November 2020 - Linux-kselftest-mirror

[PATCH v3] lib: Convert test_user_copy to KUnit test

by Vitor Massaru Iha

This adds the conversion of the runtime tests of test_user_copy fuctions, from `lib/test_user_copy.c`to KUnit tests. Signed-off-by: Vitor Massaru Iha <vitor(a)massaru.org> --- v2: * splitted patch in 3: - Allows to install and load modules in root filesystem; - Provides an userspace memory context when tests are compiled as module; - Convert test_user_copy to KUnit test; * removed entry for CONFIG_TEST_USER_COPY; * replaced pr_warn to KUNIT_EXPECT_FALSE_MSG in test macro to decrease the diff; v3: * rebased with last kunit branch * Please apply this commit from kunit-fixes: 3f37d14b8a3152441f36b6bc74000996679f0998 And these from patchwork: https://patchwork.kernel.org/patch/11676331/ https://patchwork.kernel.org/patch/11676335/ --- lib/Kconfig.debug | 28 ++++++++------ lib/Makefile | 2 +- lib/{test_user_copy.c => user_copy_kunit.c} | 42 +++++++++------------ 3 files changed, 35 insertions(+), 37 deletions(-) rename lib/{test_user_copy.c => user_copy_kunit.c} (91%) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 9ad9210d70a1..f699a3624ae7 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2078,18 +2078,6 @@ 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 @@ -2154,6 +2142,22 @@ config SYSCTL_KUNIT_TEST If unsure, say N. +config USER_COPY_KUNIT + tristate "KUnit Test for user/kernel boundary protections" + depends on KUNIT + depends on m + help + This builds the "user_copy_kunit" 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. + + 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 LIST_KUNIT_TEST tristate "KUnit Test for Kernel Linked-list structures" if !KUNIT_ALL_TESTS depends on KUNIT diff --git a/lib/Makefile b/lib/Makefile index b1c42c10073b..8c145f85accc 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -78,7 +78,6 @@ obj-$(CONFIG_TEST_VMALLOC) += test_vmalloc.o obj-$(CONFIG_TEST_OVERFLOW) += test_overflow.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_PRINTF) += test_printf.o @@ -318,3 +317,4 @@ obj-$(CONFIG_OBJAGG) += objagg.o # KUnit tests obj-$(CONFIG_LIST_KUNIT_TEST) += list-test.o obj-$(CONFIG_LINEAR_RANGES_TEST) += test_linear_ranges.o +obj-$(CONFIG_USER_COPY_KUNIT) += user_copy_kunit.o diff --git a/lib/test_user_copy.c b/lib/user_copy_kunit.c similarity index 91% rename from lib/test_user_copy.c rename to lib/user_copy_kunit.c index 5ff04d8fe971..a10ddd15b4cd 100644 --- a/lib/test_user_copy.c +++ b/lib/user_copy_kunit.c @@ -16,6 +16,7 @@ #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/vmalloc.h> +#include <kunit/test.h> /* * Several 32-bit architectures support 64-bit {get,put}_user() calls. @@ -35,7 +36,7 @@ ({ \ int cond = (condition); \ if (cond) \ - pr_warn("[%d] " msg "\n", __LINE__, ##__VA_ARGS__); \ + KUNIT_EXPECT_FALSE_MSG(test, cond, msg, ##__VA_ARGS__); \ cond; \ }) @@ -44,7 +45,7 @@ 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) +static int test_check_nonzero_user(struct kunit *test, char *kmem, char __user *umem, size_t size) { int ret = 0; size_t start, end, i, zero_start, zero_end; @@ -102,7 +103,7 @@ static int test_check_nonzero_user(char *kmem, char __user *umem, size_t size) return ret; } -static int test_copy_struct_from_user(char *kmem, char __user *umem, +static int test_copy_struct_from_user(struct kunit *test, char *kmem, char __user *umem, size_t size) { int ret = 0; @@ -177,7 +178,7 @@ static int test_copy_struct_from_user(char *kmem, char __user *umem, return ret; } -static int __init test_user_copy_init(void) +static void user_copy_test(struct kunit *test) { int ret = 0; char *kmem; @@ -192,16 +193,14 @@ static int __init test_user_copy_init(void) #endif kmem = kmalloc(PAGE_SIZE * 2, GFP_KERNEL); - if (!kmem) - return -ENOMEM; + KUNIT_EXPECT_FALSE_MSG(test, kmem == NULL, "kmalloc failed"); 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; + KUNIT_FAIL(test, "Failed to allocate user memory"); } usermem = (char __user *)user_addr; @@ -245,9 +244,9 @@ static int __init test_user_copy_init(void) #undef test_legit /* Test usage of check_nonzero_user(). */ - ret |= test_check_nonzero_user(kmem, usermem, 2 * PAGE_SIZE); + ret |= test_check_nonzero_user(test, kmem, usermem, 2 * PAGE_SIZE); /* Test usage of copy_struct_from_user(). */ - ret |= test_copy_struct_from_user(kmem, usermem, 2 * PAGE_SIZE); + ret |= test_copy_struct_from_user(test, kmem, usermem, 2 * PAGE_SIZE); /* * Invalid usage: none of these copies should succeed. @@ -309,23 +308,18 @@ static int __init test_user_copy_init(void) 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"); -} +static struct kunit_case user_copy_test_cases[] = { + KUNIT_CASE(user_copy_test), + {} +}; -module_exit(test_user_copy_exit); +static struct kunit_suite user_copy_test_suite = { + .name = "user_copy", + .test_cases = user_copy_test_cases, +}; +kunit_test_suites(&user_copy_test_suite); MODULE_AUTHOR("Kees Cook <keescook(a)chromium.org>"); MODULE_LICENSE("GPL"); base-commit: d43c7fb05765152d4d4a39a8ef957c4ea14d8847 -- 2.26.2

