diff options
Diffstat (limited to 'tools')
97 files changed, 3344 insertions, 1023 deletions
diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile index 74bc9a105225..0a6d09a3e91f 100644 --- a/tools/bpf/Makefile +++ b/tools/bpf/Makefile @@ -9,7 +9,8 @@ MAKE = make INSTALL ?= install CFLAGS += -Wall -O2 -CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/include/uapi -I$(srctree)/include +CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi \ + -I$(srctree)/tools/include # This will work when bpf is built in tools env. where srctree # isn't set and when invoked from selftests build, where srctree diff --git a/tools/cgroup/iocost_monitor.py b/tools/cgroup/iocost_monitor.py index 3c21de88af9e..f4699f9b46ba 100644 --- a/tools/cgroup/iocost_monitor.py +++ b/tools/cgroup/iocost_monitor.py @@ -173,7 +173,7 @@ class IocgStat: self.usages = [] self.usage = 0 for i in range(NR_USAGE_SLOTS): - usage = iocg.usages[(usage_idx + i) % NR_USAGE_SLOTS].value_() + usage = iocg.usages[(usage_idx + 1 + i) % NR_USAGE_SLOTS].value_() upct = usage * 100 / HWEIGHT_WHOLE self.usages.append(upct) self.usage = max(self.usage, upct) diff --git a/tools/gpio/gpio-event-mon.c b/tools/gpio/gpio-event-mon.c index 30ed0e06f52a..1a303a81aeef 100644 --- a/tools/gpio/gpio-event-mon.c +++ b/tools/gpio/gpio-event-mon.c @@ -45,7 +45,7 @@ int monitor_device(const char *device_name, if (fd == -1) { ret = -errno; fprintf(stderr, "Failed to open %s\n", chrdev_name); - goto exit_close_error; + goto exit_free_name; } req.lineoffset = line; @@ -117,6 +117,7 @@ int monitor_device(const char *device_name, exit_close_error: if (close(fd) == -1) perror("Failed to close GPIO character device file"); +exit_free_name: free(chrdev_name); return ret; } diff --git a/tools/gpio/gpio-utils.c b/tools/gpio/gpio-utils.c index 06003789e7c7..16a5d9cb9da2 100644 --- a/tools/gpio/gpio-utils.c +++ b/tools/gpio/gpio-utils.c @@ -75,7 +75,7 @@ int gpiotools_request_linehandle(const char *device_name, unsigned int *lines, ret = -errno; fprintf(stderr, "Failed to open %s, %s\n", chrdev_name, strerror(errno)); - goto exit_close_error; + goto exit_free_name; } for (i = 0; i < nlines; i++) @@ -94,9 +94,9 @@ int gpiotools_request_linehandle(const char *device_name, unsigned int *lines, "GPIO_GET_LINEHANDLE_IOCTL", ret, strerror(errno)); } -exit_close_error: if (close(fd) == -1) perror("Failed to close GPIO character device file"); +exit_free_name: free(chrdev_name); return ret < 0 ? ret : req.fd; } diff --git a/tools/gpio/lsgpio.c b/tools/gpio/lsgpio.c index 8a71ad36f83b..b08d7a5e779b 100644 --- a/tools/gpio/lsgpio.c +++ b/tools/gpio/lsgpio.c @@ -94,7 +94,7 @@ int list_device(const char *device_name) if (fd == -1) { ret = -errno; fprintf(stderr, "Failed to open %s\n", chrdev_name); - goto exit_close_error; + goto exit_free_name; } /* Inspect this GPIO chip */ @@ -141,6 +141,7 @@ int list_device(const char *device_name) exit_close_error: if (close(fd) == -1) perror("Failed to close GPIO character device file"); +exit_free_name: free(chrdev_name); return ret; } diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index 6eac24d44e81..2b3f7353e891 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -111,8 +111,6 @@ # define noinline #endif -#define uninitialized_var(x) x = *(&(x)) - #include <linux/types.h> /* diff --git a/tools/include/linux/irqflags.h b/tools/include/linux/irqflags.h index 67e01bbadbfe..501262aee8ff 100644 --- a/tools/include/linux/irqflags.h +++ b/tools/include/linux/irqflags.h @@ -2,9 +2,9 @@ #ifndef _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_ #define _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_ -# define lockdep_hardirq_context(p) 0 +# define lockdep_hardirq_context() 0 # define lockdep_softirq_context(p) 0 -# define lockdep_hardirqs_enabled(p) 0 +# define lockdep_hardirqs_enabled() 0 # define lockdep_softirqs_enabled(p) 0 # define lockdep_hardirq_enter() do { } while (0) # define lockdep_hardirq_exit() do { } while (0) diff --git a/tools/include/uapi/linux/filter.h b/tools/include/uapi/linux/filter.h new file mode 100644 index 000000000000..eaef459e7bd4 --- /dev/null +++ b/tools/include/uapi/linux/filter.h @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Linux Socket Filter Data Structures + */ + +#ifndef __LINUX_FILTER_H__ +#define __LINUX_FILTER_H__ + + +#include <linux/types.h> +#include <linux/bpf_common.h> + +/* + * Current version of the filter code architecture. + */ +#define BPF_MAJOR_VERSION 1 +#define BPF_MINOR_VERSION 1 + +/* + * Try and keep these values and structures similar to BSD, especially + * the BPF code definitions which need to match so you can share filters + */ + +struct sock_filter { /* Filter block */ + __u16 code; /* Actual filter code */ + __u8 jt; /* Jump true */ + __u8 jf; /* Jump false */ + __u32 k; /* Generic multiuse field */ +}; + +struct sock_fprog { /* Required for SO_ATTACH_FILTER. */ + unsigned short len; /* Number of filter blocks */ + struct sock_filter *filter; +}; + +/* ret - BPF_K and BPF_X also apply */ +#define BPF_RVAL(code) ((code) & 0x18) +#define BPF_A 0x10 + +/* misc */ +#define BPF_MISCOP(code) ((code) & 0xf8) +#define BPF_TAX 0x00 +#define BPF_TXA 0x80 + +/* + * Macros for filter block array initializers. + */ +#ifndef BPF_STMT +#define BPF_STMT(code, k) { (unsigned short)(code), 0, 0, k } +#endif +#ifndef BPF_JUMP +#define BPF_JUMP(code, k, jt, jf) { (unsigned short)(code), jt, jf, k } +#endif + +/* + * Number of scratch memory words for: BPF_ST and BPF_STX + */ +#define BPF_MEMWORDS 16 + +/* RATIONALE. Negative offsets are invalid in BPF. + We use them to reference ancillary data. + Unlike introduction new instructions, it does not break + existing compilers/optimizers. + */ +#define SKF_AD_OFF (-0x1000) +#define SKF_AD_PROTOCOL 0 +#define SKF_AD_PKTTYPE 4 +#define SKF_AD_IFINDEX 8 +#define SKF_AD_NLATTR 12 +#define SKF_AD_NLATTR_NEST 16 +#define SKF_AD_MARK 20 +#define SKF_AD_QUEUE 24 +#define SKF_AD_HATYPE 28 +#define SKF_AD_RXHASH 32 +#define SKF_AD_CPU 36 +#define SKF_AD_ALU_XOR_X 40 +#define SKF_AD_VLAN_TAG 44 +#define SKF_AD_VLAN_TAG_PRESENT 48 +#define SKF_AD_PAY_OFFSET 52 +#define SKF_AD_RANDOM 56 +#define SKF_AD_VLAN_TPID 60 +#define SKF_AD_MAX 64 + +#define SKF_NET_OFF (-0x100000) +#define SKF_LL_OFF (-0x200000) + +#define BPF_NET_OFF SKF_NET_OFF +#define BPF_LL_OFF SKF_LL_OFF + +#endif /* __LINUX_FILTER_H__ */ diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 7b2d6fc9e6ed..21a1edd08cbe 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -532,9 +532,10 @@ struct perf_event_mmap_page { cap_bit0_is_deprecated : 1, /* Always 1, signals that bit 0 is zero */ cap_user_rdpmc : 1, /* The RDPMC instruction can be used to read counts */ - cap_user_time : 1, /* The time_* fields are used */ + cap_user_time : 1, /* The time_{shift,mult,offset} fields are used */ cap_user_time_zero : 1, /* The time_zero field is used */ - cap_____res : 59; + cap_user_time_short : 1, /* the time_{cycle,mask} fields are used */ + cap_____res : 58; }; }; @@ -593,13 +594,29 @@ struct perf_event_mmap_page { * ((rem * time_mult) >> time_shift); */ __u64 time_zero; + __u32 size; /* Header size up to __reserved[] fields. */ + __u32 __reserved_1; + + /* + * If cap_usr_time_short, the hardware clock is less than 64bit wide + * and we must compute the 'cyc' value, as used by cap_usr_time, as: + * + * cyc = time_cycles + ((cyc - time_cycles) & time_mask) + * + * NOTE: this form is explicitly chosen such that cap_usr_time_short + * is a correction on top of cap_usr_time, and code that doesn't + * know about cap_usr_time_short still works under the assumption + * the counter doesn't wrap. + */ + __u64 time_cycles; + __u64 time_mask; /* * Hole for extension of the self monitor capabilities */ - __u8 __reserved[118*8+4]; /* align to 1k. */ + __u8 __reserved[116*8]; /* align to 1k. */ /* * Control data for the mmap() data buffer. diff --git a/tools/io_uring/liburing.h b/tools/io_uring/liburing.h index 5f305c86b892..28a837b6069d 100644 --- a/tools/io_uring/liburing.h +++ b/tools/io_uring/liburing.h @@ -10,6 +10,7 @@ extern "C" { #include <string.h> #include "../../include/uapi/linux/io_uring.h" #include <inttypes.h> +#include <linux/swab.h> #include "barrier.h" /* @@ -145,11 +146,14 @@ static inline void io_uring_prep_write_fixed(struct io_uring_sqe *sqe, int fd, } static inline void io_uring_prep_poll_add(struct io_uring_sqe *sqe, int fd, - short poll_mask) + unsigned poll_mask) { memset(sqe, 0, sizeof(*sqe)); sqe->opcode = IORING_OP_POLL_ADD; sqe->fd = fd; +#if __BYTE_ORDER == __BIG_ENDIAN + poll_mask = __swahw32(poll_mask); +#endif sqe->poll_events = poll_mask; } diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt index e91a2eb19592..f9d610d5a1a4 100644 --- a/tools/memory-model/Documentation/explanation.txt +++ b/tools/memory-model/Documentation/explanation.txt @@ -1122,12 +1122,10 @@ maintain at least the appearance of FIFO order. In practice, this difficulty is solved by inserting a special fence between P1's two loads when the kernel is compiled for the Alpha architecture. In fact, as of version 4.15, the kernel automatically -adds this fence (called smp_read_barrier_depends() and defined as -nothing at all on non-Alpha builds) after every READ_ONCE() and atomic -load. The effect of the fence is to cause the CPU not to execute any -po-later instructions until after the local cache has finished -processing all the stores it has already received. Thus, if the code -was changed to: +adds this fence after every READ_ONCE() and atomic load on Alpha. The +effect of the fence is to cause the CPU not to execute any po-later +instructions until after the local cache has finished processing all +the stores it has already received. Thus, if the code was changed to: P1() { @@ -1146,14 +1144,14 @@ READ_ONCE() or another synchronization primitive rather than accessed directly. The LKMM requires that smp_rmb(), acquire fences, and strong fences -share this property with smp_read_barrier_depends(): They do not allow -the CPU to execute any po-later instructions (or po-later loads in the -case of smp_rmb()) until all outstanding stores have been processed by -the local cache. In the case of a strong fence, the CPU first has to -wait for all of its po-earlier stores to propagate to every other CPU -in the system; then it has to wait for the local cache to process all -the stores received as of that time -- not just the stores received -when the strong fence began. +share this property: They do not allow the CPU to execute any po-later +instructions (or po-later loads in the case of smp_rmb()) until all +outstanding stores have been processed by the local cache. In the +case of a strong fence, the CPU first has to wait for all of its +po-earlier stores to propagate to every other CPU in the system; then +it has to wait for the local cache to process all the stores received +as of that time -- not just the stores received when the strong fence +began. And of course, none of this matters for any architecture other than Alpha. @@ -1987,28 +1985,36 @@ outcome undefined. In technical terms, the compiler is allowed to assume that when the program executes, there will not be any data races. A "data race" -occurs when two conflicting memory accesses execute concurrently; -two memory accesses "conflict" if: +occurs when there are two memory accesses such that: - they access the same location, +1. they access the same location, - they occur on different CPUs (or in different threads on the - same CPU), +2. at least one of them is a store, - at least one of them is a plain access, +3. at least one of them is plain, - and at least one of them is a store. +4. they occur on different CPUs (or in different threads on the + same CPU), and -The LKMM tries to determine whether a program contains two conflicting -accesses which may execute concurrently; if it does then the LKMM says -there is a potential data race and makes no predictions about the -program's outcome. +5. they execute concurrently. -Determining whether two accesses conflict is easy; you can see that -all the concepts involved in the definition above are already part of -the memory model. The hard part is telling whether they may execute -concurrently. The LKMM takes a conservative attitude, assuming that -accesses may be concurrent unless it can prove they cannot. +In the literature, two accesses are said to "conflict" if they satisfy +1 and 2 above. We'll go a little farther and say that two accesses +are "race candidates" if they satisfy 1 - 4. Thus, whether or not two +race candidates actually do race in a given execution depends on +whether they are concurrent. + +The LKMM tries to determine whether a program contains race candidates +which may execute concurrently; if it does then the LKMM says there is +a potential data race and makes no predictions about the program's +outcome. + +Determining whether two accesses are race candidates is easy; you can +see that all the concepts involved in the definition above are already +part of the memory model. The hard part is telling whether they may +execute concurrently. The LKMM takes a conservative attitude, +assuming that accesses may be concurrent unless it can prove they +are not. If two memory accesses aren't concurrent then one must execute before the other. Therefore the LKMM decides two accesses aren't concurrent @@ -2171,8 +2177,8 @@ again, now using plain accesses for buf: } This program does not contain a data race. Although the U and V -accesses conflict, the LKMM can prove they are not concurrent as -follows: +accesses are race candidates, the LKMM can prove they are not +concurrent as follows: The smp_wmb() fence in P0 is both a compiler barrier and a cumul-fence. It guarantees that no matter what hash of @@ -2326,12 +2332,11 @@ could now perform the load of x before the load of ptr (there might be a control dependency but no address dependency at the machine level). Finally, it turns out there is a situation in which a plain write does -not need to be w-post-bounded: when it is separated from the -conflicting access by a fence. At first glance this may seem -impossible. After all, to be conflicting the second access has to be -on a different CPU from the first, and fences don't link events on -different CPUs. Well, normal fences don't -- but rcu-fence can! -Here's an example: +not need to be w-post-bounded: when it is separated from the other +race-candidate access by a fence. At first glance this may seem +impossible. After all, to be race candidates the two accesses must +be on different CPUs, and fences don't link events on different CPUs. +Well, normal fences don't -- but rcu-fence can! Here's an example: int x, y; @@ -2367,7 +2372,7 @@ concurrent and there is no race, even though P1's plain store to y isn't w-post-bounded by any marked accesses. Putting all this material together yields the following picture. For -two conflicting stores W and W', where W ->co W', the LKMM says the +race-candidate stores W and W', where W ->co W', the LKMM says the stores don't race if W can be linked to W' by a w-post-bounded ; vis ; w-pre-bounded @@ -2380,8 +2385,8 @@ sequence, and if W' is plain then they also have to be linked by a w-post-bounded ; vis ; r-pre-bounded -sequence. For a conflicting load R and store W, the LKMM says the two -accesses don't race if R can be linked to W by an +sequence. For race-candidate load R and store W, the LKMM says the +two accesses don't race if R can be linked to W by an r-post-bounded ; xb* ; w-pre-bounded @@ -2413,20 +2418,20 @@ is, the rules governing the memory subsystem's choice of a store to satisfy a load request and its determination of where a store will fall in the coherence order): - If R and W conflict and it is possible to link R to W by one - of the xb* sequences listed above, then W ->rfe R is not - allowed (i.e., a load cannot read from a store that it + If R and W are race candidates and it is possible to link R to + W by one of the xb* sequences listed above, then W ->rfe R is + not allowed (i.e., a load cannot read from a store that it executes before, even if one or both is plain). - If W and R conflict and it is possible to link W to R by one - of the vis sequences listed above, then R ->fre W is not - allowed (i.e., if a store is visible to a load then the load - must read from that store or one coherence-after it). + If W and R are race candidates and it is possible to link W to + R by one of the vis sequences listed above, then R ->fre W is + not allowed (i.e., if a store is visible to a load then the + load must read from that store or one coherence-after it). - If W and W' conflict and it is possible to link W to W' by one - of the vis sequences listed above, then W' ->co W is not - allowed (i.e., if one store is visible to a second then the - second must come after the first in the coherence order). + If W and W' are race candidates and it is possible to link W + to W' by one of the vis sequences listed above, then W' ->co W + is not allowed (i.e., if one store is visible to a second then + the second must come after the first in the coherence order). This is the extent to which the LKMM deals with plain accesses. Perhaps it could say more (for example, plain accesses might diff --git a/tools/memory-model/Documentation/recipes.txt b/tools/memory-model/Documentation/recipes.txt index 7fe8d7aa3029..63c4adfed884 100644 --- a/tools/memory-model/Documentation/recipes.txt +++ b/tools/memory-model/Documentation/recipes.txt @@ -126,7 +126,7 @@ However, it is not necessarily the case that accesses ordered by locking will be seen as ordered by CPUs not holding that lock. Consider this example: - /* See Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus. */ + /* See Z6.0+pooncelock+pooncelock+pombonce.litmus. */ void CPU0(void) { spin_lock(&mylock); diff --git a/tools/memory-model/Documentation/references.txt b/tools/memory-model/Documentation/references.txt index b177f3e4a614..ecbbaa5396d4 100644 --- a/tools/memory-model/Documentation/references.txt +++ b/tools/memory-model/Documentation/references.txt @@ -73,6 +73,18 @@ o Christopher Pulte, Shaked Flur, Will Deacon, Jon French, Linux-kernel memory model ========================= +o Jade Alglave, Will Deacon, Boqun Feng, David Howells, Daniel + Lustig, Luc Maranget, Paul E. McKenney, Andrea Parri, Nicholas + Piggin, Alan Stern, Akira Yokosawa, and Peter Zijlstra. + 2019. "Calibrating your fear of big bad optimizing compilers" + Linux Weekly News. https://lwn.net/Articles/799218/ + +o Jade Alglave, Will Deacon, Boqun Feng, David Howells, Daniel + Lustig, Luc Maranget, Paul E. McKenney, Andrea Parri, Nicholas + Piggin, Alan Stern, Akira Yokosawa, and Peter Zijlstra. + 2019. "Who's afraid of a big bad optimizing compiler?" + Linux Weekly News. https://lwn.net/Articles/793253/ + o Jade Alglave, Luc Maranget, Paul E. McKenney, Andrea Parri, and Alan Stern. 