Hankerson, Darrel and Menezes, Alfred J. and Vanstone, Scott}, - * title = {Guide to Elliptic Curve Cryptography}, - * year = {2003}, isbn = {038795273X}, - * url = {http://www.cacr.math.uwaterloo.ca/ecc/}, - * publisher = {Springer-Verlag New York, Inc.}} - */ - unsigned int nbits; - int j; - - if (mpi_cmp(scalar, ctx->p) >= 0) - nbits = mpi_get_nbits(scalar); - else - nbits = mpi_get_nbits(ctx->p); - - mpi_set_ui(result->x, 0); - mpi_set_ui(result->y, 1); - mpi_set_ui(result->z, 1); - point_resize(point, ctx); - - point_resize(result, ctx); - point_resize(point, ctx); - - for (j = nbits-1; j >= 0; j--) { - mpi_ec_dup_point(result, result, ctx); - if (mpi_test_bit(scalar, j)) - mpi_ec_add_points(result, result, point, ctx); - } - return; - } else if (ctx->model == MPI_EC_MONTGOMERY) { - unsigned int nbits; - int j; - struct gcry_mpi_point p1_, p2_; - MPI_POINT q1, q2, prd, sum; - unsigned long sw; - mpi_size_t rsize; - - /* Compute scalar point multiplication with Montgomery Ladder. - * Note that we don't use Y-coordinate in the points at all. - * RESULT->Y will be filled by zero. - */ - - nbits = mpi_get_nbits(scalar); - point_init(&p1); - point_init(&p2); - point_init(&p1_); - point_init(&p2_); - mpi_set_ui(p1.x, 1); - mpi_free(p2.x); - p2.x = mpi_copy(point->x); - mpi_set_ui(p2.z, 1); - - point_resize(&p1, ctx); - point_resize(&p2, ctx); - point_resize(&p1_, ctx); - point_resize(&p2_, ctx); - - mpi_resize(point->x, ctx->p->nlimbs); - point->x->nlimbs = ctx->p->nlimbs; - - q1 = &p1; - q2 = &p2; - prd = &p1_; - sum = &p2_; - - for (j = nbits-1; j >= 0; j--) { - MPI_POINT t; - - sw = mpi_test_bit(scalar, j); - point_swap_cond(q1, q2, sw, ctx); - montgomery_ladder(prd, sum, q1, q2, point->x, ctx); - point_swap_cond(prd, sum, sw, ctx); - t = q1; q1 = prd; prd = t; - t = q2; q2 = sum; sum = t; - } - - mpi_clear(result->y); - sw = (nbits & 1); - point_swap_cond(&p1, &p1_, sw, ctx); - - rsize = p1.z->nlimbs; - MPN_NORMALIZE(p1.z->d, rsize); - if (rsize == 0) { - mpi_set_ui(result->x, 1); - mpi_set_ui(result->z, 0); - } else { - z1 = mpi_new(0); - ec_invm(z1, p1.z, ctx); - ec_mulm(result->x, p1.x, z1, ctx); - mpi_set_ui(result->z, 1); - mpi_free(z1); - } - - point_free(&p1); - point_free(&p2); - point_free(&p1_); - point_free(&p2_); - return; - } - - x1 = mpi_alloc_like(ctx->p); - y1 = mpi_alloc_like(ctx->p); - h = mpi_alloc_like(ctx->p); - k = mpi_copy(scalar); - yy = mpi_copy(point->y); - - if (mpi_has_sign(k)) { - k->sign = 0; - ec_invm(yy, yy, ctx); - } - - if (!mpi_cmp_ui(point->z, 1)) { - mpi_set(x1, point->x); - mpi_set(y1, yy); - } else { - MPI z2, z3; - - z2 = mpi_alloc_like(ctx->p); - z3 = mpi_alloc_like(ctx->p); - ec_mulm(z2, point->z, point->z, ctx); - ec_mulm(z3, point->z, z2, ctx); - ec_invm(z2, z2, ctx); - ec_mulm(x1, point->x, z2, ctx); - ec_invm(z3, z3, ctx); - ec_mulm(y1, yy, z3, ctx); - mpi_free(z2); - mpi_free(z3); - } - z1 = mpi_copy(mpi_const(MPI_C_ONE)); - - mpi_mul(h, k, mpi_const(MPI_C_THREE)); /* h = 3k */ - loops = mpi_get_nbits(h); - if (loops < 2) { - /* If SCALAR is zero, the above mpi_mul sets H to zero and thus - * LOOPs will be zero. To avoid an underflow of I in the main - * loop we set LOOP to 2 and the result to (0,0,0). - */ - loops = 2; - mpi_clear(result->x); - mpi_clear(result->y); - mpi_clear(result->z); - } else { - mpi_set(result->x, point->x); - mpi_set(result->y, yy); - mpi_set(result->z, point->z); - } - mpi_free(yy); yy = NULL; - - p1.x = x1; x1 = NULL; - p1.y = y1; y1 = NULL; - p1.z = z1; z1 = NULL; - point_init(&p2); - point_init(&p1inv); - - /* Invert point: y = p - y mod p */ - point_set(&p1inv, &p1); - ec_subm(p1inv.y, ctx->p, p1inv.y, ctx); - - for (i = loops-2; i > 0; i--) { - mpi_ec_dup_point(result, result, ctx); - if (mpi_test_bit(h, i) == 1 && mpi_test_bit(k, i) == 0) { - point_set(&p2, result); - mpi_ec_add_points(result, &p2, &p1, ctx); - } - if (mpi_test_bit(h, i) == 0 && mpi_test_bit(k, i) == 1) { - point_set(&p2, result); - mpi_ec_add_points(result, &p2, &p1inv, ctx); - } - } - - point_free(&p1); - point_free(&p2); - point_free(&p1inv); - mpi_free(h); - mpi_free(k); -} -EXPORT_SYMBOL_GPL(mpi_ec_mul_point); - -/* Return true if POINT is on the curve described by CTX. */ -int mpi_ec_curve_point(MPI_POINT point, struct mpi_ec_ctx *ctx) -{ - int res = 0; - MPI x, y, w; - - x = mpi_new(0); - y = mpi_new(0); - w = mpi_new(0); - - /* Check that the point is in range. This needs to be done here and - * not after conversion to affine coordinates. - */ - if (mpi_cmpabs(point->x, ctx->p) >= 0) - goto leave; - if (mpi_cmpabs(point->y, ctx->p) >= 0) - goto leave; - if (mpi_cmpabs(point->z, ctx->p) >= 0) - goto leave; - - switch (ctx->model) { - case MPI_EC_WEIERSTRASS: - { - MPI xxx; - - if (mpi_ec_get_affine(x, y, point, ctx)) - goto leave; - - xxx = mpi_new(0); - - /* y^2 == x^3 + a·x + b */ - ec_pow2(y, y, ctx); - - ec_pow3(xxx, x, ctx); - ec_mulm(w, ctx->a, x, ctx); - ec_addm(w, w, ctx->b, ctx); - ec_addm(w, w, xxx, ctx); - - if (!mpi_cmp(y, w)) - res = 1; - - mpi_free(xxx); - } - break; - - case MPI_EC_MONTGOMERY: - { -#define xx y - /* With Montgomery curve, only X-coordinate is valid. */ - if (mpi_ec_get_affine(x, NULL, point, ctx)) - goto leave; - - /* The equation is: b * y^2 == x^3 + a · x^2 + x */ - /* We check if right hand is quadratic residue or not by - * Euler's criterion. - */ - /* CTX->A has (a-2)/4 and CTX->B has b^-1 */ - ec_mulm(w, ctx->a, mpi_const(MPI_C_FOUR), ctx); - ec_addm(w, w, mpi_const(MPI_C_TWO), ctx); - ec_mulm(w, w, x, ctx); - ec_pow2(xx, x, ctx); - ec_addm(w, w, xx, ctx); - ec_addm(w, w, mpi_const(MPI_C_ONE), ctx); - ec_mulm(w, w, x, ctx); - ec_mulm(w, w, ctx->b, ctx); -#undef xx - /* Compute Euler's criterion: w^(p-1)/2 */ -#define p_minus1 y - ec_subm(p_minus1, ctx->p, mpi_const(MPI_C_ONE), ctx); - mpi_rshift(p_minus1, p_minus1, 1); - ec_powm(w, w, p_minus1, ctx); - - res = !mpi_cmp_ui(w, 1); -#undef p_minus1 - } - break; - - case MPI_EC_EDWARDS: - { - if (mpi_ec_get_affine(x, y, point, ctx)) - goto leave; - - mpi_resize(w, ctx->p->nlimbs); - w->nlimbs = ctx->p->nlimbs; - - /* a · x^2 + y^2 - 1 - b · x^2 · y^2 == 0 */ - ctx->pow2(x, x, ctx); - ctx->pow2(y, y, ctx); - if (ctx->dialect == ECC_DIALECT_ED25519) - ctx->subm(w, ctx->p, x, ctx); - else - ctx->mulm(w, ctx->a, x, ctx); - ctx->addm(w, w, y, ctx); - ctx->mulm(x, x, y, ctx); - ctx->mulm(x, x, ctx->b, ctx); - ctx->subm(w, w, x, ctx); - if (!mpi_cmp_ui(w, 1)) - res = 1; - } - break; - } - -leave: - mpi_free(w); - mpi_free(x); - mpi_free(y); - - return res; -} -EXPORT_SYMBOL_GPL(mpi_ec_curve_point); diff --git a/lib/crypto/mpi/mpi-add.c b/lib/crypto/mpi/mpi-add.c index 9056fc5167fc..3015140d4860 100644 --- a/lib/crypto/mpi/mpi-add.c +++ b/lib/crypto/mpi/mpi-add.c @@ -13,62 +13,12 @@ #include "mpi-internal.h" -/**************** - * Add the unsigned integer V to the mpi-integer U and store the - * result in W. U and V may be the same. - */ -void mpi_add_ui(MPI w, MPI u, unsigned long v) -{ - mpi_ptr_t wp, up; - mpi_size_t usize, wsize; - int usign, wsign; - - usize = u->nlimbs; - usign = u->sign; - wsign = 0; - - /* If not space for W (and possible carry), increase space. */ - wsize = usize + 1; - if (w->alloced < wsize) - mpi_resize(w, wsize); - - /* These must be after realloc (U may be the same as W). */ - up = u->d; - wp = w->d; - - if (!usize) { /* simple */ - wp[0] = v; - wsize = v ? 1:0; - } else if (!usign) { /* mpi is not negative */ - mpi_limb_t cy; - cy = mpihelp_add_1(wp, up, usize, v); - wp[usize] = cy; - wsize = usize + cy; - } else { - /* The signs are different. Need exact comparison to determine - * which operand to subtract from which. - */ - if (usize == 1 && up[0] < v) { - wp[0] = v - up[0]; - wsize = 1; - } else { - mpihelp_sub_1(wp, up, usize, v); - /* Size can decrease with at most one limb. */ - wsize = usize - (wp[usize-1] == 0); - wsign = 1; - } - } - - w->nlimbs = wsize; - w->sign = wsign; -} - - -void mpi_add(MPI w, MPI u, MPI v) +int mpi_add(MPI w, MPI u, MPI v) { mpi_ptr_t wp, up, vp; mpi_size_t usize, vsize, wsize; int usign, vsign, wsign; + int err; if (u->nlimbs < v->nlimbs) { /* Swap U and V. */ usize = v->nlimbs; @@ -76,7 +26,9 @@ void mpi_add(MPI w, MPI u, MPI v) vsize = u->nlimbs; vsign = u->sign; wsize = usize + 1; - RESIZE_IF_NEEDED(w, wsize); + err = RESIZE_IF_NEEDED(w, wsize); + if (err) + return err; /* These must be after realloc (u or v may be the same as w). */ up = v->d; vp = u->d; @@ -86,7 +38,9 @@ void mpi_add(MPI w, MPI u, MPI v) vsize = v->nlimbs; vsign = v->sign; wsize = usize + 1; - RESIZE_IF_NEEDED(w, wsize); + err = RESIZE_IF_NEEDED(w, wsize); + if (err) + return err; /* These must be after realloc (u or v may be the same as w). */ up = u->d; vp = v->d; @@ -128,28 +82,37 @@ void mpi_add(MPI w, MPI u, MPI v) w->nlimbs = wsize; w->sign = wsign; + return 0; } EXPORT_SYMBOL_GPL(mpi_add); -void mpi_sub(MPI w, MPI u, MPI v) +int mpi_sub(MPI w, MPI u, MPI v) { - MPI vv = mpi_copy(v); + int err; + MPI vv; + + vv = mpi_copy(v); + if (!vv) + return -ENOMEM; + vv->sign = !vv->sign; - mpi_add(w, u, vv); + err = mpi_add(w, u, vv); mpi_free(vv); + + return err; } EXPORT_SYMBOL_GPL(mpi_sub); -void mpi_addm(MPI w, MPI u, MPI v, MPI m) +int mpi_addm(MPI w, MPI u, MPI v, MPI m) { - mpi_add(w, u, v); - mpi_mod(w, w, m); + return mpi_add(w, u, v) ?: + mpi_mod(w, w, m); } EXPORT_SYMBOL_GPL(mpi_addm); -void mpi_subm(MPI w, MPI u, MPI v, MPI m) +int mpi_subm(MPI w, MPI u, MPI v, MPI m) { - mpi_sub(w, u, v); - mpi_mod(w, w, m); + return mpi_sub(w, u, v) ?: + mpi_mod(w, w, m); } EXPORT_SYMBOL_GPL(mpi_subm); diff --git a/lib/crypto/mpi/mpi-bit.c b/lib/crypto/mpi/mpi-bit.c index 070ba784c9f1..934d81311360 100644 --- a/lib/crypto/mpi/mpi-bit.c +++ b/lib/crypto/mpi/mpi-bit.c @@ -32,7 +32,6 @@ void mpi_normalize(MPI a) for (; a->nlimbs && !a->d[a->nlimbs - 1]; a->nlimbs--) ; } -EXPORT_SYMBOL_GPL(mpi_normalize); /**************** * Return the number of bits in A. @@ -77,9 +76,10 @@ EXPORT_SYMBOL_GPL(mpi_test_bit); /**************** * Set bit N of A. */ -void mpi_set_bit(MPI a, unsigned int n) +int mpi_set_bit(MPI a, unsigned int n) { unsigned int i, limbno, bitno; + int err; limbno = n / BITS_PER_MPI_LIMB; bitno = n % BITS_PER_MPI_LIMB; @@ -87,106 +87,32 @@ void mpi_set_bit(MPI a, unsigned int n) if (limbno >= a->nlimbs) { for (i = a->nlimbs; i < a->alloced; i++) a->d[i] = 0; - mpi_resize(a, limbno+1); + err = mpi_resize(a, limbno+1); + if (err) + return err; a->nlimbs = limbno+1; } a->d[limbno] |= (A_LIMB_1<<bitno); + return 0; } - -/**************** - * Set bit N of A. and clear all bits above - */ -void mpi_set_highbit(MPI a, unsigned int n) -{ - unsigned int i, limbno, bitno; - - limbno = n / BITS_PER_MPI_LIMB; - bitno = n % BITS_PER_MPI_LIMB; - - if (limbno >= a->nlimbs) { - for (i = a->nlimbs; i < a->alloced; i++) - a->d[i] = 0; - mpi_resize(a, limbno+1); - a->nlimbs = limbno+1; - } - a->d[limbno] |= (A_LIMB_1<<bitno); - for (bitno++; bitno < BITS_PER_MPI_LIMB; bitno++) - a->d[limbno] &= ~(A_LIMB_1 << bitno); - a->nlimbs = limbno+1; -} -EXPORT_SYMBOL_GPL(mpi_set_highbit); - -/**************** - * clear bit N of A and all bits above - */ -void mpi_clear_highbit(MPI a, unsigned int n) -{ - unsigned int limbno, bitno; - - limbno = n / BITS_PER_MPI_LIMB; - bitno = n % BITS_PER_MPI_LIMB; - - if (limbno >= a->nlimbs) - return; /* not allocated, therefore no need to clear bits :-) */ - - for ( ; bitno < BITS_PER_MPI_LIMB; bitno++) - a->d[limbno] &= ~(A_LIMB_1 << bitno); - a->nlimbs = limbno+1; -} - -/**************** - * Clear bit N of A. - */ -void mpi_clear_bit(MPI a, unsigned int n) -{ - unsigned int limbno, bitno; - - limbno = n / BITS_PER_MPI_LIMB; - bitno = n % BITS_PER_MPI_LIMB; - - if (limbno >= a->nlimbs) - return; /* Don't need to clear this bit, it's far too left. */ - a->d[limbno] &= ~(A_LIMB_1 << bitno); -} -EXPORT_SYMBOL_GPL(mpi_clear_bit); - - -/**************** - * Shift A by COUNT limbs to the right - * This is used only within the MPI library - */ -void mpi_rshift_limbs(MPI a, unsigned int count) -{ - mpi_ptr_t ap = a->d; - mpi_size_t n = a->nlimbs; - unsigned int i; - - if (count >= n) { - a->nlimbs = 0; - return; - } - - for (i = 0; i < n - count; i++) - ap[i] = ap[i+count]; - ap[i] = 0; - a->nlimbs -= count; -} +EXPORT_SYMBOL_GPL(mpi_set_bit); /* * Shift A by N bits to the right. */ -void mpi_rshift(MPI x, MPI a, unsigned int n) +int mpi_rshift(MPI x, MPI a, unsigned int n) { mpi_size_t xsize; unsigned int i; unsigned int nlimbs = (n/BITS_PER_MPI_LIMB); unsigned int nbits = (n%BITS_PER_MPI_LIMB); + int err; if (x == a) { /* In-place operation. */ if (nlimbs >= x->nlimbs) { x->nlimbs = 0; - return; + return 0; } if (nlimbs) { @@ -201,7 +127,9 @@ void mpi_rshift(MPI x, MPI a, unsigned int n) /* Copy and shift by more or equal bits than in a limb. */ xsize = a->nlimbs; x->sign = a->sign; - RESIZE_IF_NEEDED(x, xsize); + err = RESIZE_IF_NEEDED(x, xsize); + if (err) + return err; x->nlimbs = xsize; for (i = 0; i < a->nlimbs; i++) x->d[i] = a->d[i]; @@ -209,15 +137,13 @@ void mpi_rshift(MPI x, MPI a, unsigned int n) if (nlimbs >= x->nlimbs) { x->nlimbs = 0; - return; + return 0; } - if (nlimbs) { - for (i = 0; i < x->nlimbs - nlimbs; i++) - x->d[i] = x->d[i+nlimbs]; - x->d[i] = 0; - x->nlimbs -= nlimbs; - } + for (i = 0; i < x->nlimbs - nlimbs; i++) + x->d[i] = x->d[i+nlimbs]; + x->d[i] = 0; + x->nlimbs -= nlimbs; if (x->nlimbs && nbits) mpihelp_rshift(x->d, x->d, x->nlimbs, nbits); @@ -225,7 +151,9 @@ void mpi_rshift(MPI x, MPI a, unsigned int n) /* Copy and shift by less than bits in a limb. */ xsize = a->nlimbs; x->sign = a->sign; - RESIZE_IF_NEEDED(x, xsize); + err = RESIZE_IF_NEEDED(x, xsize); + if (err) + return err; x->nlimbs = xsize; if (xsize) { @@ -241,68 +169,7 @@ void mpi_rshift(MPI x, MPI a, unsigned int n) } } MPN_NORMALIZE(x->d, x->nlimbs); -} -EXPORT_SYMBOL_GPL(mpi_rshift); -/**************** - * Shift A by COUNT limbs to the left - * This is used only within the MPI library - */ -void mpi_lshift_limbs(MPI a, unsigned int count) -{ - mpi_ptr_t ap; - int n = a->nlimbs; - int i; - - if (!count || !n) - return; - - RESIZE_IF_NEEDED(a, n+count); - - ap = a->d; - for (i = n-1; i >= 0; i--) - ap[i+count] = ap[i]; - for (i = 0; i < count; i++) - ap[i] = 0; - a->nlimbs += count; -} - -/* - * Shift A by N bits to the left. - */ -void mpi_lshift(MPI x, MPI a, unsigned int n) -{ - unsigned int nlimbs = (n/BITS_PER_MPI_LIMB); - unsigned int nbits = (n%BITS_PER_MPI_LIMB); - - if (x == a && !n) - return; /* In-place shift with an amount of zero. */ - - if (x != a) { - /* Copy A to X. */ - unsigned int alimbs = a->nlimbs; - int asign = a->sign; - mpi_ptr_t xp, ap; - - RESIZE_IF_NEEDED(x, alimbs+nlimbs+1); - xp = x->d; - ap = a->d; - MPN_COPY(xp, ap, alimbs); - x->nlimbs = alimbs; - x->flags = a->flags; - x->sign = asign; - } - - if (nlimbs && !nbits) { - /* Shift a full number of limbs. */ - mpi_lshift_limbs(x, nlimbs); - } else if (n) { - /* We use a very dump approach: Shift left by the number of - * limbs plus one and than fix it up by an rshift. - */ - mpi_lshift_limbs(x, nlimbs+1); - mpi_rshift(x, x, BITS_PER_MPI_LIMB - nbits); - } - - MPN_NORMALIZE(x->d, x->nlimbs); + return 0; } +EXPORT_SYMBOL_GPL(mpi_rshift); diff --git a/lib/crypto/mpi/mpi-cmp.c b/lib/crypto/mpi/mpi-cmp.c index 0835b6213235..ceaebe181cd7 100644 --- a/lib/crypto/mpi/mpi-cmp.c +++ b/lib/crypto/mpi/mpi-cmp.c @@ -45,54 +45,28 @@ int mpi_cmp_ui(MPI u, unsigned long v) } EXPORT_SYMBOL_GPL(mpi_cmp_ui); -static int do_mpi_cmp(MPI u, MPI v, int absmode) +int mpi_cmp(MPI u, MPI v) { - mpi_size_t usize; - mpi_size_t vsize; - int usign; - int vsign; + mpi_size_t usize, vsize; int cmp; mpi_normalize(u); mpi_normalize(v); - usize = u->nlimbs; vsize = v->nlimbs; - usign = absmode ? 0 : u->sign; - vsign = absmode ? 0 : v->sign; - - /* Compare sign bits. */ - - if (!usign && vsign) + if (!u->sign && v->sign) return 1; - if (usign && !vsign) + if (u->sign && !v->sign) return -1; - - /* U and V are either both positive or both negative. */ - - if (usize != vsize && !usign && !vsign) + if (usize != vsize && !u->sign && !v->sign) return usize - vsize; - if (usize != vsize && usign && vsign) - return vsize + usize; + if (usize != vsize && u->sign && v->sign) + return vsize - usize; if (!usize) return 0; cmp = mpihelp_cmp(u->d, v->d, usize); - if (!cmp) - return 0; - if ((cmp < 0?1:0) == (usign?1:0)) - return 1; - - return -1; -} - -int mpi_cmp(MPI u, MPI v) -{ - return do_mpi_cmp(u, v, 0); + if (u->sign) + return -cmp; + return cmp; } EXPORT_SYMBOL_GPL(mpi_cmp); - -int mpi_cmpabs(MPI u, MPI v) -{ - return do_mpi_cmp(u, v, 1); -} -EXPORT_SYMBOL_GPL(mpi_cmpabs); diff --git a/lib/crypto/mpi/mpi-div.c b/lib/crypto/mpi/mpi-div.c index 45beab8b9e9e..6e5044e72595 100644 --- a/lib/crypto/mpi/mpi-div.c +++ b/lib/crypto/mpi/mpi-div.c @@ -14,13 +14,13 @@ #include "mpi-internal.h" #include "longlong.h" -void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den); -void mpi_fdiv_qr(MPI quot, MPI rem, MPI dividend, MPI divisor); +int mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den); -void mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor) +int mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor) { int divisor_sign = divisor->sign; MPI temp_divisor = NULL; + int err; /* We need the original value of the divisor after the remainder has been * preliminary calculated. We have to copy it to temporary space if it's @@ -28,44 +28,22 @@ void mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor) */ if (rem == divisor) { temp_divisor = mpi_copy(divisor); + if (!temp_divisor) + return -ENOMEM; divisor = temp_divisor; } - mpi_tdiv_r(rem, dividend, divisor); + err = mpi_tdiv_r(rem, dividend, divisor); + if (err) + goto free_temp_divisor; if (((divisor_sign?1:0) ^ (dividend->sign?1:0)) && rem->nlimbs) - mpi_add(rem, rem, divisor); + err = mpi_add(rem, rem, divisor); - if (temp_divisor) - mpi_free(temp_divisor); -} +free_temp_divisor: + mpi_free(temp_divisor); -void mpi_fdiv_q(MPI quot, MPI dividend, MPI divisor) -{ - MPI tmp = mpi_alloc(mpi_get_nlimbs(quot)); - mpi_fdiv_qr(quot, tmp, dividend, divisor); - mpi_free(tmp); -} - -void mpi_fdiv_qr(MPI quot, MPI rem, MPI dividend, MPI divisor) -{ - int divisor_sign = divisor->sign; - MPI temp_divisor = NULL; - - if (quot == divisor || rem == divisor) { - temp_divisor = mpi_copy(divisor); - divisor = temp_divisor; - } - - mpi_tdiv_qr(quot, rem, dividend, divisor); - - if ((divisor_sign ^ dividend->sign) && rem->nlimbs) { - mpi_sub_ui(quot, quot, 1); - mpi_add(rem, rem, divisor); - } - - if (temp_divisor) - mpi_free(temp_divisor); + return err; } /* If den == quot, den needs temporary storage. @@ -75,12 +53,12 @@ void mpi_fdiv_qr(MPI quot, MPI rem, MPI dividend, MPI divisor) * i.e no extra storage should be allocated. */ -void mpi_tdiv_r(MPI rem, MPI num, MPI den) +int mpi_tdiv_r(MPI rem, MPI num, MPI den) { - mpi_tdiv_qr(NULL, rem, num, den); + return mpi_tdiv_qr(NULL, rem, num, den); } -void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den) +int mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den) { mpi_ptr_t np, dp; mpi_ptr_t qp, rp; @@ -93,13 +71,16 @@ void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den) mpi_limb_t q_limb; mpi_ptr_t marker[5]; int markidx = 0; + int err; /* Ensure space is enough for quotient and remainder. * We need space for an extra limb in the remainder, because it's * up-shifted (normalized) below. */ rsize = nsize + 1; - mpi_resize(rem, rsize); + err = mpi_resize(rem, rsize); + if (err) + return err; qsize = rsize - dsize; /* qsize cannot be bigger than this. */ if (qsize <= 0) { @@ -115,11 +96,14 @@ void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den) quot->nlimbs = 0; quot->sign = 0; } - return; + return 0; } - if (quot) - mpi_resize(quot, qsize); + if (quot) { + err = mpi_resize(quot, qsize); + if (err) + return err; + } /* Read pointers here, when reallocation is finished. */ np = num->d; @@ -141,10 +125,10 @@ void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den) rsize = rlimb != 0?1:0; rem->nlimbs = rsize; rem->sign = sign_remainder; - return; + return 0; } - + err = -ENOMEM; if (quot) { qp = quot->d; /* Make sure QP and NP point to different objects. Otherwise the @@ -152,6 +136,8 @@ void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den) */ if (qp == np) { /* Copy NP object to temporary space. */ np = marker[markidx++] = mpi_alloc_limb_space(nsize); + if (!np) + goto out_free_marker; MPN_COPY(np, qp, nsize); } } else /* Put quotient at top of remainder. */ @@ -172,6 +158,8 @@ void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den) * the original contents of the denominator. */ tp = marker[markidx++] = mpi_alloc_limb_space(dsize); + if (!tp) + goto out_free_marker; mpihelp_lshift(tp, dp, dsize, normalization_steps); dp = tp; @@ -193,6 +181,8 @@ void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den) mpi_ptr_t tp; tp = marker[markidx++] = mpi_alloc_limb_space(dsize); + if (!tp) + goto out_free_marker; MPN_COPY(tp, dp, dsize); dp = tp; } @@ -227,8 +217,14 @@ void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den) rem->nlimbs = rsize; rem->sign = sign_remainder; + + err = 0; + +out_free_marker: while (markidx) { markidx--; mpi_free_limb_space(marker[markidx]); } + + return err; } diff --git a/lib/crypto/mpi/mpi-internal.h b/lib/crypto/mpi/mpi-internal.h index 554002182db1..8a4f49e3043c 100644 --- a/lib/crypto/mpi/mpi-internal.h +++ b/lib/crypto/mpi/mpi-internal.h @@ -52,11 +52,12 @@ typedef mpi_limb_t *mpi_ptr_t; /* pointer to a limb */ typedef int mpi_size_t; /* (must be a signed type) */ -#define RESIZE_IF_NEEDED(a, b) \ - do { \ - if ((a)->alloced < (b)) \ - mpi_resize((a), (b)); \ - } while (0) +static inline int RESIZE_IF_NEEDED(MPI a, unsigned b) +{ + if (a->alloced < b) + return mpi_resize(a, b); + return 0; +} /* Copy N limbs from S to D. */ #define MPN_COPY(d, s, n) \ @@ -66,14 +67,6 @@ typedef int mpi_size_t; /* (must be a signed type) */ (d)[_i] = (s)[_i]; \ } while (0) -#define MPN_COPY_INCR(d, s, n) \ - do { \ - mpi_size_t _i; \ - for (_i = 0; _i < (n); _i++) \ - (d)[_i] = (s)[_i]; \ - } while (0) - - #define MPN_COPY_DECR(d, s, n) \ do { \ mpi_size_t _i; \ @@ -181,8 +174,6 @@ int mpihelp_mul(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t usize, void mpih_sqr_n_basecase(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t size); void mpih_sqr_n(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t size, mpi_ptr_t tspace); -void mpihelp_mul_n(mpi_ptr_t prodp, - mpi_ptr_t up, mpi_ptr_t vp, mpi_size_t size); int mpihelp_mul_karatsuba_case(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t usize, diff --git a/lib/crypto/mpi/mpi-inv.c b/lib/crypto/mpi/mpi-inv.c deleted file mode 100644 index 61e37d18f793..000000000000 --- a/lib/crypto/mpi/mpi-inv.c +++ /dev/null @@ -1,143 +0,0 @@ -/* mpi-inv.c - MPI functions - * Copyright (C) 1998, 2001, 2002, 2003 Free Software Foundation, Inc. - * - * This file is part of Libgcrypt. - * - * Libgcrypt is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as - * published by the Free Software Foundation; either version 2.1 of - * the License, or (at your option) any later version. - * - * Libgcrypt is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -#include "mpi-internal.h" - -/**************** - * Calculate the multiplicative inverse X of A mod N - * That is: Find the solution x for - * 1 = (a*x) mod n - */ -int mpi_invm(MPI x, MPI a, MPI n) -{ - /* Extended Euclid's algorithm (See TAOCP Vol II, 4.5.2, Alg X) - * modified according to Michael Penk's solution for Exercise 35 - * with further enhancement - */ - MPI u, v, u1, u2 = NULL, u3, v1, v2 = NULL, v3, t1, t2 = NULL, t3; - unsigned int k; - int sign; - int odd; - - if (!mpi_cmp_ui(a, 0)) - return 0; /* Inverse does not exists. */ - if (!mpi_cmp_ui(n, 1)) - return 0; /* Inverse does not exists. */ - - u = mpi_copy(a); - v = mpi_copy(n); - - for (k = 0; !mpi_test_bit(u, 0) && !mpi_test_bit(v, 0); k++) { - mpi_rshift(u, u, 1); - mpi_rshift(v, v, 1); - } - odd = mpi_test_bit(v, 0); - - u1 = mpi_alloc_set_ui(1); - if (!odd) - u2 = mpi_alloc_set_ui(0); - u3 = mpi_copy(u); - v1 = mpi_copy(v); - if (!odd) { - v2 = mpi_alloc(mpi_get_nlimbs(u)); - mpi_sub(v2, u1, u); /* U is used as const 1 */ - } - v3 = mpi_copy(v); - if (mpi_test_bit(u, 0)) { /* u is odd */ - t1 = mpi_alloc_set_ui(0); - if (!odd) { - t2 = mpi_alloc_set_ui(1); - t2->sign = 1; - } - t3 = mpi_copy(v); - t3->sign = !t3->sign; - goto Y4; - } else { - t1 = mpi_alloc_set_ui(1); - if (!odd) - t2 = mpi_alloc_set_ui(0); - t3 = mpi_copy(u); - } - - do { - do { - if (!odd) { - if (mpi_test_bit(t1, 0) || mpi_test_bit(t2, 0)) { - /* one is odd */ - mpi_add(t1, t1, v); - mpi_sub(t2, t2, u); - } - mpi_rshift(t1, t1, 1); - mpi_rshift(t2, t2, 1); - mpi_rshift(t3, t3, 1); - } else { - if (mpi_test_bit(t1, 0)) - mpi_add(t1, t1, v); - mpi_rshift(t1, t1, 1); - mpi_rshift(t3, t3, 1); - } -Y4: - ; - } while (!mpi_test_bit(t3, 0)); /* while t3 is even */ - - if (!t3->sign) { - mpi_set(u1, t1); - if (!odd) - mpi_set(u2, t2); - mpi_set(u3, t3); - } else { - mpi_sub(v1, v, t1); - sign = u->sign; u->sign = !u->sign; - if (!odd) - mpi_sub(v2, u, t2); - u->sign = sign; - sign = t3->sign; t3->sign = !t3->sign; - mpi_set(v3, t3); - t3->sign = sign; - } - mpi_sub(t1, u1, v1); - if (!odd) - mpi_sub(t2, u2, v2); - mpi_sub(t3, u3, v3); - if (t1->sign) { - mpi_add(t1, t1, v); - if (!odd) - mpi_sub(t2, t2, u); - } - } while (mpi_cmp_ui(t3, 0)); /* while t3 != 0 */ - /* mpi_lshift( u3, k ); */ - mpi_set(x, u1); - - mpi_free(u1); - mpi_free(v1); - mpi_free(t1); - if (!odd) { - mpi_free(u2); - mpi_free(v2); - mpi_free(t2); - } - mpi_free(u3); - mpi_free(v3); - mpi_free(t3); - - mpi_free(u); - mpi_free(v); - return 1; -} -EXPORT_SYMBOL_GPL(mpi_invm); diff --git a/lib/crypto/mpi/mpi-mod.c b/lib/crypto/mpi/mpi-mod.c index 54fcc01564d9..d5fdaec3d0b6 100644 --- a/lib/crypto/mpi/mpi-mod.c +++ b/lib/crypto/mpi/mpi-mod.c @@ -5,153 +5,9 @@ * This file is part of Libgcrypt. */ - #include "mpi-internal.h" -#include "longlong.h" - -/* Context used with Barrett reduction. */ -struct barrett_ctx_s { - MPI m; /* The modulus - may not be modified. */ - int m_copied; /* If true, M needs to be released. */ - int k; - MPI y; - MPI r1; /* Helper MPI. */ - MPI r2; /* Helper MPI. */ - MPI r3; /* Helper MPI allocated on demand. */ -}; - - - -void mpi_mod(MPI rem, MPI dividend, MPI divisor) -{ - mpi_fdiv_r(rem, dividend, divisor); -} - -/* This function returns a new context for Barrett based operations on - * the modulus M. This context needs to be released using - * _gcry_mpi_barrett_free. If COPY is true M will be transferred to - * the context and the user may change M. If COPY is false, M may not - * be changed until gcry_mpi_barrett_free has been called. - */ -mpi_barrett_t mpi_barrett_init(MPI m, int copy) -{ - mpi_barrett_t ctx; - MPI tmp; - - mpi_normalize(m); - ctx = kcalloc(1, sizeof(*ctx), GFP_KERNEL); - if (!ctx) - return NULL; - - if (copy) { - ctx->m = mpi_copy(m); - ctx->m_copied = 1; - } else - ctx->m = m; - - ctx->k = mpi_get_nlimbs(m); - tmp = mpi_alloc(ctx->k + 1); - - /* Barrett precalculation: y = floor(b^(2k) / m). */ - mpi_set_ui(tmp, 1); - mpi_lshift_limbs(tmp, 2 * ctx->k); - mpi_fdiv_q(tmp, tmp, m); - - ctx->y = tmp; - ctx->r1 = mpi_alloc(2 * ctx->k + 1); - ctx->r2 = mpi_alloc(2 * ctx->k + 1); - - return ctx; -} - -void mpi_barrett_free(mpi_barrett_t ctx) -{ - if (ctx) { - mpi_free(ctx->y); - mpi_free(ctx->r1); - mpi_free(ctx->r2); - if (ctx->r3) - mpi_free(ctx->r3); - if (ctx->m_copied) - mpi_free(ctx->m); - kfree(ctx); - } -} - - -/* R = X mod M - * - * Using Barrett reduction. Before using this function - * _gcry_mpi_barrett_init must have been called to do the - * precalculations. CTX is the context created by this precalculation - * and also conveys M. If the Barret reduction could no be done a - * straightforward reduction method is used. - * - * We assume that these conditions are met: - * Input: x =(x_2k-1 ...x_0)_b - * m =(m_k-1 ....m_0)_b with m_k-1 != 0 - * Output: r = x mod m - */ -void mpi_mod_barrett(MPI r, MPI x, mpi_barrett_t ctx) -{ - MPI m = ctx->m; - int k = ctx->k; - MPI y = ctx->y; - MPI r1 = ctx->r1; - MPI r2 = ctx->r2; - int sign; - - mpi_normalize(x); - if (mpi_get_nlimbs(x) > 2*k) { - mpi_mod(r, x, m); - return; - } - - sign = x->sign; - x->sign = 0; - - /* 1. q1 = floor( x / b^k-1) - * q2 = q1 * y - * q3 = floor( q2 / b^k+1 ) - * Actually, we don't need qx, we can work direct on r2 - */ - mpi_set(r2, x); - mpi_rshift_limbs(r2, k-1); - mpi_mul(r2, r2, y); - mpi_rshift_limbs(r2, k+1); - - /* 2. r1 = x mod b^k+1 - * r2 = q3 * m mod b^k+1 - * r = r1 - r2 - * 3. if r < 0 then r = r + b^k+1 - */ - mpi_set(r1, x); - if (r1->nlimbs > k+1) /* Quick modulo operation. */ - r1->nlimbs = k+1; - mpi_mul(r2, r2, m); - if (r2->nlimbs > k+1) /* Quick modulo operation. */ - r2->nlimbs = k+1; - mpi_sub(r, r1, r2); - - if (mpi_has_sign(r)) { - if (!ctx->r3) { - ctx->r3 = mpi_alloc(k + 2); - mpi_set_ui(ctx->r3, 1); - mpi_lshift_limbs(ctx->r3, k + 1); - } - mpi_add(r, r, ctx->r3); - } - - /* 4. while r >= m do r = r - m */ - while (mpi_cmp(r, m) >= 0) - mpi_sub(r, r, m); - - x->sign = sign; -} - -void mpi_mul_barrett(MPI w, MPI u, MPI v, mpi_barrett_t ctx) +int mpi_mod(MPI rem, MPI dividend, MPI divisor) { - mpi_mul(w, u, v); - mpi_mod_barrett(w, w, ctx); + return mpi_fdiv_r(rem, dividend, divisor); } diff --git a/lib/crypto/mpi/mpi-mul.c b/lib/crypto/mpi/mpi-mul.c index 7f4eda8560dc..7e6ff1ce3e9b 100644 --- a/lib/crypto/mpi/mpi-mul.c +++ b/lib/crypto/mpi/mpi-mul.c @@ -13,7 +13,7 @@ #include "mpi-internal.h" -void mpi_mul(MPI w, MPI u, MPI v) +int mpi_mul(MPI w, MPI u, MPI v) { mpi_size_t usize, vsize, wsize; mpi_ptr_t up, vp, wp; @@ -21,6 +21,7 @@ void mpi_mul(MPI w, MPI u, MPI v) int usign, vsign, sign_product; int assign_wp = 0; mpi_ptr_t tmp_limb = NULL; + int err = 0; if (u->nlimbs < v->nlimbs) { /* Swap U and V. */ @@ -46,15 +47,21 @@ void mpi_mul(MPI w, MPI u, MPI v) if (w->alloced < wsize) { if (wp == up || wp == vp) { wp = mpi_alloc_limb_space(wsize); + if (!wp) + return -ENOMEM; assign_wp = 1; } else { - mpi_resize(w, wsize); + err = mpi_resize(w, wsize); + if (err) + return err; wp = w->d; } } else { /* Make U and V not overlap with W. */ if (wp == up) { /* W and U are identical. Allocate temporary space for U. */ up = tmp_limb = mpi_alloc_limb_space(usize); + if (!up) + return -ENOMEM; /* Is V identical too? Keep it identical with U. */ if (wp == vp) vp = up; @@ -63,6 +70,8 @@ void mpi_mul(MPI w, MPI u, MPI v) } else if (wp == vp) { /* W and V are identical. Allocate temporary space for V. */ vp = tmp_limb = mpi_alloc_limb_space(vsize); + if (!vp) + return -ENOMEM; /* Copy to the temporary space. */ MPN_COPY(vp, wp, vsize); } @@ -71,7 +80,12 @@ void mpi_mul(MPI w, MPI u, MPI v) if (!vsize) wsize = 0; else { - mpihelp_mul(wp, up, usize, vp, vsize, &cy); + err = mpihelp_mul(wp, up, usize, vp, vsize, &cy); + if (err) { + if (assign_wp) + mpi_free_limb_space(wp); + goto free_tmp_limb; + } wsize -= cy ? 0:1; } @@ -79,14 +93,17 @@ void mpi_mul(MPI w, MPI u, MPI v) mpi_assign_limb_space(w, wp, wsize); w->nlimbs = wsize; w->sign = sign_product; + +free_tmp_limb: if (tmp_limb) mpi_free_limb_space(tmp_limb); + return err; } EXPORT_SYMBOL_GPL(mpi_mul); -void mpi_mulm(MPI w, MPI u, MPI v, MPI m) +int mpi_mulm(MPI w, MPI u, MPI v, MPI m) { - mpi_mul(w, u, v); - mpi_tdiv_r(w, w, m); + return mpi_mul(w, u, v) ?: + mpi_tdiv_r(w, w, m); } EXPORT_SYMBOL_GPL(mpi_mulm); diff --git a/lib/crypto/mpi/mpi-pow.c b/lib/crypto/mpi/mpi-pow.c index 2fd7a46d55ec..67fbd4c2503d 100644 --- a/lib/crypto/mpi/mpi-pow.c +++ b/lib/crypto/mpi/mpi-pow.c @@ -176,7 +176,6 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod) for (;;) { while (c) { - mpi_ptr_t tp; mpi_size_t xsize; /*if (mpihelp_mul_n(xp, rp, rp, rsize) < 0) goto enomem */ @@ -207,9 +206,7 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod) xsize = msize; } - tp = rp; - rp = xp; - xp = tp; + swap(rp, xp); rsize = xsize; if ((mpi_limb_signed_t) e < 0) { @@ -235,9 +232,7 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod) xsize = msize; } - tp = rp; - rp = xp; - xp = tp; + swap(rp, xp); rsize = xsize; } e <<= 1; diff --git a/lib/crypto/mpi/mpicoder.c b/lib/crypto/mpi/mpicoder.c index 3cb6bd148fa9..dde01030807d 100644 --- a/lib/crypto/mpi/mpicoder.c +++ b/lib/crypto/mpi/mpicoder.c @@ -25,7 +25,6 @@ #include <linux/string.h> #include "mpi-internal.h" -#define MAX_EXTERN_SCAN_BYTES (16*1024*1024) #define MAX_EXTERN_MPI_BITS 16384 /** @@ -110,112 +109,6 @@ MPI mpi_read_from_buffer(const void *xbuffer, unsigned *ret_nread) } EXPORT_SYMBOL_GPL(mpi_read_from_buffer); -/**************** - * Fill the mpi VAL from the hex string in STR. - */ -int mpi_fromstr(MPI val, const char *str) -{ - int sign = 0; - int prepend_zero = 0; - int i, j, c, c1, c2; - unsigned int nbits, nbytes, nlimbs; - mpi_limb_t a; - - if (*str == '-') { - sign = 1; - str++; - } - - /* Skip optional hex prefix. */ - if (*str == '0' && str[1] == 'x') - str += 2; - - nbits = strlen(str); - if (nbits > MAX_EXTERN_SCAN_BYTES) { - mpi_clear(val); - return -EINVAL; - } - nbits *= 4; - if ((nbits % 8)) - prepend_zero = 1; - - nbytes = (nbits+7) / 8; - nlimbs = (nbytes+BYTES_PER_MPI_LIMB-1) / BYTES_PER_MPI_LIMB; - - if (val->alloced < nlimbs) - mpi_resize(val, nlimbs); - - i = BYTES_PER_MPI_LIMB - (nbytes % BYTES_PER_MPI_LIMB); - i %= BYTES_PER_MPI_LIMB; - j = val->nlimbs = nlimbs; - val->sign = sign; - for (; j > 0; j--) { - a = 0; - for (; i < BYTES_PER_MPI_LIMB; i++) { - if (prepend_zero) { - c1 = '0'; - prepend_zero = 0; - } else - c1 = *str++; - - if (!c1) { - mpi_clear(val); - return -EINVAL; - } - c2 = *str++; - if (!c2) { - mpi_clear(val); - return -EINVAL; - } - if (c1 >= '0' && c1 <= '9') - c = c1 - '0'; - else if (c1 >= 'a' && c1 <= 'f') - c = c1 - 'a' + 10; - else if (c1 >= 'A' && c1 <= 'F') - c = c1 - 'A' + 10; - else { - mpi_clear(val); - return -EINVAL; - } - c <<= 4; - if (c2 >= '0' && c2 <= '9') - c |= c2 - '0'; - else if (c2 >= 'a' && c2 <= 'f') - c |= c2 - 'a' + 10; - else if (c2 >= 'A' && c2 <= 'F') - c |= c2 - 'A' + 10; - else { - mpi_clear(val); - return -EINVAL; - } - a <<= 8; - a |= c; - } - i = 0; - val->d[j-1] = a; - } - - return 0; -} -EXPORT_SYMBOL_GPL(mpi_fromstr); - -MPI mpi_scanval(const char *string) -{ - MPI a; - - a = mpi_alloc(0); - if (!a) - return NULL; - - if (mpi_fromstr(a, string)) { - mpi_free(a); - return NULL; - } - mpi_normalize(a); - return a; -} -EXPORT_SYMBOL_GPL(mpi_scanval); - static int count_lzeros(MPI a) { mpi_limb_t alimb; @@ -521,232 +414,3 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes) return val; } EXPORT_SYMBOL_GPL(mpi_read_raw_from_sgl); - -/* Perform a two's complement operation on buffer P of size N bytes. */ -static void twocompl(unsigned char *p, unsigned int n) -{ - int i; - - for (i = n-1; i >= 0 && !p[i]; i--) - ; - if (i >= 0) { - if ((p[i] & 0x01)) - p[i] = (((p[i] ^ 0xfe) | 0x01) & 0xff); - else if ((p[i] & 0x02)) - p[i] = (((p[i] ^ 0xfc) | 0x02) & 0xfe); - else if ((p[i] & 0x04)) - p[i] = (((p[i] ^ 0xf8) | 0x04) & 0xfc); - else if ((p[i] & 0x08)) - p[i] = (((p[i] ^ 0xf0) | 0x08) & 0xf8); - else if ((p[i] & 0x10)) - p[i] = (((p[i] ^ 0xe0) | 0x10) & 0xf0); - else if ((p[i] & 0x20)) - p[i] = (((p[i] ^ 0xc0) | 0x20) & 0xe0); - else if ((p[i] & 0x40)) - p[i] = (((p[i] ^ 0x80) | 0x40) & 0xc0); - else - p[i] = 0x80; - - for (i--; i >= 0; i--) - p[i] ^= 0xff; - } -} - -int mpi_print(enum gcry_mpi_format format, unsigned char *buffer, - size_t buflen, size_t *nwritten, MPI a) -{ - unsigned int nbits = mpi_get_nbits(a); - size_t len; - size_t dummy_nwritten; - int negative; - - if (!nwritten) - nwritten = &dummy_nwritten; - - /* Libgcrypt does no always care to set clear the sign if the value - * is 0. For printing this is a bit of a surprise, in particular - * because if some of the formats don't support negative numbers but - * should be able to print a zero. Thus we need this extra test - * for a negative number. - */ - if (a->sign && mpi_cmp_ui(a, 0)) - negative = 1; - else - negative = 0; - - len = buflen; - *nwritten = 0; - if (format == GCRYMPI_FMT_STD) { - unsigned char *tmp; - int extra = 0; - unsigned int n; - - tmp = mpi_get_buffer(a, &n, NULL); - if (!tmp) - return -EINVAL; - - if (negative) { - twocompl(tmp, n); - if (!(*tmp & 0x80)) { - /* Need to extend the sign. */ - n++; - extra = 2; - } - } else if (n && (*tmp & 0x80)) { - /* Positive but the high bit of the returned buffer is set. - * Thus we need to print an extra leading 0x00 so that the - * output is interpreted as a positive number. - */ - n++; - extra = 1; - } - - if (buffer && n > len) { - /* The provided buffer is too short. */ - kfree(tmp); - return -E2BIG; - } - if (buffer) { - unsigned char *s = buffer; - - if (extra == 1) - *s++ = 0; - else if (extra) - *s++ = 0xff; - memcpy(s, tmp, n-!!extra); - } - kfree(tmp); - *nwritten = n; - return 0; - } else if (format == GCRYMPI_FMT_USG) { - unsigned int n = (nbits + 7)/8; - - /* Note: We ignore the sign for this format. */ - /* FIXME: for performance reasons we should put this into - * mpi_aprint because we can then use the buffer directly. - */ - - if (buffer && n > len) - return -E2BIG; - if (buffer) { - unsigned char *tmp; - - tmp = mpi_get_buffer(a, &n, NULL); - if (!tmp) - return -EINVAL; - memcpy(buffer, tmp, n); - kfree(tmp); - } - *nwritten = n; - return 0; - } else if (format == GCRYMPI_FMT_PGP) { - unsigned int n = (nbits + 7)/8; - - /* The PGP format can only handle unsigned integers. */ - if (negative) - return -EINVAL; - - if (buffer && n+2 > len) - return -E2BIG; - - if (buffer) { - unsigned char *tmp; - unsigned char *s = buffer; - - s[0] = nbits >> 8; - s[1] = nbits; - - tmp = mpi_get_buffer(a, &n, NULL); - if (!tmp) - return -EINVAL; - memcpy(s+2, tmp, n); - kfree(tmp); - } - *nwritten = n+2; - return 0; - } else if (format == GCRYMPI_FMT_SSH) { - unsigned char *tmp; - int extra = 0; - unsigned int n; - - tmp = mpi_get_buffer(a, &n, NULL); - if (!tmp) - return -EINVAL; - - if (negative) { - twocompl(tmp, n); - if (!(*tmp & 0x80)) { - /* Need to extend the sign. */ - n++; - extra = 2; - } - } else if (n && (*tmp & 0x80)) { - n++; - extra = 1; - } - - if (buffer && n+4 > len) { - kfree(tmp); - return -E2BIG; - } - - if (buffer) { - unsigned char *s = buffer; - - *s++ = n >> 24; - *s++ = n >> 16; - *s++ = n >> 8; - *s++ = n; - if (extra == 1) - *s++ = 0; - else if (extra) - *s++ = 0xff; - memcpy(s, tmp, n-!!extra); - } - kfree(tmp); - *nwritten = 4+n; - return 0; - } else if (format == GCRYMPI_FMT_HEX) { - unsigned char *tmp; - int i; - int extra = 0; - unsigned int n = 0; - - tmp = mpi_get_buffer(a, &n, NULL); - if (!tmp) - return -EINVAL; - if (!n || (*tmp & 0x80)) - extra = 2; - - if (buffer && 2*n + extra + negative + 1 > len) { - kfree(tmp); - return -E2BIG; - } - if (buffer) { - unsigned char *s = buffer; - - if (negative) - *s++ = '-'; - if (extra) { - *s++ = '0'; - *s++ = '0'; - } - - for (i = 0; i < n; i++) { - unsigned int c = tmp[i]; - - *s++ = (c >> 4) < 10 ? '0'+(c>>4) : 'A'+(c>>4)-10; - c &= 15; - *s++ = c < 10 ? '0'+c : 'A'+c-10; - } - *s++ = 0; - *nwritten = s - buffer; - } else { - *nwritten = 2*n + extra + negative + 1; - } - kfree(tmp); - return 0; - } else - return -EINVAL; -} -EXPORT_SYMBOL_GPL(mpi_print); diff --git a/lib/crypto/mpi/mpih-mul.c b/lib/crypto/mpi/mpih-mul.c index e5f1c84e3c48..a93647564054 100644 --- a/lib/crypto/mpi/mpih-mul.c +++ b/lib/crypto/mpi/mpih-mul.c @@ -317,31 +317,6 @@ mpih_sqr_n(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t size, mpi_ptr_t tspace) } } - -void mpihelp_mul_n(mpi_ptr_t prodp, - mpi_ptr_t up, mpi_ptr_t vp, mpi_size_t size) -{ - if (up == vp) { - if (size < KARATSUBA_THRESHOLD) - mpih_sqr_n_basecase(prodp, up, size); - else { - mpi_ptr_t tspace; - tspace = mpi_alloc_limb_space(2 * size); - mpih_sqr_n(prodp, up, size, tspace); - mpi_free_limb_space(tspace); - } - } else { - if (size < KARATSUBA_THRESHOLD) - mul_n_basecase(prodp, up, vp, size); - else { - mpi_ptr_t tspace; - tspace = mpi_alloc_limb_space(2 * size); - mul_n(prodp, up, vp, size, tspace); - mpi_free_limb_space(tspace); - } - } -} - int mpihelp_mul_karatsuba_case(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t usize, diff --git a/lib/crypto/mpi/mpiutil.c b/lib/crypto/mpi/mpiutil.c index aa8c46544af8..979ece5a81d2 100644 --- a/lib/crypto/mpi/mpiutil.c +++ b/lib/crypto/mpi/mpiutil.c @@ -20,63 +20,6 @@ #include "mpi-internal.h" -/* Constants allocated right away at startup. */ -static MPI constants[MPI_NUMBER_OF_CONSTANTS]; - -/* Initialize the MPI subsystem. This is called early and allows to - * do some initialization without taking care of threading issues. - */ -static int __init mpi_init(void) -{ - int idx; - unsigned long value; - - for (idx = 0; idx < MPI_NUMBER_OF_CONSTANTS; idx++) { - switch (idx) { - case MPI_C_ZERO: - value = 0; - break; - case MPI_C_ONE: - value = 1; - break; - case MPI_C_TWO: - value = 2; - break; - case MPI_C_THREE: - value = 3; - break; - case MPI_C_FOUR: - value = 4; - break; - case MPI_C_EIGHT: - value = 8; - break; - default: - pr_err("MPI: invalid mpi_const selector %d\n", idx); - return -EFAULT; - } - constants[idx] = mpi_alloc_set_ui(value); - constants[idx]->flags = (16|32); - } - - return 0; -} -postcore_initcall(mpi_init); - -/* Return a constant MPI descripbed by NO which is one of the - * MPI_C_xxx macros. There is no need to copy this returned value; it - * may be used directly. - */ -MPI mpi_const(enum gcry_mpi_constants no) -{ - if ((int)no < 0 || no > MPI_NUMBER_OF_CONSTANTS) - pr_err("MPI: invalid mpi_const selector %d\n", no); - if (!constants[no]) - pr_err("MPI: MPI subsystem not initialized\n"); - return constants[no]; -} -EXPORT_SYMBOL_GPL(mpi_const); - /**************** * Note: It was a bad idea to use the number of limbs to allocate * because on a alpha the limbs are large but we normally need @@ -163,15 +106,6 @@ int mpi_resize(MPI a, unsigned nlimbs) return 0; } -void mpi_clear(MPI a) -{ - if (!a) - return; - a->nlimbs = 0; - a->flags = 0; -} -EXPORT_SYMBOL_GPL(mpi_clear); - void mpi_free(MPI a) { if (!a) @@ -199,6 +133,8 @@ MPI mpi_copy(MPI a) if (a) { b = mpi_alloc(a->nlimbs); + if (!b) + return NULL; b->nlimbs = a->nlimbs; b->sign = a->sign; b->flags = a->flags; @@ -210,121 +146,5 @@ MPI mpi_copy(MPI a) return b; } -/**************** - * This function allocates an MPI which is optimized to hold - * a value as large as the one given in the argument and allocates it - * with the same flags as A. - */ -MPI mpi_alloc_like(MPI a) -{ - MPI b; - - if (a) { - b = mpi_alloc(a->nlimbs); - b->nlimbs = 0; - b->sign = 0; - b->flags = a->flags; - } else - b = NULL; - - return b; -} - - -/* Set U into W and release U. If W is NULL only U will be released. */ -void mpi_snatch(MPI w, MPI u) -{ - if (w) { - mpi_assign_limb_space(w, u->d, u->alloced); - w->nlimbs = u->nlimbs; - w->sign = u->sign; - w->flags = u->flags; - u->alloced = 0; - u->nlimbs = 0; - u->d = NULL; - } - mpi_free(u); -} - - -MPI mpi_set(MPI w, MPI u) -{ - mpi_ptr_t wp, up; - mpi_size_t usize = u->nlimbs; - int usign = u->sign; - - if (!w) - w = mpi_alloc(mpi_get_nlimbs(u)); - RESIZE_IF_NEEDED(w, usize); - wp = w->d; - up = u->d; - MPN_COPY(wp, up, usize); - w->nlimbs = usize; - w->flags = u->flags; - w->flags &= ~(16|32); /* Reset the immutable and constant flags. */ - w->sign = usign; - return w; -} -EXPORT_SYMBOL_GPL(mpi_set); - -MPI mpi_set_ui(MPI w, unsigned long u) -{ - if (!w) - w = mpi_alloc(1); - /* FIXME: If U is 0 we have no need to resize and thus possible - * allocating the limbs. - */ - RESIZE_IF_NEEDED(w, 1); - w->d[0] = u; - w->nlimbs = u ? 1 : 0; - w->sign = 0; - w->flags = 0; - return w; -} -EXPORT_SYMBOL_GPL(mpi_set_ui); - -MPI mpi_alloc_set_ui(unsigned long u) -{ - MPI w = mpi_alloc(1); - w->d[0] = u; - w->nlimbs = u ? 1 : 0; - w->sign = 0; - return w; -} - -/**************** - * Swap the value of A and B, when SWAP is 1. - * Leave the value when SWAP is 0. - * This implementation should be constant-time regardless of SWAP. - */ -void mpi_swap_cond(MPI a, MPI b, unsigned long swap) -{ - mpi_size_t i; - mpi_size_t nlimbs; - mpi_limb_t mask = ((mpi_limb_t)0) - swap; - mpi_limb_t x; - - if (a->alloced > b->alloced) - nlimbs = b->alloced; - else - nlimbs = a->alloced; - if (a->nlimbs > nlimbs || b->nlimbs > nlimbs) - return; - - for (i = 0; i < nlimbs; i++) { - x = mask & (a->d[i] ^ b->d[i]); - a->d[i] = a->d[i] ^ x; - b->d[i] = b->d[i] ^ x; - } - - x = mask & (a->nlimbs ^ b->nlimbs); - a->nlimbs = a->nlimbs ^ x; - b->nlimbs = b->nlimbs ^ x; - - x = mask & (a->sign ^ b->sign); - a->sign = a->sign ^ x; - b->sign = b->sign ^ x; -} - MODULE_DESCRIPTION("Multiprecision maths library"); MODULE_LICENSE("GPL"); diff --git a/lib/crypto/poly1305-donna32.c b/lib/crypto/poly1305-donna32.c index 7fb71845cc84..0a4a2d99e365 100644 --- a/lib/crypto/poly1305-donna32.c +++ b/lib/crypto/poly1305-donna32.c @@ -7,7 +7,7 @@ */ #include <linux/kernel.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/internal/poly1305.h> void poly1305_core_setkey(struct poly1305_core_key *key, diff --git a/lib/crypto/poly1305-donna64.c b/lib/crypto/poly1305-donna64.c index 988702c9b3b2..530287531b2e 100644 --- a/lib/crypto/poly1305-donna64.c +++ b/lib/crypto/poly1305-donna64.c @@ -7,7 +7,7 @@ */ #include <linux/kernel.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/internal/poly1305.h> void poly1305_core_setkey(struct poly1305_core_key *key, diff --git a/lib/crypto/poly1305.c b/lib/crypto/poly1305.c index 26d87fc3823e..6e80214ebad8 100644 --- a/lib/crypto/poly1305.c +++ b/lib/crypto/poly1305.c @@ -10,7 +10,7 @@ #include <crypto/internal/poly1305.h> #include <linux/kernel.h> #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> void poly1305_init_generic(struct poly1305_desc_ctx *desc, const u8 key[POLY1305_KEY_SIZE]) @@ -76,3 +76,4 @@ EXPORT_SYMBOL_GPL(poly1305_final_generic); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Martin Willi <martin@strongswan.org>"); +MODULE_DESCRIPTION("Poly1305 authenticator algorithm, RFC7539"); diff --git a/lib/crypto/sha1.c b/lib/crypto/sha1.c index 1aebe7be9401..ebb60519ae93 100644 --- a/lib/crypto/sha1.c +++ b/lib/crypto/sha1.c @@ -12,7 +12,7 @@ #include <linux/bitops.h> #include <linux/string.h> #include <crypto/sha1.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* * If you have 32 registers or more, the compiler can (and should) @@ -137,4 +137,5 @@ void sha1_init(__u32 *buf) } EXPORT_SYMBOL(sha1_init); +MODULE_DESCRIPTION("SHA-1 Algorithm"); MODULE_LICENSE("GPL"); diff --git a/lib/crypto/sha256.c b/lib/crypto/sha256.c index 3ac1ef8677db..04c1f2557e6c 100644 --- a/lib/crypto/sha256.c +++ b/lib/crypto/sha256.c @@ -11,7 +11,7 @@ * Copyright (c) 2014 Red Hat Inc. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/sha256_base.h> #include <linux/kernel.h> #include <linux/module.h> @@ -165,4 +165,5 @@ void sha256(const u8 *data, unsigned int len, u8 *out) } EXPORT_SYMBOL(sha256); +MODULE_DESCRIPTION("SHA-256 Algorithm"); MODULE_LICENSE("GPL"); diff --git a/lib/crypto/simd.c b/lib/crypto/simd.c new file mode 100644 index 000000000000..9c36cb3bb49c --- /dev/null +++ b/lib/crypto/simd.c @@ -0,0 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * SIMD testing utility functions + * + * Copyright 2024 Google LLC + */ + +#include <crypto/internal/simd.h> + +DEFINE_PER_CPU(bool, crypto_simd_disabled_for_test); +EXPORT_PER_CPU_SYMBOL_GPL(crypto_simd_disabled_for_test); diff --git a/lib/crypto/utils.c b/lib/crypto/utils.c index c852c7151b0a..87da2a6dd161 100644 --- a/lib/crypto/utils.c +++ b/lib/crypto/utils.c @@ -5,7 +5,7 @@ * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <crypto/utils.h> #include <linux/module.h> @@ -85,4 +85,5 @@ void __crypto_xor(u8 *dst, const u8 *src1, const u8 *src2, unsigned int len) } EXPORT_SYMBOL_GPL(__crypto_xor); +MODULE_DESCRIPTION("Crypto library utility functions"); MODULE_LICENSE("GPL"); diff --git a/lib/debugobjects.c b/lib/debugobjects.c index fb12a9bacd2f..7f50c4480a4e 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -7,25 +7,30 @@ #define pr_fmt(fmt) "ODEBUG: " fmt +#include <linux/cpu.h> #include <linux/debugobjects.h> -#include <linux/interrupt.h> +#include <linux/debugfs.h> +#include <linux/hash.h> +#include <linux/kmemleak.h> #include <linux/sched.h> +#include <linux/sched/loadavg.h> #include <linux/sched/task_stack.h> #include <linux/seq_file.h> -#include <linux/debugfs.h> #include <linux/slab.h> -#include <linux/hash.h> -#include <linux/kmemleak.h> -#include <linux/cpu.h> +#include <linux/static_key.h> #define ODEBUG_HASH_BITS 14 #define ODEBUG_HASH_SIZE (1 << ODEBUG_HASH_BITS) -#define ODEBUG_POOL_SIZE 1024 -#define ODEBUG_POOL_MIN_LEVEL 256 -#define ODEBUG_POOL_PERCPU_SIZE 64 +/* Must be power of two */ #define ODEBUG_BATCH_SIZE 16 +/* Initial values. Must all be a multiple of batch size */ +#define ODEBUG_POOL_SIZE (64 * ODEBUG_BATCH_SIZE) +#define ODEBUG_POOL_MIN_LEVEL (ODEBUG_POOL_SIZE / 4) + +#define ODEBUG_POOL_PERCPU_SIZE (8 * ODEBUG_BATCH_SIZE) + #define ODEBUG_CHUNK_SHIFT PAGE_SHIFT #define ODEBUG_CHUNK_SIZE (1 << ODEBUG_CHUNK_SHIFT) #define ODEBUG_CHUNK_MASK (~(ODEBUG_CHUNK_SIZE - 1)) @@ -35,7 +40,7 @@ * frequency of 10Hz and about 1024 objects for each freeing operation. * So it is freeing at most 10k debug objects per second. */ -#define ODEBUG_FREE_WORK_MAX 1024 +#define ODEBUG_FREE_WORK_MAX (1024 / ODEBUG_BATCH_SIZE) #define ODEBUG_FREE_WORK_DELAY DIV_ROUND_UP(HZ, 10) struct debug_bucket { @@ -43,16 +48,24 @@ struct debug_bucket { raw_spinlock_t lock; }; -/* - * Debug object percpu free list - * Access is protected by disabling irq - */ -struct debug_percpu_free { - struct hlist_head free_objs; - int obj_free; +struct pool_stats { + unsigned int cur_used; + unsigned int max_used; + unsigned int min_fill; }; -static DEFINE_PER_CPU(struct debug_percpu_free, percpu_obj_pool); +struct obj_pool { + struct hlist_head objects; + unsigned int cnt; + unsigned int min_cnt; + unsigned int max_cnt; + struct pool_stats stats; +} ____cacheline_aligned; + + +static DEFINE_PER_CPU_ALIGNED(struct obj_pool, pool_pcpu) = { + .max_cnt = ODEBUG_POOL_PERCPU_SIZE, +}; static struct debug_bucket obj_hash[ODEBUG_HASH_SIZE]; @@ -60,59 +73,56 @@ static struct debug_obj obj_static_pool[ODEBUG_POOL_SIZE] __initdata; static DEFINE_RAW_SPINLOCK(pool_lock); -static HLIST_HEAD(obj_pool); -static HLIST_HEAD(obj_to_free); +static struct obj_pool pool_global = { + .min_cnt = ODEBUG_POOL_MIN_LEVEL, + .max_cnt = ODEBUG_POOL_SIZE, + .stats = { + .min_fill = ODEBUG_POOL_SIZE, + }, +}; -/* - * Because of the presence of percpu free pools, obj_pool_free will - * under-count those in the percpu free pools. Similarly, obj_pool_used - * will over-count those in the percpu free pools. Adjustments will be - * made at debug_stats_show(). Both obj_pool_min_free and obj_pool_max_used - * can be off. - */ -static int obj_pool_min_free = ODEBUG_POOL_SIZE; -static int obj_pool_free = ODEBUG_POOL_SIZE; -static int obj_pool_used; -static int obj_pool_max_used; +static struct obj_pool pool_to_free = { + .max_cnt = UINT_MAX, +}; + +static HLIST_HEAD(pool_boot); + +static unsigned long avg_usage; static bool obj_freeing; -/* The number of objs on the global free list */ -static int obj_nr_tofree; - -static int debug_objects_maxchain __read_mostly; -static int __maybe_unused debug_objects_maxchecked __read_mostly; -static int debug_objects_fixups __read_mostly; -static int debug_objects_warnings __read_mostly; -static int debug_objects_enabled __read_mostly - = CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT; -static int debug_objects_pool_size __read_mostly - = ODEBUG_POOL_SIZE; -static int debug_objects_pool_min_level __read_mostly - = ODEBUG_POOL_MIN_LEVEL; -static const struct debug_obj_descr *descr_test __read_mostly; -static struct kmem_cache *obj_cache __ro_after_init; + +static int __data_racy debug_objects_maxchain __read_mostly; +static int __data_racy __maybe_unused debug_objects_maxchecked __read_mostly; +static int __data_racy debug_objects_fixups __read_mostly; +static int __data_racy debug_objects_warnings __read_mostly; +static bool __data_racy debug_objects_enabled __read_mostly + = CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT; + +static const struct debug_obj_descr *descr_test __read_mostly; +static struct kmem_cache *obj_cache __ro_after_init; /* * Track numbers of kmem_cache_alloc()/free() calls done. */ -static int debug_objects_allocated; -static int debug_objects_freed; +static int __data_racy debug_objects_allocated; +static int __data_racy debug_objects_freed; static void free_obj_work(struct work_struct *work); static DECLARE_DELAYED_WORK(debug_obj_work, free_obj_work); +static DEFINE_STATIC_KEY_FALSE(obj_cache_enabled); + static int __init enable_object_debug(char *str) { - debug_objects_enabled = 1; + debug_objects_enabled = true; return 0; } +early_param("debug_objects", enable_object_debug); static int __init disable_object_debug(char *str) { - debug_objects_enabled = 0; + debug_objects_enabled = false; return 0; } - -early_param("debug_objects", enable_object_debug); early_param("no_debug_objects", disable_object_debug); static const char *obj_states[ODEBUG_STATE_MAX] = { @@ -124,62 +134,280 @@ static const char *obj_states[ODEBUG_STATE_MAX] = { [ODEBUG_STATE_NOTAVAILABLE] = "not available", }; -static void fill_pool(void) +static __always_inline unsigned int pool_count(struct obj_pool *pool) +{ + return READ_ONCE(pool->cnt); +} + +static __always_inline bool pool_should_refill(struct obj_pool *pool) +{ + return pool_count(pool) < pool->min_cnt; +} + +static __always_inline bool pool_must_refill(struct obj_pool *pool) { - gfp_t gfp = __GFP_HIGH | __GFP_NOWARN; + return pool_count(pool) < pool->min_cnt / 2; +} + +static bool pool_move_batch(struct obj_pool *dst, struct obj_pool *src) +{ + struct hlist_node *last, *next_batch, *first_batch; struct debug_obj *obj; - unsigned long flags; - if (likely(READ_ONCE(obj_pool_free) >= debug_objects_pool_min_level)) + if (dst->cnt >= dst->max_cnt || !src->cnt) + return false; + + first_batch = src->objects.first; + obj = hlist_entry(first_batch, typeof(*obj), node); + last = obj->batch_last; + next_batch = last->next; + + /* Move the next batch to the front of the source pool */ + src->objects.first = next_batch; + if (next_batch) + next_batch->pprev = &src->objects.first; + + /* Add the extracted batch to the destination pool */ + last->next = dst->objects.first; + if (last->next) + last->next->pprev = &last->next; + first_batch->pprev = &dst->objects.first; + dst->objects.first = first_batch; + + WRITE_ONCE(src->cnt, src->cnt - ODEBUG_BATCH_SIZE); + WRITE_ONCE(dst->cnt, dst->cnt + ODEBUG_BATCH_SIZE); + return true; +} + +static bool pool_push_batch(struct obj_pool *dst, struct hlist_head *head) +{ + struct hlist_node *last; + struct debug_obj *obj; + + if (dst->cnt >= dst->max_cnt) + return false; + + obj = hlist_entry(head->first, typeof(*obj), node); + last = obj->batch_last; + + hlist_splice_init(head, last, &dst->objects); + WRITE_ONCE(dst->cnt, dst->cnt + ODEBUG_BATCH_SIZE); + return true; +} + +static bool pool_pop_batch(struct hlist_head *head, struct obj_pool *src) +{ + struct hlist_node *last, *next; + struct debug_obj *obj; + + if (!src->cnt) + return false; + + /* Move the complete list to the head */ + hlist_move_list(&src->objects, head); + + obj = hlist_entry(head->first, typeof(*obj), node); + last = obj->batch_last; + next = last->next; + /* Disconnect the batch from the list */ + last->next = NULL; + + /* Move the node after last back to the source pool. */ + src->objects.first = next; + if (next) + next->pprev = &src->objects.first; + + WRITE_ONCE(src->cnt, src->cnt - ODEBUG_BATCH_SIZE); + return true; +} + +static struct debug_obj *__alloc_object(struct hlist_head *list) +{ + struct debug_obj *obj; + + if (unlikely(!list->first)) + return NULL; + + obj = hlist_entry(list->first, typeof(*obj), node); + hlist_del(&obj->node); + return obj; +} + +static void pcpu_refill_stats(void) +{ + struct pool_stats *stats = &pool_global.stats; + + WRITE_ONCE(stats->cur_used, stats->cur_used + ODEBUG_BATCH_SIZE); + + if (stats->cur_used > stats->max_used) + stats->max_used = stats->cur_used; + + if (pool_global.cnt < stats->min_fill) + stats->min_fill = pool_global.cnt; +} + +static struct debug_obj *pcpu_alloc(void) +{ + struct obj_pool *pcp = this_cpu_ptr(&pool_pcpu); + + lockdep_assert_irqs_disabled(); + + for (;;) { + struct debug_obj *obj = __alloc_object(&pcp->objects); + + if (likely(obj)) { + pcp->cnt--; + /* + * If this emptied a batch try to refill from the + * free pool. Don't do that if this was the top-most + * batch as pcpu_free() expects the per CPU pool + * to be less than ODEBUG_POOL_PERCPU_SIZE. + */ + if (unlikely(pcp->cnt < (ODEBUG_POOL_PERCPU_SIZE - ODEBUG_BATCH_SIZE) && + !(pcp->cnt % ODEBUG_BATCH_SIZE))) { + /* + * Don't try to allocate from the regular pool here + * to not exhaust it prematurely. + */ + if (pool_count(&pool_to_free)) { + guard(raw_spinlock)(&pool_lock); + pool_move_batch(pcp, &pool_to_free); + pcpu_refill_stats(); + } + } + return obj; + } + + guard(raw_spinlock)(&pool_lock); + if (!pool_move_batch(pcp, &pool_to_free)) { + if (!pool_move_batch(pcp, &pool_global)) + return NULL; + } + pcpu_refill_stats(); + } +} + +static void pcpu_free(struct debug_obj *obj) +{ + struct obj_pool *pcp = this_cpu_ptr(&pool_pcpu); + struct debug_obj *first; + + lockdep_assert_irqs_disabled(); + + if (!(pcp->cnt % ODEBUG_BATCH_SIZE)) { + obj->batch_last = &obj->node; + } else { + first = hlist_entry(pcp->objects.first, typeof(*first), node); + obj->batch_last = first->batch_last; + } + hlist_add_head(&obj->node, &pcp->objects); + pcp->cnt++; + + /* Pool full ? */ + if (pcp->cnt < ODEBUG_POOL_PERCPU_SIZE) + return; + + /* Remove a batch from the per CPU pool */ + guard(raw_spinlock)(&pool_lock); + /* Try to fit the batch into the pool_global first */ + if (!pool_move_batch(&pool_global, pcp)) + pool_move_batch(&pool_to_free, pcp); + WRITE_ONCE(pool_global.stats.cur_used, pool_global.stats.cur_used - ODEBUG_BATCH_SIZE); +} + +static void free_object_list(struct hlist_head *head) +{ + struct hlist_node *tmp; + struct debug_obj *obj; + int cnt = 0; + + hlist_for_each_entry_safe(obj, tmp, head, node) { + hlist_del(&obj->node); + kmem_cache_free(obj_cache, obj); + cnt++; + } + debug_objects_freed += cnt; +} + +static void fill_pool_from_freelist(void) +{ + static unsigned long state; + + /* + * Reuse objs from the global obj_to_free list; they will be + * reinitialized when allocating. + */ + if (!pool_count(&pool_to_free)) return; /* - * Reuse objs from the global free list; they will be reinitialized - * when allocating. - * - * Both obj_nr_tofree and obj_pool_free are checked locklessly; the - * READ_ONCE()s pair with the WRITE_ONCE()s in pool_lock critical - * sections. + * Prevent the context from being scheduled or interrupted after + * setting the state flag; */ - while (READ_ONCE(obj_nr_tofree) && (READ_ONCE(obj_pool_free) < obj_pool_min_free)) { - raw_spin_lock_irqsave(&pool_lock, flags); - /* - * Recheck with the lock held as the worker thread might have - * won the race and freed the global free list already. - */ - while (obj_nr_tofree && (obj_pool_free < obj_pool_min_free)) { - obj = hlist_entry(obj_to_free.first, typeof(*obj), node); - hlist_del(&obj->node); - WRITE_ONCE(obj_nr_tofree, obj_nr_tofree - 1); - hlist_add_head(&obj->node, &obj_pool); - WRITE_ONCE(obj_pool_free, obj_pool_free + 1); + guard(irqsave)(); + + /* + * Avoid lock contention on &pool_lock and avoid making the cache + * line exclusive by testing the bit before attempting to set it. + */ + if (test_bit(0, &state) || test_and_set_bit(0, &state)) + return; + + /* Avoid taking the lock when there is no work to do */ + while (pool_should_refill(&pool_global) && pool_count(&pool_to_free)) { + guard(raw_spinlock)(&pool_lock); + /* Move a batch if possible */ + pool_move_batch(&pool_global, &pool_to_free); + } + clear_bit(0, &state); +} + +static bool kmem_alloc_batch(struct hlist_head *head, struct kmem_cache *cache, gfp_t gfp) +{ + struct hlist_node *last = NULL; + struct debug_obj *obj; + + for (int cnt = 0; cnt < ODEBUG_BATCH_SIZE; cnt++) { + obj = kmem_cache_zalloc(cache, gfp); + if (!obj) { + free_object_list(head); + return false; } - raw_spin_unlock_irqrestore(&pool_lock, flags); + debug_objects_allocated++; + + if (!last) + last = &obj->node; + obj->batch_last = last; + + hlist_add_head(&obj->node, head); } + return true; +} + +static void fill_pool(void) +{ + static atomic_t cpus_allocating; - if (unlikely(!obj_cache)) + /* + * Avoid allocation and lock contention when: + * - One other CPU is already allocating + * - the global pool has not reached the critical level yet + */ + if (!pool_must_refill(&pool_global) && atomic_read(&cpus_allocating)) return; - while (READ_ONCE(obj_pool_free) < debug_objects_pool_min_level) { - struct debug_obj *new[ODEBUG_BATCH_SIZE]; - int cnt; + atomic_inc(&cpus_allocating); + while (pool_should_refill(&pool_global)) { + HLIST_HEAD(head); - for (cnt = 0; cnt < ODEBUG_BATCH_SIZE; cnt++) { - new[cnt] = kmem_cache_zalloc(obj_cache, gfp); - if (!new[cnt]) - break; - } - if (!cnt) - return; + if (!kmem_alloc_batch(&head, obj_cache, __GFP_HIGH | __GFP_NOWARN)) + break; - raw_spin_lock_irqsave(&pool_lock, flags); - while (cnt) { - hlist_add_head(&new[--cnt]->node, &obj_pool); - debug_objects_allocated++; - WRITE_ONCE(obj_pool_free, obj_pool_free + 1); - } - raw_spin_unlock_irqrestore(&pool_lock, flags); + guard(raw_spinlock_irqsave)(&pool_lock); + if (!pool_push_batch(&pool_global, &head)) + pool_push_batch(&pool_to_free, &head); } + atomic_dec(&cpus_allocating); } /* @@ -201,72 +429,37 @@ static struct debug_obj *lookup_object(void *addr, struct debug_bucket *b) return NULL; } -/* - * Allocate a new object from the hlist - */ -static struct debug_obj *__alloc_object(struct hlist_head *list) +static void calc_usage(void) { - struct debug_obj *obj = NULL; + static DEFINE_RAW_SPINLOCK(avg_lock); + static unsigned long avg_period; + unsigned long cur, now = jiffies; - if (list->first) { - obj = hlist_entry(list->first, typeof(*obj), node); - hlist_del(&obj->node); - } + if (!time_after_eq(now, READ_ONCE(avg_period))) + return; - return obj; + if (!raw_spin_trylock(&avg_lock)) + return; + + WRITE_ONCE(avg_period, now + msecs_to_jiffies(10)); + cur = READ_ONCE(pool_global.stats.cur_used) * ODEBUG_FREE_WORK_MAX; + WRITE_ONCE(avg_usage, calc_load(avg_usage, EXP_5, cur)); + raw_spin_unlock(&avg_lock); } -static struct debug_obj * -alloc_object(void *addr, struct debug_bucket *b, const struct debug_obj_descr *descr) +static struct debug_obj *alloc_object(void *addr, struct debug_bucket *b, + const struct debug_obj_descr *descr) { - struct debug_percpu_free *percpu_pool = this_cpu_ptr(&percpu_obj_pool); struct debug_obj *obj; - if (likely(obj_cache)) { - obj = __alloc_object(&percpu_pool->free_objs); - if (obj) { - percpu_pool->obj_free--; - goto init_obj; - } - } - - raw_spin_lock(&pool_lock); - obj = __alloc_object(&obj_pool); - if (obj) { - obj_pool_used++; - WRITE_ONCE(obj_pool_free, obj_pool_free - 1); - - /* - * Looking ahead, allocate one batch of debug objects and - * put them into the percpu free pool. - */ - if (likely(obj_cache)) { - int i; - - for (i = 0; i < ODEBUG_BATCH_SIZE; i++) { - struct debug_obj *obj2; - - obj2 = __alloc_object(&obj_pool); - if (!obj2) - break; - hlist_add_head(&obj2->node, - &percpu_pool->free_objs); - percpu_pool->obj_free++; - obj_pool_used++; - WRITE_ONCE(obj_pool_free, obj_pool_free - 1); - } - } + calc_usage(); - if (obj_pool_used > obj_pool_max_used) - obj_pool_max_used = obj_pool_used; - - if (obj_pool_free < obj_pool_min_free) - obj_pool_min_free = obj_pool_free; - } - raw_spin_unlock(&pool_lock); + if (static_branch_likely(&obj_cache_enabled)) + obj = pcpu_alloc(); + else + obj = __alloc_object(&pool_boot); -init_obj: - if (obj) { + if (likely(obj)) { obj->object = addr; obj->descr = descr; obj->state = ODEBUG_STATE_NONE; @@ -276,142 +469,58 @@ init_obj: return obj; } -/* - * workqueue function to free objects. - * - * To reduce contention on the global pool_lock, the actual freeing of - * debug objects will be delayed if the pool_lock is busy. - */ +/* workqueue function to free objects. */ static void free_obj_work(struct work_struct *work) { - struct hlist_node *tmp; - struct debug_obj *obj; - unsigned long flags; - HLIST_HEAD(tofree); + static unsigned long last_use_avg; + unsigned long cur_used, last_used, delta; + unsigned int max_free = 0; WRITE_ONCE(obj_freeing, false); - if (!raw_spin_trylock_irqsave(&pool_lock, flags)) - return; - if (obj_pool_free >= debug_objects_pool_size) - goto free_objs; + /* Rate limit freeing based on current use average */ + cur_used = READ_ONCE(avg_usage); + last_used = last_use_avg; + last_use_avg = cur_used; - /* - * The objs on the pool list might be allocated before the work is - * run, so recheck if pool list it full or not, if not fill pool - * list from the global free list. As it is likely that a workload - * may be gearing up to use more and more objects, don't free any - * of them until the next round. - */ - while (obj_nr_tofree && obj_pool_free < debug_objects_pool_size) { - obj = hlist_entry(obj_to_free.first, typeof(*obj), node); - hlist_del(&obj->node); - hlist_add_head(&obj->node, &obj_pool); - WRITE_ONCE(obj_pool_free, obj_pool_free + 1); - WRITE_ONCE(obj_nr_tofree, obj_nr_tofree - 1); - } - raw_spin_unlock_irqrestore(&pool_lock, flags); - return; + if (!pool_count(&pool_to_free)) + return; -free_objs: - /* - * Pool list is already full and there are still objs on the free - * list. Move remaining free objs to a temporary list to free the - * memory outside the pool_lock held region. - */ - if (obj_nr_tofree) { - hlist_move_list(&obj_to_free, &tofree); - debug_objects_freed += obj_nr_tofree; - WRITE_ONCE(obj_nr_tofree, 0); + if (cur_used <= last_used) { + delta = (last_used - cur_used) / ODEBUG_FREE_WORK_MAX; + max_free = min(delta, ODEBUG_FREE_WORK_MAX); } - raw_spin_unlock_irqrestore(&pool_lock, flags); - hlist_for_each_entry_safe(obj, tmp, &tofree, node) { - hlist_del(&obj->node); - kmem_cache_free(obj_cache, obj); + for (int cnt = 0; cnt < ODEBUG_FREE_WORK_MAX; cnt++) { + HLIST_HEAD(tofree); + + /* Acquire and drop the lock for each batch */ + scoped_guard(raw_spinlock_irqsave, &pool_lock) { + if (!pool_to_free.cnt) + return; + + /* Refill the global pool if possible */ + if (pool_move_batch(&pool_global, &pool_to_free)) { + /* Don't free as there seems to be demand */ + max_free = 0; + } else if (max_free) { + pool_pop_batch(&tofree, &pool_to_free); + max_free--; + } else { + return; + } + } + free_object_list(&tofree); } } static void __free_object(struct debug_obj *obj) { - struct debug_obj *objs[ODEBUG_BATCH_SIZE]; - struct debug_percpu_free *percpu_pool; - int lookahead_count = 0; - unsigned long flags; - bool work; - - local_irq_save(flags); - if (!obj_cache) - goto free_to_obj_pool; - - /* - * Try to free it into the percpu pool first. - */ - percpu_pool = this_cpu_ptr(&percpu_obj_pool); - if (percpu_pool->obj_free < ODEBUG_POOL_PERCPU_SIZE) { - hlist_add_head(&obj->node, &percpu_pool->free_objs); - percpu_pool->obj_free++; - local_irq_restore(flags); - return; - } - - /* - * As the percpu pool is full, look ahead and pull out a batch - * of objects from the percpu pool and free them as well. - */ - for (; lookahead_count < ODEBUG_BATCH_SIZE; lookahead_count++) { - objs[lookahead_count] = __alloc_object(&percpu_pool->free_objs); - if (!objs[lookahead_count]) - break; - percpu_pool->obj_free--; - } - -free_to_obj_pool: - raw_spin_lock(&pool_lock); - work = (obj_pool_free > debug_objects_pool_size) && obj_cache && - (obj_nr_tofree < ODEBUG_FREE_WORK_MAX); - obj_pool_used--; - - if (work) { - WRITE_ONCE(obj_nr_tofree, obj_nr_tofree + 1); - hlist_add_head(&obj->node, &obj_to_free); - if (lookahead_count) { - WRITE_ONCE(obj_nr_tofree, obj_nr_tofree + lookahead_count); - obj_pool_used -= lookahead_count; - while (lookahead_count) { - hlist_add_head(&objs[--lookahead_count]->node, - &obj_to_free); - } - } - - if ((obj_pool_free > debug_objects_pool_size) && - (obj_nr_tofree < ODEBUG_FREE_WORK_MAX)) { - int i; - - /* - * Free one more batch of objects from obj_pool. - */ - for (i = 0; i < ODEBUG_BATCH_SIZE; i++) { - obj = __alloc_object(&obj_pool); - hlist_add_head(&obj->node, &obj_to_free); - WRITE_ONCE(obj_pool_free, obj_pool_free - 1); - WRITE_ONCE(obj_nr_tofree, obj_nr_tofree + 1); - } - } - } else { - WRITE_ONCE(obj_pool_free, obj_pool_free + 1); - hlist_add_head(&obj->node, &obj_pool); - if (lookahead_count) { - WRITE_ONCE(obj_pool_free, obj_pool_free + lookahead_count); - obj_pool_used -= lookahead_count; - while (lookahead_count) { - hlist_add_head(&objs[--lookahead_count]->node, - &obj_pool); - } - } - } - raw_spin_unlock(&pool_lock); - local_irq_restore(flags); + guard(irqsave)(); + if (static_branch_likely(&obj_cache_enabled)) + pcpu_free(obj); + else + hlist_add_head(&obj->node, &pool_boot); } /* @@ -421,63 +530,52 @@ free_to_obj_pool: static void free_object(struct debug_obj *obj) { __free_object(obj); - if (!READ_ONCE(obj_freeing) && READ_ONCE(obj_nr_tofree)) { + if (!READ_ONCE(obj_freeing) && pool_count(&pool_to_free)) { WRITE_ONCE(obj_freeing, true); schedule_delayed_work(&debug_obj_work, ODEBUG_FREE_WORK_DELAY); } } -#ifdef CONFIG_HOTPLUG_CPU -static int object_cpu_offline(unsigned int cpu) +static void put_objects(struct hlist_head *list) { - struct debug_percpu_free *percpu_pool; struct hlist_node *tmp; struct debug_obj *obj; - unsigned long flags; - /* Remote access is safe as the CPU is dead already */ - percpu_pool = per_cpu_ptr(&percpu_obj_pool, cpu); - hlist_for_each_entry_safe(obj, tmp, &percpu_pool->free_objs, node) { + /* + * Using free_object() puts the objects into reuse or schedules + * them for freeing and it get's all the accounting correct. + */ + hlist_for_each_entry_safe(obj, tmp, list, node) { hlist_del(&obj->node); - kmem_cache_free(obj_cache, obj); + free_object(obj); } +} - raw_spin_lock_irqsave(&pool_lock, flags); - obj_pool_used -= percpu_pool->obj_free; - debug_objects_freed += percpu_pool->obj_free; - raw_spin_unlock_irqrestore(&pool_lock, flags); - - percpu_pool->obj_free = 0; +#ifdef CONFIG_HOTPLUG_CPU +static int object_cpu_offline(unsigned int cpu) +{ + /* Remote access is safe as the CPU is dead already */ + struct obj_pool *pcp = per_cpu_ptr(&pool_pcpu, cpu); + put_objects(&pcp->objects); + pcp->cnt = 0; return 0; } #endif -/* - * We run out of memory. That means we probably have tons of objects - * allocated. - */ +/* Out of memory. Free all objects from hash */ static void debug_objects_oom(void) { struct debug_bucket *db = obj_hash; - struct hlist_node *tmp; HLIST_HEAD(freelist); - struct debug_obj *obj; - unsigned long flags; - int i; pr_warn("Out of memory. ODEBUG disabled\n"); - for (i = 0; i < ODEBUG_HASH_SIZE; i++, db++) { - raw_spin_lock_irqsave(&db->lock, flags); - hlist_move_list(&db->list, &freelist); - raw_spin_unlock_irqrestore(&db->lock, flags); + for (int i = 0; i < ODEBUG_HASH_SIZE; i++, db++) { + scoped_guard(raw_spinlock_irqsave, &db->lock) + hlist_move_list(&db->list, &freelist); - /* Now free them */ - hlist_for_each_entry_safe(obj, tmp, &freelist, node) { - hlist_del(&obj->node); - free_object(obj); - } + put_objects(&freelist); } } @@ -592,12 +690,24 @@ static struct debug_obj *lookup_object_or_alloc(void *addr, struct debug_bucket } /* Out of memory. Do the cleanup outside of the locked region */ - debug_objects_enabled = 0; + debug_objects_enabled = false; return NULL; } static void debug_objects_fill_pool(void) { + if (!static_branch_likely(&obj_cache_enabled)) + return; + + if (likely(!pool_should_refill(&pool_global))) + return; + + /* Try reusing objects from obj_to_free_list */ + fill_pool_from_freelist(); + + if (likely(!pool_should_refill(&pool_global))) + return; + /* * On RT enabled kernels the pool refill must happen in preemptible * context -- for !RT kernels we rely on the fact that spinlock_t and @@ -1007,7 +1117,7 @@ repeat: debug_objects_maxchecked = objs_checked; /* Schedule work to actually kmem_cache_free() objects */ - if (!READ_ONCE(obj_freeing) && READ_ONCE(obj_nr_tofree)) { + if (!READ_ONCE(obj_freeing) && pool_count(&pool_to_free)) { WRITE_ONCE(obj_freeing, true); schedule_delayed_work(&debug_obj_work, ODEBUG_FREE_WORK_DELAY); } @@ -1024,23 +1134,33 @@ void debug_check_no_obj_freed(const void *address, unsigned long size) static int debug_stats_show(struct seq_file *m, void *v) { - int cpu, obj_percpu_free = 0; + unsigned int cpu, pool_used, pcp_free = 0; + /* + * pool_global.stats.cur_used is the number of batches currently + * handed out to per CPU pools. Convert it to number of objects + * and subtract the number of free objects in the per CPU pools. + * As this is lockless the number is an estimate. + */ for_each_possible_cpu(cpu) - obj_percpu_free += per_cpu(percpu_obj_pool.obj_free, cpu); - - seq_printf(m, "max_chain :%d\n", debug_objects_maxchain); - seq_printf(m, "max_checked :%d\n", debug_objects_maxchecked); - seq_printf(m, "warnings :%d\n", debug_objects_warnings); - seq_printf(m, "fixups :%d\n", debug_objects_fixups); - seq_printf(m, "pool_free :%d\n", READ_ONCE(obj_pool_free) + obj_percpu_free); - seq_printf(m, "pool_pcp_free :%d\n", obj_percpu_free); - seq_printf(m, "pool_min_free :%d\n", obj_pool_min_free); - seq_printf(m, "pool_used :%d\n", obj_pool_used - obj_percpu_free); - seq_printf(m, "pool_max_used :%d\n", obj_pool_max_used); - seq_printf(m, "on_free_list :%d\n", READ_ONCE(obj_nr_tofree)); - seq_printf(m, "objs_allocated:%d\n", debug_objects_allocated); - seq_printf(m, "objs_freed :%d\n", debug_objects_freed); + pcp_free += per_cpu(pool_pcpu.cnt, cpu); + + pool_used = READ_ONCE(pool_global.stats.cur_used); + pcp_free = min(pool_used, pcp_free); + pool_used -= pcp_free; + + seq_printf(m, "max_chain : %d\n", debug_objects_maxchain); + seq_printf(m, "max_checked : %d\n", debug_objects_maxchecked); + seq_printf(m, "warnings : %d\n", debug_objects_warnings); + seq_printf(m, "fixups : %d\n", debug_objects_fixups); + seq_printf(m, "pool_free : %u\n", pool_count(&pool_global) + pcp_free); + seq_printf(m, "pool_pcp_free : %u\n", pcp_free); + seq_printf(m, "pool_min_free : %u\n", data_race(pool_global.stats.min_fill)); + seq_printf(m, "pool_used : %u\n", pool_used); + seq_printf(m, "pool_max_used : %u\n", data_race(pool_global.stats.max_used)); + seq_printf(m, "on_free_list : %u\n", pool_count(&pool_to_free)); + seq_printf(m, "objs_allocated: %d\n", debug_objects_allocated); + seq_printf(m, "objs_freed : %d\n", debug_objects_freed); return 0; } DEFINE_SHOW_ATTRIBUTE(debug_stats); @@ -1194,7 +1314,7 @@ check_results(void *addr, enum debug_obj_state state, int fixups, int warnings) out: raw_spin_unlock_irqrestore(&db->lock, flags); if (res) - debug_objects_enabled = 0; + debug_objects_enabled = false; return res; } @@ -1209,7 +1329,7 @@ static __initconst const struct debug_obj_descr descr_type_test = { static __initdata struct self_test obj = { .static_init = 0 }; -static void __init debug_objects_selftest(void) +static bool __init debug_objects_selftest(void) { int fixups, oldfixups, warnings, oldwarnings; unsigned long flags; @@ -1278,9 +1398,10 @@ out: descr_test = NULL; local_irq_restore(flags); + return debug_objects_enabled; } #else -static inline void debug_objects_selftest(void) { } +static inline bool debug_objects_selftest(void) { return true; } #endif /* @@ -1295,65 +1416,54 @@ void __init debug_objects_early_init(void) for (i = 0; i < ODEBUG_HASH_SIZE; i++) raw_spin_lock_init(&obj_hash[i].lock); + /* Keep early boot simple and add everything to the boot list */ for (i = 0; i < ODEBUG_POOL_SIZE; i++) - hlist_add_head(&obj_static_pool[i].node, &obj_pool); + hlist_add_head(&obj_static_pool[i].node, &pool_boot); } /* - * Convert the statically allocated objects to dynamic ones: + * Convert the statically allocated objects to dynamic ones. + * debug_objects_mem_init() is called early so only one CPU is up and + * interrupts are disabled, which means it is safe to replace the active + * object references. */ -static int __init debug_objects_replace_static_objects(void) +static bool __init debug_objects_replace_static_objects(struct kmem_cache *cache) { struct debug_bucket *db = obj_hash; struct hlist_node *tmp; - struct debug_obj *obj, *new; + struct debug_obj *obj; HLIST_HEAD(objects); - int i, cnt = 0; + int i; - for (i = 0; i < ODEBUG_POOL_SIZE; i++) { - obj = kmem_cache_zalloc(obj_cache, GFP_KERNEL); - if (!obj) + for (i = 0; i < ODEBUG_POOL_SIZE; i += ODEBUG_BATCH_SIZE) { + if (!kmem_alloc_batch(&objects, cache, GFP_KERNEL)) goto free; - hlist_add_head(&obj->node, &objects); + pool_push_batch(&pool_global, &objects); } - debug_objects_allocated += i; - - /* - * debug_objects_mem_init() is now called early that only one CPU is up - * and interrupts have been disabled, so it is safe to replace the - * active object references. - */ - - /* Remove the statically allocated objects from the pool */ - hlist_for_each_entry_safe(obj, tmp, &obj_pool, node) - hlist_del(&obj->node); - /* Move the allocated objects to the pool */ - hlist_move_list(&objects, &obj_pool); + /* Disconnect the boot pool. */ + pool_boot.first = NULL; /* Replace the active object references */ for (i = 0; i < ODEBUG_HASH_SIZE; i++, db++) { hlist_move_list(&db->list, &objects); hlist_for_each_entry(obj, &objects, node) { - new = hlist_entry(obj_pool.first, typeof(*obj), node); - hlist_del(&new->node); + struct debug_obj *new = pcpu_alloc(); + /* copy object data */ *new = *obj; hlist_add_head(&new->node, &db->list); - cnt++; } } - - pr_debug("%d of %d active objects replaced\n", - cnt, obj_pool_used); - return 0; + return true; free: - hlist_for_each_entry_safe(obj, tmp, &objects, node) { + /* Can't use free_object_list() as the cache is not populated yet */ + hlist_for_each_entry_safe(obj, tmp, &pool_global.objects, node) { hlist_del(&obj->node); - kmem_cache_free(obj_cache, obj); + kmem_cache_free(cache, obj); } - return -ENOMEM; + return false; } /* @@ -1364,43 +1474,40 @@ free: */ void __init debug_objects_mem_init(void) { - int cpu, extras; + struct kmem_cache *cache; + int extras; if (!debug_objects_enabled) return; - /* - * Initialize the percpu object pools - * - * Initialization is not strictly necessary, but was done for - * completeness. - */ - for_each_possible_cpu(cpu) - INIT_HLIST_HEAD(&per_cpu(percpu_obj_pool.free_objs, cpu)); + if (!debug_objects_selftest()) + return; - obj_cache = kmem_cache_create("debug_objects_cache", - sizeof (struct debug_obj), 0, - SLAB_DEBUG_OBJECTS | SLAB_NOLEAKTRACE, - NULL); + cache = kmem_cache_create("debug_objects_cache", sizeof (struct debug_obj), 0, + SLAB_DEBUG_OBJECTS | SLAB_NOLEAKTRACE, NULL); - if (!obj_cache || debug_objects_replace_static_objects()) { - debug_objects_enabled = 0; - kmem_cache_destroy(obj_cache); - pr_warn("out of memory.\n"); + if (!cache || !debug_objects_replace_static_objects(cache)) { + debug_objects_enabled = false; + pr_warn("Out of memory.\n"); return; - } else - debug_objects_selftest(); - -#ifdef CONFIG_HOTPLUG_CPU - cpuhp_setup_state_nocalls(CPUHP_DEBUG_OBJ_DEAD, "object:offline", NULL, - object_cpu_offline); -#endif + } /* - * Increase the thresholds for allocating and freeing objects - * according to the number of possible CPUs available in the system. + * Adjust the thresholds for allocating and freeing objects + * according to the number of possible CPUs available in the + * system. */ extras = num_possible_cpus() * ODEBUG_BATCH_SIZE; - debug_objects_pool_size += extras; - debug_objects_pool_min_level += extras; + pool_global.max_cnt += extras; + pool_global.min_cnt += extras; + + /* Everything worked. Expose the cache */ + obj_cache = cache; + static_branch_enable(&obj_cache_enabled); + +#ifdef CONFIG_HOTPLUG_CPU + cpuhp_setup_state_nocalls(CPUHP_DEBUG_OBJ_DEAD, "object:offline", NULL, + object_cpu_offline); +#endif + return; } diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c index 3518e7394eca..ca736166f100 100644 --- a/lib/decompress_bunzip2.c +++ b/lib/decompress_bunzip2.c @@ -232,7 +232,8 @@ static int INIT get_next_block(struct bunzip_data *bd) RUNB) */ symCount = symTotal+2; for (j = 0; j < groupCount; j++) { - unsigned char length[MAX_SYMBOLS], temp[MAX_HUFCODE_BITS+1]; + unsigned char length[MAX_SYMBOLS]; + unsigned short temp[MAX_HUFCODE_BITS+1]; int minLen, maxLen, pp; /* Read Huffman code lengths for each symbol. They're stored in a way similar to mtf; record a starting diff --git a/lib/decompress_unlz4.c b/lib/decompress_unlz4.c index e6327391b6b6..c0dbb3cea915 100644 --- a/lib/decompress_unlz4.c +++ b/lib/decompress_unlz4.c @@ -16,7 +16,7 @@ #include <linux/decompress/mm.h> #include <linux/compiler.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /* * Note: Uncompressed chunk size is used in the compressor side diff --git a/lib/decompress_unlzma.c b/lib/decompress_unlzma.c index 20a858031f12..9d34d35908da 100644 --- a/lib/decompress_unlzma.c +++ b/lib/decompress_unlzma.c @@ -37,7 +37,9 @@ #include <linux/decompress/mm.h> +#ifndef MIN #define MIN(a, b) (((a) < (b)) ? (a) : (b)) +#endif static long long INIT read_int(unsigned char *ptr, int size) { diff --git a/lib/decompress_unlzo.c b/lib/decompress_unlzo.c index 64c1358500ce..57a9e93743e1 100644 --- a/lib/decompress_unlzo.c +++ b/lib/decompress_unlzo.c @@ -28,7 +28,7 @@ #include <linux/decompress/mm.h> #include <linux/compiler.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> static const unsigned char lzop_magic[] = { 0x89, 0x4c, 0x5a, 0x4f, 0x00, 0x0d, 0x0a, 0x1a, 0x0a }; diff --git a/lib/decompress_unxz.c b/lib/decompress_unxz.c index 842894158944..32138bb8ef77 100644 --- a/lib/decompress_unxz.c +++ b/lib/decompress_unxz.c @@ -1,10 +1,9 @@ +// SPDX-License-Identifier: 0BSD + /* * Wrapper for decompressing XZ-compressed kernel, initramfs, and initrd * * Author: Lasse Collin <lasse.collin@tukaani.org> - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ /* @@ -103,12 +102,11 @@ #ifdef STATIC # define XZ_PREBOOT #else -#include <linux/decompress/unxz.h> +# include <linux/decompress/unxz.h> #endif #ifdef __KERNEL__ # include <linux/decompress/mm.h> #endif -#define XZ_EXTERN STATIC #ifndef XZ_PREBOOT # include <linux/slab.h> @@ -127,11 +125,21 @@ #ifdef CONFIG_X86 # define XZ_DEC_X86 #endif -#ifdef CONFIG_PPC +#if defined(CONFIG_PPC) && defined(CONFIG_CPU_BIG_ENDIAN) # define XZ_DEC_POWERPC #endif #ifdef CONFIG_ARM -# define XZ_DEC_ARM +# ifdef CONFIG_THUMB2_KERNEL +# define XZ_DEC_ARMTHUMB +# else +# define XZ_DEC_ARM +# endif +#endif +#ifdef CONFIG_ARM64 +# define XZ_DEC_ARM64 +#endif +#ifdef CONFIG_RISCV +# define XZ_DEC_RISCV #endif #ifdef CONFIG_SPARC # define XZ_DEC_SPARC @@ -220,7 +228,7 @@ void *memmove(void *dest, const void *src, size_t size) #endif /* - * Since we need memmove anyway, would use it as memcpy too. + * Since we need memmove anyway, we could use it as memcpy too. * Commented out for now to avoid breaking things. */ /* @@ -390,17 +398,17 @@ error_alloc_state: } /* - * This macro is used by architecture-specific files to decompress + * This function is used by architecture-specific files to decompress * the kernel image. */ #ifdef XZ_PREBOOT -STATIC int INIT __decompress(unsigned char *buf, long len, - long (*fill)(void*, unsigned long), - long (*flush)(void*, unsigned long), - unsigned char *out_buf, long olen, - long *pos, - void (*error)(char *x)) +STATIC int INIT __decompress(unsigned char *in, long in_size, + long (*fill)(void *dest, unsigned long size), + long (*flush)(void *src, unsigned long size), + unsigned char *out, long out_size, + long *in_used, + void (*error)(char *x)) { - return unxz(buf, len, fill, flush, out_buf, pos, error); + return unxz(in, in_size, fill, flush, out, in_used, error); } #endif diff --git a/lib/devres.c b/lib/devres.c index fe0c63caeb68..73901160197e 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -1,10 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 +#include <linux/bug.h> #include <linux/device.h> -#include <linux/err.h> -#include <linux/io.h> -#include <linux/gfp.h> +#include <linux/errno.h> #include <linux/export.h> +#include <linux/gfp_types.h> +#include <linux/io.h> +#include <linux/ioport.h> #include <linux/of_address.h> +#include <linux/types.h> enum devm_ioremap_type { DEVM_IOREMAP = 0, @@ -112,9 +115,8 @@ EXPORT_SYMBOL(devm_ioremap_wc); */ void devm_iounmap(struct device *dev, void __iomem *addr) { - WARN_ON(devres_destroy(dev, devm_ioremap_release, devm_ioremap_match, + WARN_ON(devres_release(dev, devm_ioremap_release, devm_ioremap_match, (__force void *)addr)); - iounmap(addr); } EXPORT_SYMBOL(devm_iounmap); @@ -125,12 +127,13 @@ __devm_ioremap_resource(struct device *dev, const struct resource *res, resource_size_t size; void __iomem *dest_ptr; char *pretty_name; + int ret; BUG_ON(!dev); if (!res || resource_type(res) != IORESOURCE_MEM) { - dev_err(dev, "invalid resource %pR\n", res); - return IOMEM_ERR_PTR(-EINVAL); + ret = dev_err_probe(dev, -EINVAL, "invalid resource %pR\n", res); + return IOMEM_ERR_PTR(ret); } if (type == DEVM_IOREMAP && res->flags & IORESOURCE_MEM_NONPOSTED) @@ -144,20 +147,20 @@ __devm_ioremap_resource(struct device *dev, const struct resource *res, else pretty_name = devm_kstrdup(dev, dev_name(dev), GFP_KERNEL); if (!pretty_name) { - dev_err(dev, "can't generate pretty name for resource %pR\n", res); - return IOMEM_ERR_PTR(-ENOMEM); + ret = dev_err_probe(dev, -ENOMEM, "can't generate pretty name for resource %pR\n", res); + return IOMEM_ERR_PTR(ret); } if (!devm_request_mem_region(dev, res->start, size, pretty_name)) { - dev_err(dev, "can't request region for resource %pR\n", res); - return IOMEM_ERR_PTR(-EBUSY); + ret = dev_err_probe(dev, -EBUSY, "can't request region for resource %pR\n", res); + return IOMEM_ERR_PTR(ret); } dest_ptr = __devm_ioremap(dev, res->start, size, type); if (!dest_ptr) { - dev_err(dev, "ioremap failed for resource %pR\n", res); devm_release_mem_region(dev, res->start, size); - dest_ptr = IOMEM_ERR_PTR(-ENOMEM); + ret = dev_err_probe(dev, -ENOMEM, "ioremap failed for resource %pR\n", res); + return IOMEM_ERR_PTR(ret); } return dest_ptr; @@ -304,8 +307,7 @@ EXPORT_SYMBOL(devm_ioport_map); */ void devm_ioport_unmap(struct device *dev, void __iomem *addr) { - ioport_unmap(addr); - WARN_ON(devres_destroy(dev, devm_ioport_map_release, + WARN_ON(devres_release(dev, devm_ioport_map_release, devm_ioport_map_match, (__force void *)addr)); } EXPORT_SYMBOL(devm_ioport_unmap); diff --git a/lib/dhry_run.c b/lib/dhry_run.c index e6a279dabf84..4a6d05ce4361 100644 --- a/lib/dhry_run.c +++ b/lib/dhry_run.c @@ -83,4 +83,5 @@ static int __init dhry_init(void) module_init(dhry_init); MODULE_AUTHOR("Geert Uytterhoeven <geert+renesas@glider.be>"); +MODULE_DESCRIPTION("Dhrystone benchmark test module"); MODULE_LICENSE("GPL"); diff --git a/lib/dim/Makefile b/lib/dim/Makefile index c4cc4026c451..5b9bfaac7ac1 100644 --- a/lib/dim/Makefile +++ b/lib/dim/Makefile @@ -4,4 +4,4 @@ obj-$(CONFIG_DIMLIB) += dimlib.o -dimlib-objs := dim.o net_dim.o rdma_dim.o +dimlib-y := dim.o net_dim.o rdma_dim.o diff --git a/lib/dim/dim.c b/lib/dim/dim.c index 83b65ac74d73..97c3d084ebf0 100644 --- a/lib/dim/dim.c +++ b/lib/dim/dim.c @@ -54,7 +54,8 @@ void dim_park_tired(struct dim *dim) } EXPORT_SYMBOL(dim_park_tired); -bool dim_calc_stats(struct dim_sample *start, struct dim_sample *end, +bool dim_calc_stats(const struct dim_sample *start, + const struct dim_sample *end, struct dim_stats *curr_stats) { /* u32 holds up to 71 minutes, should be enough */ diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c index 4e32f7aaac86..d6aa09a979b3 100644 --- a/lib/dim/net_dim.c +++ b/lib/dim/net_dim.c @@ -4,6 +4,7 @@ */ #include <linux/dim.h> +#include <linux/rtnetlink.h> /* * Net DIM profiles: @@ -11,12 +12,6 @@ * There are different set of profiles for RX/TX CQs. * Each profile size must be of NET_DIM_PARAMS_NUM_PROFILES */ -#define NET_DIM_PARAMS_NUM_PROFILES 5 -#define NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE 256 -#define NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE 128 -#define NET_DIM_DEF_PROFILE_CQE 1 -#define NET_DIM_DEF_PROFILE_EQE 1 - #define NET_DIM_RX_EQE_PROFILES { \ {.usec = 1, .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \ {.usec = 8, .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \ @@ -101,6 +96,143 @@ net_dim_get_def_tx_moderation(u8 cq_period_mode) } EXPORT_SYMBOL(net_dim_get_def_tx_moderation); +int net_dim_init_irq_moder(struct net_device *dev, u8 profile_flags, + u8 coal_flags, u8 rx_mode, u8 tx_mode, + void (*rx_dim_work)(struct work_struct *work), + void (*tx_dim_work)(struct work_struct *work)) +{ + struct dim_cq_moder *rxp = NULL, *txp; + struct dim_irq_moder *moder; + int len; + + dev->irq_moder = kzalloc(sizeof(*dev->irq_moder), GFP_KERNEL); + if (!dev->irq_moder) + return -ENOMEM; + + moder = dev->irq_moder; + len = NET_DIM_PARAMS_NUM_PROFILES * sizeof(*moder->rx_profile); + + moder->coal_flags = coal_flags; + moder->profile_flags = profile_flags; + + if (profile_flags & DIM_PROFILE_RX) { + moder->rx_dim_work = rx_dim_work; + moder->dim_rx_mode = rx_mode; + rxp = kmemdup(rx_profile[rx_mode], len, GFP_KERNEL); + if (!rxp) + goto free_moder; + + rcu_assign_pointer(moder->rx_profile, rxp); + } + + if (profile_flags & DIM_PROFILE_TX) { + moder->tx_dim_work = tx_dim_work; + moder->dim_tx_mode = tx_mode; + txp = kmemdup(tx_profile[tx_mode], len, GFP_KERNEL); + if (!txp) + goto free_rxp; + + rcu_assign_pointer(moder->tx_profile, txp); + } + + return 0; + +free_rxp: + kfree(rxp); +free_moder: + kfree(moder); + return -ENOMEM; +} +EXPORT_SYMBOL(net_dim_init_irq_moder); + +/* RTNL lock is held. */ +void net_dim_free_irq_moder(struct net_device *dev) +{ + struct dim_cq_moder *rxp, *txp; + + if (!dev->irq_moder) + return; + + rxp = rtnl_dereference(dev->irq_moder->rx_profile); + txp = rtnl_dereference(dev->irq_moder->tx_profile); + + rcu_assign_pointer(dev->irq_moder->rx_profile, NULL); + rcu_assign_pointer(dev->irq_moder->tx_profile, NULL); + + kfree_rcu(rxp, rcu); + kfree_rcu(txp, rcu); + kfree(dev->irq_moder); +} +EXPORT_SYMBOL(net_dim_free_irq_moder); + +void net_dim_setting(struct net_device *dev, struct dim *dim, bool is_tx) +{ + struct dim_irq_moder *irq_moder = dev->irq_moder; + + if (!irq_moder) + return; + + if (is_tx) { + INIT_WORK(&dim->work, irq_moder->tx_dim_work); + dim->mode = READ_ONCE(irq_moder->dim_tx_mode); + return; + } + + INIT_WORK(&dim->work, irq_moder->rx_dim_work); + dim->mode = READ_ONCE(irq_moder->dim_rx_mode); +} +EXPORT_SYMBOL(net_dim_setting); + +void net_dim_work_cancel(struct dim *dim) +{ + cancel_work_sync(&dim->work); +} +EXPORT_SYMBOL(net_dim_work_cancel); + +struct dim_cq_moder net_dim_get_rx_irq_moder(struct net_device *dev, + struct dim *dim) +{ + struct dim_cq_moder res, *profile; + + rcu_read_lock(); + profile = rcu_dereference(dev->irq_moder->rx_profile); + res = profile[dim->profile_ix]; + rcu_read_unlock(); + + res.cq_period_mode = dim->mode; + + return res; +} +EXPORT_SYMBOL(net_dim_get_rx_irq_moder); + +struct dim_cq_moder net_dim_get_tx_irq_moder(struct net_device *dev, + struct dim *dim) +{ + struct dim_cq_moder res, *profile; + + rcu_read_lock(); + profile = rcu_dereference(dev->irq_moder->tx_profile); + res = profile[dim->profile_ix]; + rcu_read_unlock(); + + res.cq_period_mode = dim->mode; + + return res; +} +EXPORT_SYMBOL(net_dim_get_tx_irq_moder); + +void net_dim_set_rx_mode(struct net_device *dev, u8 rx_mode) +{ + WRITE_ONCE(dev->irq_moder->dim_rx_mode, rx_mode); +} +EXPORT_SYMBOL(net_dim_set_rx_mode); + +void net_dim_set_tx_mode(struct net_device *dev, u8 tx_mode) +{ + WRITE_ONCE(dev->irq_moder->dim_tx_mode, tx_mode); +} +EXPORT_SYMBOL(net_dim_set_tx_mode); + static int net_dim_step(struct dim *dim) { if (dim->tired == (NET_DIM_PARAMS_NUM_PROFILES * 2)) @@ -215,7 +347,7 @@ static bool net_dim_decision(struct dim_stats *curr_stats, struct dim *dim) return dim->profile_ix != prev_ix; } -void net_dim(struct dim *dim, struct dim_sample end_sample) +void net_dim(struct dim *dim, const struct dim_sample *end_sample) { struct dim_stats curr_stats; u16 nevents; @@ -223,11 +355,11 @@ void net_dim(struct dim *dim, struct dim_sample end_sample) switch (dim->state) { case DIM_MEASURE_IN_PROGRESS: nevents = BIT_GAP(BITS_PER_TYPE(u16), - end_sample.event_ctr, + end_sample->event_ctr, dim->start_sample.event_ctr); if (nevents < DIM_NEVENTS) break; - if (!dim_calc_stats(&dim->start_sample, &end_sample, &curr_stats)) + if (!dim_calc_stats(&dim->start_sample, end_sample, &curr_stats)) break; if (net_dim_decision(&curr_stats, dim)) { dim->state = DIM_APPLY_NEW_PROFILE; @@ -236,8 +368,8 @@ void net_dim(struct dim *dim, struct dim_sample end_sample) } fallthrough; case DIM_START_MEASURE: - dim_update_sample(end_sample.event_ctr, end_sample.pkt_ctr, - end_sample.byte_ctr, &dim->start_sample); + dim_update_sample(end_sample->event_ctr, end_sample->pkt_ctr, + end_sample->byte_ctr, &dim->start_sample); dim->state = DIM_MEASURE_IN_PROGRESS; break; case DIM_APPLY_NEW_PROFILE: diff --git a/lib/dump_stack.c b/lib/dump_stack.c index 222c6d6c8281..388da1aea14a 100644 --- a/lib/dump_stack.c +++ b/lib/dump_stack.c @@ -54,20 +54,26 @@ void __init dump_stack_set_arch_desc(const char *fmt, ...) */ void dump_stack_print_info(const char *log_lvl) { - printk("%sCPU: %d PID: %d Comm: %.20s %s%s %s %.*s" BUILD_ID_FMT "\n", - log_lvl, raw_smp_processor_id(), current->pid, current->comm, + printk("%sCPU: %d UID: %u PID: %d Comm: %.20s %s%s %s %.*s" BUILD_ID_FMT "\n", + log_lvl, raw_smp_processor_id(), + __kuid_val(current_real_cred()->euid), + current->pid, current->comm, kexec_crash_loaded() ? "Kdump: loaded " : "", print_tainted(), init_utsname()->release, (int)strcspn(init_utsname()->version, " "), init_utsname()->version, BUILD_ID_VAL); + if (get_taint()) + printk("%s%s\n", log_lvl, print_tainted_verbose()); + if (dump_stack_arch_desc_str[0] != '\0') printk("%sHardware name: %s\n", log_lvl, dump_stack_arch_desc_str); print_worker_info(log_lvl, current); print_stop_info(log_lvl, current); + print_scx_info(log_lvl, current); } /** diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index f2c5e7910bb1..5a007952f7f2 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -1147,7 +1147,7 @@ static int ddebug_proc_show(struct seq_file *m, void *p) iter->table->mod_name, dp->function, ddebug_describe_flags(dp->flags, &flags)); seq_escape_str(m, dp->format, ESCAPE_SPACE, "\t\r\n\""); - seq_puts(m, "\""); + seq_putc(m, '"'); if (dp->class_id != _DPRINTK_CLASS_DFLT) { class = ddebug_class_name(iter, dp); @@ -1156,7 +1156,7 @@ static int ddebug_proc_show(struct seq_file *m, void *p) else seq_printf(m, " class unknown, _id:%d", dp->class_id); } - seq_puts(m, "\n"); + seq_putc(m, '\n'); return 0; } diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c index e49deddd3de9..c1b7638a594a 100644 --- a/lib/dynamic_queue_limits.c +++ b/lib/dynamic_queue_limits.c @@ -179,7 +179,7 @@ void dql_completed(struct dql *dql, unsigned int count) dql->adj_limit = limit + completed; dql->prev_ovlimit = ovlimit; - dql->prev_last_obj_cnt = dql->last_obj_cnt; + dql->prev_last_obj_cnt = READ_ONCE(dql->last_obj_cnt); dql->num_completed = completed; dql->prev_num_queued = num_queued; diff --git a/lib/fault-inject.c b/lib/fault-inject.c index d608f9b48c10..999053fa133e 100644 --- a/lib/fault-inject.c +++ b/lib/fault-inject.c @@ -1,7 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/init.h> -#include <linux/random.h> +#include <linux/prandom.h> +#include <linux/debugfs.h> #include <linux/sched.h> #include <linux/stat.h> #include <linux/types.h> @@ -12,6 +13,24 @@ #include <linux/fault-inject.h> /* + * The should_fail() functions use prandom instead of the normal Linux RNG + * since they don't need cryptographically secure random numbers. + */ +static DEFINE_PER_CPU(struct rnd_state, fault_rnd_state); + +static u32 fault_prandom_u32_below_100(void) +{ + struct rnd_state *state; + u32 res; + + state = &get_cpu_var(fault_rnd_state); + res = prandom_u32_state(state); + put_cpu_var(fault_rnd_state); + + return res % 100; +} + +/* * setup_fault_attr() is a helper function for various __setup handlers, so it * returns 0 on error, because that is what __setup handlers do. */ @@ -30,6 +49,8 @@ int setup_fault_attr(struct fault_attr *attr, char *str) return 0; } + prandom_init_once(&fault_rnd_state); + attr->probability = probability; attr->interval = interval; atomic_set(&attr->times, times); @@ -145,7 +166,7 @@ bool should_fail_ex(struct fault_attr *attr, ssize_t size, int flags) return false; } - if (attr->probability <= get_random_u32_below(100)) + if (attr->probability <= fault_prandom_u32_below_100()) return false; fail: @@ -218,6 +239,8 @@ struct dentry *fault_create_debugfs_attr(const char *name, if (IS_ERR(dir)) return dir; + prandom_init_once(&fault_rnd_state); + debugfs_create_ul("probability", mode, dir, &attr->probability); debugfs_create_ul("interval", mode, dir, &attr->interval); debugfs_create_atomic_t("times", mode, dir, &attr->times); @@ -430,6 +453,8 @@ static const struct config_item_type fault_config_type = { void fault_config_init(struct fault_config *config, const char *name) { + prandom_init_once(&fault_rnd_state); + config_group_init_type_name(&config->group, name, &fault_config_type); } EXPORT_SYMBOL_GPL(fault_config_init); diff --git a/lib/find_bit.c b/lib/find_bit.c index dacadd904250..0836bb3d76c5 100644 --- a/lib/find_bit.c +++ b/lib/find_bit.c @@ -87,7 +87,7 @@ out: \ if (sz % BITS_PER_LONG) \ tmp = (FETCH) & BITMAP_LAST_WORD_MASK(sz); \ found: \ - sz = min(idx * BITS_PER_LONG + fns(tmp, nr), sz); \ + sz = idx * BITS_PER_LONG + fns(tmp, nr); \ out: \ sz; \ }) diff --git a/lib/find_bit_benchmark.c b/lib/find_bit_benchmark.c index d3fb09e6eff1..402e160e7186 100644 --- a/lib/find_bit_benchmark.c +++ b/lib/find_bit_benchmark.c @@ -194,4 +194,5 @@ static int __init find_bit_test(void) } module_init(find_bit_test); +MODULE_DESCRIPTION("Test for find_*_bit functions"); MODULE_LICENSE("GPL"); diff --git a/lib/fonts/Kconfig b/lib/fonts/Kconfig index 7e945fdcbf11..ae59b5b4e225 100644 --- a/lib/fonts/Kconfig +++ b/lib/fonts/Kconfig @@ -10,7 +10,7 @@ if FONT_SUPPORT config FONTS bool "Select compiled-in fonts" - depends on FRAMEBUFFER_CONSOLE || STI_CONSOLE + depends on FRAMEBUFFER_CONSOLE || STI_CONSOLE || DRM_PANIC || DRM_CLIENT_LOG help Say Y here if you would like to use fonts other than the default your frame buffer console usually use. @@ -23,7 +23,7 @@ config FONTS config FONT_8x8 bool "VGA 8x8 font" if FONTS - depends on FRAMEBUFFER_CONSOLE || STI_CONSOLE + depends on FRAMEBUFFER_CONSOLE || STI_CONSOLE || DRM_PANIC default y if !SPARC && !FONTS help This is the "high resolution" font for the VGA frame buffer (the one @@ -46,7 +46,7 @@ config FONT_8x16 config FONT_6x11 bool "Mac console 6x11 font (not supported by all drivers)" if FONTS - depends on FRAMEBUFFER_CONSOLE || STI_CONSOLE + depends on FRAMEBUFFER_CONSOLE || STI_CONSOLE || DRM_PANIC default y if !SPARC && !FONTS && MAC help Small console font with Macintosh-style high-half glyphs. Some Mac @@ -54,7 +54,7 @@ config FONT_6x11 config FONT_7x14 bool "console 7x14 font (not supported by all drivers)" if FONTS - depends on FRAMEBUFFER_CONSOLE + depends on FRAMEBUFFER_CONSOLE || DRM_PANIC help Console font with characters just a bit smaller than the default. If the standard 8x16 font is a little too big for you, say Y. @@ -62,7 +62,7 @@ config FONT_7x14 config FONT_PEARL_8x8 bool "Pearl (old m68k) console 8x8 font" if FONTS - depends on FRAMEBUFFER_CONSOLE + depends on FRAMEBUFFER_CONSOLE || DRM_PANIC default y if !SPARC && !FONTS && AMIGA help Small console font with PC-style control-character and high-half @@ -70,7 +70,7 @@ config FONT_PEARL_8x8 config FONT_ACORN_8x8 bool "Acorn console 8x8 font" if FONTS - depends on FRAMEBUFFER_CONSOLE + depends on FRAMEBUFFER_CONSOLE || DRM_PANIC default y if !SPARC && !FONTS && ARM && ARCH_ACORN help Small console font with PC-style control characters and high-half @@ -90,7 +90,7 @@ config FONT_6x10 config FONT_10x18 bool "console 10x18 font (not supported by all drivers)" if FONTS - depends on FRAMEBUFFER_CONSOLE + depends on FRAMEBUFFER_CONSOLE || DRM_PANIC help This is a high resolution console font for machines with very big letters. It fits between the sun 12x22 and the normal 8x16 font. @@ -105,7 +105,8 @@ config FONT_SUN8x16 config FONT_SUN12x22 bool "Sparc console 12x22 font (not supported by all drivers)" - depends on FRAMEBUFFER_CONSOLE && (!SPARC && FONTS || SPARC) + depends on FRAMEBUFFER_CONSOLE || DRM_PANIC + depends on !SPARC && FONTS help This is the high resolution console font for Sun machines with very big letters (like the letters used in the SPARC PROM). If the @@ -113,7 +114,8 @@ config FONT_SUN12x22 config FONT_TER16x32 bool "Terminus 16x32 font (not supported by all drivers)" - depends on FRAMEBUFFER_CONSOLE && (!SPARC && FONTS || SPARC) + depends on FRAMEBUFFER_CONSOLE || DRM_PANIC + depends on !SPARC && FONTS || SPARC help Terminus Font is a clean, fixed width bitmap font, designed for long (8 and more hours per day) work with computers. @@ -122,7 +124,7 @@ config FONT_TER16x32 config FONT_6x8 bool "OLED 6x8 font" if FONTS - depends on FRAMEBUFFER_CONSOLE + depends on FRAMEBUFFER_CONSOLE || DRM_PANIC help This font is useful for small displays (OLED). diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c index d2377e00caab..ecb638d4cde1 100644 --- a/lib/fortify_kunit.c +++ b/lib/fortify_kunit.c @@ -234,11 +234,6 @@ static void fortify_test_alloc_size_##allocator##_dynamic(struct kunit *test) \ checker(expected_size, \ kmalloc_array_node(alloc_size, 1, gfp, NUMA_NO_NODE), \ kfree(p)); \ - checker(expected_size, __kmalloc(alloc_size, gfp), \ - kfree(p)); \ - checker(expected_size, \ - __kmalloc_node(alloc_size, gfp, NUMA_NO_NODE), \ - kfree(p)); \ \ orig = kmalloc(alloc_size, gfp); \ KUNIT_EXPECT_TRUE(test, orig != NULL); \ @@ -311,8 +306,7 @@ DEFINE_ALLOC_SIZE_TEST_PAIR(vmalloc) orig = kvmalloc(prev_size, gfp); \ KUNIT_EXPECT_TRUE(test, orig != NULL); \ checker(((expected_pages) * PAGE_SIZE) * 2, \ - kvrealloc(orig, prev_size, \ - ((alloc_pages) * PAGE_SIZE) * 2, gfp), \ + kvrealloc(orig, ((alloc_pages) * PAGE_SIZE) * 2, gfp), \ kvfree(p)); \ } while (0) DEFINE_ALLOC_SIZE_TEST_PAIR(kvmalloc) @@ -377,7 +371,7 @@ static const char * const test_strs[] = { for (i = 0; i < ARRAY_SIZE(test_strs); i++) { \ len = strlen(test_strs[i]); \ KUNIT_EXPECT_EQ(test, __builtin_constant_p(len), 0); \ - checker(len, kmemdup_array(test_strs[i], len, 1, gfp), \ + checker(len, kmemdup_array(test_strs[i], 1, len, gfp), \ kfree(p)); \ checker(len, kmemdup(test_strs[i], len, gfp), \ kfree(p)); \ @@ -913,10 +907,9 @@ static void fortify_test_##memfunc(struct kunit *test) \ memfunc(zero.buf, srcB, 0 + unconst); \ KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); \ KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0); \ - /* We currently explicitly ignore zero-sized dests. */ \ memfunc(zero.buf, srcB, 1 + unconst); \ KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); \ - KUNIT_EXPECT_EQ(test, fortify_write_overflows, 0); \ + KUNIT_EXPECT_EQ(test, fortify_write_overflows, 1); \ } __fortify_test(memcpy) __fortify_test(memmove) @@ -990,7 +983,7 @@ static void fortify_test_memcmp(struct kunit *test) KUNIT_ASSERT_EQ(test, memcmp(one, two, one_len), 0); KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); /* Still in bounds, but no longer matching. */ - KUNIT_ASSERT_EQ(test, memcmp(one, two, one_len + 1), -32); + KUNIT_ASSERT_LT(test, memcmp(one, two, one_len + 1), 0); KUNIT_EXPECT_EQ(test, fortify_read_overflows, 0); /* Catch too-large ranges. */ @@ -1099,4 +1092,5 @@ static struct kunit_suite fortify_test_suite = { kunit_test_suite(fortify_test_suite); +MODULE_DESCRIPTION("Runtime test cases for CONFIG_FORTIFY_SOURCE"); MODULE_LICENSE("GPL"); diff --git a/lib/gen_crc32table.c b/lib/gen_crc32table.c index f755b997b967..6d03425b849e 100644 --- a/lib/gen_crc32table.c +++ b/lib/gen_crc32table.c @@ -2,30 +2,11 @@ #include <stdio.h> #include "../include/linux/crc32poly.h" #include "../include/generated/autoconf.h" -#include "crc32defs.h" #include <inttypes.h> -#define ENTRIES_PER_LINE 4 - -#if CRC_LE_BITS > 8 -# define LE_TABLE_ROWS (CRC_LE_BITS/8) -# define LE_TABLE_SIZE 256 -#else -# define LE_TABLE_ROWS 1 -# define LE_TABLE_SIZE (1 << CRC_LE_BITS) -#endif - -#if CRC_BE_BITS > 8 -# define BE_TABLE_ROWS (CRC_BE_BITS/8) -# define BE_TABLE_SIZE 256 -#else -# define BE_TABLE_ROWS 1 -# define BE_TABLE_SIZE (1 << CRC_BE_BITS) -#endif - -static uint32_t crc32table_le[LE_TABLE_ROWS][256]; -static uint32_t crc32table_be[BE_TABLE_ROWS][256]; -static uint32_t crc32ctable_le[LE_TABLE_ROWS][256]; +static uint32_t crc32table_le[256]; +static uint32_t crc32table_be[256]; +static uint32_t crc32ctable_le[256]; /** * crc32init_le() - allocate and initialize LE table data @@ -34,25 +15,17 @@ static uint32_t crc32ctable_le[LE_TABLE_ROWS][256]; * fact that crctable[i^j] = crctable[i] ^ crctable[j]. * */ -static void crc32init_le_generic(const uint32_t polynomial, - uint32_t (*tab)[256]) +static void crc32init_le_generic(const uint32_t polynomial, uint32_t tab[256]) { unsigned i, j; uint32_t crc = 1; - tab[0][0] = 0; + tab[0] = 0; - for (i = LE_TABLE_SIZE >> 1; i; i >>= 1) { + for (i = 128; i; i >>= 1) { crc = (crc >> 1) ^ ((crc & 1) ? polynomial : 0); - for (j = 0; j < LE_TABLE_SIZE; j += 2 * i) - tab[0][i + j] = crc ^ tab[0][j]; - } - for (i = 0; i < LE_TABLE_SIZE; i++) { - crc = tab[0][i]; - for (j = 1; j < LE_TABLE_ROWS; j++) { - crc = tab[0][crc & 0xff] ^ (crc >> 8); - tab[j][i] = crc; - } + for (j = 0; j < 256; j += 2 * i) + tab[i + j] = crc ^ tab[j]; } } @@ -74,34 +47,22 @@ static void crc32init_be(void) unsigned i, j; uint32_t crc = 0x80000000; - crc32table_be[0][0] = 0; + crc32table_be[0] = 0; - for (i = 1; i < BE_TABLE_SIZE; i <<= 1) { + for (i = 1; i < 256; i <<= 1) { crc = (crc << 1) ^ ((crc & 0x80000000) ? CRC32_POLY_BE : 0); for (j = 0; j < i; j++) - crc32table_be[0][i + j] = crc ^ crc32table_be[0][j]; - } - for (i = 0; i < BE_TABLE_SIZE; i++) { - crc = crc32table_be[0][i]; - for (j = 1; j < BE_TABLE_ROWS; j++) { - crc = crc32table_be[0][(crc >> 24) & 0xff] ^ (crc << 8); - crc32table_be[j][i] = crc; - } + crc32table_be[i + j] = crc ^ crc32table_be[j]; } } -static void output_table(uint32_t (*table)[256], int rows, int len, char *trans) +static void output_table(const uint32_t table[256]) { - int i, j; - - for (j = 0 ; j < rows; j++) { - printf("{"); - for (i = 0; i < len - 1; i++) { - if (i % ENTRIES_PER_LINE == 0) - printf("\n"); - printf("%s(0x%8.8xL), ", trans, table[j][i]); - } - printf("%s(0x%8.8xL)},\n", trans, table[j][len - 1]); + int i; + + for (i = 0; i < 256; i += 4) { + printf("\t0x%08x, 0x%08x, 0x%08x, 0x%08x,\n", + table[i], table[i + 1], table[i + 2], table[i + 3]); } } @@ -109,34 +70,20 @@ int main(int argc, char** argv) { printf("/* this file is generated - do not edit */\n\n"); - if (CRC_LE_BITS > 1) { - crc32init_le(); - printf("static const u32 ____cacheline_aligned " - "crc32table_le[%d][%d] = {", - LE_TABLE_ROWS, LE_TABLE_SIZE); - output_table(crc32table_le, LE_TABLE_ROWS, - LE_TABLE_SIZE, "tole"); - printf("};\n"); - } + crc32init_le(); + printf("static const u32 ____cacheline_aligned crc32table_le[256] = {\n"); + output_table(crc32table_le); + printf("};\n"); - if (CRC_BE_BITS > 1) { - crc32init_be(); - printf("static const u32 ____cacheline_aligned " - "crc32table_be[%d][%d] = {", - BE_TABLE_ROWS, BE_TABLE_SIZE); - output_table(crc32table_be, LE_TABLE_ROWS, - BE_TABLE_SIZE, "tobe"); - printf("};\n"); - } - if (CRC_LE_BITS > 1) { - crc32cinit_le(); - printf("static const u32 ____cacheline_aligned " - "crc32ctable_le[%d][%d] = {", - LE_TABLE_ROWS, LE_TABLE_SIZE); - output_table(crc32ctable_le, LE_TABLE_ROWS, - LE_TABLE_SIZE, "tole"); - printf("};\n"); - } + crc32init_be(); + printf("static const u32 ____cacheline_aligned crc32table_be[256] = {\n"); + output_table(crc32table_be); + printf("};\n"); + + crc32cinit_le(); + printf("static const u32 ____cacheline_aligned crc32ctable_le[256] = {\n"); + output_table(crc32ctable_le); + printf("};\n"); return 0; } diff --git a/lib/generic-radix-tree.c b/lib/generic-radix-tree.c index aaefb9b678c8..79e067b51488 100644 --- a/lib/generic-radix-tree.c +++ b/lib/generic-radix-tree.c @@ -5,99 +5,31 @@ #include <linux/gfp.h> #include <linux/kmemleak.h> -#define GENRADIX_ARY (GENRADIX_NODE_SIZE / sizeof(struct genradix_node *)) -#define GENRADIX_ARY_SHIFT ilog2(GENRADIX_ARY) - -struct genradix_node { - union { - /* Interior node: */ - struct genradix_node *children[GENRADIX_ARY]; - - /* Leaf: */ - u8 data[GENRADIX_NODE_SIZE]; - }; -}; - -static inline int genradix_depth_shift(unsigned depth) -{ - return GENRADIX_NODE_SHIFT + GENRADIX_ARY_SHIFT * depth; -} - -/* - * Returns size (of data, in bytes) that a tree of a given depth holds: - */ -static inline size_t genradix_depth_size(unsigned depth) -{ - return 1UL << genradix_depth_shift(depth); -} - -/* depth that's needed for a genradix that can address up to ULONG_MAX: */ -#define GENRADIX_MAX_DEPTH \ - DIV_ROUND_UP(BITS_PER_LONG - GENRADIX_NODE_SHIFT, GENRADIX_ARY_SHIFT) - -#define GENRADIX_DEPTH_MASK \ - ((unsigned long) (roundup_pow_of_two(GENRADIX_MAX_DEPTH + 1) - 1)) - -static inline unsigned genradix_root_to_depth(struct genradix_root *r) -{ - return (unsigned long) r & GENRADIX_DEPTH_MASK; -} - -static inline struct genradix_node *genradix_root_to_node(struct genradix_root *r) -{ - return (void *) ((unsigned long) r & ~GENRADIX_DEPTH_MASK); -} - /* * Returns pointer to the specified byte @offset within @radix, or NULL if not * allocated */ void *__genradix_ptr(struct __genradix *radix, size_t offset) { - struct genradix_root *r = READ_ONCE(radix->root); - struct genradix_node *n = genradix_root_to_node(r); - unsigned level = genradix_root_to_depth(r); - - if (ilog2(offset) >= genradix_depth_shift(level)) - return NULL; - - while (1) { - if (!n) - return NULL; - if (!level) - break; - - level--; - - n = n->children[offset >> genradix_depth_shift(level)]; - offset &= genradix_depth_size(level) - 1; - } - - return &n->data[offset]; + return __genradix_ptr_inlined(radix, offset); } EXPORT_SYMBOL(__genradix_ptr); -static inline struct genradix_node *genradix_alloc_node(gfp_t gfp_mask) -{ - return kzalloc(GENRADIX_NODE_SIZE, gfp_mask); -} - -static inline void genradix_free_node(struct genradix_node *node) -{ - kfree(node); -} - /* * Returns pointer to the specified byte @offset within @radix, allocating it if * necessary - newly allocated slots are always zeroed out: */ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset, + struct genradix_node **preallocated, gfp_t gfp_mask) { struct genradix_root *v = READ_ONCE(radix->root); struct genradix_node *n, *new_node = NULL; unsigned level; + if (preallocated) + swap(new_node, *preallocated); + /* Increase tree depth if necessary: */ while (1) { struct genradix_root *r = v, *new_root; @@ -121,6 +53,8 @@ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset, if ((v = cmpxchg_release(&radix->root, r, new_root)) == r) { v = new_root; new_node = NULL; + } else { + new_node->children[0] = NULL; } } @@ -279,7 +213,7 @@ int __genradix_prealloc(struct __genradix *radix, size_t size, size_t offset; for (offset = 0; offset < size; offset += GENRADIX_NODE_SIZE) - if (!__genradix_ptr_alloc(radix, offset, gfp_mask)) + if (!__genradix_ptr_alloc(radix, offset, NULL, gfp_mask)) return -ENOMEM; return 0; diff --git a/lib/glob.c b/lib/glob.c index 15b73f490720..aa57900d2062 100644 --- a/lib/glob.c +++ b/lib/glob.c @@ -68,6 +68,8 @@ bool __pure glob_match(char const *pat, char const *str) back_str = --str; /* Allow zero-length match */ break; case '[': { /* Character class */ + if (c == '\0') /* No possible match */ + return false; bool match = false, inverted = (*pat == '!'); char const *class = pat + inverted; unsigned char a = *class++; diff --git a/lib/hashtable_test.c b/lib/hashtable_test.c index 1d1b3288dee2..3521de6bad15 100644 --- a/lib/hashtable_test.c +++ b/lib/hashtable_test.c @@ -314,4 +314,5 @@ static struct kunit_suite hashtable_test_module = { kunit_test_suites(&hashtable_test_module); +MODULE_DESCRIPTION("KUnit test for the Kernel Hashtable structures"); MODULE_LICENSE("GPL"); diff --git a/lib/hexdump.c b/lib/hexdump.c index 06833d404398..c3db7c3a7643 100644 --- a/lib/hexdump.c +++ b/lib/hexdump.c @@ -9,7 +9,7 @@ #include <linux/kernel.h> #include <linux/minmax.h> #include <linux/export.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> const char hex_asc[] = "0123456789abcdef"; EXPORT_SYMBOL(hex_asc); diff --git a/lib/inflate.c b/lib/inflate.c index fbaf03c1748d..eab886baa1b4 100644 --- a/lib/inflate.c +++ b/lib/inflate.c @@ -1257,8 +1257,6 @@ static int INIT gunzip(void) /* Decompress */ if ((res = inflate())) { switch (res) { - case 0: - break; case 1: error("invalid compressed format (err=1)"); break; diff --git a/lib/interval_tree_test.c b/lib/interval_tree_test.c index f37f4d44faa9..837064b83a6c 100644 --- a/lib/interval_tree_test.c +++ b/lib/interval_tree_test.c @@ -2,7 +2,7 @@ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/interval_tree.h> -#include <linux/random.h> +#include <linux/prandom.h> #include <linux/slab.h> #include <asm/timex.h> diff --git a/lib/iomap_copy.c b/lib/iomap_copy.c index 5de7c04e05ef..2fd5712fb7c0 100644 --- a/lib/iomap_copy.c +++ b/lib/iomap_copy.c @@ -16,9 +16,8 @@ * time. Order of access is not guaranteed, nor is a memory barrier * performed afterwards. */ -void __attribute__((weak)) __iowrite32_copy(void __iomem *to, - const void *from, - size_t count) +#ifndef __iowrite32_copy +void __iowrite32_copy(void __iomem *to, const void *from, size_t count) { u32 __iomem *dst = to; const u32 *src = from; @@ -28,6 +27,7 @@ void __attribute__((weak)) __iowrite32_copy(void __iomem *to, __raw_writel(*src++, dst++); } EXPORT_SYMBOL_GPL(__iowrite32_copy); +#endif /** * __ioread32_copy - copy data from MMIO space, in 32-bit units @@ -60,9 +60,8 @@ EXPORT_SYMBOL_GPL(__ioread32_copy); * time. Order of access is not guaranteed, nor is a memory barrier * performed afterwards. */ -void __attribute__((weak)) __iowrite64_copy(void __iomem *to, - const void *from, - size_t count) +#ifndef __iowrite64_copy +void __iowrite64_copy(void __iomem *to, const void *from, size_t count) { #ifdef CONFIG_64BIT u64 __iomem *dst = to; @@ -75,5 +74,5 @@ void __attribute__((weak)) __iowrite64_copy(void __iomem *to, __iowrite32_copy(to, from, count * 2); #endif } - EXPORT_SYMBOL_GPL(__iowrite64_copy); +#endif diff --git a/lib/iomem_copy.c b/lib/iomem_copy.c new file mode 100644 index 000000000000..dec7eaea60e0 --- /dev/null +++ b/lib/iomem_copy.c @@ -0,0 +1,136 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2024 Kalray, Inc. All Rights Reserved. + */ + +#include <linux/align.h> +#include <linux/export.h> +#include <linux/io.h> +#include <linux/types.h> +#include <linux/unaligned.h> + +#ifndef memset_io +/** + * memset_io() - Set a range of I/O memory to a constant value + * @addr: The beginning of the I/O-memory range to set + * @val: The value to set the memory to + * @count: The number of bytes to set + * + * Set a range of I/O memory to a given value. + */ +void memset_io(volatile void __iomem *addr, int val, size_t count) +{ + long qc = (u8)val; + + qc *= ~0UL / 0xff; + + while (count && !IS_ALIGNED((long)addr, sizeof(long))) { + __raw_writeb(val, addr); + addr++; + count--; + } + + while (count >= sizeof(long)) { +#ifdef CONFIG_64BIT + __raw_writeq(qc, addr); +#else + __raw_writel(qc, addr); +#endif + + addr += sizeof(long); + count -= sizeof(long); + } + + while (count) { + __raw_writeb(val, addr); + addr++; + count--; + } +} +EXPORT_SYMBOL(memset_io); +#endif + +#ifndef memcpy_fromio +/** + * memcpy_fromio() - Copy a block of data from I/O memory + * @dst: The (RAM) destination for the copy + * @src: The (I/O memory) source for the data + * @count: The number of bytes to copy + * + * Copy a block of data from I/O memory. + */ +void memcpy_fromio(void *dst, const volatile void __iomem *src, size_t count) +{ + while (count && !IS_ALIGNED((long)src, sizeof(long))) { + *(u8 *)dst = __raw_readb(src); + src++; + dst++; + count--; + } + + while (count >= sizeof(long)) { +#ifdef CONFIG_64BIT + long val = __raw_readq(src); +#else + long val = __raw_readl(src); +#endif + put_unaligned(val, (long *)dst); + + + src += sizeof(long); + dst += sizeof(long); + count -= sizeof(long); + } + + while (count) { + *(u8 *)dst = __raw_readb(src); + src++; + dst++; + count--; + } +} +EXPORT_SYMBOL(memcpy_fromio); +#endif + +#ifndef memcpy_toio +/** + * memcpy_toio() -Copy a block of data into I/O memory + * @dst: The (I/O memory) destination for the copy + * @src: The (RAM) source for the data + * @count: The number of bytes to copy + * + * Copy a block of data to I/O memory. + */ +void memcpy_toio(volatile void __iomem *dst, const void *src, size_t count) +{ + while (count && !IS_ALIGNED((long)dst, sizeof(long))) { + __raw_writeb(*(u8 *)src, dst); + src++; + dst++; + count--; + } + + while (count >= sizeof(long)) { + long val = get_unaligned((long *)src); +#ifdef CONFIG_64BIT + __raw_writeq(val, dst); +#else + __raw_writel(val, dst); +#endif + + src += sizeof(long); + dst += sizeof(long); + count -= sizeof(long); + } + + while (count) { + __raw_writeb(*(u8 *)src, dst); + src++; + dst++; + count--; + } +} +EXPORT_SYMBOL(memcpy_toio); +#endif + + diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 4a6a9f419bd7..9ec806f989f2 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -461,6 +461,8 @@ size_t copy_page_from_iter_atomic(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { size_t n, copied = 0; + bool uses_kmap = IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) || + PageHighMem(page); if (!page_copy_sane(page, offset, bytes)) return 0; @@ -471,7 +473,7 @@ size_t copy_page_from_iter_atomic(struct page *page, size_t offset, char *p; n = bytes - copied; - if (PageHighMem(page)) { + if (uses_kmap) { page += offset / PAGE_SIZE; offset %= PAGE_SIZE; n = min_t(size_t, n, PAGE_SIZE - offset); @@ -482,7 +484,7 @@ size_t copy_page_from_iter_atomic(struct page *page, size_t offset, kunmap_atomic(p); copied += n; offset += n; - } while (PageHighMem(page) && copied != bytes && n > 0); + } while (uses_kmap && copied != bytes && n > 0); return copied; } @@ -527,6 +529,39 @@ static void iov_iter_iovec_advance(struct iov_iter *i, size_t size) i->__iov = iov; } +static void iov_iter_folioq_advance(struct iov_iter *i, size_t size) +{ + const struct folio_queue *folioq = i->folioq; + unsigned int slot = i->folioq_slot; + + if (!i->count) + return; + i->count -= size; + + if (slot >= folioq_nr_slots(folioq)) { + folioq = folioq->next; + slot = 0; + } + + size += i->iov_offset; /* From beginning of current segment. */ + do { + size_t fsize = folioq_folio_size(folioq, slot); + + if (likely(size < fsize)) + break; + size -= fsize; + slot++; + if (slot >= folioq_nr_slots(folioq) && folioq->next) { + folioq = folioq->next; + slot = 0; + } + } while (size); + + i->iov_offset = size; + i->folioq_slot = slot; + i->folioq = folioq; +} + void iov_iter_advance(struct iov_iter *i, size_t size) { if (unlikely(i->count < size)) @@ -539,12 +574,40 @@ void iov_iter_advance(struct iov_iter *i, size_t size) iov_iter_iovec_advance(i, size); } else if (iov_iter_is_bvec(i)) { iov_iter_bvec_advance(i, size); + } else if (iov_iter_is_folioq(i)) { + iov_iter_folioq_advance(i, size); } else if (iov_iter_is_discard(i)) { i->count -= size; } } EXPORT_SYMBOL(iov_iter_advance); +static void iov_iter_folioq_revert(struct iov_iter *i, size_t unroll) +{ + const struct folio_queue *folioq = i->folioq; + unsigned int slot = i->folioq_slot; + + for (;;) { + size_t fsize; + + if (slot == 0) { + folioq = folioq->prev; + slot = folioq_nr_slots(folioq); + } + slot--; + + fsize = folioq_folio_size(folioq, slot); + if (unroll <= fsize) { + i->iov_offset = fsize - unroll; + break; + } + unroll -= fsize; + } + + i->folioq_slot = slot; + i->folioq = folioq; +} + void iov_iter_revert(struct iov_iter *i, size_t unroll) { if (!unroll) @@ -576,6 +639,9 @@ void iov_iter_revert(struct iov_iter *i, size_t unroll) } unroll -= n; } + } else if (iov_iter_is_folioq(i)) { + i->iov_offset = 0; + iov_iter_folioq_revert(i, unroll); } else { /* same logics for iovec and kvec */ const struct iovec *iov = iter_iov(i); while (1) { @@ -603,6 +669,9 @@ size_t iov_iter_single_seg_count(const struct iov_iter *i) if (iov_iter_is_bvec(i)) return min(i->count, i->bvec->bv_len - i->iov_offset); } + if (unlikely(iov_iter_is_folioq(i))) + return !i->count ? 0 : + umin(folioq_folio_size(i->folioq, i->folioq_slot), i->count); return i->count; } EXPORT_SYMBOL(iov_iter_single_seg_count); @@ -640,6 +709,36 @@ void iov_iter_bvec(struct iov_iter *i, unsigned int direction, EXPORT_SYMBOL(iov_iter_bvec); /** + * iov_iter_folio_queue - Initialise an I/O iterator to use the folios in a folio queue + * @i: The iterator to initialise. + * @direction: The direction of the transfer. + * @folioq: The starting point in the folio queue. + * @first_slot: The first slot in the folio queue to use + * @offset: The offset into the folio in the first slot to start at + * @count: The size of the I/O buffer in bytes. + * + * Set up an I/O iterator to either draw data out of the pages attached to an + * inode or to inject data into those pages. The pages *must* be prevented + * from evaporation, either by taking a ref on them or locking them by the + * caller. + */ +void iov_iter_folio_queue(struct iov_iter *i, unsigned int direction, + const struct folio_queue *folioq, unsigned int first_slot, + unsigned int offset, size_t count) +{ + BUG_ON(direction & ~1); + *i = (struct iov_iter) { + .iter_type = ITER_FOLIOQ, + .data_source = direction, + .folioq = folioq, + .folioq_slot = first_slot, + .count = count, + .iov_offset = offset, + }; +} +EXPORT_SYMBOL(iov_iter_folio_queue); + +/** * iov_iter_xarray - Initialise an I/O iterator to use the pages in an xarray * @i: The iterator to initialise. * @direction: The direction of the transfer. @@ -765,12 +864,19 @@ bool iov_iter_is_aligned(const struct iov_iter *i, unsigned addr_mask, if (iov_iter_is_bvec(i)) return iov_iter_aligned_bvec(i, addr_mask, len_mask); + /* With both xarray and folioq types, we're dealing with whole folios. */ if (iov_iter_is_xarray(i)) { if (i->count & len_mask) return false; if ((i->xarray_start + i->iov_offset) & addr_mask) return false; } + if (iov_iter_is_folioq(i)) { + if (i->count & len_mask) + return false; + if (i->iov_offset & addr_mask) + return false; + } return true; } @@ -835,6 +941,9 @@ unsigned long iov_iter_alignment(const struct iov_iter *i) if (iov_iter_is_bvec(i)) return iov_iter_alignment_bvec(i); + /* With both xarray and folioq types, we're dealing with whole folios. */ + if (iov_iter_is_folioq(i)) + return i->iov_offset | i->count; if (iov_iter_is_xarray(i)) return (i->xarray_start + i->iov_offset) | i->count; @@ -887,6 +996,65 @@ static int want_pages_array(struct page ***res, size_t size, return count; } +static ssize_t iter_folioq_get_pages(struct iov_iter *iter, + struct page ***ppages, size_t maxsize, + unsigned maxpages, size_t *_start_offset) +{ + const struct folio_queue *folioq = iter->folioq; + struct page **pages; + unsigned int slot = iter->folioq_slot; + size_t extracted = 0, count = iter->count, iov_offset = iter->iov_offset; + + if (slot >= folioq_nr_slots(folioq)) { + folioq = folioq->next; + slot = 0; + if (WARN_ON(iov_offset != 0)) + return -EIO; + } + + maxpages = want_pages_array(ppages, maxsize, iov_offset & ~PAGE_MASK, maxpages); + if (!maxpages) + return -ENOMEM; + *_start_offset = iov_offset & ~PAGE_MASK; + pages = *ppages; + + for (;;) { + struct folio *folio = folioq_folio(folioq, slot); + size_t offset = iov_offset, fsize = folioq_folio_size(folioq, slot); + size_t part = PAGE_SIZE - offset % PAGE_SIZE; + + if (offset < fsize) { + part = umin(part, umin(maxsize - extracted, fsize - offset)); + count -= part; + iov_offset += part; + extracted += part; + + *pages = folio_page(folio, offset / PAGE_SIZE); + get_page(*pages); + pages++; + maxpages--; + } + + if (maxpages == 0 || extracted >= maxsize) + break; + + if (iov_offset >= fsize) { + iov_offset = 0; + slot++; + if (slot == folioq_nr_slots(folioq) && folioq->next) { + folioq = folioq->next; + slot = 0; + } + } + } + + iter->count = count; + iter->iov_offset = iov_offset; + iter->folioq = folioq; + iter->folioq_slot = slot; + return extracted; +} + static ssize_t iter_xarray_populate_pages(struct page **pages, struct xarray *xa, pgoff_t index, unsigned int nr_pages) { @@ -1034,6 +1202,8 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i, } return maxsize; } + if (iov_iter_is_folioq(i)) + return iter_folioq_get_pages(i, pages, maxsize, maxpages, start); if (iov_iter_is_xarray(i)) return iter_xarray_get_pages(i, pages, maxsize, maxpages, start); return -EFAULT; @@ -1118,6 +1288,11 @@ int iov_iter_npages(const struct iov_iter *i, int maxpages) return iov_npages(i, maxpages); if (iov_iter_is_bvec(i)) return bvec_npages(i, maxpages); + if (iov_iter_is_folioq(i)) { + unsigned offset = i->iov_offset % PAGE_SIZE; + int npages = DIV_ROUND_UP(offset + i->count, PAGE_SIZE); + return min(npages, maxpages); + } if (iov_iter_is_xarray(i)) { unsigned offset = (i->xarray_start + i->iov_offset) % PAGE_SIZE; int npages = DIV_ROUND_UP(offset + i->count, PAGE_SIZE); @@ -1399,6 +1574,68 @@ void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state) } /* + * Extract a list of contiguous pages from an ITER_FOLIOQ iterator. This does + * not get references on the pages, nor does it get a pin on them. + */ +static ssize_t iov_iter_extract_folioq_pages(struct iov_iter *i, + struct page ***pages, size_t maxsize, + unsigned int maxpages, + iov_iter_extraction_t extraction_flags, + size_t *offset0) +{ + const struct folio_queue *folioq = i->folioq; + struct page **p; + unsigned int nr = 0; + size_t extracted = 0, offset, slot = i->folioq_slot; + + if (slot >= folioq_nr_slots(folioq)) { + folioq = folioq->next; + slot = 0; + if (WARN_ON(i->iov_offset != 0)) + return -EIO; + } + + offset = i->iov_offset & ~PAGE_MASK; + *offset0 = offset; + + maxpages = want_pages_array(pages, maxsize, offset, maxpages); + if (!maxpages) + return -ENOMEM; + p = *pages; + + for (;;) { + struct folio *folio = folioq_folio(folioq, slot); + size_t offset = i->iov_offset, fsize = folioq_folio_size(folioq, slot); + size_t part = PAGE_SIZE - offset % PAGE_SIZE; + + if (offset < fsize) { + part = umin(part, umin(maxsize - extracted, fsize - offset)); + i->count -= part; + i->iov_offset += part; + extracted += part; + + p[nr++] = folio_page(folio, offset / PAGE_SIZE); + } + + if (nr >= maxpages || extracted >= maxsize) + break; + + if (i->iov_offset >= fsize) { + i->iov_offset = 0; + slot++; + if (slot == folioq_nr_slots(folioq) && folioq->next) { + folioq = folioq->next; + slot = 0; + } + } + } + + i->folioq = folioq; + i->folioq_slot = slot; + return extracted; +} + +/* * Extract a list of contiguous pages from an ITER_XARRAY iterator. This does not * get references on the pages, nor does it get a pin on them. */ @@ -1445,8 +1682,8 @@ static ssize_t iov_iter_extract_xarray_pages(struct iov_iter *i, } /* - * Extract a list of contiguous pages from an ITER_BVEC iterator. This does - * not get references on the pages, nor does it get a pin on them. + * Extract a list of virtually contiguous pages from an ITER_BVEC iterator. + * This does not get references on the pages, nor does it get a pin on them. */ static ssize_t iov_iter_extract_bvec_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, @@ -1454,35 +1691,59 @@ static ssize_t iov_iter_extract_bvec_pages(struct iov_iter *i, iov_iter_extraction_t extraction_flags, size_t *offset0) { - struct page **p, *page; - size_t skip = i->iov_offset, offset, size; - int k; + size_t skip = i->iov_offset, size = 0; + struct bvec_iter bi; + int k = 0; - for (;;) { - if (i->nr_segs == 0) - return 0; - size = min(maxsize, i->bvec->bv_len - skip); - if (size) - break; + if (i->nr_segs == 0) + return 0; + + if (i->iov_offset == i->bvec->bv_len) { i->iov_offset = 0; i->nr_segs--; i->bvec++; skip = 0; } + bi.bi_idx = 0; + bi.bi_size = maxsize; + bi.bi_bvec_done = skip; + + maxpages = want_pages_array(pages, maxsize, skip, maxpages); + + while (bi.bi_size && bi.bi_idx < i->nr_segs) { + struct bio_vec bv = bvec_iter_bvec(i->bvec, bi); + + /* + * The iov_iter_extract_pages interface only allows an offset + * into the first page. Break out of the loop if we see an + * offset into subsequent pages, the caller will have to call + * iov_iter_extract_pages again for the reminder. + */ + if (k) { + if (bv.bv_offset) + break; + } else { + *offset0 = bv.bv_offset; + } - skip += i->bvec->bv_offset; - page = i->bvec->bv_page + skip / PAGE_SIZE; - offset = skip % PAGE_SIZE; - *offset0 = offset; + (*pages)[k++] = bv.bv_page; + size += bv.bv_len; - maxpages = want_pages_array(pages, size, offset, maxpages); - if (!maxpages) - return -ENOMEM; - p = *pages; - for (k = 0; k < maxpages; k++) - p[k] = page + k; + if (k >= maxpages) + break; + + /* + * We are done when the end of the bvec doesn't align to a page + * boundary as that would create a hole in the returned space. + * The caller will handle this with another call to + * iov_iter_extract_pages. + */ + if (bv.bv_offset + bv.bv_len != PAGE_SIZE) + break; + + bvec_iter_advance_single(i->bvec, &bi, bv.bv_len); + } - size = min_t(size_t, size, maxpages * PAGE_SIZE - offset); iov_iter_advance(i, size); return size; } @@ -1618,8 +1879,8 @@ static ssize_t iov_iter_extract_user_pages(struct iov_iter *i, * added to the pages, but refs will not be taken. * iov_iter_extract_will_pin() will return true. * - * (*) If the iterator is ITER_KVEC, ITER_BVEC or ITER_XARRAY, the pages are - * merely listed; no extra refs or pins are obtained. + * (*) If the iterator is ITER_KVEC, ITER_BVEC, ITER_FOLIOQ or ITER_XARRAY, the + * pages are merely listed; no extra refs or pins are obtained. * iov_iter_extract_will_pin() will return 0. * * Note also: @@ -1654,6 +1915,10 @@ ssize_t iov_iter_extract_pages(struct iov_iter *i, return iov_iter_extract_bvec_pages(i, pages, maxsize, maxpages, extraction_flags, offset0); + if (iov_iter_is_folioq(i)) + return iov_iter_extract_folioq_pages(i, pages, maxsize, + maxpages, extraction_flags, + offset0); if (iov_iter_is_xarray(i)) return iov_iter_extract_xarray_pages(i, pages, maxsize, maxpages, extraction_flags, diff --git a/lib/irq_poll.c b/lib/irq_poll.c index 2d5329a42105..08b242bbdbdf 100644 --- a/lib/irq_poll.c +++ b/lib/irq_poll.c @@ -75,7 +75,7 @@ void irq_poll_complete(struct irq_poll *iop) } EXPORT_SYMBOL(irq_poll_complete); -static void __latent_entropy irq_poll_softirq(struct softirq_action *h) +static void __latent_entropy irq_poll_softirq(void) { struct list_head *list = this_cpu_ptr(&blk_cpu_iopoll); int rearm = 0, budget = irq_poll_budget; diff --git a/lib/is_signed_type_kunit.c b/lib/is_signed_type_kunit.c index 0a7f6ae62839..88adbe813f3a 100644 --- a/lib/is_signed_type_kunit.c +++ b/lib/is_signed_type_kunit.c @@ -46,4 +46,5 @@ static struct kunit_suite is_signed_type_test_suite = { kunit_test_suite(is_signed_type_test_suite); +MODULE_DESCRIPTION("is_signed_type() KUnit test suite"); MODULE_LICENSE("Dual MIT/GPL"); diff --git a/lib/kfifo.c b/lib/kfifo.c index 12f5a347aa13..a8b2eed90599 100644 --- a/lib/kfifo.c +++ b/lib/kfifo.c @@ -5,13 +5,14 @@ * Copyright (C) 2009/2010 Stefani Seibold <stefani@seibold.net> */ -#include <linux/kernel.h> -#include <linux/export.h> -#include <linux/slab.h> +#include <linux/dma-mapping.h> #include <linux/err.h> +#include <linux/export.h> +#include <linux/kfifo.h> #include <linux/log2.h> +#include <linux/scatterlist.h> +#include <linux/slab.h> #include <linux/uaccess.h> -#include <linux/kfifo.h> /* * internal helper to calculate the unused elements in a fifo @@ -163,6 +164,19 @@ unsigned int __kfifo_out_peek(struct __kfifo *fifo, } EXPORT_SYMBOL(__kfifo_out_peek); +unsigned int __kfifo_out_linear(struct __kfifo *fifo, + unsigned int *tail, unsigned int n) +{ + unsigned int size = fifo->mask + 1; + unsigned int off = fifo->out & fifo->mask; + + if (tail) + *tail = off; + + return min3(n, fifo->in - fifo->out, size - off); +} +EXPORT_SYMBOL(__kfifo_out_linear); + unsigned int __kfifo_out(struct __kfifo *fifo, void *buf, unsigned int len) { @@ -292,51 +306,31 @@ int __kfifo_to_user(struct __kfifo *fifo, void __user *to, } EXPORT_SYMBOL(__kfifo_to_user); -static int setup_sgl_buf(struct scatterlist *sgl, void *buf, - int nents, unsigned int len) +static unsigned int setup_sgl_buf(struct __kfifo *fifo, struct scatterlist *sgl, + unsigned int data_offset, int nents, + unsigned int len, dma_addr_t dma) { - int n; - unsigned int l; - unsigned int off; - struct page *page; + const void *buf = fifo->data + data_offset; - if (!nents) + if (!nents || !len) return 0; - if (!len) - return 0; + sg_set_buf(sgl, buf, len); - n = 0; - page = virt_to_page(buf); - off = offset_in_page(buf); - l = 0; - - while (len >= l + PAGE_SIZE - off) { - struct page *npage; - - l += PAGE_SIZE; - buf += PAGE_SIZE; - npage = virt_to_page(buf); - if (page_to_phys(page) != page_to_phys(npage) - l) { - sg_set_page(sgl, page, l - off, off); - sgl = sg_next(sgl); - if (++n == nents || sgl == NULL) - return n; - page = npage; - len -= l - off; - l = off = 0; - } + if (dma != DMA_MAPPING_ERROR) { + sg_dma_address(sgl) = dma + data_offset; + sg_dma_len(sgl) = len; } - sg_set_page(sgl, page, len, off); - return n + 1; + + return 1; } static unsigned int setup_sgl(struct __kfifo *fifo, struct scatterlist *sgl, - int nents, unsigned int len, unsigned int off) + int nents, unsigned int len, unsigned int off, dma_addr_t dma) { unsigned int size = fifo->mask + 1; unsigned int esize = fifo->esize; - unsigned int l; + unsigned int len_to_end; unsigned int n; off &= fifo->mask; @@ -345,16 +339,17 @@ static unsigned int setup_sgl(struct __kfifo *fifo, struct scatterlist *sgl, size *= esize; len *= esize; } - l = min(len, size - off); + len_to_end = min(len, size - off); - n = setup_sgl_buf(sgl, fifo->data + off, nents, l); - n += setup_sgl_buf(sgl + n, fifo->data, nents - n, len - l); + n = setup_sgl_buf(fifo, sgl, off, nents, len_to_end, dma); + n += setup_sgl_buf(fifo, sgl + n, 0, nents - n, len - len_to_end, dma); return n; } unsigned int __kfifo_dma_in_prepare(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len) + struct scatterlist *sgl, int nents, unsigned int len, + dma_addr_t dma) { unsigned int l; @@ -362,12 +357,13 @@ unsigned int __kfifo_dma_in_prepare(struct __kfifo *fifo, if (len > l) len = l; - return setup_sgl(fifo, sgl, nents, len, fifo->in); + return setup_sgl(fifo, sgl, nents, len, fifo->in, dma); } EXPORT_SYMBOL(__kfifo_dma_in_prepare); unsigned int __kfifo_dma_out_prepare(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len) + struct scatterlist *sgl, int nents, unsigned int len, + dma_addr_t dma) { unsigned int l; @@ -375,7 +371,7 @@ unsigned int __kfifo_dma_out_prepare(struct __kfifo *fifo, if (len > l) len = l; - return setup_sgl(fifo, sgl, nents, len, fifo->out); + return setup_sgl(fifo, sgl, nents, len, fifo->out, dma); } EXPORT_SYMBOL(__kfifo_dma_out_prepare); @@ -473,6 +469,19 @@ unsigned int __kfifo_out_peek_r(struct __kfifo *fifo, void *buf, } EXPORT_SYMBOL(__kfifo_out_peek_r); +unsigned int __kfifo_out_linear_r(struct __kfifo *fifo, + unsigned int *tail, unsigned int n, size_t recsize) +{ + if (fifo->in == fifo->out) + return 0; + + if (tail) + *tail = fifo->out + recsize; + + return min(n, __kfifo_peek_n(fifo, recsize)); +} +EXPORT_SYMBOL(__kfifo_out_linear_r); + unsigned int __kfifo_out_r(struct __kfifo *fifo, void *buf, unsigned int len, size_t recsize) { @@ -546,7 +555,8 @@ int __kfifo_to_user_r(struct __kfifo *fifo, void __user *to, EXPORT_SYMBOL(__kfifo_to_user_r); unsigned int __kfifo_dma_in_prepare_r(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len, size_t recsize) + struct scatterlist *sgl, int nents, unsigned int len, size_t recsize, + dma_addr_t dma) { BUG_ON(!nents); @@ -555,7 +565,7 @@ unsigned int __kfifo_dma_in_prepare_r(struct __kfifo *fifo, if (len + recsize > kfifo_unused(fifo)) return 0; - return setup_sgl(fifo, sgl, nents, len, fifo->in + recsize); + return setup_sgl(fifo, sgl, nents, len, fifo->in + recsize, dma); } EXPORT_SYMBOL(__kfifo_dma_in_prepare_r); @@ -569,7 +579,8 @@ void __kfifo_dma_in_finish_r(struct __kfifo *fifo, EXPORT_SYMBOL(__kfifo_dma_in_finish_r); unsigned int __kfifo_dma_out_prepare_r(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len, size_t recsize) + struct scatterlist *sgl, int nents, unsigned int len, size_t recsize, + dma_addr_t dma) { BUG_ON(!nents); @@ -578,15 +589,7 @@ unsigned int __kfifo_dma_out_prepare_r(struct __kfifo *fifo, if (len + recsize > fifo->in - fifo->out) return 0; - return setup_sgl(fifo, sgl, nents, len, fifo->out + recsize); + return setup_sgl(fifo, sgl, nents, len, fifo->out + recsize, dma); } EXPORT_SYMBOL(__kfifo_dma_out_prepare_r); -void __kfifo_dma_out_finish_r(struct __kfifo *fifo, size_t recsize) -{ - unsigned int len; - - len = __kfifo_peek_n(fifo, recsize); - fifo->out += len + recsize; -} -EXPORT_SYMBOL(__kfifo_dma_out_finish_r); diff --git a/lib/kobject.c b/lib/kobject.c index 72fa20f405f1..abe5f5b856ce 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -1096,30 +1096,6 @@ void *kobj_ns_grab_current(enum kobj_ns_type type) } EXPORT_SYMBOL_GPL(kobj_ns_grab_current); -const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk) -{ - const void *ns = NULL; - - spin_lock(&kobj_ns_type_lock); - if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) - ns = kobj_ns_ops_tbl[type]->netlink_ns(sk); - spin_unlock(&kobj_ns_type_lock); - - return ns; -} - -const void *kobj_ns_initial(enum kobj_ns_type type) -{ - const void *ns = NULL; - - spin_lock(&kobj_ns_type_lock); - if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) - ns = kobj_ns_ops_tbl[type]->initial_ns(); - spin_unlock(&kobj_ns_type_lock); - - return ns; -} - void kobj_ns_drop(enum kobj_ns_type type, void *ns) { spin_lock(&kobj_ns_type_lock); diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index 03b427e2707e..b7f2fa08d9c8 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -433,8 +433,23 @@ static void zap_modalias_env(struct kobj_uevent_env *env) len = strlen(env->envp[i]) + 1; if (i != env->envp_idx - 1) { + /* @env->envp[] contains pointers to @env->buf[] + * with @env->buflen chars, and we are removing + * variable MODALIAS here pointed by @env->envp[i] + * with length @len as shown below: + * + * 0 @env->buf[] @env->buflen + * --------------------------------------------- + * ^ ^ ^ ^ + * | |-> @len <-| target block | + * @env->envp[0] @env->envp[i] @env->envp[i + 1] + * + * so the "target block" indicated above is moved + * backward by @len, and its right size is + * @env->buflen - (@env->envp[i + 1] - @env->envp[0]). + */ memmove(env->envp[i], env->envp[i + 1], - env->buflen - len); + env->buflen - (env->envp[i + 1] - env->envp[0])); for (j = i; j < env->envp_idx - 1; j++) env->envp[j] = env->envp[j + 1] - len; diff --git a/lib/kunit/Kconfig b/lib/kunit/Kconfig index 34d7242d526d..a97897edd964 100644 --- a/lib/kunit/Kconfig +++ b/lib/kunit/Kconfig @@ -81,4 +81,16 @@ config KUNIT_DEFAULT_ENABLED In most cases this should be left as Y. Only if additional opt-in behavior is needed should this be set to N. +config KUNIT_AUTORUN_ENABLED + bool "Default value of kunit.autorun" + default y + help + Sets the default value of kunit.autorun. If set to N then KUnit + tests will not run after initialization unless kunit.autorun=1 is + passed to the kernel command line. The test can still be run manually + via debugfs interface. + + In most cases this should be left as Y. Only if additional opt-in + behavior is needed should this be set to N. + endif # KUNIT diff --git a/lib/kunit/Makefile b/lib/kunit/Makefile index 309659a32a78..5aa51978e456 100644 --- a/lib/kunit/Makefile +++ b/lib/kunit/Makefile @@ -2,13 +2,15 @@ obj-$(CONFIG_KUNIT) += kunit.o kunit-objs += test.o \ resource.o \ + user_alloc.o \ static_stub.o \ string-stream.o \ assert.o \ try-catch.o \ executor.o \ attributes.o \ - device.o + device.o \ + platform.o ifeq ($(CONFIG_KUNIT_DEBUGFS),y) kunit-objs += debugfs.o @@ -18,10 +20,12 @@ endif obj-y += hooks.o obj-$(CONFIG_KUNIT_TEST) += kunit-test.o +obj-$(CONFIG_KUNIT_TEST) += platform-test.o # string-stream-test compiles built-in only. ifeq ($(CONFIG_KUNIT_TEST),y) obj-$(CONFIG_KUNIT_TEST) += string-stream-test.o +obj-$(CONFIG_KUNIT_TEST) += assert_test.o endif obj-$(CONFIG_KUNIT_EXAMPLE_TEST) += kunit-example-test.o diff --git a/lib/kunit/assert.c b/lib/kunit/assert.c index dd1d633d0fe2..867aa5c4bccf 100644 --- a/lib/kunit/assert.c +++ b/lib/kunit/assert.c @@ -7,6 +7,7 @@ */ #include <kunit/assert.h> #include <kunit/test.h> +#include <kunit/visibility.h> #include "string-stream.h" @@ -30,8 +31,9 @@ void kunit_assert_prologue(const struct kunit_loc *loc, } EXPORT_SYMBOL_GPL(kunit_assert_prologue); -static void kunit_assert_print_msg(const struct va_format *message, - struct string_stream *stream) +VISIBLE_IF_KUNIT +void kunit_assert_print_msg(const struct va_format *message, + struct string_stream *stream) { if (message->fmt) string_stream_add(stream, "\n%pV", message); @@ -89,7 +91,7 @@ void kunit_ptr_not_err_assert_format(const struct kunit_assert *assert, EXPORT_SYMBOL_GPL(kunit_ptr_not_err_assert_format); /* Checks if `text` is a literal representing `value`, e.g. "5" and 5 */ -static bool is_literal(const char *text, long long value) +VISIBLE_IF_KUNIT bool is_literal(const char *text, long long value) { char *buffer; int len; @@ -166,7 +168,7 @@ EXPORT_SYMBOL_GPL(kunit_binary_ptr_assert_format); /* Checks if KUNIT_EXPECT_STREQ() args were string literals. * Note: `text` will have ""s where as `value` will not. */ -static bool is_str_literal(const char *text, const char *value) +VISIBLE_IF_KUNIT bool is_str_literal(const char *text, const char *value) { int len; @@ -208,10 +210,11 @@ EXPORT_SYMBOL_GPL(kunit_binary_str_assert_format); /* Adds a hexdump of a buffer to a string_stream comparing it with * a second buffer. The different bytes are marked with <>. */ -static void kunit_assert_hexdump(struct string_stream *stream, - const void *buf, - const void *compared_buf, - const size_t len) +VISIBLE_IF_KUNIT +void kunit_assert_hexdump(struct string_stream *stream, + const void *buf, + const void *compared_buf, + const size_t len) { size_t i; const u8 *buf1 = buf; diff --git a/lib/kunit/assert_test.c b/lib/kunit/assert_test.c new file mode 100644 index 000000000000..4a5967712186 --- /dev/null +++ b/lib/kunit/assert_test.c @@ -0,0 +1,388 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * KUnit test for the assertion formatting functions. + * Author: Ivan Orlov <ivan.orlov0322@gmail.com> + */ +#include <kunit/test.h> +#include "string-stream.h" + +#define TEST_PTR_EXPECTED_BUF_SIZE 32 +#define HEXDUMP_TEST_BUF_LEN 5 +#define ASSERT_TEST_EXPECT_CONTAIN(test, str, substr) KUNIT_EXPECT_TRUE(test, strstr(str, substr)) +#define ASSERT_TEST_EXPECT_NCONTAIN(test, str, substr) KUNIT_EXPECT_FALSE(test, strstr(str, substr)) + +static void kunit_test_is_literal(struct kunit *test) +{ + KUNIT_EXPECT_TRUE(test, is_literal("5", 5)); + KUNIT_EXPECT_TRUE(test, is_literal("0", 0)); + KUNIT_EXPECT_TRUE(test, is_literal("1234567890", 1234567890)); + KUNIT_EXPECT_TRUE(test, is_literal("-1234567890", -1234567890)); + KUNIT_EXPECT_FALSE(test, is_literal("05", 5)); + KUNIT_EXPECT_FALSE(test, is_literal("", 0)); + KUNIT_EXPECT_FALSE(test, is_literal("-0", 0)); + KUNIT_EXPECT_FALSE(test, is_literal("12#45", 1245)); +} + +static void kunit_test_is_str_literal(struct kunit *test) +{ + KUNIT_EXPECT_TRUE(test, is_str_literal("\"Hello, World!