4 months, 2 weeks

4
11
0 0

[PATCH net-next v2 0/3] net: introduce rps_default_mask

by Paolo Abeni

Real-time setups try hard to ensure proper isolation between time critical applications and e.g. network processing performed by the network stack in softirq and RPS is used to move the softirq activity away from the isolated core. If the network configuration is dynamic, with netns and devices routinely created at run-time, enforcing the correct RPS setting on each newly created device allowing to transient bad configuration became complex. These series try to address the above, introducing a new sysctl knob: rps_default_mask. The new sysctl entry allows configuring a systemwide RPS mask, to be enforced since receive queue creation time without any fourther per device configuration required. Additionally, a simple self-test is introduced to check the rps_default_mask behavior. v1 -> v2: - fix sparse warning in patch 2/3 Paolo Abeni (3): net/sysctl: factor-out netdev_rx_queue_set_rps_mask() helper net/core: introduce default_rps_mask netns attribute self-tests: introduce self-tests for RPS default mask Documentation/admin-guide/sysctl/net.rst | 6 ++ include/linux/netdevice.h | 1 + net/core/net-sysfs.c | 73 +++++++++++-------- net/core/sysctl_net_core.c | 58 +++++++++++++++ tools/testing/selftests/net/Makefile | 1 + tools/testing/selftests/net/config | 3 + .../testing/selftests/net/rps_default_mask.sh | 57 +++++++++++++++ 7 files changed, 169 insertions(+), 30 deletions(-) create mode 100755 tools/testing/selftests/net/rps_default_mask.sh -- 2.26.2

1 year, 10 months

4
12
0 0

[PATCH v2 net-next 0/3] ptp: Add adjust phase to support phase offset.

by vincent.cheng.xh＠renesas.com

From: Vincent Cheng <vincent.cheng.xh(a)renesas.com> This series adds adjust phase to the PTP Hardware Clock device interface. Some PTP hardware clocks have a write phase mode that has a built-in hardware filtering capability. The write phase mode utilizes a phase offset control word instead of a frequency offset control word. Add adjust phase function to take advantage of this capability. Changes since v1: - As suggested by Richard Cochran: 1. ops->adjphase is new so need to check for non-null function pointer. 2. Kernel coding style uses lower_case_underscores. 3. Use existing PTP clock API for delayed worker. Vincent Cheng (3): ptp: Add adjphase function to support phase offset control. ptp: Add adjust_phase to ptp_clock_caps capability. ptp: ptp_clockmatrix: Add adjphase() to support PHC write phase mode. drivers/ptp/ptp_chardev.c | 1 + drivers/ptp/ptp_clock.c | 3 ++ drivers/ptp/ptp_clockmatrix.c | 92 +++++++++++++++++++++++++++++++++++ drivers/ptp/ptp_clockmatrix.h | 8 ++- include/linux/ptp_clock_kernel.h | 6 ++- include/uapi/linux/ptp_clock.h | 4 +- tools/testing/selftests/ptp/testptp.c | 6 ++- 7 files changed, 114 insertions(+), 6 deletions(-) -- 2.7.4