2018. "Frightening small children and disconcerting grown-ups: Concurrency in the Linux kernel". In Proceedings of @@ -88,6 +100,11 @@ o Jade Alglave, Luc Maranget, Paul E. McKenney, Andrea Parri, and Alan Stern. 2017. "A formal kernel memory-ordering model (part 2)" Linux Weekly News. https://lwn.net/Articles/720550/ +o Jade Alglave, Luc Maranget, Paul E. McKenney, Andrea Parri, and + Alan Stern. 2017-2019. "A Formal Model of Linux-Kernel Memory + Ordering" (backup material for the LWN articles) + https://mirrors.edge.kernel.org/pub/linux/kernel/people/paulmck/LWNLinuxMM/ + Memory-model tooling ==================== @@ -110,5 +127,5 @@ Memory-model comparisons ======================== o Paul E. McKenney, Ulrich Weigand, Andrea Parri, and Boqun - Feng. 2016. "Linux-Kernel Memory Model". (6 June 2016). - http://open-std.org/JTC1/SC22/WG21/docs/papers/2016/p0124r2.html. + Feng. 2018. "Linux-Kernel Memory Model". (27 September 2018). + http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2018/p0124r6.html. diff --git a/tools/memory-model/README b/tools/memory-model/README index fc07b52f2028..ecb7385376bf 100644 --- a/tools/memory-model/README +++ b/tools/memory-model/README @@ -28,8 +28,34 @@ downloaded separately: See "herdtools7/INSTALL.md" for installation instructions. Note that although these tools usually provide backwards compatibility, -this is not absolutely guaranteed. Therefore, if a later version does -not work, please try using the exact version called out above. +this is not absolutely guaranteed. + +For example, a future version of herd7 might not work with the model +in this release. A compatible model will likely be made available in +a later release of Linux kernel. + +If you absolutely need to run the model in this particular release, +please try using the exact version called out above. + +klitmus7 is independent of the model provided here. It has its own +dependency on a target kernel release where converted code is built +and executed. Any change in kernel APIs essential to klitmus7 will +necessitate an upgrade of klitmus7. + +If you find any compatibility issues in klitmus7, please inform the +memory model maintainers. + +klitmus7 Compatibility Table +---------------------------- + + ============ ========== + target Linux herdtools7 + ------------ ---------- + -- 4.18 7.48 -- + 4.15 -- 4.19 7.49 -- + 4.20 -- 5.5 7.54 -- + 5.6 -- 7.56 -- + ============ ========== ================== @@ -207,11 +233,15 @@ The Linux-kernel memory model (LKMM) has the following limitations: case as a store release. b. The "unless" RMW operations are not currently modeled: - atomic_long_add_unless(), atomic_add_unless(), - atomic_inc_unless_negative(), and - atomic_dec_unless_positive(). These can be emulated + atomic_long_add_unless(), atomic_inc_unless_negative(), + and atomic_dec_unless_positive(). These can be emulated in litmus tests, for example, by using atomic_cmpxchg(). + One exception of this limitation is atomic_add_unless(), + which is provided directly by herd7 (so no corresponding + definition in linux-kernel.def). atomic_add_unless() is + modeled by herd7 therefore it can be used in litmus tests. + c. The call_rcu() function is not modeled. It can be emulated in litmus tests by adding another process that invokes synchronize_rcu() and the body of the callback diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h index 3c5967748abb..2e2ce089b0e9 100644 --- a/tools/objtool/arch.h +++ b/tools/objtool/arch.h @@ -82,7 +82,7 @@ bool arch_callee_saved_reg(unsigned char reg); unsigned long arch_jump_destination(struct instruction *insn); -unsigned long arch_dest_rela_offset(int addend); +unsigned long arch_dest_reloc_offset(int addend); const char *arch_nop_insn(int len); diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 9872195f998b..1967370440b3 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -67,7 +67,7 @@ bool arch_callee_saved_reg(unsigned char reg) } } -unsigned long arch_dest_rela_offset(int addend) +unsigned long arch_dest_reloc_offset(int addend) { return addend + 4; } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 5e0d70a89fb8..e034a8f24f46 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -353,7 +353,7 @@ static struct instruction *find_last_insn(struct objtool_file *file, static int add_dead_ends(struct objtool_file *file) { struct section *sec; - struct rela *rela; + struct reloc *reloc; struct instruction *insn; /* @@ -371,24 +371,24 @@ static int add_dead_ends(struct objtool_file *file) if (!sec) goto reachable; - list_for_each_entry(rela, &sec->rela_list, list) { - if (rela->sym->type != STT_SECTION) { + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", sec->name); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (insn) insn = list_prev_entry(insn, list); - else if (rela->addend == rela->sym->sec->len) { - insn = find_last_insn(file, rela->sym->sec); + else if (reloc->addend == reloc->sym->sec->len) { + insn = find_last_insn(file, reloc->sym->sec); if (!insn) { WARN("can't find unreachable insn at %s+0x%x", - rela->sym->sec->name, rela->addend); + reloc->sym->sec->name, reloc->addend); return -1; } } else { WARN("can't find unreachable insn at %s+0x%x", - rela->sym->sec->name, rela->addend); + reloc->sym->sec->name, reloc->addend); return -1; } @@ -406,24 +406,24 @@ reachable: if (!sec) return 0; - list_for_each_entry(rela, &sec->rela_list, list) { - if (rela->sym->type != STT_SECTION) { + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", sec->name); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (insn) insn = list_prev_entry(insn, list); - else if (rela->addend == rela->sym->sec->len) { - insn = find_last_insn(file, rela->sym->sec); + else if (reloc->addend == reloc->sym->sec->len) { + insn = find_last_insn(file, reloc->sym->sec); if (!insn) { WARN("can't find reachable insn at %s+0x%x", - rela->sym->sec->name, rela->addend); + reloc->sym->sec->name, reloc->addend); return -1; } } else { WARN("can't find reachable insn at %s+0x%x", - rela->sym->sec->name, rela->addend); + reloc->sym->sec->name, reloc->addend); return -1; } @@ -441,26 +441,26 @@ static void add_ignores(struct objtool_file *file) struct instruction *insn; struct section *sec; struct symbol *func; - struct rela *rela; + struct reloc *reloc; sec = find_section_by_name(file->elf, ".rela.discard.func_stack_frame_non_standard"); if (!sec) return; - list_for_each_entry(rela, &sec->rela_list, list) { - switch (rela->sym->type) { + list_for_each_entry(reloc, &sec->reloc_list, list) { + switch (reloc->sym->type) { case STT_FUNC: - func = rela->sym; + func = reloc->sym; break; case STT_SECTION: - func = find_func_by_offset(rela->sym->sec, rela->addend); + func = find_func_by_offset(reloc->sym->sec, reloc->addend); if (!func) continue; break; default: - WARN("unexpected relocation symbol type in %s: %d", sec->name, rela->sym->type); + WARN("unexpected relocation symbol type in %s: %d", sec->name, reloc->sym->type); continue; } @@ -580,20 +580,20 @@ static void add_uaccess_safe(struct objtool_file *file) static int add_ignore_alternatives(struct objtool_file *file) { struct section *sec; - struct rela *rela; + struct reloc *reloc; struct instruction *insn; sec = find_section_by_name(file->elf, ".rela.discard.ignore_alts"); if (!sec) return 0; - list_for_each_entry(rela, &sec->rela_list, list) { - if (rela->sym->type != STT_SECTION) { + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", sec->name); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (!insn) { WARN("bad .discard.ignore_alts entry"); return -1; @@ -611,7 +611,7 @@ static int add_ignore_alternatives(struct objtool_file *file) static int add_jump_destinations(struct objtool_file *file) { struct instruction *insn; - struct rela *rela; + struct reloc *reloc; struct section *dest_sec; unsigned long dest_off; @@ -622,19 +622,19 @@ static int add_jump_destinations(struct objtool_file *file) if (insn->ignore || insn->offset == FAKE_JUMP_OFFSET) continue; - rela = find_rela_by_dest_range(file->elf, insn->sec, + reloc = find_reloc_by_dest_range(file->elf, insn->sec, insn->offset, insn->len); - if (!rela) { + if (!reloc) { dest_sec = insn->sec; dest_off = arch_jump_destination(insn); - } else if (rela->sym->type == STT_SECTION) { - dest_sec = rela->sym->sec; - dest_off = arch_dest_rela_offset(rela->addend); - } else if (rela->sym->sec->idx) { - dest_sec = rela->sym->sec; - dest_off = rela->sym->sym.st_value + - arch_dest_rela_offset(rela->addend); - } else if (strstr(rela->sym->name, "_indirect_thunk_")) { + } else if (reloc->sym->type == STT_SECTION) { + dest_sec = reloc->sym->sec; + dest_off = arch_dest_reloc_offset(reloc->addend); + } else if (reloc->sym->sec->idx) { + dest_sec = reloc->sym->sec; + dest_off = reloc->sym->sym.st_value + + arch_dest_reloc_offset(reloc->addend); + } else if (strstr(reloc->sym->name, "_indirect_thunk_")) { /* * Retpoline jumps are really dynamic jumps in * disguise, so convert them accordingly. @@ -648,7 +648,7 @@ static int add_jump_destinations(struct objtool_file *file) continue; } else { /* external sibling call */ - insn->call_dest = rela->sym; + insn->call_dest = reloc->sym; continue; } @@ -724,15 +724,15 @@ static int add_call_destinations(struct objtool_file *file) { struct instruction *insn; unsigned long dest_off; - struct rela *rela; + struct reloc *reloc; for_each_insn(file, insn) { if (insn->type != INSN_CALL) continue; - rela = find_rela_by_dest_range(file->elf, insn->sec, + reloc = find_reloc_by_dest_range(file->elf, insn->sec, insn->offset, insn->len); - if (!rela) { + if (!reloc) { dest_off = arch_jump_destination(insn); insn->call_dest = find_func_by_offset(insn->sec, dest_off); if (!insn->call_dest) @@ -752,19 +752,19 @@ static int add_call_destinations(struct objtool_file *file) return -1; } - } else if (rela->sym->type == STT_SECTION) { - dest_off = arch_dest_rela_offset(rela->addend); - insn->call_dest = find_func_by_offset(rela->sym->sec, + } else if (reloc->sym->type == STT_SECTION) { + dest_off = arch_dest_reloc_offset(reloc->addend); + insn->call_dest = find_func_by_offset(reloc->sym->sec, dest_off); if (!insn->call_dest) { WARN_FUNC("can't find call dest symbol at %s+0x%lx", insn->sec, insn->offset, - rela->sym->sec->name, + reloc->sym->sec->name, dest_off); return -1; } } else - insn->call_dest = rela->sym; + insn->call_dest = reloc->sym; /* * Many compilers cannot disable KCOV with a function attribute @@ -773,9 +773,9 @@ static int add_call_destinations(struct objtool_file *file) */ if (insn->sec->noinstr && !strncmp(insn->call_dest->name, "__sanitizer_cov_", 16)) { - if (rela) { - rela->type = R_NONE; - elf_write_rela(file->elf, rela); + if (reloc) { + reloc->type = R_NONE; + elf_write_reloc(file->elf, reloc); } elf_write_insn(file->elf, insn->sec, @@ -890,7 +890,7 @@ static int handle_group_alt(struct objtool_file *file, */ if ((insn->offset != special_alt->new_off || (insn->type != INSN_CALL && !is_static_jump(insn))) && - find_rela_by_dest_range(file->elf, insn->sec, insn->offset, insn->len)) { + find_reloc_by_dest_range(file->elf, insn->sec, insn->offset, insn->len)) { WARN_FUNC("unsupported relocation in alternatives section", insn->sec, insn->offset); @@ -1036,34 +1036,34 @@ out: } static int add_jump_table(struct objtool_file *file, struct instruction *insn, - struct rela *table) + struct reloc *table) { - struct rela *rela = table; + struct reloc *reloc = table; struct instruction *dest_insn; struct alternative *alt; struct symbol *pfunc = insn->func->pfunc; unsigned int prev_offset = 0; /* - * Each @rela is a switch table relocation which points to the target + * Each @reloc is a switch table relocation which points to the target * instruction. */ - list_for_each_entry_from(rela, &table->sec->rela_list, list) { + list_for_each_entry_from(reloc, &table->sec->reloc_list, list) { /* Check for the end of the table: */ - if (rela != table && rela->jump_table_start) + if (reloc != table && reloc->jump_table_start) break; /* Make sure the table entries are consecutive: */ - if (prev_offset && rela->offset != prev_offset + 8) + if (prev_offset && reloc->offset != prev_offset + 8) break; /* Detect function pointers from contiguous objects: */ - if (rela->sym->sec == pfunc->sec && - rela->addend == pfunc->offset) + if (reloc->sym->sec == pfunc->sec && + reloc->addend == pfunc->offset) break; - dest_insn = find_insn(file, rela->sym->sec, rela->addend); + dest_insn = find_insn(file, reloc->sym->sec, reloc->addend); if (!dest_insn) break; @@ -1079,7 +1079,7 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn, alt->insn = dest_insn; list_add_tail(&alt->list, &insn->alts); - prev_offset = rela->offset; + prev_offset = reloc->offset; } if (!prev_offset) { @@ -1134,11 +1134,11 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn, * * NOTE: RETPOLINE made it harder still to decode dynamic jumps. */ -static struct rela *find_jump_table(struct objtool_file *file, +static struct reloc *find_jump_table(struct objtool_file *file, struct symbol *func, struct instruction *insn) { - struct rela *text_rela, *table_rela; + struct reloc *text_reloc, *table_reloc; struct instruction *dest_insn, *orig_insn = insn; struct section *table_sec; unsigned long table_offset; @@ -1163,16 +1163,16 @@ static struct rela *find_jump_table(struct objtool_file *file, break; /* look for a relocation which references .rodata */ - text_rela = find_rela_by_dest_range(file->elf, insn->sec, + text_reloc = find_reloc_by_dest_range(file->elf, insn->sec, insn->offset, insn->len); - if (!text_rela || text_rela->sym->type != STT_SECTION || - !text_rela->sym->sec->rodata) + if (!text_reloc || text_reloc->sym->type != STT_SECTION || + !text_reloc->sym->sec->rodata) continue; - table_offset = text_rela->addend; - table_sec = text_rela->sym->sec; + table_offset = text_reloc->addend; + table_sec = text_reloc->sym->sec; - if (text_rela->type == R_X86_64_PC32) + if (text_reloc->type == R_X86_64_PC32) table_offset += 4; /* @@ -1189,14 +1189,14 @@ static struct rela *find_jump_table(struct objtool_file *file, continue; /* - * Each table entry has a rela associated with it. The rela + * Each table entry has a reloc associated with it. The reloc * should reference text in the same function as the original * instruction. */ - table_rela = find_rela_by_dest(file->elf, table_sec, table_offset); - if (!table_rela) + table_reloc = find_reloc_by_dest(file->elf, table_sec, table_offset); + if (!table_reloc) continue; - dest_insn = find_insn(file, table_rela->sym->sec, table_rela->addend); + dest_insn = find_insn(file, table_reloc->sym->sec, table_reloc->addend); if (!dest_insn || !dest_insn->func || dest_insn->func->pfunc != func) continue; @@ -1205,10 +1205,10 @@ static struct rela *find_jump_table(struct objtool_file *file, * indicates a rare GCC quirk/bug which can leave dead code * behind. */ - if (text_rela->type == R_X86_64_PC32) + if (text_reloc->type == R_X86_64_PC32) file->ignore_unreachables = true; - return table_rela; + return table_reloc; } return NULL; @@ -1222,7 +1222,7 @@ static void mark_func_jump_tables(struct objtool_file *file, struct symbol *func) { struct instruction *insn, *last = NULL; - struct rela *rela; + struct reloc *reloc; func_for_each_insn(file, func, insn) { if (!last) @@ -1245,10 +1245,10 @@ static void mark_func_jump_tables(struct objtool_file *file, if (insn->type != INSN_JUMP_DYNAMIC) continue; - rela = find_jump_table(file, func, insn); - if (rela) { - rela->jump_table_start = true; - insn->jump_table = rela; + reloc = find_jump_table(file, func, insn); + if (reloc) { + reloc->jump_table_start = true; + insn->jump_table = reloc; } } } @@ -1302,8 +1302,8 @@ static int add_jump_table_alts(struct objtool_file *file) static int read_unwind_hints(struct objtool_file *file) { - struct section *sec, *relasec; - struct rela *rela; + struct section *sec, *relocsec; + struct reloc *reloc; struct unwind_hint *hint; struct instruction *insn; struct cfi_reg *cfa; @@ -1313,8 +1313,8 @@ static int read_unwind_hints(struct objtool_file *file) if (!sec) return 0; - relasec = sec->rela; - if (!relasec) { + relocsec = sec->reloc; + if (!relocsec) { WARN("missing .rela.discard.unwind_hints section"); return -1; } @@ -1329,13 +1329,13 @@ static int read_unwind_hints(struct objtool_file *file) for (i = 0; i < sec->len / sizeof(struct unwind_hint); i++) { hint = (struct unwind_hint *)sec->data->d_buf + i; - rela = find_rela_by_dest(file->elf, sec, i * sizeof(*hint)); - if (!rela) { - WARN("can't find rela for unwind_hints[%d]", i); + reloc = find_reloc_by_dest(file->elf, sec, i * sizeof(*hint)); + if (!reloc) { + WARN("can't find reloc for unwind_hints[%d]", i); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (!insn) { WARN("can't find insn for unwind_hints[%d]", i); return -1; @@ -1393,19 +1393,19 @@ static int read_retpoline_hints(struct objtool_file *file) { struct section *sec; struct instruction *insn; - struct rela *rela; + struct reloc *reloc; sec = find_section_by_name(file->elf, ".rela.discard.retpoline_safe"); if (!sec) return 0; - list_for_each_entry(rela, &sec->rela_list, list) { - if (rela->sym->type != STT_SECTION) { + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", sec->name); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (!insn) { WARN("bad .discard.retpoline_safe entry"); return -1; @@ -1428,19 +1428,19 @@ static int read_instr_hints(struct objtool_file *file) { struct section *sec; struct instruction *insn; - struct rela *rela; + struct reloc *reloc; sec = find_section_by_name(file->elf, ".rela.discard.instr_end"); if (!sec) return 0; - list_for_each_entry(rela, &sec->rela_list, list) { - if (rela->sym->type != STT_SECTION) { + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", sec->name); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (!insn) { WARN("bad .discard.instr_end entry"); return -1; @@ -1453,13 +1453,13 @@ static int read_instr_hints(struct objtool_file *file) if (!sec) return 0; - list_for_each_entry(rela, &sec->rela_list, list) { - if (rela->sym->type != STT_SECTION) { + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", sec->name); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (!insn) { WARN("bad .discard.instr_begin entry"); return -1; @@ -1475,22 +1475,22 @@ static int read_intra_function_calls(struct objtool_file *file) { struct instruction *insn; struct section *sec; - struct rela *rela; + struct reloc *reloc; sec = find_section_by_name(file->elf, ".rela.discard.intra_function_calls"); if (!sec) return 0; - list_for_each_entry(rela, &sec->rela_list, list) { + list_for_each_entry(reloc, &sec->reloc_list, list) { unsigned long dest_off; - if (rela->sym->type != STT_SECTION) { + if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", sec->name); return -1; } - insn = find_insn(file, rela->sym->sec, rela->addend); + insn = find_insn(file, reloc->sym->sec, reloc->addend); if (!insn) { WARN("bad .discard.intra_function_call entry"); return -1; diff --git a/tools/objtool/check.h b/tools/objtool/check.h index 906b5210f7ca..061aa96e15d3 100644 --- a/tools/objtool/check.h +++ b/tools/objtool/check.h @@ -37,7 +37,7 @@ struct instruction { struct symbol *call_dest; struct instruction *jump_dest; struct instruction *first_jump_src; - struct rela *jump_table; + struct reloc *jump_table; struct list_head alts; struct symbol *func; struct list_head stack_ops; diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 26d11d821941..3ddbd66f1a37 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -228,26 +228,26 @@ struct symbol *find_symbol_by_name(const struct elf *elf, const char *name) return NULL; } -struct rela *find_rela_by_dest_range(const struct elf *elf, struct section *sec, +struct reloc *find_reloc_by_dest_range(const struct elf *elf, struct section *sec, unsigned long offset, unsigned int len) { - struct rela *rela, *r = NULL; + struct reloc *reloc, *r = NULL; unsigned long o; - if (!sec->rela) + if (!sec->reloc) return NULL; - sec = sec->rela; + sec = sec->reloc; for_offset_range(o, offset, offset + len) { - elf_hash_for_each_possible(elf->rela_hash, rela, hash, + elf_hash_for_each_possible(elf->reloc_hash, reloc, hash, sec_offset_hash(sec, o)) { - if (rela->sec != sec) + if (reloc->sec != sec) continue; - if (rela->offset >= offset && rela->offset < offset + len) { - if (!r || rela->offset < r->offset) - r = rela; + if (reloc->offset >= offset && reloc->offset < offset + len) { + if (!r || reloc->offset < r->offset) + r = reloc; } } if (r) @@ -257,9 +257,9 @@ struct rela *find_rela_by_dest_range(const struct elf *elf, struct section *sec, return NULL; } -struct rela *find_rela_by_dest(const struct elf *elf, struct section *sec, unsigned long offset) +struct reloc *find_reloc_by_dest(const struct elf *elf, struct section *sec, unsigned long offset) { - return find_rela_by_dest_range(elf, sec, offset, 1); + return find_reloc_by_dest_range(elf, sec, offset, 1); } static int read_sections(struct elf *elf) @@ -288,7 +288,7 @@ static int read_sections(struct elf *elf) memset(sec, 0, sizeof(*sec)); INIT_LIST_HEAD(&sec->symbol_list); - INIT_LIST_HEAD(&sec->rela_list); + INIT_LIST_HEAD(&sec->reloc_list); s = elf_getscn(elf->elf, i); if (!s) { @@ -434,7 +434,13 @@ static int read_symbols(struct elf *elf) size_t pnamelen; if (sym->type != STT_FUNC) continue; - sym->pfunc = sym->cfunc = sym; + + if (sym->pfunc == NULL) + sym->pfunc = sym; + + if (sym->cfunc == NULL) + sym->cfunc = sym; + coldstr = strstr(sym->name, ".cold"); if (!coldstr) continue; @@ -482,72 +488,101 @@ err: return -1; } -void elf_add_rela(struct elf *elf, struct rela *rela) +void elf_add_reloc(struct elf *elf, struct reloc *reloc) +{ + struct section *sec = reloc->sec; + + list_add_tail(&reloc->list, &sec->reloc_list); + elf_hash_add(elf->reloc_hash, &reloc->hash, reloc_hash(reloc)); +} + +static int read_rel_reloc(struct section *sec, int i, struct reloc *reloc, unsigned int *symndx) { - struct section *sec = rela->sec; + if (!gelf_getrel(sec->data, i, &reloc->rel)) { + WARN_ELF("gelf_getrel"); + return -1; + } + reloc->type = GELF_R_TYPE(reloc->rel.r_info); + reloc->addend = 0; + reloc->offset = reloc->rel.r_offset; + *symndx = GELF_R_SYM(reloc->rel.r_info); + return 0; +} - list_add_tail(&rela->list, &sec->rela_list); - elf_hash_add(elf->rela_hash, &rela->hash, rela_hash(rela)); +static int read_rela_reloc(struct section *sec, int i, struct reloc *reloc, unsigned int *symndx) +{ + if (!gelf_getrela(sec->data, i, &reloc->rela)) { + WARN_ELF("gelf_getrela"); + return -1; + } + reloc->type = GELF_R_TYPE(reloc->rela.r_info); + reloc->addend = reloc->rela.r_addend; + reloc->offset = reloc->rela.r_offset; + *symndx = GELF_R_SYM(reloc->rela.r_info); + return 0; } -static int read_relas(struct elf *elf) +static int read_relocs(struct elf *elf) { struct section *sec; - struct rela *rela; + struct reloc *reloc; int i; unsigned int symndx; - unsigned long nr_rela, max_rela = 0, tot_rela = 0; + unsigned long nr_reloc, max_reloc = 0, tot_reloc = 0; list_for_each_entry(sec, &elf->sections, list) { - if (sec->sh.sh_type != SHT_RELA) + if ((sec->sh.sh_type != SHT_RELA) && + (sec->sh.sh_type != SHT_REL)) continue; - sec->base = find_section_by_name(elf, sec->name + 5); + sec->base = find_section_by_index(elf, sec->sh.sh_info); if (!sec->base) { - WARN("can't find base section for rela section %s", + WARN("can't find base section for reloc section %s", sec->name); return -1; } - sec->base->rela = sec; + sec->base->reloc = sec; - nr_rela = 0; + nr_reloc = 0; for (i = 0; i < sec->sh.sh_size / sec->sh.sh_entsize; i++) { - rela = malloc(sizeof(*rela)); - if (!rela) { + reloc = malloc(sizeof(*reloc)); + if (!reloc) { perror("malloc"); return -1; } - memset(rela, 0, sizeof(*rela)); - - if (!gelf_getrela(sec->data, i, &rela->rela)) { - WARN_ELF("gelf_getrela"); - return -1; + memset(reloc, 0, sizeof(*reloc)); + switch (sec->sh.sh_type) { + case SHT_REL: + if (read_rel_reloc(sec, i, reloc, &symndx)) + return -1; + break; + case SHT_RELA: + if (read_rela_reloc(sec, i, reloc, &symndx)) + return -1; + break; + default: return -1; } - rela->type = GELF_R_TYPE(rela->rela.r_info); - rela->addend = rela->rela.r_addend; - rela->offset = rela->rela.r_offset; - symndx = GELF_R_SYM(rela->rela.r_info); - rela->sec = sec; - rela->idx = i; - rela->sym = find_symbol_by_index(elf, symndx); - if (!rela->sym) { - WARN("can't find rela entry symbol %d for %s", + reloc->sec = sec; + reloc->idx = i; + reloc->sym = find_symbol_by_index(elf, symndx); + if (!reloc->sym) { + WARN("can't find reloc entry symbol %d for %s", symndx, sec->name); return -1; } - elf_add_rela(elf, rela); - nr_rela++; + elf_add_reloc(elf, reloc); + nr_reloc++; } - max_rela = max(max_rela, nr_rela); - tot_rela += nr_rela; + max_reloc = max(max_reloc, nr_reloc); + tot_reloc += nr_reloc; } if (stats) { - printf("max_rela: %lu\n", max_rela); - printf("tot_rela: %lu\n", tot_rela); + printf("max_reloc: %lu\n", max_reloc); + printf("tot_reloc: %lu\n", tot_reloc); } return 0; @@ -573,7 +608,7 @@ struct elf *elf_open_read(const char *name, int flags) elf_hash_init(elf->symbol_name_hash); elf_hash_init(elf->section_hash); elf_hash_init(elf->section_name_hash); - elf_hash_init(elf->rela_hash); + elf_hash_init(elf->reloc_hash); elf->fd = open(name, flags); if (elf->fd == -1) { @@ -606,7 +641,7 @@ struct elf *elf_open_read(const char *name, int flags) if (read_symbols(elf)) goto err; - if (read_relas(elf)) + if (read_relocs(elf)) goto err; return elf; @@ -632,7 +667,7 @@ struct section *elf_create_section(struct elf *elf, const char *name, memset(sec, 0, sizeof(*sec)); INIT_LIST_HEAD(&sec->symbol_list); - INIT_LIST_HEAD(&sec->rela_list); + INIT_LIST_HEAD(&sec->reloc_list); s = elf_newscn(elf->elf); if (!s) { @@ -719,28 +754,28 @@ struct section *elf_create_section(struct elf *elf, const char *name, return sec; } -struct section *elf_create_rela_section(struct elf *elf, struct section *base) +static struct section *elf_create_rel_reloc_section(struct elf *elf, struct section *base) { - char *relaname; + char *relocname; struct section *sec; - relaname = malloc(strlen(base->name) + strlen(".rela") + 1); - if (!relaname) { + relocname = malloc(strlen(base->name) + strlen(".rel") + 1); + if (!relocname) { perror("malloc"); return NULL; } - strcpy(relaname, ".rela"); - strcat(relaname, base->name); + strcpy(relocname, ".rel"); + strcat(relocname, base->name); - sec = elf_create_section(elf, relaname, sizeof(GElf_Rela), 0); - free(relaname); + sec = elf_create_section(elf, relocname, sizeof(GElf_Rel), 0); + free(relocname); if (!sec) return NULL; - base->rela = sec; + base->reloc = sec; sec->base = base; - sec->sh.sh_type = SHT_RELA; + sec->sh.sh_type = SHT_REL; sec->sh.sh_addralign = 8; sec->sh.sh_link = find_section_by_name(elf, ".symtab")->idx; sec->sh.sh_info = base->idx; @@ -749,42 +784,125 @@ struct section *elf_create_rela_section(struct elf *elf, struct section *base) return sec; } -int elf_rebuild_rela_section(struct elf *elf, struct section *sec) +static struct section *elf_create_rela_reloc_section(struct elf *elf, struct section *base) { - struct rela *rela; - int nr, idx = 0, size; - GElf_Rela *relas; + char *relocname; + struct section *sec; - nr = 0; - list_for_each_entry(rela, &sec->rela_list, list) - nr++; + relocname = malloc(strlen(base->name) + strlen(".rela") + 1); + if (!relocname) { + perror("malloc"); + return NULL; + } + strcpy(relocname, ".rela"); + strcat(relocname, base->name); + + sec = elf_create_section(elf, relocname, sizeof(GElf_Rela), 0); + free(relocname); + if (!sec) + return NULL; - size = nr * sizeof(*relas); - relas = malloc(size); - if (!relas) { + base->reloc = sec; + sec->base = base; + + sec->sh.sh_type = SHT_RELA; + sec->sh.sh_addralign = 8; + sec->sh.sh_link = find_section_by_name(elf, ".symtab")->idx; + sec->sh.sh_info = base->idx; + sec->sh.sh_flags = SHF_INFO_LINK; + + return sec; +} + +struct section *elf_create_reloc_section(struct elf *elf, + struct section *base, + int reltype) +{ + switch (reltype) { + case SHT_REL: return elf_create_rel_reloc_section(elf, base); + case SHT_RELA: return elf_create_rela_reloc_section(elf, base); + default: return NULL; + } +} + +static int elf_rebuild_rel_reloc_section(struct section *sec, int nr) +{ + struct reloc *reloc; + int idx = 0, size; + GElf_Rel *relocs; + + /* Allocate a buffer for relocations */ + size = nr * sizeof(*relocs); + relocs = malloc(size); + if (!relocs) { perror("malloc"); return -1; } - sec->changed = true; - elf->changed = true; + sec->data->d_buf = relocs; + sec->data->d_size = size; + + sec->sh.sh_size = size; + + idx = 0; + list_for_each_entry(reloc, &sec->reloc_list, list) { + relocs[idx].r_offset = reloc->offset; + relocs[idx].r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); + idx++; + } + + return 0; +} + +static int elf_rebuild_rela_reloc_section(struct section *sec, int nr) +{ + struct reloc *reloc; + int idx = 0, size; + GElf_Rela *relocs; + + /* Allocate a buffer for relocations with addends */ + size = nr * sizeof(*relocs); + relocs = malloc(size); + if (!relocs) { + perror("malloc"); + return -1; + } - sec->data->d_buf = relas; + sec->data->d_buf = relocs; sec->data->d_size = size; sec->sh.sh_size = size; idx = 0; - list_for_each_entry(rela, &sec->rela_list, list) { - relas[idx].r_offset = rela->offset; - relas[idx].r_addend = rela->addend; - relas[idx].r_info = GELF_R_INFO(rela->sym->idx, rela->type); + list_for_each_entry(reloc, &sec->reloc_list, list) { + relocs[idx].r_offset = reloc->offset; + relocs[idx].r_addend = reloc->addend; + relocs[idx].r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); idx++; } return 0; } +int elf_rebuild_reloc_section(struct elf *elf, struct section *sec) +{ + struct reloc *reloc; + int nr; + + sec->changed = true; + elf->changed = true; + + nr = 0; + list_for_each_entry(reloc, &sec->reloc_list, list) + nr++; + + switch (sec->sh.sh_type) { + case SHT_REL: return elf_rebuild_rel_reloc_section(sec, nr); + case SHT_RELA: return elf_rebuild_rela_reloc_section(sec, nr); + default: return -1; + } +} + int elf_write_insn(struct elf *elf, struct section *sec, unsigned long offset, unsigned int len, const char *insn) @@ -804,17 +922,27 @@ int elf_write_insn(struct elf *elf, struct section *sec, return 0; } -int elf_write_rela(struct elf *elf, struct rela *rela) +int elf_write_reloc(struct elf *elf, struct reloc *reloc) { - struct section *sec = rela->sec; + struct section *sec = reloc->sec; - rela->rela.r_info = GELF_R_INFO(rela->sym->idx, rela->type); - rela->rela.r_addend = rela->addend; - rela->rela.r_offset = rela->offset; + if (sec->sh.sh_type == SHT_REL) { + reloc->rel.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); + reloc->rel.r_offset = reloc->offset; - if (!gelf_update_rela(sec->data, rela->idx, &rela->rela)) { - WARN_ELF("gelf_update_rela"); - return -1; + if (!gelf_update_rel(sec->data, reloc->idx, &reloc->rel)) { + WARN_ELF("gelf_update_rel"); + return -1; + } + } else { + reloc->rela.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); + reloc->rela.r_addend = reloc->addend; + reloc->rela.r_offset = reloc->offset; + + if (!gelf_update_rela(sec->data, reloc->idx, &reloc->rela)) { + WARN_ELF("gelf_update_rela"); + return -1; + } } elf->changed = true; @@ -862,7 +990,7 @@ void elf_close(struct elf *elf) { struct section *sec, *tmpsec; struct symbol *sym, *tmpsym; - struct rela *rela, *tmprela; + struct reloc *reloc, *tmpreloc; if (elf->elf) elf_end(elf->elf); @@ -876,10 +1004,10 @@ void elf_close(struct elf *elf) hash_del(&sym->hash); free(sym); } - list_for_each_entry_safe(rela, tmprela, &sec->rela_list, list) { - list_del(&rela->list); - hash_del(&rela->hash); - free(rela); + list_for_each_entry_safe(reloc, tmpreloc, &sec->reloc_list, list) { + list_del(&reloc->list); + hash_del(&reloc->hash); + free(reloc); } list_del(&sec->list); free(sec); diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h index 7324e772583e..6cc80a075166 100644 --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -32,8 +32,8 @@ struct section { GElf_Shdr sh; struct rb_root symbol_tree; struct list_head symbol_list; - struct list_head rela_list; - struct section *base, *rela; + struct list_head reloc_list; + struct section *base, *reloc; struct symbol *sym; Elf_Data *data; char *name; @@ -58,10 +58,13 @@ struct symbol { bool uaccess_safe; }; -struct rela { +struct reloc { struct list_head list; struct hlist_node hash; - GElf_Rela rela; + union { + GElf_Rela rela; + GElf_Rel rel; + }; struct section *sec; struct symbol *sym; unsigned long offset; @@ -84,7 +87,7 @@ struct elf { DECLARE_HASHTABLE(symbol_name_hash, ELF_HASH_BITS); DECLARE_HASHTABLE(section_hash, ELF_HASH_BITS); DECLARE_HASHTABLE(section_name_hash, ELF_HASH_BITS); - DECLARE_HASHTABLE(rela_hash, ELF_HASH_BITS); + DECLARE_HASHTABLE(reloc_hash, ELF_HASH_BITS); }; #define OFFSET_STRIDE_BITS 4 @@ -111,19 +114,19 @@ static inline u32 sec_offset_hash(struct section *sec, unsigned long offset) return ol; } -static inline u32 rela_hash(struct rela *rela) +static inline u32 reloc_hash(struct reloc *reloc) { - return sec_offset_hash(rela->sec, rela->offset); + return sec_offset_hash(reloc->sec, reloc->offset); } struct elf *elf_open_read(const char *name, int flags); struct section *elf_create_section(struct elf *elf, const char *name, size_t entsize, int nr); -struct section *elf_create_rela_section(struct elf *elf, struct section *base); -void elf_add_rela(struct elf *elf, struct rela *rela); +struct section *elf_create_reloc_section(struct elf *elf, struct section *base, int reltype); +void elf_add_reloc(struct elf *elf, struct reloc *reloc); int elf_write_insn(struct elf *elf, struct section *sec, unsigned long offset, unsigned int len, const char *insn); -int elf_write_rela(struct elf *elf, struct rela *rela); +int elf_write_reloc(struct elf *elf, struct reloc *reloc); int elf_write(struct elf *elf); void elf_close(struct elf *elf); @@ -132,11 +135,11 @@ struct symbol *find_func_by_offset(struct section *sec, unsigned long offset); struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset); struct symbol *find_symbol_by_name(const struct elf *elf, const char *name); struct symbol *find_symbol_containing(const struct section *sec, unsigned long offset); -struct rela *find_rela_by_dest(const struct elf *elf, struct section *sec, unsigned long offset); -struct rela *find_rela_by_dest_range(const struct elf *elf, struct section *sec, +struct reloc *find_reloc_by_dest(const struct elf *elf, struct section *sec, unsigned long offset); +struct reloc *find_reloc_by_dest_range(const struct elf *elf, struct section *sec, unsigned long offset, unsigned int len); struct symbol *find_func_containing(struct section *sec, unsigned long offset); -int elf_rebuild_rela_section(struct elf *elf, struct section *sec); +int elf_rebuild_reloc_section(struct elf *elf, struct section *sec); #define for_each_sec(file, sec) \ list_for_each_entry(sec, &file->elf->sections, list) diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index 4c37f80eb987..968f55e6dd94 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -80,56 +80,56 @@ int create_orc(struct objtool_file *file) return 0; } -static int create_orc_entry(struct elf *elf, struct section *u_sec, struct section *ip_relasec, +static int create_orc_entry(struct elf *elf, struct section *u_sec, struct section *ip_relocsec, unsigned int idx, struct section *insn_sec, unsigned long insn_off, struct orc_entry *o) { struct orc_entry *orc; - struct rela *rela; + struct reloc *reloc; /* populate ORC data */ orc = (struct orc_entry *)u_sec->data->d_buf + idx; memcpy(orc, o, sizeof(*orc)); - /* populate rela for ip */ - rela = malloc(sizeof(*rela)); - if (!rela) { + /* populate reloc for ip */ + reloc = malloc(sizeof(*reloc)); + if (!reloc) { perror("malloc"); return -1; } - memset(rela, 0, sizeof(*rela)); + memset(reloc, 0, sizeof(*reloc)); if (insn_sec->sym) { - rela->sym = insn_sec->sym; - rela->addend = insn_off; + reloc->sym = insn_sec->sym; + reloc->addend = insn_off; } else { /* * The Clang assembler doesn't produce section symbols, so we * have to reference the function symbol instead: */ - rela->sym = find_symbol_containing(insn_sec, insn_off); - if (!rela->sym) { + reloc->sym = find_symbol_containing(insn_sec, insn_off); + if (!reloc->sym) { /* * Hack alert. This happens when we need to reference * the NOP pad insn immediately after the function. */ - rela->sym = find_symbol_containing(insn_sec, + reloc->sym = find_symbol_containing(insn_sec, insn_off - 1); } - if (!rela->sym) { + if (!reloc->sym) { WARN("missing symbol for insn at offset 0x%lx\n", insn_off); return -1; } - rela->addend = insn_off - rela->sym->offset; + reloc->addend = insn_off - reloc->sym->offset; } - rela->type = R_X86_64_PC32; - rela->offset = idx * sizeof(int); - rela->sec = ip_relasec; + reloc->type = R_X86_64_PC32; + reloc->offset = idx * sizeof(int); + reloc->sec = ip_relocsec; - elf_add_rela(elf, rela); + elf_add_reloc(elf, reloc); return 0; } @@ -137,7 +137,7 @@ static int create_orc_entry(struct elf *elf, struct section *u_sec, struct secti int create_orc_sections(struct objtool_file *file) { struct instruction *insn, *prev_insn; - struct section *sec, *u_sec, *ip_relasec; + struct section *sec, *u_sec, *ip_relocsec; unsigned int idx; struct orc_entry empty = { @@ -181,8 +181,8 @@ int create_orc_sections(struct objtool_file *file) if (!sec) return -1; - ip_relasec = elf_create_rela_section(file->elf, sec); - if (!ip_relasec) + ip_relocsec = elf_create_reloc_section(file->elf, sec, SHT_RELA); + if (!ip_relocsec) return -1; /* create .orc_unwind section */ @@ -200,7 +200,7 @@ int create_orc_sections(struct objtool_file *file) if (!prev_insn || memcmp(&insn->orc, &prev_insn->orc, sizeof(struct orc_entry))) { - if (create_orc_entry(file->elf, u_sec, ip_relasec, idx, + if (create_orc_entry(file->elf, u_sec, ip_relocsec, idx, insn->sec, insn->offset, &insn->orc)) return -1; @@ -212,7 +212,7 @@ int create_orc_sections(struct objtool_file *file) /* section terminator */ if (prev_insn) { - if (create_orc_entry(file->elf, u_sec, ip_relasec, idx, + if (create_orc_entry(file->elf, u_sec, ip_relocsec, idx, prev_insn->sec, prev_insn->offset + prev_insn->len, &empty)) @@ -222,7 +222,7 @@ int create_orc_sections(struct objtool_file *file) } } - if (elf_rebuild_rela_section(file->elf, ip_relasec)) + if (elf_rebuild_reloc_section(file->elf, ip_relocsec)) return -1; return 0; diff --git a/tools/objtool/special.c b/tools/objtool/special.c index e74e0189de22..e893f1e48e44 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -72,7 +72,7 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, struct section *sec, int idx, struct special_alt *alt) { - struct rela *orig_rela, *new_rela; + struct reloc *orig_reloc, *new_reloc; unsigned long offset; offset = idx * entry->size; @@ -118,30 +118,30 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, } } - orig_rela = find_rela_by_dest(elf, sec, offset + entry->orig); - if (!orig_rela) { - WARN_FUNC("can't find orig rela", sec, offset + entry->orig); + orig_reloc = find_reloc_by_dest(elf, sec, offset + entry->orig); + if (!orig_reloc) { + WARN_FUNC("can't find orig reloc", sec, offset + entry->orig); return -1; } - if (orig_rela->sym->type != STT_SECTION) { - WARN_FUNC("don't know how to handle non-section rela symbol %s", - sec, offset + entry->orig, orig_rela->sym->name); + if (orig_reloc->sym->type != STT_SECTION) { + WARN_FUNC("don't know how to handle non-section reloc symbol %s", + sec, offset + entry->orig, orig_reloc->sym->name); return -1; } - alt->orig_sec = orig_rela->sym->sec; - alt->orig_off = orig_rela->addend; + alt->orig_sec = orig_reloc->sym->sec; + alt->orig_off = orig_reloc->addend; if (!entry->group || alt->new_len) { - new_rela = find_rela_by_dest(elf, sec, offset + entry->new); - if (!new_rela) { - WARN_FUNC("can't find new rela", + new_reloc = find_reloc_by_dest(elf, sec, offset + entry->new); + if (!new_reloc) { + WARN_FUNC("can't find new reloc", sec, offset + entry->new); return -1; } - alt->new_sec = new_rela->sym->sec; - alt->new_off = (unsigned int)new_rela->addend; + alt->new_sec = new_reloc->sym->sec; + alt->new_off = (unsigned int)new_reloc->addend; /* _ASM_EXTABLE_EX hack */ if (alt->new_off >= 0x7ffffff0) diff --git a/tools/power/cpupower/lib/cpufreq.c b/tools/power/cpupower/lib/cpufreq.c index 6e04304560ca..c3b56db8b921 100644 --- a/tools/power/cpupower/lib/cpufreq.c +++ b/tools/power/cpupower/lib/cpufreq.c @@ -285,7 +285,7 @@ struct cpufreq_available_governors *cpufreq_get_available_governors(unsigned } else { first = malloc(sizeof(*first)); if (!first) - goto error_out; + return NULL; current = first; } current->first = first; @@ -362,7 +362,7 @@ struct cpufreq_available_frequencies } else { first = malloc(sizeof(*first)); if (!first) - goto error_out; + return NULL; current = first; } current->first = first; @@ -418,7 +418,7 @@ struct cpufreq_available_frequencies } else { first = malloc(sizeof(*first)); if (!first) - goto error_out; + return NULL; current = first; } current->first = first; @@ -493,7 +493,7 @@ static struct cpufreq_affected_cpus *sysfs_get_cpu_list(unsigned int cpu, } else { first = malloc(sizeof(*first)); if (!first) - goto error_out; + return NULL; current = first; } current->first = first; @@ -726,7 +726,7 @@ struct cpufreq_stats *cpufreq_get_stats(unsigned int cpu, } else { first = malloc(sizeof(*first)); if (!first) - goto error_out; + return NULL; current = first; } current->first = first; diff --git a/tools/power/cpupower/man/cpupower-idle-info.1 b/tools/power/cpupower/man/cpupower-idle-info.1 index 80a1311fa747..20b6345c53ad 100644 --- a/tools/power/cpupower/man/cpupower-idle-info.1 +++ b/tools/power/cpupower/man/cpupower-idle-info.1 @@ -75,7 +75,7 @@ By default only values of core zero are displayed. How to display settings of other cores is described in the cpupower(1) manpage in the \-\-cpu option section. .SH REFERENCES -http://www.acpi.info/spec.htm +https://uefi.org/specifications .SH "FILES" .nf \fI/sys/devices/system/cpu/cpu*/cpuidle/state*\fP diff --git a/tools/power/cpupower/man/cpupower-monitor.1 b/tools/power/cpupower/man/cpupower-monitor.1 index 70a56476f4b0..8ee737eefa5c 100644 --- a/tools/power/cpupower/man/cpupower-monitor.1 +++ b/tools/power/cpupower/man/cpupower-monitor.1 @@ -170,7 +170,7 @@ displayed. .SH REFERENCES "BIOS and Kernel Developer’s Guide (BKDG) for AMD Family 14h Processors" -http://support.amd.com/us/Processor_TechDocs/43170.pdf +https://support.amd.com/us/Processor_TechDocs/43170.pdf "Intel® Turbo Boost Technology in Intel® Coreâ„¢ Microarchitecture (Nehalem) Based Processors" @@ -178,7 +178,7 @@ http://download.intel.com/design/processor/applnots/320354.pdf "Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide" -http://www.intel.com/products/processor/manuals +https://www.intel.com/products/processor/manuals .SH FILES .ta diff --git a/tools/power/cpupower/utils/helpers/bitmask.c b/tools/power/cpupower/utils/helpers/bitmask.c index 6c7932f5bd66..649d87cb8b0f 100644 --- a/tools/power/cpupower/utils/helpers/bitmask.c +++ b/tools/power/cpupower/utils/helpers/bitmask.c @@ -26,11 +26,11 @@ struct bitmask *bitmask_alloc(unsigned int n) struct bitmask *bmp; bmp = malloc(sizeof(*bmp)); - if (bmp == 0) + if (!bmp) return 0; bmp->size = n; bmp->maskp = calloc(longsperbits(n), sizeof(unsigned long)); - if (bmp->maskp == 0) { + if (!bmp->maskp) { free(bmp); return 0; } @@ -40,7 +40,7 @@ struct bitmask *bitmask_alloc(unsigned int n) /* Free `struct bitmask` */ void bitmask_free(struct bitmask *bmp) { - if (bmp == 0) + if (!bmp) return; free(bmp->maskp); bmp->maskp = (unsigned long *)0xdeadcdef; /* double free tripwire */ diff --git a/tools/power/pm-graph/README b/tools/power/pm-graph/README index afe6beb40ad9..89d0a7dab4bc 100644 --- a/tools/power/pm-graph/README +++ b/tools/power/pm-graph/README @@ -6,7 +6,7 @@ |_| |___/ |_| pm-graph: suspend/resume/boot timing analysis tools - Version: 5.6 + Version: 5.7 Author: Todd Brandt <todd.e.brandt@intel.com> Home Page: https://01.org/pm-graph diff --git a/tools/power/pm-graph/sleepgraph.py b/tools/power/pm-graph/sleepgraph.py index 602e64b68ba7..46ff97e909c6 100755 --- a/tools/power/pm-graph/sleepgraph.py +++ b/tools/power/pm-graph/sleepgraph.py @@ -81,7 +81,7 @@ def ascii(text): # store system values and test parameters class SystemValues: title = 'SleepGraph' - version = '5.6' + version = '5.7' ansi = False rs = 0 display = '' @@ -198,7 +198,7 @@ class SystemValues: 'suspend_console': {}, 'acpi_pm_prepare': {}, 'syscore_suspend': {}, - 'arch_thaw_secondary_cpus_end': {}, + 'arch_enable_nonboot_cpus_end': {}, 'syscore_resume': {}, 'acpi_pm_finish': {}, 'resume_console': {}, @@ -924,10 +924,7 @@ class SystemValues: tp = TestProps() tf = self.openlog(self.ftracefile, 'r') for line in tf: - # determine the trace data type (required for further parsing) - m = re.match(tp.tracertypefmt, line) - if(m): - tp.setTracerType(m.group('t')) + if tp.stampInfo(line, self): continue # parse only valid lines, if this is not one move on m = re.match(tp.ftrace_line_fmt, line) @@ -1244,8 +1241,8 @@ class DevProps: if self.xtraclass: return ' '+self.xtraclass if self.isasync: - return ' async_device' - return ' sync_device' + return ' (async)' + return ' (sync)' # Class: DeviceNode # Description: @@ -1301,6 +1298,7 @@ class Data: 'FAIL' : r'(?i).*\bFAILED\b.*', 'INVALID' : r'(?i).*\bINVALID\b.*', 'CRASH' : r'(?i).*\bCRASHED\b.*', + 'TIMEOUT' : r'(?i).*\bTIMEOUT\b.*', 'IRQ' : r'.*\bgenirq: .*', 'TASKFAIL': r'.*Freezing of tasks *.*', 'ACPI' : r'.*\bACPI *(?P<b>[A-Za-z]*) *Error[: ].*', @@ -1358,11 +1356,11 @@ class Data: if self.dmesg[p]['order'] == order: return p return '' - def lastPhase(self): + def lastPhase(self, depth=1): plist = self.sortedPhases() - if len(plist) < 1: + if len(plist) < depth: return '' - return plist[-1] + return plist[-1*depth] def turbostatInfo(self): tp = TestProps() out = {'syslpi':'N/A','pkgpc10':'N/A'} @@ -1382,9 +1380,12 @@ class Data: if len(self.dmesgtext) < 1 and sysvals.dmesgfile: lf = sysvals.openlog(sysvals.dmesgfile, 'r') i = 0 + tp = TestProps() list = [] for line in lf: i += 1 + if tp.stampInfo(line, sysvals): + continue m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line) if not m: continue @@ -1400,15 +1401,15 @@ class Data: list.append((msg, err, dir, t, i, i)) self.kerror = True break - msglist = [] + tp.msglist = [] for msg, type, dir, t, idx1, idx2 in list: - msglist.append(msg) + tp.msglist.append(msg) self.errorinfo[dir].append((type, t, idx1, idx2)) if self.kerror: sysvals.dmesglog = True if len(self.dmesgtext) < 1 and sysvals.dmesgfile: lf.close() - return msglist + return tp def setStart(self, time, msg=''): self.start = time if msg: @@ -1623,6 +1624,8 @@ class Data: if('src' in d): for e in d['src']: e.time = self.trimTimeVal(e.time, t0, dT, left) + e.end = self.trimTimeVal(e.end, t0, dT, left) + e.length = e.end - e.time for dir in ['suspend', 'resume']: list = [] for e in self.errorinfo[dir]: @@ -1640,7 +1643,12 @@ class Data: if tL > 0: left = True if tR > tZero else False self.trimTime(tS, tL, left) - self.tLow.append('%.0f'%(tL*1000)) + if 'trying' in self.dmesg[lp] and self.dmesg[lp]['trying'] >= 0.001: + tTry = round(self.dmesg[lp]['trying'] * 1000) + text = '%.0f (-%.0f waking)' % (tL * 1000, tTry) + else: + text = '%.0f' % (tL * 1000) + self.tLow.append(text) lp = phase def getMemTime(self): if not self.hwstart or not self.hwend: @@ -1776,7 +1784,7 @@ class Data: length = -1.0 if(start >= 0 and end >= 0): length = end - start - if pid == -2: + if pid == -2 or name not in sysvals.tracefuncs.keys(): i = 2 origname = name while(name in list): @@ -1789,6 +1797,15 @@ class Data: if color: list[name]['color'] = color return name + def findDevice(self, phase, name): + list = self.dmesg[phase]['list'] + mydev = '' + for devname in sorted(list): + if name == devname or re.match('^%s\[(?P<num>[0-9]*)\]$' % name, devname): + mydev = devname + if mydev: + return list[mydev] + return False def deviceChildren(self, devname, phase): devlist = [] list = self.dmesg[phase]['list'] @@ -2779,6 +2796,7 @@ class TestProps: testerrfmt = '^# enter_sleep_error (?P<e>.