\"", "Hello, World!")); + KUNIT_EXPECT_TRUE(test, is_str_literal("\"\"", "")); + KUNIT_EXPECT_TRUE(test, is_str_literal("\"\"\"", "\"")); + KUNIT_EXPECT_FALSE(test, is_str_literal("", "")); + KUNIT_EXPECT_FALSE(test, is_str_literal("\"", "\"")); + KUNIT_EXPECT_FALSE(test, is_str_literal("\"Abacaba", "Abacaba")); + KUNIT_EXPECT_FALSE(test, is_str_literal("Abacaba\"", "Abacaba")); + KUNIT_EXPECT_FALSE(test, is_str_literal("\"Abacaba\"", "\"Abacaba\"")); +} + +KUNIT_DEFINE_ACTION_WRAPPER(kfree_wrapper, kfree, const void *); + +/* this function is used to get a "char *" string from the string stream and defer its cleanup */ +static char *get_str_from_stream(struct kunit *test, struct string_stream *stream) +{ + char *str = string_stream_get_string(stream); + + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, str); + kunit_add_action(test, kfree_wrapper, (void *)str); + + return str; +} + +static void kunit_test_assert_prologue(struct kunit *test) +{ + struct string_stream *stream; + char *str; + const struct kunit_loc location = { + .file = "testfile.c", + .line = 1337, + }; + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + + /* Test an expectation fail prologue */ + kunit_assert_prologue(&location, KUNIT_EXPECTATION, stream); + str = get_str_from_stream(test, stream); + ASSERT_TEST_EXPECT_CONTAIN(test, str, "EXPECTATION"); + ASSERT_TEST_EXPECT_CONTAIN(test, str, "testfile.c"); + ASSERT_TEST_EXPECT_CONTAIN(test, str, "1337"); + + /* Test an assertion fail prologue */ + string_stream_clear(stream); + kunit_assert_prologue(&location, KUNIT_ASSERTION, stream); + str = get_str_from_stream(test, stream); + ASSERT_TEST_EXPECT_CONTAIN(test, str, "ASSERTION"); + ASSERT_TEST_EXPECT_CONTAIN(test, str, "testfile.c"); + ASSERT_TEST_EXPECT_CONTAIN(test, str, "1337"); +} + +/* + * This function accepts an arbitrary count of parameters and generates a va_format struct, + * which can be used to validate kunit_assert_print_msg function + */ +static void verify_assert_print_msg(struct kunit *test, + struct string_stream *stream, + char *expected, const char *format, ...) +{ + va_list list; + const struct va_format vformat = { + .fmt = format, + .va = &list, + }; + + va_start(list, format); + string_stream_clear(stream); + kunit_assert_print_msg(&vformat, stream); + KUNIT_EXPECT_STREQ(test, get_str_from_stream(test, stream), expected); +} + +static void kunit_test_assert_print_msg(struct kunit *test) +{ + struct string_stream *stream; + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + + verify_assert_print_msg(test, stream, "\nTest", "Test"); + verify_assert_print_msg(test, stream, "\nAbacaba -123 234", "%s %d %u", + "Abacaba", -123, 234U); + verify_assert_print_msg(test, stream, "", NULL); +} + +/* + * Further code contains the tests for different assert format functions. + * This helper function accepts the assert format function, executes it and + * validates the result string from the stream by checking that all of the + * substrings exist in the output. + */ +static void validate_assert(assert_format_t format_func, struct kunit *test, + const struct kunit_assert *assert, + struct string_stream *stream, int num_checks, ...) +{ + size_t i; + va_list checks; + char *cur_substr_exp; + struct va_format message = { NULL, NULL }; + + va_start(checks, num_checks); + string_stream_clear(stream); + format_func(assert, &message, stream); + + for (i = 0; i < num_checks; i++) { + cur_substr_exp = va_arg(checks, char *); + ASSERT_TEST_EXPECT_CONTAIN(test, get_str_from_stream(test, stream), cur_substr_exp); + } +} + +static void kunit_test_unary_assert_format(struct kunit *test) +{ + struct string_stream *stream; + struct kunit_assert assert = {}; + struct kunit_unary_assert un_assert = { + .assert = assert, + .condition = "expr", + .expected_true = true, + }; + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + + validate_assert(kunit_unary_assert_format, test, &un_assert.assert, + stream, 2, "true", "is false"); + + un_assert.expected_true = false; + validate_assert(kunit_unary_assert_format, test, &un_assert.assert, + stream, 2, "false", "is true"); +} + +static void kunit_test_ptr_not_err_assert_format(struct kunit *test) +{ + struct string_stream *stream; + struct kunit_assert assert = {}; + struct kunit_ptr_not_err_assert not_err_assert = { + .assert = assert, + .text = "expr", + .value = NULL, + }; + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + + /* Value is NULL. The corresponding message should be printed out */ + validate_assert(kunit_ptr_not_err_assert_format, test, + ¬_err_assert.assert, + stream, 1, "null"); + + /* Value is not NULL, but looks like an error pointer. Error should be printed out */ + not_err_assert.value = (void *)-12; + validate_assert(kunit_ptr_not_err_assert_format, test, + ¬_err_assert.assert, stream, 2, + "error", "-12"); +} + +static void kunit_test_binary_assert_format(struct kunit *test) +{ + struct string_stream *stream; + struct kunit_assert assert = {}; + struct kunit_binary_assert_text text = { + .left_text = "1 + 2", + .operation = "==", + .right_text = "2", + }; + const struct kunit_binary_assert binary_assert = { + .assert = assert, + .text = &text, + .left_value = 3, + .right_value = 2, + }; + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + + /* + * Printed values should depend on the input we provide: the left text, right text, left + * value and the right value. + */ + validate_assert(kunit_binary_assert_format, test, &binary_assert.assert, + stream, 4, "1 + 2", "2", "3", "=="); + + text.right_text = "4 - 2"; + validate_assert(kunit_binary_assert_format, test, &binary_assert.assert, + stream, 3, "==", "1 + 2", "4 - 2"); + + text.left_text = "3"; + validate_assert(kunit_binary_assert_format, test, &binary_assert.assert, + stream, 4, "3", "4 - 2", "2", "=="); + + text.right_text = "2"; + validate_assert(kunit_binary_assert_format, test, &binary_assert.assert, + stream, 3, "3", "2", "=="); +} + +static void kunit_test_binary_ptr_assert_format(struct kunit *test) +{ + struct string_stream *stream; + struct kunit_assert assert = {}; + char *addr_var_a, *addr_var_b; + static const void *var_a = (void *)0xDEADBEEF; + static const void *var_b = (void *)0xBADDCAFE; + struct kunit_binary_assert_text text = { + .left_text = "var_a", + .operation = "==", + .right_text = "var_b", + }; + struct kunit_binary_ptr_assert binary_ptr_assert = { + .assert = assert, + .text = &text, + .left_value = var_a, + .right_value = var_b, + }; + + addr_var_a = kunit_kzalloc(test, TEST_PTR_EXPECTED_BUF_SIZE, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, addr_var_a); + addr_var_b = kunit_kzalloc(test, TEST_PTR_EXPECTED_BUF_SIZE, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, addr_var_b); + /* + * Print the addresses to the buffers first. + * This is necessary as we may have different count of leading zeros in the pointer + * on different architectures. + */ + snprintf(addr_var_a, TEST_PTR_EXPECTED_BUF_SIZE, "%px", var_a); + snprintf(addr_var_b, TEST_PTR_EXPECTED_BUF_SIZE, "%px", var_b); + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + validate_assert(kunit_binary_ptr_assert_format, test, &binary_ptr_assert.assert, + stream, 3, addr_var_a, addr_var_b, "=="); +} + +static void kunit_test_binary_str_assert_format(struct kunit *test) +{ + struct string_stream *stream; + struct kunit_assert assert = {}; + static const char *var_a = "abacaba"; + static const char *var_b = "kernel"; + struct kunit_binary_assert_text text = { + .left_text = "var_a", + .operation = "==", + .right_text = "var_b", + }; + struct kunit_binary_str_assert binary_str_assert = { + .assert = assert, + .text = &text, + .left_value = var_a, + .right_value = var_b, + }; + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + + validate_assert(kunit_binary_str_assert_format, test, + &binary_str_assert.assert, + stream, 5, "var_a", "var_b", "\"abacaba\"", + "\"kernel\"", "=="); + + text.left_text = "\"abacaba\""; + validate_assert(kunit_binary_str_assert_format, test, &binary_str_assert.assert, + stream, 4, "\"abacaba\"", "var_b", "\"kernel\"", "=="); + + text.right_text = "\"kernel\""; + validate_assert(kunit_binary_str_assert_format, test, &binary_str_assert.assert, + stream, 3, "\"abacaba\"", "\"kernel\"", "=="); +} + +static const u8 hex_testbuf1[] = { 0x26, 0x74, 0x6b, 0x9c, 0x55, + 0x45, 0x9d, 0x47, 0xd6, 0x47, + 0x2, 0x89, 0x8c, 0x81, 0x94, + 0x12, 0xfe, 0x01 }; +static const u8 hex_testbuf2[] = { 0x26, 0x74, 0x6b, 0x9c, 0x55, + 0x45, 0x9d, 0x47, 0x21, 0x47, + 0xcd, 0x89, 0x24, 0x50, 0x94, + 0x12, 0xba, 0x01 }; +static void kunit_test_assert_hexdump(struct kunit *test) +{ + struct string_stream *stream; + char *str; + size_t i; + char buf[HEXDUMP_TEST_BUF_LEN]; + + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + /* Check that we are getting output like <xx> for non-matching numbers. */ + kunit_assert_hexdump(stream, hex_testbuf1, hex_testbuf2, sizeof(hex_testbuf1)); + str = get_str_from_stream(test, stream); + for (i = 0; i < sizeof(hex_testbuf1); i++) { + snprintf(buf, HEXDUMP_TEST_BUF_LEN, "<%02x>", hex_testbuf1[i]); + if (hex_testbuf1[i] != hex_testbuf2[i]) + ASSERT_TEST_EXPECT_CONTAIN(test, str, buf); + } + /* We shouldn't get any <xx> numbers when comparing the buffer with itself. */ + string_stream_clear(stream); + kunit_assert_hexdump(stream, hex_testbuf1, hex_testbuf1, sizeof(hex_testbuf1)); + str = get_str_from_stream(test, stream); + ASSERT_TEST_EXPECT_NCONTAIN(test, str, "<"); + ASSERT_TEST_EXPECT_NCONTAIN(test, str, ">"); +} + +static void kunit_test_mem_assert_format(struct kunit *test) +{ + struct string_stream *stream; + struct string_stream *expected_stream; + struct kunit_assert assert = {}; + static const struct kunit_binary_assert_text text = { + .left_text = "hex_testbuf1", + .operation = "==", + .right_text = "hex_testbuf2", + }; + struct kunit_mem_assert mem_assert = { + .assert = assert, + .text = &text, + .left_value = NULL, + .right_value = hex_testbuf2, + .size = sizeof(hex_testbuf1), + }; + + expected_stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, expected_stream); + stream = kunit_alloc_string_stream(test, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, stream); + + /* The left value is NULL */ + validate_assert(kunit_mem_assert_format, test, &mem_assert.assert, + stream, 2, "hex_testbuf1", "is not null"); + + /* The right value is NULL, the left value is not NULL */ + mem_assert.left_value = hex_testbuf1; + mem_assert.right_value = NULL; + validate_assert(kunit_mem_assert_format, test, &mem_assert.assert, + stream, 2, "hex_testbuf2", "is not null"); + + /* Both arguments are not null */ + mem_assert.left_value = hex_testbuf1; + mem_assert.right_value = hex_testbuf2; + + validate_assert(kunit_mem_assert_format, test, &mem_assert.assert, + stream, 3, "hex_testbuf1", "hex_testbuf2", "=="); +} + +static struct kunit_case assert_test_cases[] = { + KUNIT_CASE(kunit_test_is_literal), + KUNIT_CASE(kunit_test_is_str_literal), + KUNIT_CASE(kunit_test_assert_prologue), + KUNIT_CASE(kunit_test_assert_print_msg), + KUNIT_CASE(kunit_test_unary_assert_format), + KUNIT_CASE(kunit_test_ptr_not_err_assert_format), + KUNIT_CASE(kunit_test_binary_assert_format), + KUNIT_CASE(kunit_test_binary_ptr_assert_format), + KUNIT_CASE(kunit_test_binary_str_assert_format), + KUNIT_CASE(kunit_test_assert_hexdump), + KUNIT_CASE(kunit_test_mem_assert_format), + {} +}; + +static struct kunit_suite assert_test_suite = { + .name = "kunit-assert", + .test_cases = assert_test_cases, +}; + +kunit_test_suites(&assert_test_suite); diff --git a/lib/kunit/debugfs.c b/lib/kunit/debugfs.c index d548750a325a..9c326f1837bd 100644 --- a/lib/kunit/debugfs.c +++ b/lib/kunit/debugfs.c @@ -145,7 +145,7 @@ static ssize_t debugfs_run(struct file *file, struct inode *f_inode = file->f_inode; struct kunit_suite *suite = (struct kunit_suite *) f_inode->i_private; - __kunit_test_suites_init(&suite, 1); + __kunit_test_suites_init(&suite, 1, true); return count; } @@ -181,7 +181,7 @@ void kunit_debugfs_create_suite(struct kunit_suite *suite) * successfully. */ stream = alloc_string_stream(GFP_KERNEL); - if (IS_ERR_OR_NULL(stream)) + if (IS_ERR(stream)) return; string_stream_set_append_newlines(stream, true); @@ -189,7 +189,7 @@ void kunit_debugfs_create_suite(struct kunit_suite *suite) kunit_suite_for_each_test_case(suite, test_case) { stream = alloc_string_stream(GFP_KERNEL); - if (IS_ERR_OR_NULL(stream)) + if (IS_ERR(stream)) goto err; string_stream_set_append_newlines(stream, true); @@ -212,8 +212,11 @@ void kunit_debugfs_create_suite(struct kunit_suite *suite) err: string_stream_destroy(suite->log); - kunit_suite_for_each_test_case(suite, test_case) + suite->log = NULL; + kunit_suite_for_each_test_case(suite, test_case) { string_stream_destroy(test_case->log); + test_case->log = NULL; + } } void kunit_debugfs_destroy_suite(struct kunit_suite *suite) diff --git a/lib/kunit/device.c b/lib/kunit/device.c index 25c81ed465fb..520c1fccee8a 100644 --- a/lib/kunit/device.c +++ b/lib/kunit/device.c @@ -89,7 +89,7 @@ struct device_driver *kunit_driver_create(struct kunit *test, const char *name) if (!driver) return ERR_PTR(err); - driver->name = name; + driver->name = kunit_kstrdup_const(test, name, GFP_KERNEL); driver->bus = &kunit_bus_type; driver->owner = THIS_MODULE; @@ -192,8 +192,11 @@ void kunit_device_unregister(struct kunit *test, struct device *dev) const struct device_driver *driver = to_kunit_device(dev)->driver; kunit_release_action(test, device_unregister_wrapper, dev); - if (driver) + if (driver) { + const char *driver_name = driver->name; kunit_release_action(test, driver_unregister_wrapper, (void *)driver); + kunit_kfree_const(test, driver_name); + } } EXPORT_SYMBOL_GPL(kunit_device_unregister); diff --git a/lib/kunit/executor.c b/lib/kunit/executor.c index 70b9a43cd257..3f39955cb0f1 100644 --- a/lib/kunit/executor.c +++ b/lib/kunit/executor.c @@ -29,6 +29,22 @@ const char *kunit_action(void) return action_param; } +/* + * Run KUnit tests after initialization + */ +#ifdef CONFIG_KUNIT_AUTORUN_ENABLED +static bool autorun_param = true; +#else +static bool autorun_param; +#endif +module_param_named(autorun, autorun_param, bool, 0); +MODULE_PARM_DESC(autorun, "Run KUnit tests after initialization"); + +bool kunit_autorun(void) +{ + return autorun_param; +} + static char *filter_glob_param; static char *filter_param; static char *filter_action_param; @@ -70,32 +86,26 @@ struct kunit_glob_filter { static int kunit_parse_glob_filter(struct kunit_glob_filter *parsed, const char *filter_glob) { - const int len = strlen(filter_glob); const char *period = strchr(filter_glob, '.'); if (!period) { - parsed->suite_glob = kzalloc(len + 1, GFP_KERNEL); + parsed->suite_glob = kstrdup(filter_glob, GFP_KERNEL); if (!parsed->suite_glob) return -ENOMEM; - parsed->test_glob = NULL; - strcpy(parsed->suite_glob, filter_glob); return 0; } - parsed->suite_glob = kzalloc(period - filter_glob + 1, GFP_KERNEL); + parsed->suite_glob = kstrndup(filter_glob, period - filter_glob, GFP_KERNEL); if (!parsed->suite_glob) return -ENOMEM; - parsed->test_glob = kzalloc(len - (period - filter_glob) + 1, GFP_KERNEL); + parsed->test_glob = kstrdup(period + 1, GFP_KERNEL); if (!parsed->test_glob) { kfree(parsed->suite_glob); return -ENOMEM; } - strncpy(parsed->suite_glob, filter_glob, period - filter_glob); - strncpy(parsed->test_glob, period + 1, len - (period - filter_glob)); - return 0; } @@ -266,13 +276,14 @@ free_copy: void kunit_exec_run_tests(struct kunit_suite_set *suite_set, bool builtin) { size_t num_suites = suite_set->end - suite_set->start; + bool autorun = kunit_autorun(); - if (builtin || num_suites) { + if (autorun && (builtin || num_suites)) { pr_info("KTAP version 1\n"); pr_info("1..%zu\n", num_suites); } - __kunit_test_suites_init(suite_set->start, num_suites); + __kunit_test_suites_init(suite_set->start, num_suites, autorun); } void kunit_exec_list_tests(struct kunit_suite_set *suite_set, bool include_attr) diff --git a/lib/kunit/executor_test.c b/lib/kunit/executor_test.c index 3f7f967e3688..f0090c2729cd 100644 --- a/lib/kunit/executor_test.c +++ b/lib/kunit/executor_test.c @@ -286,7 +286,7 @@ static struct kunit_suite *alloc_fake_suite(struct kunit *test, /* We normally never expect to allocate suites, hence the non-const cast. */ suite = kunit_kzalloc(test, sizeof(*suite), GFP_KERNEL); - strncpy((char *)suite->name, suite_name, sizeof(suite->name) - 1); + strscpy((char *)suite->name, suite_name, sizeof(suite->name)); suite->test_cases = test_cases; return suite; diff --git a/lib/kunit/kunit-example-test.c b/lib/kunit/kunit-example-test.c index 798924f7cc86..3056d6bc705d 100644 --- a/lib/kunit/kunit-example-test.c +++ b/lib/kunit/kunit-example-test.c @@ -374,4 +374,5 @@ static struct kunit_suite example_init_test_suite = { */ kunit_test_init_section_suites(&example_init_test_suite); +MODULE_DESCRIPTION("Example KUnit test suite"); MODULE_LICENSE("GPL v2"); diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c index e3412e0ca399..d9c781c859fd 100644 --- a/lib/kunit/kunit-test.c +++ b/lib/kunit/kunit-test.c @@ -805,6 +805,8 @@ static void kunit_device_driver_test(struct kunit *test) struct device *test_device; struct driver_test_state *test_state = kunit_kzalloc(test, sizeof(*test_state), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, test_state); + test->priv = test_state; test_driver = kunit_driver_create(test, "my_driver"); @@ -871,4 +873,5 @@ kunit_test_suites(&kunit_try_catch_test_suite, &kunit_resource_test_suite, &kunit_current_test_suite, &kunit_device_test_suite, &kunit_fault_test_suite); +MODULE_DESCRIPTION("KUnit test for core test infrastructure"); MODULE_LICENSE("GPL v2"); diff --git a/lib/kunit/platform-test.c b/lib/kunit/platform-test.c new file mode 100644 index 000000000000..e3debb8fbcef --- /dev/null +++ b/lib/kunit/platform-test.c @@ -0,0 +1,224 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KUnit test for KUnit platform driver infrastructure. + */ + +#include <linux/platform_device.h> + +#include <kunit/platform_device.h> +#include <kunit/test.h> + +/* + * Test that kunit_platform_device_alloc() creates a platform device. + */ +static void kunit_platform_device_alloc_test(struct kunit *test) +{ + KUNIT_EXPECT_NOT_ERR_OR_NULL(test, + kunit_platform_device_alloc(test, "kunit-platform", 1)); +} + +/* + * Test that kunit_platform_device_add() registers a platform device on the + * platform bus with the proper name and id. + */ +static void kunit_platform_device_add_test(struct kunit *test) +{ + struct platform_device *pdev; + const char *name = "kunit-platform-add"; + const int id = -1; + + pdev = kunit_platform_device_alloc(test, name, id); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pdev); + + KUNIT_EXPECT_EQ(test, 0, kunit_platform_device_add(test, pdev)); + KUNIT_EXPECT_TRUE(test, dev_is_platform(&pdev->dev)); + KUNIT_EXPECT_STREQ(test, pdev->name, name); + KUNIT_EXPECT_EQ(test, pdev->id, id); +} + +/* + * Test that kunit_platform_device_add() called twice with the same device name + * and id fails the second time and properly cleans up. + */ +static void kunit_platform_device_add_twice_fails_test(struct kunit *test) +{ + struct platform_device *pdev; + const char *name = "kunit-platform-add-2"; + const int id = -1; + + pdev = kunit_platform_device_alloc(test, name, id); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pdev); + KUNIT_ASSERT_EQ(test, 0, kunit_platform_device_add(test, pdev)); + + pdev = kunit_platform_device_alloc(test, name, id); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pdev); + + KUNIT_EXPECT_NE(test, 0, kunit_platform_device_add(test, pdev)); +} + +static int kunit_platform_device_find_by_name(struct device *dev, const void *data) +{ + return strcmp(dev_name(dev), data) == 0; +} + +/* + * Test that kunit_platform_device_add() cleans up by removing the platform + * device when the test finishes. */ +static void kunit_platform_device_add_cleans_up(struct kunit *test) +{ + struct platform_device *pdev; + const char *name = "kunit-platform-clean"; + const int id = -1; + struct kunit fake; + struct device *dev; + + kunit_init_test(&fake, "kunit_platform_device_add_fake_test", NULL); + KUNIT_ASSERT_EQ(test, fake.status, KUNIT_SUCCESS); + + pdev = kunit_platform_device_alloc(&fake, name, id); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pdev); + KUNIT_ASSERT_EQ(test, 0, kunit_platform_device_add(&fake, pdev)); + dev = bus_find_device(&platform_bus_type, NULL, name, + kunit_platform_device_find_by_name); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev); + put_device(dev); + + /* Remove pdev */ + kunit_cleanup(&fake); + + /* + * Failing to migrate the kunit_resource would lead to an extra + * put_device() call on the platform device. The best we can do here is + * make sure the device no longer exists on the bus, but if something + * is wrong we'll see a refcount underflow here. We can't test for a + * refcount underflow because the kref matches the lifetime of the + * device which should already be freed and could be used by something + * else. + */ + dev = bus_find_device(&platform_bus_type, NULL, name, + kunit_platform_device_find_by_name); + KUNIT_EXPECT_PTR_EQ(test, NULL, dev); + put_device(dev); +} + +/* + * Test suite for struct platform_device kunit APIs + */ +static struct kunit_case kunit_platform_device_test_cases[] = { + KUNIT_CASE(kunit_platform_device_alloc_test), + KUNIT_CASE(kunit_platform_device_add_test), + KUNIT_CASE(kunit_platform_device_add_twice_fails_test), + KUNIT_CASE(kunit_platform_device_add_cleans_up), + {} +}; + +static struct kunit_suite kunit_platform_device_suite = { + .name = "kunit_platform_device", + .test_cases = kunit_platform_device_test_cases, +}; + +struct kunit_platform_driver_test_context { + struct platform_driver pdrv; + const char *data; +}; + +static const char * const test_data = "test data"; + +static inline struct kunit_platform_driver_test_context * +to_test_context(struct platform_device *pdev) +{ + return container_of(to_platform_driver(pdev->dev.driver), + struct kunit_platform_driver_test_context, + pdrv); +} + +static int kunit_platform_driver_probe(struct platform_device *pdev) +{ + struct kunit_platform_driver_test_context *ctx; + + ctx = to_test_context(pdev); + ctx->data = test_data; + + return 0; +} + +/* Test that kunit_platform_driver_register() registers a driver that probes. */ +static void kunit_platform_driver_register_test(struct kunit *test) +{ + struct platform_device *pdev; + struct kunit_platform_driver_test_context *ctx; + DECLARE_COMPLETION_ONSTACK(comp); + const char *name = "kunit-platform-register"; + + ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + + pdev = kunit_platform_device_alloc(test, name, -1); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pdev); + KUNIT_ASSERT_EQ(test, 0, kunit_platform_device_add(test, pdev)); + + ctx->pdrv.probe = kunit_platform_driver_probe; + ctx->pdrv.driver.name = name; + ctx->pdrv.driver.owner = THIS_MODULE; + + KUNIT_ASSERT_EQ(test, 0, kunit_platform_device_prepare_wait_for_probe(test, pdev, &comp)); + + KUNIT_EXPECT_EQ(test, 0, kunit_platform_driver_register(test, &ctx->pdrv)); + KUNIT_EXPECT_NE(test, 0, wait_for_completion_timeout(&comp, 3 * HZ)); + KUNIT_EXPECT_STREQ(test, ctx->data, test_data); +} + +/* + * Test that kunit_platform_device_prepare_wait_for_probe() completes the completion + * when the device is already probed. + */ +static void kunit_platform_device_prepare_wait_for_probe_completes_when_already_probed(struct kunit *test) +{ + struct platform_device *pdev; + struct kunit_platform_driver_test_context *ctx; + DECLARE_COMPLETION_ONSTACK(comp); + const char *name = "kunit-platform-wait"; + + ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + + pdev = kunit_platform_device_alloc(test, name, -1); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pdev); + KUNIT_ASSERT_EQ(test, 0, kunit_platform_device_add(test, pdev)); + + ctx->pdrv.probe = kunit_platform_driver_probe; + ctx->pdrv.driver.name = name; + ctx->pdrv.driver.owner = THIS_MODULE; + + /* Make sure driver has actually probed */ + KUNIT_ASSERT_EQ(test, 0, kunit_platform_device_prepare_wait_for_probe(test, pdev, &comp)); + KUNIT_ASSERT_EQ(test, 0, kunit_platform_driver_register(test, &ctx->pdrv)); + KUNIT_ASSERT_NE(test, 0, wait_for_completion_timeout(&comp, 3 * HZ)); + + reinit_completion(&comp); + KUNIT_ASSERT_EQ(test, 0, kunit_platform_device_prepare_wait_for_probe(test, pdev, &comp)); + + KUNIT_EXPECT_NE(test, 0, wait_for_completion_timeout(&comp, HZ)); +} + +static struct kunit_case kunit_platform_driver_test_cases[] = { + KUNIT_CASE(kunit_platform_driver_register_test), + KUNIT_CASE(kunit_platform_device_prepare_wait_for_probe_completes_when_already_probed), + {} +}; + +/* + * Test suite for struct platform_driver kunit APIs + */ +static struct kunit_suite kunit_platform_driver_suite = { + .name = "kunit_platform_driver", + .test_cases = kunit_platform_driver_test_cases, +}; + +kunit_test_suites( + &kunit_platform_device_suite, + &kunit_platform_driver_suite, +); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("KUnit test for KUnit platform driver infrastructure"); diff --git a/lib/kunit/platform.c b/lib/kunit/platform.c new file mode 100644 index 000000000000..0b518de26065 --- /dev/null +++ b/lib/kunit/platform.c @@ -0,0 +1,302 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test managed platform driver + */ + +#include <linux/completion.h> +#include <linux/device/bus.h> +#include <linux/device/driver.h> +#include <linux/platform_device.h> + +#include <kunit/platform_device.h> +#include <kunit/resource.h> + +struct kunit_platform_device_alloc_params { + const char *name; + int id; +}; + +static int kunit_platform_device_alloc_init(struct kunit_resource *res, void *context) +{ + struct kunit_platform_device_alloc_params *params = context; + struct platform_device *pdev; + + pdev = platform_device_alloc(params->name, params->id); + if (!pdev) + return -ENOMEM; + + res->data = pdev; + + return 0; +} + +static void kunit_platform_device_alloc_exit(struct kunit_resource *res) +{ + struct platform_device *pdev = res->data; + + platform_device_put(pdev); +} + +/** + * kunit_platform_device_alloc() - Allocate a KUnit test managed platform device + * @test: test context + * @name: device name of platform device to alloc + * @id: identifier of platform device to alloc. + * + * Allocate a test managed platform device. The device is put when the test completes. + * + * Return: Allocated platform device on success, NULL on failure. + */ +struct platform_device * +kunit_platform_device_alloc(struct kunit *test, const char *name, int id) +{ + struct kunit_platform_device_alloc_params params = { + .name = name, + .id = id, + }; + + return kunit_alloc_resource(test, + kunit_platform_device_alloc_init, + kunit_platform_device_alloc_exit, + GFP_KERNEL, ¶ms); +} +EXPORT_SYMBOL_GPL(kunit_platform_device_alloc); + +static void kunit_platform_device_add_exit(struct kunit_resource *res) +{ + struct platform_device *pdev = res->data; + + platform_device_unregister(pdev); +} + +static bool +kunit_platform_device_alloc_match(struct kunit *test, + struct kunit_resource *res, void *match_data) +{ + struct platform_device *pdev = match_data; + + return res->data == pdev && res->free == kunit_platform_device_alloc_exit; +} + +KUNIT_DEFINE_ACTION_WRAPPER(platform_device_unregister_wrapper, + platform_device_unregister, struct platform_device *); +/** + * kunit_platform_device_add() - Register a KUnit test managed platform device + * @test: test context + * @pdev: platform device to add + * + * Register a test managed platform device. The device is unregistered when the + * test completes. + * + * Return: 0 on success, negative errno on failure. + */ +int kunit_platform_device_add(struct kunit *test, struct platform_device *pdev) +{ + struct kunit_resource *res; + int ret; + + ret = platform_device_add(pdev); + if (ret) + return ret; + + res = kunit_find_resource(test, kunit_platform_device_alloc_match, pdev); + if (res) { + /* + * Transfer the reference count of the platform device if it + * was allocated with kunit_platform_device_alloc(). In this + * case, calling platform_device_put() when the test exits from + * kunit_platform_device_alloc_exit() would lead to reference + * count underflow because platform_device_unregister_wrapper() + * calls platform_device_unregister() which also calls + * platform_device_put(). + * + * Usually callers transfer the refcount initialized in + * platform_device_alloc() to platform_device_add() by calling + * platform_device_unregister() when platform_device_add() + * succeeds or platform_device_put() when it fails. KUnit has to + * keep this straight by redirecting the free routine for the + * resource to the right function. Luckily this only has to + * account for the success scenario. + */ + res->free = kunit_platform_device_add_exit; + kunit_put_resource(res); + } else { + ret = kunit_add_action_or_reset(test, platform_device_unregister_wrapper, pdev); + if (ret) + return ret; + } + + return 0; +} +EXPORT_SYMBOL_GPL(kunit_platform_device_add); + +struct kunit_platform_device_probe_nb { + struct completion *x; + struct device *dev; + struct notifier_block nb; +}; + +static int kunit_platform_device_probe_notify(struct notifier_block *nb, + unsigned long event, void *data) +{ + struct kunit_platform_device_probe_nb *knb; + struct device *dev = data; + + knb = container_of(nb, struct kunit_platform_device_probe_nb, nb); + if (event != BUS_NOTIFY_BOUND_DRIVER || knb->dev != dev) + return NOTIFY_DONE; + + complete(knb->x); + + return NOTIFY_OK; +} + +static void kunit_platform_device_probe_nb_remove(void *nb) +{ + bus_unregister_notifier(&platform_bus_type, nb); +} + +/** + * kunit_platform_device_prepare_wait_for_probe() - Prepare a completion + * variable to wait for a platform device to probe + * @test: test context + * @pdev: platform device to prepare to wait for probe of + * @x: completion variable completed when @dev has probed + * + * Prepare a completion variable @x to wait for @pdev to probe. Waiting on the + * completion forces a preemption, allowing the platform driver to probe. + * + * Example + * + * .. code-block:: c + * + * static int kunit_platform_driver_probe(struct platform_device *pdev) + * { + * return 0; + * } + * + * static void kunit_platform_driver_test(struct kunit *test) + * { + * struct platform_device *pdev; + * struct platform_driver *pdrv; + * DECLARE_COMPLETION_ONSTACK(comp); + * + * pdev = kunit_platform_device_alloc(test, "kunit-platform", -1); + * KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pdev); + * KUNIT_ASSERT_EQ(test, 0, kunit_platform_device_add(test, pdev)); + * + * pdrv = kunit_kzalloc(test, sizeof(*pdrv), GFP_KERNEL); + * KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pdrv); + * + * pdrv->probe = kunit_platform_driver_probe; + * pdrv->driver.name = "kunit-platform"; + * pdrv->driver.owner = THIS_MODULE; + * + * KUNIT_ASSERT_EQ(test, 0, kunit_platform_device_prepare_wait_for_probe(test, pdev, &comp)); + * KUNIT_ASSERT_EQ(test, 0, kunit_platform_driver_register(test, pdrv)); + * + * KUNIT_EXPECT_NE(test, 0, wait_for_completion_timeout(&comp, 3 * HZ)); + * } + * + * Return: 0 on success, negative errno on failure. + */ +int kunit_platform_device_prepare_wait_for_probe(struct kunit *test, + struct platform_device *pdev, + struct completion *x) +{ + struct device *dev = &pdev->dev; + struct kunit_platform_device_probe_nb *knb; + bool bound; + + knb = kunit_kzalloc(test, sizeof(*knb), GFP_KERNEL); + if (!knb) + return -ENOMEM; + + knb->nb.notifier_call = kunit_platform_device_probe_notify; + knb->dev = dev; + knb->x = x; + + device_lock(dev); + bound = device_is_bound(dev); + if (bound) { + device_unlock(dev); + complete(x); + kunit_kfree(test, knb); + return 0; + } + + bus_register_notifier(&platform_bus_type, &knb->nb); + device_unlock(&pdev->dev); + + return kunit_add_action_or_reset(test, kunit_platform_device_probe_nb_remove, &knb->nb); +} +EXPORT_SYMBOL_GPL(kunit_platform_device_prepare_wait_for_probe); + +KUNIT_DEFINE_ACTION_WRAPPER(platform_driver_unregister_wrapper, + platform_driver_unregister, struct platform_driver *); +/** + * kunit_platform_driver_register() - Register a KUnit test managed platform driver + * @test: test context + * @drv: platform driver to register + * + * Register a test managed platform driver. This allows callers to embed the + * @drv in a container structure and use container_of() in the probe function + * to pass information to KUnit tests. + * + * Example + * + * .. code-block:: c + * + * struct kunit_test_context { + * struct platform_driver pdrv; + * const char *data; + * }; + * + * static inline struct kunit_test_context * + * to_test_context(struct platform_device *pdev) + * { + * return container_of(to_platform_driver(pdev->dev.driver), + * struct kunit_test_context, + * pdrv); + * } + * + * static int kunit_platform_driver_probe(struct platform_device *pdev) + * { + * struct kunit_test_context *ctx; + * + * ctx = to_test_context(pdev); + * ctx->data = "test data"; + * + * return 0; + * } + * + * static void kunit_platform_driver_test(struct kunit *test) + * { + * struct kunit_test_context *ctx; + * + * ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL); + * KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + * + * ctx->pdrv.probe = kunit_platform_driver_probe; + * ctx->pdrv.driver.name = "kunit-platform"; + * ctx->pdrv.driver.owner = THIS_MODULE; + * + * KUNIT_EXPECT_EQ(test, 0, kunit_platform_driver_register(test, &ctx->pdrv)); + * <... wait for driver to probe ...> + * KUNIT_EXPECT_STREQ(test, ctx->data, "test data"); + * } + * + * Return: 0 on success, negative errno on failure. + */ +int kunit_platform_driver_register(struct kunit *test, + struct platform_driver *drv) +{ + int ret; + + ret = platform_driver_register(drv); + if (ret) + return ret; + + return kunit_add_action_or_reset(test, platform_driver_unregister_wrapper, drv); +} +EXPORT_SYMBOL_GPL(kunit_platform_driver_register); diff --git a/lib/kunit/string-stream-test.c b/lib/kunit/string-stream-test.c index 7511442ea98f..7734e33156f9 100644 --- a/lib/kunit/string-stream-test.c +++ b/lib/kunit/string-stream-test.c @@ -9,6 +9,7 @@ #include <kunit/static_stub.h> #include <kunit/test.h> #include <linux/ktime.h> +#include <linux/prandom.h> #include <linux/slab.h> #include <linux/timekeeping.h> diff --git a/lib/kunit/test.c b/lib/kunit/test.c index b8514dbb337c..146d1b48a096 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -708,7 +708,8 @@ bool kunit_enabled(void) return enable_param; } -int __kunit_test_suites_init(struct kunit_suite * const * const suites, int num_suites) +int __kunit_test_suites_init(struct kunit_suite * const * const suites, int num_suites, + bool run_tests) { unsigned int i; @@ -731,7 +732,8 @@ int __kunit_test_suites_init(struct kunit_suite * const * const suites, int num_ for (i = 0; i < num_suites; i++) { kunit_init_suite(suites[i]); - kunit_run_tests(suites[i]); + if (run_tests) + kunit_run_tests(suites[i]); } static_branch_dec(&kunit_running); @@ -874,6 +876,25 @@ void kunit_kfree(struct kunit *test, const void *ptr) } EXPORT_SYMBOL_GPL(kunit_kfree); +void kunit_kfree_const(struct kunit *test, const void *x) +{ +#if !IS_MODULE(CONFIG_KUNIT) + if (!is_kernel_rodata((unsigned long)x)) +#endif + kunit_kfree(test, x); +} +EXPORT_SYMBOL_GPL(kunit_kfree_const); + +const char *kunit_kstrdup_const(struct kunit *test, const char *str, gfp_t gfp) +{ +#if !IS_MODULE(CONFIG_KUNIT) + if (is_kernel_rodata((unsigned long)str)) + return str; +#endif + return kunit_kstrdup(test, str, gfp); +} +EXPORT_SYMBOL_GPL(kunit_kstrdup_const); + void kunit_cleanup(struct kunit *test) { struct kunit_resource *res; @@ -938,4 +959,5 @@ static void __exit kunit_exit(void) } module_exit(kunit_exit); +MODULE_DESCRIPTION("Base unit test (KUnit) API"); MODULE_LICENSE("GPL v2"); diff --git a/lib/kunit/user_alloc.c b/lib/kunit/user_alloc.c new file mode 100644 index 000000000000..46951be018be --- /dev/null +++ b/lib/kunit/user_alloc.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KUnit userspace memory allocation resource management. + */ +#include <kunit/resource.h> +#include <kunit/test.h> +#include <linux/kthread.h> +#include <linux/mm.h> + +struct kunit_vm_mmap_resource { + unsigned long addr; + size_t size; +}; + +/* vm_mmap() arguments */ +struct kunit_vm_mmap_params { + struct file *file; + unsigned long addr; + unsigned long len; + unsigned long prot; + unsigned long flag; + unsigned long offset; +}; + +/* Create and attach a new mm if it doesn't already exist. */ +static int kunit_attach_mm(void) +{ + struct mm_struct *mm; + + if (current->mm) + return 0; + + /* arch_pick_mmap_layout() is only sane with MMU systems. */ + if (!IS_ENABLED(CONFIG_MMU)) + return -EINVAL; + + mm = mm_alloc(); + if (!mm) + return -ENOMEM; + + /* Define the task size. */ + mm->task_size = TASK_SIZE; + + /* Make sure we can allocate new VMAs. */ + arch_pick_mmap_layout(mm, ¤t->signal->rlim[RLIMIT_STACK]); + + /* Attach the mm. It will be cleaned up when the process dies. */ + kthread_use_mm(mm); + + return 0; +} + +static int kunit_vm_mmap_init(struct kunit_resource *res, void *context) +{ + struct kunit_vm_mmap_params *p = context; + struct kunit_vm_mmap_resource vres; + int ret; + + ret = kunit_attach_mm(); + if (ret) + return ret; + + vres.size = p->len; + vres.addr = vm_mmap(p->file, p->addr, p->len, p->prot, p->flag, p->offset); + if (!vres.addr) + return -ENOMEM; + res->data = kmemdup(&vres, sizeof(vres), GFP_KERNEL); + if (!res->data) { + vm_munmap(vres.addr, vres.size); + return -ENOMEM; + } + + return 0; +} + +static void kunit_vm_mmap_free(struct kunit_resource *res) +{ + struct kunit_vm_mmap_resource *vres = res->data; + + /* + * Since this is executed from the test monitoring process, + * the test's mm has already been torn down. We don't need + * to run vm_munmap(vres->addr, vres->size), only clean up + * the vres. + */ + + kfree(vres); + res->data = NULL; +} + +unsigned long kunit_vm_mmap(struct kunit *test, struct file *file, + unsigned long addr, unsigned long len, + unsigned long prot, unsigned long flag, + unsigned long offset) +{ + struct kunit_vm_mmap_params params = { + .file = file, + .addr = addr, + .len = len, + .prot = prot, + .flag = flag, + .offset = offset, + }; + struct kunit_vm_mmap_resource *vres; + + vres = kunit_alloc_resource(test, + kunit_vm_mmap_init, + kunit_vm_mmap_free, + GFP_KERNEL, + ¶ms); + if (vres) + return vres->addr; + return 0; +} +EXPORT_SYMBOL_GPL(kunit_vm_mmap); + +MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING"); diff --git a/lib/kunit_iov_iter.c b/lib/kunit_iov_iter.c index 27e0c8ee71d8..48342736d016 100644 --- a/lib/kunit_iov_iter.c +++ b/lib/kunit_iov_iter.c @@ -12,6 +12,7 @@ #include <linux/mm.h> #include <linux/uio.h> #include <linux/bvec.h> +#include <linux/folio_queue.h> #include <kunit/test.h> MODULE_DESCRIPTION("iov_iter testing"); @@ -56,7 +57,7 @@ static void *__init iov_kunit_create_buffer(struct kunit *test, KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pages); *ppages = pages; - got = alloc_pages_bulk_array(GFP_KERNEL, npages, pages); + got = alloc_pages_bulk(GFP_KERNEL, npages, pages); if (got != npages) { release_pages(pages, got); KUNIT_ASSERT_EQ(test, got, npages); @@ -362,6 +363,179 @@ stop: KUNIT_SUCCEED(test); } +static void iov_kunit_destroy_folioq(void *data) +{ + struct folio_queue *folioq, *next; + + for (folioq = data; folioq; folioq = next) { + next = folioq->next; + for (int i = 0; i < folioq_nr_slots(folioq); i++) + if (folioq_folio(folioq, i)) + folio_put(folioq_folio(folioq, i)); + kfree(folioq); + } +} + +static void __init iov_kunit_load_folioq(struct kunit *test, + struct iov_iter *iter, int dir, + struct folio_queue *folioq, + struct page **pages, size_t npages) +{ + struct folio_queue *p = folioq; + size_t size = 0; + int i; + + for (i = 0; i < npages; i++) { + if (folioq_full(p)) { + p->next = kzalloc(sizeof(struct folio_queue), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, p->next); + folioq_init(p->next, 0); + p->next->prev = p; + p = p->next; + } + folioq_append(p, page_folio(pages[i])); + size += PAGE_SIZE; + } + iov_iter_folio_queue(iter, dir, folioq, 0, 0, size); +} + +static struct folio_queue *iov_kunit_create_folioq(struct kunit *test) +{ + struct folio_queue *folioq; + + folioq = kzalloc(sizeof(struct folio_queue), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, folioq); + kunit_add_action_or_reset(test, iov_kunit_destroy_folioq, folioq); + folioq_init(folioq, 0); + return folioq; +} + +/* + * Test copying to a ITER_FOLIOQ-type iterator. + */ +static void __init iov_kunit_copy_to_folioq(struct kunit *test) +{ + const struct kvec_test_range *pr; + struct iov_iter iter; + struct folio_queue *folioq; + struct page **spages, **bpages; + u8 *scratch, *buffer; + size_t bufsize, npages, size, copied; + int i, patt; + + bufsize = 0x100000; + npages = bufsize / PAGE_SIZE; + + folioq = iov_kunit_create_folioq(test); + + scratch = iov_kunit_create_buffer(test, &spages, npages); + for (i = 0; i < bufsize; i++) + scratch[i] = pattern(i); + + buffer = iov_kunit_create_buffer(test, &bpages, npages); + memset(buffer, 0, bufsize); + + iov_kunit_load_folioq(test, &iter, READ, folioq, bpages, npages); + + i = 0; + for (pr = kvec_test_ranges; pr->from >= 0; pr++) { + size = pr->to - pr->from; + KUNIT_ASSERT_LE(test, pr->to, bufsize); + + iov_iter_folio_queue(&iter, READ, folioq, 0, 0, pr->to); + iov_iter_advance(&iter, pr->from); + copied = copy_to_iter(scratch + i, size, &iter); + + KUNIT_EXPECT_EQ(test, copied, size); + KUNIT_EXPECT_EQ(test, iter.count, 0); + KUNIT_EXPECT_EQ(test, iter.iov_offset, pr->to % PAGE_SIZE); + i += size; + if (test->status == KUNIT_FAILURE) + goto stop; + } + + /* Build the expected image in the scratch buffer. */ + patt = 0; + memset(scratch, 0, bufsize); + for (pr = kvec_test_ranges; pr->from >= 0; pr++) + for (i = pr->from; i < pr->to; i++) + scratch[i] = pattern(patt++); + + /* Compare the images */ + for (i = 0; i < bufsize; i++) { + KUNIT_EXPECT_EQ_MSG(test, buffer[i], scratch[i], "at i=%x", i); + if (buffer[i] != scratch[i]) + return; + } + +stop: + KUNIT_SUCCEED(test); +} + +/* + * Test copying from a ITER_FOLIOQ-type iterator. + */ +static void __init iov_kunit_copy_from_folioq(struct kunit *test) +{ + const struct kvec_test_range *pr; + struct iov_iter iter; + struct folio_queue *folioq; + struct page **spages, **bpages; + u8 *scratch, *buffer; + size_t bufsize, npages, size, copied; + int i, j; + + bufsize = 0x100000; + npages = bufsize / PAGE_SIZE; + + folioq = iov_kunit_create_folioq(test); + + buffer = iov_kunit_create_buffer(test, &bpages, npages); + for (i = 0; i < bufsize; i++) + buffer[i] = pattern(i); + + scratch = iov_kunit_create_buffer(test, &spages, npages); + memset(scratch, 0, bufsize); + + iov_kunit_load_folioq(test, &iter, READ, folioq, bpages, npages); + + i = 0; + for (pr = kvec_test_ranges; pr->from >= 0; pr++) { + size = pr->to - pr->from; + KUNIT_ASSERT_LE(test, pr->to, bufsize); + + iov_iter_folio_queue(&iter, WRITE, folioq, 0, 0, pr->to); + iov_iter_advance(&iter, pr->from); + copied = copy_from_iter(scratch + i, size, &iter); + + KUNIT_EXPECT_EQ(test, copied, size); + KUNIT_EXPECT_EQ(test, iter.count, 0); + KUNIT_EXPECT_EQ(test, iter.iov_offset, pr->to % PAGE_SIZE); + i += size; + } + + /* Build the expected image in the main buffer. */ + i = 0; + memset(buffer, 0, bufsize); + for (pr = kvec_test_ranges; pr->from >= 0; pr++) { + for (j = pr->from; j < pr->to; j++) { + buffer[i++] = pattern(j); + if (i >= bufsize) + goto stop; + } + } +stop: + + /* Compare the images */ + for (i = 0; i < bufsize; i++) { + KUNIT_EXPECT_EQ_MSG(test, scratch[i], buffer[i], "at i=%x", i); + if (scratch[i] != buffer[i]) + return; + } + + KUNIT_SUCCEED(test); +} + static void iov_kunit_destroy_xarray(void *data) { struct xarray *xarray = data; @@ -678,6 +852,85 @@ stop: } /* + * Test the extraction of ITER_FOLIOQ-type iterators. + */ +static void __init iov_kunit_extract_pages_folioq(struct kunit *test) +{ + const struct kvec_test_range *pr; + struct folio_queue *folioq; + struct iov_iter iter; + struct page **bpages, *pagelist[8], **pages = pagelist; + ssize_t len; + size_t bufsize, size = 0, npages; + int i, from; + + bufsize = 0x100000; + npages = bufsize / PAGE_SIZE; + + folioq = iov_kunit_create_folioq(test); + + iov_kunit_create_buffer(test, &bpages, npages); + iov_kunit_load_folioq(test, &iter, READ, folioq, bpages, npages); + + for (pr = kvec_test_ranges; pr->from >= 0; pr++) { + from = pr->from; + size = pr->to - from; + KUNIT_ASSERT_LE(test, pr->to, bufsize); + + iov_iter_folio_queue(&iter, WRITE, folioq, 0, 0, pr->to); + iov_iter_advance(&iter, from); + + do { + size_t offset0 = LONG_MAX; + + for (i = 0; i < ARRAY_SIZE(pagelist); i++) + pagelist[i] = (void *)(unsigned long)0xaa55aa55aa55aa55ULL; + + len = iov_iter_extract_pages(&iter, &pages, 100 * 1024, + ARRAY_SIZE(pagelist), 0, &offset0); + KUNIT_EXPECT_GE(test, len, 0); + if (len < 0) + break; + KUNIT_EXPECT_LE(test, len, size); + KUNIT_EXPECT_EQ(test, iter.count, size - len); + if (len == 0) + break; + size -= len; + KUNIT_EXPECT_GE(test, (ssize_t)offset0, 0); + KUNIT_EXPECT_LT(test, offset0, PAGE_SIZE); + + for (i = 0; i < ARRAY_SIZE(pagelist); i++) { + struct page *p; + ssize_t part = min_t(ssize_t, len, PAGE_SIZE - offset0); + int ix; + + KUNIT_ASSERT_GE(test, part, 0); + ix = from / PAGE_SIZE; + KUNIT_ASSERT_LT(test, ix, npages); + p = bpages[ix]; + KUNIT_EXPECT_PTR_EQ(test, pagelist[i], p); + KUNIT_EXPECT_EQ(test, offset0, from % PAGE_SIZE); + from += part; + len -= part; + KUNIT_ASSERT_GE(test, len, 0); + if (len == 0) + break; + offset0 = 0; + } + + if (test->status == KUNIT_FAILURE) + goto stop; + } while (iov_iter_count(&iter) > 0); + + KUNIT_EXPECT_EQ(test, size, 0); + KUNIT_EXPECT_EQ(test, iter.count, 0); + } + +stop: + KUNIT_SUCCEED(test); +} + +/* * Test the extraction of ITER_XARRAY-type iterators. */ static void __init iov_kunit_extract_pages_xarray(struct kunit *test) @@ -761,10 +1014,13 @@ static struct kunit_case __refdata iov_kunit_cases[] = { KUNIT_CASE(iov_kunit_copy_from_kvec), KUNIT_CASE(iov_kunit_copy_to_bvec), KUNIT_CASE(iov_kunit_copy_from_bvec), + KUNIT_CASE(iov_kunit_copy_to_folioq), + KUNIT_CASE(iov_kunit_copy_from_folioq), KUNIT_CASE(iov_kunit_copy_to_xarray), KUNIT_CASE(iov_kunit_copy_from_xarray), KUNIT_CASE(iov_kunit_extract_pages_kvec), KUNIT_CASE(iov_kunit_extract_pages_bvec), + KUNIT_CASE(iov_kunit_extract_pages_folioq), KUNIT_CASE(iov_kunit_extract_pages_xarray), {} }; diff --git a/lib/libcrc32c.c b/lib/libcrc32c.c deleted file mode 100644 index 649e687413a0..000000000000 --- a/lib/libcrc32c.c +++ /dev/null @@ -1,74 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * CRC32C - *@Article{castagnoli-crc, - * author = { Guy Castagnoli and Stefan Braeuer and Martin Herrman}, - * title = {{Optimization of Cyclic Redundancy-Check Codes with 24 - * and 32 Parity Bits}}, - * journal = IEEE Transactions on Communication, - * year = {1993}, - * volume = {41}, - * number = {6}, - * pages = {}, - * month = {June}, - *} - * Used by the iSCSI driver, possibly others, and derived from - * the iscsi-crc.c module of the linux-iscsi driver at - * http://linux-iscsi.sourceforge.net. - * - * Following the example of lib/crc32, this function is intended to be - * flexible and useful for all users. Modules that currently have their - * own crc32c, but hopefully may be able to use this one are: - * net/sctp (please add all your doco to here if you change to - * use this one!) - * <endoflist> - * - * Copyright (c) 2004 Cisco Systems, Inc. - */ - -#include <crypto/hash.h> -#include <linux/err.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/crc32c.h> - -static struct crypto_shash *tfm; - -u32 crc32c(u32 crc, const void *address, unsigned int length) -{ - SHASH_DESC_ON_STACK(shash, tfm); - u32 ret, *ctx = (u32 *)shash_desc_ctx(shash); - int err; - - shash->tfm = tfm; - *ctx = crc; - - err = crypto_shash_update(shash, address, length); - BUG_ON(err); - - ret = *ctx; - barrier_data(ctx); - return ret; -} - -EXPORT_SYMBOL(crc32c); - -static int __init libcrc32c_mod_init(void) -{ - tfm = crypto_alloc_shash("crc32c", 0, 0); - return PTR_ERR_OR_ZERO(tfm); -} - -static void __exit libcrc32c_mod_fini(void) -{ - crypto_free_shash(tfm); -} - -module_init(libcrc32c_mod_init); -module_exit(libcrc32c_mod_fini); - -MODULE_AUTHOR("Clay Haapala <chaapala@cisco.com>"); -MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations"); -MODULE_LICENSE("GPL"); -MODULE_SOFTDEP("pre: crc32c"); diff --git a/lib/list-test.c b/lib/list-test.c index 0cc27de9cec8..9135cdc1bb39 100644 --- a/lib/list-test.c +++ b/lib/list-test.c @@ -102,6 +102,8 @@ static void list_test_list_replace(struct kunit *test) /* now: [list] -> a_new -> b */ KUNIT_EXPECT_PTR_EQ(test, list.next, &a_new); KUNIT_EXPECT_PTR_EQ(test, b.prev, &a_new); + KUNIT_EXPECT_PTR_EQ(test, a_new.next, &b); + KUNIT_EXPECT_PTR_EQ(test, a_new.prev, &list); } static void list_test_list_replace_init(struct kunit *test) @@ -118,6 +120,8 @@ static void list_test_list_replace_init(struct kunit *test) /* now: [list] -> a_new -> b */ KUNIT_EXPECT_PTR_EQ(test, list.next, &a_new); KUNIT_EXPECT_PTR_EQ(test, b.prev, &a_new); + KUNIT_EXPECT_PTR_EQ(test, a_new.next, &b); + KUNIT_EXPECT_PTR_EQ(test, a_new.prev, &list); /* check a_old is empty (initialized) */ KUNIT_EXPECT_TRUE(test, list_empty_careful(&a_old)); @@ -408,6 +412,8 @@ static void list_test_list_cut_position(struct kunit *test) KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); i++; } + + KUNIT_EXPECT_EQ(test, i, 3); } static void list_test_list_cut_before(struct kunit *test) @@ -436,6 +442,8 @@ static void list_test_list_cut_before(struct kunit *test) KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); i++; } + + KUNIT_EXPECT_EQ(test, i, 3); } static void list_test_list_splice(struct kunit *test) @@ -1201,12 +1209,6 @@ static struct kunit_suite hlist_test_module = { }; -struct klist_test_struct { - int data; - struct klist klist; - struct klist_node klist_node; -}; - static int node_count; static struct klist_node *last_node; @@ -1499,4 +1501,5 @@ static struct kunit_suite klist_test_module = { kunit_test_suites(&list_test_module, &hlist_test_module, &klist_test_module); +MODULE_DESCRIPTION("KUnit test for the Kernel Linked-list structures"); MODULE_LICENSE("GPL v2"); diff --git a/lib/list_debug.c b/lib/list_debug.c index db602417febf..ee7eeeb8f92c 100644 --- a/lib/list_debug.c +++ b/lib/list_debug.c @@ -22,17 +22,17 @@ __list_valid_slowpath bool __list_add_valid_or_report(struct list_head *new, struct list_head *prev, struct list_head *next) { - if (CHECK_DATA_CORRUPTION(prev == NULL, + if (CHECK_DATA_CORRUPTION(prev == NULL, NULL, "list_add corruption. prev is NULL.\n") || - CHECK_DATA_CORRUPTION(next == NULL, + CHECK_DATA_CORRUPTION(next == NULL, NULL, "list_add corruption. next is NULL.\n") || - CHECK_DATA_CORRUPTION(next->prev != prev, + CHECK_DATA_CORRUPTION(next->prev != prev, next, "list_add corruption. next->prev should be prev (%px), but was %px. (next=%px).\n", prev, next->prev, next) || - CHECK_DATA_CORRUPTION(prev->next != next, + CHECK_DATA_CORRUPTION(prev->next != next, prev, "list_add corruption. prev->next should be next (%px), but was %px. (prev=%px).\n", next, prev->next, prev) || - CHECK_DATA_CORRUPTION(new == prev || new == next, + CHECK_DATA_CORRUPTION(new == prev || new == next, NULL, "list_add double add: new=%px, prev=%px, next=%px.\n", new, prev, next)) return false; @@ -49,20 +49,20 @@ bool __list_del_entry_valid_or_report(struct list_head *entry) prev = entry->prev; next = entry->next; - if (CHECK_DATA_CORRUPTION(next == NULL, + if (CHECK_DATA_CORRUPTION(next == NULL, NULL, "list_del corruption, %px->next is NULL\n", entry) || - CHECK_DATA_CORRUPTION(prev == NULL, + CHECK_DATA_CORRUPTION(prev == NULL, NULL, "list_del corruption, %px->prev is NULL\n", entry) || - CHECK_DATA_CORRUPTION(next == LIST_POISON1, + CHECK_DATA_CORRUPTION(next == LIST_POISON1, next, "list_del corruption, %px->next is LIST_POISON1 (%px)\n", entry, LIST_POISON1) || - CHECK_DATA_CORRUPTION(prev == LIST_POISON2, + CHECK_DATA_CORRUPTION(prev == LIST_POISON2, prev, "list_del corruption, %px->prev is LIST_POISON2 (%px)\n", entry, LIST_POISON2) || - CHECK_DATA_CORRUPTION(prev->next != entry, + CHECK_DATA_CORRUPTION(prev->next != entry, prev, "list_del corruption. prev->next should be %px, but was %px. (prev=%px)\n", entry, prev->next, prev) || - CHECK_DATA_CORRUPTION(next->prev != entry, + CHECK_DATA_CORRUPTION(next->prev != entry, next, "list_del corruption. next->prev should be %px, but was %px. (next=%px)\n", entry, next->prev, next)) return false; diff --git a/lib/list_sort.c b/lib/list_sort.c index 0fb59e92ca2d..a310ecb7ccc0 100644 --- a/lib/list_sort.c +++ b/lib/list_sort.c @@ -1,9 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/kernel.h> -#include <linux/bug.h> #include <linux/compiler.h> #include <linux/export.h> -#include <linux/string.h> #include <linux/list_sort.h> #include <linux/list.h> @@ -111,6 +108,13 @@ static void merge_final(void *priv, list_cmp_func_t cmp, struct list_head *head, * and list_sort is a stable sort, so it is not necessary to distinguish * the @a < @b and @a == @b cases. * + * The comparison function must adhere to specific mathematical properties + * to ensure correct and stable sorting: + * - Antisymmetry: cmp(@a, @b) must return the opposite sign of + * cmp(@b, @a). + * - Transitivity: if cmp(@a, @b) <= 0 and cmp(@b, @c) <= 0, then + * cmp(@a, @c) <= 0. + * * This is compatible with two styles of @cmp function: * - The traditional style which returns <0 / =0 / >0, or * - Returning a boolean 0/1. diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c index 6f6a5fc85b42..ed99344317f5 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -1720,8 +1720,6 @@ static void ww_test_normal(void) { int ret; - WWAI(&t); - /* * None of the ww_mutex codepaths should be taken in the 'normal' * mutex calls. The easiest way to verify this is by using the @@ -1770,6 +1768,8 @@ static void ww_test_normal(void) ww_mutex_base_unlock(&o.base); WARN_ON(o.ctx != (void *)~0UL); + WWAI(&t); + /* nest_lock */ o.ctx = (void *)~0UL; ww_mutex_base_lock_nest_lock(&o.base, &t); @@ -2710,6 +2710,43 @@ static void local_lock_3B(void) } +#ifdef CONFIG_DEBUG_LOCK_ALLOC +static inline const char *rw_semaphore_lockdep_name(struct rw_semaphore *rwsem) +{ + return rwsem->dep_map.name; +} +#else +static inline const char *rw_semaphore_lockdep_name(struct rw_semaphore *rwsem) +{ + return NULL; +} +#endif + +static void test_lockdep_set_subclass_name(void) +{ + const char *name_before = rw_semaphore_lockdep_name(&rwsem_X1); + const char *name_after; + + lockdep_set_subclass(&rwsem_X1, 1); + name_after = rw_semaphore_lockdep_name(&rwsem_X1); + DEBUG_LOCKS_WARN_ON(name_before != name_after); +} + +/* + * lockdep_set_subclass() should reuse the existing lock class name instead + * of creating a new one. + */ +static void lockdep_set_subclass_name_test(void) +{ + printk(" --------------------------------------------------------------------------\n"); + printk(" | lockdep_set_subclass() name test|\n"); + printk(" -----------------------------------\n"); + + print_testname("compare name before and after"); + dotest(test_lockdep_set_subclass_name, SUCCESS, LOCKTYPE_RWSEM); + pr_cont("\n"); +} + static void local_lock_tests(void) { printk(" --------------------------------------------------------------------------\n"); @@ -2920,6 +2957,8 @@ void locking_selftest(void) dotest(hardirq_deadlock_softirq_not_deadlock, FAILURE, LOCKTYPE_SPECIAL); pr_cont("\n"); + lockdep_set_subclass_name_test(); + if (unexpected_testcase_failures) { printk("-----------------------------------------------------------------\n"); debug_locks = 0; diff --git a/lib/lockref.c b/lib/lockref.c index 2afe4c5d8919..5d8e3ef3860e 100644 --- a/lib/lockref.c +++ b/lib/lockref.c @@ -58,23 +58,22 @@ EXPORT_SYMBOL(lockref_get); * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count was zero */ -int lockref_get_not_zero(struct lockref *lockref) +bool lockref_get_not_zero(struct lockref *lockref) { - int retval; + bool retval = false; CMPXCHG_LOOP( new.count++; if (old.count <= 0) - return 0; + return false; , - return 1; + return true; ); spin_lock(&lockref->lock); - retval = 0; if (lockref->count > 0) { lockref->count++; - retval = 1; + retval = true; } spin_unlock(&lockref->lock); return retval; @@ -82,39 +81,11 @@ int lockref_get_not_zero(struct lockref *lockref) EXPORT_SYMBOL(lockref_get_not_zero); /** - * lockref_put_not_zero - Decrements count unless count <= 1 before decrement - * @lockref: pointer to lockref structure - * Return: 1 if count updated successfully or 0 if count would become zero - */ -int lockref_put_not_zero(struct lockref *lockref) -{ - int retval; - - CMPXCHG_LOOP( - new.count--; - if (old.count <= 1) - return 0; - , - return 1; - ); - - spin_lock(&lockref->lock); - retval = 0; - if (lockref->count > 1) { - lockref->count--; - retval = 1; - } - spin_unlock(&lockref->lock); - return retval; -} -EXPORT_SYMBOL(lockref_put_not_zero); - -/** * lockref_put_return - Decrement reference count if possible * @lockref: pointer to lockref structure * * Decrement the reference count and return the new value. - * If the lockref was dead or locked, return an error. + * If the lockref was dead or locked, return -1. */ int lockref_put_return(struct lockref *lockref) { @@ -134,22 +105,22 @@ EXPORT_SYMBOL(lockref_put_return); * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count <= 1 and lock taken */ -int lockref_put_or_lock(struct lockref *lockref) +bool lockref_put_or_lock(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 1) break; , - return 1; + return true; ); spin_lock(&lockref->lock); if (lockref->count <= 1) - return 0; + return false; lockref->count--; spin_unlock(&lockref->lock); - return 1; + return true; } EXPORT_SYMBOL(lockref_put_or_lock); @@ -169,23 +140,22 @@ EXPORT_SYMBOL(lockref_mark_dead); * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if lockref was dead */ -int lockref_get_not_dead(struct lockref *lockref) +bool lockref_get_not_dead(struct lockref *lockref) { - int retval; + bool retval = false; CMPXCHG_LOOP( new.count++; if (old.count < 0) - return 0; + return false; , - return 1; + return true; ); spin_lock(&lockref->lock); - retval = 0; if (lockref->count >= 0) { lockref->count++; - retval = 1; + retval = true; } spin_unlock(&lockref->lock); return retval; diff --git a/lib/logic_pio.c b/lib/logic_pio.c index 2ea564a40064..e29496a38d06 100644 --- a/lib/logic_pio.c +++ b/lib/logic_pio.c @@ -122,7 +122,7 @@ void logic_pio_unregister_range(struct logic_pio_hwaddr *range) * * Traverse the io_range_list to find the registered node for @fwnode. */ -struct logic_pio_hwaddr *find_io_range_by_fwnode(struct fwnode_handle *fwnode) +struct logic_pio_hwaddr *find_io_range_by_fwnode(const struct fwnode_handle *fwnode) { struct logic_pio_hwaddr *range, *found_range = NULL; @@ -186,7 +186,7 @@ resource_size_t logic_pio_to_hwaddr(unsigned long pio) * * Returns Logical PIO value if successful, ~0UL otherwise */ -unsigned long logic_pio_trans_hwaddr(struct fwnode_handle *fwnode, +unsigned long logic_pio_trans_hwaddr(const struct fwnode_handle *fwnode, resource_size_t addr, resource_size_t size) { struct logic_pio_hwaddr *range; diff --git a/lib/lru_cache.c b/lib/lru_cache.c index b3d9187611de..9e0d469c7658 100644 --- a/lib/lru_cache.c +++ b/lib/lru_cache.c @@ -243,7 +243,7 @@ static struct lc_element *__lc_find(struct lru_cache *lc, unsigned int enr, BUG_ON(!lc); BUG_ON(!lc->nr_elements); - hlist_for_each_entry(e, lc_hash_slot(lc, enr), colision) { + hlist_for_each_entry(e, lc_hash_slot(lc, enr), collision) { /* "about to be changed" elements, pending transaction commit, * are hashed by their "new number". "Normal" elements have * lc_number == lc_new_number. */ @@ -303,7 +303,7 @@ void lc_del(struct lru_cache *lc, struct lc_element *e) BUG_ON(e->refcnt); e->lc_number = e->lc_new_number = LC_FREE; - hlist_del_init(&e->colision); + hlist_del_init(&e->collision); list_move(&e->list, &lc->free); RETURN(); } @@ -324,9 +324,9 @@ static struct lc_element *lc_prepare_for_change(struct lru_cache *lc, unsigned n PARANOIA_LC_ELEMENT(lc, e); e->lc_new_number = new_number; - if (!hlist_unhashed(&e->colision)) - __hlist_del(&e->colision); - hlist_add_head(&e->colision, lc_hash_slot(lc, new_number)); + if (!hlist_unhashed(&e->collision)) + __hlist_del(&e->collision); + hlist_add_head(&e->collision, lc_hash_slot(lc, new_number)); list_move(&e->list, &lc->to_be_changed); return e; diff --git a/lib/lz4/lz4_compress.c b/lib/lz4/lz4_compress.c index 90bb67994688..2a397bb2c661 100644 --- a/lib/lz4/lz4_compress.c +++ b/lib/lz4/lz4_compress.c @@ -33,11 +33,10 @@ /*-************************************ * Dependencies **************************************/ -#include <linux/lz4.h> #include "lz4defs.h" #include <linux/module.h> #include <linux/kernel.