2 years, 4 months

5
8
0 0

[PATCH V2 0/3] riscv: add support for restartable sequence

by Vincent Chen

Add RSEQ, restartable sequence, support and related selftest to RISCV. The Kconfig option HAVE_REGS_AND_STACK_ACCESS_API is also required by RSEQ because RSEQ will modify the content of pt_regs.sepc through instruction_pointer_set() during the fixup procedure. In order to select the config HAVE_REGS_AND_STACK_ACCESS_API, the missing APIs for accessing pt_regs are also added in this patch set. The relevant RSEQ tests in kselftest require the Binutils patch "RISC-V: Fix linker problems with TLS copy relocs" to avoid placing PREINIT_ARRAY and TLS variable of librseq.so at the same address. https://sourceware.org/git/gitweb.cgi?p=binutils-gdb.git;a=commit;h=3e7bd7f… A segmental fault will happen if binutils misses this patch. Patrick Stählin (1): riscv: add required functions to enable HAVE_REGS_AND_STACK_ACCESS_API Vincent Chen (2): riscv: Add support for restartable sequence rseq/selftests: Add support for riscv Changes since v1: 1. Use the correct register name to access pt_regs arch/riscv/Kconfig | 2 + arch/riscv/include/asm/ptrace.h | 29 +- arch/riscv/kernel/entry.S | 4 + arch/riscv/kernel/ptrace.c | 99 +++++ arch/riscv/kernel/signal.c | 2 + tools/testing/selftests/rseq/param_test.c | 23 ++ tools/testing/selftests/rseq/rseq-riscv.h | 622 ++++++++++++++++++++++++++++++ tools/testing/selftests/rseq/rseq.h | 2 + 8 files changed, 782 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/rseq/rseq-riscv.h -- 2.7.4

3 years, 5 months

3
8
0 0

[PATCH v8 0/7] Syscall User Dispatch

by Gabriel Krisman Bertazi

Hi, This is v8 of syscall user dispatch. Last version got some acks but there was one small documentation fix I wanted to do, as requested by Florian. This also addresses the commit message fixup Peter requested. The only actual code change from v7 is solving a trivial merge conflict I myself created with the entry code fixup I made week and with something else in the TIP tree. I also shared this with glibc and there wasn't any complaints other than the matter about user-notif vs. siginfo, which was discussed in v7 and the understanding is that it is not necessary now and can be added later, if needed, on the same infrastructure without a new api. I'm not sure about TIP the rules, but is it too late to be queued for the next merge window? I'd love to have this in 5.11 if possible, since it has been flying for quite a while. This is based on tip/master. As usual, a working tree with this patchset is available at: https://gitlab.collabora.com/krisman/linux -b syscall-user-dispatch-v8 Previous submissions are archived at: RFC/v1: https://lkml.org/lkml/2020/7/8/96 v2: https://lkml.org/lkml/2020/7/9/17 v3: https://lkml.org/lkml/2020/7/12/4 v4: https://www.spinics.net/lists/linux-kselftest/msg16377.html v5: https://lkml.org/lkml/2020/8/10/1320 v6: https://lkml.org/lkml/2020/9/4/1122 v7: https://lwn.net/Articles/837598/ Gabriel Krisman Bertazi (7): x86: vdso: Expose sigreturn address on vdso to the kernel signal: Expose SYS_USER_DISPATCH si_code type kernel: Implement selective syscall userspace redirection entry: Support Syscall User Dispatch on common syscall entry selftests: Add kselftest for syscall user dispatch selftests: Add benchmark for syscall user dispatch docs: Document Syscall User Dispatch .../admin-guide/syscall-user-dispatch.rst | 87 +++++ arch/x86/entry/vdso/vdso2c.c | 2 + arch/x86/entry/vdso/vdso32/sigreturn.S | 2 + arch/x86/entry/vdso/vma.c | 15 + arch/x86/include/asm/elf.h | 2 + arch/x86/include/asm/vdso.h | 2 + arch/x86/kernel/signal_compat.c | 2 +- fs/exec.c | 3 + include/linux/entry-common.h | 2 + include/linux/sched.h | 2 + include/linux/syscall_user_dispatch.h | 40 +++ include/linux/thread_info.h | 2 + include/uapi/asm-generic/siginfo.h | 3 +- include/uapi/linux/prctl.h | 5 + kernel/entry/Makefile | 2 +- kernel/entry/common.c | 17 + kernel/entry/common.h | 16 + kernel/entry/syscall_user_dispatch.c | 102 ++++++ kernel/fork.c | 1 + kernel/sys.c | 5 + tools/testing/selftests/Makefile | 1 + .../syscall_user_dispatch/.gitignore | 3 + .../selftests/syscall_user_dispatch/Makefile | 9 + .../selftests/syscall_user_dispatch/config | 1 + .../syscall_user_dispatch/sud_benchmark.c | 200 +++++++++++ .../syscall_user_dispatch/sud_test.c | 310 ++++++++++++++++++ 26 files changed, 833 insertions(+), 3 deletions(-) create mode 100644 Documentation/admin-guide/syscall-user-dispatch.rst create mode 100644 include/linux/syscall_user_dispatch.h create mode 100644 kernel/entry/common.h create mode 100644 kernel/entry/syscall_user_dispatch.c create mode 100644 tools/testing/selftests/syscall_user_dispatch/.gitignore create mode 100644 tools/testing/selftests/syscall_user_dispatch/Makefile create mode 100644 tools/testing/selftests/syscall_user_dispatch/config create mode 100644 tools/testing/selftests/syscall_user_dispatch/sud_benchmark.c create mode 100644 tools/testing/selftests/syscall_user_dispatch/sud_test.c -- 2.29.2

3 years, 5 months

6
17
0 0

[PATCH V3 00/10] PKS: Add Protection Keys Supervisor (PKS) support V3

by ira.weiny＠intel.com

From: Ira Weiny <ira.weiny(a)intel.com> Changes from V2 [4] Rebased on tip-tree/core/entry From Thomas Gleixner Address bisectability Drop Patch: x86/entry: Move nmi entry/exit into common code From Greg KH Remove WARN_ON's From Dan Williams Add __must_check to pks_key_alloc() New patch: x86/pks: Add PKS defines and config options Split from Enable patch to build on through the series Fix compile errors Changes from V1 Rebase to TIP master; resolve conflicts and test Clean up some kernel docs updates missed in V1 Add irqentry_state_t kernel doc for PKRS field Removed redundant irq_state->pkrs This is only needed when we add the global state and somehow ended up in this patch series. That will come back when we add the global functionality in. From Thomas Gleixner Update commit messages Add kernel doc for struct irqentry_state_t From Dave Hansen add flags to pks_key_alloc() Changes from RFC V3[3] Rebase to TIP master Update test error output Standardize on 'irq_state' for state variables From Dave Hansen Update commit messages Add/clean up comments Add X86_FEATURE_PKS to disabled-features.h and remove some explicit CONFIG checks Move saved_pkrs member of thread_struct Remove superfluous preempt_disable() s/irq_save_pks/irq_save_set_pks/ Ensure PKRS is not seen in faults if not configured or not supported s/pks_mknoaccess/pks_mk_noaccess/ s/pks_mkread/pks_mk_readonly/ s/pks_mkrdwr/pks_mk_readwrite/ Change pks_key_alloc return to -EOPNOTSUPP when not supported From Peter Zijlstra Clean up Attribution Remove superfluous preempt_disable() Add union to differentiate exit_rcu/lockdep use in irqentry_state_t From Thomas Gleixner Add preliminary clean up patch and adjust series as needed Introduce a new page protection mechanism for supervisor pages, Protection Key Supervisor (PKS). 2 use cases for PKS are being developed, trusted keys and PMEM. Trusted keys is a newer use case which is still being explored. PMEM was submitted as part of the RFC (v2) series[1]. However, since then it was found that some callers of kmap() require a global implementation of PKS. Specifically some users of kmap() expect mappings to be available to all kernel threads. While global use of PKS is rare it needs to be included for correctness. Unfortunately the kmap() updates required a large patch series to make the needed changes at the various kmap() call sites so that patch set has been split out. Because the global PKS feature is only required for that use case it will be deferred to that set as well.[2] This patch set is being submitted as a precursor to both of the use cases. For an overview of the entire PKS ecosystem, a git tree including this series and 2 proposed use cases can be found here: https://lore.kernel.org/lkml/20201009195033.3208459-1-ira.weiny@intel.com/ https://lore.kernel.org/lkml/20201009201410.3209180-1-ira.weiny@intel.com/ PKS enables protections on 'domains' of supervisor pages to limit supervisor mode access to those pages beyond the normal paging protections. PKS works in a similar fashion to user space pkeys, PKU. As with PKU, supervisor pkeys are checked in addition to normal paging protections and Access or Writes can be disabled via a MSR update without TLB flushes when permissions change. Also like PKU, a page mapping