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> static const int LZ4_minLength = (MFLIMIT + 1); static const int LZ4_64Klimit = ((64 * KB) + (MFLIMIT - 1)); diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index 59fe69a63800..3a2cd9acada4 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -33,12 +33,11 @@ /*-************************************ * Dependencies **************************************/ -#include <linux/lz4.h> #include "lz4defs.h" #include <linux/init.h> #include <linux/module.h> #include <linux/kernel.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /*-***************************** * Decompression functions diff --git a/lib/lz4/lz4defs.h b/lib/lz4/lz4defs.h index 330aa539b46e..17277ec16919 100644 --- a/lib/lz4/lz4defs.h +++ b/lib/lz4/lz4defs.h @@ -35,10 +35,11 @@ * Sven Schmidt <4sschmid@informatik.uni-hamburg.de> */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/bitops.h> #include <linux/string.h> /* memset, memcpy */ +#include <linux/lz4.h> #define FORCE_INLINE __always_inline @@ -92,8 +93,7 @@ typedef uintptr_t uptrval; #define MB (1 << 20) #define GB (1U << 30) -#define MAXD_LOG 16 -#define MAX_DISTANCE ((1 << MAXD_LOG) - 1) +#define MAX_DISTANCE LZ4_DISTANCE_MAX #define STEPSIZE sizeof(size_t) #define ML_BITS 4 diff --git a/lib/lz4/lz4hc_compress.c b/lib/lz4/lz4hc_compress.c index e7ac8694b797..91936dc3d14b 100644 --- a/lib/lz4/lz4hc_compress.c +++ b/lib/lz4/lz4hc_compress.c @@ -34,7 +34,6 @@ /*-************************************ * Dependencies **************************************/ -#include <linux/lz4.h> #include "lz4defs.h" #include <linux/module.h> #include <linux/kernel.h> @@ -621,6 +620,7 @@ void LZ4_resetStreamHC(LZ4_streamHC_t *LZ4_streamHCPtr, int compressionLevel) LZ4_streamHCPtr->internal_donotuse.base = NULL; LZ4_streamHCPtr->internal_donotuse.compressionLevel = (unsigned int)compressionLevel; } +EXPORT_SYMBOL(LZ4_resetStreamHC); int LZ4_loadDictHC(LZ4_streamHC_t *LZ4_streamHCPtr, const char *dictionary, diff --git a/lib/lzo/lzo1x_compress.c b/lib/lzo/lzo1x_compress.c index 9d31e7126606..47d6d43ea957 100644 --- a/lib/lzo/lzo1x_compress.c +++ b/lib/lzo/lzo1x_compress.c @@ -14,7 +14,7 @@ #include <linux/module.h> #include <linux/kernel.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/lzo.h> #include "lzodefs.h" diff --git a/lib/lzo/lzo1x_decompress_safe.c b/lib/lzo/lzo1x_decompress_safe.c index 7892a40cf765..c94f4928e188 100644 --- a/lib/lzo/lzo1x_decompress_safe.c +++ b/lib/lzo/lzo1x_decompress_safe.c @@ -16,7 +16,7 @@ #include <linux/module.h> #include <linux/kernel.h> #endif -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/lzo.h> #include "lzodefs.h" diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 2d7d27e6ae3c..f7153ade1be5 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -64,6 +64,21 @@ #define CREATE_TRACE_POINTS #include <trace/events/maple_tree.h> +/* + * Kernel pointer hashing renders much of the maple tree dump useless as tagged + * pointers get hashed to arbitrary values. + * + * If CONFIG_DEBUG_VM_MAPLE_TREE is set we are in a debug mode where it is + * permissible to bypass this. Otherwise remain cautious and retain the hashing. + * + * Userland doesn't know about %px so also use %p there. + */ +#if defined(__KERNEL__) && defined(CONFIG_DEBUG_VM_MAPLE_TREE) +#define PTR_FMT "%px" +#else +#define PTR_FMT "%p" +#endif + #define MA_ROOT_PARENT 1 /* @@ -120,7 +135,6 @@ static const unsigned char mt_min_slots[] = { #define MAPLE_BIG_NODE_GAPS (MAPLE_ARANGE64_SLOTS * 2 + 1) struct maple_big_node { - struct maple_pnode *parent; unsigned long pivot[MAPLE_BIG_NODE_SLOTS - 1]; union { struct maple_enode *slot[MAPLE_BIG_NODE_SLOTS]; @@ -348,17 +362,17 @@ static inline void *mte_safe_root(const struct maple_enode *node) return (void *)((unsigned long)node & ~MAPLE_ROOT_NODE); } -static inline void *mte_set_full(const struct maple_enode *node) +static inline void __maybe_unused *mte_set_full(const struct maple_enode *node) { return (void *)((unsigned long)node & ~MAPLE_ENODE_NULL); } -static inline void *mte_clear_full(const struct maple_enode *node) +static inline void __maybe_unused *mte_clear_full(const struct maple_enode *node) { return (void *)((unsigned long)node | MAPLE_ENODE_NULL); } -static inline bool mte_has_null(const struct maple_enode *node) +static inline bool __maybe_unused mte_has_null(const struct maple_enode *node) { return (unsigned long)node & MAPLE_ENODE_NULL; } @@ -474,6 +488,7 @@ enum maple_type mas_parent_type(struct ma_state *mas, struct maple_enode *enode) /* * mas_set_parent() - Set the parent node and encode the slot + * @mas: The maple state * @enode: The encoded maple node. * @parent: The encoded maple node that is the parent of @enode. * @slot: The slot that @enode resides in @parent. @@ -534,7 +549,7 @@ unsigned int mte_parent_slot(const struct maple_enode *enode) /* * mte_parent() - Get the parent of @node. - * @node: The encoded maple node. + * @enode: The encoded maple node. * * Return: The parent maple node. */ @@ -641,8 +656,8 @@ static inline unsigned int mas_alloc_req(const struct ma_state *mas) /* * ma_pivots() - Get a pointer to the maple node pivots. - * @node - the maple node - * @type - the node type + * @node: the maple node + * @type: the node type * * In the event of a dead node, this array may be %NULL * @@ -665,8 +680,8 @@ static inline unsigned long *ma_pivots(struct maple_node *node, /* * ma_gaps() - Get a pointer to the maple node gaps. - * @node - the maple node - * @type - the node type + * @node: the maple node + * @type: the node type * * Return: A pointer to the maple node gaps */ @@ -880,8 +895,6 @@ static inline void ma_set_meta(struct maple_node *mn, enum maple_type mt, * @mt: The maple tree * @mn: The maple node * @type: The maple node type - * @offset: The offset of the highest sub-gap in this node. - * @end: The end of the data in this node. */ static inline void mt_clear_meta(struct maple_tree *mt, struct maple_node *mn, enum maple_type type) @@ -939,7 +952,7 @@ static inline unsigned char ma_meta_gap(struct maple_node *mn) /* * ma_set_meta_gap() - Set the largest gap location in a nodes metadata * @mn: The maple node - * @mn: The maple node type + * @mt: The maple node type * @offset: The location of the largest gap. */ static inline void ma_set_meta_gap(struct maple_node *mn, enum maple_type mt, @@ -953,8 +966,8 @@ static inline void ma_set_meta_gap(struct maple_node *mn, enum maple_type mt, /* * mat_add() - Add a @dead_enode to the ma_topiary of a list of dead nodes. - * @mat - the ma_topiary, a linked list of dead nodes. - * @dead_enode - the node to be marked as dead and added to the tail of the list + * @mat: the ma_topiary, a linked list of dead nodes. + * @dead_enode: the node to be marked as dead and added to the tail of the list * * Add the @dead_enode to the linked list in @mat. */ @@ -977,8 +990,8 @@ static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt, bool free); /* * mas_mat_destroy() - Free all nodes and subtrees in a dead list. - * @mas - the maple state - * @mat - the ma_topiary linked list of dead nodes to free. + * @mas: the maple state + * @mat: the ma_topiary linked list of dead nodes to free. * * Destroy walk a dead list. */ @@ -999,7 +1012,7 @@ static void mas_mat_destroy(struct ma_state *mas, struct ma_topiary *mat) } /* * mas_descend() - Descend into the slot stored in the ma_state. - * @mas - the maple state. + * @mas: the maple state. * * Note: Not RCU safe, only use in write side or debug code. */ @@ -1194,19 +1207,17 @@ static inline void mas_push_node(struct ma_state *mas, struct maple_node *used) reuse->request_count = 0; reuse->node_count = 0; - if (count && (head->node_count < MAPLE_ALLOC_SLOTS)) { - head->slot[head->node_count++] = reuse; - head->total++; - goto done; - } - - reuse->total = 1; - if ((head) && !((unsigned long)head & 0x1)) { + if (count) { + if (head->node_count < MAPLE_ALLOC_SLOTS) { + head->slot[head->node_count++] = reuse; + head->total++; + goto done; + } reuse->slot[0] = head; reuse->node_count = 1; - reuse->total += head->total; } + reuse->total = count + 1; mas->alloc = reuse; done: if (requested > 1) @@ -1252,11 +1263,11 @@ static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp) mas->alloc = node; node->total = ++allocated; + node->request_count = 0; requested--; } node = mas->alloc; - node->request_count = 0; while (requested) { max_req = MAPLE_ALLOC_SLOTS - node->node_count; slots = (void **)&node->slot[node->node_count]; @@ -1272,7 +1283,10 @@ static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp) node->node_count += count; allocated += count; - node = node->slot[0]; + /* find a non-full node*/ + do { + node = node->slot[0]; + } while (unlikely(node->node_count == MAPLE_ALLOC_SLOTS)); requested -= count; } mas->alloc->total = allocated; @@ -1281,10 +1295,9 @@ static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp) nomem_bulk: /* Clean up potential freed allocations on bulk failure */ memset(slots, 0, max_req * sizeof(unsigned long)); + mas->alloc->total = allocated; nomem_one: mas_set_alloc_req(mas, requested); - if (mas->alloc && !(((unsigned long)mas->alloc & 0x1))) - mas->alloc->total = allocated; mas_set_err(mas, -ENOMEM); } @@ -1346,8 +1359,8 @@ static void mas_node_count(struct ma_state *mas, int count) * Return: * - If mas->node is an error or not mas_start, return NULL. * - If it's an empty tree: NULL & mas->status == ma_none - * - If it's a single entry: The entry & mas->status == mas_root - * - If it's a tree: NULL & mas->status == safe root node. + * - If it's a single entry: The entry & mas->status == ma_root + * - If it's a tree: NULL & mas->status == ma_active */ static inline struct maple_enode *mas_start(struct ma_state *mas) { @@ -1372,9 +1385,9 @@ retry: return NULL; } + mas->node = NULL; /* empty tree */ if (unlikely(!root)) { - mas->node = NULL; mas->status = ma_none; mas->offset = MAPLE_NODE_SLOTS; return NULL; @@ -1462,7 +1475,7 @@ static inline unsigned char mas_data_end(struct ma_state *mas) /* * mas_leaf_max_gap() - Returns the largest gap in a leaf node - * @mas - the maple state + * @mas: the maple state * * Return: The maximum gap in the leaf. */ @@ -1544,7 +1557,7 @@ static unsigned long mas_leaf_max_gap(struct ma_state *mas) * @node: The maple node * @gaps: The pointer to the gaps * @mt: The maple node type - * @*off: Pointer to store the offset location of the gap. + * @off: Pointer to store the offset location of the gap. * * Uses the metadata data end to scan backwards across set gaps. * @@ -1651,7 +1664,7 @@ ascend: /* * mas_update_gap() - Update a nodes gaps and propagate up if necessary. - * @mas - the maple state. + * @mas: the maple state. */ static inline void mas_update_gap(struct ma_state *mas) { @@ -1678,8 +1691,8 @@ static inline void mas_update_gap(struct ma_state *mas) /* * mas_adopt_children() - Set the parent pointer of all nodes in @parent to * @parent with the slot encoded. - * @mas - the maple state (for the tree) - * @parent - the maple encoded node containing the children. + * @mas: the maple state (for the tree) + * @parent: the maple encoded node containing the children. */ static inline void mas_adopt_children(struct ma_state *mas, struct maple_enode *parent) @@ -1701,8 +1714,8 @@ static inline void mas_adopt_children(struct ma_state *mas, /* * mas_put_in_tree() - Put a new node in the tree, smp_wmb(), and mark the old * node as dead. - * @mas - the maple state with the new node - * @old_enode - The old maple encoded node to replace. + * @mas: the maple state with the new node + * @old_enode: The old maple encoded node to replace. */ static inline void mas_put_in_tree(struct ma_state *mas, struct maple_enode *old_enode) @@ -1730,8 +1743,8 @@ static inline void mas_put_in_tree(struct ma_state *mas, * mas_replace_node() - Replace a node by putting it in the tree, marking it * dead, and freeing it. * the parent encoding to locate the maple node in the tree. - * @mas - the ma_state with @mas->node pointing to the new node. - * @old_enode - The old maple encoded node. + * @mas: the ma_state with @mas->node pointing to the new node. + * @old_enode: The old maple encoded node. */ static inline void mas_replace_node(struct ma_state *mas, struct maple_enode *old_enode) @@ -1796,7 +1809,6 @@ static inline void mab_shift_right(struct maple_big_node *b_node, /* * mab_middle_node() - Check if a middle node is needed (unlikely) * @b_node: the maple_big_node that contains the data. - * @size: the amount of data in the b_node * @split: the potential split location * @slot_count: the size that can be stored in a single node being considered. * @@ -1844,17 +1856,18 @@ static inline int mab_no_null_split(struct maple_big_node *b_node, /* * mab_calc_split() - Calculate the split location and if there needs to be two * splits. + * @mas: The maple state * @bn: The maple_big_node with the data * @mid_split: The second split, if required. 0 otherwise. * * Return: The first split location. The middle split is set in @mid_split. */ static inline int mab_calc_split(struct ma_state *mas, - struct maple_big_node *bn, unsigned char *mid_split, unsigned long min) + struct maple_big_node *bn, unsigned char *mid_split) { unsigned char b_end = bn->b_end; int split = b_end / 2; /* Assume equal split. */ - unsigned char slot_min, slot_count = mt_slots[bn->type]; + unsigned char slot_count = mt_slots[bn->type]; /* * To support gap tracking, all NULL entries are kept together and a node cannot @@ -1887,18 +1900,7 @@ static inline int mab_calc_split(struct ma_state *mas, split = b_end / 3; *mid_split = split * 2; } else { - slot_min = mt_min_slots[bn->type]; - *mid_split = 0; - /* - * Avoid having a range less than the slot count unless it - * causes one node to be deficient. - * NOTE: mt_min_slots is 1 based, b_end and split are zero. - */ - while ((split < slot_count - 1) && - ((bn->pivot[split] - min) < slot_count - 1) && - (b_end - split > slot_min)) - split++; } /* Avoid ending a node on a NULL entry */ @@ -1944,14 +1946,13 @@ static inline void mas_mab_cp(struct ma_state *mas, unsigned char mas_start, for (; i < piv_end; i++, j++) { b_node->pivot[j] = pivots[i]; if (unlikely(!b_node->pivot[j])) - break; + goto complete; if (unlikely(mas->max == b_node->pivot[j])) goto complete; } - if (likely(i <= mas_end)) - b_node->pivot[j] = mas_safe_pivot(mas, pivots, i, mt); + b_node->pivot[j] = mas_safe_pivot(mas, pivots, i, mt); complete: b_node->b_end = ++j; @@ -2140,9 +2141,7 @@ static inline bool mas_prev_sibling(struct ma_state *mas) { unsigned int p_slot = mte_parent_slot(mas->node); - if (mte_is_root(mas->node)) - return false; - + /* For root node, p_slot is set to 0 by mte_parent_slot(). */ if (!p_slot) return false; @@ -2177,7 +2176,8 @@ static inline bool mas_next_sibling(struct ma_state *mas) } /* - * mte_node_or_none() - Set the enode and state. + * mas_node_or_none() - Set the enode and state. + * @mas: the maple state * @enode: The encoded maple node. * * Set the node to the enode and the status. @@ -2196,6 +2196,8 @@ static inline void mas_node_or_none(struct ma_state *mas, /* * mas_wr_node_walk() - Find the correct offset for the index in the @mas. + * If @mas->index cannot be found within the containing + * node, we traverse to the last entry in the node. * @wr_mas: The maple write state * * Uses mas_slot_locked() and does not need to worry about dead nodes. @@ -2228,7 +2230,6 @@ static inline void mas_wr_node_walk(struct ma_wr_state *wr_mas) /* * mast_rebalance_next() - Rebalance against the next node * @mast: The maple subtree state - * @old_r: The encoded maple node to the right (next node). */ static inline void mast_rebalance_next(struct maple_subtree_state *mast) { @@ -2242,7 +2243,6 @@ static inline void mast_rebalance_next(struct maple_subtree_state *mast) /* * mast_rebalance_prev() - Rebalance against the previous node * @mast: The maple subtree state - * @old_l: The encoded maple node to the left (previous node) */ static inline void mast_rebalance_prev(struct maple_subtree_state *mast) { @@ -2366,7 +2366,7 @@ static inline struct maple_enode static inline unsigned char mas_mab_to_node(struct ma_state *mas, struct maple_big_node *b_node, struct maple_enode **left, struct maple_enode **right, struct maple_enode **middle, - unsigned char *mid_split, unsigned long min) + unsigned char *mid_split) { unsigned char split = 0; unsigned char slot_count = mt_slots[b_node->type]; @@ -2379,7 +2379,7 @@ static inline unsigned char mas_mab_to_node(struct ma_state *mas, if (b_node->b_end < slot_count) { split = b_node->b_end; } else { - split = mab_calc_split(mas, b_node, mid_split, min); + split = mab_calc_split(mas, b_node, mid_split); *right = mas_new_ma_node(mas, b_node); } @@ -2393,9 +2393,9 @@ static inline unsigned char mas_mab_to_node(struct ma_state *mas, /* * mab_set_b_end() - Add entry to b_node at b_node->b_end and increment the end * pointer. - * @b_node - the big node to add the entry - * @mas - the maple state to get the pivot (mas->max) - * @entry - the entry to add, if NULL nothing happens. + * @b_node: the big node to add the entry + * @mas: the maple state to get the pivot (mas->max) + * @entry: the entry to add, if NULL nothing happens. */ static inline void mab_set_b_end(struct maple_big_node *b_node, struct ma_state *mas, @@ -2414,11 +2414,11 @@ static inline void mab_set_b_end(struct maple_big_node *b_node, * mas_set_split_parent() - combine_then_separate helper function. Sets the parent * of @mas->node to either @left or @right, depending on @slot and @split * - * @mas - the maple state with the node that needs a parent - * @left - possible parent 1 - * @right - possible parent 2 - * @slot - the slot the mas->node was placed - * @split - the split location between @left and @right + * @mas: the maple state with the node that needs a parent + * @left: possible parent 1 + * @right: possible parent 2 + * @slot: the slot the mas->node was placed + * @split: the split location between @left and @right */ static inline void mas_set_split_parent(struct ma_state *mas, struct maple_enode *left, @@ -2438,11 +2438,11 @@ static inline void mas_set_split_parent(struct ma_state *mas, /* * mte_mid_split_check() - Check if the next node passes the mid-split - * @**l: Pointer to left encoded maple node. - * @**m: Pointer to middle encoded maple node. - * @**r: Pointer to right encoded maple node. + * @l: Pointer to left encoded maple node. + * @m: Pointer to middle encoded maple node. + * @r: Pointer to right encoded maple node. * @slot: The offset - * @*split: The split location. + * @split: The split location. * @mid_split: The middle split. */ static inline void mte_mid_split_check(struct maple_enode **l, @@ -2466,10 +2466,10 @@ static inline void mte_mid_split_check(struct maple_enode **l, /* * mast_set_split_parents() - Helper function to set three nodes parents. Slot * is taken from @mast->l. - * @mast - the maple subtree state - * @left - the left node - * @right - the right node - * @split - the split location. + * @mast: the maple subtree state + * @left: the left node + * @right: the right node + * @split: the split location. */ static inline void mast_set_split_parents(struct maple_subtree_state *mast, struct maple_enode *left, @@ -2503,7 +2503,6 @@ static inline void mast_set_split_parents(struct maple_subtree_state *mast, /* * mas_topiary_node() - Dispose of a single node * @mas: The maple state for pushing nodes - * @enode: The encoded maple node * @in_rcu: If the tree is in rcu mode * * The node will either be RCU freed or pushed back on the maple state. @@ -2635,7 +2634,7 @@ static inline void mas_topiary_replace(struct ma_state *mas, /* * mas_wmb_replace() - Write memory barrier and replace * @mas: The maple state - * @old: The old maple encoded node that is being replaced. + * @old_enode: The old maple encoded node that is being replaced. * * Updates gap as necessary. */ @@ -2823,10 +2822,8 @@ dead_node: * orig_l_mas->last is used in mas_consume to find the slots that will need to * be either freed or destroyed. orig_l_mas->depth keeps track of the height of * the new sub-tree in case the sub-tree becomes the full tree. - * - * Return: the number of elements in b_node during the last loop. */ -static int mas_spanning_rebalance(struct ma_state *mas, +static void mas_spanning_rebalance(struct ma_state *mas, struct maple_subtree_state *mast, unsigned char count) { unsigned char split, mid_split; @@ -2869,7 +2866,7 @@ static int mas_spanning_rebalance(struct ma_state *mas, mast->bn->b_end--; mast->bn->type = mte_node_type(mast->orig_l->node); split = mas_mab_to_node(mas, mast->bn, &left, &right, &middle, - &mid_split, mast->orig_l->min); + &mid_split); mast_set_split_parents(mast, left, middle, right, split, mid_split); mast_cp_to_nodes(mast, left, middle, right, split, mid_split); @@ -2942,7 +2939,7 @@ new_root: mas->offset = l_mas.offset; mas_wmb_replace(mas, old_enode); mtree_range_walk(mas); - return mast->bn->b_end; + return; } /* @@ -2952,10 +2949,8 @@ new_root: * * Rebalance two nodes into a single node or two new nodes that are sufficient. * Continue upwards until tree is sufficient. - * - * Return: the number of elements in b_node during the last loop. */ -static inline int mas_rebalance(struct ma_state *mas, +static inline void mas_rebalance(struct ma_state *mas, struct maple_big_node *b_node) { char empty_count = mas_mt_height(mas); @@ -2976,9 +2971,6 @@ static inline int mas_rebalance(struct ma_state *mas, * tries to combine the data in the same way. If one node contains the * entire range of the tree, then that node is used as a new root node. */ - mas_node_count(mas, empty_count * 2 - 1); - if (mas_is_err(mas)) - return 0; mast.orig_l = &l_mas; mast.orig_r = &r_mas; @@ -3029,11 +3021,6 @@ static inline void mas_destroy_rebalance(struct ma_state *mas, unsigned char end /* set up node. */ if (in_rcu) { - /* Allocate for both left and right as well as parent. */ - mas_node_count(mas, 3); - if (mas_is_err(mas)) - return; - newnode = mas_pop_node(mas); } else { newnode = &reuse; @@ -3172,10 +3159,7 @@ static inline void mast_fill_bnode(struct maple_subtree_state *mast, bool cp = true; unsigned char split; - memset(mast->bn->gap, 0, sizeof(unsigned long) * ARRAY_SIZE(mast->bn->gap)); - memset(mast->bn->slot, 0, sizeof(unsigned long) * ARRAY_SIZE(mast->bn->slot)); - memset(mast->bn->pivot, 0, sizeof(unsigned long) * ARRAY_SIZE(mast->bn->pivot)); - mast->bn->b_end = 0; + memset(mast->bn, 0, sizeof(struct maple_big_node)); if (mte_is_root(mas->node)) { cp = false; @@ -3308,9 +3292,8 @@ static inline bool mas_push_data(struct ma_state *mas, int height, * mas_split() - Split data that is too big for one node into two. * @mas: The maple state * @b_node: The maple big node - * Return: 1 on success, 0 on failure. */ -static int mas_split(struct ma_state *mas, struct maple_big_node *b_node) +static void mas_split(struct ma_state *mas, struct maple_big_node *b_node) { struct maple_subtree_state mast; int height = 0; @@ -3341,10 +3324,6 @@ static int mas_split(struct ma_state *mas, struct maple_big_node *b_node) trace_ma_op(__func__, mas); mas->depth = mas_mt_height(mas); - /* Allocation failures will happen early. */ - mas_node_count(mas, 1 + mas->depth * 2); - if (mas_is_err(mas)) - return 0; mast.l = &l_mas; mast.r = &r_mas; @@ -3375,7 +3354,7 @@ static int mas_split(struct ma_state *mas, struct maple_big_node *b_node) if (mas_push_data(mas, height, &mast, false)) break; - split = mab_calc_split(mas, b_node, &mid_split, prev_l_mas.min); + split = mab_calc_split(mas, b_node, &mid_split); mast_split_data(&mast, mas, split); /* * Usually correct, mab_mas_cp in the above call overwrites @@ -3392,75 +3371,25 @@ static int mas_split(struct ma_state *mas, struct maple_big_node *b_node) mas->node = l_mas.node; mas_wmb_replace(mas, old); mtree_range_walk(mas); - return 1; -} - -/* - * mas_reuse_node() - Reuse the node to store the data. - * @wr_mas: The maple write state - * @bn: The maple big node - * @end: The end of the data. - * - * Will always return false in RCU mode. - * - * Return: True if node was reused, false otherwise. - */ -static inline bool mas_reuse_node(struct ma_wr_state *wr_mas, - struct maple_big_node *bn, unsigned char end) -{ - /* Need to be rcu safe. */ - if (mt_in_rcu(wr_mas->mas->tree)) - return false; - - if (end > bn->b_end) { - int clear = mt_slots[wr_mas->type] - bn->b_end; - - memset(wr_mas->slots + bn->b_end, 0, sizeof(void *) * clear--); - memset(wr_mas->pivots + bn->b_end, 0, sizeof(void *) * clear); - } - mab_mas_cp(bn, 0, bn->b_end, wr_mas->mas, false); - return true; + return; } /* * mas_commit_b_node() - Commit the big node into the tree. * @wr_mas: The maple write state * @b_node: The maple big node - * @end: The end of the data. */ -static noinline_for_kasan int mas_commit_b_node(struct ma_wr_state *wr_mas, - struct maple_big_node *b_node, unsigned char end) +static noinline_for_kasan void mas_commit_b_node(struct ma_wr_state *wr_mas, + struct maple_big_node *b_node) { - struct maple_node *node; - struct maple_enode *old_enode; - unsigned char b_end = b_node->b_end; - enum maple_type b_type = b_node->type; - - old_enode = wr_mas->mas->node; - if ((b_end < mt_min_slots[b_type]) && - (!mte_is_root(old_enode)) && - (mas_mt_height(wr_mas->mas) > 1)) - return mas_rebalance(wr_mas->mas, b_node); - - if (b_end >= mt_slots[b_type]) - return mas_split(wr_mas->mas, b_node); + enum store_type type = wr_mas->mas->store_type; - if (mas_reuse_node(wr_mas, b_node, end)) - goto reuse_node; + WARN_ON_ONCE(type != wr_rebalance && type != wr_split_store); - mas_node_count(wr_mas->mas, 1); - if (mas_is_err(wr_mas->mas)) - return 0; + if (type == wr_rebalance) + return mas_rebalance(wr_mas->mas, b_node); - node = mas_pop_node(wr_mas->mas); - node->parent = mas_mn(wr_mas->mas)->parent; - wr_mas->mas->node = mt_mk_node(node, b_type); - mab_mas_cp(b_node, 0, b_end, wr_mas->mas, false); - mas_replace_node(wr_mas->mas, old_enode); -reuse_node: - mas_update_gap(wr_mas->mas); - wr_mas->mas->end = b_end; - return 1; + return mas_split(wr_mas->mas, b_node); } /* @@ -3468,7 +3397,7 @@ reuse_node: * @mas: The maple state * @entry: The entry to store into the tree */ -static inline int mas_root_expand(struct ma_state *mas, void *entry) +static inline void mas_root_expand(struct ma_state *mas, void *entry) { void *contents = mas_root_locked(mas); enum maple_type type = maple_leaf_64; @@ -3477,10 +3406,6 @@ static inline int mas_root_expand(struct ma_state *mas, void *entry) unsigned long *pivots; int slot = 0; - mas_node_count(mas, 1); - if (unlikely(mas_is_err(mas))) - return 0; - node = mas_pop_node(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); @@ -3508,12 +3433,23 @@ static inline int mas_root_expand(struct ma_state *mas, void *entry) ma_set_meta(node, maple_leaf_64, 0, slot); /* swap the new root into the tree */ rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); - return slot; + return; } +/* + * mas_store_root() - Storing value into root. + * @mas: The maple state + * @entry: The entry to store. + * + * There is no root node now and we are storing a value into the root - this + * function either assigns the pointer or expands into a node. + */ static inline void mas_store_root(struct ma_state *mas, void *entry) { - if (likely((mas->last != 0) || (mas->index != 0))) + if (!entry) { + if (!mas->index) + rcu_assign_pointer(mas->tree->ma_root, NULL); + } else if (likely((mas->last != 0) || (mas->index != 0))) mas_root_expand(mas, entry); else if (((unsigned long) (entry) & 3) == 2) mas_root_expand(mas, entry); @@ -3526,10 +3462,7 @@ static inline void mas_store_root(struct ma_state *mas, void *entry) /* * mas_is_span_wr() - Check if the write needs to be treated as a write that * spans the node. - * @mas: The maple state - * @piv: The pivot value being written - * @type: The maple node type - * @entry: The data to write + * @wr_mas: The maple write state * * Spanning writes are writes that start in one node and end in another OR if * the write of a %NULL will cause the node to end with a %NULL. @@ -3609,7 +3542,7 @@ static bool mas_wr_walk(struct ma_wr_state *wr_mas) return true; } -static bool mas_wr_walk_index(struct ma_wr_state *wr_mas) +static void mas_wr_walk_index(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; @@ -3618,11 +3551,9 @@ static bool mas_wr_walk_index(struct ma_wr_state *wr_mas) wr_mas->content = mas_slot_locked(mas, wr_mas->slots, mas->offset); if (ma_is_leaf(wr_mas->type)) - return true; + return; mas_wr_walk_traverse(wr_mas); - } - return true; } /* * mas_extend_spanning_null() - Extend a store of a %NULL to include surrounding %NULLs. @@ -3730,10 +3661,8 @@ static void mte_destroy_walk(struct maple_enode *, struct maple_tree *); * @entry: The entry to store. * * Only valid when the index == 0 and the last == ULONG_MAX - * - * Return 0 on error, 1 on success. */ -static inline int mas_new_root(struct ma_state *mas, void *entry) +static inline void mas_new_root(struct ma_state *mas, void *entry) { struct maple_enode *root = mas_root_locked(mas); enum maple_type type = maple_leaf_64; @@ -3741,7 +3670,9 @@ static inline int mas_new_root(struct ma_state *mas, void *entry) void __rcu **slots; unsigned long *pivots; - if (!entry && !mas->index && mas->last == ULONG_MAX) { + WARN_ON_ONCE(mas->index || mas->last != ULONG_MAX); + + if (!entry) { mas->depth = 0; mas_set_height(mas); rcu_assign_pointer(mas->tree->ma_root, entry); @@ -3749,10 +3680,6 @@ static inline int mas_new_root(struct ma_state *mas, void *entry) goto done; } - mas_node_count(mas, 1); - if (mas_is_err(mas)) - return 0; - node = mas_pop_node(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); @@ -3769,7 +3696,7 @@ done: if (xa_is_node(root)) mte_destroy_walk(root, mas->tree); - return 1; + return; } /* * mas_wr_spanning_store() - Create a subtree with the store operation completed @@ -3777,10 +3704,8 @@ done: * Note that mas is expected to point to the node which caused the store to * span. * @wr_mas: The maple write state - * - * Return: 0 on error, positive on success. */ -static inline int mas_wr_spanning_store(struct ma_wr_state *wr_mas) +static noinline void mas_wr_spanning_store(struct ma_wr_state *wr_mas) { struct maple_subtree_state mast; struct maple_big_node b_node; @@ -3815,9 +3740,6 @@ static inline int mas_wr_spanning_store(struct ma_wr_state *wr_mas) * entries per level plus a new root. */ height = mas_mt_height(mas); - mas_node_count(mas, 1 + height * 3); - if (mas_is_err(mas)) - return 0; /* * Set up right side. Need to get to the next offset after the spanning @@ -3853,8 +3775,8 @@ static inline int mas_wr_spanning_store(struct ma_wr_state *wr_mas) memset(&b_node, 0, sizeof(struct maple_big_node)); /* Copy l_mas and store the value in b_node. */ mas_store_b_node(&l_wr_mas, &b_node, l_mas.end); - /* Copy r_mas into b_node. */ - if (r_mas.offset <= r_mas.end) + /* Copy r_mas into b_node if there is anything to copy. */ + if (r_mas.max > r_mas.last) mas_mab_cp(&r_mas, r_mas.offset, r_mas.end, &b_node, b_node.b_end + 1); else @@ -3875,10 +3797,8 @@ static inline int mas_wr_spanning_store(struct ma_wr_state *wr_mas) * @wr_mas: The maple write state * * Attempts to reuse the node, but may allocate. - * - * Return: True if stored, false otherwise */ -static inline bool mas_wr_node_store(struct ma_wr_state *wr_mas, +static inline void mas_wr_node_store(struct ma_wr_state *wr_mas, unsigned char new_end) { struct ma_state *mas = wr_mas->mas; @@ -3889,11 +3809,6 @@ static inline bool mas_wr_node_store(struct ma_wr_state *wr_mas, unsigned char copy_size, node_pivots = mt_pivots[wr_mas->type]; bool in_rcu = mt_in_rcu(mas->tree); - /* Check if there is enough data. The room is enough. */ - if (!mte_is_root(mas->node) && (new_end <= mt_min_slots[wr_mas->type]) && - !(mas->mas_flags & MA_STATE_BULK)) - return false; - if (mas->last == wr_mas->end_piv) offset_end++; /* don't copy this offset */ else if (unlikely(wr_mas->r_max == ULONG_MAX)) @@ -3901,10 +3816,6 @@ static inline bool mas_wr_node_store(struct ma_wr_state *wr_mas, /* set up node. */ if (in_rcu) { - mas_node_count(mas, 1); - if (mas_is_err(mas)) - return false; - newnode = mas_pop_node(mas); } else { memset(&reuse, 0, sizeof(struct maple_node)); @@ -3960,16 +3871,14 @@ done: trace_ma_write(__func__, mas, 0, wr_mas->entry); mas_update_gap(mas); mas->end = new_end; - return true; + return; } /* * mas_wr_slot_store: Attempt to store a value in a slot. * @wr_mas: the maple write state - * - * Return: True if stored, false otherwise */ -static inline bool mas_wr_slot_store(struct ma_wr_state *wr_mas) +static inline void mas_wr_slot_store(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char offset = mas->offset; @@ -3990,7 +3899,8 @@ static inline bool mas_wr_slot_store(struct ma_wr_state *wr_mas) wr_mas->pivots[offset] = mas->index - 1; mas->offset++; /* Keep mas accurate. */ } - } else if (!mt_in_rcu(mas->tree)) { + } else { + WARN_ON_ONCE(mt_in_rcu(mas->tree)); /* * Expand the range, only partially overwriting the previous and * next ranges @@ -4000,8 +3910,6 @@ static inline bool mas_wr_slot_store(struct ma_wr_state *wr_mas) wr_mas->pivots[offset] = mas->index - 1; wr_mas->pivots[offset + 1] = mas->last; mas->offset++; /* Keep mas accurate. */ - } else { - return false; } trace_ma_write(__func__, mas, 0, wr_mas->entry); @@ -4012,7 +3920,7 @@ static inline bool mas_wr_slot_store(struct ma_wr_state *wr_mas) if (!wr_mas->entry || gap) mas_update_gap(mas); - return true; + return; } static inline void mas_wr_extend_null(struct ma_wr_state *wr_mas) @@ -4061,9 +3969,6 @@ static inline void mas_wr_end_piv(struct ma_wr_state *wr_mas) wr_mas->end_piv = wr_mas->pivots[wr_mas->offset_end]; else wr_mas->end_piv = wr_mas->mas->max; - - if (!wr_mas->entry) - mas_wr_extend_null(wr_mas); } static inline unsigned char mas_wr_new_end(struct ma_wr_state *wr_mas) @@ -4089,23 +3994,13 @@ static inline unsigned char mas_wr_new_end(struct ma_wr_state *wr_mas) * This is currently unsafe in rcu mode since the end of the node may be cached * by readers while the node contents may be updated which could result in * inaccurate information. - * - * Return: True if appended, false otherwise */ -static inline bool mas_wr_append(struct ma_wr_state *wr_mas, +static inline void mas_wr_append(struct ma_wr_state *wr_mas, unsigned char new_end) { - struct ma_state *mas; + struct ma_state *mas = wr_mas->mas; void __rcu **slots; - unsigned char end; - - mas = wr_mas->mas; - if (mt_in_rcu(mas->tree)) - return false; - - end = mas->end; - if (mas->offset != end) - return false; + unsigned char end = mas->end; if (new_end < mt_pivots[wr_mas->type]) { wr_mas->pivots[new_end] = wr_mas->pivots[end]; @@ -4139,7 +4034,7 @@ static inline bool mas_wr_append(struct ma_wr_state *wr_mas, mas->end = new_end; trace_ma_write(__func__, mas, new_end, wr_mas->entry); - return true; + return; } /* @@ -4155,79 +4050,213 @@ static void mas_wr_bnode(struct ma_wr_state *wr_mas) trace_ma_write(__func__, wr_mas->mas, 0, wr_mas->entry); memset(&b_node, 0, sizeof(struct maple_big_node)); mas_store_b_node(wr_mas, &b_node, wr_mas->offset_end); - mas_commit_b_node(wr_mas, &b_node, wr_mas->mas->end); + mas_commit_b_node(wr_mas, &b_node); } -static inline void mas_wr_modify(struct ma_wr_state *wr_mas) +/* + * mas_wr_store_entry() - Internal call to store a value + * @wr_mas: The maple write state + */ +static inline void mas_wr_store_entry(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; - unsigned char new_end; + unsigned char new_end = mas_wr_new_end(wr_mas); - /* Direct replacement */ - if (wr_mas->r_min == mas->index && wr_mas->r_max == mas->last) { + switch (mas->store_type) { + case wr_invalid: + MT_BUG_ON(mas->tree, 1); + return; + case wr_new_root: + mas_new_root(mas, wr_mas->entry); + break; + case wr_store_root: + mas_store_root(mas, wr_mas->entry); + break; + case wr_exact_fit: rcu_assign_pointer(wr_mas->slots[mas->offset], wr_mas->entry); if (!!wr_mas->entry ^ !!wr_mas->content) mas_update_gap(mas); - return; + break; + case wr_append: + mas_wr_append(wr_mas, new_end); + break; + case wr_slot_store: + mas_wr_slot_store(wr_mas); + break; + case wr_node_store: + mas_wr_node_store(wr_mas, new_end); + break; + case wr_spanning_store: + mas_wr_spanning_store(wr_mas); + break; + case wr_split_store: + case wr_rebalance: + mas_wr_bnode(wr_mas); + break; + } + + return; +} + +static inline void mas_wr_prealloc_setup(struct ma_wr_state *wr_mas) +{ + struct ma_state *mas = wr_mas->mas; + + if (!mas_is_active(mas)) { + if (mas_is_start(mas)) + goto set_content; + + if (unlikely(mas_is_paused(mas))) + goto reset; + + if (unlikely(mas_is_none(mas))) + goto reset; + + if (unlikely(mas_is_overflow(mas))) + goto reset; + + if (unlikely(mas_is_underflow(mas))) + goto reset; } /* - * new_end exceeds the size of the maple node and cannot enter the fast - * path. + * A less strict version of mas_is_span_wr() where we allow spanning + * writes within this node. This is to stop partial walks in + * mas_prealloc() from being reset. */ - new_end = mas_wr_new_end(wr_mas); - if (new_end >= mt_slots[wr_mas->type]) - goto slow_path; + if (mas->last > mas->max) + goto reset; - /* Attempt to append */ - if (mas_wr_append(wr_mas, new_end)) - return; + if (wr_mas->entry) + goto set_content; - if (new_end == mas->end && mas_wr_slot_store(wr_mas)) - return; + if (mte_is_leaf(mas->node) && mas->last == mas->max) + goto reset; - if (mas_wr_node_store(wr_mas, new_end)) - return; + goto set_content; - if (mas_is_err(mas)) - return; +reset: + mas_reset(mas); +set_content: + wr_mas->content = mas_start(mas); +} -slow_path: - mas_wr_bnode(wr_mas); +/** + * mas_prealloc_calc() - Calculate number of nodes needed for a + * given store oepration + * @mas: The maple state + * @entry: The entry to store into the tree + * + * Return: Number of nodes required for preallocation. + */ +static inline int mas_prealloc_calc(struct ma_state *mas, void *entry) +{ + int ret = mas_mt_height(mas) * 3 + 1; + + switch (mas->store_type) { + case wr_invalid: + WARN_ON_ONCE(1); + break; + case wr_new_root: + ret = 1; + break; + case wr_store_root: + if (likely((mas->last != 0) || (mas->index != 0))) + ret = 1; + else if (((unsigned long) (entry) & 3) == 2) + ret = 1; + else + ret = 0; + break; + case wr_spanning_store: + ret = mas_mt_height(mas) * 3 + 1; + break; + case wr_split_store: + ret = mas_mt_height(mas) * 2 + 1; + break; + case wr_rebalance: + ret = mas_mt_height(mas) * 2 - 1; + break; + case wr_node_store: + ret = mt_in_rcu(mas->tree) ? 1 : 0; + break; + case wr_append: + case wr_exact_fit: + case wr_slot_store: + ret = 0; + } + + return ret; } /* - * mas_wr_store_entry() - Internal call to store a value - * @mas: The maple state - * @entry: The entry to store. + * mas_wr_store_type() - Determine the store type for a given + * store operation. + * @wr_mas: The maple write state * - * Return: The contents that was stored at the index. + * Return: the type of store needed for the operation */ -static inline void *mas_wr_store_entry(struct ma_wr_state *wr_mas) +static inline enum store_type mas_wr_store_type(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; + unsigned char new_end; - wr_mas->content = mas_start(mas); - if (mas_is_none(mas) || mas_is_ptr(mas)) { - mas_store_root(mas, wr_mas->entry); - return wr_mas->content; - } + if (unlikely(mas_is_none(mas) || mas_is_ptr(mas))) + return wr_store_root; - if (unlikely(!mas_wr_walk(wr_mas))) { - mas_wr_spanning_store(wr_mas); - return wr_mas->content; - } + if (unlikely(!mas_wr_walk(wr_mas))) + return wr_spanning_store; /* At this point, we are at the leaf node that needs to be altered. */ mas_wr_end_piv(wr_mas); - /* New root for a single pointer */ - if (unlikely(!mas->index && mas->last == ULONG_MAX)) { - mas_new_root(mas, wr_mas->entry); - return wr_mas->content; + if (!wr_mas->entry) + mas_wr_extend_null(wr_mas); + + if ((wr_mas->r_min == mas->index) && (wr_mas->r_max == mas->last)) + return wr_exact_fit; + + if (unlikely(!mas->index && mas->last == ULONG_MAX)) + return wr_new_root; + + new_end = mas_wr_new_end(wr_mas); + /* Potential spanning rebalance collapsing a node */ + if (new_end < mt_min_slots[wr_mas->type]) { + if (!mte_is_root(mas->node) && !(mas->mas_flags & MA_STATE_BULK)) + return wr_rebalance; + return wr_node_store; } - mas_wr_modify(wr_mas); - return wr_mas->content; + if (new_end >= mt_slots[wr_mas->type]) + return wr_split_store; + + if (!mt_in_rcu(mas->tree) && (mas->offset == mas->end)) + return wr_append; + + if ((new_end == mas->end) && (!mt_in_rcu(mas->tree) || + (wr_mas->offset_end - mas->offset == 1))) + return wr_slot_store; + + return wr_node_store; +} + +/** + * mas_wr_preallocate() - Preallocate enough nodes for a store operation + * @wr_mas: The maple write state + * @entry: The entry that will be stored + * + */ +static inline void mas_wr_preallocate(struct ma_wr_state *wr_mas, void *entry) +{ + struct ma_state *mas = wr_mas->mas; + int request; + + mas_wr_prealloc_setup(wr_mas); + mas->store_type = mas_wr_store_type(wr_mas); + request = mas_prealloc_calc(mas, entry); + if (!request) + return; + + mas_node_count(mas, request); } /** @@ -4260,26 +4289,24 @@ static inline void *mas_insert(struct ma_state *mas, void *entry) if (wr_mas.content) goto exists; - if (mas_is_none(mas) || mas_is_ptr(mas)) { - mas_store_root(mas, entry); + mas_wr_preallocate(&wr_mas, entry); + if (mas_is_err(mas)) return NULL; - } /* spanning writes always overwrite something */ - if (!mas_wr_walk(&wr_mas)) + if (mas->store_type == wr_spanning_store) goto exists; /* At this point, we are at the leaf node that needs to be altered. */ - wr_mas.offset_end = mas->offset; - wr_mas.end_piv = wr_mas.r_max; - - if (wr_mas.content || (mas->last > wr_mas.r_max)) - goto exists; + if (mas->store_type != wr_new_root && mas->store_type != wr_store_root) { + wr_mas.offset_end = mas->offset; + wr_mas.end_piv = wr_mas.r_max; - if (!entry) - return NULL; + if (wr_mas.content || (mas->last > wr_mas.r_max)) + goto exists; + } - mas_wr_modify(&wr_mas); + mas_wr_store_entry(&wr_mas); return wr_mas.content; exists: @@ -4316,6 +4343,7 @@ int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, ret = 1; } if (ret < 0 && range_lo > min) { + mas_reset(mas); ret = mas_empty_area(mas, min, range_hi, 1); if (ret == 0) ret = 1; @@ -4334,6 +4362,7 @@ int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, if (*next == 0) mas->tree->ma_flags |= MT_FLAGS_ALLOC_WRAPPED; + mas_destroy(mas); return ret; } EXPORT_SYMBOL(mas_alloc_cyclic); @@ -4443,9 +4472,8 @@ no_entry: * mas_prev_slot() - Get the entry in the previous slot * * @mas: The maple state - * @max: The minimum starting range + * @min: The minimum starting range * @empty: Can be empty - * @set_underflow: Set the @mas->node to underflow state on limit. * * Return: The entry in the previous slot which is possibly NULL */ @@ -4528,6 +4556,7 @@ underflow: /* * mas_next_node() - Get the next node at the same level in the tree. * @mas: The maple state + * @node: The maple node * @max: The maximum pivot value to check. * * The next value will be mas->node[mas->offset] or the status will have @@ -4618,8 +4647,6 @@ overflow: * @mas: The maple state * @max: The maximum starting range * @empty: Can be empty - * @set_overflow: Should @mas->node be set to overflow when the limit is - * reached. * * Return: The entry in the next slot which is possibly NULL */ @@ -4708,29 +4735,6 @@ again: } /* - * mas_next_entry() - Internal function to get the next entry. - * @mas: The maple state - * @limit: The maximum range start. - * - * Set the @mas->node to the next entry and the range_start to - * the beginning value for the entry. Does not check beyond @limit. - * Sets @mas->index and @mas->last to the range, Does not update @mas->index and - * @mas->last on overflow. - * Restarts on dead nodes. - * - * Return: the next entry or %NULL. - */ -static inline void *mas_next_entry(struct ma_state *mas, unsigned long limit) -{ - if (mas->last >= limit) { - mas->status = ma_overflow; - return NULL; - } - - return mas_next_slot(mas, limit, false); -} - -/* * mas_rev_awalk() - Internal function. Reverse allocation walk. Find the * highest gap address of a given size in a given node and descend. * @mas: The maple state @@ -4865,15 +4869,14 @@ static inline bool mas_anode_descend(struct ma_state *mas, unsigned long size) if (gap >= size) { if (ma_is_leaf(type)) { found = true; - goto done; - } - if (mas->index <= pivot) { - mas->node = mas_slot(mas, slots, offset); - mas->min = min; - mas->max = pivot; - offset = 0; break; } + + mas->node = mas_slot(mas, slots, offset); + mas->min = min; + mas->max = pivot; + offset = 0; + break; } next_slot: min = pivot + 1; @@ -4883,9 +4886,6 @@ next_slot: } } - if (mte_is_root(mas->node)) - found = true; -done: mas->offset = offset; return found; } @@ -4989,8 +4989,8 @@ static inline void mas_awalk(struct ma_state *mas, unsigned long size) * There are 4 options: * go to child (descend) * go back to parent (ascend) - * no gap found. (return, slot == MAPLE_NODE_SLOTS) - * found the gap. (return, slot != MAPLE_NODE_SLOTS) + * no gap found. (return, error == -EBUSY) + * found the gap. (return) */ while (!mas_is_err(mas) && !mas_anode_descend(mas, size)) { if (last == mas->node) @@ -5075,9 +5075,6 @@ int mas_empty_area(struct ma_state *mas, unsigned long min, return xa_err(mas->node); offset = mas->offset; - if (unlikely(offset == MAPLE_NODE_SLOTS)) - return -EBUSY; - node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); @@ -5153,9 +5150,9 @@ EXPORT_SYMBOL_GPL(mas_empty_area_rev); /* * mte_dead_leaves() - Mark all leaves of a node as dead. - * @mas: The maple state + * @enode: the encoded node + * @mt: the maple tree * @slots: Pointer to the slot array - * @type: The maple node type * * Must hold the write lock. * @@ -5361,47 +5358,6 @@ static inline void mte_destroy_walk(struct maple_enode *enode, mt_destroy_walk(enode, mt, true); } } - -static void mas_wr_store_setup(struct ma_wr_state *wr_mas) -{ - if (!mas_is_active(wr_mas->mas)) { - if (mas_is_start(wr_mas->mas)) - return; - - if (unlikely(mas_is_paused(wr_mas->mas))) - goto reset; - - if (unlikely(mas_is_none(wr_mas->mas))) - goto reset; - - if (unlikely(mas_is_overflow(wr_mas->mas))) - goto reset; - - if (unlikely(mas_is_underflow(wr_mas->mas))) - goto reset; - } - - /* - * A less strict version of mas_is_span_wr() where we allow spanning - * writes within this node. This is to stop partial walks in - * mas_prealloc() from being reset. - */ - if (wr_mas->mas->last > wr_mas->mas->max) - goto reset; - - if (wr_mas->entry) - return; - - if (mte_is_leaf(wr_mas->mas->node) && - wr_mas->mas->last == wr_mas->mas->max) - goto reset; - - return; - -reset: - mas_reset(wr_mas->mas); -} - /* Interface */ /** @@ -5410,19 +5366,19 @@ reset: * @entry: The entry to store. * * The @mas->index and @mas->last is used to set the range for the @entry. - * Note: The @mas should have pre-allocated entries to ensure there is memory to - * store the entry. Please see mas_expected_entries()/mas_destroy() for more details. * * Return: the first entry between mas->index and mas->last or %NULL. */ void *mas_store(struct ma_state *mas, void *entry) { + int request; MA_WR_STATE(wr_mas, mas, entry); trace_ma_write(__func__, mas, 0, entry); #ifdef CONFIG_DEBUG_MAPLE_TREE if (MAS_WARN_ON(mas, mas->index > mas->last)) - pr_err("Error %lX > %lX %p\n", mas->index, mas->last, entry); + pr_err("Error %lX > %lX " PTR_FMT "\n", mas->index, mas->last, + entry); if (mas->index > mas->last) { mas_set_err(mas, -EINVAL); @@ -5437,8 +5393,25 @@ void *mas_store(struct ma_state *mas, void *entry) * want to examine what happens if a single store operation was to * overwrite multiple entries within a self-balancing B-Tree. */ - mas_wr_store_setup(&wr_mas); + mas_wr_prealloc_setup(&wr_mas); + mas->store_type = mas_wr_store_type(&wr_mas); + if (mas->mas_flags & MA_STATE_PREALLOC) { + mas_wr_store_entry(&wr_mas); + MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas)); + return wr_mas.content; + } + + request = mas_prealloc_calc(mas, entry); + if (!request) + goto store; + + mas_node_count(mas, request); + if (mas_is_err(mas)) + return NULL; + +store: mas_wr_store_entry(&wr_mas); + mas_destroy(mas); return wr_mas.content; } EXPORT_SYMBOL_GPL(mas_store); @@ -5454,19 +5427,28 @@ EXPORT_SYMBOL_GPL(mas_store); */ int mas_store_gfp(struct ma_state *mas, void *entry, gfp_t gfp) { + unsigned long index = mas->index; + unsigned long last = mas->last; MA_WR_STATE(wr_mas, mas, entry); + int ret = 0; - mas_wr_store_setup(&wr_mas); - trace_ma_write(__func__, mas, 0, entry); retry: - mas_wr_store_entry(&wr_mas); - if (unlikely(mas_nomem(mas, gfp))) + mas_wr_preallocate(&wr_mas, entry); + if (unlikely(mas_nomem(mas, gfp))) { + if (!entry) + __mas_set_range(mas, index, last); goto retry; + } - if (unlikely(mas_is_err(mas))) - return xa_err(mas->node); + if (mas_is_err(mas)) { + ret = xa_err(mas->node); + goto out; + } - return 0; + mas_wr_store_entry(&wr_mas); +out: + mas_destroy(mas); + return ret; } EXPORT_SYMBOL_GPL(mas_store_gfp); @@ -5480,7 +5462,19 @@ void mas_store_prealloc(struct ma_state *mas, void *entry) { MA_WR_STATE(wr_mas, mas, entry); - mas_wr_store_setup(&wr_mas); + if (mas->store_type == wr_store_root) { + mas_wr_prealloc_setup(&wr_mas); + goto store; + } + + mas_wr_walk_descend(&wr_mas); + if (mas->store_type != wr_spanning_store) { + /* set wr_mas->content to current slot */ + wr_mas.content = mas_slot_locked(mas, wr_mas.slots, mas->offset); + mas_wr_end_piv(&wr_mas); + } + +store: trace_ma_write(__func__, mas, 0, entry); mas_wr_store_entry(&wr_mas); MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas)); @@ -5499,70 +5493,25 @@ EXPORT_SYMBOL_GPL(mas_store_prealloc); int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp) { MA_WR_STATE(wr_mas, mas, entry); - unsigned char node_size; - int request = 1; - int ret; - - - if (unlikely(!mas->index && mas->last == ULONG_MAX)) - goto ask_now; - - mas_wr_store_setup(&wr_mas); - wr_mas.content = mas_start(mas); - /* Root expand */ - if (unlikely(mas_is_none(mas) || mas_is_ptr(mas))) - goto ask_now; - - if (unlikely(!mas_wr_walk(&wr_mas))) { - /* Spanning store, use worst case for now */ - request = 1 + mas_mt_height(mas) * 3; - goto ask_now; - } - - /* At this point, we are at the leaf node that needs to be altered. */ - /* Exact fit, no nodes needed. */ - if (wr_mas.r_min == mas->index && wr_mas.r_max == mas->last) - return 0; - - mas_wr_end_piv(&wr_mas); - node_size = mas_wr_new_end(&wr_mas); + int ret = 0; + int request; - /* Slot store, does not require additional nodes */ - if (node_size == mas->end) { - /* reuse node */ - if (!mt_in_rcu(mas->tree)) - return 0; - /* shifting boundary */ - if (wr_mas.offset_end - mas->offset == 1) - return 0; - } + mas_wr_prealloc_setup(&wr_mas); + mas->store_type = mas_wr_store_type(&wr_mas); + request = mas_prealloc_calc(mas, entry); + if (!request) + return ret; - if (node_size >= mt_slots[wr_mas.type]) { - /* Split, worst case for now. */ - request = 1 + mas_mt_height(mas) * 2; - goto ask_now; + mas_node_count_gfp(mas, request, gfp); + if (mas_is_err(mas)) { + mas_set_alloc_req(mas, 0); + ret = xa_err(mas->node); + mas_destroy(mas); + mas_reset(mas); + return ret; } - /* New root needs a single node */ - if (unlikely(mte_is_root(mas->node))) - goto ask_now; - - /* Potential spanning rebalance collapsing a node, use worst-case */ - if (node_size - 1 <= mt_min_slots[wr_mas.type]) - request = mas_mt_height(mas) * 2 - 1; - - /* node store, slot store needs one node */ -ask_now: - mas_node_count_gfp(mas, request, gfp); mas->mas_flags |= MA_STATE_PREALLOC; - if (likely(!mas_is_err(mas))) - return 0; - - mas_set_alloc_req(mas, 0); - ret = xa_err(mas->node); - mas_reset(mas); - mas_destroy(mas); - mas_reset(mas); return ret; } EXPORT_SYMBOL_GPL(mas_preallocate); @@ -5588,7 +5537,8 @@ void mas_destroy(struct ma_state *mas) */ if (mas->mas_flags & MA_STATE_REBALANCE) { unsigned char end; - + if (mas_is_err(mas)) + mas_reset(mas); mas_start(mas); mtree_range_walk(mas); end = mas->end + 1; @@ -6248,24 +6198,32 @@ EXPORT_SYMBOL_GPL(mas_find_range_rev); void *mas_erase(struct ma_state *mas) { void *entry; + unsigned long index = mas->index; MA_WR_STATE(wr_mas, mas, NULL); if (!mas_is_active(mas) || !mas_is_start(mas)) mas->status = ma_start; - /* Retry unnecessary when holding the write lock. */ +write_retry: entry = mas_state_walk(mas); if (!entry) return NULL; -write_retry: /* Must reset to ensure spanning writes of last slot are detected */ mas_reset(mas); - mas_wr_store_setup(&wr_mas); - mas_wr_store_entry(&wr_mas); - if (mas_nomem(mas, GFP_KERNEL)) + mas_wr_preallocate(&wr_mas, NULL); + if (mas_nomem(mas, GFP_KERNEL)) { + /* in case the range of entry changed when unlocked */ + mas->index = mas->last = index; goto write_retry; + } + + if (mas_is_err(mas)) + goto out; + mas_wr_store_entry(&wr_mas); +out: + mas_destroy(mas); return entry; } EXPORT_SYMBOL_GPL(mas_erase); @@ -6280,10 +6238,8 @@ EXPORT_SYMBOL_GPL(mas_erase); bool mas_nomem(struct ma_state *mas, gfp_t gfp) __must_hold(mas->tree->ma_lock) { - if (likely(mas->node != MA_ERROR(-ENOMEM))) { - mas_destroy(mas); + if (likely(mas->node != MA_ERROR(-ENOMEM))) return false; - } if (gfpflags_allow_blocking(gfp) && !mt_external_lock(mas->tree)) { mtree_unlock(mas->tree); @@ -6360,7 +6316,7 @@ int mtree_store_range(struct maple_tree *mt, unsigned long index, unsigned long last, void *entry, gfp_t gfp) { MA_STATE(mas, mt, index, last); - MA_WR_STATE(wr_mas, &mas, entry); + int ret = 0; trace_ma_write(__func__, &mas, 0, entry); if (WARN_ON_ONCE(xa_is_advanced(entry))) @@ -6370,16 +6326,10 @@ int mtree_store_range(struct maple_tree *mt, unsigned long index, return -EINVAL; mtree_lock(mt); -retry: - mas_wr_store_entry(&wr_mas); - if (mas_nomem(&mas, gfp)) - goto retry; - + ret = mas_store_gfp(&mas, entry, gfp); mtree_unlock(mt); - if (mas_is_err(&mas)) - return xa_err(mas.node); - return 0; + return ret; } EXPORT_SYMBOL(mtree_store_range); @@ -6415,6 +6365,7 @@ int mtree_insert_range(struct maple_tree *mt, unsigned long first, unsigned long last, void *entry, gfp_t gfp) { MA_STATE(ms, mt, first, last); + int ret = 0; if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; @@ -6430,9 +6381,10 @@ retry: mtree_unlock(mt); if (mas_is_err(&ms)) - return xa_err(ms.node); + ret = xa_err(ms.node); - return 0; + mas_destroy(&ms); + return ret; } EXPORT_SYMBOL(mtree_insert_range); @@ -6487,6 +6439,7 @@ retry: unlock: mtree_unlock(mt); + mas_destroy(&mas); return ret; } EXPORT_SYMBOL(mtree_alloc_range); @@ -6568,6 +6521,7 @@ retry: unlock: mtree_unlock(mt); + mas_destroy(&mas); return ret; } EXPORT_SYMBOL(mtree_alloc_rrange); @@ -6943,7 +6897,7 @@ retry: goto unlock; while (mas_is_active(&mas) && (mas.last < max)) { - entry = mas_next_entry(&mas, max); + entry = mas_next_slot(&mas, max, false); if (likely(entry && !xa_is_zero(entry))) break; } @@ -7000,6 +6954,19 @@ void mt_set_non_kernel(unsigned int val) kmem_cache_set_non_kernel(maple_node_cache, val); } +extern void kmem_cache_set_callback(struct kmem_cache *cachep, + void (*callback)(void *)); +void mt_set_callback(void (*callback)(void *)) +{ + kmem_cache_set_callback(maple_node_cache, callback); +} + +extern void kmem_cache_set_private(struct kmem_cache *cachep, void *private); +void mt_set_private(void *private) +{ + kmem_cache_set_private(maple_node_cache, private); +} + extern unsigned long kmem_cache_get_alloc(struct kmem_cache *); unsigned long mt_get_alloc_size(void) { @@ -7116,14 +7083,14 @@ static void mt_dump_entry(void *entry, unsigned long min, unsigned long max, mt_dump_range(min, max, depth, format); if (xa_is_value(entry)) - pr_cont("value %ld (0x%lx) [%p]\n", xa_to_value(entry), - xa_to_value(entry), entry); + pr_cont("value %ld (0x%lx) [" PTR_FMT "]\n", xa_to_value(entry), + xa_to_value(entry), entry); else if (xa_is_zero(entry)) pr_cont("zero (%ld)\n", xa_to_internal(entry)); else if (mt_is_reserved(entry)) - pr_cont("UNKNOWN ENTRY (%p)\n", entry); + pr_cont("UNKNOWN ENTRY (" PTR_FMT ")\n", entry); else - pr_cont("%p\n", entry); + pr_cont(PTR_FMT "\n", entry); } static void mt_dump_range64(const struct maple_tree *mt, void *entry, @@ -7139,13 +7106,13 @@ static void mt_dump_range64(const struct maple_tree *mt, void *entry, for (i = 0; i < MAPLE_RANGE64_SLOTS - 1; i++) { switch(format) { case mt_dump_hex: - pr_cont("%p %lX ", node->slot[i], node->pivot[i]); + pr_cont(PTR_FMT " %lX ", node->slot[i], node->pivot[i]); break; case mt_dump_dec: - pr_cont("%p %lu ", node->slot[i], node->pivot[i]); + pr_cont(PTR_FMT " %lu ", node->slot[i], node->pivot[i]); } } - pr_cont("%p\n", node->slot[i]); + pr_cont(PTR_FMT "\n", node->slot[i]); for (i = 0; i < MAPLE_RANGE64_SLOTS; i++) { unsigned long last = max; @@ -7167,11 +7134,11 @@ static void mt_dump_range64(const struct maple_tree *mt, void *entry, if (last > max) { switch(format) { case mt_dump_hex: - pr_err("node %p last (%lx) > max (%lx) at pivot %d!\n", + pr_err("node " PTR_FMT " last (%lx) > max (%lx) at pivot %d!\n", node, last, max, i); break; case mt_dump_dec: - pr_err("node %p last (%lu) > max (%lu) at pivot %d!\n", + pr_err("node " PTR_FMT " last (%lu) > max (%lu) at pivot %d!\n", node, last, max, i); } } @@ -7184,7 +7151,6 @@ static void mt_dump_arange64(const struct maple_tree *mt, void *entry, enum mt_dump_format format) { struct maple_arange_64 *node = &mte_to_node(entry)->ma64; - bool leaf = mte_is_leaf(entry); unsigned long first = min; int i; @@ -7202,13 +7168,13 @@ static void mt_dump_arange64(const struct maple_tree *mt, void *entry, for (i = 0; i < MAPLE_ARANGE64_SLOTS - 1; i++) { switch (format) { case mt_dump_hex: - pr_cont("%p %lX ", node->slot[i], node->pivot[i]); + pr_cont(PTR_FMT " %lX ", node->slot[i], node->pivot[i]); break; case mt_dump_dec: - pr_cont("%p %lu ", node->slot[i], node->pivot[i]); + pr_cont(PTR_FMT " %lu ", node->slot[i], node->pivot[i]); } } - pr_cont("%p\n", node->slot[i]); + pr_cont(PTR_FMT "\n", node->slot[i]); for (i = 0; i < MAPLE_ARANGE64_SLOTS; i++) { unsigned long last = max; @@ -7218,19 +7184,22 @@ static void mt_dump_arange64(const struct maple_tree *mt, void *entry, break; if (last == 0 && i > 0) break; - if (leaf) - mt_dump_entry(mt_slot(mt, node->slot, i), - first, last, depth + 1, format); - else if (node->slot[i]) + if (node->slot[i]) mt_dump_node(mt, mt_slot(mt, node->slot, i), first, last, depth + 1, format); if (last == max) break; if (last > max) { - pr_err("node %p last (%lu) > max (%lu) at pivot %d!\n", + switch(format) { + case mt_dump_hex: + pr_err("node " PTR_FMT " last (%lx) > max (%lx) at pivot %d!\n", node, last, max, i); - break; + break; + case mt_dump_dec: + pr_err("node " PTR_FMT " last (%lu) > max (%lu) at pivot %d!\n", + node, last, max, i); + } } first = last + 1; } @@ -7246,8 +7215,8 @@ static void mt_dump_node(const struct maple_tree *mt, void *entry, mt_dump_range(min, max, depth, format); - pr_cont("node %p depth %d type %d parent %p", node, depth, type, - node ? node->parent : NULL); + pr_cont("node " PTR_FMT " depth %d type %d parent " PTR_FMT, node, + depth, type, node ? node->parent : NULL); switch (type) { case maple_dense: pr_cont("\n"); @@ -7275,12 +7244,14 @@ void mt_dump(const struct maple_tree *mt, enum mt_dump_format format) { void *entry = rcu_dereference_check(mt->ma_root, mt_locked(mt)); - pr_info("maple_tree(%p) flags %X, height %u root %p\n", + pr_info("maple_tree(" PTR_FMT ") flags %X, height %u root " PTR_FMT "\n", mt, mt->ma_flags, mt_height(mt), entry); - if (!xa_is_node(entry)) - mt_dump_entry(entry, 0, 0, 0, format); - else if (entry) + if (xa_is_node(entry)) mt_dump_node(mt, entry, 0, mt_node_max(entry), 0, format); + else if (entry) + mt_dump_entry(entry, 0, 0, 0, format); + else + pr_info("(empty)\n"); } EXPORT_SYMBOL_GPL(mt_dump); @@ -7327,7 +7298,7 @@ static void mas_validate_gaps(struct ma_state *mas) MT_BUG_ON(mas->tree, !entry); if (gap > p_end - p_start + 1) { - pr_err("%p[%u] %lu >= %lu - %lu + 1 (%lu)\n", + pr_err(PTR_FMT "[%u] %lu >= %lu - %lu + 1 (%lu)\n", mas_mn(mas), i, gap, p_end, p_start, p_end - p_start + 1); MT_BUG_ON(mas->tree, gap > p_end - p_start + 1); @@ -7347,19 +7318,19 @@ counted: MT_BUG_ON(mas->tree, !gaps); offset = ma_meta_gap(node); if (offset > i) { - pr_err("gap offset %p[%u] is invalid\n", node, offset); + pr_err("gap offset " PTR_FMT "[%u] is invalid\n", node, offset); MT_BUG_ON(mas->tree, 1); } if (gaps[offset] != max_gap) { - pr_err("gap %p[%u] is not the largest gap %lu\n", + pr_err("gap " PTR_FMT "[%u] is not the largest gap %lu\n", node, offset, max_gap); MT_BUG_ON(mas->tree, 1); } for (i++ ; i < mt_slot_count(mte); i++) { if (gaps[i] != 0) { - pr_err("gap %p[%u] beyond node limit != 0\n", + pr_err("gap " PTR_FMT "[%u] beyond node limit != 0\n", node, i); MT_BUG_ON(mas->tree, 1); } @@ -7373,7 +7344,7 @@ counted: p_mn = mte_parent(mte); MT_BUG_ON(mas->tree, max_gap > mas->max); if (ma_gaps(p_mn, mas_parent_type(mas, mte))[p_slot] != max_gap) { - pr_err("gap %p[%u] != %lu\n", p_mn, p_slot, max_gap); + pr_err("gap " PTR_FMT "[%u] != %lu\n", p_mn, p_slot, max_gap); mt_dump(mas->tree, mt_dump_hex); MT_BUG_ON(mas->tree, 1); } @@ -7403,11 +7374,11 @@ static void mas_validate_parent_slot(struct ma_state *mas) node = mas_slot(mas, slots, i); if (i == p_slot) { if (node != mas->node) - pr_err("parent %p[%u] does not have %p\n", + pr_err("parent " PTR_FMT "[%u] does not have " PTR_FMT "\n", parent, i, mas_mn(mas)); MT_BUG_ON(mas->tree, node != mas->node); } else if (node == mas->node) { - pr_err("Invalid child %p at parent %p[%u] p_slot %u\n", + pr_err("Invalid child " PTR_FMT " at parent " PTR_FMT "[%u] p_slot %u\n", mas_mn(mas), parent, i, p_slot); MT_BUG_ON(mas->tree, node == mas->node); } @@ -7429,20 +7400,20 @@ static void mas_validate_child_slot(struct ma_state *mas) child = mas_slot(mas, slots, i); if (!child) { - pr_err("Non-leaf node lacks child at %p[%u]\n", + pr_err("Non-leaf node lacks child at " PTR_FMT "[%u]\n", mas_mn(mas), i); MT_BUG_ON(mas->tree, 1); } if (mte_parent_slot(child) != i) { - pr_err("Slot error at %p[%u]: child %p has pslot %u\n", + pr_err("Slot error at " PTR_FMT "[%u]: child " PTR_FMT " has pslot %u\n", mas_mn(mas), i, mte_to_node(child), mte_parent_slot(child)); MT_BUG_ON(mas->tree, 1); } if (mte_parent(child) != mte_to_node(mas->node)) { - pr_err("child %p has parent %p not %p\n", + pr_err("child " PTR_FMT " has parent " PTR_FMT " not " PTR_FMT "\n", mte_to_node(child), mte_parent(child), mte_to_node(mas->node)); MT_BUG_ON(mas->tree, 1); @@ -7472,24 +7443,24 @@ static void mas_validate_limits(struct ma_state *mas) piv = mas_safe_pivot(mas, pivots, i, type); if (!piv && (i != 0)) { - pr_err("Missing node limit pivot at %p[%u]", + pr_err("Missing node limit pivot at " PTR_FMT "[%u]", mas_mn(mas), i); MAS_WARN_ON(mas, 1); } if (prev_piv > piv) { - pr_err("%p[%u] piv %lu < prev_piv %lu\n", + pr_err(PTR_FMT "[%u] piv %lu < prev_piv %lu\n", mas_mn(mas), i, piv, prev_piv); MAS_WARN_ON(mas, piv < prev_piv); } if (piv < mas->min) { - pr_err("%p[%u] %lu < %lu\n", mas_mn(mas), i, + pr_err(PTR_FMT "[%u] %lu < %lu\n", mas_mn(mas), i, piv, mas->min); MAS_WARN_ON(mas, piv < mas->min); } if (piv > mas->max) { - pr_err("%p[%u] %lu > %lu\n", mas_mn(mas), i, + pr_err(PTR_FMT "[%u] %lu > %lu\n", mas_mn(mas), i, piv, mas->max); MAS_WARN_ON(mas, piv > mas->max); } @@ -7499,7 +7470,7 @@ static void mas_validate_limits(struct ma_state *mas) } if (mas_data_end(mas) != i) { - pr_err("node%p: data_end %u != the last slot offset %u\n", + pr_err("node" PTR_FMT ": data_end %u != the last slot offset %u\n", mas_mn(mas), mas_data_end(mas), i); MT_BUG_ON(mas->tree, 1); } @@ -7508,8 +7479,8 @@ static void mas_validate_limits(struct ma_state *mas) void *entry = mas_slot(mas, slots, i); if (entry && (i != mt_slots[type] - 1)) { - pr_err("%p[%u] should not have entry %p\n", mas_mn(mas), - i, entry); + pr_err(PTR_FMT "[%u] should not have entry " PTR_FMT "\n", + mas_mn(mas), i, entry); MT_BUG_ON(mas->tree, entry != NULL); } @@ -7519,7 +7490,7 @@ static void mas_validate_limits(struct ma_state *mas) if (!piv) continue; - pr_err("%p[%u] should not have piv %lu\n", + pr_err(PTR_FMT "[%u] should not have piv %lu\n", mas_mn(mas), i, piv); MAS_WARN_ON(mas, i < mt_pivots[type] - 1); } @@ -7544,7 +7515,7 @@ static void mt_validate_nulls(struct maple_tree *mt) do { entry = mas_slot(&mas, slots, offset); if (!last && !entry) { - pr_err("Sequential nulls end at %p[%u]\n", + pr_err("Sequential nulls end at " PTR_FMT "[%u]\n", mas_mn(&mas), offset); } MT_BUG_ON(mt, !last && !entry); @@ -7569,14 +7540,14 @@ static void mt_validate_nulls(struct maple_tree *mt) * 2. The gap is correctly set in the parents */ void mt_validate(struct maple_tree *mt) + __must_hold(mas->tree->ma_lock) { unsigned char end; MA_STATE(mas, mt, 0, 0); - rcu_read_lock(); mas_start(&mas); if (!mas_is_active(&mas)) - goto done; + return; while (!mte_is_leaf(mas.node)) mas_descend(&mas); @@ -7585,8 +7556,9 @@ void mt_validate(struct maple_tree *mt) MAS_WARN_ON(&mas, mte_dead_node(mas.node)); end = mas_data_end(&mas); if (MAS_WARN_ON(&mas, (end < mt_min_slot_count(mas.node)) && - (mas.max != ULONG_MAX))) { - pr_err("Invalid size %u of %p\n", end, mas_mn(&mas)); + (!mte_is_root(mas.node)))) { + pr_err("Invalid size %u of " PTR_FMT "\n", + end, mas_mn(&mas)); } mas_validate_parent_slot(&mas); @@ -7597,15 +7569,13 @@ void mt_validate(struct maple_tree *mt) mas_dfs_postorder(&mas, ULONG_MAX); } mt_validate_nulls(mt); -done: - rcu_read_unlock(); - } EXPORT_SYMBOL_GPL(mt_validate); void mas_dump(const struct ma_state *mas) { - pr_err("MAS: tree=%p enode=%p ", mas->tree, mas->node); + pr_err("MAS: tree=" PTR_FMT " enode=" PTR_FMT " ", + mas->tree, mas->node); switch (mas->status) { case ma_active: pr_err("(ma_active)"); @@ -7633,9 +7603,43 @@ void mas_dump(const struct ma_state *mas) break; } + pr_err("Store Type: "); + switch (mas->store_type) { + case wr_invalid: + pr_err("invalid store type\n"); + break; + case wr_new_root: + pr_err("new_root\n"); + break; + case wr_store_root: + pr_err("store_root\n"); + break; + case wr_exact_fit: + pr_err("exact_fit\n"); + break; + case wr_split_store: + pr_err("split_store\n"); + break; + case wr_slot_store: + pr_err("slot_store\n"); + break; + case wr_append: + pr_err("append\n"); + break; + case wr_node_store: + pr_err("node_store\n"); + break; + case wr_spanning_store: + pr_err("spanning_store\n"); + break; + case wr_rebalance: + pr_err("rebalance\n"); + break; + } + pr_err("[%u/%u] index=%lx last=%lx\n", mas->offset, mas->end, mas->index, mas->last); - pr_err(" min=%lx max=%lx alloc=%p, depth=%u, flags=%x\n", + pr_err(" min=%lx max=%lx alloc=" PTR_FMT ", depth=%u, flags=%x\n", mas->min, mas->max, mas->alloc, mas->depth, mas->mas_flags); if (mas->index > mas->last) pr_err("Check index & last\n"); @@ -7644,7 +7648,7 @@ EXPORT_SYMBOL_GPL(mas_dump); void mas_wr_dump(const struct ma_wr_state *wr_mas) { - pr_err("WR_MAS: node=%p r_min=%lx r_max=%lx\n", + pr_err("WR_MAS: node=" PTR_FMT " r_min=%lx r_max=%lx\n", wr_mas->node, wr_mas->r_min, wr_mas->r_max); pr_err(" type=%u off_end=%u, node_end=%u, end_piv=%lx\n", wr_mas->type, wr_mas->offset_end, wr_mas->mas->end, diff --git a/lib/math/Makefile b/lib/math/Makefile index 91fcdb0c9efe..853f023ae537 100644 --- a/lib/math/Makefile +++ b/lib/math/Makefile @@ -5,5 +5,8 @@ obj-$(CONFIG_CORDIC) += cordic.o obj-$(CONFIG_PRIME_NUMBERS) += prime_numbers.o obj-$(CONFIG_RATIONAL) += rational.o +obj-$(CONFIG_INT_POW_TEST) += tests/int_pow_kunit.o obj-$(CONFIG_TEST_DIV64) += test_div64.o +obj-$(CONFIG_TEST_MULDIV64) += test_mul_u64_u64_div_u64.o obj-$(CONFIG_RATIONAL_KUNIT_TEST) += rational-test.o +obj-$(CONFIG_INT_SQRT_KUNIT_TEST) += tests/int_sqrt_kunit.o