is assigned to a domain by setting pkey bits in the page table entry for that mapping. Access is controlled through a PKRS register which is updated via WRMSR/RDMSR. XSAVE is not supported for the PKRS MSR. Therefore the implementation saves/restores the MSR across context switches and during exceptions. Nested exceptions are supported by each exception getting a new PKS state. For consistent behavior with current paging protections, pkey 0 is reserved and configured to allow full access via the pkey mechanism, thus preserving the default paging protections on mappings with the default pkey value of 0. Other keys, (1-15) are allocated by an allocator which prepares us for key contention from day one. Kernel users should be prepared for the allocator to fail either because of key exhaustion or due to PKS not being supported on the arch and/or CPU instance. The following are key attributes of PKS. 1) Fast switching of permissions 1a) Prevents access without page table manipulations 1b) No TLB flushes required 2) Works on a per thread basis PKS is available with 4 and 5 level paging. Like PKRU it consumes 4 bits from the PTE to store the pkey within the entry. [1] https://lore.kernel.org/lkml/20200717072056.73134-1-ira.weiny@intel.com/ [2] https://lore.kernel.org/lkml/20201009195033.3208459-2-ira.weiny@intel.com/ [3] https://lore.kernel.org/lkml/20201009194258.3207172-1-ira.weiny@intel.com/ [4] https://lore.kernel.org/lkml/20201102205320.1458656-1-ira.weiny@intel.com/ Fenghua Yu (2): x86/pks: Add PKS kernel API x86/pks: Enable Protection Keys Supervisor (PKS) Ira Weiny (8): x86/pkeys: Create pkeys_common.h x86/fpu: Refactor arch_set_user_pkey_access() for PKS support x86/pks: Add PKS defines and Kconfig options x86/pks: Preserve the PKRS MSR on context switch x86/entry: Pass irqentry_state_t by reference x86/entry: Preserve PKRS MSR across exceptions x86/fault: Report the PKRS state on fault x86/pks: Add PKS test code Documentation/core-api/protection-keys.rst | 103 ++- arch/x86/Kconfig | 1 + arch/x86/entry/common.c | 46 +- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/include/asm/disabled-features.h | 8 +- arch/x86/include/asm/idtentry.h | 25 +- arch/x86/include/asm/msr-index.h | 1 + arch/x86/include/asm/pgtable.h | 13 +- arch/x86/include/asm/pgtable_types.h | 12 + arch/x86/include/asm/pkeys.h | 15 + arch/x86/include/asm/pkeys_common.h | 40 ++ arch/x86/include/asm/processor.h | 18 +- arch/x86/include/uapi/asm/processor-flags.h | 2 + arch/x86/kernel/cpu/common.c | 15 + arch/x86/kernel/cpu/mce/core.c | 4 +- arch/x86/kernel/fpu/xstate.c | 22 +- arch/x86/kernel/kvm.c | 6 +- arch/x86/kernel/nmi.c | 4 +- arch/x86/kernel/process.c | 26 + arch/x86/kernel/traps.c | 21 +- arch/x86/mm/fault.c | 87 ++- arch/x86/mm/pkeys.c | 196 +++++- include/linux/entry-common.h | 31 +- include/linux/pgtable.h | 4 + include/linux/pkeys.h | 24 + kernel/entry/common.c | 44 +- lib/Kconfig.debug | 12 + lib/Makefile | 3 + lib/pks/Makefile | 3 + lib/pks/pks_test.c | 692 ++++++++++++++++++++ mm/Kconfig | 2 + tools/testing/selftests/x86/Makefile | 3 +- tools/testing/selftests/x86/test_pks.c | 66 ++ 33 files changed, 1410 insertions(+), 140 deletions(-) create mode 100644 arch/x86/include/asm/pkeys_common.h create mode 100644 lib/pks/Makefile create mode 100644 lib/pks/pks_test.c create mode 100644 tools/testing/selftests/x86/test_pks.c -- 2.28.0.rc0.12.gb6a658bd00c9

3 years, 12 months

9
44
0 0

[PATCH v4 0/5] Speed up mremap on large regions

by Kalesh Singh

This is a repost of the mremap speed up patches, adding Kirill's Acked-by's (from a separate discussion). The previous versions are posted at: v1 - https://lore.kernel.org/r/20200930222130.4175584-1-kaleshsingh@google.com v2 - https://lore.kernel.org/r/20201002162101.665549-1-kaleshsingh@google.com v3 - http://lore.kernel.org/r/20201005154017.474722-1-kaleshsingh@google.com mremap time can be optimized by moving entries at the PMD/PUD level if the source and destination addresses are PMD/PUD-aligned and PMD/PUD-sized. Enable moving at the PMD and PUD levels on arm64 and x86. Other architectures where this type of move is supported and known to be safe can also opt-in to these optimizations by enabling HAVE_MOVE_PMD and HAVE_MOVE_PUD. Observed Performance Improvements for remapping a PUD-aligned 1GB-sized region on x86 and arm64: - HAVE_MOVE_PMD is already enabled on x86 : N/A - Enabling HAVE_MOVE_PUD on x86 : ~13x speed up - Enabling HAVE_MOVE_PMD on arm64 : ~ 8x speed up - Enabling HAVE_MOVE_PUD on arm64 : ~19x speed up Altogether, HAVE_MOVE_PMD and HAVE_MOVE_PUD give a total of ~150x speed up on arm64. Changes in v2: - Reduce mremap_test time by only validating a configurable threshold of the remapped region, as per John. - Use a random pattern for mremap validation. Provide pattern seed in test output, as per John. - Moved set_pud_at() to separate patch, per Kirill. - Use switch() instead of ifs in move_pgt_entry(), per Kirill. - Update commit message with description of Android garbage collector use case for HAVE_MOVE_PUD, as per Joel. - Fix build test error reported by kernel test robot in [1]. Changes in v3: - Make lines 80 cols or less where they don’t need to be longer, per John. - Removed unused PATTERN_SIZE in mremap_test - Added Reviewed-by tag for patch 1/5 (mremap kselftest patch). - Use switch() instead of ifs in get_extent(), per Kirill - Add BUILD_BUG() is get_extent() default case. - Move get_old_pud() and alloc_new_pud() out of #ifdef CONFIG_HAVE_MOVE_PUD, per Kirill. - Have get_old_pmd() and alloc_new_pmd() use get_old_pud() and alloc_old_pud(), per Kirill. - Replace #ifdef CONFIG_HAVE_MOVE_PMD / PUD in move_page_tables() with IS_ENABLED(CONFIG_HAVE_MOVE_PMD / PUD), per Kirill. - Fold Add set_pud_at() patch into patch 4/5, per Kirill. [1] https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org/thread/CKPGL4F… Kalesh Singh (5): kselftests: vm: Add mremap tests arm64: mremap speedup - Enable HAVE_MOVE_PMD mm: Speedup mremap on 1GB or larger regions arm64: mremap speedup - Enable HAVE_MOVE_PUD x86: mremap speedup - Enable HAVE_MOVE_PUD arch/Kconfig | 7 + arch/arm64/Kconfig | 2 + arch/arm64/include/asm/pgtable.h | 1 + arch/x86/Kconfig | 1 + mm/mremap.c | 230 ++++++++++++--- tools/testing/selftests/vm/.gitignore | 1 + tools/testing/selftests/vm/Makefile | 1 + tools/testing/selftests/vm/mremap_test.c | 344 +++++++++++++++++++++++ tools/testing/selftests/vm/run_vmtests | 11 + 9 files changed, 558 insertions(+), 40 deletions(-) create mode 100644 tools/testing/selftests/vm/mremap_test.c -- 2.28.0.1011.ga647a8990f-goog