\ No newline at end of file diff --git a/lib/math/div64.c b/lib/math/div64.c index 191761b1b623..5faa29208bdb 100644 --- a/lib/math/div64.c +++ b/lib/math/div64.c @@ -186,55 +186,84 @@ EXPORT_SYMBOL(iter_div_u64_rem); #ifndef mul_u64_u64_div_u64 u64 mul_u64_u64_div_u64(u64 a, u64 b, u64 c) { - u64 res = 0, div, rem; - int shift; + if (ilog2(a) + ilog2(b) <= 62) + return div64_u64(a * b, c); - /* can a * b overflow ? */ - if (ilog2(a) + ilog2(b) > 62) { - /* - * Note that the algorithm after the if block below might lose - * some precision and the result is more exact for b > a. So - * exchange a and b if a is bigger than b. - * - * For example with a = 43980465100800, b = 100000000, c = 1000000000 - * the below calculation doesn't modify b at all because div == 0 - * and then shift becomes 45 + 26 - 62 = 9 and so the result - * becomes 4398035251080. However with a and b swapped the exact - * result is calculated (i.e. 4398046510080). - */ - if (a > b) - swap(a, b); +#if defined(__SIZEOF_INT128__) + + /* native 64x64=128 bits multiplication */ + u128 prod = (u128)a * b; + u64 n_lo = prod, n_hi = prod >> 64; + +#else + + /* perform a 64x64=128 bits multiplication manually */ + u32 a_lo = a, a_hi = a >> 32, b_lo = b, b_hi = b >> 32; + u64 x, y, z; + + x = (u64)a_lo * b_lo; + y = (u64)a_lo * b_hi + (u32)(x >> 32); + z = (u64)a_hi * b_hi + (u32)(y >> 32); + y = (u64)a_hi * b_lo + (u32)y; + z += (u32)(y >> 32); + x = (y << 32) + (u32)x; + + u64 n_lo = x, n_hi = z; + +#endif + + /* make sure c is not zero, trigger exception otherwise */ +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdiv-by-zero" + if (unlikely(c == 0)) + return 1/0; +#pragma GCC diagnostic pop + + int shift = __builtin_ctzll(c); + /* try reducing the fraction in case the dividend becomes <= 64 bits */ + if ((n_hi >> shift) == 0) { + u64 n = shift ? (n_lo >> shift) | (n_hi << (64 - shift)) : n_lo; + + return div64_u64(n, c >> shift); /* - * (b * a) / c is equal to - * - * (b / c) * a + - * (b % c) * a / c - * - * if nothing overflows. Can the 1st multiplication - * overflow? Yes, but we do not care: this can only - * happen if the end result can't fit in u64 anyway. - * - * So the code below does - * - * res = (b / c) * a; - * b = b % c; + * The remainder value if needed would be: + * res = div64_u64_rem(n, c >> shift, &rem); + * rem = (rem << shift) + (n_lo - (n << shift)); */ - div = div64_u64_rem(b, c, &rem); - res = div * a; - b = rem; - - shift = ilog2(a) + ilog2(b) - 62; - if (shift > 0) { - /* drop precision */ - b >>= shift; - c >>= shift; - if (!c) - return res; - } } - return res + div64_u64(a * b, c); + if (n_hi >= c) { + /* overflow: result is unrepresentable in a u64 */ + return -1; + } + + /* Do the full 128 by 64 bits division */ + + shift = __builtin_clzll(c); + c <<= shift; + + int p = 64 + shift; + u64 res = 0; + bool carry; + + do { + carry = n_hi >> 63; + shift = carry ? 1 : __builtin_clzll(n_hi); + if (p < shift) + break; + p -= shift; + n_hi <<= shift; + n_hi |= n_lo >> (64 - shift); + n_lo <<= shift; + if (carry || (n_hi >= c)) { + n_hi -= c; + res |= 1ULL << p; + } + } while (n_hi); + /* The remainder value if needed would be n_hi << p */ + + return res; } EXPORT_SYMBOL(mul_u64_u64_div_u64); #endif diff --git a/lib/math/prime_numbers.c b/lib/math/prime_numbers.c index d3b64b10da1c..9a17ee9af93a 100644 --- a/lib/math/prime_numbers.c +++ b/lib/math/prime_numbers.c @@ -311,4 +311,5 @@ module_exit(primes_exit); module_param_named(selftest, selftest_max, ulong, 0400); MODULE_AUTHOR("Intel Corporation"); +MODULE_DESCRIPTION("Prime number library"); MODULE_LICENSE("GPL"); diff --git a/lib/math/rational-test.c b/lib/math/rational-test.c index 01611ddff420..47486a95f088 100644 --- a/lib/math/rational-test.c +++ b/lib/math/rational-test.c @@ -53,4 +53,5 @@ static struct kunit_suite rational_test_suite = { kunit_test_suites(&rational_test_suite); +MODULE_DESCRIPTION("Rational fractions unit test"); MODULE_LICENSE("GPL v2"); diff --git a/lib/math/rational.c b/lib/math/rational.c index ec59d426ea63..d2c34e629ee1 100644 --- a/lib/math/rational.c +++ b/lib/math/rational.c @@ -108,4 +108,5 @@ void rational_best_approximation( EXPORT_SYMBOL(rational_best_approximation); +MODULE_DESCRIPTION("Rational fraction support library"); MODULE_LICENSE("GPL v2"); diff --git a/lib/math/test_div64.c b/lib/math/test_div64.c index c15edd688dd2..3cd699b654d9 100644 --- a/lib/math/test_div64.c +++ b/lib/math/test_div64.c @@ -26,6 +26,9 @@ static const u64 test_div64_dividends[] = { 0x0072db27380dd689, 0x0842f488162e2284, 0xf66745411d8ab063, + 0xfffffffffffffffb, + 0xfffffffffffffffc, + 0xffffffffffffffff, }; #define SIZE_DIV64_DIVIDENDS ARRAY_SIZE(test_div64_dividends) @@ -37,7 +40,10 @@ static const u64 test_div64_dividends[] = { #define TEST_DIV64_DIVISOR_5 0x0008a880 #define TEST_DIV64_DIVISOR_6 0x003fd3ae #define TEST_DIV64_DIVISOR_7 0x0b658fac -#define TEST_DIV64_DIVISOR_8 0xdc08b349 +#define TEST_DIV64_DIVISOR_8 0x80000001 +#define TEST_DIV64_DIVISOR_9 0xdc08b349 +#define TEST_DIV64_DIVISOR_A 0xfffffffe +#define TEST_DIV64_DIVISOR_B 0xffffffff static const u32 test_div64_divisors[] = { TEST_DIV64_DIVISOR_0, @@ -49,13 +55,16 @@ static const u32 test_div64_divisors[] = { TEST_DIV64_DIVISOR_6, TEST_DIV64_DIVISOR_7, TEST_DIV64_DIVISOR_8, + TEST_DIV64_DIVISOR_9, + TEST_DIV64_DIVISOR_A, + TEST_DIV64_DIVISOR_B, }; #define SIZE_DIV64_DIVISORS ARRAY_SIZE(test_div64_divisors) static const struct { u64 quotient; u32 remainder; -} test_div64_results[SIZE_DIV64_DIVISORS][SIZE_DIV64_DIVIDENDS] = { +} test_div64_results[SIZE_DIV64_DIVIDENDS][SIZE_DIV64_DIVISORS] = { { { 0x0000000013045e47, 0x00000001 }, { 0x000000000161596c, 0x00000030 }, @@ -65,6 +74,9 @@ static const struct { { 0x00000000000013c4, 0x0004ce80 }, { 0x00000000000002ae, 0x001e143c }, { 0x000000000000000f, 0x0033e56c }, + { 0x0000000000000001, 0x2b27507f }, + { 0x0000000000000000, 0xab275080 }, + { 0x0000000000000000, 0xab275080 }, { 0x0000000000000000, 0xab275080 }, }, { { 0x00000001c45c02d1, 0x00000000 }, @@ -75,7 +87,10 @@ static const struct { { 0x000000000001d637, 0x0004e5d9 }, { 0x0000000000003fc9, 0x000713bb }, { 0x0000000000000165, 0x029abe7d }, + { 0x000000000000001f, 0x673c193a }, { 0x0000000000000012, 0x6e9f7e37 }, + { 0x000000000000000f, 0xe73c1977 }, + { 0x000000000000000f, 0xe73c1968 }, }, { { 0x000000197a3a0cf7, 0x00000002 }, { 0x00000001d9632e5c, 0x00000021 }, @@ -85,7 +100,10 @@ static const struct { { 0x00000000001a7bb3, 0x00072331 }, { 0x00000000000397ad, 0x0002c61b }, { 0x000000000000141e, 0x06ea2e89 }, + { 0x00000000000001ca, 0x4c0a72e7 }, { 0x000000000000010a, 0xab002ad7 }, + { 0x00000000000000e5, 0x4c0a767b }, + { 0x00000000000000e5, 0x4c0a7596 }, }, { { 0x0000017949e37538, 0x00000001 }, { 0x0000001b62441f37, 0x00000055 }, @@ -95,7 +113,10 @@ static const struct { { 0x0000000001882ec6, 0x0005cbf9 }, { 0x000000000035333b, 0x0017abdf }, { 0x00000000000129f1, 0x0ab4520d }, + { 0x0000000000001a87, 0x18ff0472 }, { 0x0000000000000f6e, 0x8ac0ce9b }, + { 0x0000000000000d43, 0x98ff397f }, + { 0x0000000000000d43, 0x98ff2c3c }, }, { { 0x000011f321a74e49, 0x00000006 }, { 0x0000014d8481d211, 0x0000005b }, @@ -105,7 +126,10 @@ static const struct { { 0x0000000012a88828, 0x00036c97 }, { 0x000000000287f16f, 0x002c2a25 }, { 0x00000000000e2cc7, 0x02d581e3 }, + { 0x0000000000014318, 0x2ee07d7f }, { 0x000000000000bbf4, 0x1ba08c03 }, + { 0x000000000000a18c, 0x2ee303af }, + { 0x000000000000a18c, 0x2ee26223 }, }, { { 0x0000d8db8f72935d, 0x00000005 }, { 0x00000fbd5aed7a2e, 0x00000002 }, @@ -115,7 +139,10 @@ static const struct { { 0x00000000e16b20fa, 0x0002a14a }, { 0x000000001e940d22, 0x00353b2e }, { 0x0000000000ab40ac, 0x06fba6ba }, + { 0x00000000000f3f70, 0x0af7eeda }, { 0x000000000008debd, 0x72d98365 }, + { 0x0000000000079fb8, 0x0b166dba }, + { 0x0000000000079fb8, 0x0b0ece02 }, }, { { 0x000cc3045b8fc281, 0x00000000 }, { 0x0000ed1f48b5c9fc, 0x00000079 }, @@ -125,7 +152,10 @@ static const struct { { 0x0000000d43fce827, 0x00082b09 }, { 0x00000001ccaba11a, 0x0037e8dd }, { 0x000000000a13f729, 0x0566dffd }, + { 0x0000000000e5b64e, 0x3728203b }, { 0x000000000085a14b, 0x23d36726 }, + { 0x000000000072db27, 0x38f38cd7 }, + { 0x000000000072db27, 0x3880b1b0 }, }, { { 0x00eafeb9c993592b, 0x00000001 }, { 0x00110e5befa9a991, 0x00000048 }, @@ -135,7 +165,10 @@ static const struct { { 0x000000f4459740fc, 0x00084484 }, { 0x0000002122c47bf9, 0x002ca446 }, { 0x00000000b9936290, 0x004979c4 }, + { 0x000000001085e910, 0x05a83974 }, { 0x00000000099ca89d, 0x9db446bf }, + { 0x000000000842f488, 0x26b40b94 }, + { 0x000000000842f488, 0x1e71170c }, }, { { 0x1b60cece589da1d2, 0x00000001 }, { 0x01fcb42be1453f5b, 0x0000004f }, @@ -145,7 +178,49 @@ static const struct { { 0x00001c757dfab350, 0x00048863 }, { 0x000003dc4979c652, 0x00224ea7 }, { 0x000000159edc3144, 0x06409ab3 }, + { 0x00000001ecce8a7e, 0x30bc25e5 }, { 0x000000011eadfee3, 0xa99c48a8 }, + { 0x00000000f6674543, 0x0a593ae9 }, + { 0x00000000f6674542, 0x13f1f5a5 }, + }, { + { 0x1c71c71c71c71c71, 0x00000002 }, + { 0x0210842108421084, 0x0000000b }, + { 0x007f01fc07f01fc0, 0x000000fb }, + { 0x00014245eabf1f9a, 0x0000a63d }, + { 0x0000ffffffffffff, 0x0000fffb }, + { 0x00001d913cecc509, 0x0007937b }, + { 0x00000402c70c678f, 0x0005bfc9 }, + { 0x00000016766cb70b, 0x045edf97 }, + { 0x00000001fffffffb, 0x80000000 }, + { 0x0000000129d84b3a, 0xa2e8fe71 }, + { 0x0000000100000001, 0xfffffffd }, + { 0x0000000100000000, 0xfffffffb }, + }, { + { 0x1c71c71c71c71c71, 0x00000003 }, + { 0x0210842108421084, 0x0000000c }, + { 0x007f01fc07f01fc0, 0x000000fc }, + { 0x00014245eabf1f9a, 0x0000a63e }, + { 0x0000ffffffffffff, 0x0000fffc }, + { 0x00001d913cecc509, 0x0007937c }, + { 0x00000402c70c678f, 0x0005bfca }, + { 0x00000016766cb70b, 0x045edf98 }, + { 0x00000001fffffffc, 0x00000000 }, + { 0x0000000129d84b3a, 0xa2e8fe72 }, + { 0x0000000100000002, 0x00000000 }, + { 0x0000000100000000, 0xfffffffc }, + }, { + { 0x1c71c71c71c71c71, 0x00000006 }, + { 0x0210842108421084, 0x0000000f }, + { 0x007f01fc07f01fc0, 0x000000ff }, + { 0x00014245eabf1f9a, 0x0000a641 }, + { 0x0000ffffffffffff, 0x0000ffff }, + { 0x00001d913cecc509, 0x0007937f }, + { 0x00000402c70c678f, 0x0005bfcd }, + { 0x00000016766cb70b, 0x045edf9b }, + { 0x00000001fffffffc, 0x00000003 }, + { 0x0000000129d84b3a, 0xa2e8fe75 }, + { 0x0000000100000002, 0x00000003 }, + { 0x0000000100000001, 0x00000000 }, }, }; @@ -208,6 +283,12 @@ static bool __init test_div64(void) return false; if (!test_div64_one(dividend, TEST_DIV64_DIVISOR_8, i, 8)) return false; + if (!test_div64_one(dividend, TEST_DIV64_DIVISOR_9, i, 9)) + return false; + if (!test_div64_one(dividend, TEST_DIV64_DIVISOR_A, i, 10)) + return false; + if (!test_div64_one(dividend, TEST_DIV64_DIVISOR_B, i, 11)) + return false; for (j = 0; j < SIZE_DIV64_DIVISORS; j++) { if (!test_div64_one(dividend, test_div64_divisors[j], i, j)) diff --git a/lib/math/test_mul_u64_u64_div_u64.c b/lib/math/test_mul_u64_u64_div_u64.c new file mode 100644 index 000000000000..58d058de4e73 --- /dev/null +++ b/lib/math/test_mul_u64_u64_div_u64.c @@ -0,0 +1,99 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 BayLibre SAS + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/printk.h> +#include <linux/math64.h> + +typedef struct { u64 a; u64 b; u64 c; u64 result; } test_params; + +static test_params test_values[] = { +/* this contains many edge values followed by a couple random values */ +{ 0xb, 0x7, 0x3, 0x19 }, +{ 0xffff0000, 0xffff0000, 0xf, 0x1110eeef00000000 }, +{ 0xffffffff, 0xffffffff, 0x1, 0xfffffffe00000001 }, +{ 0xffffffff, 0xffffffff, 0x2, 0x7fffffff00000000 }, +{ 0x1ffffffff, 0xffffffff, 0x2, 0xfffffffe80000000 }, +{ 0x1ffffffff, 0xffffffff, 0x3, 0xaaaaaaa9aaaaaaab }, +{ 0x1ffffffff, 0x1ffffffff, 0x4, 0xffffffff00000000 }, +{ 0xffff000000000000, 0xffff000000000000, 0xffff000000000001, 0xfffeffffffffffff }, +{ 0x3333333333333333, 0x3333333333333333, 0x5555555555555555, 0x1eb851eb851eb851 }, +{ 0x7fffffffffffffff, 0x2, 0x3, 0x5555555555555554 }, +{ 0xffffffffffffffff, 0x2, 0x8000000000000000, 0x3 }, +{ 0xffffffffffffffff, 0x2, 0xc000000000000000, 0x2 }, +{ 0xffffffffffffffff, 0x4000000000000004, 0x8000000000000000, 0x8000000000000007 }, +{ 0xffffffffffffffff, 0x4000000000000001, 0x8000000000000000, 0x8000000000000001 }, +{ 0xffffffffffffffff, 0x8000000000000001, 0xffffffffffffffff, 0x8000000000000001 }, +{ 0xfffffffffffffffe, 0x8000000000000001, 0xffffffffffffffff, 0x8000000000000000 }, +{ 0xffffffffffffffff, 0x8000000000000001, 0xfffffffffffffffe, 0x8000000000000001 }, +{ 0xffffffffffffffff, 0x8000000000000001, 0xfffffffffffffffd, 0x8000000000000002 }, +{ 0x7fffffffffffffff, 0xffffffffffffffff, 0xc000000000000000, 0xaaaaaaaaaaaaaaa8 }, +{ 0xffffffffffffffff, 0x7fffffffffffffff, 0xa000000000000000, 0xccccccccccccccca }, +{ 0xffffffffffffffff, 0x7fffffffffffffff, 0x9000000000000000, 0xe38e38e38e38e38b }, +{ 0x7fffffffffffffff, 0x7fffffffffffffff, 0x5000000000000000, 0xccccccccccccccc9 }, +{ 0xffffffffffffffff, 0xfffffffffffffffe, 0xffffffffffffffff, 0xfffffffffffffffe }, +{ 0xe6102d256d7ea3ae, 0x70a77d0be4c31201, 0xd63ec35ab3220357, 0x78f8bf8cc86c6e18 }, +{ 0xf53bae05cb86c6e1, 0x3847b32d2f8d32e0, 0xcfd4f55a647f403c, 0x42687f79d8998d35 }, +{ 0x9951c5498f941092, 0x1f8c8bfdf287a251, 0xa3c8dc5f81ea3fe2, 0x1d887cb25900091f }, +{ 0x374fee9daa1bb2bb, 0x0d0bfbff7b8ae3ef, 0xc169337bd42d5179, 0x03bb2dbaffcbb961 }, +{ 0xeac0d03ac10eeaf0, 0x89be05dfa162ed9b, 0x92bb1679a41f0e4b, 0xdc5f5cc9e270d216 }, +}; + +/* + * The above table can be verified with the following shell script: + * + * #!/bin/sh + * sed -ne 's/^{ \+\(.*\), \+\(.*\), \+\(.*\), \+\(.*\) },$/\1 \2 \3 \4/p' \ + * lib/math/test_mul_u64_u64_div_u64.c | + * while read a b c r; do + * expected=$( printf "obase=16; ibase=16; %X * %X / %X\n" $a $b $c | bc ) + * given=$( printf "%X\n" $r ) + * if [ "$expected" = "$given" ]; then + * echo "$a * $b / $c = $r OK" + * else + * echo "$a * $b / $c = $r is wrong" >&2 + * echo "should be equivalent to 0x$expected" >&2 + * exit 1 + * fi + * done + */ + +static int __init test_init(void) +{ + int i; + + pr_info("Starting mul_u64_u64_div_u64() test\n"); + + for (i = 0; i < ARRAY_SIZE(test_values); i++) { + u64 a = test_values[i].a; + u64 b = test_values[i].b; + u64 c = test_values[i].c; + u64 expected_result = test_values[i].result; + u64 result = mul_u64_u64_div_u64(a, b, c); + + if (result != expected_result) { + pr_err("ERROR: 0x%016llx * 0x%016llx / 0x%016llx\n", a, b, c); + pr_err("ERROR: expected result: %016llx\n", expected_result); + pr_err("ERROR: obtained result: %016llx\n", result); + } + } + + pr_info("Completed mul_u64_u64_div_u64() test\n"); + return 0; +} + +static void __exit test_exit(void) +{ +} + +module_init(test_init); +module_exit(test_exit); + +MODULE_AUTHOR("Nicolas Pitre"); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("mul_u64_u64_div_u64() test module"); diff --git a/lib/math/tests/Makefile b/lib/math/tests/Makefile new file mode 100644 index 000000000000..e1a79f093b2d --- /dev/null +++ b/lib/math/tests/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only + +obj-$(CONFIG_INT_POW_TEST) += int_pow_kunit.o +obj-$(CONFIG_INT_SQRT_KUNIT_TEST) += int_sqrt_kunit.o diff --git a/lib/math/tests/int_pow_kunit.c b/lib/math/tests/int_pow_kunit.c new file mode 100644 index 000000000000..34b33677d458 --- /dev/null +++ b/lib/math/tests/int_pow_kunit.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <kunit/test.h> +#include <linux/math.h> + +struct test_case_params { + u64 base; + unsigned int exponent; + u64 expected_result; + const char *name; +}; + +static const struct test_case_params params[] = { + { 64, 0, 1, "Power of zero" }, + { 64, 1, 64, "Power of one"}, + { 0, 5, 0, "Base zero" }, + { 1, 64, 1, "Base one" }, + { 2, 2, 4, "Two squared"}, + { 2, 3, 8, "Two cubed"}, + { 5, 5, 3125, "Five raised to the fifth power" }, + { U64_MAX, 1, U64_MAX, "Max base" }, + { 2, 63, 9223372036854775808ULL, "Large result"}, +}; + +static void get_desc(const struct test_case_params *tc, char *desc) +{ + strscpy(desc, tc->name, KUNIT_PARAM_DESC_SIZE); +} + +KUNIT_ARRAY_PARAM(int_pow, params, get_desc); + +static void int_pow_test(struct kunit *test) +{ + const struct test_case_params *tc = (const struct test_case_params *)test->param_value; + + KUNIT_EXPECT_EQ(test, tc->expected_result, int_pow(tc->base, tc->exponent)); +} + +static struct kunit_case math_int_pow_test_cases[] = { + KUNIT_CASE_PARAM(int_pow_test, int_pow_gen_params), + {} +}; + +static struct kunit_suite int_pow_test_suite = { + .name = "math-int_pow", + .test_cases = math_int_pow_test_cases, +}; + +kunit_test_suites(&int_pow_test_suite); + +MODULE_DESCRIPTION("math.int_pow KUnit test suite"); +MODULE_LICENSE("GPL"); diff --git a/lib/math/tests/int_sqrt_kunit.c b/lib/math/tests/int_sqrt_kunit.c new file mode 100644 index 000000000000..1798e1312eb7 --- /dev/null +++ b/lib/math/tests/int_sqrt_kunit.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <kunit/test.h> +#include <linux/limits.h> +#include <linux/math.h> +#include <linux/module.h> +#include <linux/string.h> + +struct test_case_params { + unsigned long x; + unsigned long expected_result; + const char *name; +}; + +static const struct test_case_params params[] = { + { 0, 0, "edge case: square root of 0" }, + { 1, 1, "perfect square: square root of 1" }, + { 2, 1, "non-perfect square: square root of 2" }, + { 3, 1, "non-perfect square: square root of 3" }, + { 4, 2, "perfect square: square root of 4" }, + { 5, 2, "non-perfect square: square root of 5" }, + { 6, 2, "non-perfect square: square root of 6" }, + { 7, 2, "non-perfect square: square root of 7" }, + { 8, 2, "non-perfect square: square root of 8" }, + { 9, 3, "perfect square: square root of 9" }, + { 15, 3, "non-perfect square: square root of 15 (N-1 from 16)" }, + { 16, 4, "perfect square: square root of 16" }, + { 17, 4, "non-perfect square: square root of 17 (N+1 from 16)" }, + { 80, 8, "non-perfect square: square root of 80 (N-1 from 81)" }, + { 81, 9, "perfect square: square root of 81" }, + { 82, 9, "non-perfect square: square root of 82 (N+1 from 81)" }, + { 255, 15, "non-perfect square: square root of 255 (N-1 from 256)" }, + { 256, 16, "perfect square: square root of 256" }, + { 257, 16, "non-perfect square: square root of 257 (N+1 from 256)" }, + { 2147483648, 46340, "large input: square root of 2147483648" }, + { 4294967295, 65535, "edge case: ULONG_MAX for 32-bit" }, +}; + +static void get_desc(const struct test_case_params *tc, char *desc) +{ + strscpy(desc, tc->name, KUNIT_PARAM_DESC_SIZE); +} + +KUNIT_ARRAY_PARAM(int_sqrt, params, get_desc); + +static void int_sqrt_test(struct kunit *test) +{ + const struct test_case_params *tc = (const struct test_case_params *)test->param_value; + + KUNIT_EXPECT_EQ(test, tc->expected_result, int_sqrt(tc->x)); +} + +static struct kunit_case math_int_sqrt_test_cases[] = { + KUNIT_CASE_PARAM(int_sqrt_test, int_sqrt_gen_params), + {} +}; + +static struct kunit_suite int_sqrt_test_suite = { + .name = "math-int_sqrt", + .test_cases = math_int_sqrt_test_cases, +}; + +kunit_test_suites(&int_sqrt_test_suite); + +MODULE_DESCRIPTION("math.int_sqrt KUnit test suite"); +MODULE_LICENSE("GPL"); diff --git a/lib/memcpy_kunit.c b/lib/memcpy_kunit.c index 20ea9038c3ff..d36933554e46 100644 --- a/lib/memcpy_kunit.c +++ b/lib/memcpy_kunit.c @@ -510,4 +510,5 @@ static struct kunit_suite memcpy_test_suite = { kunit_test_suite(memcpy_test_suite); +MODULE_DESCRIPTION("test cases for memcpy(), memmove(), and memset()"); MODULE_LICENSE("GPL"); diff --git a/lib/min_heap.c b/lib/min_heap.c new file mode 100644 index 000000000000..4485372ff3b1 --- /dev/null +++ b/lib/min_heap.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/export.h> +#include <linux/min_heap.h> + +void __min_heap_init(min_heap_char *heap, void *data, int size) +{ + __min_heap_init_inline(heap, data, size); +} +EXPORT_SYMBOL(__min_heap_init); + +void *__min_heap_peek(struct min_heap_char *heap) +{ + return __min_heap_peek_inline(heap); +} +EXPORT_SYMBOL(__min_heap_peek); + +bool __min_heap_full(min_heap_char *heap) +{ + return __min_heap_full_inline(heap); +} +EXPORT_SYMBOL(__min_heap_full); + +void __min_heap_sift_down(min_heap_char *heap, int pos, size_t elem_size, + const struct min_heap_callbacks *func, void *args) +{ + __min_heap_sift_down_inline(heap, pos, elem_size, func, args); +} +EXPORT_SYMBOL(__min_heap_sift_down); + +void __min_heap_sift_up(min_heap_char *heap, size_t elem_size, size_t idx, + const struct min_heap_callbacks *func, void *args) +{ + __min_heap_sift_up_inline(heap, elem_size, idx, func, args); +} +EXPORT_SYMBOL(__min_heap_sift_up); + +void __min_heapify_all(min_heap_char *heap, size_t elem_size, + const struct min_heap_callbacks *func, void *args) +{ + __min_heapify_all_inline(heap, elem_size, func, args); +} +EXPORT_SYMBOL(__min_heapify_all); + +bool __min_heap_pop(min_heap_char *heap, size_t elem_size, + const struct min_heap_callbacks *func, void *args) +{ + return __min_heap_pop_inline(heap, elem_size, func, args); +} +EXPORT_SYMBOL(__min_heap_pop); + +void __min_heap_pop_push(min_heap_char *heap, const void *element, size_t elem_size, + const struct min_heap_callbacks *func, void *args) +{ + __min_heap_pop_push_inline(heap, element, elem_size, func, args); +} +EXPORT_SYMBOL(__min_heap_pop_push); + +bool __min_heap_push(min_heap_char *heap, const void *element, size_t elem_size, + const struct min_heap_callbacks *func, void *args) +{ + return __min_heap_push_inline(heap, element, elem_size, func, args); +} +EXPORT_SYMBOL(__min_heap_push); + +bool __min_heap_del(min_heap_char *heap, size_t elem_size, size_t idx, + const struct min_heap_callbacks *func, void *args) +{ + return __min_heap_del_inline(heap, elem_size, idx, func, args); +} +EXPORT_SYMBOL(__min_heap_del); diff --git a/lib/objagg.c b/lib/objagg.c index 1e248629ed64..363e43e849ac 100644 --- a/lib/objagg.c +++ b/lib/objagg.c @@ -167,6 +167,9 @@ static int objagg_obj_parent_assign(struct objagg *objagg, { void *delta_priv; + if (WARN_ON(!objagg_obj_is_root(parent))) + return -EINVAL; + delta_priv = objagg->ops->delta_create(objagg->priv, parent->obj, objagg_obj->obj); if (IS_ERR(delta_priv)) @@ -421,7 +424,7 @@ static struct objagg_obj *__objagg_obj_get(struct objagg *objagg, void *obj) * * There are 3 main options this function wraps: * 1) The object according to "obj" already exist. In that case - * the reference counter is incrementes and the object is returned. + * the reference counter is incremented and the object is returned. * 2) The object does not exist, but it can be aggregated within * another object. In that case, user ops->delta_create() is called * to obtain delta data and a new object is created with returned @@ -903,20 +906,6 @@ static const struct objagg_opt_algo *objagg_opt_algos[] = { [OBJAGG_OPT_ALGO_SIMPLE_GREEDY] = &objagg_opt_simple_greedy, }; -static int objagg_hints_obj_cmp(struct rhashtable_compare_arg *arg, - const void *obj) -{ - struct rhashtable *ht = arg->ht; - struct objagg_hints *objagg_hints = - container_of(ht, struct objagg_hints, node_ht); - const struct objagg_ops *ops = objagg_hints->ops; - const char *ptr = obj; - - ptr += ht->p.key_offset; - return ops->hints_obj_cmp ? ops->hints_obj_cmp(ptr, arg->key) : - memcmp(ptr, arg->key, ht->p.key_len); -} - /** * objagg_hints_get - obtains hints instance * @objagg: objagg instance @@ -955,7 +944,6 @@ struct objagg_hints *objagg_hints_get(struct objagg *objagg, offsetof(struct objagg_hints_node, obj); objagg_hints->ht_params.head_offset = offsetof(struct objagg_hints_node, ht_node); - objagg_hints->ht_params.obj_cmpfn = objagg_hints_obj_cmp; err = rhashtable_init(&objagg_hints->node_ht, &objagg_hints->ht_params); if (err) diff --git a/lib/objpool.c b/lib/objpool.c index cfdc02420884..b998b720c732 100644 --- a/lib/objpool.c +++ b/lib/objpool.c @@ -50,7 +50,7 @@ objpool_init_percpu_slots(struct objpool_head *pool, int nr_objs, { int i, cpu_count = 0; - for (i = 0; i < pool->nr_cpus; i++) { + for (i = 0; i < nr_cpu_ids; i++) { struct objpool_slot *slot; int nodes, size, rc; @@ -60,8 +60,8 @@ objpool_init_percpu_slots(struct objpool_head *pool, int nr_objs, continue; /* compute how many objects to be allocated with this slot */ - nodes = nr_objs / num_possible_cpus(); - if (cpu_count < (nr_objs % num_possible_cpus())) + nodes = nr_objs / pool->nr_possible_cpus; + if (cpu_count < (nr_objs % pool->nr_possible_cpus)) nodes++; cpu_count++; @@ -74,15 +74,21 @@ objpool_init_percpu_slots(struct objpool_head *pool, int nr_objs, * warm caches and TLB hits. in default vmalloc is used to * reduce the pressure of kernel slab system. as we know, * mimimal size of vmalloc is one page since vmalloc would - * always align the requested size to page size + * always align the requested size to page size. + * but if vmalloc fails or it is not available (e.g. GFP_ATOMIC) + * allocate percpu slot with kmalloc. */ - if (pool->gfp & GFP_ATOMIC) - slot = kmalloc_node(size, pool->gfp, cpu_to_node(i)); - else + slot = NULL; + + if ((pool->gfp & (GFP_ATOMIC | GFP_KERNEL)) != GFP_ATOMIC) slot = __vmalloc_node(size, sizeof(void *), pool->gfp, cpu_to_node(i), __builtin_return_address(0)); - if (!slot) - return -ENOMEM; + + if (!slot) { + slot = kmalloc_node(size, pool->gfp, cpu_to_node(i)); + if (!slot) + return -ENOMEM; + } memset(slot, 0, size); pool->cpu_slots[i] = slot; @@ -103,7 +109,7 @@ static void objpool_fini_percpu_slots(struct objpool_head *pool) if (!pool->cpu_slots) return; - for (i = 0; i < pool->nr_cpus; i++) + for (i = 0; i < nr_cpu_ids; i++) kvfree(pool->cpu_slots[i]); kfree(pool->cpu_slots); } @@ -130,13 +136,13 @@ int objpool_init(struct objpool_head *pool, int nr_objs, int object_size, /* initialize objpool pool */ memset(pool, 0, sizeof(struct objpool_head)); - pool->nr_cpus = nr_cpu_ids; + pool->nr_possible_cpus = num_possible_cpus(); pool->obj_size = object_size; pool->capacity = capacity; pool->gfp = gfp & ~__GFP_ZERO; pool->context = context; pool->release = release; - slot_size = pool->nr_cpus * sizeof(struct objpool_slot); + slot_size = nr_cpu_ids * sizeof(struct objpool_slot); pool->cpu_slots = kzalloc(slot_size, pool->gfp); if (!pool->cpu_slots) return -ENOMEM; @@ -152,106 +158,6 @@ int objpool_init(struct objpool_head *pool, int nr_objs, int object_size, } EXPORT_SYMBOL_GPL(objpool_init); -/* adding object to slot, abort if the slot was already full */ -static inline int -objpool_try_add_slot(void *obj, struct objpool_head *pool, int cpu) -{ - struct objpool_slot *slot = pool->cpu_slots[cpu]; - uint32_t head, tail; - - /* loading tail and head as a local snapshot, tail first */ - tail = READ_ONCE(slot->tail); - - do { - head = READ_ONCE(slot->head); - /* fault caught: something must be wrong */ - WARN_ON_ONCE(tail - head > pool->nr_objs); - } while (!try_cmpxchg_acquire(&slot->tail, &tail, tail + 1)); - - /* now the tail position is reserved for the given obj */ - WRITE_ONCE(slot->entries[tail & slot->mask], obj); - /* update sequence to make this obj available for pop() */ - smp_store_release(&slot->last, tail + 1); - - return 0; -} - -/* reclaim an object to object pool */ -int objpool_push(void *obj, struct objpool_head *pool) -{ - unsigned long flags; - int rc; - - /* disable local irq to avoid preemption & interruption */ - raw_local_irq_save(flags); - rc = objpool_try_add_slot(obj, pool, raw_smp_processor_id()); - raw_local_irq_restore(flags); - - return rc; -} -EXPORT_SYMBOL_GPL(objpool_push); - -/* try to retrieve object from slot */ -static inline void *objpool_try_get_slot(struct objpool_head *pool, int cpu) -{ - struct objpool_slot *slot = pool->cpu_slots[cpu]; - /* load head snapshot, other cpus may change it */ - uint32_t head = smp_load_acquire(&slot->head); - - while (head != READ_ONCE(slot->last)) { - void *obj; - - /* - * data visibility of 'last' and 'head' could be out of - * order since memory updating of 'last' and 'head' are - * performed in push() and pop() independently - * - * before any retrieving attempts, pop() must guarantee - * 'last' is behind 'head', that is to say, there must - * be available objects in slot, which could be ensured - * by condition 'last != head && last - head <= nr_objs' - * that is equivalent to 'last - head - 1 < nr_objs' as - * 'last' and 'head' are both unsigned int32 - */ - if (READ_ONCE(slot->last) - head - 1 >= pool->nr_objs) { - head = READ_ONCE(slot->head); - continue; - } - - /* obj must be retrieved before moving forward head */ - obj = READ_ONCE(slot->entries[head & slot->mask]); - - /* move head forward to mark it's consumption */ - if (try_cmpxchg_release(&slot->head, &head, head + 1)) - return obj; - } - - return NULL; -} - -/* allocate an object from object pool */ -void *objpool_pop(struct objpool_head *pool) -{ - void *obj = NULL; - unsigned long flags; - int i, cpu; - - /* disable local irq to avoid preemption & interruption */ - raw_local_irq_save(flags); - - cpu = raw_smp_processor_id(); - for (i = 0; i < num_possible_cpus(); i++) { - obj = objpool_try_get_slot(pool, cpu); - if (obj) - break; - cpu = cpumask_next_wrap(cpu, cpu_possible_mask, -1, 1); - } - raw_local_irq_restore(flags); - - return obj; -} -EXPORT_SYMBOL_GPL(objpool_pop); - /* release whole objpool forcely */ void objpool_free(struct objpool_head *pool) { diff --git a/lib/overflow_kunit.c b/lib/overflow_kunit.c index 4ef31b0bb74d..5222c6393f11 100644 --- a/lib/overflow_kunit.c +++ b/lib/overflow_kunit.c @@ -668,7 +668,6 @@ DEFINE_TEST_ALLOC(devm_kzalloc, devm_kfree, 1, 1, 0); static void overflow_allocation_test(struct kunit *test) { - const char device_name[] = "overflow-test"; struct device *dev; int count = 0; @@ -678,7 +677,7 @@ static void overflow_allocation_test(struct kunit *test) } while (0) /* Create dummy device for devm_kmalloc()-family tests. */ - dev = kunit_device_register(test, device_name); + dev = kunit_device_register(test, "overflow-test"); KUNIT_ASSERT_FALSE_MSG(test, IS_ERR(dev), "Cannot register test device\n"); @@ -1178,14 +1177,28 @@ struct foo { s16 array[] __counted_by(counter); }; +struct bar { + int a; + u32 counter; + s16 array[]; +}; + static void DEFINE_FLEX_test(struct kunit *test) { - DEFINE_RAW_FLEX(struct foo, two, array, 2); + /* Using _RAW_ on a __counted_by struct will initialize "counter" to zero */ + DEFINE_RAW_FLEX(struct foo, two_but_zero, array, 2); +#ifdef CONFIG_CC_HAS_COUNTED_BY + int expected_raw_size = sizeof(struct foo); +#else + int expected_raw_size = sizeof(struct foo) + 2 * sizeof(s16); +#endif + /* Without annotation, it will always be on-stack size. */ + DEFINE_RAW_FLEX(struct bar, two, array, 2); DEFINE_FLEX(struct foo, eight, array, counter, 8); DEFINE_FLEX(struct foo, empty, array, counter, 0); - KUNIT_EXPECT_EQ(test, __struct_size(two), - sizeof(struct foo) + sizeof(s16) + sizeof(s16)); + KUNIT_EXPECT_EQ(test, __struct_size(two_but_zero), expected_raw_size); + KUNIT_EXPECT_EQ(test, __struct_size(two), sizeof(struct bar) + 2 * sizeof(s16)); KUNIT_EXPECT_EQ(test, __struct_size(eight), 24); KUNIT_EXPECT_EQ(test, __struct_size(empty), sizeof(struct foo)); } @@ -1223,4 +1236,5 @@ static struct kunit_suite overflow_test_suite = { kunit_test_suite(overflow_test_suite); +MODULE_DESCRIPTION("Test cases for arithmetic overflow checks"); MODULE_LICENSE("Dual MIT/GPL"); diff --git a/lib/packing.c b/lib/packing.c index 3f656167c17e..bb1643d9e64d 100644 --- a/lib/packing.c +++ b/lib/packing.c @@ -5,56 +5,163 @@ #include <linux/packing.h> #include <linux/module.h> #include <linux/bitops.h> +#include <linux/bits.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/bitrev.h> -static int get_le_offset(int offset) -{ - int closest_multiple_of_4; +#define __pack_fields(pbuf, pbuflen, ustruct, fields, num_fields, quirks) \ + ({ \ + for (size_t i = 0; i < (num_fields); i++) { \ + typeof(&(fields)[0]) field = &(fields)[i]; \ + u64 uval; \ + \ + uval = ustruct_field_to_u64(ustruct, field->offset, field->size); \ + \ + __pack(pbuf, uval, field->startbit, field->endbit, \ + pbuflen, quirks); \ + } \ + }) - closest_multiple_of_4 = (offset / 4) * 4; - offset -= closest_multiple_of_4; - return closest_multiple_of_4 + (3 - offset); -} +#define __unpack_fields(pbuf, pbuflen, ustruct, fields, num_fields, quirks) \ + ({ \ + for (size_t i = 0; i < (num_fields); i++) { \ + typeof(&(fields)[0]) field = &fields[i]; \ + u64 uval; \ + \ + __unpack(pbuf, &uval, field->startbit, field->endbit, \ + pbuflen, quirks); \ + \ + u64_to_ustruct_field(ustruct, field->offset, field->size, uval); \ + } \ + }) -static int get_reverse_lsw32_offset(int offset, size_t len) +/** + * calculate_box_addr - Determine physical location of byte in buffer + * @box: Index of byte within buffer seen as a logical big-endian big number + * @len: Size of buffer in bytes + * @quirks: mask of QUIRK_LSW32_IS_FIRST and QUIRK_LITTLE_ENDIAN + * + * Function interprets the buffer as a @len byte sized big number, and returns + * the physical offset of the @box logical octet within it. Internally, it + * treats the big number as groups of 4 bytes. If @len is not a multiple of 4, + * the last group may be shorter. + * + * @QUIRK_LSW32_IS_FIRST gives the ordering of groups of 4 octets relative to + * each other. If set, the most significant group of 4 octets is last in the + * buffer (and may be truncated if @len is not a multiple of 4). + * + * @QUIRK_LITTLE_ENDIAN gives the ordering of bytes within each group of 4. + * If set, the most significant byte is last in the group. If @len takes the + * form of 4k+3, the last group will only be able to represent 24 bits, and its + * most significant octet is byte 2. + * + * Return: the physical offset into the buffer corresponding to the logical box. + */ +static size_t calculate_box_addr(size_t box, size_t len, u8 quirks) { - int closest_multiple_of_4; - int word_index; - - word_index = offset / 4; - closest_multiple_of_4 = word_index * 4; - offset -= closest_multiple_of_4; - word_index = (len / 4) - word_index - 1; - return word_index * 4 + offset; + size_t offset_of_group, offset_in_group, this_group = box / 4; + size_t group_size; + + if (quirks & QUIRK_LSW32_IS_FIRST) + offset_of_group = this_group * 4; + else + offset_of_group = len - ((this_group + 1) * 4); + + group_size = min(4, len - offset_of_group); + + if (quirks & QUIRK_LITTLE_ENDIAN) + offset_in_group = box - this_group * 4; + else + offset_in_group = group_size - (box - this_group * 4) - 1; + + return offset_of_group + offset_in_group; } -static void adjust_for_msb_right_quirk(u64 *to_write, int *box_start_bit, - int *box_end_bit, u8 *box_mask) +static void __pack(void *pbuf, u64 uval, size_t startbit, size_t endbit, + size_t pbuflen, u8 quirks) { - int box_bit_width = *box_start_bit - *box_end_bit + 1; - int new_box_start_bit, new_box_end_bit; - - *to_write >>= *box_end_bit; - *to_write = bitrev8(*to_write) >> (8 - box_bit_width); - *to_write <<= *box_end_bit; - - new_box_end_bit = box_bit_width - *box_start_bit - 1; - new_box_start_bit = box_bit_width - *box_end_bit - 1; - *box_mask = GENMASK_ULL(new_box_start_bit, new_box_end_bit); - *box_start_bit = new_box_start_bit; - *box_end_bit = new_box_end_bit; + /* Logical byte indices corresponding to the + * start and end of the field. + */ + int plogical_first_u8 = startbit / BITS_PER_BYTE; + int plogical_last_u8 = endbit / BITS_PER_BYTE; + int value_width = startbit - endbit + 1; + int box; + + /* Check if "uval" fits in "value_width" bits. + * The test only works for value_width < 64, but in the latter case, + * any 64-bit uval will surely fit. + */ + WARN(value_width < 64 && uval >= (1ull << value_width), + "Cannot store 0x%llx inside bits %zu-%zu - will truncate\n", + uval, startbit, endbit); + + /* Iterate through an idealistic view of the pbuf as an u64 with + * no quirks, u8 by u8 (aligned at u8 boundaries), from high to low + * logical bit significance. "box" denotes the current logical u8. + */ + for (box = plogical_first_u8; box >= plogical_last_u8; box--) { + /* Bit indices into the currently accessed 8-bit box */ + size_t box_start_bit, box_end_bit, box_addr; + u8 box_mask; + /* Corresponding bits from the unpacked u64 parameter */ + size_t proj_start_bit, proj_end_bit; + u64 proj_mask; + u64 pval; + + /* This u8 may need to be accessed in its entirety + * (from bit 7 to bit 0), or not, depending on the + * input arguments startbit and endbit. + */ + if (box == plogical_first_u8) + box_start_bit = startbit % BITS_PER_BYTE; + else + box_start_bit = 7; + if (box == plogical_last_u8) + box_end_bit = endbit % BITS_PER_BYTE; + else + box_end_bit = 0; + + /* We have determined the box bit start and end. + * Now we calculate where this (masked) u8 box would fit + * in the unpacked (CPU-readable) u64 - the u8 box's + * projection onto the unpacked u64. Though the + * box is u8, the projection is u64 because it may fall + * anywhere within the unpacked u64. + */ + proj_start_bit = ((box * BITS_PER_BYTE) + box_start_bit) - endbit; + proj_end_bit = ((box * BITS_PER_BYTE) + box_end_bit) - endbit; + proj_mask = GENMASK_ULL(proj_start_bit, proj_end_bit); + box_mask = GENMASK(box_start_bit, box_end_bit); + + /* Determine the offset of the u8 box inside the pbuf, + * adjusted for quirks. The adjusted box_addr will be used for + * effective addressing inside the pbuf (so it's not + * logical any longer). + */ + box_addr = calculate_box_addr(box, pbuflen, quirks); + + /* Write to pbuf, read from uval */ + pval = uval & proj_mask; + pval >>= proj_end_bit; + pval <<= box_end_bit; + + if (quirks & QUIRK_MSB_ON_THE_RIGHT) { + pval = bitrev8(pval); + box_mask = bitrev8(box_mask); + } + + ((u8 *)pbuf)[box_addr] &= ~box_mask; + ((u8 *)pbuf)[box_addr] |= pval; + } } /** - * packing - Convert numbers (currently u64) between a packed and an unpacked - * format. Unpacked means laid out in memory in the CPU's native - * understanding of integers, while packed means anything else that - * requires translation. + * pack - Pack u64 number into bitfield of buffer. * * @pbuf: Pointer to a buffer holding the packed value. - * @uval: Pointer to an u64 holding the unpacked value. + * @uval: CPU-readable unpacked value to pack. * @startbit: The index (in logical notation, compensated for quirks) where * the packed value starts within pbuf. Must be larger than, or * equal to, endbit. @@ -62,79 +169,68 @@ static void adjust_for_msb_right_quirk(u64 *to_write, int *box_start_bit, * the packed value ends within pbuf. Must be smaller than, or equal * to, startbit. * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf. - * @op: If PACK, then uval will be treated as const pointer and copied (packed) - * into pbuf, between startbit and endbit. - * If UNPACK, then pbuf will be treated as const pointer and the logical - * value between startbit and endbit will be copied (unpacked) to uval. * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and * QUIRK_MSB_ON_THE_RIGHT. * * Return: 0 on success, EINVAL or ERANGE if called incorrectly. Assuming - * correct usage, return code may be discarded. - * If op is PACK, pbuf is modified. - * If op is UNPACK, uval is modified. + * correct usage, return code may be discarded. The @pbuf memory will + * be modified on success. */ -int packing(void *pbuf, u64 *uval, int startbit, int endbit, size_t pbuflen, - enum packing_op op, u8 quirks) +int pack(void *pbuf, u64 uval, size_t startbit, size_t endbit, size_t pbuflen, + u8 quirks) { - /* Number of bits for storing "uval" - * also width of the field to access in the pbuf + /* startbit is expected to be larger than endbit, and both are + * expected to be within the logically addressable range of the buffer. */ - u64 value_width; - /* Logical byte indices corresponding to the - * start and end of the field. - */ - int plogical_first_u8, plogical_last_u8, box; - - /* startbit is expected to be larger than endbit */ - if (startbit < endbit) + if (unlikely(startbit < endbit || startbit >= BITS_PER_BYTE * pbuflen)) /* Invalid function call */ return -EINVAL; - value_width = startbit - endbit + 1; - if (value_width > 64) + if (unlikely(startbit - endbit >= 64)) return -ERANGE; - /* Check if "uval" fits in "value_width" bits. - * If value_width is 64, the check will fail, but any - * 64-bit uval will surely fit. + __pack(pbuf, uval, startbit, endbit, pbuflen, quirks); + + return 0; +} +EXPORT_SYMBOL(pack); + +static void __unpack(const void *pbuf, u64 *uval, size_t startbit, size_t endbit, + size_t pbuflen, u8 quirks) +{ + /* Logical byte indices corresponding to the + * start and end of the field. */ - if (op == PACK && value_width < 64 && (*uval >= (1ull << value_width))) - /* Cannot store "uval" inside "value_width" bits. - * Truncating "uval" is most certainly not desirable, - * so simply erroring out is appropriate. - */ - return -ERANGE; + int plogical_first_u8 = startbit / BITS_PER_BYTE; + int plogical_last_u8 = endbit / BITS_PER_BYTE; + int box; /* Initialize parameter */ - if (op == UNPACK) - *uval = 0; + *uval = 0; /* Iterate through an idealistic view of the pbuf as an u64 with * no quirks, u8 by u8 (aligned at u8 boundaries), from high to low * logical bit significance. "box" denotes the current logical u8. */ - plogical_first_u8 = startbit / 8; - plogical_last_u8 = endbit / 8; - for (box = plogical_first_u8; box >= plogical_last_u8; box--) { /* Bit indices into the currently accessed 8-bit box */ - int box_start_bit, box_end_bit, box_addr; + size_t box_start_bit, box_end_bit, box_addr; u8 box_mask; /* Corresponding bits from the unpacked u64 parameter */ - int proj_start_bit, proj_end_bit; + size_t proj_start_bit, proj_end_bit; u64 proj_mask; + u64 pval; /* This u8 may need to be accessed in its entirety * (from bit 7 to bit 0), or not, depending on the * input arguments startbit and endbit. */ if (box == plogical_first_u8) - box_start_bit = startbit % 8; + box_start_bit = startbit % BITS_PER_BYTE; else box_start_bit = 7; if (box == plogical_last_u8) - box_end_bit = endbit % 8; + box_end_bit = endbit % BITS_PER_BYTE; else box_end_bit = 0; @@ -145,57 +241,238 @@ int packing(void *pbuf, u64 *uval, int startbit, int endbit, size_t pbuflen, * box is u8, the projection is u64 because it may fall * anywhere within the unpacked u64. */ - proj_start_bit = ((box * 8) + box_start_bit) - endbit; - proj_end_bit = ((box * 8) + box_end_bit) - endbit; + proj_start_bit = ((box * BITS_PER_BYTE) + box_start_bit) - endbit; + proj_end_bit = ((box * BITS_PER_BYTE) + box_end_bit) - endbit; proj_mask = GENMASK_ULL(proj_start_bit, proj_end_bit); - box_mask = GENMASK_ULL(box_start_bit, box_end_bit); + box_mask = GENMASK(box_start_bit, box_end_bit); /* Determine the offset of the u8 box inside the pbuf, * adjusted for quirks. The adjusted box_addr will be used for * effective addressing inside the pbuf (so it's not * logical any longer). */ - box_addr = pbuflen - box - 1; - if (quirks & QUIRK_LITTLE_ENDIAN) - box_addr = get_le_offset(box_addr); - if (quirks & QUIRK_LSW32_IS_FIRST) - box_addr = get_reverse_lsw32_offset(box_addr, - pbuflen); - - if (op == UNPACK) { - u64 pval; - - /* Read from pbuf, write to uval */ - pval = ((u8 *)pbuf)[box_addr] & box_mask; - if (quirks & QUIRK_MSB_ON_THE_RIGHT) - adjust_for_msb_right_quirk(&pval, - &box_start_bit, - &box_end_bit, - &box_mask); - - pval >>= box_end_bit; - pval <<= proj_end_bit; - *uval &= ~proj_mask; - *uval |= pval; - } else { - u64 pval; - - /* Write to pbuf, read from uval */ - pval = (*uval) & proj_mask; - pval >>= proj_end_bit; - if (quirks & QUIRK_MSB_ON_THE_RIGHT) - adjust_for_msb_right_quirk(&pval, - &box_start_bit, - &box_end_bit, - &box_mask); - - pval <<= box_end_bit; - ((u8 *)pbuf)[box_addr] &= ~box_mask; - ((u8 *)pbuf)[box_addr] |= pval; - } + box_addr = calculate_box_addr(box, pbuflen, quirks); + + /* Read from pbuf, write to uval */ + pval = ((u8 *)pbuf)[box_addr]; + + if (quirks & QUIRK_MSB_ON_THE_RIGHT) + pval = bitrev8(pval); + + pval &= box_mask; + + pval >>= box_end_bit; + pval <<= proj_end_bit; + *uval &= ~proj_mask; + *uval |= pval; } +} + +/** + * unpack - Unpack u64 number from packed buffer. + * + * @pbuf: Pointer to a buffer holding the packed value. + * @uval: Pointer to an u64 holding the unpacked value. + * @startbit: The index (in logical notation, compensated for quirks) where + * the packed value starts within pbuf. Must be larger than, or + * equal to, endbit. + * @endbit: The index (in logical notation, compensated for quirks) where + * the packed value ends within pbuf. Must be smaller than, or equal + * to, startbit. + * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf. + * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and + * QUIRK_MSB_ON_THE_RIGHT. + * + * Return: 0 on success, EINVAL or ERANGE if called incorrectly. Assuming + * correct usage, return code may be discarded. The @uval will be + * modified on success. + */ +int unpack(const void *pbuf, u64 *uval, size_t startbit, size_t endbit, + size_t pbuflen, u8 quirks) +{ + /* width of the field to access in the pbuf */ + u64 value_width; + + /* startbit is expected to be larger than endbit, and both are + * expected to be within the logically addressable range of the buffer. + */ + if (startbit < endbit || startbit >= BITS_PER_BYTE * pbuflen) + /* Invalid function call */ + return -EINVAL; + + value_width = startbit - endbit + 1; + if (value_width > 64) + return -ERANGE; + + __unpack(pbuf, uval, startbit, endbit, pbuflen, quirks); + return 0; } +EXPORT_SYMBOL(unpack); + +/** + * packing - Convert numbers (currently u64) between a packed and an unpacked + * format. Unpacked means laid out in memory in the CPU's native + * understanding of integers, while packed means anything else that + * requires translation. + * + * @pbuf: Pointer to a buffer holding the packed value. + * @uval: Pointer to an u64 holding the unpacked value. + * @startbit: The index (in logical notation, compensated for quirks) where + * the packed value starts within pbuf. Must be larger than, or + * equal to, endbit. + * @endbit: The index (in logical notation, compensated for quirks) where + * the packed value ends within pbuf. Must be smaller than, or equal + * to, startbit. + * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf. + * @op: If PACK, then uval will be treated as const pointer and copied (packed) + * into pbuf, between startbit and endbit. + * If UNPACK, then pbuf will be treated as const pointer and the logical + * value between startbit and endbit will be copied (unpacked) to uval. + * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and + * QUIRK_MSB_ON_THE_RIGHT. + * + * Note: this is deprecated, prefer to use pack() or unpack() in new code. + * + * Return: 0 on success, EINVAL or ERANGE if called incorrectly. Assuming + * correct usage, return code may be discarded. + * If op is PACK, pbuf is modified. + * If op is UNPACK, uval is modified. + */ +int packing(void *pbuf, u64 *uval, int startbit, int endbit, size_t pbuflen, + enum packing_op op, u8 quirks) +{ + if (op == PACK) + return pack(pbuf, *uval, startbit, endbit, pbuflen, quirks); + + return unpack(pbuf, uval, startbit, endbit, pbuflen, quirks); +} EXPORT_SYMBOL(packing); +static u64 ustruct_field_to_u64(const void *ustruct, size_t field_offset, + size_t field_size) +{ + switch (field_size) { + case 1: + return *((u8 *)(ustruct + field_offset)); + case 2: + return *((u16 *)(ustruct + field_offset)); + case 4: + return *((u32 *)(ustruct + field_offset)); + default: + return *((u64 *)(ustruct + field_offset)); + } +} + +static void u64_to_ustruct_field(void *ustruct, size_t field_offset, + size_t field_size, u64 uval) +{ + switch (field_size) { + case 1: + *((u8 *)(ustruct + field_offset)) = uval; + break; + case 2: + *((u16 *)(ustruct + field_offset)) = uval; + break; + case 4: + *((u32 *)(ustruct + field_offset)) = uval; + break; + default: + *((u64 *)(ustruct + field_offset)) = uval; + break; + } +} + +/** + * pack_fields_u8 - Pack array of fields + * + * @pbuf: Pointer to a buffer holding the packed value. + * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf. + * @ustruct: Pointer to CPU-readable structure holding the unpacked value. + * It is expected (but not checked) that this has the same data type + * as all struct packed_field_u8 definitions. + * @fields: Array of packed_field_u8 field definition. They must not overlap. + * @num_fields: Length of @fields array. + * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and + * QUIRK_MSB_ON_THE_RIGHT. + * + * Use the pack_fields() macro instead of calling this directly. + */ +void pack_fields_u8(void *pbuf, size_t pbuflen, const void *ustruct, + const struct packed_field_u8 *fields, size_t num_fields, + u8 quirks) +{ + __pack_fields(pbuf, pbuflen, ustruct, fields, num_fields, quirks); +} +EXPORT_SYMBOL(pack_fields_u8); + +/** + * pack_fields_u16 - Pack array of fields + * + * @pbuf: Pointer to a buffer holding the packed value. + * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf. + * @ustruct: Pointer to CPU-readable structure holding the unpacked value. + * It is expected (but not checked) that this has the same data type + * as all struct packed_field_u16 definitions. + * @fields: Array of packed_field_u16 field definitions. They must not overlap. + * @num_fields: Length of @fields array. + * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and + * QUIRK_MSB_ON_THE_RIGHT. + * + * Use the pack_fields() macro instead of calling this directly. + */ +void pack_fields_u16(void *pbuf, size_t pbuflen, const void *ustruct, + const struct packed_field_u16 *fields, size_t num_fields, + u8 quirks) +{ + __pack_fields(pbuf, pbuflen, ustruct, fields, num_fields, quirks); +} +EXPORT_SYMBOL(pack_fields_u16); + +/** + * unpack_fields_u8 - Unpack array of fields + * + * @pbuf: Pointer to a buffer holding the packed value. + * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf. + * @ustruct: Pointer to CPU-readable structure holding the unpacked value. + * It is expected (but not checked) that this has the same data type + * as all struct packed_field_u8 definitions. + * @fields: Array of packed_field_u8 field definitions. They must not overlap. + * @num_fields: Length of @fields array. + * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and + * QUIRK_MSB_ON_THE_RIGHT. + * + * Use the unpack_fields() macro instead of calling this directly. + */ +void unpack_fields_u8(const void *pbuf, size_t pbuflen, void *ustruct, + const struct packed_field_u8 *fields, size_t num_fields, + u8 quirks) +{ + __unpack_fields(pbuf, pbuflen, ustruct, fields, num_fields, quirks); +} +EXPORT_SYMBOL(unpack_fields_u8); + +/** + * unpack_fields_u16 - Unpack array of fields + * + * @pbuf: Pointer to a buffer holding the packed value. + * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf. + * @ustruct: Pointer to CPU-readable structure holding the unpacked value. + * It is expected (but not checked) that this has the same data type + * as all struct packed_field_u16 definitions. + * @fields: Array of packed_field_u16 field definitions. They must not overlap. + * @num_fields: Length of @fields array. + * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and + * QUIRK_MSB_ON_THE_RIGHT. + * + * Use the unpack_fields() macro instead of calling this directly. + */ +void unpack_fields_u16(const void *pbuf, size_t pbuflen, void *ustruct, + const struct packed_field_u16 *fields, size_t num_fields, + u8 quirks) +{ + __unpack_fields(pbuf, pbuflen, ustruct, fields, num_fields, quirks); +} +EXPORT_SYMBOL(unpack_fields_u16); + MODULE_DESCRIPTION("Generic bitfield packing and unpacking"); diff --git a/lib/packing_test.c b/lib/packing_test.c new file mode 100644 index 000000000000..ce3b83d33b04 --- /dev/null +++ b/lib/packing_test.c @@ -0,0 +1,474 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024, Vladimir Oltean <olteanv@gmail.com> + * Copyright (c) 2024, Intel Corporation. + */ +#include <kunit/test.h> +#include <linux/packing.h> + +struct packing_test_case { + const char *desc; + const u8 *pbuf; + size_t pbuf_size; + u64 uval; + size_t start_bit; + size_t end_bit; + u8 quirks; +}; + +#define NO_QUIRKS 0 + +/** + * PBUF - Initialize .pbuf and .pbuf_size + * @array: elements of constant physical buffer + * + * Initializes the .pbuf and .pbuf_size fields of a struct packing_test_case + * with a constant array of the specified elements. + */ +#define PBUF(array...) \ + .pbuf = (const u8[]){ array }, \ + .pbuf_size = sizeof((const u8 []){ array }) + +static const struct packing_test_case cases[] = { + /* These tests pack and unpack a magic 64-bit value + * (0xcafedeadbeefcafe) at a fixed logical offset (32) within an + * otherwise zero array of 128 bits (16 bytes). They test all possible + * bit layouts of the 128 bit buffer. + */ + { + .desc = "no quirks, 16 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0xca, 0xfe, 0xde, 0xad, + 0xbe, 0xef, 0xca, 0xfe, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = NO_QUIRKS, + }, + { + .desc = "lsw32 first, 16 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0xbe, 0xef, 0xca, 0xfe, + 0xca, 0xfe, 0xde, 0xad, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_LSW32_IS_FIRST, + }, + { + .desc = "little endian words, 16 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0xad, 0xde, 0xfe, 0xca, + 0xfe, 0xca, 0xef, 0xbe, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "lsw32 first + little endian words, 16 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0xfe, 0xca, 0xef, 0xbe, + 0xad, 0xde, 0xfe, 0xca, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "msb right, 16 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0x53, 0x7f, 0x7b, 0xb5, + 0x7d, 0xf7, 0x53, 0x7f, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_MSB_ON_THE_RIGHT, + }, + { + .desc = "msb right + lsw32 first, 16 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0x7d, 0xf7, 0x53, 0x7f, + 0x53, 0x7f, 0x7b, 0xb5, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LSW32_IS_FIRST, + }, + { + .desc = "msb right + little endian words, 16 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0xb5, 0x7b, 0x7f, 0x53, + 0x7f, 0x53, 0xf7, 0x7d, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "msb right + lsw32 first + little endian words, 16 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0x7f, 0x53, 0xf7, 0x7d, + 0xb5, 0x7b, 0x7f, 0x53, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, + /* These tests pack and unpack a magic 64-bit value + * (0xcafedeadbeefcafe) at a fixed logical offset (32) within an + * otherwise zero array of varying size from 18 bytes to 24 bytes. + */ + { + .desc = "no quirks, 18 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xca, 0xfe, + 0xde, 0xad, 0xbe, 0xef, 0xca, 0xfe, 0x00, 0x00, + 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = NO_QUIRKS, + }, + { + .desc = "no quirks, 19 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xca, + 0xfe, 0xde, 0xad, 0xbe, 0xef, 0xca, 0xfe, 0x00, + 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = NO_QUIRKS, + }, + { + .desc = "no quirks, 20 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0xca, 0xfe, 0xde, 0xad, 0xbe, 0xef, 0xca, 0xfe, + 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = NO_QUIRKS, + }, + { + .desc = "no quirks, 22 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0xca, 0xfe, 0xde, 0xad, 0xbe, 0xef, + 0xca, 0xfe, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = NO_QUIRKS, + }, + { + .desc = "no quirks, 24 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0xca, 0xfe, 0xde, 0xad, + 0xbe, 0xef, 0xca, 0xfe, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = NO_QUIRKS, + }, + { + .desc = "lsw32 first + little endian words, 18 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0xfe, 0xca, 0xef, 0xbe, + 0xad, 0xde, 0xfe, 0xca, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "lsw32 first + little endian words, 19 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0xfe, 0xca, 0xef, 0xbe, + 0xad, 0xde, 0xfe, 0xca, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "lsw32 first + little endian words, 20 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0xfe, 0xca, 0xef, 0xbe, + 0xad, 0xde, 0xfe, 0xca, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "lsw32 first + little endian words, 22 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0xfe, 0xca, 0xef, 0xbe, + 0xad, 0xde, 0xfe, 0xca, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "lsw32 first + little endian words, 24 bytes", + PBUF(0x00, 0x00, 0x00, 0x00, 0xfe, 0xca, 0xef, 0xbe, + 0xad, 0xde, 0xfe, 0xca, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00), + .uval = 0xcafedeadbeefcafe, + .start_bit = 95, + .end_bit = 32, + .quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, + /* These tests pack and unpack a magic 64-bit value + * (0x1122334455667788) at an odd starting bit (43) within an + * otherwise zero array of 128 bits (16 bytes). They test all possible + * bit layouts of the 128 bit buffer. + */ + { + .desc = "no quirks, 16 bytes, non-aligned", + PBUF(0x00, 0x00, 0x00, 0x89, 0x11, 0x9a, 0x22, 0xab, + 0x33, 0xbc, 0x40, 0x00, 0x00, 0x00, 0x00, 0x00), + .uval = 0x1122334455667788, + .start_bit = 106, + .end_bit = 43, + .quirks = NO_QUIRKS, + }, + { + .desc = "lsw32 first, 16 bytes, non-aligned", + PBUF(0x00, 0x00, 0x00, 0x00, 0x33, 0xbc, 0x40, 0x00, + 0x11, 0x9a, 0x22, 0xab, 0x00, 0x00, 0x00, 0x89), + .uval = 0x1122334455667788, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_LSW32_IS_FIRST, + }, + { + .desc = "little endian words, 16 bytes, non-aligned", + PBUF(0x89, 0x00, 0x00, 0x00, 0xab, 0x22, 0x9a, 0x11, + 0x00, 0x40, 0xbc, 0x33, 0x00, 0x00, 0x00, 0x00), + .uval = 0x1122334455667788, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "lsw32 first + little endian words, 16 bytes, non-aligned", + PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x40, 0xbc, 0x33, + 0xab, 0x22, 0x9a, 0x11, 0x89, 0x00, 0x00, 0x00), + .uval = 0x1122334455667788, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "msb right, 16 bytes, non-aligned", + PBUF(0x00, 0x00, 0x00, 0x91, 0x88, 0x59, 0x44, 0xd5, + 0xcc, 0x3d, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00), + .uval = 0x1122334455667788, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_MSB_ON_THE_RIGHT, + }, + { + .desc = "msb right + lsw32 first, 16 bytes, non-aligned", + PBUF(0x00, 0x00, 0x00, 0x00, 0xcc, 0x3d, 0x02, 0x00, + 0x88, 0x59, 0x44, 0xd5, 0x00, 0x00, 0x00, 0x91), + .uval = 0x1122334455667788, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LSW32_IS_FIRST, + }, + { + .desc = "msb right + little endian words, 16 bytes, non-aligned", + PBUF(0x91, 0x00, 0x00, 0x00, 0xd5, 0x44, 0x59, 0x88, + 0x00, 0x02, 0x3d, 0xcc, 0x00, 0x00, 0x00, 0x00), + .uval = 0x1122334455667788, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "msb right + lsw32 first + little endian words, 16 bytes, non-aligned", + PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x02, 0x3d, 0xcc, + 0xd5, 0x44, 0x59, 0x88, 0x91, 0x00, 0x00, 0x00), + .uval = 0x1122334455667788, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, + /* These tests pack and unpack a u64 with all bits set + * (0xffffffffffffffff) at an odd starting bit (43) within an + * otherwise zero array of 128 bits (16 bytes). They test all possible + * bit layouts of the 128 bit buffer. + */ + { + .desc = "no quirks, 16 bytes, non-aligned, 0xff", + PBUF(0x00, 0x00, 0x07, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0xf8, 0x00, 0x00, 0x00, 0x00, 0x00), + .uval = 0xffffffffffffffff, + .start_bit = 106, + .end_bit = 43, + .quirks = NO_QUIRKS, + }, + { + .desc = "lsw32 first, 16 bytes, non-aligned, 0xff", + PBUF(0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xf8, 0x00, + 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x07, 0xff), + .uval = 0xffffffffffffffff, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_LSW32_IS_FIRST, + }, + { + .desc = "little endian words, 16 bytes, non-aligned, 0xff", + PBUF(0xff, 0x07, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, + 0x00, 0xf8, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00), + .uval = 0xffffffffffffffff, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "lsw32 first + little endian words, 16 bytes, non-aligned, 0xff", + PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0xf8, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0x07, 0x00, 0x00), + .uval = 0xffffffffffffffff, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "msb right, 16 bytes, non-aligned, 0xff", + PBUF(0x00, 0x00, 0xe0, 0xff, 0xff, 0xff, 0xff, 0xff, + 0xff, 0xff, 0x1f, 0x00, 0x00, 0x00, 0x00, 0x00), + .uval = 0xffffffffffffffff, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_MSB_ON_THE_RIGHT, + }, + { + .desc = "msb right + lsw32 first, 16 bytes, non-aligned, 0xff", + PBUF(0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0x1f, 0x00, + 0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0xe0, 0xff), + .uval = 0xffffffffffffffff, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LSW32_IS_FIRST, + }, + { + .desc = "msb right + little endian words, 16 bytes, non-aligned, 0xff", + PBUF(0xff, 0xe0, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff, + 0x00, 0x1f, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00), + .uval = 0xffffffffffffffff, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LITTLE_ENDIAN, + }, + { + .desc = "msb right + lsw32 first + little endian words, 16 bytes, non-aligned, 0xff", + PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x1f, 0xff, 0xff, + 0xff, 0xff, 0xff, 0xff, 0xff, 0xe0, 0x00, 0x00), + .uval = 0xffffffffffffffff, + .start_bit = 106, + .end_bit = 43, + .quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN, + }, +}; + +KUNIT_ARRAY_PARAM_DESC(packing, cases, desc); + +static void packing_test_pack(struct kunit *test) +{ + const struct packing_test_case *params = test->param_value; + u8 *pbuf; + int err; + + pbuf = kunit_kzalloc(test, params->pbuf_size, GFP_KERNEL); + KUNIT_ASSERT_NOT_NULL(test, pbuf); + + err = pack(pbuf, params->uval, params->start_bit, params->end_bit, + params->pbuf_size, params->quirks); + + KUNIT_EXPECT_EQ_MSG(test, err, 0, "pack() returned %pe\n", ERR_PTR(err)); + KUNIT_EXPECT_MEMEQ(test, pbuf, params->pbuf, params->pbuf_size); +} + +static void packing_test_unpack(struct kunit *test) +{ + const struct packing_test_case *params = test->param_value; + u64 uval; + int err; + + err = unpack(params->pbuf, &uval, params->start_bit, params->end_bit, + params->pbuf_size, params->quirks); + KUNIT_EXPECT_EQ_MSG(test, err, 0, "unpack() returned %pe\n", ERR_PTR(err)); + KUNIT_EXPECT_EQ(test, uval, params->uval); +} + +#define PACKED_BUF_SIZE 8 + +typedef struct __packed { u8 buf[PACKED_BUF_SIZE]; } packed_buf_t; + +struct test_data { + u32 field3; + u16 field2; + u16 field4; + u16 field6; + u8 field1; + u8 field5; +}; + +static const struct packed_field_u8 test_fields[] = { + PACKED_FIELD(63, 61, struct test_data, field1), + PACKED_FIELD(60, 52, struct test_data, field2), + PACKED_FIELD(51, 28, struct test_data, field3), + PACKED_FIELD(27, 14, struct test_data, field4), + PACKED_FIELD(13, 9, struct test_data, field5), + PACKED_FIELD(8, 0, struct test_data, field6), +}; + +static void packing_test_pack_fields(struct kunit *test) +{ + const struct test_data data = { + .field1 = 0x2, + .field2 = 0x100, + .field3 = 0xF00050, + .field4 = 0x7D3, + .field5 = 0x9, + .field6 = 0x10B, + }; + packed_buf_t expect = { + .buf = { 0x50, 0x0F, 0x00, 0x05, 0x01, 0xF4, 0xD3, 0x0B }, + }; + packed_buf_t buf = {}; + + pack_fields(&buf, sizeof(buf), &data, test_fields, 0); + + KUNIT_EXPECT_MEMEQ(test, &expect, &buf, sizeof(buf)); +} + +static void packing_test_unpack_fields(struct kunit *test) +{ + const packed_buf_t buf = { + .buf = { 0x17, 0x28, 0x10, 0x19, 0x3D, 0xA9, 0x07, 0x9C }, + }; + struct test_data data = {}; + + unpack_fields(&buf, sizeof(buf), &data, test_fields, 0); + + KUNIT_EXPECT_EQ(test, 0, data.field1); + KUNIT_EXPECT_EQ(test, 0x172, data.field2); + KUNIT_EXPECT_EQ(test, 0x810193, data.field3); + KUNIT_EXPECT_EQ(test, 0x36A4, data.field4); + KUNIT_EXPECT_EQ(test, 0x3, data.field5); + KUNIT_EXPECT_EQ(test, 0x19C, data.field6); +} + +static struct kunit_case packing_test_cases[] = { + KUNIT_CASE_PARAM(packing_test_pack, packing_gen_params), + KUNIT_CASE_PARAM(packing_test_unpack, packing_gen_params), + KUNIT_CASE(packing_test_pack_fields), + KUNIT_CASE(packing_test_unpack_fields), + {}, +}; + +static struct kunit_suite packing_test_suite = { + .name = "packing", + .test_cases = packing_test_cases, +}; + +kunit_test_suite(packing_test_suite); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("KUnit tests for packing library"); diff --git a/lib/parser.c b/lib/parser.c index f4eafb9d74e6..73e8f8e5be73 100644 --- a/lib/parser.c +++ b/lib/parser.c @@ -275,8 +275,9 @@ EXPORT_SYMBOL(match_hex); * * Description: Parse the string @str to check if matches wildcard * pattern @pattern. The pattern may contain two types of wildcards: - * '*' - matches zero or more characters - * '?' - matches one character + * + * * '*' - matches zero or more characters + * * '?' - matches one character * * Return: If the @str matches the @pattern, return true, else return false. */ diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index 44dd133594d4..2891f94a11c6 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -73,17 +73,50 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount) EXPORT_SYMBOL(percpu_counter_set); /* - * local_irq_save() is needed to make the function irq safe: - * - The slow path would be ok as protected by an irq-safe spinlock. - * - this_cpu_add would be ok as it is irq-safe by definition. - * But: - * The decision slow path/fast path and the actual update must be atomic, too. + * Add to a counter while respecting batch size. + * + * There are 2 implementations, both dealing with the following problem: + * + * The decision slow path/fast path and the actual update must be atomic. * Otherwise a call in process context could check the current values and * decide that the fast path can be used. If now an interrupt occurs before * the this_cpu_add(), and the interrupt updates this_cpu(*fbc->counters), * then the this_cpu_add() that is executed after the interrupt has completed * can produce values larger than "batch" or even overflows. */ +#ifdef CONFIG_HAVE_CMPXCHG_LOCAL +/* + * Safety against interrupts is achieved in 2 ways: + * 1. the fast path uses local cmpxchg (note: no lock prefix) + * 2. the slow path operates with interrupts disabled + */ +void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) +{ + s64 count; + unsigned long flags; + + count = this_cpu_read(*fbc->counters); + do { + if (unlikely(abs(count + amount) >= batch)) { + raw_spin_lock_irqsave(&fbc->lock, flags); + /* + * Note: by now we might have migrated to another CPU + * or the value might have changed. + */ + count = __this_cpu_read(*fbc->counters); + fbc->count += count + amount; + __this_cpu_sub(*fbc->counters, count); + raw_spin_unlock_irqrestore(&fbc->lock, flags); + return; + } + } while (!this_cpu_try_cmpxchg(*fbc->counters, &count, count + amount)); +} +#else +/* + * local_irq_save() is used to make the function irq safe: + * - The slow path would be ok as protected by an irq-safe spinlock. + * - this_cpu_add would be ok as it is irq-safe by definition. + */ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; @@ -101,6 +134,7 @@ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) } local_irq_restore(flags); } +#endif EXPORT_SYMBOL(percpu_counter_add_batch); /* @@ -175,7 +209,7 @@ int __percpu_counter_init_many(struct percpu_counter *fbc, s64 amount, INIT_LIST_HEAD(&fbc[i].list); #endif fbc[i].count = amount; - fbc[i].counters = (void *)counters + (i * counter_size); + fbc[i].counters = (void __percpu *)counters + i * counter_size; debug_percpu_counter_activate(&fbc[i]); } diff --git a/lib/percpu_test.c b/lib/percpu_test.c index 4a3d70bbc1a0..ce7124b16dab 100644 --- a/lib/percpu_test.c +++ b/lib/percpu_test.