4 years

4
11
0 0

[PATCH v2 1/4] lib: vsprintf: Fix handling of number field widths in vsscanf

by Richard Fitzgerald

The existing code attempted to handle numbers by doing a strto[u]l(), ignoring the field width, and then bitshifting the field out of the converted value. If the string contains a run of valid digits longer than will fit in a long or long long, this would overflow and no amount of bitshifting can recover the correct value. This patch fixes vsscanf to obey number field widths when parsing the number. A new _parse_integer_limit() is added that takes a limit for the number of characters to parse. The number field conversion in vsscanf is changed to use this new function. The cases of a base prefix or leading '-' that is >= the maximum field width is handled such that the result of a sccanf is consistent with the observed behaviour of userland sscanf. Signed-off-by: Richard Fitzgerald <rf(a)opensource.cirrus.com> --- lib/kstrtox.c | 13 +++++-- lib/kstrtox.h | 2 ++ lib/vsprintf.c | 93 ++++++++++++++++++++++++++++++-------------------- 3 files changed, 68 insertions(+), 40 deletions(-) diff --git a/lib/kstrtox.c b/lib/kstrtox.c index a14ccf905055..0ac2ee8bd9d0 100644 --- a/lib/kstrtox.c +++ b/lib/kstrtox.c @@ -39,20 +39,22 @@ const char *_parse_integer_fixup_radix(const char *s, unsigned int *base) /* * Convert non-negative integer string representation in explicitly given radix - * to an integer. + * to an integer. A maximum of max_chars characters will be converted. + * * Return number of characters consumed maybe or-ed with overflow bit. * If overflow occurs, result integer (incorrect) is still returned. * * Don't you dare use this function. */ -unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long *p) +unsigned int _parse_integer_limit(const char *s, unsigned int base, + unsigned long long *p, size_t max_chars) { unsigned long long res; unsigned int rv; res = 0; rv = 0; - while (1) { + for (; max_chars > 0; max_chars--) { unsigned int c = *s; unsigned int lc = c | 0x20; /* don't tolower() this line */ unsigned int val; @@ -82,6 +84,11 @@ unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long return rv; } +unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long *p) +{ + return _parse_integer_limit(s, base, p, INT_MAX); +} + static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res) { unsigned long long _res; diff --git a/lib/kstrtox.h b/lib/kstrtox.h index 3b4637bcd254..4c6536f85cac 100644 --- a/lib/kstrtox.h +++ b/lib/kstrtox.h @@ -4,6 +4,8 @@ #define KSTRTOX_OVERFLOW (1U << 31) const char *_parse_integer_fixup_radix(const char *s, unsigned int *base); +unsigned int _parse_integer_limit(const char *s, unsigned int base, + unsigned long long *res, size_t max_chars); unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long *res); #endif diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 14c9a6af1b23..21145da468e0 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -53,29 +53,47 @@ #include <linux/string_helpers.h> #include "kstrtox.h" -/** - * simple_strtoull - convert a string to an unsigned long long - * @cp: The start of the string - * @endp: A pointer to the end of the parsed string will be placed here - * @base: The number base to use - * - * This function has caveats. Please use kstrtoull instead. - */ -unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base) +static unsigned long long simple_strntoull(const char *startp, size_t max_chars, + char **endp, unsigned int base) { - unsigned long long result; + const char *cp; + unsigned long long result = 0ULL; unsigned int rv; - cp = _parse_integer_fixup_radix(cp, &base); - rv = _parse_integer(cp, base, &result); + if (max_chars == 0) { + cp = startp; + goto out; + } + + cp = _parse_integer_fixup_radix(startp, &base); + if ((cp - startp) >= max_chars) { + cp = startp + max_chars; + goto out; + } + + max_chars -= (cp - startp); + rv = _parse_integer_limit(cp, base, &result, max_chars); /* FIXME */ cp += (rv & ~KSTRTOX_OVERFLOW); - +out: if (endp) *endp = (char *)cp; return result; } + +/** + * simple_strtoull - convert a string to an unsigned long long + * @cp: The start of the string + * @endp: A pointer to the end of the parsed string will be placed here + * @base: The number base to use + * + * This function has caveats. Please use kstrtoull instead. + */ +unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base) +{ + return simple_strntoull(cp, UINT_MAX, endp, base); +} EXPORT_SYMBOL(simple_strtoull); /** @@ -88,7 +106,7 @@ EXPORT_SYMBOL(simple_strtoull); */ unsigned long simple_strtoul(const char *cp, char **endp, unsigned int base) { - return simple_strtoull(cp, endp, base); + return simple_strntoull(cp, UINT_MAX, endp, base); } EXPORT_SYMBOL(simple_strtoul); @@ -109,6 +127,19 @@ long simple_strtol(const char *cp, char **endp, unsigned int base) } EXPORT_SYMBOL(simple_strtol); +static long long simple_strntoll(const char *cp, size_t max_chars, char **endp, + unsigned int base) +{ + /* + * simple_strntoull safely handles receiving max_chars==0 in the + * case we start with max_chars==1 and find a '-' prefix. + */ + if (*cp == '-' && max_chars > 0) + return -simple_strntoull(cp + 1, max_chars - 1, endp, base); + + return simple_strntoull(cp, max_chars, endp, base); +} + /** * simple_strtoll - convert a string to a signed long long * @cp: The start of the string @@ -119,10 +150,7 @@ EXPORT_SYMBOL(simple_strtol); */ long long simple_strtoll(const char *cp, char **endp, unsigned int base) { - if (*cp == '-') - return -simple_strtoull(cp + 1, endp, base); - - return simple_strtoull(cp, endp, base); + return simple_strntoll(cp, UINT_MAX, endp, base); } EXPORT_SYMBOL(simple_strtoll); @@ -3433,8 +3461,11 @@ int vsscanf(const char *buf, const char *fmt, va_list args) str = skip_spaces(str); digit = *str; - if (is_sign && digit == '-') + if (is_sign && digit == '-') { + if (field_width == 1) + break; digit = *(str + 1); + } if (!digit || (base == 16 && !isxdigit(digit)) @@ -3444,25 +3475,13 @@ int vsscanf(const char *buf, const char *fmt, va_list args) break; if (is_sign) - val.s = qualifier != 'L' ? - simple_strtol(str, &next, base) : - simple_strtoll(str, &next, base); + val.s = simple_strntoll(str, + field_width > 0 ? field_width : UINT_MAX, + &next, base); else - val.u = qualifier != 'L' ? - simple_strtoul(str, &next, base) : - simple_strtoull(str, &next, base); - - if (field_width > 0 && next - str > field_width) { - if (base == 0) - _parse_integer_fixup_radix(str, &base); - while (next - str > field_width) { - if (is_sign) - val.s = div_s64(val.s, base); - else - val.u = div_u64(val.u, base); - --next; - } - } + val.u = simple_strntoull(str, + field_width > 0 ? field_width : UINT_MAX, + &next, base); switch (qualifier) { case 'H': /* that's 'hh' in format */ -- 2.20.1

4 years

4
10
0 0

Re: [PATCH bpf-next v3 1/5] selftests/bpf: xsk selftests framework

by Weqaar Janjua

On Fri, 27 Nov 2020 at 04:19, Yonghong Song <yhs(a)fb.com> wrote: > > > > On 11/26/20 1:22 PM, Weqaar Janjua wrote: > > On Thu, 26 Nov 2020 at 09:01, Björn Töpel <bjorn.topel(a)intel.com> wrote: > >> > >> On 2020-11-26 07:44, Yonghong Song wrote: > >>> > >> [...] > >>> > >>> What other configures I am missing? > >>> > >>> BTW, I cherry-picked the following pick from bpf tree in this experiment. > >>> commit e7f4a5919bf66e530e08ff352d9b78ed89574e6b (HEAD -> xsk) > >>> Author: Björn Töpel <bjorn.topel(a)intel.com> > >>> Date: Mon Nov 23 18:56:00 2020 +0100 > >>> > >>> net, xsk: Avoid taking multiple skbuff references > >>> > >> > >> Hmm, I'm getting an oops, unless I cherry-pick: > >> > >> 36ccdf85829a ("net, xsk: Avoid taking multiple skbuff references") > >> > >> *AND* > >> > >> 537cf4e3cc2f ("xsk: Fix umem cleanup bug at socket destruct") > >> > >> from bpf/master. > >> > > > > Same as Bjorn's findings ^^^, additionally applying the second patch > > 537cf4e3cc2f [PASS] all tests for me > > > > PREREQUISITES: [ PASS ] > > SKB NOPOLL: [ PASS ] > > SKB POLL: [ PASS ] > > DRV NOPOLL: [ PASS ] > > DRV POLL: [ PASS ] > > SKB SOCKET TEARDOWN: [ PASS ] > > DRV SOCKET TEARDOWN: [ PASS ] > > SKB BIDIRECTIONAL SOCKETS: [ PASS ] > > DRV BIDIRECTIONAL SOCKETS: [ PASS ] > > > > With the first patch alone, as soon as we enter DRV/Native NOPOLL mode > > kernel panics, whereas in your case NOPOLL tests were falling with > > packets being *lost* as per seqnum mismatch. > > > > Can you please test this out with both patches and let us know? > > I applied both the above patches in bpf-next as well as this patch set, > I still see failures. I am attaching my config file. Maybe you can take > a look at what is the issue. > Thanks for the config, can you please confirm the compiler version, and resource limits i.e. stack size, memory, etc.? Only NOPOLL tests are failing for you as I see it, do the same tests fail every time? I will need to spend some time debugging this to have a fix. Thanks, /Weqaar > > > >> Can I just run test_xsk.sh at tools/testing/selftests/bpf/ directory? > >> This will be easier than the above for bpf developers. If it does not > >> work, I would like to recommend to make it work. > >> > > yes test_xsk.shis self contained, will update the instructions in there with v4. > > That will be great. Thanks! > > > > > Thanks, > > /Weqaar > >> > >> Björn

4 years

2
3
0 0

[PATCH v2] selftests/clone3: Fix build error

by Xingxing Su

When compiling the selftests with the -std=gnu99 option the build can fail with. Following build error: test_core.c: In function ‘test_cgcore_destroy’: test_core.c:87:2: error: ‘for’ loop initial declarations are only allowed in C99 mode for (int i = 0; i < 10; i++) { ^ test_core.c:87:2: note: use option -std=c99 or -std=gnu99 to compile Add -std=gnu99 to the clone3 selftest Makefile to fix this. Signed-off-by: Xingxing Su <suxingxing(a)loongson.cn> Acked-by: Christian Brauner <christian.brauner(a)ubuntu.com> --- tools/testing/selftests/clone3/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/clone3/Makefile b/tools/testing/selftests/clone3/Makefile index ef7564c..88354a8 100644 --- a/tools/testing/selftests/clone3/Makefile +++ b/tools/testing/selftests/clone3/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -g -I../../../../usr/include/ +CFLAGS += -g -std=gnu99 -I../../../../usr/include/ LDLIBS += -lcap TEST_GEN_PROGS := clone3 clone3_clear_sighand clone3_set_tid \ -- 1.8.3.1

4 years

2
1
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror November 2020