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only +#include <linux/limits.h> #include <linux/module.h> /* validate @native and @pcp counter values match @expected */ @@ -24,8 +25,9 @@ static int __init percpu_test_init(void) * +ul_one/-ul_one below would replace with inc/dec instructions. */ volatile unsigned int ui_one = 1; - long l = 0; + unsigned long long ull = 0; unsigned long ul = 0; + long l = 0; pr_info("percpu test start\n"); @@ -112,6 +114,13 @@ static int __init percpu_test_init(void) CHECK(ul, ulong_counter, -1); CHECK(ul, ulong_counter, ULONG_MAX); + ul = ull = 0; + __this_cpu_write(ulong_counter, 0); + + ul = ull += UINT_MAX; + __this_cpu_add(ulong_counter, ull); + CHECK(ul, ulong_counter, UINT_MAX); + ul = 3; __this_cpu_write(ulong_counter, 3); diff --git a/lib/pldmfw/pldmfw.c b/lib/pldmfw/pldmfw.c index 54e1809a38fd..6264e2013f25 100644 --- a/lib/pldmfw/pldmfw.c +++ b/lib/pldmfw/pldmfw.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) 2018-2019, Intel Corporation. */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/crc32.h> #include <linux/device.h> #include <linux/firmware.h> @@ -481,9 +481,17 @@ static int pldm_parse_components(struct pldmfw_priv *data) component->component_data = data->fw->data + offset; component->component_size = size; + if (data->context->mode == PLDMFW_UPDATE_MODE_SINGLE_COMPONENT && + data->context->component_identifier != component->identifier) + continue; + list_add_tail(&component->entry, &data->components); } + if (data->context->mode == PLDMFW_UPDATE_MODE_SINGLE_COMPONENT && + list_empty(&data->components)) + return -ENOENT; + header_crc_ptr = data->fw->data + data->offset; err = pldm_move_fw_offset(data, sizeof(data->header_crc)); diff --git a/lib/plist.c b/lib/plist.c index 0d86ed7a76ac..c6bce1226874 100644 --- a/lib/plist.c +++ b/lib/plist.c @@ -47,8 +47,8 @@ static void plist_check_list(struct list_head *top) plist_check_prev_next(top, prev, next); while (next != top) { - prev = next; - next = prev->next; + WRITE_ONCE(prev, next); + WRITE_ONCE(next, prev->next); plist_check_prev_next(top, prev, next); } } @@ -72,7 +72,7 @@ static void plist_check_head(struct plist_head *head) */ void plist_add(struct plist_node *node, struct plist_head *head) { - struct plist_node *first, *iter, *prev = NULL; + struct plist_node *first, *iter, *prev = NULL, *last, *reverse_iter; struct list_head *node_next = &head->node_list; plist_check_head(head); @@ -83,16 +83,26 @@ void plist_add(struct plist_node *node, struct plist_head *head) goto ins_node; first = iter = plist_first(head); + last = reverse_iter = list_entry(first->prio_list.prev, struct plist_node, prio_list); do { if (node->prio < iter->prio) { node_next = &iter->node_list; break; + } else if (node->prio >= reverse_iter->prio) { + prev = reverse_iter; + iter = list_entry(reverse_iter->prio_list.next, + struct plist_node, prio_list); + if (likely(reverse_iter != last)) + node_next = &iter->node_list; + break; } prev = iter; iter = list_entry(iter->prio_list.next, struct plist_node, prio_list); + reverse_iter = list_entry(reverse_iter->prio_list.prev, + struct plist_node, prio_list); } while (iter != first); if (!prev || prev->prio != node->prio) @@ -255,6 +265,32 @@ static int __init plist_test(void) } printk(KERN_DEBUG "end plist test\n"); + + /* Worst case test for plist_add() */ + unsigned int test_data[241]; + + for (i = 0; i < ARRAY_SIZE(test_data); i++) + test_data[i] = i; + + ktime_t start, end, time_elapsed = 0; + + plist_head_init(&test_head); + + for (i = 0; i < ARRAY_SIZE(test_node); i++) { + plist_node_init(test_node + i, 0); + test_node[i].prio = test_data[i]; + } + + for (i = 0; i < ARRAY_SIZE(test_node); i++) { + if (plist_node_empty(test_node + i)) { + start = ktime_get(); + plist_add(test_node + i, &test_head); + end = ktime_get(); + time_elapsed += (end - start); + } + } + + pr_debug("plist_add worst case test time elapsed %lld\n", time_elapsed); return 0; } diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile index 385a94aa0b99..29127dd05d63 100644 --- a/lib/raid6/Makefile +++ b/lib/raid6/Makefile @@ -33,27 +33,8 @@ CFLAGS_REMOVE_vpermxor8.o += -msoft-float endif endif -# The GCC option -ffreestanding is required in order to compile code containing -# ARM/NEON intrinsics in a non C99-compliant environment (such as the kernel) -ifeq ($(CONFIG_KERNEL_MODE_NEON),y) -NEON_FLAGS := -ffreestanding -# Enable <arm_neon.h> -NEON_FLAGS += -isystem $(shell $(CC) -print-file-name=include) -ifeq ($(ARCH),arm) -NEON_FLAGS += -march=armv7-a -mfloat-abi=softfp -mfpu=neon -endif -CFLAGS_recov_neon_inner.o += $(NEON_FLAGS) -ifeq ($(ARCH),arm64) -CFLAGS_REMOVE_recov_neon_inner.o += -mgeneral-regs-only -CFLAGS_REMOVE_neon1.o += -mgeneral-regs-only -CFLAGS_REMOVE_neon2.o += -mgeneral-regs-only -CFLAGS_REMOVE_neon4.o += -mgeneral-regs-only -CFLAGS_REMOVE_neon8.o += -mgeneral-regs-only -endif -endif - quiet_cmd_unroll = UNROLL $@ - cmd_unroll = $(AWK) -v N=$* -f $(srctree)/$(src)/unroll.awk < $< > $@ + cmd_unroll = $(AWK) -v N=$* -f $(src)/unroll.awk < $< > $@ targets += int1.c int2.c int4.c int8.c $(obj)/int%.c: $(src)/int.uc $(src)/unroll.awk FORCE @@ -75,10 +56,16 @@ targets += vpermxor1.c vpermxor2.c vpermxor4.c vpermxor8.c $(obj)/vpermxor%.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE $(call if_changed,unroll) -CFLAGS_neon1.o += $(NEON_FLAGS) -CFLAGS_neon2.o += $(NEON_FLAGS) -CFLAGS_neon4.o += $(NEON_FLAGS) -CFLAGS_neon8.o += $(NEON_FLAGS) +CFLAGS_neon1.o += $(CC_FLAGS_FPU) +CFLAGS_neon2.o += $(CC_FLAGS_FPU) +CFLAGS_neon4.o += $(CC_FLAGS_FPU) +CFLAGS_neon8.o += $(CC_FLAGS_FPU) +CFLAGS_recov_neon_inner.o += $(CC_FLAGS_FPU) +CFLAGS_REMOVE_neon1.o += $(CC_FLAGS_NO_FPU) +CFLAGS_REMOVE_neon2.o += $(CC_FLAGS_NO_FPU) +CFLAGS_REMOVE_neon4.o += $(CC_FLAGS_NO_FPU) +CFLAGS_REMOVE_neon8.o += $(CC_FLAGS_NO_FPU) +CFLAGS_REMOVE_recov_neon_inner.o += $(CC_FLAGS_NO_FPU) targets += neon1.c neon2.c neon4.c neon8.c $(obj)/neon%.c: $(src)/neon.uc $(src)/unroll.awk FORCE $(call if_changed,unroll) diff --git a/lib/random32.c b/lib/random32.c index 32060b852668..24e7acd9343f 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -36,11 +36,11 @@ #include <linux/percpu.h> #include <linux/export.h> #include <linux/jiffies.h> -#include <linux/random.h> +#include <linux/prandom.h> #include <linux/sched.h> #include <linux/bitops.h> #include <linux/slab.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> /** * prandom_u32_state - seeded pseudo-random number generator. diff --git a/lib/rbtree.c b/lib/rbtree.c index 5114eda6309c..989c2d615f92 100644 --- a/lib/rbtree.c +++ b/lib/rbtree.c @@ -297,9 +297,9 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root, * / \ / \ * N S --> N sl * / \ \ - * sl Sr S + * sl sr S * \ - * Sr + * sr * * Note: p might be red, and then both * p and sl are red after rotation(which @@ -312,9 +312,9 @@ ____rb_erase_color(struct rb_node *parent, struct rb_root *root, * / \ / \ * N sl --> P S * \ / \ - * S N Sr + * S N sr * \ - * Sr + * sr */ tmp1 = tmp2->rb_right; WRITE_ONCE(sibling->rb_left, tmp1); diff --git a/lib/rbtree_test.c b/lib/rbtree_test.c index 41ae3c7570d3..8655a76d29a1 100644 --- a/lib/rbtree_test.c +++ b/lib/rbtree_test.c @@ -2,7 +2,7 @@ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/rbtree_augmented.h> -#include <linux/random.h> +#include <linux/prandom.h> #include <linux/slab.h> #include <asm/timex.h> diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 6ae2ba8e06a2..3e555d012ed6 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -130,7 +130,8 @@ static union nested_table *nested_table_alloc(struct rhashtable *ht, if (ntbl) return ntbl; - ntbl = kzalloc(PAGE_SIZE, GFP_ATOMIC); + ntbl = alloc_hooks_tag(ht->alloc_tag, + kmalloc_noprof(PAGE_SIZE, GFP_ATOMIC|__GFP_ZERO)); if (ntbl && leaf) { for (i = 0; i < PAGE_SIZE / sizeof(ntbl[0]); i++) @@ -157,7 +158,8 @@ static struct bucket_table *nested_bucket_table_alloc(struct rhashtable *ht, size = sizeof(*tbl) + sizeof(tbl->buckets[0]); - tbl = kzalloc(size, gfp); + tbl = alloc_hooks_tag(ht->alloc_tag, + kmalloc_noprof(size, gfp|__GFP_ZERO)); if (!tbl) return NULL; @@ -181,11 +183,13 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht, int i; static struct lock_class_key __key; - tbl = kvzalloc(struct_size(tbl, buckets, nbuckets), gfp); + tbl = alloc_hooks_tag(ht->alloc_tag, + kvmalloc_node_noprof(struct_size(tbl, buckets, nbuckets), + gfp|__GFP_ZERO, NUMA_NO_NODE)); size = nbuckets; - if (tbl == NULL && (gfp & ~__GFP_NOFAIL) != GFP_KERNEL) { + if (tbl == NULL && !gfpflags_allow_blocking(gfp)) { tbl = nested_bucket_table_alloc(ht, nbuckets, gfp); nbuckets = 0; } @@ -580,10 +584,6 @@ static struct bucket_table *rhashtable_insert_one( */ rht_assign_locked(bkt, obj); - atomic_inc(&ht->nelems); - if (rht_grow_above_75(ht, tbl)) - schedule_work(&ht->run_work); - return NULL; } @@ -611,15 +611,23 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key, new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); data = ERR_PTR(-EAGAIN); } else { + bool inserted; + flags = rht_lock(tbl, bkt); data = rhashtable_lookup_one(ht, bkt, tbl, hash, key, obj); new_tbl = rhashtable_insert_one(ht, bkt, tbl, hash, obj, data); + inserted = data && !new_tbl; + if (inserted) + atomic_inc(&ht->nelems); if (PTR_ERR(new_tbl) != -EEXIST) data = ERR_CAST(new_tbl); rht_unlock(tbl, bkt, flags); + + if (inserted && rht_grow_above_75(ht, tbl)) + schedule_work(&ht->run_work); } } while (!IS_ERR_OR_NULL(new_tbl)); @@ -661,7 +669,7 @@ EXPORT_SYMBOL_GPL(rhashtable_insert_slow); * structure outside the hash table. * * This function may be called from any process context, including - * non-preemptable context, but cannot be called from softirq or + * non-preemptible context, but cannot be called from softirq or * hardirq context. * * You must call rhashtable_walk_exit after this function returns. @@ -1016,7 +1024,7 @@ static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed) * .obj_hashfn = my_hash_fn, * }; */ -int rhashtable_init(struct rhashtable *ht, +int rhashtable_init_noprof(struct rhashtable *ht, const struct rhashtable_params *params) { struct bucket_table *tbl; @@ -1031,6 +1039,8 @@ int rhashtable_init(struct rhashtable *ht, spin_lock_init(&ht->lock); memcpy(&ht->p, params, sizeof(*params)); + alloc_tag_record(ht->alloc_tag); + if (params->min_size) ht->p.min_size = roundup_pow_of_two(params->min_size); @@ -1076,7 +1086,7 @@ int rhashtable_init(struct rhashtable *ht, return 0; } -EXPORT_SYMBOL_GPL(rhashtable_init); +EXPORT_SYMBOL_GPL(rhashtable_init_noprof); /** * rhltable_init - initialize a new hash list table @@ -1087,15 +1097,15 @@ EXPORT_SYMBOL_GPL(rhashtable_init); * * See documentation for rhashtable_init. */ -int rhltable_init(struct rhltable *hlt, const struct rhashtable_params *params) +int rhltable_init_noprof(struct rhltable *hlt, const struct rhashtable_params *params) { int err; - err = rhashtable_init(&hlt->ht, params); + err = rhashtable_init_noprof(&hlt->ht, params); hlt->ht.rhlist = true; return err; } -EXPORT_SYMBOL_GPL(rhltable_init); +EXPORT_SYMBOL_GPL(rhltable_init_noprof); static void rhashtable_free_one(struct rhashtable *ht, struct rhash_head *obj, void (*free_fn)(void *ptr, void *arg), diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 1e453f825c05..d3412984170c 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -60,12 +60,30 @@ static inline void update_alloc_hint_after_get(struct sbitmap *sb, /* * See if we have deferred clears that we can batch move */ -static inline bool sbitmap_deferred_clear(struct sbitmap_word *map) +static inline bool sbitmap_deferred_clear(struct sbitmap_word *map, + unsigned int depth, unsigned int alloc_hint, bool wrap) { - unsigned long mask; + unsigned long mask, word_mask; - if (!READ_ONCE(map->cleared)) - return false; + guard(raw_spinlock_irqsave)(&map->swap_lock); + + if (!map->cleared) { + if (depth == 0) + return false; + + word_mask = (~0UL) >> (BITS_PER_LONG - depth); + /* + * The current behavior is to always retry after moving + * ->cleared to word, and we change it to retry in case + * of any free bits. To avoid an infinite loop, we need + * to take wrap & alloc_hint into account, otherwise a + * soft lockup may occur. + */ + if (!wrap && alloc_hint) + word_mask &= ~((1UL << alloc_hint) - 1); + + return (READ_ONCE(map->word) & word_mask) != word_mask; + } /* * First get a stable cleared mask, setting the old mask to 0. @@ -85,6 +103,7 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, bool alloc_hint) { unsigned int bits_per_word; + int i; if (shift < 0) shift = sbitmap_calculate_shift(depth); @@ -116,6 +135,9 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, return -ENOMEM; } + for (i = 0; i < sb->map_nr; i++) + raw_spin_lock_init(&sb->map[i].swap_lock); + return 0; } EXPORT_SYMBOL_GPL(sbitmap_init_node); @@ -126,7 +148,7 @@ void sbitmap_resize(struct sbitmap *sb, unsigned int depth) unsigned int i; for (i = 0; i < sb->map_nr; i++) - sbitmap_deferred_clear(&sb->map[i]); + sbitmap_deferred_clear(&sb->map[i], 0, 0, 0); sb->depth = depth; sb->map_nr = DIV_ROUND_UP(sb->depth, bits_per_word); @@ -179,7 +201,7 @@ static int sbitmap_find_bit_in_word(struct sbitmap_word *map, alloc_hint, wrap); if (nr != -1) break; - if (!sbitmap_deferred_clear(map)) + if (!sbitmap_deferred_clear(map, depth, alloc_hint, wrap)) break; } while (1); @@ -496,7 +518,7 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags, unsigned int map_depth = __map_depth(sb, index); unsigned long val; - sbitmap_deferred_clear(map); + sbitmap_deferred_clear(map, 0, 0, 0); val = READ_ONCE(map->word); if (val == (1UL << (map_depth - 1)) - 1) goto next; diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 7bc2220fea80..5bb6b8aff232 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -11,6 +11,7 @@ #include <linux/kmemleak.h> #include <linux/bvec.h> #include <linux/uio.h> +#include <linux/folio_queue.h> /** * sg_next - return the next scatterlist entry in a list @@ -473,14 +474,14 @@ int sg_alloc_append_table_from_pages(struct sg_append_table *sgt_append, return -EOPNOTSUPP; if (sgt_append->prv) { - unsigned long next_pfn = (page_to_phys(sg_page(sgt_append->prv)) + - sgt_append->prv->offset + sgt_append->prv->length) / PAGE_SIZE; + unsigned long next_pfn; if (WARN_ON(offset)) return -EINVAL; /* Merge contiguous pages into the last SG */ prv_len = sgt_append->prv->length; + next_pfn = (sg_phys(sgt_append->prv) + prv_len) / PAGE_SIZE; if (page_to_pfn(pages[0]) == next_pfn) { last_pg = pfn_to_page(next_pfn - 1); while (n_pages && pages_are_mergeable(pages[0], last_pg)) { @@ -1262,6 +1263,67 @@ static ssize_t extract_kvec_to_sg(struct iov_iter *iter, } /* + * Extract up to sg_max folios from an FOLIOQ-type iterator and add them to + * the scatterlist. The pages are not pinned. + */ +static ssize_t extract_folioq_to_sg(struct iov_iter *iter, + ssize_t maxsize, + struct sg_table *sgtable, + unsigned int sg_max, + iov_iter_extraction_t extraction_flags) +{ + const struct folio_queue *folioq = iter->folioq; + struct scatterlist *sg = sgtable->sgl + sgtable->nents; + unsigned int slot = iter->folioq_slot; + ssize_t ret = 0; + size_t offset = iter->iov_offset; + + BUG_ON(!folioq); + + if (slot >= folioq_nr_slots(folioq)) { + folioq = folioq->next; + if (WARN_ON_ONCE(!folioq)) + return 0; + slot = 0; + } + + do { + struct folio *folio = folioq_folio(folioq, slot); + size_t fsize = folioq_folio_size(folioq, slot); + + if (offset < fsize) { + size_t part = umin(maxsize - ret, fsize - offset); + + sg_set_page(sg, folio_page(folio, 0), part, offset); + sgtable->nents++; + sg++; + sg_max--; + offset += part; + ret += part; + } + + if (offset >= fsize) { + offset = 0; + slot++; + if (slot >= folioq_nr_slots(folioq)) { + if (!folioq->next) { + WARN_ON_ONCE(ret < iter->count); + break; + } + folioq = folioq->next; + slot = 0; + } + } + } while (sg_max > 0 && ret < maxsize); + + iter->folioq = folioq; + iter->folioq_slot = slot; + iter->iov_offset = offset; + iter->count -= ret; + return ret; +} + +/* * Extract up to sg_max folios from an XARRAY-type iterator and add them to * the scatterlist. The pages are not pinned. */ @@ -1323,8 +1385,8 @@ static ssize_t extract_xarray_to_sg(struct iov_iter *iter, * addition of @sg_max elements. * * The pages referred to by UBUF- and IOVEC-type iterators are extracted and - * pinned; BVEC-, KVEC- and XARRAY-type are extracted but aren't pinned; PIPE- - * and DISCARD-type are not supported. + * pinned; BVEC-, KVEC-, FOLIOQ- and XARRAY-type are extracted but aren't + * pinned; DISCARD-type is not supported. * * No end mark is placed on the scatterlist; that's left to the caller. * @@ -1356,6 +1418,9 @@ ssize_t extract_iter_to_sg(struct iov_iter *iter, size_t maxsize, case ITER_KVEC: return extract_kvec_to_sg(iter, maxsize, sgtable, sg_max, extraction_flags); + case ITER_FOLIOQ: + return extract_folioq_to_sg(iter, maxsize, sgtable, sg_max, + extraction_flags); case ITER_XARRAY: return extract_xarray_to_sg(iter, maxsize, sgtable, sg_max, extraction_flags); diff --git a/lib/siphash.c b/lib/siphash.c index 15bc5b6f368c..9e4e88752d2e 100644 --- a/lib/siphash.c +++ b/lib/siphash.c @@ -10,7 +10,7 @@ */ #include <linux/siphash.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64 #include <linux/dcache.h> diff --git a/lib/siphash_kunit.c b/lib/siphash_kunit.c index a3c697e8be35..26bd4e8dc03e 100644 --- a/lib/siphash_kunit.c +++ b/lib/siphash_kunit.c @@ -194,4 +194,5 @@ static struct kunit_suite siphash_test_suite = { kunit_test_suite(siphash_test_suite); MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>"); +MODULE_DESCRIPTION("Test cases for siphash.c"); MODULE_LICENSE("Dual BSD/GPL"); diff --git a/lib/slub_kunit.c b/lib/slub_kunit.c index 4ce960438806..f11691315c2f 100644 --- a/lib/slub_kunit.c +++ b/lib/slub_kunit.c @@ -5,6 +5,7 @@ #include <linux/slab.h> #include <linux/module.h> #include <linux/kernel.h> +#include <linux/rcupdate.h> #include "../mm/slab.h" static struct kunit_resource resource; @@ -140,7 +141,7 @@ static void test_kmalloc_redzone_access(struct kunit *test) { struct kmem_cache *s = test_kmem_cache_create("TestSlub_RZ_kmalloc", 32, SLAB_KMALLOC|SLAB_STORE_USER|SLAB_RED_ZONE); - u8 *p = kmalloc_trace(s, GFP_KERNEL, 18); + u8 *p = alloc_hooks(__kmalloc_cache_noprof(s, GFP_KERNEL, 18)); kasan_disable_current(); @@ -157,6 +158,81 @@ static void test_kmalloc_redzone_access(struct kunit *test) kmem_cache_destroy(s); } +struct test_kfree_rcu_struct { + struct rcu_head rcu; +}; + +static void test_kfree_rcu(struct kunit *test) +{ + struct kmem_cache *s; + struct test_kfree_rcu_struct *p; + + if (IS_BUILTIN(CONFIG_SLUB_KUNIT_TEST)) + kunit_skip(test, "can't do kfree_rcu() when test is built-in"); + + s = test_kmem_cache_create("TestSlub_kfree_rcu", + sizeof(struct test_kfree_rcu_struct), + SLAB_NO_MERGE); + p = kmem_cache_alloc(s, GFP_KERNEL); + + kfree_rcu(p, rcu); + kmem_cache_destroy(s); + + KUNIT_EXPECT_EQ(test, 0, slab_errors); +} + +static void test_leak_destroy(struct kunit *test) +{ + struct kmem_cache *s = test_kmem_cache_create("TestSlub_leak_destroy", + 64, SLAB_NO_MERGE); + kmem_cache_alloc(s, GFP_KERNEL); + + kmem_cache_destroy(s); + + KUNIT_EXPECT_EQ(test, 2, slab_errors); +} + +static void test_krealloc_redzone_zeroing(struct kunit *test) +{ + u8 *p; + int i; + struct kmem_cache *s = test_kmem_cache_create("TestSlub_krealloc", 64, + SLAB_KMALLOC|SLAB_STORE_USER|SLAB_RED_ZONE); + + p = alloc_hooks(__kmalloc_cache_noprof(s, GFP_KERNEL, 48)); + memset(p, 0xff, 48); + + kasan_disable_current(); + OPTIMIZER_HIDE_VAR(p); + + /* Test shrink */ + p = krealloc(p, 40, GFP_KERNEL | __GFP_ZERO); + for (i = 40; i < 64; i++) + KUNIT_EXPECT_EQ(test, p[i], SLUB_RED_ACTIVE); + + /* Test grow within the same 64B kmalloc object */ + p = krealloc(p, 56, GFP_KERNEL | __GFP_ZERO); + for (i = 40; i < 56; i++) + KUNIT_EXPECT_EQ(test, p[i], 0); + for (i = 56; i < 64; i++) + KUNIT_EXPECT_EQ(test, p[i], SLUB_RED_ACTIVE); + + validate_slab_cache(s); + KUNIT_EXPECT_EQ(test, 0, slab_errors); + + memset(p, 0xff, 56); + /* Test grow with allocating a bigger 128B object */ + p = krealloc(p, 112, GFP_KERNEL | __GFP_ZERO); + for (i = 0; i < 56; i++) + KUNIT_EXPECT_EQ(test, p[i], 0xff); + for (i = 56; i < 112; i++) + KUNIT_EXPECT_EQ(test, p[i], 0); + + kfree(p); + kasan_enable_current(); + kmem_cache_destroy(s); +} + static int test_init(struct kunit *test) { slab_errors = 0; @@ -177,6 +253,9 @@ static struct kunit_case test_cases[] = { KUNIT_CASE(test_clobber_redzone_free), KUNIT_CASE(test_kmalloc_redzone_access), + KUNIT_CASE(test_kfree_rcu), + KUNIT_CASE(test_leak_destroy), + KUNIT_CASE(test_krealloc_redzone_zeroing), {} }; diff --git a/lib/sort.c b/lib/sort.c index a0509088f82a..8e73dc55476b 100644 --- a/lib/sort.c +++ b/lib/sort.c @@ -5,13 +5,11 @@ * This performs n*log2(n) + 0.37*n + o(n) comparisons on average, * and 1.5*n*log2(n) + O(n) in the (very contrived) worst case. * - * Glibc qsort() manages n*log2(n) - 1.26*n for random inputs (1.63*n + * Quicksort manages n*log2(n) - 1.26*n for random inputs (1.63*n * better) at the expense of stack usage and much larger code to avoid * quicksort's O(n^2) worst case. */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - #include <linux/types.h> #include <linux/export.h> #include <linux/sort.h> @@ -202,6 +200,13 @@ static size_t parent(size_t i, unsigned int lsbit, size_t size) * copy (e.g. fix up pointers or auxiliary data), but the built-in swap * avoids a slow retpoline and so is significantly faster. * + * The comparison function must adhere to specific mathematical + * properties to ensure correct and stable sorting: + * - Antisymmetry: cmp_func(a, b) must return the opposite sign of + * cmp_func(b, a). + * - Transitivity: if cmp_func(a, b) <= 0 and cmp_func(b, c) <= 0, then + * cmp_func(a, c) <= 0. + * * Sorting time is O(n log n) both on average and worst-case. While * quicksort is slightly faster on average, it suffers from exploitable * O(n*n) worst-case behavior and extra memory requirements that make @@ -252,10 +257,7 @@ void sort_r(void *base, size_t num, size_t size, a = size << shift; n -= size; do_swap(base + a, base + n, size, swap_func, priv); - } else if (n > size) { /* Sorting: Extract root */ - n -= size; - do_swap(base, base + n, size, swap_func, priv); - } else { /* Sort complete */ + } else { /* Sort complete */ break; } @@ -285,6 +287,11 @@ void sort_r(void *base, size_t num, size_t size, do_swap(base + b, base + c, size, swap_func, priv); } } + + n -= size; + do_swap(base, base + n, size, swap_func, priv); + if (n == size * 2 && do_cmp(base, base + size, cmp_func, priv) > 0) + do_swap(base, base + size, size, swap_func, priv); } EXPORT_SYMBOL(sort_r); diff --git a/lib/stackdepot.c b/lib/stackdepot.c index cd8f23455285..245d5b416699 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -624,20 +624,21 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries, * we won't be able to do that under the lock. */ if (unlikely(can_alloc && !READ_ONCE(new_pool))) { - /* - * Zero out zone modifiers, as we don't have specific zone - * requirements. Keep the flags related to allocation in atomic - * contexts, I/O, nolockdep. - */ - alloc_flags &= ~GFP_ZONEMASK; - alloc_flags &= (GFP_ATOMIC | GFP_KERNEL | __GFP_NOLOCKDEP); - alloc_flags |= __GFP_NOWARN; - page = alloc_pages(alloc_flags, DEPOT_POOL_ORDER); + page = alloc_pages(gfp_nested_mask(alloc_flags), + DEPOT_POOL_ORDER); if (page) prealloc = page_address(page); } - raw_spin_lock_irqsave(&pool_lock, flags); + if (in_nmi()) { + /* We can never allocate in NMI context. */ + WARN_ON_ONCE(can_alloc); + /* Best effort; bail if we fail to take the lock. */ + if (!raw_spin_trylock_irqsave(&pool_lock, flags)) + goto exit; + } else { + raw_spin_lock_irqsave(&pool_lock, flags); + } printk_deferred_enter(); /* Try to find again, to avoid concurrently inserting duplicates. */ diff --git a/lib/stackinit_kunit.c b/lib/stackinit_kunit.c index 3bc14d1ee816..135322592faf 100644 --- a/lib/stackinit_kunit.c +++ b/lib/stackinit_kunit.c @@ -47,10 +47,12 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size, #define DO_NOTHING_TYPE_SCALAR(var_type) var_type #define DO_NOTHING_TYPE_STRING(var_type) void #define DO_NOTHING_TYPE_STRUCT(var_type) void +#define DO_NOTHING_TYPE_UNION(var_type) void #define DO_NOTHING_RETURN_SCALAR(ptr) *(ptr) #define DO_NOTHING_RETURN_STRING(ptr) /**/ #define DO_NOTHING_RETURN_STRUCT(ptr) /**/ +#define DO_NOTHING_RETURN_UNION(ptr) /**/ #define DO_NOTHING_CALL_SCALAR(var, name) \ (var) = do_nothing_ ## name(&(var)) @@ -58,10 +60,13 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size, do_nothing_ ## name(var) #define DO_NOTHING_CALL_STRUCT(var, name) \ do_nothing_ ## name(&(var)) +#define DO_NOTHING_CALL_UNION(var, name) \ + do_nothing_ ## name(&(var)) #define FETCH_ARG_SCALAR(var) &var #define FETCH_ARG_STRING(var) var #define FETCH_ARG_STRUCT(var) &var +#define FETCH_ARG_UNION(var) &var /* * On m68k, if the leaf function test variable is longer than 8 bytes, @@ -70,13 +75,16 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size, */ #ifdef CONFIG_M68K #define FILL_SIZE_STRING 8 +#define FILL_SIZE_ARRAY 2 #else #define FILL_SIZE_STRING 16 +#define FILL_SIZE_ARRAY 8 #endif #define INIT_CLONE_SCALAR /**/ #define INIT_CLONE_STRING [FILL_SIZE_STRING] #define INIT_CLONE_STRUCT /**/ +#define INIT_CLONE_UNION /**/ #define ZERO_CLONE_SCALAR(zero) memset(&(zero), 0x00, sizeof(zero)) #define ZERO_CLONE_STRING(zero) memset(&(zero), 0x00, sizeof(zero)) @@ -92,6 +100,7 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size, zero.three = 0; \ zero.four = 0; \ } while (0) +#define ZERO_CLONE_UNION(zero) ZERO_CLONE_STRUCT(zero) #define INIT_SCALAR_none(var_type) /**/ #define INIT_SCALAR_zero(var_type) = 0 @@ -101,6 +110,7 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size, #define INIT_STRUCT_none(var_type) /**/ #define INIT_STRUCT_zero(var_type) = { } +#define INIT_STRUCT_old_zero(var_type) = { 0 } #define __static_partial { .two = 0, } @@ -146,6 +156,34 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size, #define INIT_STRUCT_assigned_copy(var_type) \ ; var = *(arg) +/* Union initialization is the same as structs. */ +#define INIT_UNION_none(var_type) INIT_STRUCT_none(var_type) +#define INIT_UNION_zero(var_type) INIT_STRUCT_zero(var_type) +#define INIT_UNION_old_zero(var_type) INIT_STRUCT_old_zero(var_type) + +#define INIT_UNION_static_partial(var_type) \ + INIT_STRUCT_static_partial(var_type) +#define INIT_UNION_static_all(var_type) \ + INIT_STRUCT_static_all(var_type) +#define INIT_UNION_dynamic_partial(var_type) \ + INIT_STRUCT_dynamic_partial(var_type) +#define INIT_UNION_dynamic_all(var_type) \ + INIT_STRUCT_dynamic_all(var_type) +#define INIT_UNION_runtime_partial(var_type) \ + INIT_STRUCT_runtime_partial(var_type) +#define INIT_UNION_runtime_all(var_type) \ + INIT_STRUCT_runtime_all(var_type) +#define INIT_UNION_assigned_static_partial(var_type) \ + INIT_STRUCT_assigned_static_partial(var_type) +#define INIT_UNION_assigned_static_all(var_type) \ + INIT_STRUCT_assigned_static_all(var_type) +#define INIT_UNION_assigned_dynamic_partial(var_type) \ + INIT_STRUCT_assigned_dynamic_partial(var_type) +#define INIT_UNION_assigned_dynamic_all(var_type) \ + INIT_STRUCT_assigned_dynamic_all(var_type) +#define INIT_UNION_assigned_copy(var_type) \ + INIT_STRUCT_assigned_copy(var_type) + /* * @name: unique string name for the test * @var_type: type to be tested for zeroing initialization @@ -212,6 +250,7 @@ static noinline void test_ ## name (struct kunit *test) \ static noinline DO_NOTHING_TYPE_ ## which(var_type) \ do_nothing_ ## name(var_type *ptr) \ { \ + OPTIMIZER_HIDE_VAR(ptr); \ /* Will always be true, but compiler doesn't know. */ \ if ((unsigned long)ptr > 0x2) \ return DO_NOTHING_RETURN_ ## which(ptr); \ @@ -293,6 +332,33 @@ struct test_user { unsigned long four; }; +/* No padding: all members are the same size. */ +union test_same_sizes { + unsigned long one; + unsigned long two; + unsigned long three; + unsigned long four; +}; + +/* Mismatched sizes, with one and two being small */ +union test_small_start { + char one:1; + char two; + short three; + unsigned long four; + struct big_struct { + unsigned long array[FILL_SIZE_ARRAY]; + } big; +}; + +/* Mismatched sizes, with three and four being small */ +union test_small_end { + short one; + unsigned long two; + char three:1; + char four; +}; + #define ALWAYS_PASS WANT_SUCCESS #define ALWAYS_FAIL XFAIL @@ -331,6 +397,11 @@ struct test_user { struct test_ ## name, STRUCT, init, \ xfail) +#define DEFINE_UNION_TEST(name, init, xfail) \ + DEFINE_TEST(name ## _ ## init, \ + union test_ ## name, STRUCT, init, \ + xfail) + #define DEFINE_STRUCT_TESTS(init, xfail) \ DEFINE_STRUCT_TEST(small_hole, init, xfail); \ DEFINE_STRUCT_TEST(big_hole, init, xfail); \ @@ -342,9 +413,22 @@ struct test_user { xfail); \ DEFINE_STRUCT_TESTS(base ## _ ## all, xfail) +#define DEFINE_UNION_INITIALIZER_TESTS(base, xfail) \ + DEFINE_UNION_TESTS(base ## _ ## partial, \ + xfail); \ + DEFINE_UNION_TESTS(base ## _ ## all, xfail) + +#define DEFINE_UNION_TESTS(init, xfail) \ + DEFINE_UNION_TEST(same_sizes, init, xfail); \ + DEFINE_UNION_TEST(small_start, init, xfail); \ + DEFINE_UNION_TEST(small_end, init, xfail); + /* These should be fully initialized all the time! */ DEFINE_SCALAR_TESTS(zero, ALWAYS_PASS); DEFINE_STRUCT_TESTS(zero, ALWAYS_PASS); +DEFINE_STRUCT_TESTS(old_zero, ALWAYS_PASS); +DEFINE_UNION_TESTS(zero, ALWAYS_PASS); +DEFINE_UNION_TESTS(old_zero, ALWAYS_PASS); /* Struct initializers: padding may be left uninitialized. */ DEFINE_STRUCT_INITIALIZER_TESTS(static, STRONG_PASS); DEFINE_STRUCT_INITIALIZER_TESTS(dynamic, STRONG_PASS); @@ -352,6 +436,12 @@ DEFINE_STRUCT_INITIALIZER_TESTS(runtime, STRONG_PASS); DEFINE_STRUCT_INITIALIZER_TESTS(assigned_static, STRONG_PASS); DEFINE_STRUCT_INITIALIZER_TESTS(assigned_dynamic, STRONG_PASS); DEFINE_STRUCT_TESTS(assigned_copy, ALWAYS_FAIL); +DEFINE_UNION_INITIALIZER_TESTS(static, STRONG_PASS); +DEFINE_UNION_INITIALIZER_TESTS(dynamic, STRONG_PASS); +DEFINE_UNION_INITIALIZER_TESTS(runtime, STRONG_PASS); +DEFINE_UNION_INITIALIZER_TESTS(assigned_static, STRONG_PASS); +DEFINE_UNION_INITIALIZER_TESTS(assigned_dynamic, STRONG_PASS); +DEFINE_UNION_TESTS(assigned_copy, ALWAYS_FAIL); /* No initialization without compiler instrumentation. */ DEFINE_SCALAR_TESTS(none, STRONG_PASS); DEFINE_STRUCT_TESTS(none, BYREF_PASS); @@ -435,13 +525,23 @@ DEFINE_TEST_DRIVER(switch_2_none, uint64_t, SCALAR, ALWAYS_FAIL); KUNIT_CASE(test_trailing_hole_ ## init),\ KUNIT_CASE(test_packed_ ## init) \ +#define KUNIT_test_unions(init) \ + KUNIT_CASE(test_same_sizes_ ## init), \ + KUNIT_CASE(test_small_start_ ## init), \ + KUNIT_CASE(test_small_end_ ## init) \ + static struct kunit_case stackinit_test_cases[] = { /* These are explicitly initialized and should always pass. */ KUNIT_test_scalars(zero), KUNIT_test_structs(zero), + KUNIT_test_structs(old_zero), + KUNIT_test_unions(zero), + KUNIT_test_unions(old_zero), /* Padding here appears to be accidentally always initialized? */ KUNIT_test_structs(dynamic_partial), KUNIT_test_structs(assigned_dynamic_partial), + KUNIT_test_unions(dynamic_partial), + KUNIT_test_unions(assigned_dynamic_partial), /* Padding initialization depends on compiler behaviors. */ KUNIT_test_structs(static_partial), KUNIT_test_structs(static_all), @@ -451,8 +551,17 @@ static struct kunit_case stackinit_test_cases[] = { KUNIT_test_structs(assigned_static_partial), KUNIT_test_structs(assigned_static_all), KUNIT_test_structs(assigned_dynamic_all), + KUNIT_test_unions(static_partial), + KUNIT_test_unions(static_all), + KUNIT_test_unions(dynamic_all), + KUNIT_test_unions(runtime_partial), + KUNIT_test_unions(runtime_all), + KUNIT_test_unions(assigned_static_partial), + KUNIT_test_unions(assigned_static_all), + KUNIT_test_unions(assigned_dynamic_all), /* Everything fails this since it effectively performs a memcpy(). */ KUNIT_test_structs(assigned_copy), + KUNIT_test_unions(assigned_copy), /* STRUCTLEAK_BYREF_ALL should cover everything from here down. */ KUNIT_test_scalars(none), KUNIT_CASE(test_switch_1_none), @@ -471,4 +580,5 @@ static struct kunit_suite stackinit_test_suite = { kunit_test_suites(&stackinit_test_suite); +MODULE_DESCRIPTION("Test cases for compiler-based stack variable zeroing"); MODULE_LICENSE("GPL"); diff --git a/lib/string.c b/lib/string.c index 966da44bfc86..eb4486ed40d2 100644 --- a/lib/string.c +++ b/lib/string.c @@ -27,7 +27,7 @@ #include <asm/page.h> #include <asm/rwonce.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <asm/word-at-a-time.h> #ifndef __HAVE_ARCH_STRNCASECMP @@ -104,6 +104,12 @@ char *strncpy(char *dest, const char *src, size_t count) EXPORT_SYMBOL(strncpy); #endif +#ifdef __BIG_ENDIAN +# define ALLBUTLAST_BYTE_MASK (~255ul) +#else +# define ALLBUTLAST_BYTE_MASK (~0ul >> 8) +#endif + ssize_t sized_strscpy(char *dest, const char *src, size_t count) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; @@ -147,13 +153,18 @@ ssize_t sized_strscpy(char *dest, const char *src, size_t count) *(unsigned long *)(dest+res) = c & zero_bytemask(data); return res + find_zero(data); } + count -= sizeof(unsigned long); + if (unlikely(!count)) { + c &= ALLBUTLAST_BYTE_MASK; + *(unsigned long *)(dest+res) = c; + return -E2BIG; + } *(unsigned long *)(dest+res) = c; res += sizeof(unsigned long); - count -= sizeof(unsigned long); max -= sizeof(unsigned long); } - while (count) { + while (count > 1) { char c; c = src[res]; @@ -164,11 +175,11 @@ ssize_t sized_strscpy(char *dest, const char *src, size_t count) count--; } - /* Hit buffer length without finding a NUL; force NUL-termination. */ - if (res) - dest[res-1] = '\0'; + /* Force NUL-termination. */ + dest[res] = '\0'; - return -E2BIG; + /* Return E2BIG if the source didn't stop */ + return src[res] ? -E2BIG : res; } EXPORT_SYMBOL(sized_strscpy); diff --git a/lib/string_helpers.c b/lib/string_helpers.c index 69ba49b853c7..91fa37b5c510 100644 --- a/lib/string_helpers.c +++ b/lib/string_helpers.c @@ -57,7 +57,7 @@ int string_get_size(u64 size, u64 blk_size, const enum string_size_units units, static const unsigned int rounding[] = { 500, 50, 5 }; int i = 0, j; u32 remainder = 0, sf_cap; - char tmp[8]; + char tmp[12]; const char *unit; tmp[0] = '\0'; @@ -321,6 +321,9 @@ int string_unescape(char *src, char *dst, size_t size, unsigned int flags) { char *out = dst; + if (!size) + size = SIZE_MAX; + while (*src && --size) { if (src[0] == '\\' && src[1] != '\0' && size > 1) { src++; diff --git a/lib/string_helpers_kunit.c b/lib/string_helpers_kunit.c index f88e39fd68d6..c853046183d2 100644 --- a/lib/string_helpers_kunit.c +++ b/lib/string_helpers_kunit.c @@ -625,4 +625,5 @@ static struct kunit_suite string_helpers_test_suite = { kunit_test_suites(&string_helpers_test_suite); +MODULE_DESCRIPTION("Test cases for string helpers module"); MODULE_LICENSE("Dual BSD/GPL"); diff --git a/lib/string_kunit.c b/lib/string_kunit.c index 2a812decf14b..c919e3293da6 100644 --- a/lib/string_kunit.c +++ b/lib/string_kunit.c @@ -633,4 +633,5 @@ static struct kunit_suite string_test_suite = { kunit_test_suites(&string_test_suite); +MODULE_DESCRIPTION("Test cases for string functions"); MODULE_LICENSE("GPL v2"); diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c index 6432b8c3e431..6dc234913dd5 100644 --- a/lib/strncpy_from_user.c +++ b/lib/strncpy_from_user.c @@ -120,6 +120,18 @@ long strncpy_from_user(char *dst, const char __user *src, long count) if (unlikely(count <= 0)) return 0; + kasan_check_write(dst, count); + check_object_size(dst, count, false); + + if (can_do_masked_user_access()) { + long retval; + + src = masked_user_access_begin(src); + retval = do_strncpy_from_user(dst, src, count, count); + user_read_access_end(); + return retval; + } + max_addr = TASK_SIZE_MAX; src_addr = (unsigned long)untagged_addr(src); if (likely(src_addr < max_addr)) { @@ -133,8 +145,6 @@ long strncpy_from_user(char *dst, const char __user *src, long count) if (max > count) max = count; - kasan_check_write(dst, count); - check_object_size(dst, count, false); if (user_read_access_begin(src, max)) { retval = do_strncpy_from_user(dst, src, count, max); user_read_access_end(); diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c index feeb935a2299..6e489f9e90f1 100644 --- a/lib/strnlen_user.c +++ b/lib/strnlen_user.c @@ -96,6 +96,15 @@ long strnlen_user(const char __user *str, long count) if (unlikely(count <= 0)) return 0; + if (can_do_masked_user_access()) { + long retval; + + str = masked_user_access_begin(str); + retval = do_strnlen_user(str, count, count); + user_read_access_end(); + return retval; + } + max_addr = TASK_SIZE_MAX; src_addr = (unsigned long)untagged_addr(str); if (likely(src_addr < max_addr)) { diff --git a/lib/test-kstrtox.c b/lib/test-kstrtox.c index f355f67169b6..ee87fef66cb5 100644 --- a/lib/test-kstrtox.c +++ b/lib/test-kstrtox.c @@ -732,4 +732,5 @@ static int __init test_kstrtox_init(void) return -EINVAL; } module_init(test_kstrtox_init); +MODULE_DESCRIPTION("Module test for kstrto*() APIs"); MODULE_LICENSE("Dual BSD/GPL"); diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index 83019beabce4..65a75d58ed9e 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -244,7 +244,7 @@ static void __init test_find_nth_bit(void) expect_eq_uint(60, find_nth_bit(bmap, 64 * 3, 5)); expect_eq_uint(80, find_nth_bit(bmap, 64 * 3, 6)); expect_eq_uint(123, find_nth_bit(bmap, 64 * 3, 7)); - expect_eq_uint(64 * 3, find_nth_bit(bmap, 64 * 3, 8)); + expect_eq_uint(0, !!(find_nth_bit(bmap, 64 * 3, 8) < 64 * 3)); expect_eq_uint(10, find_nth_bit(bmap, 64 * 3 - 1, 0)); expect_eq_uint(20, find_nth_bit(bmap, 64 * 3 - 1, 1)); @@ -254,7 +254,7 @@ static void __init test_find_nth_bit(void) expect_eq_uint(60, find_nth_bit(bmap, 64 * 3 - 1, 5)); expect_eq_uint(80, find_nth_bit(bmap, 64 * 3 - 1, 6)); expect_eq_uint(123, find_nth_bit(bmap, 64 * 3 - 1, 7)); - expect_eq_uint(64 * 3 - 1, find_nth_bit(bmap, 64 * 3 - 1, 8)); + expect_eq_uint(0, !!(find_nth_bit(bmap, 64 * 3 - 1, 8) < 64 * 3 - 1)); for_each_set_bit(bit, exp1, EXP1_IN_BITS) { b = find_nth_bit(exp1, EXP1_IN_BITS, cnt++); @@ -1486,4 +1486,5 @@ static void __init selftest(void) KSTM_MODULE_LOADERS(test_bitmap); MODULE_AUTHOR("david decotigny <david.decotigny@googlers.com>"); +MODULE_DESCRIPTION("Test cases for bitmap API"); MODULE_LICENSE("GPL"); diff --git a/lib/test_bitops.c b/lib/test_bitops.c index 3b7bcbee84db..55669624bb28 100644 --- a/lib/test_bitops.c +++ b/lib/test_bitops.c @@ -5,9 +5,11 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/cleanup.h> #include <linux/init.h> #include <linux/module.h> #include <linux/printk.h> +#include <linux/slab.h> /* a tiny module only meant to test * @@ -50,6 +52,30 @@ static unsigned long order_comb_long[][2] = { }; #endif +static int __init test_fns(void) +{ + static volatile __always_used unsigned long tmp __initdata; + unsigned long *buf __free(kfree) = NULL; + unsigned int i, n; + ktime_t time; + + buf = kmalloc_array(10000, sizeof(unsigned long), GFP_KERNEL); + if (!buf) + return -ENOMEM; + + get_random_bytes(buf, 10000 * sizeof(unsigned long)); + time = ktime_get(); + + for (n = 0; n < BITS_PER_LONG; n++) + for (i = 0; i < 10000; i++) + tmp = fns(buf[i], n); + + time = ktime_get() - time; + pr_err("fns: %18llu ns\n", time); + + return 0; +} + static int __init test_bitops_startup(void) { int i, bit_set; @@ -94,6 +120,8 @@ static int __init test_bitops_startup(void) if (bit_set != BITOPS_LAST) pr_err("ERROR: FOUND SET BIT %d\n", bit_set); + test_fns(); + pr_info("Completed bitops test\n"); return 0; diff --git a/lib/test_bits.c b/lib/test_bits.c index c9368a2314e7..c7b38d91e1f1 100644 --- a/lib/test_bits.c +++ b/lib/test_bits.c @@ -39,6 +39,36 @@ static void genmask_ull_test(struct kunit *test) #endif } +static void genmask_u128_test(struct kunit *test) +{ +#ifdef CONFIG_ARCH_SUPPORTS_INT128 + /* Below 64 bit masks */ + KUNIT_EXPECT_EQ(test, 0x0000000000000001ull, GENMASK_U128(0, 0)); + KUNIT_EXPECT_EQ(test, 0x0000000000000003ull, GENMASK_U128(1, 0)); + KUNIT_EXPECT_EQ(test, 0x0000000000000006ull, GENMASK_U128(2, 1)); + KUNIT_EXPECT_EQ(test, 0x00000000ffffffffull, GENMASK_U128(31, 0)); + KUNIT_EXPECT_EQ(test, 0x000000ffffe00000ull, GENMASK_U128(39, 21)); + KUNIT_EXPECT_EQ(test, 0xffffffffffffffffull, GENMASK_U128(63, 0)); + + /* Above 64 bit masks - only 64 bit portion can be validated once */ + KUNIT_EXPECT_EQ(test, 0xffffffffffffffffull, GENMASK_U128(64, 0) >> 1); + KUNIT_EXPECT_EQ(test, 0x00000000ffffffffull, GENMASK_U128(81, 50) >> 50); + KUNIT_EXPECT_EQ(test, 0x0000000000ffffffull, GENMASK_U128(87, 64) >> 64); + KUNIT_EXPECT_EQ(test, 0x0000000000ff0000ull, GENMASK_U128(87, 80) >> 64); + + KUNIT_EXPECT_EQ(test, 0xffffffffffffffffull, GENMASK_U128(127, 0) >> 64); + KUNIT_EXPECT_EQ(test, 0xffffffffffffffffull, (u64)GENMASK_U128(127, 0)); + KUNIT_EXPECT_EQ(test, 0x0000000000000003ull, GENMASK_U128(127, 126) >> 126); + KUNIT_EXPECT_EQ(test, 0x0000000000000001ull, GENMASK_U128(127, 127) >> 127); +#ifdef TEST_GENMASK_FAILURES + /* these should fail compilation */ + GENMASK_U128(0, 1); + GENMASK_U128(0, 10); + GENMASK_U128(9, 10); +#endif /* TEST_GENMASK_FAILURES */ +#endif /* CONFIG_ARCH_SUPPORTS_INT128 */ +} + static void genmask_input_check_test(struct kunit *test) { unsigned int x, y; @@ -56,12 +86,16 @@ static void genmask_input_check_test(struct kunit *test) /* Valid input */ KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(1, 1)); KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(39, 21)); + KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(100, 80)); + KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(110, 65)); + KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(127, 0)); } static struct kunit_case bits_test_cases[] = { KUNIT_CASE(genmask_test), KUNIT_CASE(genmask_ull_test), + KUNIT_CASE(genmask_u128_test), KUNIT_CASE(genmask_input_check_test), {} }; @@ -72,4 +106,5 @@ static struct kunit_suite bits_test_suite = { }; kunit_test_suite(bits_test_suite); +MODULE_DESCRIPTION("Test cases for functions and macros in bits.h"); MODULE_LICENSE("GPL"); diff --git a/lib/test_blackhole_dev.c b/lib/test_blackhole_dev.c index f247089d63c0..ec290ac2a0d9 100644 --- a/lib/test_blackhole_dev.c +++ b/lib/test_blackhole_dev.c @@ -96,4 +96,5 @@ module_init(test_blackholedev_init); module_exit(test_blackholedev_exit); MODULE_AUTHOR("Mahesh Bandewar <maheshb@google.com>"); +MODULE_DESCRIPTION("module test of the blackhole_dev"); MODULE_LICENSE("GPL"); diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 207ff87194db..af0041df2b72 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -14,7 +14,7 @@ #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/if_vlan.h> -#include <linux/random.h> +#include <linux/prandom.h> #include <linux/highmem.h> #include <linux/sched.h> @@ -478,7 +478,7 @@ static int __bpf_ld_imm64(struct bpf_insn insns[2], u8 reg, s64 imm64) * to overflow the field size of the native instruction, triggering * a branch conversion mechanism in some JITs. */ -static int __bpf_fill_max_jmp(struct bpf_test *self, int jmp, int imm) +static int __bpf_fill_max_jmp(struct bpf_test *self, int jmp, int imm, bool alu32) { struct bpf_insn *insns; int len = S16_MAX + 5; @@ -501,7 +501,7 @@ static int __bpf_fill_max_jmp(struct bpf_test *self, int jmp, int imm) }; int op = ops[(i >> 1) % ARRAY_SIZE(ops)]; - if (i & 1) + if ((i & 1) || alu32) insns[i++] = BPF_ALU32_REG(op, R0, R1); else insns[i++] = BPF_ALU64_REG(op, R0, R1); @@ -516,27 +516,47 @@ static int __bpf_fill_max_jmp(struct bpf_test *self, int jmp, int imm) } /* Branch taken by runtime decision */ +static int bpf_fill_max_jmp_taken_32(struct bpf_test *self) +{ + return __bpf_fill_max_jmp(self, BPF_JEQ, 1, true); +} + static int bpf_fill_max_jmp_taken(struct bpf_test *self) { - return __bpf_fill_max_jmp(self, BPF_JEQ, 1); + return __bpf_fill_max_jmp(self, BPF_JEQ, 1, false); } /* Branch not taken by runtime decision */ +static int bpf_fill_max_jmp_not_taken_32(struct bpf_test *self) +{ + return __bpf_fill_max_jmp(self, BPF_JEQ, 0, true); +} + static int bpf_fill_max_jmp_not_taken(struct bpf_test *self) { - return __bpf_fill_max_jmp(self, BPF_JEQ, 0); + return __bpf_fill_max_jmp(self, BPF_JEQ, 0, false); } /* Branch always taken, known at JIT time */ +static int bpf_fill_max_jmp_always_taken_32(struct bpf_test *self) +{ + return __bpf_fill_max_jmp(self, BPF_JGE, 0, true); +} + static int bpf_fill_max_jmp_always_taken(struct bpf_test *self) { - return __bpf_fill_max_jmp(self, BPF_JGE, 0); + return __bpf_fill_max_jmp(self, BPF_JGE, 0, false); } /* Branch never taken, known at JIT time */ +static int bpf_fill_max_jmp_never_taken_32(struct bpf_test *self) +{ + return __bpf_fill_max_jmp(self, BPF_JLT, 0, true); +} + static int bpf_fill_max_jmp_never_taken(struct bpf_test *self) { - return __bpf_fill_max_jmp(self, BPF_JLT, 0); + return __bpf_fill_max_jmp(self, BPF_JLT, 0, false); } /* ALU result computation used in tests */ @@ -1740,7 +1760,7 @@ static int __bpf_emit_cmpxchg32(struct bpf_test *self, void *arg, /* Result unsuccessful */ insns[i++] = BPF_STX_MEM(BPF_W, R10, R1, -4); insns[i++] = BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, R10, R2, -4); - insns[i++] = BPF_ZEXT_REG(R0), /* Zext always inserted by verifier */ + insns[i++] = BPF_ZEXT_REG(R0); /* Zext always inserted by verifier */ insns[i++] = BPF_LDX_MEM(BPF_W, R3, R10, -4); insns[i++] = BPF_JMP32_REG(BPF_JEQ, R1, R3, 2); @@ -1754,7 +1774,7 @@ static int __bpf_emit_cmpxchg32(struct bpf_test *self, void *arg, /* Result successful */ i += __bpf_ld_imm64(&insns[i], R0, dst); insns[i++] = BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, R10, R2, -4); - insns[i++] = BPF_ZEXT_REG(R0), /* Zext always inserted by verifier */ + insns[i++] = BPF_ZEXT_REG(R0); /* Zext always inserted by verifier */ insns[i++] = BPF_LDX_MEM(BPF_W, R3, R10, -4); insns[i++] = BPF_JMP32_REG(BPF_JEQ, R2, R3, 2); @@ -14234,6 +14254,38 @@ static struct bpf_test tests[] = { }, /* Conditional branch conversions */ { + "Long conditional jump: taken at runtime (32 bits)", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_max_jmp_taken_32, + }, + { + "Long conditional jump: not taken at runtime (32 bits)", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 2 } }, + .fill_helper = bpf_fill_max_jmp_not_taken_32, + }, + { + "Long conditional jump: always taken, known at JIT time (32 bits)", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 1 } }, + .fill_helper = bpf_fill_max_jmp_always_taken_32, + }, + { + "Long conditional jump: never taken, known at JIT time (32 bits)", + { }, + INTERNAL | FLAG_NO_DATA, + { }, + { { 0, 2 } }, + .fill_helper = bpf_fill_max_jmp_never_taken_32, + }, + { "Long conditional jump: taken at runtime", { }, INTERNAL | FLAG_NO_DATA, @@ -15077,8 +15129,7 @@ static struct skb_segment_test skb_segment_tests[] __initconst = { .build_skb = build_test_skb_linear_no_head_frag, .features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_GSO | - NETIF_F_LLTX | NETIF_F_GRO | - NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM | + NETIF_F_GRO | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_STAG_TX } }; @@ -15198,6 +15249,7 @@ struct tail_call_test { int flags; int result; int stack_depth; + bool has_tail_call; }; /* Flags that can be passed to tail call test cases */ @@ -15273,6 +15325,7 @@ static struct tail_call_test tail_call_tests[] = { BPF_EXIT_INSN(), }, .result = 3, + .has_tail_call = true, }, { "Tail call 3", @@ -15283,6 +15336,7 @@ static struct tail_call_test tail_call_tests[] = { BPF_EXIT_INSN(), }, .result = 6, + .has_tail_call = true, }, { "Tail call 4", @@ -15293,6 +15347,7 @@ static struct tail_call_test tail_call_tests[] = { BPF_EXIT_INSN(), }, .result = 10, + .has_tail_call = true, }, { "Tail call load/store leaf", @@ -15323,6 +15378,7 @@ static struct tail_call_test tail_call_tests[] = { }, .result = 0, .stack_depth = 16, + .has_tail_call = true, }, { "Tail call error path, max count reached", @@ -15335,6 +15391,7 @@ static struct tail_call_test tail_call_tests[] = { }, .flags = FLAG_NEED_STATE | FLAG_RESULT_IN_STATE, .result = (MAX_TAIL_CALL_CNT + 1) * MAX_TESTRUNS, + .has_tail_call = true, }, { "Tail call count preserved across function calls", @@ -15357,6 +15414,7 @@ static struct tail_call_test tail_call_tests[] = { .stack_depth = 8, .flags = FLAG_NEED_STATE | FLAG_RESULT_IN_STATE, .result = (MAX_TAIL_CALL_CNT + 1) * MAX_TESTRUNS, + .has_tail_call = true, }, { "Tail call error path, NULL target", @@ -15369,6 +15427,7 @@ static struct tail_call_test tail_call_tests[] = { }, .flags = FLAG_NEED_STATE | FLAG_RESULT_IN_STATE, .result = MAX_TESTRUNS, + .has_tail_call = true, }, { "Tail call error path, index out of range", @@ -15381,6 +15440,7 @@ static struct tail_call_test tail_call_tests[] = { }, .flags = FLAG_NEED_STATE | FLAG_RESULT_IN_STATE, .result = MAX_TESTRUNS, + .has_tail_call = true, }, }; @@ -15430,6 +15490,7 @@ static __init int prepare_tail_call_tests(struct bpf_array **pprogs) fp->len = len; fp->type = BPF_PROG_TYPE_SOCKET_FILTER; fp->aux->stack_depth = test->stack_depth; + fp->aux->tail_call_reachable = test->has_tail_call; memcpy(fp->insnsi, test->insns, len * sizeof(struct bpf_insn)); /* Relocate runtime tail call offsets and addresses */ @@ -15706,4 +15767,5 @@ static void __exit test_bpf_exit(void) module_init(test_bpf_init); module_exit(test_bpf_exit); +MODULE_DESCRIPTION("Testsuite for BPF interpreter and BPF JIT compiler"); MODULE_LICENSE("GPL"); diff --git a/lib/test_dynamic_debug.c b/lib/test_dynamic_debug.c index 8dd250ad022b..77c2a669b6af 100644 --- a/lib/test_dynamic_debug.c +++ b/lib/test_dynamic_debug.c @@ -162,4 +162,5 @@ module_init(test_dynamic_debug_init); module_exit(test_dynamic_debug_exit); MODULE_AUTHOR("Jim Cromie <jim.cromie@gmail.com>"); +MODULE_DESCRIPTION("Kernel module for testing dynamic_debug"); MODULE_LICENSE("GPL"); diff --git a/lib/test_firmware.c b/lib/test_firmware.c index 9cfdcd6d21db..211222e63328 100644 --- a/lib/test_firmware.c +++ b/lib/test_firmware.c @@ -27,7 +27,7 @@ #include <linux/vmalloc.h> #include <linux/efi_embedded_fw.h> -MODULE_IMPORT_NS(TEST_FIRMWARE); +MODULE_IMPORT_NS("TEST_FIRMWARE"); #define TEST_FIRMWARE_NAME "test-firmware.bin" #define TEST_FIRMWARE_NUM_REQS 4 @@ -1567,4 +1567,5 @@ static void __exit test_firmware_exit(void) module_exit(test_firmware_exit); MODULE_AUTHOR("Kees Cook <keescook@chromium.org>"); +MODULE_DESCRIPTION("interface to trigger and test firmware loading"); MODULE_LICENSE("GPL"); diff --git a/lib/test_fortify/.gitignore b/lib/test_fortify/.gitignore new file mode 100644 index 000000000000..c1ba37d14b50 --- /dev/null +++ b/lib/test_fortify/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +/*.log diff --git a/lib/test_fortify/Makefile b/lib/test_fortify/Makefile new file mode 100644 index 000000000000..1c3f82ad8bb2 --- /dev/null +++ b/lib/test_fortify/Makefile @@ -0,0 +1,28 @@ +# SPDX-License-Identifier: GPL-2.0 + +ccflags-y := $(call cc-disable-warning,fortify-source) + +quiet_cmd_test_fortify = TEST $@ + cmd_test_fortify = $(CONFIG_SHELL) $(src)/test_fortify.sh \ + $< $@ "$(NM)" $(CC) $(c_flags) -DKBUILD_EXTRA_WARN1 + +$(obj)/%.log: $(src)/%.c $(src)/test_fortify.sh FORCE + $(call if_changed_dep,test_fortify) + +logs = $(patsubst $(src)/%.c, %.log, $(wildcard $(src)/*-*.c)) +targets += $(logs) + +quiet_cmd_gen_fortify_log = CAT $@ + cmd_gen_fortify_log = cat $(or $(real-prereqs),/dev/null) > $@ + +$(obj)/test_fortify.log: $(addprefix $(obj)/, $(logs)) FORCE + $(call if_changed,gen_fortify_log) + +# GCC<=7 does not always produce *.d files. +# Run the tests only for GCC>=8 or Clang. +always-$(call gcc-min-version, 80000) += test_fortify.log +always-$(CONFIG_CC_IS_CLANG) += test_fortify.log + +# Some architectures define __NO_FORTIFY if __SANITIZE_ADDRESS__ is undefined. +# Pass CFLAGS_KASAN to avoid warnings. +KASAN_SANITIZE := y diff --git a/lib/test_fortify/test_fortify.sh b/lib/test_fortify/test_fortify.sh new file mode 100644 index 000000000000..c2688ab8281d --- /dev/null +++ b/lib/test_fortify/test_fortify.sh @@ -0,0 +1,66 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0-only +set -e + +# Argument 1: Source file to build. +IN="$1" +shift +# Extract just the filename for error messages below. +FILE="${IN##*/}" +# Extract the function name for error messages below. +FUNC="${FILE#*-}" +FUNC="${FUNC%%-*}" +FUNC="${FUNC%%.*}" +# Extract the symbol to test for in build/symbol test below. +WANT="__${FILE%%-*}" + +# Argument 2: Where to write the build log. +OUT="$1" +shift +TMP="${OUT}.tmp" + +# Argument 3: Path to "nm" tool. +NM="$1" +shift + +# Remaining arguments are: $(CC) $(c_flags) + +# Clean up temporary file at exit. +__cleanup() { + rm -f "$TMP" +} +trap __cleanup EXIT + +# Function names in warnings are wrapped in backticks under UTF-8 locales. +# Run the commands with LANG=C so that grep output will not change. +export LANG=C + +status= +# Attempt to build a source that is expected to fail with a specific warning. +if "$@" -Werror -c "$IN" -o "$OUT".o 2> "$TMP" ; then + # If the build succeeds, either the test has failed or the + # warning may only happen at link time (Clang). In that case, + # make sure the expected symbol is unresolved in the symbol list. + # If so, FORTIFY is working for this case. + if ! $NM -A "$OUT".o | grep -m1 "\bU ${WANT}$" >>"$TMP" ; then + status="warning: unsafe ${FUNC}() usage lacked '$WANT' symbol in $IN" + fi +else + # If the build failed, check for the warning in the stderr. + # GCC: + # ./include/linux/fortify-string.h:316:25: error: call to '__write_overflow_field' declared with attribute warning: detected write beyond size of field (1st parameter); maybe use struct_group()? [-Werror=attribute-warning] + # Clang 14: + # ./include/linux/fortify-string.h:316:4: error: call to __write_overflow_field declared with 'warning' attribute: detected write beyond size of field (1st parameter); maybe use struct_group()? [-Werror,-Wattribute-warning] + if ! grep -Eq -m1 "error: call to .?\b${WANT}\b.?" "$TMP" ; then + status="warning: unsafe ${FUNC}() usage lacked '$WANT' warning in $IN" + fi +fi + +if [ -n "$status" ]; then + # Report on failure results, including compilation warnings. + echo "$status" | tee "$OUT" >&2 +else + # Report on good results, and save any compilation output to log. + echo "ok: unsafe ${FUNC}() usage correctly detected with '$WANT' in $IN" >"$OUT" +fi +cat "$TMP" >>"$OUT" diff --git a/lib/test_fprobe.c b/lib/test_fprobe.c index 24de0e5ff859..cf92111b5c79 100644 --- a/lib/test_fprobe.c +++ b/lib/test_fprobe.c @@ -17,10 +17,8 @@ static u32 rand1, entry_val, exit_val; /* Use indirect calls to avoid inlining the target functions */ static u32 (*target)(u32 value); static u32 (*target2)(u32 value); -static u32 (*target_nest)(u32 value, u32 (*nest)(u32)); static unsigned long target_ip; static unsigned long target2_ip; -static unsigned long target_nest_ip; static int entry_return_value; static noinline u32 fprobe_selftest_target(u32 value) @@ -33,14 +31,9 @@ static noinline u32 fprobe_selftest_target2(u32 value) return (value / div_factor) + 1; } -static noinline u32 fprobe_selftest_nest_target(u32 value, u32 (*nest)(u32)) -{ - return nest(value + 2); -} - static notrace int fp_entry_handler(struct fprobe *fp, unsigned long ip, unsigned long ret_ip, - struct pt_regs *regs, void *data) + struct ftrace_regs *fregs, void *data) { KUNIT_EXPECT_FALSE(current_test, preemptible()); /* This can be called on the fprobe_selftest_target and the fprobe_selftest_target2 */ @@ -59,9 +52,9 @@ static notrace int fp_entry_handler(struct fprobe *fp, unsigned long ip, static notrace void fp_exit_handler(struct fprobe *fp, unsigned long ip, unsigned long ret_ip, - struct pt_regs *regs, void *data) + struct ftrace_regs *fregs, void *data) { - unsigned long ret = regs_return_value(regs); + unsigned long ret = ftrace_regs_get_return_value(fregs); KUNIT_EXPECT_FALSE(current_test, preemptible()); if (ip != target_ip) { @@ -79,22 +72,6 @@ static notrace void fp_exit_handler(struct fprobe *fp, unsigned long ip, KUNIT_EXPECT_NULL(current_test, data); } -static notrace int nest_entry_handler(struct fprobe *fp, unsigned long ip, - unsigned long ret_ip, - struct pt_regs *regs, void *data) -{ - KUNIT_EXPECT_FALSE(current_test, preemptible()); - return 0; -} - -static notrace void nest_exit_handler(struct fprobe *fp, unsigned long ip, - unsigned long ret_ip, - struct pt_regs *regs, void *data) -{ - KUNIT_EXPECT_FALSE(current_test, preemptible()); - KUNIT_EXPECT_EQ(current_test, ip, target_nest_ip); -} - /* Test entry only (no rethook) */ static void test_fprobe_entry(struct kunit *test) { @@ -191,25 +168,6 @@ static void test_fprobe_data(struct kunit *test) KUNIT_EXPECT_EQ(test, 0, unregister_fprobe(&fp)); } -/* Test nr_maxactive */ -static void test_fprobe_nest(struct kunit *test) -{ - static const char *syms[] = {"fprobe_selftest_target", "fprobe_selftest_nest_target"}; - struct fprobe fp = { - .entry_handler = nest_entry_handler, - .exit_handler = nest_exit_handler, - .nr_maxactive = 1, - }; - - current_test = test; - KUNIT_EXPECT_EQ(test, 0, register_fprobe_syms(&fp, syms, 2)); - - target_nest(rand1, target); - KUNIT_EXPECT_EQ(test, 1, fp.nmissed); - - KUNIT_EXPECT_EQ(test, 0, unregister_fprobe(&fp)); -} - static void test_fprobe_skip(struct kunit *test) { struct fprobe fp = { @@ -247,10 +205,8 @@ static int fprobe_test_init(struct kunit *test) rand1 = get_random_u32_above(div_factor); target = fprobe_selftest_target; target2 = fprobe_selftest_target2; - target_nest = fprobe_selftest_nest_target; target_ip = get_ftrace_location(target); target2_ip = get_ftrace_location(target2); - target_nest_ip = get_ftrace_location(target_nest); return 0; } @@ -260,7 +216,6 @@ static struct kunit_case fprobe_testcases[] = { KUNIT_CASE(test_fprobe), KUNIT_CASE(test_fprobe_syms), KUNIT_CASE(test_fprobe_data), - KUNIT_CASE(test_fprobe_nest), KUNIT_CASE(test_fprobe_skip), {} }; diff --git a/lib/test_fpu.h b/lib/test_fpu.h new file mode 100644 index 000000000000..4459807084bc --- /dev/null +++ b/lib/test_fpu.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef _LIB_TEST_FPU_H +#define _LIB_TEST_FPU_H + +int test_fpu(void); + +#endif diff --git a/lib/test_fpu.c b/lib/test_fpu_glue.c index e82db19fed84..c0596426370a 100644 --- a/lib/test_fpu.c +++ b/lib/test_fpu_glue.c @@ -17,39 +17,9 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/debugfs.h> -#include <asm/fpu/api.h> +#include <linux/fpu.h> -static int test_fpu(void) -{ - /* - * This sequence of operations tests that rounding mode is - * to nearest and that denormal numbers are supported. - * Volatile variables are used to avoid compiler optimizing - * the calculations away. - */ - volatile double a, b, c, d, e, f, g; - - a = 4.0; - b = 1e-15; - c = 1e-310; - - /* Sets precision flag */ - d = a + b; - - /* Result depends on rounding mode */ - e = a + b / 2; - - /* Denormal and very large values */ - f = b / c; - - /* Depends on denormal support */ - g = a + c * f; - - if (d > a && e > a && g > a) - return 0; - else - return -EINVAL; -} +#include "test_fpu.h" static int test_fpu_get(void *data, u64 *val) { @@ -68,8 +38,11 @@ static struct dentry *selftest_dir; static int __init test_fpu_init(void) { + if (!kernel_fpu_available()) + return -EINVAL; + selftest_dir = debugfs_create_dir("selftest_helpers", NULL); - if (!selftest_dir) + if (IS_ERR(selftest_dir)) return -ENOMEM; debugfs_create_file_unsafe("test_fpu", 0444, selftest_dir, NULL, @@ -86,4 +59,5 @@ static void __exit test_fpu_exit(void) module_init(test_fpu_init); module_exit(test_fpu_exit); +MODULE_DESCRIPTION("Test cases for floating point operations"); MODULE_LICENSE("GPL"); diff --git a/lib/test_fpu_impl.c b/lib/test_fpu_impl.c new file mode 100644 index 000000000000..777894dbbe86 --- /dev/null +++ b/lib/test_fpu_impl.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include <linux/errno.h> + +#include "test_fpu.h" + +int test_fpu(void) +{ + /* + * This sequence of operations tests that rounding mode is + * to nearest and that denormal numbers are supported. + * Volatile variables are used to avoid compiler optimizing + * the calculations away. + */ + volatile double a, b, c, d, e, f, g; + + a = 4.0; + b = 1e-15; + c = 1e-310; + + /* Sets precision flag */ + d = a + b; + + /* Result depends on rounding mode */ + e = a + b / 2; + + /* Denormal and very large values */ + f = b / c; + + /* Depends on denormal support */ + g = a + c * f; + + if (d > a && e > a && g > a) + return 0; + else + return -EINVAL; +} diff --git a/lib/test_free_pages.c b/lib/test_free_pages.c index 9ebf6f5549f3..48952364c540 100644 --- a/lib/test_free_pages.c +++ b/lib/test_free_pages.c @@ -44,4 +44,5 @@ static void m_ex(void) module_init(m_in); module_exit(m_ex); MODULE_AUTHOR("Matthew Wilcox <willy@infradead.org>"); +MODULE_DESCRIPTION("Check that free_pages() doesn't leak memory"); MODULE_LICENSE("GPL"); diff --git a/lib/test_hash.c b/lib/test_hash.c index bb25fda34794..a7af39662a0a 100644 --- a/lib/test_hash.c +++ b/lib/test_hash.c @@ -235,4 +235,5 @@ static struct kunit_suite hash_test_suite = { kunit_test_suite(hash_test_suite); +MODULE_DESCRIPTION("Test cases for <linux/hash.h> and <linux/stringhash.h>"); MODULE_LICENSE("GPL"); diff --git a/lib/test_hexdump.c b/lib/test_hexdump.c index b916801f23a8..751645645988 100644 --- a/lib/test_hexdump.c +++ b/lib/test_hexdump.c @@ -113,7 +113,7 @@ static void __init test_hexdump_prepare_test(size_t len, int rowsize, *p++ = ' '; } while (p < test + rs * 2 + rs / gs + 1); - strncpy(p, data_a, l); + memcpy(p, data_a, l); p += l; } @@ -253,4 +253,5 @@ static void __exit test_hexdump_exit(void) module_exit(test_hexdump_exit); MODULE_AUTHOR("Andy Shevchenko <andriy.shevchenko@linux.intel.com>"); +MODULE_DESCRIPTION("Test cases for lib/hexdump.c module"); MODULE_LICENSE("Dual BSD/GPL"); diff --git a/lib/test_hmm.c b/lib/test_hmm.c index 717dcb830127..056f2e411d7b 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -799,10 +799,7 @@ static int dmirror_exclusive(struct dmirror *dmirror, unsigned long mapped = 0; int i; - if (end < addr + (ARRAY_SIZE(pages) << PAGE_SHIFT)) - next = end; - else - next = addr + (ARRAY_SIZE(pages) << PAGE_SHIFT); + next = min(end, addr + (ARRAY_SIZE(pages) << PAGE_SHIFT)); ret = make_device_exclusive_range(mm, addr, next, pages, NULL); /* @@ -1226,8 +1223,8 @@ static void dmirror_device_evict_chunk(struct dmirror_chunk *chunk) unsigned long *src_pfns; unsigned long *dst_pfns; - src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL); - dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL); + src_pfns = kvcalloc(npages, sizeof(*src_pfns), GFP_KERNEL | __GFP_NOFAIL); + dst_pfns = kvcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL | __GFP_NOFAIL); migrate_device_range(src_pfns, start_pfn, npages); for (i = 0; i < npages; i++) { @@ -1250,8 +1247,8 @@ static void dmirror_device_evict_chunk(struct dmirror_chunk *chunk) } migrate_device_pages(src_pfns, dst_pfns, npages); migrate_device_finalize(src_pfns, dst_pfns, npages); - kfree(src_pfns); - kfree(dst_pfns); + kvfree(src_pfns); + kvfree(dst_pfns); } /* Removes free pages from the free list so they can't be re-allocated */ @@ -1550,4 +1547,5 @@ static void __exit hmm_dmirror_exit(void) module_init(hmm_dmirror_init); module_exit(hmm_dmirror_exit); +MODULE_DESCRIPTION("HMM (Heterogeneous Memory Management) test module"); MODULE_LICENSE("GPL"); diff --git a/lib/test_ida.c b/lib/test_ida.c index 072a49897e71..c80155a1956d 100644 --- a/lib/test_ida.c +++ b/lib/test_ida.c @@ -214,4 +214,5 @@ static void ida_exit(void) module_init(ida_checks); module_exit(ida_exit); MODULE_AUTHOR("Matthew Wilcox <willy@infradead.org>"); +MODULE_DESCRIPTION("Test the IDA API"); MODULE_LICENSE("GPL"); diff --git a/lib/test_kmod.c b/lib/test_kmod.c index 1eec3b7ac67c..064ed0fce75a 100644 --- a/lib/test_kmod.c +++ b/lib/test_kmod.c @@ -1223,4 +1223,5 @@ static void __exit test_kmod_exit(void) module_exit(test_kmod_exit); MODULE_AUTHOR("Luis R. Rodriguez <mcgrof@kernel.org>"); +MODULE_DESCRIPTION("kmod stress test driver"); MODULE_LICENSE("GPL"); diff --git a/lib/test_kprobes.c b/lib/test_kprobes.c index 0648f7154f5c..b7582010125c 100644 --- a/lib/test_kprobes.c +++ b/lib/test_kprobes.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * test_kprobes.c - simple sanity test for *probes + * test_kprobes.c - simple sanity test for k*probes * * Copyright IBM Corp. 2008 */ @@ -400,4 +400,5 @@ static struct kunit_suite kprobes_test_suite = { kunit_test_suites(&kprobes_test_suite); +MODULE_DESCRIPTION("simple sanity test for k*probes"); MODULE_LICENSE("GPL"); diff --git a/lib/test_linear_ranges.c b/lib/test_linear_ranges.c index c18f9c0f1f25..f482be00f1bc 100644 --- a/lib/test_linear_ranges.c +++ b/lib/test_linear_ranges.c @@ -216,4 +216,5 @@ static struct kunit_suite range_test_module = { kunit_test_suites(&range_test_module); +MODULE_DESCRIPTION("KUnit test for the linear_ranges helper"); MODULE_LICENSE("GPL"); diff --git a/lib/test_list_sort.c b/lib/test_list_sort.c index cc5f335f29b5..30879abc8a42 100644 --- a/lib/test_list_sort.c +++ b/lib/test_list_sort.c @@ -119,4 +119,5 @@ static struct kunit_suite list_sort_suite = { kunit_test_suites(&list_sort_suite); +MODULE_DESCRIPTION("list_sort() KUnit test suite"); MODULE_LICENSE("GPL"); diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c index 399380db449c..13e2a10d7554 100644 --- a/lib/test_maple_tree.c +++ b/lib/test_maple_tree.c @@ -1387,6 +1387,92 @@ static noinline void __init check_prev_entry(struct maple_tree *mt) mas_unlock(&mas); } +static noinline void __init check_store_null(struct maple_tree *mt) +{ + MA_STATE(mas, mt, 0, ULONG_MAX); + + /* + * Store NULL at range [0, ULONG_MAX] to an empty tree should result + * in an empty tree + */ + mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE); + mas_lock(&mas); + mas_store_gfp(&mas, NULL, GFP_KERNEL); + MT_BUG_ON(mt, !mtree_empty(mt)); + mas_unlock(&mas); + mtree_destroy(mt); + + /* + * Store NULL at any range to an empty tree should result in an empty + * tree + */ + mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE); + mas_lock(&mas); + mas_set_range(&mas, 3, 10); + mas_store_gfp(&mas, NULL, GFP_KERNEL); + MT_BUG_ON(mt, !mtree_empty(mt)); + mas_unlock(&mas); + mtree_destroy(mt); + + /* + * Store NULL at range [0, ULONG_MAX] to a single entry tree should + * result in an empty tree + */ + mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE); + mas_lock(&mas); + mas_set(&mas, 0); + mas_store_gfp(&mas, &mas, GFP_KERNEL); + mas_set_range(&mas, 0, ULONG_MAX); + mas_store_gfp(&mas, NULL, GFP_KERNEL); + MT_BUG_ON(mt, !mtree_empty(mt)); + mas_unlock(&mas); + mtree_destroy(mt); + + /* + * Store NULL at range [0, n] to a single entry tree should + * result in an empty tree + */ + mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE); + mas_lock(&mas); + mas_set(&mas, 0); + mas_store_gfp(&mas, &mas, GFP_KERNEL); + mas_set_range(&mas, 0, 5); + mas_store_gfp(&mas, NULL, GFP_KERNEL); + MT_BUG_ON(mt, !mtree_empty(mt)); + mas_unlock(&mas); + mtree_destroy(mt); + + /* + * Store NULL at range [m, n] where m > 0 to a single entry tree + * should still be a single entry tree + */ + mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE); + mas_lock(&mas); + mas_set(&mas, 0); + mas_store_gfp(&mas, &mas, GFP_KERNEL); + mas_set_range(&mas, 2, 5); + mas_store_gfp(&mas, NULL, GFP_KERNEL); + MT_BUG_ON(mt, mtree_empty(mt)); +// MT_BUG_ON(mt, xa_is_node(mas_root(&mas))); + mas_unlock(&mas); + mtree_destroy(mt); + + /* + * Store NULL at range [0, ULONG_MAX] to a tree with node should + * result in an empty tree + */ + mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE); + mas_lock(&mas); + mas_set_range(&mas, 1, 3); + mas_store_gfp(&mas, &mas, GFP_KERNEL); +// MT_BUG_ON(mt, !xa_is_node(mas_root(&mas))); + mas_set_range(&mas, 0, ULONG_MAX); + mas_store_gfp(&mas, NULL, GFP_KERNEL); + MT_BUG_ON(mt, !mtree_empty(mt)); + mas_unlock(&mas); + mtree_destroy(mt); +} + static noinline void __init check_root_expand(struct maple_tree *mt) { MA_STATE(mas, mt, 0, 0); @@ -1477,6 +1563,30 @@ static noinline void __init check_root_expand(struct maple_tree *mt) mas_unlock(&mas); } +static noinline void __init check_deficient_node(struct maple_tree *mt) +{ + MA_STATE(mas, mt, 0, 0); + int count; + + mas_lock(&mas); + for (count = 0; count < 10; count++) { + mas_set(&mas, count); + mas_store_gfp(&mas, xa_mk_value(count), GFP_KERNEL); + } + + for (count = 20; count < 39; count++) { + mas_set(&mas, count); + mas_store_gfp(&mas, xa_mk_value(count), GFP_KERNEL); + } + + for (count = 10; count < 12; count++) { + mas_set(&mas, count); + mas_store_gfp(&mas, xa_mk_value(count), GFP_KERNEL); + } + mas_unlock(&mas); + mt_validate(mt); +} + static noinline void __init check_gap_combining(struct maple_tree *mt) { struct maple_enode *mn1, *mn2; @@ -3628,6 +3738,34 @@ static noinline void __init alloc_cyclic_testing(struct maple_tree *mt) } mtree_destroy(mt); + + /* + * Issue with reverse search was discovered + * https://lore.kernel.org/all/20241216060600.287B4C4CED0@smtp.kernel.org/ + * Exhausting the allocation area and forcing the search to wrap needs a + * mas_reset() in mas_alloc_cyclic(). + */ + next = 0; + mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE); + for (int i = 0; i < 1023; i++) { + mtree_alloc_cyclic(mt, &location, mt, 2, 1024, &next, GFP_KERNEL); + MT_BUG_ON(mt, i != location - 2); + MT_BUG_ON(mt, i != next - 3); + MT_BUG_ON(mt, mtree_load(mt, location) != mt); + } + mtree_erase(mt, 123); + MT_BUG_ON(mt, mtree_load(mt, 123) != NULL); + mtree_alloc_cyclic(mt, &location, mt, 2, 1024, &next, GFP_KERNEL); + MT_BUG_ON(mt, 123 != location); + MT_BUG_ON(mt, 124 != next); + MT_BUG_ON(mt, mtree_load(mt, location) != mt); + mtree_erase(mt, 100); + mtree_alloc_cyclic(mt, &location, mt, 2, 1024, &next, GFP_KERNEL); + MT_BUG_ON(mt, 100 != location); + MT_BUG_ON(mt, 101 != next); + MT_BUG_ON(mt, mtree_load(mt, location) != mt); + mtree_destroy(mt); + /* Overflow test */ next = ULONG_MAX - 1; ret = mtree_alloc_cyclic(mt, &location, mt, 2, ULONG_MAX, &next, GFP_KERNEL); @@ -3711,6 +3849,14 @@ static int __init maple_tree_seed(void) #endif mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); + check_deficient_node(&tree); + mtree_destroy(&tree); + + mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); + check_store_null(&tree); + mtree_destroy(&tree); + + mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); check_root_expand(&tree); mtree_destroy(&tree); @@ -3946,4 +4092,5 @@ static void __exit maple_tree_harvest(void) module_init(maple_tree_seed); module_exit(maple_tree_harvest); MODULE_AUTHOR("Liam R. Howlett <Liam.Howlett@Oracle.com>"); +MODULE_DESCRIPTION("maple tree API test module"); MODULE_LICENSE("GPL"); diff --git a/lib/test_memcat_p.c b/lib/test_memcat_p.c index 849c477d49d0..7e0797a6bebf 100644 --- a/lib/test_memcat_p.c +++ b/lib/test_memcat_p.c @@ -112,4 +112,5 @@ static void __exit test_memcat_p_exit(void) module_init(test_memcat_p_init); module_exit(test_memcat_p_exit); +MODULE_DESCRIPTION("Test cases for memcat_p() in lib/memcat_p.c"); MODULE_LICENSE("GPL"); diff --git a/lib/test_meminit.c b/lib/test_meminit.c index 0dc173849a54..6298f66c964b 100644 --- a/lib/test_meminit.c +++ b/lib/test_meminit.c @@ -436,4 +436,5 @@ static int __init test_meminit_init(void) } module_init(test_meminit_init); +MODULE_DESCRIPTION("Test cases for SL[AOU]B/page initialization at alloc/free time"); MODULE_LICENSE("GPL"); diff --git a/lib/test_min_heap.c b/lib/test_min_heap.c index 7b01b4387cfb..a9c4a74d3898 100644 --- a/lib/test_min_heap.c +++ b/lib/test_min_heap.c @@ -11,26 +11,20 @@ #include <linux/printk.h> #include <linux/random.h> -static __init bool less_than(const void *lhs, const void *rhs) +DEFINE_MIN_HEAP(int, min_heap_test); + +static __init bool less_than(const void *lhs, const void *rhs, void __always_unused *args) { return *(int *)lhs < *(int *)rhs; } -static __init bool greater_than(const void *lhs, const void *rhs) +static __init bool greater_than(const void *lhs, const void *rhs, void __always_unused *args) { return *(int *)lhs > *(int *)rhs; } -static __init void swap_ints(void *lhs, void *rhs) -{ - int temp = *(int *)lhs; - - *(int *)lhs = *(int *)rhs; - *(int *)rhs = temp; -} - static __init int pop_verify_heap(bool min_heap, - struct min_heap *heap, + struct min_heap_test *heap, const struct min_heap_callbacks *funcs) { int *values = heap->data; @@ -38,7 +32,7 @@ static __init int pop_verify_heap(bool min_heap, int last; last = values[0]; - min_heap_pop(heap, funcs); + min_heap_pop_inline(heap, funcs, NULL); while (heap->nr > 0) { if (min_heap) { if (last > values[0]) { @@ -54,7 +48,7 @@ static __init int pop_verify_heap(bool min_heap, } } last = values[0]; - min_heap_pop(heap, funcs); + min_heap_pop_inline(heap, funcs, NULL); } return err; } @@ -63,20 +57,19 @@ static __init int test_heapify_all(bool min_heap) { int values[] = { 3, 1, 2, 4, 0x8000000, 0x7FFFFFF, 0, -3, -1, -2, -4, 0x8000000, 0x7FFFFFF }; - struct min_heap heap = { + struct min_heap_test heap = { .data = values, .nr = ARRAY_SIZE(values), .size = ARRAY_SIZE(values), }; struct min_heap_callbacks funcs = { - .elem_size = sizeof(int), .less = min_heap ? less_than : greater_than, - .swp = swap_ints, + .swp = NULL, }; int i, err; /* Test with known set of values. */ - min_heapify_all(&heap, &funcs); + min_heapify_all_inline(&heap, &funcs, NULL); err = pop_verify_heap(min_heap, &heap, &funcs); @@ -85,7 +78,7 @@ static __init int test_heapify_all(bool min_heap) for (i = 0; i < heap.nr; i++) values[i] = get_random_u32(); - min_heapify_all(&heap, &funcs); + min_heapify_all_inline(&heap, &funcs, NULL); err += pop_verify_heap(min_heap, &heap, &funcs); return err; @@ -96,28 +89,27 @@ static __init int test_heap_push(bool min_heap) const int data[] = { 3, 1, 2, 4, 0x80000000, 0x7FFFFFFF, 0, -3, -1, -2, -4, 0x80000000, 0x7FFFFFFF }; int values[ARRAY_SIZE(data)]; - struct min_heap heap = { + struct min_heap_test heap = { .data = values, .nr = 0, .size = ARRAY_SIZE(values), }; struct min_heap_callbacks funcs = { - .elem_size = sizeof(int), .less = min_heap ? less_than : greater_than, - .swp = swap_ints, + .swp = NULL, }; int i, temp, err; /* Test with known set of values copied from data. */ for (i = 0; i < ARRAY_SIZE(data); i++) - min_heap_push(&heap, &data[i], &funcs); + min_heap_push_inline(&heap, &data[i], &funcs, NULL); err = pop_verify_heap(min_heap, &heap, &funcs); /* Test with randomly generated values. */ while (heap.nr < heap.size) { temp = get_random_u32(); - min_heap_push(&heap, &temp, &funcs); + min_heap_push_inline(&heap, &temp, &funcs, NULL); } err += pop_verify_heap(min_heap, &heap, &funcs); @@ -129,43 +121,76 @@ static __init int test_heap_pop_push(bool min_heap) const int data[] = { 3, 1, 2, 4, 0x80000000, 0x7FFFFFFF, 0, -3, -1, -2, -4, 0x80000000, 0x7FFFFFFF }; int values[ARRAY_SIZE(data)]; - struct min_heap heap = { + struct min_heap_test heap = { .data = values, .nr = 0, .size = ARRAY_SIZE(values), }; struct min_heap_callbacks funcs = { - .elem_size = sizeof(int), .less = min_heap ? less_than : greater_than, - .swp = swap_ints, + .swp = NULL, }; int i, temp, err; /* Fill values with data to pop and replace. */ temp = min_heap ? 0x80000000 : 0x7FFFFFFF; for (i = 0; i < ARRAY_SIZE(data); i++) - min_heap_push(&heap, &temp, &funcs); + min_heap_push_inline(&heap, &temp, &funcs, NULL); /* Test with known set of values copied from data. */ for (i = 0; i < ARRAY_SIZE(data); i++) - min_heap_pop_push(&heap, &data[i], &funcs); + min_heap_pop_push_inline(&heap, &data[i], &funcs, NULL); err = pop_verify_heap(min_heap, &heap, &funcs); heap.nr = 0; for (i = 0; i < ARRAY_SIZE(data); i++) - min_heap_push(&heap, &temp, &funcs); + min_heap_push_inline(&heap, &temp, &funcs, NULL); /* Test with randomly generated values. */ for (i = 0; i < ARRAY_SIZE(data); i++) { temp = get_random_u32(); - min_heap_pop_push(&heap, &temp, &funcs); + min_heap_pop_push_inline(&heap, &temp, &funcs, NULL); } err += pop_verify_heap(min_heap, &heap, &funcs); return err; } +static __init int test_heap_del(bool min_heap) +{ + int values[] = { 3, 1, 2, 4, 0x8000000, 0x7FFFFFF, 0, + -3, -1, -2, -4, 0x8000000, 0x7FFFFFF }; + struct min_heap_test heap; + + min_heap_init_inline(&heap, values, ARRAY_SIZE(values)); + heap.nr = ARRAY_SIZE(values); + struct min_heap_callbacks funcs = { + .less = min_heap ? less_than : greater_than, + .swp = NULL, + }; + int i, err; + + /* Test with known set of values. */ + min_heapify_all_inline(&heap, &funcs, NULL); + for (i = 0; i < ARRAY_SIZE(values) / 2; i++) + min_heap_del_inline(&heap, get_random_u32() % heap.nr, &funcs, NULL); + err = pop_verify_heap(min_heap, &heap, &funcs); + + + /* Test with randomly generated values. */ + heap.nr = ARRAY_SIZE(values); + for (i = 0; i < heap.nr; i++) + values[i] = get_random_u32(); + min_heapify_all_inline(&heap, &funcs, NULL); + + for (i = 0; i < ARRAY_SIZE(values) / 2; i++) + min_heap_del_inline(&heap, get_random_u32() % heap.nr, &funcs, NULL); + err += pop_verify_heap(min_heap, &heap, &funcs); + + return err; +} + static int __init test_min_heap_init(void) { int err = 0; @@ -176,6 +201,8 @@ static int __init test_min_heap_init(void) err += test_heap_push(false); err += test_heap_pop_push(true); err += test_heap_pop_push(false); + err += test_heap_del(true); + err += test_heap_del(false); if (err) { pr_err("test failed with %d errors\n", err); return -EINVAL; @@ -191,4 +218,5 @@ static void __exit test_min_heap_exit(void) } module_exit(test_min_heap_exit); +MODULE_DESCRIPTION("Test cases for the min max heap"); MODULE_LICENSE("GPL"); diff --git a/lib/test_module.c b/lib/test_module.c index debd19e35198..3d1b29b74807 100644 --- a/lib/test_module.c +++ b/lib/test_module.c @@ -31,4 +31,5 @@ static void __exit test_module_exit(void) module_exit(test_module_exit); MODULE_AUTHOR("Kees Cook <keescook@chromium.org>"); +MODULE_DESCRIPTION("module loading subsystem test module"); MODULE_LICENSE("GPL"); diff --git a/lib/test_objagg.c b/lib/test_objagg.c index c0c957c50635..d34df4306b87 100644 --- a/lib/test_objagg.c +++ b/lib/test_objagg.c @@ -60,7 +60,7 @@ static struct objagg_obj *world_obj_get(struct world *world, if (!world->key_refs[key_id_index(key_id)]) { world->objagg_objs[key_id_index(key_id)] = objagg_obj; } else if (world->objagg_objs[key_id_index(key_id)] != objagg_obj) { - pr_err("Key %u: God another object for the same key.\n", + pr_err("Key %u: Got another object for the same key.\n", key_id); err = -EINVAL; goto err_key_id_check; diff --git a/lib/test_objpool.c b/lib/test_objpool.c index bfdb81599832..896c0131c9a8 100644 --- a/lib/test_objpool.c +++ b/lib/test_objpool.c @@ -371,14 +371,10 @@ static int ot_start_sync(struct ot_test *test) if (!cpu_online(cpu)) continue; - work = kthread_create_on_node(ot_thread_worker, item, - cpu_to_node(cpu), "ot_worker_%d", cpu); - if (IS_ERR(work)) { + work = kthread_run_on_cpu(ot_thread_worker, item, + cpu, "ot_worker_%d"); + if (IS_ERR(work)) pr_err("failed to create thread for cpu %d\n", cpu); - } else { - kthread_bind(work, cpu); - wake_up_process(work); - } } /* wait a while to make sure all threads waiting at start line */ @@ -562,14 +558,9 @@ static int ot_start_async(struct ot_test *test) if (!cpu_online(cpu)) continue; - work = kthread_create_on_node(ot_thread_worker, item, - cpu_to_node(cpu), "ot_worker_%d", cpu); - if (IS_ERR(work)) { + work = kthread_run_on_cpu(ot_thread_worker, item, cpu, "ot_worker_%d"); + if (IS_ERR(work)) pr_err("failed to create thread for cpu %d\n", cpu); - } else { - kthread_bind(work, cpu); - wake_up_process(work); - } } /* wait a while to make sure all threads waiting at start line */ @@ -687,4 +678,5 @@ static void __exit ot_mod_exit(void) module_init(ot_mod_init); module_exit(ot_mod_exit); -MODULE_LICENSE("GPL");
\ No newline at end of file +MODULE_DESCRIPTION("Test module for lockless object pool"); +MODULE_LICENSE("GPL"); diff --git a/lib/test_parman.c b/lib/test_parman.c index 35e32243693c..f9b97426a337 100644 --- a/lib/test_parman.c +++ b/lib/test_parman.c @@ -39,7 +39,7 @@ #include <linux/slab.h> #include <linux/bitops.h> #include <linux/err.h> -#include <linux/random.h> +#include <linux/prandom.h> #include <linux/parman.h> #define TEST_PARMAN_PRIO_SHIFT 7 /* defines number of prios for testing */ diff --git a/lib/test_printf.c b/lib/test_printf.c index 69b6a5e177f2..59dbe4f9a4cb 100644 --- a/lib/test_printf.c +++ b/lib/test_printf.c @@ -386,6 +386,66 @@ kernel_ptr(void) static void __init struct_resource(void) { + struct resource test_resource = { + .start = 0xc0ffee00, + .end = 0xc0ffee00, + .flags = IORESOURCE_MEM, + }; + + test("[mem 0xc0ffee00 flags 0x200]", + "%pr", &test_resource); + + test_resource = (struct resource) { + .start = 0xc0ffee, + .end = 0xba5eba11, + .flags = IORESOURCE_MEM, + }; + test("[mem 0x00c0ffee-0xba5eba11 flags 0x200]", + "%pr", &test_resource); + + test_resource = (struct resource) { + .start = 0xba5eba11, + .end = 0xc0ffee, + .flags = IORESOURCE_MEM, + }; + test("[mem 0xba5eba11-0x00c0ffee flags 0x200]", + "%pr", &test_resource); + + test_resource = (struct resource) { + .start = 0xba5eba11, + .end = 0xba5eca11, + .flags = IORESOURCE_MEM, + }; + + test("[mem 0xba5eba11-0xba5eca11 flags 0x200]", + "%pr", &test_resource); + + test_resource = (struct resource) { + .start = 0xba11, + .end = 0xca10, + .flags = IORESOURCE_IO | + IORESOURCE_DISABLED | + IORESOURCE_UNSET, + }; + + test("[io size 0x1000 disabled]", + "%pR", &test_resource); +} + +static void __init +struct_range(void) +{ + struct range test_range = DEFINE_RANGE(0xc0ffee00ba5eba11, + 0xc0ffee00ba5eba11); + test("[range 0xc0ffee00ba5eba11]", "%pra", &test_range); + + test_range = DEFINE_RANGE(0xc0ffee, 0xba5eba11); + test("[range 0x0000000000c0ffee-0x00000000ba5eba11]", + "%pra", &test_range); + + test_range = DEFINE_RANGE(0xba5eba11, 0xc0ffee); + test("[range 0x00000000ba5eba11-0x0000000000c0ffee]", + "%pra", &test_range); } static void __init @@ -641,26 +701,12 @@ page_flags_test(int section, int node, int zone, int last_cpupid, test(cmp_buf, "%pGp", &flags); } -static void __init page_type_test(unsigned int page_type, const char *name, - char *cmp_buf) -{ - unsigned long size; - - size = scnprintf(cmp_buf, BUF_SIZE, "%#x(", page_type); - if (page_type_has_type(page_type)) - size += scnprintf(cmp_buf + size, BUF_SIZE - size, "%s", name); - - snprintf(cmp_buf + size, BUF_SIZE - size, ")"); - test(cmp_buf, "%pGt", &page_type); -} - static void __init flags(void) { unsigned long flags; char *cmp_buffer; gfp_t gfp; - unsigned int page_type; cmp_buffer = kmalloc(BUF_SIZE, GFP_KERNEL); if (!cmp_buffer) @@ -700,18 +746,6 @@ flags(void) gfp |= __GFP_HIGH; test(cmp_buffer, "%pGg", &gfp); - page_type = ~0; - page_type_test(page_type, "", cmp_buffer); - - page_type = 10; - page_type_test(page_type, "", cmp_buffer); - - page_type = ~PG_buddy; - page_type_test(page_type, "buddy", cmp_buffer); - - page_type = ~(PG_table | PG_buddy); - page_type_test(page_type, "table|buddy", cmp_buffer); - kfree(cmp_buffer); } @@ -789,6 +823,7 @@ test_pointer(void) symbol_ptr(); kernel_ptr(); struct_resource(); + struct_range(); addr(); escaped_str(); hex_string(); @@ -824,4 +859,5 @@ static void __init selftest(void) KSTM_MODULE_LOADERS(test_printf); MODULE_AUTHOR("Rasmus Villemoes <linux@rasmusvillemoes.dk>"); +MODULE_DESCRIPTION("Test cases for printf facility"); MODULE_LICENSE("GPL"); diff --git a/lib/test_ref_tracker.c b/lib/test_ref_tracker.c index 49970a7c96f3..b983ceb12afc 100644 --- a/lib/test_ref_tracker.c +++ b/lib/test_ref_tracker.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Referrence tracker self test. + * Reference tracker self test. * * Copyright (c) 2021 Eric Dumazet <edumazet@google.com> */ @@ -112,4 +112,5 @@ static void __exit test_ref_tracker_exit(void) module_init(test_ref_tracker_init); module_exit(test_ref_tracker_exit); +MODULE_DESCRIPTION("Reference tracker self test"); MODULE_LICENSE("GPL v2"); diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index 42b585208249..c63db03ebb9d 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -811,4 +811,5 @@ static void __exit test_rht_exit(void) module_init(test_rht_init); module_exit(test_rht_exit); +MODULE_DESCRIPTION("Resizable, Scalable, Concurrent Hash Table test module"); MODULE_LICENSE("GPL v2"); diff --git a/lib/test_scanf.c b/lib/test_scanf.c index a2707af2951a..44f8508c9d88 100644 --- a/lib/test_scanf.c +++ b/lib/test_scanf.c @@ -11,7 +11,7 @@ #include <linux/module.h> #include <linux/overflow.h> #include <linux/printk.h> -#include <linux/random.h> +#include <linux/prandom.h> #include <linux/slab.h> #include <linux/string.h> @@ -810,4 +810,5 @@ static void __init selftest(void) KSTM_MODULE_LOADERS(test_scanf); MODULE_AUTHOR("Richard Fitzgerald <rf@opensource.cirrus.com>"); +MODULE_DESCRIPTION("Test cases for sscanf facility"); MODULE_LICENSE("GPL v2"); diff --git a/lib/test_sort.c b/lib/test_sort.c index be02e3a098cf..cd4a338d1153 100644 --- a/lib/test_sort.c +++ b/lib/test_sort.c @@ -29,7 +29,19 @@ static void test_sort(struct kunit *test) sort(a, TEST_LEN, sizeof(*a), cmpint, NULL); - for (i = 0; i < TEST_LEN-1; i++) + for (i = 0; i < TEST_LEN - 1; i++) + KUNIT_ASSERT_LE(test, a[i], a[i + 1]); + + r = 48; + + for (i = 0; i < TEST_LEN - 1; i++) { + r = (r * 725861) % 6599; + a[i] = r; + } + + sort(a, TEST_LEN - 1, sizeof(*a), cmpint, NULL); + + for (i = 0; i < TEST_LEN - 2; i++) KUNIT_ASSERT_LE(test, a[i], a[i + 1]); } @@ -45,4 +57,5 @@ static struct kunit_suite sort_test_suite = { kunit_test_suites(&sort_test_suite); +MODULE_DESCRIPTION("sort() KUnit test suite"); MODULE_LICENSE("GPL"); diff --git a/lib/test_static_key_base.c b/lib/test_static_key_base.c index 5089a2e2bdd8..9f507672afa5 100644 --- a/lib/test_static_key_base.c +++ b/lib/test_static_key_base.c @@ -57,4 +57,5 @@ module_init(test_static_key_base_init); module_exit(test_static_key_base_exit); MODULE_AUTHOR("Jason Baron <jbaron@akamai.com>"); +MODULE_DESCRIPTION("Kernel module to support testing static keys"); MODULE_LICENSE("GPL"); diff --git a/lib/test_static_keys.c b/lib/test_static_keys.c index 42daa74be029..00c715f30df9 100644 --- a/lib/test_static_keys.c +++ b/lib/test_static_keys.c @@ -236,4 +236,5 @@ module_init(test_static_key_init); module_exit(test_static_key_exit); MODULE_AUTHOR("Jason Baron <jbaron@akamai.com>"); +MODULE_DESCRIPTION("Kernel module for testing static keys"); MODULE_LICENSE("GPL"); diff --git a/lib/test_sysctl.c b/lib/test_sysctl.c index 9321d850931f..4249e0cc8aaf 100644 --- a/lib/test_sysctl.c +++ b/lib/test_sysctl.c @@ -71,7 +71,7 @@ static struct test_sysctl_data test_data = { }; /* These are all under /proc/sys/debug/test_sysctl/ */ -static struct ctl_table test_table[] = { +static const struct ctl_table test_table[] = { { .procname = "int_0001", .data = &test_data.int_0001, @@ -177,7 +177,7 @@ static int test_sysctl_setup_node_tests(void) } /* Used to test that unregister actually removes the directory */ -static struct ctl_table test_table_unregister[] = { +static const struct ctl_table test_table_unregister[] = { { .procname = "unregister_error", .data = &test_data.int_0001, @@ -220,7 +220,7 @@ static int test_sysctl_run_register_mount_point(void) return 0; } -static struct ctl_table test_table_empty[] = { }; +static const struct ctl_table test_table_empty[] = { }; static int test_sysctl_run_register_empty(void) { @@ -280,4 +280,5 @@ static void __exit test_sysctl_exit(void) module_exit(test_sysctl_exit); MODULE_AUTHOR("Luis R. Rodriguez <mcgrof@kernel.org>"); +MODULE_DESCRIPTION("proc sysctl test driver"); MODULE_LICENSE("GPL"); diff --git a/lib/test_ubsan.c b/lib/test_ubsan.c index c288df9372ed..5d7b10e98610 100644 --- a/lib/test_ubsan.c +++ b/lib/test_ubsan.c @@ -156,4 +156,5 @@ static void __exit test_ubsan_exit(void) module_exit(test_ubsan_exit); MODULE_AUTHOR("Jinbum Park <jinb.park7@gmail.com>"); +MODULE_DESCRIPTION("UBSAN unit test"); MODULE_LICENSE("GPL v2"); diff --git a/lib/test_user_copy.c b/lib/test_user_copy.c deleted file mode 100644 index 5ff04d8fe971..000000000000 --- a/lib/test_user_copy.c +++ /dev/null @@ -1,331 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Kernel module for testing copy_to/from_user infrastructure. - * - * Copyright 2013 Google Inc. All Rights Reserved - * - * Authors: - * Kees Cook <keescook@chromium.org> - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/mman.h> -#include <linux/module.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/uaccess.h> -#include <linux/vmalloc.h> - -/* - * Several 32-bit architectures support 64-bit {get,put}_user() calls. - * As there doesn't appear to be anything that can safely determine - * their capability at compile-time, we just have to opt-out certain archs. - */ -#if BITS_PER_LONG == 64 || (!(defined(CONFIG_ARM) && !defined(MMU)) && \ - !defined(CONFIG_M68K) && \ - !defined(CONFIG_MICROBLAZE) && \ - !defined(CONFIG_NIOS2) && \ - !defined(CONFIG_PPC32) && \ - !defined(CONFIG_SUPERH)) -# define TEST_U64 -#endif - -#define test(condition, msg, ...) \ -({ \ - int cond = (condition); \ - if (cond) \ - pr_warn("[%d] " msg "\n", __LINE__, ##__VA_ARGS__); \ - cond; \ -}) - -static bool is_zeroed(void *from, size_t size) -{ - return memchr_inv(from, 0x0, size) == NULL; -} - -static int test_check_nonzero_user(char *kmem, char __user *umem, size_t size) -{ - int ret = 0; - size_t start, end, i, zero_start, zero_end; - - if (test(size < 2 * PAGE_SIZE, "buffer too small")) - return -EINVAL; - - /* - * We want to cross a page boundary to exercise the code more - * effectively. We also don't want to make the size we scan too large, - * otherwise the test can take a long time and cause soft lockups. So - * scan a 1024 byte region across the page boundary. - */ - size = 1024; - start = PAGE_SIZE - (size / 2); - - kmem += start; - umem += start; - - zero_start = size / 4; - zero_end = size - zero_start; - - /* - * We conduct a series of check_nonzero_user() tests on a block of - * memory with the following byte-pattern (trying every possible - * [start,end] pair): - * - * [ 00 ff 00 ff ... 00 00 00 00 ... ff 00 ff 00 ] - * - * And we verify that check_nonzero_user() acts identically to - * memchr_inv(). - */ - - memset(kmem, 0x0, size); - for (i = 1; i < zero_start; i += 2) - kmem[i] = 0xff; - for (i = zero_end; i < size; i += 2) - kmem[i] = 0xff; - - ret |= test(copy_to_user(umem, kmem, size), - "legitimate copy_to_user failed"); - - for (start = 0; start <= size; start++) { - for (end = start; end <= size; end++) { - size_t len = end - start; - int retval = check_zeroed_user(umem + start, len); - int expected = is_zeroed(kmem + start, len); - - ret |= test(retval != expected, - "check_nonzero_user(=%d) != memchr_inv(=%d) mismatch (start=%zu, end=%zu)", - retval, expected, start, end); - } - } - - return ret; -} - -static int test_copy_struct_from_user(char *kmem, char __user *umem, - size_t size) -{ - int ret = 0; - char *umem_src = NULL, *expected = NULL; - size_t ksize, usize; - - umem_src = kmalloc(size, GFP_KERNEL); - ret = test(umem_src == NULL, "kmalloc failed"); - if (ret) - goto out_free; - - expected = kmalloc(size, GFP_KERNEL); - ret = test(expected == NULL, "kmalloc failed"); - if (ret) - goto out_free; - - /* Fill umem with a fixed byte pattern. */ - memset(umem_src, 0x3e, size); - ret |= test(copy_to_user(umem, umem_src, size), - "legitimate copy_to_user failed"); - - /* Check basic case -- (usize == ksize). */ - ksize = size; - usize = size; - - memcpy(expected, umem_src, ksize); - - memset(kmem, 0x0, size); - ret |= test(copy_struct_from_user(kmem, ksize, umem, usize), - "copy_struct_from_user(usize == ksize) failed"); - ret |= test(memcmp(kmem, expected, ksize), - "copy_struct_from_user(usize == ksize) gives unexpected copy"); - - /* Old userspace case -- (usize < ksize). */ - ksize = size; - usize = size / 2; - - memcpy(expected, umem_src, usize); - memset(expected + usize, 0x0, ksize - usize); - - memset(kmem, 0x0, size); - ret |= test(copy_struct_from_user(kmem, ksize, umem, usize), - "copy_struct_from_user(usize < ksize) failed"); - ret |= test(memcmp(kmem, expected, ksize), - "copy_struct_from_user(usize < ksize) gives unexpected copy"); - - /* New userspace (-E2BIG) case -- (usize > ksize). */ - ksize = size / 2; - usize = size; - - memset(kmem, 0x0, size); - ret |= test(copy_struct_from_user(kmem, ksize, umem, usize) != -E2BIG, - "copy_struct_from_user(usize > ksize) didn't give E2BIG"); - - /* New userspace (success) case -- (usize > ksize). */ - ksize = size / 2; - usize = size; - - memcpy(expected, umem_src, ksize); - ret |= test(clear_user(umem + ksize, usize - ksize), - "legitimate clear_user failed"); - - memset(kmem, 0x0, size); - ret |= test(copy_struct_from_user(kmem, ksize, umem, usize), - "copy_struct_from_user(usize > ksize) failed"); - ret |= test(memcmp(kmem, expected, ksize), - "copy_struct_from_user(usize > ksize) gives unexpected copy"); - -out_free: - kfree(expected); - kfree(umem_src); - return ret; -} - -static int __init test_user_copy_init(void) -{ - int ret = 0; - char *kmem; - char __user *usermem; - char *bad_usermem; - unsigned long user_addr; - u8 val_u8; - u16 val_u16; - u32 val_u32; -#ifdef TEST_U64 - u64 val_u64; -#endif - - kmem = kmalloc(PAGE_SIZE * 2, GFP_KERNEL); - if (!kmem) - return -ENOMEM; - - user_addr = vm_mmap(NULL, 0, PAGE_SIZE * 2, - PROT_READ | PROT_WRITE | PROT_EXEC, - MAP_ANONYMOUS | MAP_PRIVATE, 0); - if (user_addr >= (unsigned long)(TASK_SIZE)) { - pr_warn("Failed to allocate user memory\n"); - kfree(kmem); - return -ENOMEM; - } - - usermem = (char __user *)user_addr; - bad_usermem = (char *)user_addr; - - /* - * Legitimate usage: none of these copies should fail. - */ - memset(kmem, 0x3a, PAGE_SIZE * 2); - ret |= test(copy_to_user(usermem, kmem, PAGE_SIZE), - "legitimate copy_to_user failed"); - memset(kmem, 0x0, PAGE_SIZE); - ret |= test(copy_from_user(kmem, usermem, PAGE_SIZE), - "legitimate copy_from_user failed"); - ret |= test(memcmp(kmem, kmem + PAGE_SIZE, PAGE_SIZE), - "legitimate usercopy failed to copy data"); - -#define test_legit(size, check) \ - do { \ - val_##size = check; \ - ret |= test(put_user(val_##size, (size __user *)usermem), \ - "legitimate put_user (" #size ") failed"); \ - val_##size = 0; \ - ret |= test(get_user(val_##size, (size __user *)usermem), \ - "legitimate get_user (" #size ") failed"); \ - ret |= test(val_##size != check, \ - "legitimate get_user (" #size ") failed to do copy"); \ - if (val_##size != check) { \ - pr_info("0x%llx != 0x%llx\n", \ - (unsigned long long)val_##size, \ - (unsigned long long)check); \ - } \ - } while (0) - - test_legit(u8, 0x5a); - test_legit(u16, 0x5a5b); - test_legit(u32, 0x5a5b5c5d); -#ifdef TEST_U64 - test_legit(u64, 0x5a5b5c5d6a6b6c6d); -#endif -#undef test_legit - - /* Test usage of check_nonzero_user(). */ - ret |= test_check_nonzero_user(kmem, usermem, 2 * PAGE_SIZE); - /* Test usage of copy_struct_from_user(). */ - ret |= test_copy_struct_from_user(kmem, usermem, 2 * PAGE_SIZE); - - /* - * Invalid usage: none of these copies should succeed. - */ - - /* Prepare kernel memory with check values. */ - memset(kmem, 0x5a, PAGE_SIZE); - memset(kmem + PAGE_SIZE, 0, PAGE_SIZE); - - /* Reject kernel-to-kernel copies through copy_from_user(). */ - ret |= test(!copy_from_user(kmem, (char __user *)(kmem + PAGE_SIZE), - PAGE_SIZE), - "illegal all-kernel copy_from_user passed"); - - /* Destination half of buffer should have been zeroed. */ - ret |= test(memcmp(kmem + PAGE_SIZE, kmem, PAGE_SIZE), - "zeroing failure for illegal all-kernel copy_from_user"); - -#if 0 - /* - * When running with SMAP/PAN/etc, this will Oops the kernel - * due to the zeroing of userspace memory on failure. This needs - * to be tested in LKDTM instead, since this test module does not - * expect to explode. - */ - ret |= test(!copy_from_user(bad_usermem, (char __user *)kmem, - PAGE_SIZE), - "illegal reversed copy_from_user passed"); -#endif - ret |= test(!copy_to_user((char __user *)kmem, kmem + PAGE_SIZE, - PAGE_SIZE), - "illegal all-kernel copy_to_user passed"); - ret |= test(!copy_to_user((char __user *)kmem, bad_usermem, - PAGE_SIZE), - "illegal reversed copy_to_user passed"); - -#define test_illegal(size, check) \ - do { \ - val_##size = (check); \ - ret |= test(!get_user(val_##size, (size __user *)kmem), \ - "illegal get_user (" #size ") passed"); \ - ret |= test(val_##size != (size)0, \ - "zeroing failure for illegal get_user (" #size ")"); \ - if (val_##size != (size)0) { \ - pr_info("0x%llx != 0\n", \ - (unsigned long long)val_##size); \ - } \ - ret |= test(!put_user(val_##size, (size __user *)kmem), \ - "illegal put_user (" #size ") passed"); \ - } while (0) - - test_illegal(u8, 0x5a); - test_illegal(u16, 0x5a5b); - test_illegal(u32, 0x5a5b5c5d); -#ifdef TEST_U64 - test_illegal(u64, 0x5a5b5c5d6a6b6c6d); -#endif -#undef test_illegal - - vm_munmap(user_addr, PAGE_SIZE * 2); - kfree(kmem); - - if (ret == 0) { - pr_info("tests passed.\n"); - return 0; - } - - return -EINVAL; -} - -module_init(test_user_copy_init); - -static void __exit test_user_copy_exit(void) -{ - pr_info("unloaded.\n"); -} - -module_exit(test_user_copy_exit); - -MODULE_AUTHOR("Kees Cook <keescook@chromium.org>"); -MODULE_LICENSE("GPL"); diff --git a/lib/test_uuid.c b/lib/test_uuid.c index cd819c397dc7..0124fad5d72c 100644 --- a/lib/test_uuid.c +++ b/lib/test_uuid.c @@ -130,4 +130,5 @@ static void __exit test_uuid_exit(void) module_exit(test_uuid_exit); MODULE_AUTHOR("Andy Shevchenko <andriy.shevchenko@linux.intel.com>"); +MODULE_DESCRIPTION("Test cases for lib/uuid.c module"); MODULE_LICENSE("Dual BSD/GPL"); diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c index 4ddf769861ff..f585949ff696 100644 --- a/lib/test_vmalloc.c +++ b/lib/test_vmalloc.c @@ -373,7 +373,7 @@ vm_map_ram_test(void) if (!pages) return -1; - nr_allocated = alloc_pages_bulk_array(GFP_KERNEL, map_nr_pages, pages); + nr_allocated = alloc_pages_bulk(GFP_KERNEL, map_nr_pages, pages); if (nr_allocated != map_nr_pages) goto cleanup; diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 928fc20337e6..6932a26f4927 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -1448,6 +1448,41 @@ static noinline void check_pause(struct xarray *xa) XA_BUG_ON(xa, count != order_limit); xa_destroy(xa); + + index = 0; + for (order = XA_CHUNK_SHIFT; order > 0; order--) { + XA_BUG_ON(xa, xa_store_order(xa, index, order, + xa_mk_index(index), GFP_KERNEL)); + index += 1UL << order; + } + + index = 0; + count = 0; + xas_set(&xas, 0); + rcu_read_lock(); + xas_for_each(&xas, entry, ULONG_MAX) { + XA_BUG_ON(xa, entry != xa_mk_index(index)); + index += 1UL << (XA_CHUNK_SHIFT - count); + count++; + } + rcu_read_unlock(); + XA_BUG_ON(xa, count != XA_CHUNK_SHIFT); + + index = 0; + count = 0; + xas_set(&xas, XA_CHUNK_SIZE / 2 + 1); + rcu_read_lock(); + xas_for_each(&xas, entry, ULONG_MAX) { + XA_BUG_ON(xa, entry != xa_mk_index(index)); + index += 1UL << (XA_CHUNK_SHIFT - count); + count++; + xas_pause(&xas); + } + rcu_read_unlock(); + XA_BUG_ON(xa, count != XA_CHUNK_SHIFT); + + xa_destroy(xa); + } static noinline void check_move_tiny(struct xarray *xa) @@ -2001,6 +2036,97 @@ static noinline void check_get_order(struct xarray *xa) } } +static noinline void check_xas_get_order(struct xarray *xa) +{ + XA_STATE(xas, xa, 0); + + unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 20 : 1; + unsigned int order; + unsigned long i, j; + + for (order = 0; order < max_order; order++) { + for (i = 0; i < 10; i++) { + xas_set_order(&xas, i << order, order); + do { + xas_lock(&xas); + xas_store(&xas, xa_mk_value(i)); + xas_unlock(&xas); + } while (xas_nomem(&xas, GFP_KERNEL)); + + for (j = i << order; j < (i + 1) << order; j++) { + xas_set_order(&xas, j, 0); + rcu_read_lock(); + xas_load(&xas); + XA_BUG_ON(xa, xas_get_order(&xas) != order); + rcu_read_unlock(); + } + + xas_lock(&xas); + xas_set_order(&xas, i << order, order); + xas_store(&xas, NULL); + xas_unlock(&xas); + } + } +} + +static noinline void check_xas_conflict_get_order(struct xarray *xa) +{ + XA_STATE(xas, xa, 0); + + void *entry; + int only_once; + unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 20 : 1; + unsigned int order; + unsigned long i, j, k; + + for (order = 0; order < max_order; order++) { + for (i = 0; i < 10; i++) { + xas_set_order(&xas, i << order, order); + do { + xas_lock(&xas); + xas_store(&xas, xa_mk_value(i)); + xas_unlock(&xas); + } while (xas_nomem(&xas, GFP_KERNEL)); + + /* + * Ensure xas_get_order works with xas_for_each_conflict. + */ + j = i << order; + for (k = 0; k < order; k++) { + only_once = 0; + xas_set_order(&xas, j + (1 << k), k); + xas_lock(&xas); + xas_for_each_conflict(&xas, entry) { + XA_BUG_ON(xa, entry != xa_mk_value(i)); + XA_BUG_ON(xa, xas_get_order(&xas) != order); + only_once++; + } + XA_BUG_ON(xa, only_once != 1); + xas_unlock(&xas); + } + + if (order < max_order - 1) { + only_once = 0; + xas_set_order(&xas, (i & ~1UL) << order, order + 1); + xas_lock(&xas); + xas_for_each_conflict(&xas, entry) { + XA_BUG_ON(xa, entry != xa_mk_value(i)); + XA_BUG_ON(xa, xas_get_order(&xas) != order); + only_once++; + } + XA_BUG_ON(xa, only_once != 1); + xas_unlock(&xas); + } + + xas_set_order(&xas, i << order, order); + xas_lock(&xas); + xas_store(&xas, NULL); + xas_unlock(&xas); + } + } +} + + static noinline void check_destroy(struct xarray *xa) { unsigned long index; @@ -2052,6 +2178,8 @@ static int xarray_checks(void) check_multi_store(&array); check_multi_store_advanced(&array); check_get_order(&array); + check_xas_get_order(&array); + check_xas_conflict_get_order(&array); check_xa_alloc(); check_find(&array); check_find_entry(&array); @@ -2080,4 +2208,5 @@ static void xarray_exit(void) module_init(xarray_checks); module_exit(xarray_exit); MODULE_AUTHOR("Matthew Wilcox <willy@infradead.org>"); +MODULE_DESCRIPTION("XArray API test module"); MODULE_LICENSE("GPL"); diff --git a/lib/tests/Makefile b/lib/tests/Makefile new file mode 100644 index 000000000000..8e4f42cb9c54 --- /dev/null +++ b/lib/tests/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_TEST_RUNTIME_MODULE) += module/ diff --git a/lib/tests/module/.gitignore b/lib/tests/module/.gitignore new file mode 100644 index 000000000000..8be7891b250f --- /dev/null +++ b/lib/tests/module/.gitignore @@ -0,0 +1,4 @@ +test_kallsyms_a.c +test_kallsyms_b.c +test_kallsyms_c.c +test_kallsyms_d.c diff --git a/lib/tests/module/Makefile b/lib/tests/module/Makefile new file mode 100644 index 000000000000..2f3e1a772c2c --- /dev/null +++ b/lib/tests/module/Makefile @@ -0,0 +1,14 @@ +obj-$(CONFIG_TEST_KALLSYMS_A) += test_kallsyms_a.o +obj-$(CONFIG_TEST_KALLSYMS_B) += test_kallsyms_b.o +obj-$(CONFIG_TEST_KALLSYMS_C) += test_kallsyms_c.o +obj-$(CONFIG_TEST_KALLSYMS_D) += test_kallsyms_d.o + +quiet_cmd_gen_test_kallsyms = GEN $@ + cmd_gen_test_kallsyms = $< $@ \ + $(CONFIG_TEST_KALLSYMS_NUMSYMS) \ + $(CONFIG_TEST_KALLSYMS_SCALE_FACTOR) + +$(obj)/%.c: $(src)/gen_test_kallsyms.sh FORCE + $(call if_changed,gen_test_kallsyms) + +targets += $(foreach x, a b c d, test_kallsyms_$(x).c) diff --git a/lib/tests/module/gen_test_kallsyms.sh b/lib/tests/module/gen_test_kallsyms.sh new file mode 100755 index 000000000000..561dcac0f359 --- /dev/null +++ b/lib/tests/module/gen_test_kallsyms.sh @@ -0,0 +1,134 @@ +#!/bin/bash + +TARGET=$(basename $1) +DIR=lib/tests/module +TARGET="$DIR/$TARGET" +NUM_SYMS=$2 +SCALE_FACTOR=$3 +TEST_TYPE=$(echo $TARGET | sed -e 's|lib/tests/module/test_kallsyms_||g') +TEST_TYPE=$(echo $TEST_TYPE | sed -e 's|.c||g') +FIRST_B_LOOKUP=1 + +if [[ $NUM_SYMS -gt 2 ]]; then + FIRST_B_LOOKUP=$((NUM_SYMS/2)) +fi + +gen_template_module_header() +{ + cat <<____END_MODULE +// SPDX-License-Identifier: GPL-2.0-or-later OR copyleft-next-0.3.1 +/* + * Copyright (C) 2023 Luis Chamberlain <mcgrof@kernel.org> + * + * Automatically generated code for testing, do not edit manually. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/printk.h> + +____END_MODULE +} + +gen_num_syms() +{ + PREFIX=$1 + NUM=$2 + for i in $(seq 1 $NUM); do + printf "int auto_test_%s_%010d = 0;\n" $PREFIX $i + printf "EXPORT_SYMBOL_GPL(auto_test_%s_%010d);\n" $PREFIX $i + done + echo +} + +gen_template_module_data_a() +{ + gen_num_syms a $1 + cat <<____END_MODULE +static int auto_runtime_test(void) +{ + return 0; +} + +____END_MODULE +} + +gen_template_module_data_b() +{ + printf "\nextern int auto_test_a_%010d;\n\n" $FIRST_B_LOOKUP + echo "static int auto_runtime_test(void)" + echo "{" + printf "\nreturn auto_test_a_%010d;\n" $FIRST_B_LOOKUP + echo "}" +} + +gen_template_module_data_c() +{ + gen_num_syms c $1 + cat <<____END_MODULE +static int auto_runtime_test(void) +{ + return 0; +} + +____END_MODULE +} + +gen_template_module_data_d() +{ + gen_num_syms d $1 + cat <<____END_MODULE +static int auto_runtime_test(void) +{ + return 0; +} + +____END_MODULE +} + +gen_template_module_exit() +{ + cat <<____END_MODULE +static int __init auto_test_module_init(void) +{ + return auto_runtime_test(); +} +module_init(auto_test_module_init); + +static void __exit auto_test_module_exit(void) +{ +} +module_exit(auto_test_module_exit); + +MODULE_AUTHOR("Luis Chamberlain <mcgrof@kernel.org>"); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Test module for kallsyms"); +____END_MODULE +} + +case $TEST_TYPE in + a) + gen_template_module_header > $TARGET + gen_template_module_data_a $NUM_SYMS >> $TARGET + gen_template_module_exit >> $TARGET + ;; + b) + gen_template_module_header > $TARGET + gen_template_module_data_b >> $TARGET + gen_template_module_exit >> $TARGET + ;; + c) + gen_template_module_header > $TARGET + gen_template_module_data_c $((NUM_SYMS * SCALE_FACTOR)) >> $TARGET + gen_template_module_exit >> $TARGET + ;; + d) + gen_template_module_header > $TARGET + gen_template_module_data_d $((NUM_SYMS * SCALE_FACTOR * 2)) >> $TARGET + gen_template_module_exit >> $TARGET + ;; + *) + ;; +esac diff --git a/lib/ts_bm.c b/lib/ts_bm.c index e5f30f9177df..eed5967238c5 100644 --- a/lib/ts_bm.c +++ b/lib/ts_bm.c @@ -216,6 +216,7 @@ static void __exit exit_bm(void) textsearch_unregister(&bm_ops); } +MODULE_DESCRIPTION("Boyer-Moore text search implementation"); MODULE_LICENSE("GPL"); module_init(init_bm); diff --git a/lib/ts_fsm.c b/lib/ts_fsm.c index 64fd9015ad80..053615f4fcd7 100644 --- a/lib/ts_fsm.c +++ b/lib/ts_fsm.c @@ -331,6 +331,7 @@ static void __exit exit_fsm(void) textsearch_unregister(&fsm_ops); } +MODULE_DESCRIPTION("naive finite state machine text search"); MODULE_LICENSE("GPL"); module_init(init_fsm); diff --git a/lib/ts_kmp.c b/lib/ts_kmp.c index c77a3d537f24..5520dc28255a 100644 --- a/lib/ts_kmp.c +++ b/lib/ts_kmp.c @@ -147,6 +147,7 @@ static void __exit exit_kmp(void) textsearch_unregister(&kmp_ops); } +MODULE_DESCRIPTION("Knuth-Morris-Pratt text search implementation"); MODULE_LICENSE("GPL"); module_init(init_kmp); diff --git a/lib/union_find.c b/lib/union_find.c new file mode 100644 index 000000000000..413b0f8adf7a --- /dev/null +++ b/lib/union_find.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/union_find.h> + +/** + * uf_find - Find the root of a node and perform path compression + * @node: the node to find the root of + * + * This function returns the root of the node by following the parent + * pointers. It also performs path compression, making the tree shallower. + * + * Returns the root node of the set containing node. + */ +struct uf_node *uf_find(struct uf_node *node) +{ + struct uf_node *parent; + + while (node->parent != node) { + parent = node->parent; + node->parent = parent->parent; + node = parent; + } + return node; +} + +/** + * uf_union - Merge two sets, using union by rank + * @node1: the first node + * @node2: the second node + * + * This function merges the sets containing node1 and node2, by comparing + * the ranks to keep the tree balanced. + */ +void uf_union(struct uf_node *node1, struct uf_node *node2) +{ + struct uf_node *root1 = uf_find(node1); + struct uf_node *root2 = uf_find(node2); + + if (root1 == root2) + return; + + if (root1->rank < root2->rank) { + root1->parent = root2; + } else if (root1->rank > root2->rank) { + root2->parent = root1; + } else { + root2->parent = root1; + root1->rank++; + } +} diff --git a/lib/usercopy.c b/lib/usercopy.c index d29fe29c6849..7b17b83c8042 100644 --- a/lib/usercopy.c +++ b/lib/usercopy.c @@ -1,46 +1,29 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/bitops.h> +#include <linux/compiler.h> +#include <linux/errno.h> +#include <linux/export.h> #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> -#include <linux/uaccess.h> +#include <linux/kernel.h> #include <linux/nospec.h> +#include <linux/string.h> +#include <linux/uaccess.h> +#include <linux/wordpart.h> /* out-of-line parts */ -#ifndef INLINE_COPY_FROM_USER +#if !defined(INLINE_COPY_FROM_USER) || defined(CONFIG_RUST) unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n) { - unsigned long res = n; - might_fault(); - if (!should_fail_usercopy() && likely(access_ok(from, n))) { - /* - * Ensure that bad access_ok() speculation will not - * lead to nasty side effects *after* the copy is - * finished: - */ - barrier_nospec(); - instrument_copy_from_user_before(to, from, n); - res = raw_copy_from_user(to, from, n); - instrument_copy_from_user_after(to, from, n, res); - } - if (unlikely(res)) - memset(to + (n - res), 0, res); - return res; + return _inline_copy_from_user(to, from, n); } EXPORT_SYMBOL(_copy_from_user); #endif -#ifndef INLINE_COPY_TO_USER +#if !defined(INLINE_COPY_TO_USER) || defined(CONFIG_RUST) unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n) { - might_fault(); - if (should_fail_usercopy()) - return n; - if (likely(access_ok(to, n))) { - instrument_copy_to_user(to, from, n); - n = raw_copy_to_user(to, from, n); - } - return n; + return _inline_copy_to_user(to, from, n); } EXPORT_SYMBOL(_copy_to_user); #endif diff --git a/lib/usercopy_kunit.c b/lib/usercopy_kunit.c new file mode 100644 index 000000000000..77fa00a13df7 --- /dev/null +++ b/lib/usercopy_kunit.c @@ -0,0 +1,335 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Kernel module for testing copy_to/from_user infrastructure. + * + * Copyright 2013 Google Inc. All Rights Reserved + * + * Authors: + * Kees Cook <keescook@chromium.org> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/mman.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <kunit/test.h> + +/* + * Several 32-bit architectures support 64-bit {get,put}_user() calls. + * As there doesn't appear to be anything that can safely determine + * their capability at compile-time, we just have to opt-out certain archs. + */ +#if BITS_PER_LONG == 64 || (!(defined(CONFIG_ARM) && !defined(MMU)) && \ + !defined(CONFIG_M68K) && \ + !defined(CONFIG_MICROBLAZE) && \ + !defined(CONFIG_NIOS2) && \ + !defined(CONFIG_PPC32) && \ + !defined(CONFIG_SUPERH)) +# define TEST_U64 +#endif + +struct usercopy_test_priv { + char *kmem; + char __user *umem; + size_t size; +}; + +static bool is_zeroed(void *from, size_t size) +{ + return memchr_inv(from, 0x0, size) == NULL; +} + +/* Test usage of check_nonzero_user(). */ +static void usercopy_test_check_nonzero_user(struct kunit *test) +{ + size_t start, end, i, zero_start, zero_end; + struct usercopy_test_priv *priv = test->priv; + char __user *umem = priv->umem; + char *kmem = priv->kmem; + size_t size = priv->size; + + KUNIT_ASSERT_GE_MSG(test, size, 2 * PAGE_SIZE, "buffer too small"); + + /* + * We want to cross a page boundary to exercise the code more + * effectively. We also don't want to make the size we scan too large, + * otherwise the test can take a long time and cause soft lockups. So + * scan a 1024 byte region across the page boundary. + */ + size = 1024; + start = PAGE_SIZE - (size / 2); + + kmem += start; + umem += start; + + zero_start = size / 4; + zero_end = size - zero_start; + + /* + * We conduct a series of check_nonzero_user() tests on a block of + * memory with the following byte-pattern (trying every possible + * [start,end] pair): + * + * [ 00 ff 00 ff ... 00 00 00 00 ... ff 00 ff 00 ] + * + * And we verify that check_nonzero_user() acts identically to + * memchr_inv(). + */ + + memset(kmem, 0x0, size); + for (i = 1; i < zero_start; i += 2) + kmem[i] = 0xff; + for (i = zero_end; i < size; i += 2) + kmem[i] = 0xff; + + KUNIT_EXPECT_EQ_MSG(test, copy_to_user(umem, kmem, size), 0, + "legitimate copy_to_user failed"); + + for (start = 0; start <= size; start++) { + for (end = start; end <= size; end++) { + size_t len = end - start; + int retval = check_zeroed_user(umem + start, len); + int expected = is_zeroed(kmem + start, len); + + KUNIT_ASSERT_EQ_MSG(test, retval, expected, + "check_nonzero_user(=%d) != memchr_inv(=%d) mismatch (start=%zu, end=%zu)", + retval, expected, start, end); + } + } +} + +/* Test usage of copy_struct_from_user(). */ +static void usercopy_test_copy_struct_from_user(struct kunit *test) +{ + char *umem_src = NULL, *expected = NULL; + struct usercopy_test_priv *priv = test->priv; + char __user *umem = priv->umem; + char *kmem = priv->kmem; + size_t size = priv->size; + size_t ksize, usize; + + umem_src = kunit_kmalloc(test, size, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, umem_src); + + expected = kunit_kmalloc(test, size, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, expected); + + /* Fill umem with a fixed byte pattern. */ + memset(umem_src, 0x3e, size); + KUNIT_ASSERT_EQ_MSG(test, copy_to_user(umem, umem_src, size), 0, + "legitimate copy_to_user failed"); + + /* Check basic case -- (usize == ksize). */ + ksize = size; + usize = size; + + memcpy(expected, umem_src, ksize); + + memset(kmem, 0x0, size); + KUNIT_EXPECT_EQ_MSG(test, copy_struct_from_user(kmem, ksize, umem, usize), 0, + "copy_struct_from_user(usize == ksize) failed"); + KUNIT_EXPECT_MEMEQ_MSG(test, kmem, expected, ksize, + "copy_struct_from_user(usize == ksize) gives unexpected copy"); + + /* Old userspace case -- (usize < ksize). */ + ksize = size; + usize = size / 2; + + memcpy(expected, umem_src, usize); + memset(expected + usize, 0x0, ksize - usize); + + memset(kmem, 0x0, size); + KUNIT_EXPECT_EQ_MSG(test, copy_struct_from_user(kmem, ksize, umem, usize), 0, + "copy_struct_from_user(usize < ksize) failed"); + KUNIT_EXPECT_MEMEQ_MSG(test, kmem, expected, ksize, + "copy_struct_from_user(usize < ksize) gives unexpected copy"); + + /* New userspace (-E2BIG) case -- (usize > ksize). */ + ksize = size / 2; + usize = size; + + memset(kmem, 0x0, size); + KUNIT_EXPECT_EQ_MSG(test, copy_struct_from_user(kmem, ksize, umem, usize), -E2BIG, + "copy_struct_from_user(usize > ksize) didn't give E2BIG"); + + /* New userspace (success) case -- (usize > ksize). */ + ksize = size / 2; + usize = size; + + memcpy(expected, umem_src, ksize); + KUNIT_EXPECT_EQ_MSG(test, clear_user(umem + ksize, usize - ksize), 0, + "legitimate clear_user failed"); + + memset(kmem, 0x0, size); + KUNIT_EXPECT_EQ_MSG(test, copy_struct_from_user(kmem, ksize, umem, usize), 0, + "copy_struct_from_user(usize > ksize) failed"); + KUNIT_EXPECT_MEMEQ_MSG(test, kmem, expected, ksize, + "copy_struct_from_user(usize > ksize) gives unexpected copy"); +} + +/* + * Legitimate usage: none of these copies should fail. + */ +static void usercopy_test_valid(struct kunit *test) +{ + struct usercopy_test_priv *priv = test->priv; + char __user *usermem = priv->umem; + char *kmem = priv->kmem; + + memset(kmem, 0x3a, PAGE_SIZE * 2); + KUNIT_EXPECT_EQ_MSG(test, 0, copy_to_user(usermem, kmem, PAGE_SIZE), + "legitimate copy_to_user failed"); + memset(kmem, 0x0, PAGE_SIZE); + KUNIT_EXPECT_EQ_MSG(test, 0, copy_from_user(kmem, usermem, PAGE_SIZE), + "legitimate copy_from_user failed"); + KUNIT_EXPECT_MEMEQ_MSG(test, kmem, kmem + PAGE_SIZE, PAGE_SIZE, + "legitimate usercopy failed to copy data"); + +#define test_legit(size, check) \ + do { \ + size val_##size = (check); \ + KUNIT_EXPECT_EQ_MSG(test, 0, \ + put_user(val_##size, (size __user *)usermem), \ + "legitimate put_user (" #size ") failed"); \ + val_##size = 0; \ + KUNIT_EXPECT_EQ_MSG(test, 0, \ + get_user(val_##size, (size __user *)usermem), \ + "legitimate get_user (" #size ") failed"); \ + KUNIT_EXPECT_EQ_MSG(test, val_##size, check, \ + "legitimate get_user (" #size ") failed to do copy"); \ + } while (0) + + test_legit(u8, 0x5a); + test_legit(u16, 0x5a5b); + test_legit(u32, 0x5a5b5c5d); +#ifdef TEST_U64 + test_legit(u64, 0x5a5b5c5d6a6b6c6d); +#endif +#undef test_legit +} + +/* + * Invalid usage: none of these copies should succeed. + */ +static void usercopy_test_invalid(struct kunit *test) +{ + struct usercopy_test_priv *priv = test->priv; + char __user *usermem = priv->umem; + char *bad_usermem = (char *)usermem; + char *kmem = priv->kmem; + u64 *kmem_u64 = (u64 *)kmem; + + if (IS_ENABLED(CONFIG_ALTERNATE_USER_ADDRESS_SPACE) || + !IS_ENABLED(CONFIG_MMU)) { + kunit_skip(test, "Testing for kernel/userspace address confusion is only sensible on architectures with a shared address space"); + return; + } + + /* Prepare kernel memory with check values. */ + memset(kmem, 0x5a, PAGE_SIZE); + memset(kmem + PAGE_SIZE, 0, PAGE_SIZE); + + /* Reject kernel-to-kernel copies through copy_from_user(). */ + KUNIT_EXPECT_NE_MSG(test, copy_from_user(kmem, (char __user *)(kmem + PAGE_SIZE), + PAGE_SIZE), 0, + "illegal all-kernel copy_from_user passed"); + + /* Destination half of buffer should have been zeroed. */ + KUNIT_EXPECT_MEMEQ_MSG(test, kmem + PAGE_SIZE, kmem, PAGE_SIZE, + "zeroing failure for illegal all-kernel copy_from_user"); + +#if 0 + /* + * When running with SMAP/PAN/etc, this will Oops the kernel + * due to the zeroing of userspace memory on failure. This needs + * to be tested in LKDTM instead, since this test module does not + * expect to explode. + */ + KUNIT_EXPECT_NE_MSG(test, copy_from_user(bad_usermem, (char __user *)kmem, + PAGE_SIZE), 0, + "illegal reversed copy_from_user passed"); +#endif + KUNIT_EXPECT_NE_MSG(test, copy_to_user((char __user *)kmem, kmem + PAGE_SIZE, + PAGE_SIZE), 0, + "illegal all-kernel copy_to_user passed"); + + KUNIT_EXPECT_NE_MSG(test, copy_to_user((char __user *)kmem, bad_usermem, + PAGE_SIZE), 0, + "illegal reversed copy_to_user passed"); + +#define test_illegal(size, check) \ + do { \ + size val_##size = (check); \ + /* get_user() */ \ + KUNIT_EXPECT_NE_MSG(test, get_user(val_##size, (size __user *)kmem), 0, \ + "illegal get_user (" #size ") passed"); \ + KUNIT_EXPECT_EQ_MSG(test, val_##size, 0, \ + "zeroing failure for illegal get_user (" #size ")"); \ + /* put_user() */ \ + *kmem_u64 = 0xF09FA4AFF09FA4AF; \ + KUNIT_EXPECT_NE_MSG(test, put_user(val_##size, (size __user *)kmem), 0, \ + "illegal put_user (" #size ") passed"); \ + KUNIT_EXPECT_EQ_MSG(test, *kmem_u64, 0xF09FA4AFF09FA4AF, \ + "illegal put_user (" #size ") wrote to kernel memory!"); \ + } while (0) + + test_illegal(u8, 0x5a); + test_illegal(u16, 0x5a5b); + test_illegal(u32, 0x5a5b5c5d); +#ifdef TEST_U64 + test_illegal(u64, 0x5a5b5c5d6a6b6c6d); +#endif +#undef test_illegal +} + +static int usercopy_test_init(struct kunit *test) +{ + struct usercopy_test_priv *priv; + unsigned long user_addr; + + if (!IS_ENABLED(CONFIG_MMU)) { + kunit_skip(test, "Userspace allocation testing not available on non-MMU systems"); + return 0; + } + + priv = kunit_kzalloc(test, sizeof(*priv), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, priv); + test->priv = priv; + priv->size = PAGE_SIZE * 2; + + priv->kmem = kunit_kmalloc(test, priv->size, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, priv->kmem); + + user_addr = kunit_vm_mmap(test, NULL, 0, priv->size, + PROT_READ | PROT_WRITE | PROT_EXEC, + MAP_ANONYMOUS | MAP_PRIVATE, 0); + KUNIT_ASSERT_NE_MSG(test, user_addr, 0, + "Could not create userspace mm"); + KUNIT_ASSERT_LT_MSG(test, user_addr, (unsigned long)TASK_SIZE, + "Failed to allocate user memory"); + priv->umem = (char __user *)user_addr; + + return 0; +} + +static struct kunit_case usercopy_test_cases[] = { + KUNIT_CASE(usercopy_test_valid), + KUNIT_CASE(usercopy_test_invalid), + KUNIT_CASE(usercopy_test_check_nonzero_user), + KUNIT_CASE(usercopy_test_copy_struct_from_user), + {} +}; + +static struct kunit_suite usercopy_test_suite = { + .name = "usercopy", + .init = usercopy_test_init, + .test_cases = usercopy_test_cases, +}; + +kunit_test_suites(&usercopy_test_suite); +MODULE_AUTHOR("Kees Cook <kees@kernel.org>"); +MODULE_DESCRIPTION("Kernel module for testing copy_to/from_user infrastructure"); +MODULE_LICENSE("GPL"); diff --git a/lib/util_macros_kunit.c b/lib/util_macros_kunit.c new file mode 100644 index 000000000000..94cc9f0de50a --- /dev/null +++ b/lib/util_macros_kunit.c @@ -0,0 +1,240 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Test cases for bitfield helpers. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <kunit/test.h> +#include <linux/util_macros.h> + +#define FIND_CLOSEST_RANGE_CHECK(from, to, array, exp_idx) \ +{ \ + int i; \ + for (i = from; i <= to; i++) { \ + int found = find_closest(i, array, ARRAY_SIZE(array)); \ + KUNIT_ASSERT_EQ(ctx, exp_idx, found); \ + } \ +} + +static void test_find_closest(struct kunit *ctx) +{ + /* This will test a few arrays that are found in drivers */ + static const int ina226_avg_tab[] = { 1, 4, 16, 64, 128, 256, 512, 1024 }; + static const unsigned int ad7616_oversampling_avail[] = { + 1, 2, 4, 8, 16, 32, 64, 128, + }; + static u32 wd_timeout_table[] = { 2, 4, 6, 8, 16, 32, 48, 64 }; + static int array_prog1a[] = { 1, 2, 3, 4, 5 }; + static u32 array_prog1b[] = { 2, 3, 4, 5, 6 }; + static int array_prog1mix[] = { -2, -1, 0, 1, 2 }; + static int array_prog2a[] = { 1, 3, 5, 7 }; + static u32 array_prog2b[] = { 2, 4, 6, 8 }; + static int array_prog3a[] = { 1, 4, 7, 10 }; + static u32 array_prog3b[] = { 2, 5, 8, 11 }; + static int array_prog4a[] = { 1, 5, 9, 13 }; + static u32 array_prog4b[] = { 2, 6, 10, 14 }; + + FIND_CLOSEST_RANGE_CHECK(-3, 2, ina226_avg_tab, 0); + FIND_CLOSEST_RANGE_CHECK(3, 10, ina226_avg_tab, 1); + FIND_CLOSEST_RANGE_CHECK(11, 40, ina226_avg_tab, 2); + FIND_CLOSEST_RANGE_CHECK(41, 96, ina226_avg_tab, 3); + FIND_CLOSEST_RANGE_CHECK(97, 192, ina226_avg_tab, 4); + FIND_CLOSEST_RANGE_CHECK(193, 384, ina226_avg_tab, 5); + FIND_CLOSEST_RANGE_CHECK(385, 768, ina226_avg_tab, 6); + FIND_CLOSEST_RANGE_CHECK(769, 2048, ina226_avg_tab, 7); + + /* The array that found the bug that caused this kunit to exist */ + FIND_CLOSEST_RANGE_CHECK(-3, 1, ad7616_oversampling_avail, 0); + FIND_CLOSEST_RANGE_CHECK(2, 3, ad7616_oversampling_avail, 1); + FIND_CLOSEST_RANGE_CHECK(4, 6, ad7616_oversampling_avail, 2); + FIND_CLOSEST_RANGE_CHECK(7, 12, ad7616_oversampling_avail, 3); + FIND_CLOSEST_RANGE_CHECK(13, 24, ad7616_oversampling_avail, 4); + FIND_CLOSEST_RANGE_CHECK(25, 48, ad7616_oversampling_avail, 5); + FIND_CLOSEST_RANGE_CHECK(49, 96, ad7616_oversampling_avail, 6); + FIND_CLOSEST_RANGE_CHECK(97, 256, ad7616_oversampling_avail, 7); + + FIND_CLOSEST_RANGE_CHECK(-3, 3, wd_timeout_table, 0); + FIND_CLOSEST_RANGE_CHECK(4, 5, wd_timeout_table, 1); + FIND_CLOSEST_RANGE_CHECK(6, 7, wd_timeout_table, 2); + FIND_CLOSEST_RANGE_CHECK(8, 12, wd_timeout_table, 3); + FIND_CLOSEST_RANGE_CHECK(13, 24, wd_timeout_table, 4); + FIND_CLOSEST_RANGE_CHECK(25, 40, wd_timeout_table, 5); + FIND_CLOSEST_RANGE_CHECK(41, 56, wd_timeout_table, 6); + FIND_CLOSEST_RANGE_CHECK(57, 128, wd_timeout_table, 7); + + /* One could argue that find_closest() should not be used for monotonic + * arrays (like 1,2,3,4,5), but even so, it should work as long as the + * array is sorted ascending. */ + FIND_CLOSEST_RANGE_CHECK(-3, 1, array_prog1a, 0); + FIND_CLOSEST_RANGE_CHECK(2, 2, array_prog1a, 1); + FIND_CLOSEST_RANGE_CHECK(3, 3, array_prog1a, 2); + FIND_CLOSEST_RANGE_CHECK(4, 4, array_prog1a, 3); + FIND_CLOSEST_RANGE_CHECK(5, 8, array_prog1a, 4); + + FIND_CLOSEST_RANGE_CHECK(-3, 2, array_prog1b, 0); + FIND_CLOSEST_RANGE_CHECK(3, 3, array_prog1b, 1); + FIND_CLOSEST_RANGE_CHECK(4, 4, array_prog1b, 2); + FIND_CLOSEST_RANGE_CHECK(5, 5, array_prog1b, 3); + FIND_CLOSEST_RANGE_CHECK(6, 8, array_prog1b, 4); + + FIND_CLOSEST_RANGE_CHECK(-4, -2, array_prog1mix, 0); + FIND_CLOSEST_RANGE_CHECK(-1, -1, array_prog1mix, 1); + FIND_CLOSEST_RANGE_CHECK(0, 0, array_prog1mix, 2); + FIND_CLOSEST_RANGE_CHECK(1, 1, array_prog1mix, 3); + FIND_CLOSEST_RANGE_CHECK(2, 5, array_prog1mix, 4); + + FIND_CLOSEST_RANGE_CHECK(-3, 2, array_prog2a, 0); + FIND_CLOSEST_RANGE_CHECK(3, 4, array_prog2a, 1); + FIND_CLOSEST_RANGE_CHECK(5, 6, array_prog2a, 2); + FIND_CLOSEST_RANGE_CHECK(7, 10, array_prog2a, 3); + + FIND_CLOSEST_RANGE_CHECK(-3, 3, array_prog2b, 0); + FIND_CLOSEST_RANGE_CHECK(4, 5, array_prog2b, 1); + FIND_CLOSEST_RANGE_CHECK(6, 7, array_prog2b, 2); + FIND_CLOSEST_RANGE_CHECK(8, 10, array_prog2b, 3); + + FIND_CLOSEST_RANGE_CHECK(-3, 2, array_prog3a, 0); + FIND_CLOSEST_RANGE_CHECK(3, 5, array_prog3a, 1); + FIND_CLOSEST_RANGE_CHECK(6, 8, array_prog3a, 2); + FIND_CLOSEST_RANGE_CHECK(9, 20, array_prog3a, 3); + + FIND_CLOSEST_RANGE_CHECK(-3, 3, array_prog3b, 0); + FIND_CLOSEST_RANGE_CHECK(4, 6, array_prog3b, 1); + FIND_CLOSEST_RANGE_CHECK(7, 9, array_prog3b, 2); + FIND_CLOSEST_RANGE_CHECK(10, 20, array_prog3b, 3); + + FIND_CLOSEST_RANGE_CHECK(-3, 3, array_prog4a, 0); + FIND_CLOSEST_RANGE_CHECK(4, 7, array_prog4a, 1); + FIND_CLOSEST_RANGE_CHECK(8, 11, array_prog4a, 2); + FIND_CLOSEST_RANGE_CHECK(12, 20, array_prog4a, 3); + + FIND_CLOSEST_RANGE_CHECK(-3, 4, array_prog4b, 0); + FIND_CLOSEST_RANGE_CHECK(5, 8, array_prog4b, 1); + FIND_CLOSEST_RANGE_CHECK(9, 12, array_prog4b, 2); + FIND_CLOSEST_RANGE_CHECK(13, 20, array_prog4b, 3); +} + +#define FIND_CLOSEST_DESC_RANGE_CHECK(from, to, array, exp_idx) \ +{ \ + int i; \ + for (i = from; i <= to; i++) { \ + int found = find_closest_descending(i, array, \ + ARRAY_SIZE(array)); \ + KUNIT_ASSERT_EQ(ctx, exp_idx, found); \ + } \ +} + +static void test_find_closest_descending(struct kunit *ctx) +{ + /* Same arrays as 'test_find_closest' but reversed */ + static const int ina226_avg_tab[] = { 1024, 512, 256, 128, 64, 16, 4, 1 }; + static const unsigned int ad7616_oversampling_avail[] = { + 128, 64, 32, 16, 8, 4, 2, 1 + }; + static u32 wd_timeout_table[] = { 64, 48, 32, 16, 8, 6, 4, 2 }; + static int array_prog1a[] = { 5, 4, 3, 2, 1 }; + static u32 array_prog1b[] = { 6, 5, 4, 3, 2 }; + static int array_prog1mix[] = { 2, 1, 0, -1, -2 }; + static int array_prog2a[] = { 7, 5, 3, 1 }; + static u32 array_prog2b[] = { 8, 6, 4, 2 }; + static int array_prog3a[] = { 10, 7, 4, 1 }; + static u32 array_prog3b[] = { 11, 8, 5, 2 }; + static int array_prog4a[] = { 13, 9, 5, 1 }; + static u32 array_prog4b[] = { 14, 10, 6, 2 }; + + FIND_CLOSEST_DESC_RANGE_CHECK(-3, 2, ina226_avg_tab, 7); + FIND_CLOSEST_DESC_RANGE_CHECK(3, 10, ina226_avg_tab, 6); + FIND_CLOSEST_DESC_RANGE_CHECK(11, 40, ina226_avg_tab, 5); + FIND_CLOSEST_DESC_RANGE_CHECK(41, 96, ina226_avg_tab, 4); + FIND_CLOSEST_DESC_RANGE_CHECK(97, 192, ina226_avg_tab, 3); + FIND_CLOSEST_DESC_RANGE_CHECK(193, 384, ina226_avg_tab, 2); + FIND_CLOSEST_DESC_RANGE_CHECK(385, 768, ina226_avg_tab, 1); + FIND_CLOSEST_DESC_RANGE_CHECK(769, 2048, ina226_avg_tab, 0); + + FIND_CLOSEST_DESC_RANGE_CHECK(-3, 1, ad7616_oversampling_avail, 7); + FIND_CLOSEST_DESC_RANGE_CHECK(2, 3, ad7616_oversampling_avail, 6); + FIND_CLOSEST_DESC_RANGE_CHECK(4, 6, ad7616_oversampling_avail, 5); + FIND_CLOSEST_DESC_RANGE_CHECK(7, 12, ad7616_oversampling_avail, 4); + FIND_CLOSEST_DESC_RANGE_CHECK(13, 24, ad7616_oversampling_avail, 3); + FIND_CLOSEST_DESC_RANGE_CHECK(25, 48, ad7616_oversampling_avail, 2); + FIND_CLOSEST_DESC_RANGE_CHECK(49, 96, ad7616_oversampling_avail, 1); + FIND_CLOSEST_DESC_RANGE_CHECK(97, 256, ad7616_oversampling_avail, 0); + + FIND_CLOSEST_DESC_RANGE_CHECK(-3, 3, wd_timeout_table, 7); + FIND_CLOSEST_DESC_RANGE_CHECK(4, 5, wd_timeout_table, 6); + FIND_CLOSEST_DESC_RANGE_CHECK(6, 7, wd_timeout_table, 5); + FIND_CLOSEST_DESC_RANGE_CHECK(8, 12, wd_timeout_table, 4); + FIND_CLOSEST_DESC_RANGE_CHECK(13, 24, wd_timeout_table, 3); + FIND_CLOSEST_DESC_RANGE_CHECK(25, 40, wd_timeout_table, 2); + FIND_CLOSEST_DESC_RANGE_CHECK(41, 56, wd_timeout_table, 1); + FIND_CLOSEST_DESC_RANGE_CHECK(57, 128, wd_timeout_table, 0); + + /* One could argue that find_closest_descending() should not be used + * for monotonic arrays (like 5,4,3,2,1), but even so, it should still + * it should work as long as the array is sorted descending. */ + FIND_CLOSEST_DESC_RANGE_CHECK(-3, 1, array_prog1a, 4); + FIND_CLOSEST_DESC_RANGE_CHECK(2, 2, array_prog1a, 3); + FIND_CLOSEST_DESC_RANGE_CHECK(3, 3, array_prog1a, 2); + FIND_CLOSEST_DESC_RANGE_CHECK(4, 4, array_prog1a, 1); + FIND_CLOSEST_DESC_RANGE_CHECK(5, 8, array_prog1a, 0); + + FIND_CLOSEST_DESC_RANGE_CHECK(-3, 2, array_prog1b, 4); + FIND_CLOSEST_DESC_RANGE_CHECK(3, 3, array_prog1b, 3); + FIND_CLOSEST_DESC_RANGE_CHECK(4, 4, array_prog1b, 2); + FIND_CLOSEST_DESC_RANGE_CHECK(5, 5, array_prog1b, 1); + FIND_CLOSEST_DESC_RANGE_CHECK(6, 8, array_prog1b, 0); + + FIND_CLOSEST_DESC_RANGE_CHECK(-4, -2, array_prog1mix, 4); + FIND_CLOSEST_DESC_RANGE_CHECK(-1, -1, array_prog1mix, 3); + FIND_CLOSEST_DESC_RANGE_CHECK(0, 0, array_prog1mix, 2); + FIND_CLOSEST_DESC_RANGE_CHECK(1, 1, array_prog1mix, 1); + FIND_CLOSEST_DESC_RANGE_CHECK(2, 5, array_prog1mix, 0); + + FIND_CLOSEST_DESC_RANGE_CHECK(-3, 2, array_prog2a, 3); + FIND_CLOSEST_DESC_RANGE_CHECK(3, 4, array_prog2a, 2); + FIND_CLOSEST_DESC_RANGE_CHECK(5, 6, array_prog2a, 1); + FIND_CLOSEST_DESC_RANGE_CHECK(7, 10, array_prog2a, 0); + + FIND_CLOSEST_DESC_RANGE_CHECK(-3, 3, array_prog2b, 3); + FIND_CLOSEST_DESC_RANGE_CHECK(4, 5, array_prog2b, 2); + FIND_CLOSEST_DESC_RANGE_CHECK(6, 7, array_prog2b, 1); + FIND_CLOSEST_DESC_RANGE_CHECK(8, 10, array_prog2b, 0); + + FIND_CLOSEST_DESC_RANGE_CHECK(-3, 2, array_prog3a, 3); + FIND_CLOSEST_DESC_RANGE_CHECK(3, 5, array_prog3a, 2); + FIND_CLOSEST_DESC_RANGE_CHECK(6, 8, array_prog3a, 1); + FIND_CLOSEST_DESC_RANGE_CHECK(9, 20, array_prog3a, 0); + + FIND_CLOSEST_DESC_RANGE_CHECK(-3, 3, array_prog3b, 3); + FIND_CLOSEST_DESC_RANGE_CHECK(4, 6, array_prog3b, 2); + FIND_CLOSEST_DESC_RANGE_CHECK(7, 9, array_prog3b, 1); + FIND_CLOSEST_DESC_RANGE_CHECK(10, 20, array_prog3b, 0); + + FIND_CLOSEST_DESC_RANGE_CHECK(-3, 3, array_prog4a, 3); + FIND_CLOSEST_DESC_RANGE_CHECK(4, 7, array_prog4a, 2); + FIND_CLOSEST_DESC_RANGE_CHECK(8, 11, array_prog4a, 1); + FIND_CLOSEST_DESC_RANGE_CHECK(12, 20, array_prog4a, 0); + + FIND_CLOSEST_DESC_RANGE_CHECK(-3, 4, array_prog4b, 3); + FIND_CLOSEST_DESC_RANGE_CHECK(5, 8, array_prog4b, 2); + FIND_CLOSEST_DESC_RANGE_CHECK(9, 12, array_prog4b, 1); + FIND_CLOSEST_DESC_RANGE_CHECK(13, 20, array_prog4b, 0); +} + +static struct kunit_case __refdata util_macros_test_cases[] = { + KUNIT_CASE(test_find_closest), + KUNIT_CASE(test_find_closest_descending), + {} +}; + +static struct kunit_suite util_macros_test_suite = { + .name = "util_macros.h", + .test_cases = util_macros_test_cases, +}; + +kunit_test_suites(&util_macros_test_suite); + +MODULE_AUTHOR("Alexandru Ardelean <aardelean@baylibre.com>"); +MODULE_DESCRIPTION("Test cases for util_macros.h helpers"); +MODULE_LICENSE("GPL"); diff --git a/lib/vdso/Kconfig b/lib/vdso/Kconfig index c46c2300517c..82fe827af542 100644 --- a/lib/vdso/Kconfig +++ b/lib/vdso/Kconfig @@ -38,3 +38,8 @@ config GENERIC_VDSO_OVERFLOW_PROTECT in the hotpath. endif + +config VDSO_GETRANDOM + bool + help + Selected by architectures that support vDSO getrandom(). diff --git a/lib/vdso/Makefile b/lib/vdso/Makefile index 9f031eafc465..cedbf15f8087 100644 --- a/lib/vdso/Makefile +++ b/lib/vdso/Makefile @@ -4,6 +4,7 @@ GENERIC_VDSO_MK_PATH := $(abspath $(lastword $(MAKEFILE_LIST))) GENERIC_VDSO_DIR := $(dir $(GENERIC_VDSO_MK_PATH)) c-gettimeofday-$(CONFIG_GENERIC_GETTIMEOFDAY) := $(addprefix $(GENERIC_VDSO_DIR), gettimeofday.c) +c-getrandom-$(CONFIG_VDSO_GETRANDOM) := $(addprefix $(GENERIC_VDSO_DIR), getrandom.c) # This cmd checks that the vdso library does not contain dynamic relocations. # It has to be called after the linking of the vdso library and requires it diff --git a/lib/vdso/getrandom.c b/lib/vdso/getrandom.c new file mode 100644 index 000000000000..938ca539aaa6 --- /dev/null +++ b/lib/vdso/getrandom.c @@ -0,0 +1,260 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + */ + +#include <linux/array_size.h> +#include <linux/minmax.h> +#include <vdso/datapage.h> +#include <vdso/getrandom.h> +#include <vdso/unaligned.h> +#include <asm/vdso/getrandom.h> +#include <uapi/linux/mman.h> +#include <uapi/linux/random.h> + +#undef PAGE_SIZE +#undef PAGE_MASK +#define PAGE_SIZE (1UL << CONFIG_PAGE_SHIFT) +#define PAGE_MASK (~(PAGE_SIZE - 1)) + +#define MEMCPY_AND_ZERO_SRC(type, dst, src, len) do { \ + while (len >= sizeof(type)) { \ + __put_unaligned_t(type, __get_unaligned_t(type, src), dst); \ + __put_unaligned_t(type, 0, src); \ + dst += sizeof(type); \ + src += sizeof(type); \ + len -= sizeof(type); \ + } \ +} while (0) + +static void memcpy_and_zero_src(void *dst, void *src, size_t len) +{ + if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) { + if (IS_ENABLED(CONFIG_64BIT)) + MEMCPY_AND_ZERO_SRC(u64, dst, src, len); + MEMCPY_AND_ZERO_SRC(u32, dst, src, len); + MEMCPY_AND_ZERO_SRC(u16, dst, src, len); + } + MEMCPY_AND_ZERO_SRC(u8, dst, src, len); +} + +/** + * __cvdso_getrandom_data - Generic vDSO implementation of getrandom() syscall. + * @rng_info: Describes state of kernel RNG, memory shared with kernel. + * @buffer: Destination buffer to fill with random bytes. + * @len: Size of @buffer in bytes. + * @flags: Zero or more GRND_* flags. + * @opaque_state: Pointer to an opaque state area. + * @opaque_len: Length of opaque state area. + * + * This implements a "fast key erasure" RNG using ChaCha20, in the same way that the kernel's + * getrandom() syscall does. It periodically reseeds its key from the kernel's RNG, at the same + * schedule that the kernel's RNG is reseeded. If the kernel's RNG is not ready, then this always + * calls into the syscall. + * + * If @buffer, @len, and @flags are 0, and @opaque_len is ~0UL, then @opaque_state is populated + * with a struct vgetrandom_opaque_params and the function returns 0; if it does not return 0, + * this function should not be used. + * + * @opaque_state *must* be allocated by calling mmap(2) using the mmap_prot and mmap_flags fields + * from the struct vgetrandom_opaque_params, and states must not straddle pages. Unless external + * locking is used, one state must be allocated per thread, as it is not safe to call this function + * concurrently with the same @opaque_state. However, it is safe to call this using the same + * @opaque_state that is shared between main code and signal handling code, within the same thread. + * + * Returns: The number of random bytes written to @buffer, or a negative value indicating an error. + */ +static __always_inline ssize_t +__cvdso_getrandom_data(const struct vdso_rng_data *rng_info, void *buffer, size_t len, + unsigned int flags, void *opaque_state, size_t opaque_len) +{ + ssize_t ret = min_t(size_t, INT_MAX & PAGE_MASK /* = MAX_RW_COUNT */, len); + struct vgetrandom_state *state = opaque_state; + size_t batch_len, nblocks, orig_len = len; + bool in_use, have_retried = false; + void *orig_buffer = buffer; + u64 current_generation; + u32 counter[2] = { 0 }; + + if (unlikely(opaque_len == ~0UL && !buffer && !len && !flags)) { + struct vgetrandom_opaque_params *params = opaque_state; + params->size_of_opaque_state = sizeof(*state); + params->mmap_prot = PROT_READ | PROT_WRITE; + params->mmap_flags = MAP_DROPPABLE | MAP_ANONYMOUS; + for (size_t i = 0; i < ARRAY_SIZE(params->reserved); ++i) + params->reserved[i] = 0; + return 0; + } + + /* The state must not straddle a page, since pages can be zeroed at any time. */ + if (unlikely(((unsigned long)opaque_state & ~PAGE_MASK) + sizeof(*state) > PAGE_SIZE)) + return -EFAULT; + + /* Handle unexpected flags by falling back to the kernel. */ + if (unlikely(flags & ~(GRND_NONBLOCK | GRND_RANDOM | GRND_INSECURE))) + goto fallback_syscall; + + /* If the caller passes the wrong size, which might happen due to CRIU, fallback. */ + if (unlikely(opaque_len != sizeof(*state))) + goto fallback_syscall; + + /* + * If the kernel's RNG is not yet ready, then it's not possible to provide random bytes from + * userspace, because A) the various @flags require this to block, or not, depending on + * various factors unavailable to userspace, and B) the kernel's behavior before the RNG is + * ready is to reseed from the entropy pool at every invocation. + */ + if (unlikely(!READ_ONCE(rng_info->is_ready))) + goto fallback_syscall; + + /* + * This condition is checked after @rng_info->is_ready, because before the kernel's RNG is + * initialized, the @flags parameter may require this to block or return an error, even when + * len is zero. + */ + if (unlikely(!len)) + return 0; + + /* + * @state->in_use is basic reentrancy protection against this running in a signal handler + * with the same @opaque_state, but obviously not atomic wrt multiple CPUs or more than one + * level of reentrancy. If a signal interrupts this after reading @state->in_use, but before + * writing @state->in_use, there is still no race, because the signal handler will run to + * its completion before returning execution. + */ + in_use = READ_ONCE(state->in_use); + if (unlikely(in_use)) + /* The syscall simply fills the buffer and does not touch @state, so fallback. */ + goto fallback_syscall; + WRITE_ONCE(state->in_use, true); + +retry_generation: + /* + * @rng_info->generation must always be read here, as it serializes @state->key with the + * kernel's RNG reseeding schedule. + */ + current_generation = READ_ONCE(rng_info->generation); + + /* + * If @state->generation doesn't match the kernel RNG's generation, then it means the + * kernel's RNG has reseeded, and so @state->key is reseeded as well. + */ + if (unlikely(state->generation != current_generation)) { + /* + * Write the generation before filling the key, in case of fork. If there is a fork + * just after this line, the parent and child will get different random bytes from + * the syscall, which is good. However, were this line to occur after the getrandom + * syscall, then both child and parent could have the same bytes and the same + * generation counter, so the fork would not be detected. Therefore, write + * @state->generation before the call to the getrandom syscall. + */ + WRITE_ONCE(state->generation, current_generation); + + /* + * Prevent the syscall from being reordered wrt current_generation. Pairs with the + * smp_store_release(&_vdso_rng_data.generation) in random.c. + */ + smp_rmb(); + + /* Reseed @state->key using fresh bytes from the kernel. */ + if (getrandom_syscall(state->key, sizeof(state->key), 0) != sizeof(state->key)) { + /* + * If the syscall failed to refresh the key, then @state->key is now + * invalid, so invalidate the generation so that it is not used again, and + * fallback to using the syscall entirely. + */ + WRITE_ONCE(state->generation, 0); + + /* + * Set @state->in_use to false only after the last write to @state in the + * line above. + */ + WRITE_ONCE(state->in_use, false); + + goto fallback_syscall; + } + + /* + * Set @state->pos to beyond the end of the batch, so that the batch is refilled + * using the new key. + */ + state->pos = sizeof(state->batch); + } + + /* Set len to the total amount of bytes that this function is allowed to read, ret. */ + len = ret; +more_batch: + /* + * First use bytes out of @state->batch, which may have been filled by the last call to this + * function. + */ + batch_len = min_t(size_t, sizeof(state->batch) - state->pos, len); + if (batch_len) { + /* Zeroing at the same time as memcpying helps preserve forward secrecy. */ + memcpy_and_zero_src(buffer, state->batch + state->pos, batch_len); + state->pos += batch_len; + buffer += batch_len; + len -= batch_len; + } + + if (!len) { + /* Prevent the loop from being reordered wrt ->generation. */ + barrier(); + + /* + * Since @rng_info->generation will never be 0, re-read @state->generation, rather + * than using the local current_generation variable, to learn whether a fork + * occurred or if @state was zeroed due to memory pressure. Primarily, though, this + * indicates whether the kernel's RNG has reseeded, in which case generate a new key + * and start over. + */ + if (unlikely(READ_ONCE(state->generation) != READ_ONCE(rng_info->generation))) { + /* + * Prevent this from looping forever in case of low memory or racing with a + * user force-reseeding the kernel's RNG using the ioctl. + */ + if (have_retried) { + WRITE_ONCE(state->in_use, false); + goto fallback_syscall; + } + + have_retried = true; + buffer = orig_buffer; + goto retry_generation; + } + + /* + * Set @state->in_use to false only when there will be no more reads or writes of + * @state. + */ + WRITE_ONCE(state->in_use, false); + return ret; + } + + /* Generate blocks of RNG output directly into @buffer while there's enough room left. */ + nblocks = len / CHACHA_BLOCK_SIZE; + if (nblocks) { + __arch_chacha20_blocks_nostack(buffer, state->key, counter, nblocks); + buffer += nblocks * CHACHA_BLOCK_SIZE; + len -= nblocks * CHACHA_BLOCK_SIZE; + } + + BUILD_BUG_ON(sizeof(state->batch_key) % CHACHA_BLOCK_SIZE != 0); + + /* Refill the batch and overwrite the key, in order to preserve forward secrecy. */ + __arch_chacha20_blocks_nostack(state->batch_key, state->key, counter, + sizeof(state->batch_key) / CHACHA_BLOCK_SIZE); + + /* Since the batch was just refilled, set the position back to 0 to indicate a full batch. */ + state->pos = 0; + goto more_batch; + +fallback_syscall: + return getrandom_syscall(orig_buffer, orig_len, flags); +} + +static __always_inline ssize_t +__cvdso_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len) +{ + return __cvdso_getrandom_data(__arch_get_vdso_rng_data(), buffer, len, flags, opaque_state, opaque_len); +} diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c index 899850bd6f0b..c01eaafd8041 100644 --- a/lib/vdso/gettimeofday.c +++ b/lib/vdso/gettimeofday.c @@ -140,14 +140,14 @@ static __always_inline int do_hres(const struct vdso_data *vd, clockid_t clk, do { /* - * Open coded to handle VDSO_CLOCKMODE_TIMENS. Time namespace - * enabled tasks have a special VVAR page installed which - * has vd->seq set to 1 and vd->clock_mode set to - * VDSO_CLOCKMODE_TIMENS. For non time namespace affected tasks - * this does not affect performance because if vd->seq is - * odd, i.e. a concurrent update is in progress the extra - * check for vd->clock_mode is just a few extra - * instructions while spin waiting for vd->seq to become + * Open coded function vdso_read_begin() to handle + * VDSO_CLOCKMODE_TIMENS. Time namespace enabled tasks have a + * special VVAR page installed which has vd->seq set to 1 and + * vd->clock_mode set to VDSO_CLOCKMODE_TIMENS. For non time + * namespace affected tasks this does not affect performance + * because if vd->seq is odd, i.e. a concurrent update is in + * progress the extra check for vd->clock_mode is just a few + * extra instructions while spin waiting for vd->seq to become * even again. */ while (unlikely((seq = READ_ONCE(vd->seq)) & 1)) { @@ -223,8 +223,8 @@ static __always_inline int do_coarse(const struct vdso_data *vd, clockid_t clk, do { /* - * Open coded to handle VDSO_CLOCK_TIMENS. See comment in - * do_hres(). + * Open coded function vdso_read_begin() to handle + * VDSO_CLOCK_TIMENS. See comment in do_hres(). */ while ((seq = READ_ONCE(vd->seq)) & 1) { if (IS_ENABLED(CONFIG_TIME_NS) && diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 552738f14275..56fe96319292 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -51,7 +51,7 @@ #include <asm/page.h> /* for PAGE_SIZE */ #include <asm/byteorder.h> /* cpu_to_le16 */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/string_helpers.h> #include "kstrtox.h" @@ -160,8 +160,7 @@ long long simple_strtoll(const char *cp, char **endp, unsigned int base) } EXPORT_SYMBOL(simple_strtoll); -static noinline_for_stack -int skip_atoi(const char **s) +static inline int skip_atoi(const char **s) { int i = 0; @@ -407,7 +406,7 @@ int num_to_str(char *buf, int size, unsigned long long num, unsigned int width) return len + width; } -#define SIGN 1 /* unsigned/signed, must be 1 */ +#define SIGN 1 /* unsigned/signed */ #define LEFT 2 /* left justified */ #define PLUS 4 /* show plus */ #define SPACE 8 /* space if plus */ @@ -415,38 +414,26 @@ int num_to_str(char *buf, int size, unsigned long long num, unsigned int width) #define SMALL 32 /* use lowercase in hex (must be 32 == 0x20) */ #define SPECIAL 64 /* prefix hex with "0x", octal with "0" */ -static_assert(SIGN == 1); static_assert(ZEROPAD == ('0' - ' ')); static_assert(SMALL == ('a' ^ 'A')); -enum format_type { - FORMAT_TYPE_NONE, /* Just a string part */ - FORMAT_TYPE_WIDTH, - FORMAT_TYPE_PRECISION, - FORMAT_TYPE_CHAR, - FORMAT_TYPE_STR, - FORMAT_TYPE_PTR, - FORMAT_TYPE_PERCENT_CHAR, - FORMAT_TYPE_INVALID, - FORMAT_TYPE_LONG_LONG, - FORMAT_TYPE_ULONG, - FORMAT_TYPE_LONG, - FORMAT_TYPE_UBYTE, - FORMAT_TYPE_BYTE, - FORMAT_TYPE_USHORT, - FORMAT_TYPE_SHORT, - FORMAT_TYPE_UINT, - FORMAT_TYPE_INT, - FORMAT_TYPE_SIZE_T, - FORMAT_TYPE_PTRDIFF +enum format_state { + FORMAT_STATE_NONE, /* Just a string part */ + FORMAT_STATE_NUM, + FORMAT_STATE_WIDTH, + FORMAT_STATE_PRECISION, + FORMAT_STATE_CHAR, + FORMAT_STATE_STR, + FORMAT_STATE_PTR, + FORMAT_STATE_PERCENT_CHAR, + FORMAT_STATE_INVALID, }; struct printf_spec { - unsigned int type:8; /* format_type enum */ - signed int field_width:24; /* width of output field */ - unsigned int flags:8; /* flags to number() */ - unsigned int base:8; /* number base, 8, 10 or 16 only */ - signed int precision:16; /* # of digits/chars */ + unsigned char flags; /* flags to number() */ + unsigned char base; /* number base, 8, 10 or 16 only */ + short precision; /* # of digits/chars */ + int field_width; /* width of output field */ } __packed; static_assert(sizeof(struct printf_spec) == 8); @@ -579,7 +566,6 @@ char *special_hex_number(char *buf, char *end, unsigned long long num, int size) { struct printf_spec spec; - spec.type = FORMAT_TYPE_PTR; spec.field_width = 2 + 2 * size; /* 0x + hex */ spec.flags = SPECIAL | SMALL | ZEROPAD; spec.base = 16; @@ -966,13 +952,13 @@ char *bdev_name(char *buf, char *end, struct block_device *bdev, hd = bdev->bd_disk; buf = string(buf, end, hd->disk_name, spec); - if (bdev->bd_partno) { + if (bdev_is_partition(bdev)) { if (isdigit(hd->disk_name[strlen(hd->disk_name)-1])) { if (buf < end) *buf = 'p'; buf++; } - buf = number(buf, end, bdev->bd_partno, spec); + buf = number(buf, end, bdev_partno(bdev), spec); } return buf; } @@ -1040,6 +1026,20 @@ static const struct printf_spec default_dec04_spec = { }; static noinline_for_stack +char *hex_range(char *buf, char *end, u64 start_val, u64 end_val, + struct printf_spec spec) +{ + buf = number(buf, end, start_val, spec); + if (start_val == end_val) + return buf; + + if (buf < end) + *buf = '-'; + ++buf; + return number(buf, end, end_val, spec); +} + +static noinline_for_stack char *resource_string(char *buf, char *end, struct resource *res, struct printf_spec spec, const char *fmt) { @@ -1080,7 +1080,7 @@ char *resource_string(char *buf, char *end, struct resource *res, #define FLAG_BUF_SIZE (2 * sizeof(res->flags)) #define DECODED_BUF_SIZE sizeof("[mem - 64bit pref window disabled]") #define RAW_BUF_SIZE sizeof("[mem - flags 0x]") - char sym[max(2*RSRC_BUF_SIZE + DECODED_BUF_SIZE, + char sym[MAX(2*RSRC_BUF_SIZE + DECODED_BUF_SIZE, 2*RSRC_BUF_SIZE + FLAG_BUF_SIZE + RAW_BUF_SIZE)]; char *p = sym, *pend = sym + sizeof(sym); @@ -1115,11 +1115,7 @@ char *resource_string(char *buf, char *end, struct resource *res, p = string_nocheck(p, pend, "size ", str_spec); p = number(p, pend, resource_size(res), *specp); } else { - p = number(p, pend, res->start, *specp); - if (res->start != res->end) { - *p++ = '-'; - p = number(p, pend, res->end, *specp); - } + p = hex_range(p, pend, res->start, res->end, *specp); } if (decode) { if (res->flags & IORESOURCE_MEM_64) @@ -1141,6 +1137,31 @@ char *resource_string(char *buf, char *end, struct resource *res, } static noinline_for_stack +char *range_string(char *buf, char *end, const struct range *range, + struct printf_spec spec, const char *fmt) +{ + char sym[sizeof("[range 0x0123456789abcdef-0x0123456789abcdef]")]; + char *p = sym, *pend = sym + sizeof(sym); + + struct printf_spec range_spec = { + .field_width = 2 + 2 * sizeof(range->start), /* 0x + 2 * 8 */ + .flags = SPECIAL | SMALL | ZEROPAD, + .base = 16, + .precision = -1, + }; + + if (check_pointer(&buf, end, range, spec)) + return buf; + + p = string_nocheck(p, pend, "[range ", default_str_spec); + p = hex_range(p, pend, range->start, range->end, range_spec); + *p++ = ']'; + *p = '\0'; + + return string_nocheck(buf, end, sym, spec); +} + +static noinline_for_stack char *hex_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { @@ -2054,25 +2075,6 @@ char *format_page_flags(char *buf, char *end, unsigned long flags) return buf; } -static -char *format_page_type(char *buf, char *end, unsigned int page_type) -{ - buf = number(buf, end, page_type, default_flag_spec); - - if (buf < end) - *buf = '('; - buf++; - - if (page_type_has_type(page_type)) - buf = format_flags(buf, end, ~page_type, pagetype_names); - - if (buf < end) - *buf = ')'; - buf++; - - return buf; -} - static noinline_for_stack char *flags_string(char *buf, char *end, void *flags_ptr, struct printf_spec spec, const char *fmt) @@ -2086,8 +2088,6 @@ char *flags_string(char *buf, char *end, void *flags_ptr, switch (fmt[1]) { case 'p': return format_page_flags(buf, end, *(unsigned long *)flags_ptr); - case 't': - return format_page_type(buf, end, *(unsigned int *)flags_ptr); case 'v': flags = *(unsigned long *)flags_ptr; names = vmaflag_names; @@ -2250,6 +2250,15 @@ char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode, return widen_string(buf, buf - buf_start, end, spec); } +static noinline_for_stack +char *resource_or_range(const char *fmt, char *buf, char *end, void *ptr, + struct printf_spec spec) +{ + if (*fmt == 'r' && fmt[1] == 'a') + return range_string(buf, end, ptr, spec, fmt); + return resource_string(buf, end, ptr, spec, fmt); +} + int __init no_hash_pointers_enable(char *str) { if (no_hash_pointers) @@ -2298,6 +2307,7 @@ char *rust_fmt_argument(char *buf, char *end, void *ptr); * - 'Bb' as above with module build ID (for use in backtraces) * - 'R' For decoded struct resource, e.g., [mem 0x0-0x1f 64bit pref] * - 'r' For raw struct resource, e.g., [mem 0x0-0x1f flags 0x201] + * - 'ra' For struct ranges, e.g., [range 0x0000000000000000 - 0x00000000000000ff] * - 'b[l]' For a bitmap, the number of bits is determined by the field * width which must be explicitly specified either as part of the * format string '%32b[l]' or through '%*b[l]', [l] selects @@ -2422,7 +2432,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, return symbol_string(buf, end, ptr, spec, fmt); case 'R': case 'r': - return resource_string(buf, end, ptr, spec, fmt); + return resource_or_range(fmt, buf, end, ptr, spec); case 'h': return hex_string(buf, end, ptr, spec, fmt); case 'b': @@ -2506,6 +2516,26 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, } } +struct fmt { + const char *str; + unsigned char state; // enum format_state + unsigned char size; // size of numbers +}; + +#define SPEC_CHAR(x, flag) [(x)-32] = flag +static unsigned char spec_flag(unsigned char c) +{ + static const unsigned char spec_flag_array[] = { + SPEC_CHAR(' ', SPACE), + SPEC_CHAR('#', SPECIAL), + SPEC_CHAR('+', PLUS), + SPEC_CHAR('-', LEFT), + SPEC_CHAR('0', ZEROPAD), + }; + c -= 32; + return (c < sizeof(spec_flag_array)) ? spec_flag_array[c] : 0; +} + /* * Helper function to decode printf style format. * Each call decode a token from the format and return the @@ -2528,181 +2558,141 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, * @qualifier: qualifier of a number (long, size_t, ...) */ static noinline_for_stack -int format_decode(const char *fmt, struct printf_spec *spec) +struct fmt format_decode(struct fmt fmt, struct printf_spec *spec) { - const char *start = fmt; - char qualifier; + const char *start = fmt.str; + char flag; /* we finished early by reading the field width */ - if (spec->type == FORMAT_TYPE_WIDTH) { + if (unlikely(fmt.state == FORMAT_STATE_WIDTH)) { if (spec->field_width < 0) { spec->field_width = -spec->field_width; spec->flags |= LEFT; } - spec->type = FORMAT_TYPE_NONE; + fmt.state = FORMAT_STATE_NONE; goto precision; } /* we finished early by reading the precision */ - if (spec->type == FORMAT_TYPE_PRECISION) { + if (unlikely(fmt.state == FORMAT_STATE_PRECISION)) { if (spec->precision < 0) spec->precision = 0; - spec->type = FORMAT_TYPE_NONE; + fmt.state = FORMAT_STATE_NONE; goto qualifier; } /* By default */ - spec->type = FORMAT_TYPE_NONE; + fmt.state = FORMAT_STATE_NONE; - for (; *fmt ; ++fmt) { - if (*fmt == '%') + for (; *fmt.str ; fmt.str++) { + if (*fmt.str == '%') break; } /* Return the current non-format string */ - if (fmt != start || !*fmt) - return fmt - start; + if (fmt.str != start || !*fmt.str) + return fmt; - /* Process flags */ + /* Process flags. This also skips the first '%' */ spec->flags = 0; - - while (1) { /* this also skips first '%' */ - bool found = true; - - ++fmt; - - switch (*fmt) { - case '-': spec->flags |= LEFT; break; - case '+': spec->flags |= PLUS; break; - case ' ': spec->flags |= SPACE; break; - case '#': spec->flags |= SPECIAL; break; - case '0': spec->flags |= ZEROPAD; break; - default: found = false; - } - - if (!found) - break; - } + do { + /* this also skips first '%' */ + flag = spec_flag(*++fmt.str); + spec->flags |= flag; + } while (flag); /* get field width */ spec->field_width = -1; - if (isdigit(*fmt)) - spec->field_width = skip_atoi(&fmt); - else if (*fmt == '*') { + if (isdigit(*fmt.str)) + spec->field_width = skip_atoi(&fmt.str); + else if (unlikely(*fmt.str == '*')) { /* it's the next argument */ - spec->type = FORMAT_TYPE_WIDTH; - return ++fmt - start; + fmt.state = FORMAT_STATE_WIDTH; + fmt.str++; + return fmt; } precision: /* get the precision */ spec->precision = -1; - if (*fmt == '.') { - ++fmt; - if (isdigit(*fmt)) { - spec->precision = skip_atoi(&fmt); + if (unlikely(*fmt.str == '.')) { + fmt.str++; + if (isdigit(*fmt.str)) { + spec->precision = skip_atoi(&fmt.str); if (spec->precision < 0) spec->precision = 0; - } else if (*fmt == '*') { + } else if (*fmt.str == '*') { /* it's the next argument */ - spec->type = FORMAT_TYPE_PRECISION; - return ++fmt - start; + fmt.state = FORMAT_STATE_PRECISION; + fmt.str++; + return fmt; } } qualifier: - /* get the conversion qualifier */ - qualifier = 0; - if (*fmt == 'h' || _tolower(*fmt) == 'l' || - *fmt == 'z' || *fmt == 't') { - qualifier = *fmt++; - if (unlikely(qualifier == *fmt)) { - if (qualifier == 'l') { - qualifier = 'L'; - ++fmt; - } else if (qualifier == 'h') { - qualifier = 'H'; - ++fmt; - } - } - } - - /* default base */ + /* Set up default numeric format */ spec->base = 10; - switch (*fmt) { - case 'c': - spec->type = FORMAT_TYPE_CHAR; - return ++fmt - start; - - case 's': - spec->type = FORMAT_TYPE_STR; - return ++fmt - start; - - case 'p': - spec->type = FORMAT_TYPE_PTR; - return ++fmt - start; - - case '%': - spec->type = FORMAT_TYPE_PERCENT_CHAR; - return ++fmt - start; - - /* integer number formats - set up the flags and "break" */ - case 'o': - spec->base = 8; - break; + fmt.state = FORMAT_STATE_NUM; + fmt.size = sizeof(int); + static const struct format_state { + unsigned char state; + unsigned char size; + unsigned char flags_or_double_size; + unsigned char base; + } lookup_state[256] = { + // Length + ['l'] = { 0, sizeof(long), sizeof(long long) }, + ['L'] = { 0, sizeof(long long) }, + ['h'] = { 0, sizeof(short), sizeof(char) }, + ['H'] = { 0, sizeof(char) }, // Questionable historical + ['z'] = { 0, sizeof(size_t) }, + ['t'] = { 0, sizeof(ptrdiff_t) }, + + // Non-numeric formats + ['c'] = { FORMAT_STATE_CHAR }, + ['s'] = { FORMAT_STATE_STR }, + ['p'] = { FORMAT_STATE_PTR }, + ['%'] = { FORMAT_STATE_PERCENT_CHAR }, + + // Numerics + ['o'] = { FORMAT_STATE_NUM, 0, 0, 8 }, + ['x'] = { FORMAT_STATE_NUM, 0, SMALL, 16 }, + ['X'] = { FORMAT_STATE_NUM, 0, 0, 16 }, + ['d'] = { FORMAT_STATE_NUM, 0, SIGN, 10 }, + ['i'] = { FORMAT_STATE_NUM, 0, SIGN, 10 }, + ['u'] = { FORMAT_STATE_NUM, 0, 0, 10, }, - case 'x': - spec->flags |= SMALL; - fallthrough; - - case 'X': - spec->base = 16; - break; - - case 'd': - case 'i': - spec->flags |= SIGN; - break; - case 'u': - break; - - case 'n': /* * Since %n poses a greater security risk than * utility, treat it as any other invalid or * unsupported format specifier. */ - fallthrough; + }; - default: - WARN_ONCE(1, "Please remove unsupported %%%c in format string\n", *fmt); - spec->type = FORMAT_TYPE_INVALID; - return fmt - start; - } - - if (qualifier == 'L') - spec->type = FORMAT_TYPE_LONG_LONG; - else if (qualifier == 'l') { - BUILD_BUG_ON(FORMAT_TYPE_ULONG + SIGN != FORMAT_TYPE_LONG); - spec->type = FORMAT_TYPE_ULONG + (spec->flags & SIGN); - } else if (qualifier == 'z') { - spec->type = FORMAT_TYPE_SIZE_T; - } else if (qualifier == 't') { - spec->type = FORMAT_TYPE_PTRDIFF; - } else if (qualifier == 'H') { - BUILD_BUG_ON(FORMAT_TYPE_UBYTE + SIGN != FORMAT_TYPE_BYTE); - spec->type = FORMAT_TYPE_UBYTE + (spec->flags & SIGN); - } else if (qualifier == 'h') { - BUILD_BUG_ON(FORMAT_TYPE_USHORT + SIGN != FORMAT_TYPE_SHORT); - spec->type = FORMAT_TYPE_USHORT + (spec->flags & SIGN); - } else { - BUILD_BUG_ON(FORMAT_TYPE_UINT + SIGN != FORMAT_TYPE_INT); - spec->type = FORMAT_TYPE_UINT + (spec->flags & SIGN); + const struct format_state *p = lookup_state + (u8)*fmt.str; + if (p->size) { + fmt.size = p->size; + if (p->flags_or_double_size && fmt.str[0] == fmt.str[1]) { + fmt.size = p->flags_or_double_size; + fmt.str++; + } + fmt.str++; + p = lookup_state + *fmt.str; + } + if (p->state) { + if (p->base) + spec->base = p->base; + spec->flags |= p->flags_or_double_size; + fmt.state = p->state; + fmt.str++; + return fmt; } - return ++fmt - start; + WARN_ONCE(1, "Please remove unsupported %%%c in format string\n", *fmt.str); + fmt.state = FORMAT_STATE_INVALID; + return fmt; } static void @@ -2723,11 +2713,27 @@ set_precision(struct printf_spec *spec, int prec) } } +/* + * Turn a 1/2/4-byte value into a 64-bit one for printing: truncate + * as necessary and deal with signedness. + * + * 'size' is the size of the value in bytes. + */ +static unsigned long long convert_num_spec(unsigned int val, int size, struct printf_spec spec) +{ + unsigned int shift = 32 - size*8; + + val <<= shift; + if (!(spec.flags & SIGN)) + return val >> shift; + return (int)val >> shift; +} + /** * vsnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space - * @fmt: The format string to use + * @fmt_str: The format string to use * @args: Arguments for the format string * * This function generally follows C99 vsnprintf, but has some @@ -2751,11 +2757,14 @@ set_precision(struct printf_spec *spec, int prec) * * If you're not already dealing with a va_list consider using snprintf(). */ -int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) +int vsnprintf(char *buf, size_t size, const char *fmt_str, va_list args) { - unsigned long long num; char *str, *end; struct printf_spec spec = {0}; + struct fmt fmt = { + .str = fmt_str, + .state = FORMAT_STATE_NONE, + }; /* Reject out-of-range values early. Large positive sizes are used for unknown buffer sizes. */ @@ -2771,33 +2780,43 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) size = end - buf; } - while (*fmt) { - const char *old_fmt = fmt; - int read = format_decode(fmt, &spec); + while (*fmt.str) { + const char *old_fmt = fmt.str; - fmt += read; + fmt = format_decode(fmt, &spec); - switch (spec.type) { - case FORMAT_TYPE_NONE: { - int copy = read; + switch (fmt.state) { + case FORMAT_STATE_NONE: { + int read = fmt.str - old_fmt; if (str < end) { + int copy = read; if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; - break; + continue; + } + + case FORMAT_STATE_NUM: { + unsigned long long num; + if (fmt.size <= sizeof(int)) + num = convert_num_spec(va_arg(args, int), fmt.size, spec); + else + num = va_arg(args, long long); + str = number(str, end, num, spec); + continue; } - case FORMAT_TYPE_WIDTH: + case FORMAT_STATE_WIDTH: set_field_width(&spec, va_arg(args, int)); - break; + continue; - case FORMAT_TYPE_PRECISION: + case FORMAT_STATE_PRECISION: set_precision(&spec, va_arg(args, int)); - break; + continue; - case FORMAT_TYPE_CHAR: { + case FORMAT_STATE_CHAR: { char c; if (!(spec.flags & LEFT)) { @@ -2817,27 +2836,27 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) *str = ' '; ++str; } - break; + continue; } - case FORMAT_TYPE_STR: + case FORMAT_STATE_STR: str = string(str, end, va_arg(args, char *), spec); - break; + continue; - case FORMAT_TYPE_PTR: - str = pointer(fmt, str, end, va_arg(args, void *), + case FORMAT_STATE_PTR: + str = pointer(fmt.str, str, end, va_arg(args, void *), spec); - while (isalnum(*fmt)) - fmt++; - break; + while (isalnum(*fmt.str)) + fmt.str++; + continue; - case FORMAT_TYPE_PERCENT_CHAR: + case FORMAT_STATE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; - break; + continue; - case FORMAT_TYPE_INVALID: + default: /* * Presumably the arguments passed gcc's type * checking, but there is no safe or sane way @@ -2847,47 +2866,6 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) * sync. */ goto out; - - default: - switch (spec.type) { - case FORMAT_TYPE_LONG_LONG: - num = va_arg(args, long long); - break; - case FORMAT_TYPE_ULONG: - num = va_arg(args, unsigned long); - break; - case FORMAT_TYPE_LONG: - num = va_arg(args, long); - break; - case FORMAT_TYPE_SIZE_T: - if (spec.flags & SIGN) - num = va_arg(args, ssize_t); - else - num = va_arg(args, size_t); - break; - case FORMAT_TYPE_PTRDIFF: - num = va_arg(args, ptrdiff_t); - break; - case FORMAT_TYPE_UBYTE: - num = (unsigned char) va_arg(args, int); - break; - case FORMAT_TYPE_BYTE: - num = (signed char) va_arg(args, int); - break; - case FORMAT_TYPE_USHORT: - num = (unsigned short) va_arg(args, int); - break; - case FORMAT_TYPE_SHORT: - num = (short) va_arg(args, int); - break; - case FORMAT_TYPE_INT: - num = (int) va_arg(args, int); - break; - default: - num = va_arg(args, unsigned int); - } - - str = number(str, end, num, spec); } } @@ -3043,7 +3021,7 @@ EXPORT_SYMBOL(sprintf); * vbin_printf - Parse a format string and place args' binary value in a buffer * @bin_buf: The buffer to place args' binary value * @size: The size of the buffer(by words(32bits), not characters) - * @fmt: The format string to use + * @fmt_str: The format string to use * @args: Arguments for the format string * * The format follows C99 vsnprintf, except %n is ignored, and its argument @@ -3056,8 +3034,12 @@ EXPORT_SYMBOL(sprintf); * If the return value is greater than @size, the resulting bin_buf is NOT * valid for bstr_printf(). */ -int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args) +int vbin_printf(u32 *bin_buf, size_t size, const char *fmt_str, va_list args) { + struct fmt fmt = { + .str = fmt_str, + .state = FORMAT_STATE_NONE, + }; struct printf_spec spec = {0}; char *str, *end; int width; @@ -3089,31 +3071,29 @@ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args) value; \ }) - while (*fmt) { - int read = format_decode(fmt, &spec); + while (*fmt.str) { + fmt = format_decode(fmt, &spec); - fmt += read; - - switch (spec.type) { - case FORMAT_TYPE_NONE: - case FORMAT_TYPE_PERCENT_CHAR: + switch (fmt.state) { + case FORMAT_STATE_NONE: + case FORMAT_STATE_PERCENT_CHAR: break; - case FORMAT_TYPE_INVALID: + case FORMAT_STATE_INVALID: goto out; - case FORMAT_TYPE_WIDTH: - case FORMAT_TYPE_PRECISION: + case FORMAT_STATE_WIDTH: + case FORMAT_STATE_PRECISION: width = (int)save_arg(int); /* Pointers may require the width */ - if (*fmt == 'p') + if (*fmt.str == 'p') set_field_width(&spec, width); break; - case FORMAT_TYPE_CHAR: + case FORMAT_STATE_CHAR: save_arg(char); break; - case FORMAT_TYPE_STR: { + case FORMAT_STATE_STR: { const char *save_str = va_arg(args, char *); const char *err_msg; size_t len; @@ -3129,9 +3109,9 @@ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args) break; } - case FORMAT_TYPE_PTR: + case FORMAT_STATE_PTR: /* Dereferenced pointers must be done now */ - switch (*fmt) { + switch (*fmt.str) { /* Dereference of functions is still OK */ case 'S': case 's': @@ -3141,11 +3121,11 @@ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args) save_arg(void *); break; default: - if (!isalnum(*fmt)) { + if (!isalnum(*fmt.str)) { save_arg(void *); break; } - str = pointer(fmt, str, end, va_arg(args, void *), + str = pointer(fmt.str, str, end, va_arg(args, void *), spec); if (str + 1 < end) *str++ = '\0'; @@ -3153,35 +3133,14 @@ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args) end[-1] = '\0'; /* Must be nul terminated */ } /* skip all alphanumeric pointer suffixes */ - while (isalnum(*fmt)) - fmt++; + while (isalnum(*fmt.str)) + fmt.str++; break; - default: - switch (spec.type) { - - case FORMAT_TYPE_LONG_LONG: + case FORMAT_STATE_NUM: + if (fmt.size > sizeof(int)) { save_arg(long long); - break; - case FORMAT_TYPE_ULONG: - case FORMAT_TYPE_LONG: - save_arg(unsigned long); - break; - case FORMAT_TYPE_SIZE_T: - save_arg(size_t); - break; - case FORMAT_TYPE_PTRDIFF: - save_arg(ptrdiff_t); - break; - case FORMAT_TYPE_UBYTE: - case FORMAT_TYPE_BYTE: - save_arg(char); - break; - case FORMAT_TYPE_USHORT: - case FORMAT_TYPE_SHORT: - save_arg(short); - break; - default: + } else { save_arg(int); } } @@ -3197,7 +3156,7 @@ EXPORT_SYMBOL_GPL(vbin_printf); * bstr_printf - Format a string from binary arguments and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space - * @fmt: The format string to use + * @fmt_str: The format string to use * @bin_buf: Binary arguments for the format string * * This function like C99 vsnprintf, but the difference is that vsnprintf gets @@ -3215,8 +3174,12 @@ EXPORT_SYMBOL_GPL(vbin_printf); * return is greater than or equal to @size, the resulting * string is truncated. */ -int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) +int bstr_printf(char *buf, size_t size, const char *fmt_str, const u32 *bin_buf) { + struct fmt fmt = { + .str = fmt_str, + .state = FORMAT_STATE_NONE, + }; struct printf_spec spec = {0}; char *str, *end; const char *args = (const char *)bin_buf; @@ -3248,33 +3211,33 @@ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) size = end - buf; } - while (*fmt) { - const char *old_fmt = fmt; - int read = format_decode(fmt, &spec); - - fmt += read; + while (*fmt.str) { + const char *old_fmt = fmt.str; + unsigned long long num; - switch (spec.type) { - case FORMAT_TYPE_NONE: { - int copy = read; + fmt = format_decode(fmt, &spec); + switch (fmt.state) { + case FORMAT_STATE_NONE: { + int read = fmt.str - old_fmt; if (str < end) { + int copy = read; if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; - break; + continue; } - case FORMAT_TYPE_WIDTH: + case FORMAT_STATE_WIDTH: set_field_width(&spec, get_arg(int)); - break; + continue; - case FORMAT_TYPE_PRECISION: + case FORMAT_STATE_PRECISION: set_precision(&spec, get_arg(int)); - break; + continue; - case FORMAT_TYPE_CHAR: { + case FORMAT_STATE_CHAR: { char c; if (!(spec.flags & LEFT)) { @@ -3293,21 +3256,21 @@ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) *str = ' '; ++str; } - break; + continue; } - case FORMAT_TYPE_STR: { + case FORMAT_STATE_STR: { const char *str_arg = args; args += strlen(str_arg) + 1; str = string(str, end, (char *)str_arg, spec); - break; + continue; } - case FORMAT_TYPE_PTR: { + case FORMAT_STATE_PTR: { bool process = false; int copy, len; /* Non function dereferences were already done */ - switch (*fmt) { + switch (*fmt.str) { case 'S': case 's': case 'x': @@ -3316,7 +3279,7 @@ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) process = true; break; default: - if (!isalnum(*fmt)) { + if (!isalnum(*fmt.str)) { process = true; break; } @@ -3331,63 +3294,32 @@ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) } } if (process) - str = pointer(fmt, str, end, get_arg(void *), spec); + str = pointer(fmt.str, str, end, get_arg(void *), spec); - while (isalnum(*fmt)) - fmt++; - break; + while (isalnum(*fmt.str)) + fmt.str++; + continue; } - case FORMAT_TYPE_PERCENT_CHAR: + case FORMAT_STATE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; - break; + continue; - case FORMAT_TYPE_INVALID: + case FORMAT_STATE_INVALID: goto out; - default: { - unsigned long long num; - - switch (spec.type) { - - case FORMAT_TYPE_LONG_LONG: + case FORMAT_STATE_NUM: + if (fmt.size > sizeof(int)) { num = get_arg(long long); - break; - case FORMAT_TYPE_ULONG: - case FORMAT_TYPE_LONG: - num = get_arg(unsigned long); - break; - case FORMAT_TYPE_SIZE_T: - num = get_arg(size_t); - break; - case FORMAT_TYPE_PTRDIFF: - num = get_arg(ptrdiff_t); - break; - case FORMAT_TYPE_UBYTE: - num = get_arg(unsigned char); - break; - case FORMAT_TYPE_BYTE: - num = get_arg(signed char); - break; - case FORMAT_TYPE_USHORT: - num = get_arg(unsigned short); - break; - case FORMAT_TYPE_SHORT: - num = get_arg(short); - break; - case FORMAT_TYPE_UINT: - num = get_arg(unsigned int); - break; - default: - num = get_arg(int); + } else { + num = convert_num_spec(get_arg(int), fmt.size, spec); } - str = number(str, end, num, spec); - } /* default: */ - } /* switch(spec.type) */ - } /* while(*fmt) */ + continue; + } + } /* while(*fmt.str) */ out: if (size > 0) { @@ -3404,29 +3336,6 @@ out: } EXPORT_SYMBOL_GPL(bstr_printf); -/** - * bprintf - Parse a format string and place args' binary value in a buffer - * @bin_buf: The buffer to place args' binary value - * @size: The size of the buffer(by words(32bits), not characters) - * @fmt: The format string to use - * @...: Arguments for the format string - * - * The function returns the number of words(u32) written - * into @bin_buf. - */ -int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) -{ - va_list args; - int ret; - - va_start(args, fmt); - ret = vbin_printf(bin_buf, size, fmt, args); - va_end(args); - - return ret; -} -EXPORT_SYMBOL_GPL(bprintf); - #endif /* CONFIG_BINARY_PRINTF */ /** diff --git a/lib/win_minmax.c b/lib/win_minmax.c index ec10506834b6..1682e614309c 100644 --- a/lib/win_minmax.c +++ b/lib/win_minmax.c @@ -97,3 +97,4 @@ u32 minmax_running_min(struct minmax *m, u32 win, u32 t, u32 meas) return minmax_subwin_update(m, win, &val); } +EXPORT_SYMBOL(minmax_running_min); diff --git a/lib/xarray.c b/lib/xarray.c index 5e7d6334d70d..116e9286c64e 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -125,19 +125,20 @@ static inline void node_mark_all(struct xa_node *node, xa_mark_t mark) */ static void xas_squash_marks(const struct xa_state *xas) { - unsigned int mark = 0; + xa_mark_t mark = 0; unsigned int limit = xas->xa_offset + xas->xa_sibs + 1; - if (!xas->xa_sibs) - return; + for (;;) { + unsigned long *marks = node_marks(xas->xa_node, mark); - do { - unsigned long *marks = xas->xa_node->marks[mark]; - if (find_next_bit(marks, limit, xas->xa_offset + 1) == limit) - continue; - __set_bit(xas->xa_offset, marks); - bitmap_clear(marks, xas->xa_offset + 1, xas->xa_sibs); - } while (mark++ != (__force unsigned)XA_MARK_MAX); + if (find_next_bit(marks, limit, xas->xa_offset + 1) != limit) { + __set_bit(xas->xa_offset, marks); + bitmap_clear(marks, xas->xa_offset + 1, xas->xa_sibs); + } + if (mark == XA_MARK_MAX) + break; + mark_inc(mark); + } } /* extracts the offset within this node from the index */ @@ -200,7 +201,8 @@ static void *xas_start(struct xa_state *xas) return entry; } -static void *xas_descend(struct xa_state *xas, struct xa_node *node) +static __always_inline void *xas_descend(struct xa_state *xas, + struct xa_node *node) { unsigned int offset = get_offset(xas->xa_index, node); void *entry = xa_entry(xas->xa, node, offset); @@ -434,6 +436,11 @@ static unsigned long max_index(void *entry) return (XA_CHUNK_SIZE << xa_to_node(entry)->shift) - 1; } +static inline void *xa_zero_to_null(void *entry) +{ + return xa_is_zero(entry) ? NULL : entry; +} + static void xas_shrink(struct xa_state *xas) { struct xarray *xa = xas->xa; @@ -450,8 +457,8 @@ static void xas_shrink(struct xa_state *xas) break; if (!xa_is_node(entry) && node->shift) break; - if (xa_is_zero(entry) && xa_zero_busy(xa)) - entry = NULL; + if (xa_zero_busy(xa)) + entry = xa_zero_to_null(entry); xas->xa_node = XAS_BOUNDS; RCU_INIT_POINTER(xa->xa_head, entry); @@ -1021,7 +1028,7 @@ void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, unsigned int mask = xas->xa_sibs; /* XXX: no support for splitting really large entries yet */ - if (WARN_ON(xas->xa_shift + 2 * XA_CHUNK_SHIFT < order)) + if (WARN_ON(xas->xa_shift + 2 * XA_CHUNK_SHIFT <= order)) goto nomem; if (xas->xa_shift + XA_CHUNK_SHIFT > order) return; @@ -1146,6 +1153,7 @@ void xas_pause(struct xa_state *xas) if (!xa_is_sibling(xa_entry(xas->xa, node, offset))) break; } + xas->xa_index &= ~0UL << node->shift; xas->xa_index += (offset - xas->xa_offset) << node->shift; if (xas->xa_index == 0) xas->xa_node = XAS_BOUNDS; @@ -1381,6 +1389,8 @@ void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!entry && !(xa_track_free(xas->xa) && mark == XA_FREE_MARK)) continue; + if (xa_is_sibling(entry)) + continue; if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); @@ -1473,9 +1483,7 @@ void *xa_load(struct xarray *xa, unsigned long index) rcu_read_lock(); do { - entry = xas_load(&xas); - if (xa_is_zero(entry)) - entry = NULL; + entry = xa_zero_to_null(xas_load(&xas)); } while (xas_retry(&xas, entry)); rcu_read_unlock(); @@ -1485,8 +1493,6 @@ EXPORT_SYMBOL(xa_load); static void *xas_result(struct xa_state *xas, void *curr) { - if (xa_is_zero(curr)) - return NULL; if (xas_error(xas)) curr = xas->xa_node; return curr; @@ -1507,7 +1513,7 @@ static void *xas_result(struct xa_state *xas, void *curr) void *__xa_erase(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); - return xas_result(&xas, xas_store(&xas, NULL)); + return xas_result(&xas, xa_zero_to_null(xas_store(&xas, NULL))); } EXPORT_SYMBOL(__xa_erase); @@ -1566,7 +1572,7 @@ void *__xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) xas_clear_mark(&xas, XA_FREE_MARK); } while (__xas_nomem(&xas, gfp)); - return xas_result(&xas, curr); + return xas_result(&xas, xa_zero_to_null(curr)); } EXPORT_SYMBOL(__xa_store); @@ -1599,6 +1605,9 @@ void *xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) } EXPORT_SYMBOL(xa_store); +static inline void *__xa_cmpxchg_raw(struct xarray *xa, unsigned long index, + void *old, void *entry, gfp_t gfp); + /** * __xa_cmpxchg() - Store this entry in the XArray. * @xa: XArray. @@ -1618,6 +1627,13 @@ EXPORT_SYMBOL(xa_store); void *__xa_cmpxchg(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { + return xa_zero_to_null(__xa_cmpxchg_raw(xa, index, old, entry, gfp)); +} +EXPORT_SYMBOL(__xa_cmpxchg); + +static inline void *__xa_cmpxchg_raw(struct xarray *xa, unsigned long index, + void *old, void *entry, gfp_t gfp) +{ XA_STATE(xas, xa, index); void *curr; @@ -1635,7 +1651,6 @@ void *__xa_cmpxchg(struct xarray *xa, unsigned long index, return xas_result(&xas, curr); } -EXPORT_SYMBOL(__xa_cmpxchg); /** * __xa_insert() - Store this entry in the XArray if no entry is present. @@ -1655,26 +1670,16 @@ EXPORT_SYMBOL(__xa_cmpxchg); */ int __xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { - XA_STATE(xas, xa, index); void *curr; + int errno; - if (WARN_ON_ONCE(xa_is_advanced(entry))) - return -EINVAL; if (!entry) entry = XA_ZERO_ENTRY; - - do { - curr = xas_load(&xas); - if (!curr) { - xas_store(&xas, entry); - if (xa_track_free(xa)) - xas_clear_mark(&xas, XA_FREE_MARK); - } else { - xas_set_err(&xas, -EBUSY); - } - } while (__xas_nomem(&xas, gfp)); - - return xas_error(&xas); + curr = __xa_cmpxchg_raw(xa, index, NULL, entry, gfp); + errno = xa_err(curr); + if (errno) + return errno; + return (curr != NULL) ? -EBUSY : 0; } EXPORT_SYMBOL(__xa_insert); @@ -1765,39 +1770,52 @@ unlock: EXPORT_SYMBOL(xa_store_range); /** - * xa_get_order() - Get the order of an entry. - * @xa: XArray. - * @index: Index of the entry. + * xas_get_order() - Get the order of an entry. + * @xas: XArray operation state. + * + * Called after xas_load, the xas should not be in an error state. * * Return: A number between 0 and 63 indicating the order of the entry. */ -int xa_get_order(struct xarray *xa, unsigned long index) +int xas_get_order(struct xa_state *xas) { - XA_STATE(xas, xa, index); - void *entry; int order = 0; - rcu_read_lock(); - entry = xas_load(&xas); - - if (!entry) - goto unlock; - - if (!xas.xa_node) - goto unlock; + if (!xas->xa_node) + return 0; for (;;) { - unsigned int slot = xas.xa_offset + (1 << order); + unsigned int slot = xas->xa_offset + (1 << order); if (slot >= XA_CHUNK_SIZE) break; - if (!xa_is_sibling(xas.xa_node->slots[slot])) + if (!xa_is_sibling(xa_entry(xas->xa, xas->xa_node, slot))) break; order++; } - order += xas.xa_node->shift; -unlock: + order += xas->xa_node->shift; + return order; +} +EXPORT_SYMBOL_GPL(xas_get_order); + +/** + * xa_get_order() - Get the order of an entry. + * @xa: XArray. + * @index: Index of the entry. + * + * Return: A number between 0 and 63 indicating the order of the entry. + */ +int xa_get_order(struct xarray *xa, unsigned long index) +{ + XA_STATE(xas, xa, index); + int order = 0; + void *entry; + + rcu_read_lock(); + entry = xas_load(&xas); + if (entry) + order = xas_get_order(&xas); rcu_read_unlock(); return order; diff --git a/lib/xxhash.c b/lib/xxhash.c index d5bb9ff10607..b5bd567aa6b3 100644 --- a/lib/xxhash.c +++ b/lib/xxhash.c @@ -38,7 +38,7 @@ * - xxHash source repository: https://github.com/Cyan4973/xxHash */ -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <linux/errno.h> #include <linux/compiler.h> #include <linux/kernel.h> diff --git a/lib/xz/Kconfig b/lib/xz/Kconfig index aef086a6bf2f..20aa459bfb3e 100644 --- a/lib/xz/Kconfig +++ b/lib/xz/Kconfig @@ -5,7 +5,8 @@ config XZ_DEC help LZMA2 compression algorithm and BCJ filters are supported using the .xz file format as the container. For integrity checking, - CRC32 is supported. See Documentation/staging/xz.rst for more information. + CRC32 is supported. See Documentation/staging/xz.rst for more + information. if XZ_DEC @@ -29,11 +30,21 @@ config XZ_DEC_ARMTHUMB default y select XZ_DEC_BCJ +config XZ_DEC_ARM64 + bool "ARM64 BCJ filter decoder" if EXPERT + default y + select XZ_DEC_BCJ + config XZ_DEC_SPARC bool "SPARC BCJ filter decoder" if EXPERT default y select XZ_DEC_BCJ +config XZ_DEC_RISCV + bool "RISC-V BCJ filter decoder" if EXPERT + default y + select XZ_DEC_BCJ + config XZ_DEC_MICROLZMA bool "MicroLZMA decoder" default n diff --git a/lib/xz/xz_crc32.c b/lib/xz/xz_crc32.c index 88a2c35e1b59..6a7906a328ba 100644 --- a/lib/xz/xz_crc32.c +++ b/lib/xz/xz_crc32.c @@ -1,11 +1,10 @@ +// SPDX-License-Identifier: 0BSD + /* * CRC32 using the polynomial from IEEE-802.3 * * Authors: Lasse Collin <lasse.collin@tukaani.org> * Igor Pavlov <https://7-zip.org/> - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ /* @@ -27,9 +26,9 @@ STATIC_RW_DATA uint32_t xz_crc32_table[256]; -XZ_EXTERN void xz_crc32_init(void) +void xz_crc32_init(void) { - const uint32_t poly = CRC32_POLY_LE; + const uint32_t poly = 0xEDB88320; uint32_t i; uint32_t j; @@ -46,7 +45,7 @@ XZ_EXTERN void xz_crc32_init(void) return; } -XZ_EXTERN uint32_t xz_crc32(const uint8_t *buf, size_t size, uint32_t crc) +uint32_t xz_crc32(const uint8_t *buf, size_t size, uint32_t crc) { crc = ~crc; diff --git a/lib/xz/xz_dec_bcj.c b/lib/xz/xz_dec_bcj.c index ef449e97d1a1..8237db17eee3 100644 --- a/lib/xz/xz_dec_bcj.c +++ b/lib/xz/xz_dec_bcj.c @@ -1,11 +1,10 @@ +// SPDX-License-Identifier: 0BSD + /* * Branch/Call/Jump (BCJ) filter decoders * * Authors: Lasse Collin <lasse.collin@tukaani.org> * Igor Pavlov <https://7-zip.org/> - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ #include "xz_private.h" @@ -24,7 +23,9 @@ struct xz_dec_bcj { BCJ_IA64 = 6, /* Big or little endian */ BCJ_ARM = 7, /* Little endian only */ BCJ_ARMTHUMB = 8, /* Little endian only */ - BCJ_SPARC = 9 /* Big or little endian */ + BCJ_SPARC = 9, /* Big or little endian */ + BCJ_ARM64 = 10, /* AArch64 */ + BCJ_RISCV = 11 /* RV32GQC_Zfh, RV64GQC_Zfh */ } type; /* @@ -162,7 +163,9 @@ static size_t bcj_powerpc(struct xz_dec_bcj *s, uint8_t *buf, size_t size) size_t i; uint32_t instr; - for (i = 0; i + 4 <= size; i += 4) { + size &= ~(size_t)3; + + for (i = 0; i < size; i += 4) { instr = get_unaligned_be32(buf + i); if ((instr & 0xFC000003) == 0x48000001) { instr &= 0x03FFFFFC; @@ -219,7 +222,9 @@ static size_t bcj_ia64(struct xz_dec_bcj *s, uint8_t *buf, size_t size) /* Instruction normalized with bit_res for easier manipulation */ uint64_t norm; - for (i = 0; i + 16 <= size; i += 16) { + size &= ~(size_t)15; + + for (i = 0; i < size; i += 16) { mask = branch_table[buf[i] & 0x1F]; for (slot = 0, bit_pos = 5; slot < 3; ++slot, bit_pos += 41) { if (((mask >> slot) & 1) == 0) @@ -267,7 +272,9 @@ static size_t bcj_arm(struct xz_dec_bcj *s, uint8_t *buf, size_t size) size_t i; uint32_t addr; - for (i = 0; i + 4 <= size; i += 4) { + size &= ~(size_t)3; + + for (i = 0; i < size; i += 4) { if (buf[i + 3] == 0xEB) { addr = (uint32_t)buf[i] | ((uint32_t)buf[i + 1] << 8) | ((uint32_t)buf[i + 2] << 16); @@ -290,7 +297,12 @@ static size_t bcj_armthumb(struct xz_dec_bcj *s, uint8_t *buf, size_t size) size_t i; uint32_t addr; - for (i = 0; i + 4 <= size; i += 2) { + if (size < 4) + return 0; + + size -= 4; + + for (i = 0; i <= size; i += 2) { if ((buf[i + 1] & 0xF8) == 0xF0 && (buf[i + 3] & 0xF8) == 0xF8) { addr = (((uint32_t)buf[i + 1] & 0x07) << 19) @@ -318,7 +330,9 @@ static size_t bcj_sparc(struct xz_dec_bcj *s, uint8_t *buf, size_t size) size_t i; uint32_t instr; - for (i = 0; i + 4 <= size; i += 4) { + size &= ~(size_t)3; + + for (i = 0; i < size; i += 4) { instr = get_unaligned_be32(buf + i); if ((instr >> 22) == 0x100 || (instr >> 22) == 0x1FF) { instr <<= 2; @@ -334,6 +348,140 @@ static size_t bcj_sparc(struct xz_dec_bcj *s, uint8_t *buf, size_t size) } #endif +#ifdef XZ_DEC_ARM64 +static size_t bcj_arm64(struct xz_dec_bcj *s, uint8_t *buf, size_t size) +{ + size_t i; + uint32_t instr; + uint32_t addr; + + size &= ~(size_t)3; + + for (i = 0; i < size; i += 4) { + instr = get_unaligned_le32(buf + i); + + if ((instr >> 26) == 0x25) { + /* BL instruction */ + addr = instr - ((s->pos + (uint32_t)i) >> 2); + instr = 0x94000000 | (addr & 0x03FFFFFF); + put_unaligned_le32(instr, buf + i); + + } else if ((instr & 0x9F000000) == 0x90000000) { + /* ADRP instruction */ + addr = ((instr >> 29) & 3) | ((instr >> 3) & 0x1FFFFC); + + /* Only convert values in the range +/-512 MiB. */ + if ((addr + 0x020000) & 0x1C0000) + continue; + + addr -= (s->pos + (uint32_t)i) >> 12; + + instr &= 0x9000001F; + instr |= (addr & 3) << 29; + instr |= (addr & 0x03FFFC) << 3; + instr |= (0U - (addr & 0x020000)) & 0xE00000; + + put_unaligned_le32(instr, buf + i); + } + } + + return i; +} +#endif + +#ifdef XZ_DEC_RISCV +static size_t bcj_riscv(struct xz_dec_bcj *s, uint8_t *buf, size_t size) +{ + size_t i; + uint32_t b1; + uint32_t b2; + uint32_t b3; + uint32_t instr; + uint32_t instr2; + uint32_t instr2_rs1; + uint32_t addr; + + if (size < 8) + return 0; + + size -= 8; + + for (i = 0; i <= size; i += 2) { + instr = buf[i]; + + if (instr == 0xEF) { + /* JAL */ + b1 = buf[i + 1]; + if ((b1 & 0x0D) != 0) + continue; + + b2 = buf[i + 2]; + b3 = buf[i + 3]; + + addr = ((b1 & 0xF0) << 13) | (b2 << 9) | (b3 << 1); + addr -= s->pos + (uint32_t)i; + + buf[i + 1] = (uint8_t)((b1 & 0x0F) + | ((addr >> 8) & 0xF0)); + + buf[i + 2] = (uint8_t)(((addr >> 16) & 0x0F) + | ((addr >> 7) & 0x10) + | ((addr << 4) & 0xE0)); + + buf[i + 3] = (uint8_t)(((addr >> 4) & 0x7F) + | ((addr >> 13) & 0x80)); + + i += 4 - 2; + + } else if ((instr & 0x7F) == 0x17) { + /* AUIPC */ + instr |= (uint32_t)buf[i + 1] << 8; + instr |= (uint32_t)buf[i + 2] << 16; + instr |= (uint32_t)buf[i + 3] << 24; + + if (instr & 0xE80) { + /* AUIPC's rd doesn't equal x0 or x2. */ + instr2 = get_unaligned_le32(buf + i + 4); + + if (((instr << 8) ^ (instr2 - 3)) & 0xF8003) { + i += 6 - 2; + continue; + } + + addr = (instr & 0xFFFFF000) + (instr2 >> 20); + + instr = 0x17 | (2 << 7) | (instr2 << 12); + instr2 = addr; + } else { + /* AUIPC's rd equals x0 or x2. */ + instr2_rs1 = instr >> 27; + + if ((uint32_t)((instr - 0x3117) << 18) + >= (instr2_rs1 & 0x1D)) { + i += 4 - 2; + continue; + } + + addr = get_unaligned_be32(buf + i + 4); + addr -= s->pos + (uint32_t)i; + + instr2 = (instr >> 12) | (addr << 20); + + instr = 0x17 | (instr2_rs1 << 7) + | ((addr + 0x800) & 0xFFFFF000); + } + + put_unaligned_le32(instr, buf + i); + put_unaligned_le32(instr2, buf + i + 4); + + i += 8 - 2; + } + } + + return i; +} +#endif + /* * Apply the selected BCJ filter. Update *pos and s->pos to match the amount * of data that got filtered. @@ -381,6 +529,16 @@ static void bcj_apply(struct xz_dec_bcj *s, filtered = bcj_sparc(s, buf, size); break; #endif +#ifdef XZ_DEC_ARM64 + case BCJ_ARM64: + filtered = bcj_arm64(s, buf, size); + break; +#endif +#ifdef XZ_DEC_RISCV + case BCJ_RISCV: + filtered = bcj_riscv(s, buf, size); + break; +#endif default: /* Never reached but silence compiler warnings. */ filtered = 0; @@ -414,9 +572,8 @@ static void bcj_flush(struct xz_dec_bcj *s, struct xz_buf *b) * data in chunks of 1-16 bytes. To hide this issue, this function does * some buffering. */ -XZ_EXTERN enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s, - struct xz_dec_lzma2 *lzma2, - struct xz_buf *b) +enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s, struct xz_dec_lzma2 *lzma2, + struct xz_buf *b) { size_t out_start; @@ -524,7 +681,7 @@ XZ_EXTERN enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s, return s->ret; } -XZ_EXTERN struct xz_dec_bcj *xz_dec_bcj_create(bool single_call) +struct xz_dec_bcj *xz_dec_bcj_create(bool single_call) { struct xz_dec_bcj *s = kmalloc(sizeof(*s), GFP_KERNEL); if (s != NULL) @@ -533,7 +690,7 @@ XZ_EXTERN struct xz_dec_bcj *xz_dec_bcj_create(bool single_call) return s; } -XZ_EXTERN enum xz_ret xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id) +enum xz_ret xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id) { switch (id) { #ifdef XZ_DEC_X86 @@ -554,6 +711,12 @@ XZ_EXTERN enum xz_ret xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id) #ifdef XZ_DEC_SPARC case BCJ_SPARC: #endif +#ifdef XZ_DEC_ARM64 + case BCJ_ARM64: +#endif +#ifdef XZ_DEC_RISCV + case BCJ_RISCV: +#endif break; default: diff --git a/lib/xz/xz_dec_lzma2.c b/lib/xz/xz_dec_lzma2.c index 27ce34520e78..83bb66b6016d 100644 --- a/lib/xz/xz_dec_lzma2.c +++ b/lib/xz/xz_dec_lzma2.c @@ -1,11 +1,10 @@ +// SPDX-License-Identifier: 0BSD + /* * LZMA2 decoder * * Authors: Lasse Collin <lasse.collin@tukaani.org> * Igor Pavlov <https://7-zip.org/> - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ #include "xz_private.h" @@ -961,8 +960,7 @@ static bool lzma2_lzma(struct xz_dec_lzma2 *s, struct xz_buf *b) * Take care of the LZMA2 control layer, and forward the job of actual LZMA * decoding or copying of uncompressed chunks to other functions. */ -XZ_EXTERN enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s, - struct xz_buf *b) +enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s, struct xz_buf *b) { uint32_t tmp; @@ -1138,8 +1136,7 @@ XZ_EXTERN enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s, return XZ_OK; } -XZ_EXTERN struct xz_dec_lzma2 *xz_dec_lzma2_create(enum xz_mode mode, - uint32_t dict_max) +struct xz_dec_lzma2 *xz_dec_lzma2_create(enum xz_mode mode, uint32_t dict_max) { struct xz_dec_lzma2 *s = kmalloc(sizeof(*s), GFP_KERNEL); if (s == NULL) @@ -1162,7 +1159,7 @@ XZ_EXTERN struct xz_dec_lzma2 *xz_dec_lzma2_create(enum xz_mode mode, return s; } -XZ_EXTERN enum xz_ret xz_dec_lzma2_reset(struct xz_dec_lzma2 *s, uint8_t props) +enum xz_ret xz_dec_lzma2_reset(struct xz_dec_lzma2 *s, uint8_t props) { /* This limits dictionary size to 3 GiB to keep parsing simpler. */ if (props > 39) @@ -1198,7 +1195,7 @@ XZ_EXTERN enum xz_ret xz_dec_lzma2_reset(struct xz_dec_lzma2 *s, uint8_t props) return XZ_OK; } -XZ_EXTERN void xz_dec_lzma2_end(struct xz_dec_lzma2 *s) +void xz_dec_lzma2_end(struct xz_dec_lzma2 *s) { if (DEC_IS_MULTI(s->dict.mode)) vfree(s->dict.buf); diff --git a/lib/xz/xz_dec_stream.c b/lib/xz/xz_dec_stream.c index 683570b93a8c..f9d003684d56 100644 --- a/lib/xz/xz_dec_stream.c +++ b/lib/xz/xz_dec_stream.c @@ -1,10 +1,9 @@ +// SPDX-License-Identifier: 0BSD + /* * .xz Stream decoder * * Author: Lasse Collin <lasse.collin@tukaani.org> - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ #include "xz_private.h" @@ -747,7 +746,7 @@ static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b) * actually succeeds (that's the price to pay of using the output buffer as * the workspace). */ -XZ_EXTERN enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b) +enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b) { size_t in_start; size_t out_start; @@ -783,7 +782,7 @@ XZ_EXTERN enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b) return ret; } -XZ_EXTERN struct xz_dec *xz_dec_init(enum xz_mode mode, uint32_t dict_max) +struct xz_dec *xz_dec_init(enum xz_mode mode, uint32_t dict_max) { struct xz_dec *s = kmalloc(sizeof(*s), GFP_KERNEL); if (s == NULL) @@ -813,7 +812,7 @@ error_bcj: return NULL; } -XZ_EXTERN void xz_dec_reset(struct xz_dec *s) +void xz_dec_reset(struct xz_dec *s) { s->sequence = SEQ_STREAM_HEADER; s->allow_buf_error = false; @@ -825,7 +824,7 @@ XZ_EXTERN void xz_dec_reset(struct xz_dec *s) s->temp.size = STREAM_HEADER_SIZE; } -XZ_EXTERN void xz_dec_end(struct xz_dec *s) +void xz_dec_end(struct xz_dec *s) { if (s != NULL) { xz_dec_lzma2_end(s->lzma2); diff --git a/lib/xz/xz_dec_syms.c b/lib/xz/xz_dec_syms.c index 61098c67a413..f40817d65897 100644 --- a/lib/xz/xz_dec_syms.c +++ b/lib/xz/xz_dec_syms.c @@ -1,10 +1,9 @@ +// SPDX-License-Identifier: 0BSD + /* * XZ decoder module information * * Author: Lasse Collin <lasse.collin@tukaani.org> - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ #include <linux/module.h> @@ -23,11 +22,6 @@ EXPORT_SYMBOL(xz_dec_microlzma_end); #endif MODULE_DESCRIPTION("XZ decompressor"); -MODULE_VERSION("1.1"); +MODULE_VERSION("1.2"); MODULE_AUTHOR("Lasse Collin <lasse.collin@tukaani.org> and Igor Pavlov"); - -/* - * This code is in the public domain, but in Linux it's simplest to just - * say it's GPL and consider the authors as the copyright holders. - */ -MODULE_LICENSE("GPL"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/lib/xz/xz_dec_test.c b/lib/xz/xz_dec_test.c index da28a19d6c98..53d3600f2ddb 100644 --- a/lib/xz/xz_dec_test.c +++ b/lib/xz/xz_dec_test.c @@ -1,10 +1,9 @@ +// SPDX-License-Identifier: 0BSD + /* * XZ decoder tester * * Author: Lasse Collin <lasse.collin@tukaani.org> - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ #include <linux/kernel.h> @@ -212,9 +211,4 @@ module_exit(xz_dec_test_exit); MODULE_DESCRIPTION("XZ decompressor tester"); MODULE_VERSION("1.0"); MODULE_AUTHOR("Lasse Collin <lasse.collin@tukaani.org>"); - -/* - * This code is in the public domain, but in Linux it's simplest to just - * say it's GPL and consider the authors as the copyright holders. - */ -MODULE_LICENSE("GPL"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/lib/xz/xz_lzma2.h b/lib/xz/xz_lzma2.h index 92d852d4f87a..d2632b7dfb9c 100644 --- a/lib/xz/xz_lzma2.h +++ b/lib/xz/xz_lzma2.h @@ -1,11 +1,10 @@ +/* SPDX-License-Identifier: 0BSD */ + /* * LZMA2 definitions * * Authors: Lasse Collin <lasse.collin@tukaani.org> * Igor Pavlov <https://7-zip.org/> - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ #ifndef XZ_LZMA2_H diff --git a/lib/xz/xz_private.h b/lib/xz/xz_private.h index bf1e94ec7873..8409784b1639 100644 --- a/lib/xz/xz_private.h +++ b/lib/xz/xz_private.h @@ -1,10 +1,9 @@ +/* SPDX-License-Identifier: 0BSD */ + /* * Private includes and definitions * * Author: Lasse Collin <lasse.collin@tukaani.org> - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ #ifndef XZ_PRIVATE_H @@ -13,7 +12,7 @@ #ifdef __KERNEL__ # include <linux/xz.h> # include <linux/kernel.h> -# include <asm/unaligned.h> +# include <linux/unaligned.h> /* XZ_PREBOOT may be defined only via decompress_unxz.c. */ # ifndef XZ_PREBOOT # include <linux/slab.h> @@ -37,6 +36,12 @@ # ifdef CONFIG_XZ_DEC_SPARC # define XZ_DEC_SPARC # endif +# ifdef CONFIG_XZ_DEC_ARM64 +# define XZ_DEC_ARM64 +# endif +# ifdef CONFIG_XZ_DEC_RISCV +# define XZ_DEC_RISCV +# endif # ifdef CONFIG_XZ_DEC_MICROLZMA # define XZ_DEC_MICROLZMA # endif @@ -98,23 +103,19 @@ */ #ifndef XZ_DEC_BCJ # if defined(XZ_DEC_X86) || defined(XZ_DEC_POWERPC) \ - || defined(XZ_DEC_IA64) || defined(XZ_DEC_ARM) \ + || defined(XZ_DEC_IA64) \ || defined(XZ_DEC_ARM) || defined(XZ_DEC_ARMTHUMB) \ - || defined(XZ_DEC_SPARC) + || defined(XZ_DEC_SPARC) || defined(XZ_DEC_ARM64) \ + || defined(XZ_DEC_RISCV) # define XZ_DEC_BCJ # endif #endif -#ifndef CRC32_POLY_LE -#define CRC32_POLY_LE 0xedb88320 -#endif - /* * Allocate memory for LZMA2 decoder. xz_dec_lzma2_reset() must be used * before calling xz_dec_lzma2_run(). */ -XZ_EXTERN struct xz_dec_lzma2 *xz_dec_lzma2_create(enum xz_mode mode, - uint32_t dict_max); +struct xz_dec_lzma2 *xz_dec_lzma2_create(enum xz_mode mode, uint32_t dict_max); /* * Decode the LZMA2 properties (one byte) and reset the decoder. Return @@ -122,22 +123,20 @@ XZ_EXTERN struct xz_dec_lzma2 *xz_dec_lzma2_create(enum xz_mode mode, * big enough, and XZ_OPTIONS_ERROR if props indicates something that this * decoder doesn't support. */ -XZ_EXTERN enum xz_ret xz_dec_lzma2_reset(struct xz_dec_lzma2 *s, - uint8_t props); +enum xz_ret xz_dec_lzma2_reset(struct xz_dec_lzma2 *s, uint8_t props); /* Decode raw LZMA2 stream from b->in to b->out. */ -XZ_EXTERN enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s, - struct xz_buf *b); +enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s, struct xz_buf *b); /* Free the memory allocated for the LZMA2 decoder. */ -XZ_EXTERN void xz_dec_lzma2_end(struct xz_dec_lzma2 *s); +void xz_dec_lzma2_end(struct xz_dec_lzma2 *s); #ifdef XZ_DEC_BCJ /* * Allocate memory for BCJ decoders. xz_dec_bcj_reset() must be used before * calling xz_dec_bcj_run(). */ -XZ_EXTERN struct xz_dec_bcj *xz_dec_bcj_create(bool single_call); +struct xz_dec_bcj *xz_dec_bcj_create(bool single_call); /* * Decode the Filter ID of a BCJ filter. This implementation doesn't @@ -145,16 +144,15 @@ XZ_EXTERN struct xz_dec_bcj *xz_dec_bcj_create(bool single_call); * is needed. Returns XZ_OK if the given Filter ID is supported. * Otherwise XZ_OPTIONS_ERROR is returned. */ -XZ_EXTERN enum xz_ret xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id); +enum xz_ret xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id); /* * Decode raw BCJ + LZMA2 stream. This must be used only if there actually is * a BCJ filter in the chain. If the chain has only LZMA2, xz_dec_lzma2_run() * must be called directly. */ -XZ_EXTERN enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s, - struct xz_dec_lzma2 *lzma2, - struct xz_buf *b); +enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s, struct xz_dec_lzma2 *lzma2, + struct xz_buf *b); /* Free the memory allocated for the BCJ filters. */ #define xz_dec_bcj_end(s) kfree(s) diff --git a/lib/xz/xz_stream.h b/lib/xz/xz_stream.h index 430bb3a0d195..55f9f6f94b78 100644 --- a/lib/xz/xz_stream.h +++ b/lib/xz/xz_stream.h @@ -1,10 +1,9 @@ +/* SPDX-License-Identifier: 0BSD */ + /* * Definitions for handling the .xz file format * * Author: Lasse Collin <lasse.collin@tukaani.org> - * - * This file has been put into the public domain. - * You can do whatever you want with this file. */ #ifndef XZ_STREAM_H diff --git a/lib/zlib_deflate/deflate_syms.c b/lib/zlib_deflate/deflate_syms.c index 24b740b99678..68941a2350ea 100644 --- a/lib/zlib_deflate/deflate_syms.c +++ b/lib/zlib_deflate/deflate_syms.c @@ -17,4 +17,5 @@ EXPORT_SYMBOL(zlib_deflate); EXPORT_SYMBOL(zlib_deflateInit2); EXPORT_SYMBOL(zlib_deflateEnd); EXPORT_SYMBOL(zlib_deflateReset); +MODULE_DESCRIPTION("Data compression using the deflation algorithm"); MODULE_LICENSE("GPL"); diff --git a/lib/zlib_dfltcc/dfltcc.h b/lib/zlib_dfltcc/dfltcc.h index b96232bdd44d..0f2a16d7a48a 100644 --- a/lib/zlib_dfltcc/dfltcc.h +++ b/lib/zlib_dfltcc/dfltcc.h @@ -80,6 +80,7 @@ struct dfltcc_param_v0 { uint8_t csb[1152]; }; +static_assert(offsetof(struct dfltcc_param_v0, csb) == 384); static_assert(sizeof(struct dfltcc_param_v0) == 1536); #define CVT_CRC32 0 diff --git a/lib/zlib_dfltcc/dfltcc_util.h b/lib/zlib_dfltcc/dfltcc_util.h index 4a46b5009f0d..10509270d822 100644 --- a/lib/zlib_dfltcc/dfltcc_util.h +++ b/lib/zlib_dfltcc/dfltcc_util.h @@ -2,6 +2,8 @@ #ifndef DFLTCC_UTIL_H #define DFLTCC_UTIL_H +#include "dfltcc.h" +#include <linux/kmsan-checks.h> #include <linux/zutil.h> /* @@ -20,6 +22,7 @@ typedef enum { #define DFLTCC_CMPR 2 #define DFLTCC_XPND 4 #define HBT_CIRCULAR (1 << 7) +#define DFLTCC_FN_MASK ((1 << 7) - 1) #define HB_BITS 15 #define HB_SIZE (1 << HB_BITS) @@ -34,6 +37,7 @@ static inline dfltcc_cc dfltcc( ) { Byte *t2 = op1 ? *op1 : NULL; + unsigned char *orig_t2 = t2; size_t t3 = len1 ? *len1 : 0; const Byte *t4 = op2 ? *op2 : NULL; size_t t5 = len2 ? *len2 : 0; @@ -59,6 +63,30 @@ static inline dfltcc_cc dfltcc( : "cc", "memory"); t2 = r2; t3 = r3; t4 = r4; t5 = r5; + /* + * Unpoison the parameter block and the output buffer. + * This is a no-op in non-KMSAN builds. + */ + switch (fn & DFLTCC_FN_MASK) { + case DFLTCC_QAF: + kmsan_unpoison_memory(param, sizeof(struct dfltcc_qaf_param)); + break; + case DFLTCC_GDHT: + kmsan_unpoison_memory(param, offsetof(struct dfltcc_param_v0, csb)); + break; + case DFLTCC_CMPR: + kmsan_unpoison_memory(param, sizeof(struct dfltcc_param_v0)); + kmsan_unpoison_memory( + orig_t2, + t2 - orig_t2 + + (((struct dfltcc_param_v0 *)param)->sbb == 0 ? 0 : 1)); + break; + case DFLTCC_XPND: + kmsan_unpoison_memory(param, sizeof(struct dfltcc_param_v0)); + kmsan_unpoison_memory(orig_t2, t2 - orig_t2); + break; + } + if (op1) *op1 = t2; if (len1) diff --git a/lib/zstd/common/mem.h b/lib/zstd/common/mem.h index 1d9cc03924ca..c22a2e69bf46 100644 --- a/lib/zstd/common/mem.h +++ b/lib/zstd/common/mem.h @@ -15,7 +15,7 @@ /*-**************************************** * Dependencies ******************************************/ -#include <asm/unaligned.h> /* get_unaligned, put_unaligned* */ +#include <linux/unaligned.h> /* get_unaligned, put_unaligned* */ #include <linux/compiler.h> /* inline */ #include <linux/swab.h> /* swab32, swab64 */ #include <linux/types.h> /* size_t, ptrdiff_t */ diff --git a/lib/zstd/compress/zstd_compress.c b/lib/zstd/compress/zstd_compress.c index f620cafca633..16bb995bc6c4 100644 --- a/lib/zstd/compress/zstd_compress.c +++ b/lib/zstd/compress/zstd_compress.c @@ -4810,6 +4810,8 @@ ZSTD_CDict* ZSTD_createCDict_advanced2( dictLoadMethod, cctxParams.cParams, cctxParams.useRowMatchFinder, cctxParams.enableDedicatedDictSearch, customMem); + if (!cdict) + return NULL; if (ZSTD_isError( ZSTD_initCDict_internal(cdict, dict, dictSize, diff --git a/lib/zstd/zstd_compress_module.c b/lib/zstd/zstd_compress_module.c index 04e1b5c01d9b..bd8784449b31 100644 --- a/lib/zstd/zstd_compress_module.c +++ b/lib/zstd/zstd_compress_module.c @@ -66,6 +66,12 @@ int zstd_max_clevel(void) } EXPORT_SYMBOL(zstd_max_clevel); +int zstd_default_clevel(void) +{ + return ZSTD_defaultCLevel(); +} +EXPORT_SYMBOL(zstd_default_clevel); + size_t zstd_compress_bound(size_t src_size) { return ZSTD_compressBound(src_size); @@ -79,6 +85,13 @@ zstd_parameters zstd_get_params(int level, } EXPORT_SYMBOL(zstd_get_params); +zstd_compression_parameters zstd_get_cparams(int level, + unsigned long long estimated_src_size, size_t dict_size) +{ + return ZSTD_getCParams(level, estimated_src_size, dict_size); +} +EXPORT_SYMBOL(zstd_get_cparams); + size_t zstd_cctx_workspace_bound(const zstd_compression_parameters *cparams) { return ZSTD_estimateCCtxSize_usingCParams(*cparams); @@ -93,6 +106,33 @@ zstd_cctx *zstd_init_cctx(void *workspace, size_t workspace_size) } EXPORT_SYMBOL(zstd_init_cctx); +zstd_cctx *zstd_create_cctx_advanced(zstd_custom_mem custom_mem) +{ + return ZSTD_createCCtx_advanced(custom_mem); +} +EXPORT_SYMBOL(zstd_create_cctx_advanced); + +size_t zstd_free_cctx(zstd_cctx *cctx) +{ + return ZSTD_freeCCtx(cctx); +} +EXPORT_SYMBOL(zstd_free_cctx); + +zstd_cdict *zstd_create_cdict_byreference(const void *dict, size_t dict_size, + zstd_compression_parameters cparams, + zstd_custom_mem custom_mem) +{ + return ZSTD_createCDict_advanced(dict, dict_size, ZSTD_dlm_byRef, + ZSTD_dct_auto, cparams, custom_mem); +} +EXPORT_SYMBOL(zstd_create_cdict_byreference); + +size_t zstd_free_cdict(zstd_cdict *cdict) +{ + return ZSTD_freeCDict(cdict); +} +EXPORT_SYMBOL(zstd_free_cdict); + size_t zstd_compress_cctx(zstd_cctx *cctx, void *dst, size_t dst_capacity, const void *src, size_t src_size, const zstd_parameters *parameters) { @@ -101,6 +141,15 @@ size_t zstd_compress_cctx(zstd_cctx *cctx, void *dst, size_t dst_capacity, } EXPORT_SYMBOL(zstd_compress_cctx); +size_t zstd_compress_using_cdict(zstd_cctx *cctx, void *dst, + size_t dst_capacity, const void *src, size_t src_size, + const ZSTD_CDict *cdict) +{ + return ZSTD_compress_usingCDict(cctx, dst, dst_capacity, + src, src_size, cdict); +} +EXPORT_SYMBOL(zstd_compress_using_cdict); + size_t zstd_cstream_workspace_bound(const zstd_compression_parameters *cparams) { return ZSTD_estimateCStreamSize_usingCParams(*cparams); diff --git a/lib/zstd/zstd_decompress_module.c b/lib/zstd/zstd_decompress_module.c index f4ed952ed485..469fc3059be0 100644 --- a/lib/zstd/zstd_decompress_module.c +++ b/lib/zstd/zstd_decompress_module.c @@ -44,6 +44,33 @@ size_t zstd_dctx_workspace_bound(void) } EXPORT_SYMBOL(zstd_dctx_workspace_bound); +zstd_dctx *zstd_create_dctx_advanced(zstd_custom_mem custom_mem) +{ + return ZSTD_createDCtx_advanced(custom_mem); +} +EXPORT_SYMBOL(zstd_create_dctx_advanced); + +size_t zstd_free_dctx(zstd_dctx *dctx) +{ + return ZSTD_freeDCtx(dctx); +} +EXPORT_SYMBOL(zstd_free_dctx); + +zstd_ddict *zstd_create_ddict_byreference(const void *dict, size_t dict_size, + zstd_custom_mem custom_mem) +{ + return ZSTD_createDDict_advanced(dict, dict_size, ZSTD_dlm_byRef, + ZSTD_dct_auto, custom_mem); + +} +EXPORT_SYMBOL(zstd_create_ddict_byreference); + +size_t zstd_free_ddict(zstd_ddict *ddict) +{ + return ZSTD_freeDDict(ddict); +} +EXPORT_SYMBOL(zstd_free_ddict); + zstd_dctx *zstd_init_dctx(void *workspace, size_t workspace_size) { if (workspace == NULL) @@ -59,6 +86,15 @@ size_t zstd_decompress_dctx(zstd_dctx *dctx, void *dst, size_t dst_capacity, } EXPORT_SYMBOL(zstd_decompress_dctx); +size_t zstd_decompress_using_ddict(zstd_dctx *dctx, + void *dst, size_t dst_capacity, const void* src, size_t src_size, + const zstd_ddict* ddict) +{ + return ZSTD_decompress_usingDDict(dctx, dst, dst_capacity, src, + src_size, ddict); +} +EXPORT_SYMBOL(zstd_decompress_using_ddict); + size_t zstd_dstream_workspace_bound(size_t max_window_size) { return ZSTD_estimateDStreamSize(max_window_size); |