*)' sysinfofmt = '^# sysinfo .*' cmdlinefmt = '^# command \| (?P<cmd>.*)' + kparamsfmt = '^# kparams \| (?P<kp>.*)' devpropfmt = '# Device Properties: .*' pinfofmt = '# platform-(?P<val>[a-z,A-Z,0-9]*): (?P<info>.*)' tracertypefmt = '# tracer: (?P<t>.*)' @@ -2790,8 +2808,9 @@ class TestProps: '[ +!#\*@$]*(?P<dur>[0-9\.]*) .*\| (?P<msg>.*)' ftrace_line_fmt_nop = \ ' *(?P<proc>.*)-(?P<pid>[0-9]*) *\[(?P<cpu>[0-9]*)\] *'+\ - '(?P<flags>.{4}) *(?P<time>[0-9\.]*): *'+\ + '(?P<flags>\S*) *(?P<time>[0-9\.]*): *'+\ '(?P<msg>.*)' + machinesuspend = 'machine_suspend\[.*' def __init__(self): self.stamp = '' self.sysinfo = '' @@ -2812,16 +2831,13 @@ class TestProps: self.ftrace_line_fmt = self.ftrace_line_fmt_nop else: doError('Invalid tracer format: [%s]' % tracer) - def stampInfo(self, line): + def stampInfo(self, line, sv): if re.match(self.stampfmt, line): self.stamp = line return True elif re.match(self.sysinfofmt, line): self.sysinfo = line return True - elif re.match(self.cmdlinefmt, line): - self.cmdline = line - return True elif re.match(self.tstatfmt, line): self.turbostat.append(line) return True @@ -2834,6 +2850,20 @@ class TestProps: elif re.match(self.firmwarefmt, line): self.fwdata.append(line) return True + elif(re.match(self.devpropfmt, line)): + self.parseDevprops(line, sv) + return True + elif(re.match(self.pinfofmt, line)): + self.parsePlatformInfo(line, sv) + return True + m = re.match(self.cmdlinefmt, line) + if m: + self.cmdline = m.group('cmd') + return True + m = re.match(self.tracertypefmt, line) + if(m): + self.setTracerType(m.group('t')) + return True return False def parseStamp(self, data, sv): # global test data @@ -2858,9 +2888,13 @@ class TestProps: data.stamp[key] = val sv.hostname = data.stamp['host'] sv.suspendmode = data.stamp['mode'] + if sv.suspendmode == 'freeze': + self.machinesuspend = 'timekeeping_freeze\[.*' + else: + self.machinesuspend = 'machine_suspend\[.*' if sv.suspendmode == 'command' and sv.ftracefile != '': modes = ['on', 'freeze', 'standby', 'mem', 'disk'] - fp = sysvals.openlog(sv.ftracefile, 'r') + fp = sv.openlog(sv.ftracefile, 'r') for line in fp: m = re.match('.* machine_suspend\[(?P<mode>.*)\]', line) if m and m.group('mode') in ['1', '2', '3', '4']: @@ -2868,9 +2902,7 @@ class TestProps: data.stamp['mode'] = sv.suspendmode break fp.close() - m = re.match(self.cmdlinefmt, self.cmdline) - if m: - sv.cmdline = m.group('cmd') + sv.cmdline = self.cmdline if not sv.stamp: sv.stamp = data.stamp # firmware data @@ -3052,20 +3084,7 @@ def appendIncompleteTraceLog(testruns): for line in tf: # remove any latent carriage returns line = line.replace('\r\n', '') - if tp.stampInfo(line): - continue - # determine the trace data type (required for further parsing) - m = re.match(tp.tracertypefmt, line) - if(m): - tp.setTracerType(m.group('t')) - continue - # device properties line - if(re.match(tp.devpropfmt, line)): - tp.parseDevprops(line, sysvals) - continue - # platform info line - if(re.match(tp.pinfofmt, line)): - tp.parsePlatformInfo(line, sysvals) + if tp.stampInfo(line, sysvals): continue # parse only valid lines, if this is not one move on m = re.match(tp.ftrace_line_fmt, line) @@ -3166,33 +3185,19 @@ def parseTraceLog(live=False): if sysvals.usekprobes: tracewatch += ['sync_filesystems', 'freeze_processes', 'syscore_suspend', 'syscore_resume', 'resume_console', 'thaw_processes', 'CPU_ON', - 'CPU_OFF', 'timekeeping_freeze', 'acpi_suspend'] + 'CPU_OFF', 'acpi_suspend'] # extract the callgraph and traceevent data + s2idle_enter = hwsus = False tp = TestProps() - testruns = [] - testdata = [] - testrun = 0 - data, limbo = 0, True + testruns, testdata = [], [] + testrun, data, limbo = 0, 0, True tf = sysvals.openlog(sysvals.ftracefile, 'r') phase = 'suspend_prepare' for line in tf: # remove any latent carriage returns line = line.replace('\r\n', '') - if tp.stampInfo(line): - continue - # tracer type line: determine the trace data type - m = re.match(tp.tracertypefmt, line) - if(m): - tp.setTracerType(m.group('t')) - continue - # device properties line - if(re.match(tp.devpropfmt, line)): - tp.parseDevprops(line, sysvals) - continue - # platform info line - if(re.match(tp.pinfofmt, line)): - tp.parsePlatformInfo(line, sysvals) + if tp.stampInfo(line, sysvals): continue # ignore all other commented lines if line[0] == '#': @@ -3303,16 +3308,29 @@ def parseTraceLog(live=False): phase = data.setPhase('suspend_noirq', t.time, isbegin) continue # suspend_machine/resume_machine - elif(re.match('machine_suspend\[.*', t.name)): + elif(re.match(tp.machinesuspend, t.name)): + lp = data.lastPhase() if(isbegin): - lp = data.lastPhase() + hwsus = True if lp.startswith('resume_machine'): - data.dmesg[lp]['end'] = t.time + # trim out s2idle loops, track time trying to freeze + llp = data.lastPhase(2) + if llp.startswith('suspend_machine'): + if 'trying' not in data.dmesg[llp]: + data.dmesg[llp]['trying'] = 0 + data.dmesg[llp]['trying'] += \ + t.time - data.dmesg[lp]['start'] + data.currphase = '' + del data.dmesg[lp] + continue phase = data.setPhase('suspend_machine', data.dmesg[lp]['end'], True) data.setPhase(phase, t.time, False) if data.tSuspended == 0: data.tSuspended = t.time else: + if lp.startswith('resume_machine'): + data.dmesg[lp]['end'] = t.time + continue phase = data.setPhase('resume_machine', t.time, True) if(sysvals.suspendmode in ['mem', 'disk']): susp = phase.replace('resume', 'suspend') @@ -3343,6 +3361,19 @@ def parseTraceLog(live=False): # global events (outside device calls) are graphed if(name not in testrun.ttemp): testrun.ttemp[name] = [] + # special handling for s2idle_enter + if name == 'machine_suspend': + if hwsus: + s2idle_enter = hwsus = False + elif s2idle_enter and not isbegin: + if(len(testrun.ttemp[name]) > 0): + testrun.ttemp[name][-1]['end'] = t.time + testrun.ttemp[name][-1]['loop'] += 1 + elif not s2idle_enter and isbegin: + s2idle_enter = True + testrun.ttemp[name].append({'begin': t.time, + 'end': t.time, 'pid': pid, 'loop': 0}) + continue if(isbegin): # create a new list entry testrun.ttemp[name].append(\ @@ -3374,9 +3405,8 @@ def parseTraceLog(live=False): if(not m): continue n = m.group('d') - list = data.dmesg[phase]['list'] - if(n in list): - dev = list[n] + dev = data.findDevice(phase, n) + if dev: dev['length'] = t.time - dev['start'] dev['end'] = t.time # kprobe event processing @@ -3479,7 +3509,12 @@ def parseTraceLog(live=False): # add actual trace funcs for name in sorted(test.ttemp): for event in test.ttemp[name]: - data.newActionGlobal(name, event['begin'], event['end'], event['pid']) + if event['end'] - event['begin'] <= 0: + continue + title = name + if name == 'machine_suspend' and 'loop' in event: + title = 's2idle_enter_%dx' % event['loop'] + data.newActionGlobal(title, event['begin'], event['end'], event['pid']) # add the kprobe based virtual tracefuncs as actual devices for key in sorted(tp.ktemp): name, pid = key @@ -3548,8 +3583,9 @@ def parseTraceLog(live=False): for p in sorted(phasedef, key=lambda k:phasedef[k]['order']): if p not in data.dmesg: if not terr: - pprint('TEST%s FAILED: %s failed in %s phase' % (tn, sysvals.suspendmode, lp)) - terr = '%s%s failed in %s phase' % (sysvals.suspendmode, tn, lp) + ph = p if 'machine' in p else lp + terr = '%s%s failed in %s phase' % (sysvals.suspendmode, tn, ph) + pprint('TEST%s FAILED: %s' % (tn, terr)) error.append(terr) if data.tSuspended == 0: data.tSuspended = data.dmesg[lp]['end'] @@ -3611,7 +3647,7 @@ def loadKernelLog(): idx = line.find('[') if idx > 1: line = line[idx:] - if tp.stampInfo(line): + if tp.stampInfo(line, sysvals): continue m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line) if(not m): @@ -3959,18 +3995,20 @@ def addCallgraphs(sv, hf, data): if sv.cgphase and p != sv.cgphase: continue list = data.dmesg[p]['list'] - for devname in data.sortedDevices(p): - if len(sv.cgfilter) > 0 and devname not in sv.cgfilter: + for d in data.sortedDevices(p): + if len(sv.cgfilter) > 0 and d not in sv.cgfilter: continue - dev = list[devname] + dev = list[d] color = 'white' if 'color' in data.dmesg[p]: color = data.dmesg[p]['color'] if 'color' in dev: color = dev['color'] - name = devname - if(devname in sv.devprops): - name = sv.devprops[devname].altName(devname) + name = d if '[' not in d else d.split('[')[0] + if(d in sv.devprops): + name = sv.devprops[d].altName(d) + if 'drv' in dev and dev['drv']: + name += ' {%s}' % dev['drv'] if sv.suspendmode in suspendmodename: name += ' '+p if('ftrace' in dev): @@ -4517,12 +4555,9 @@ def createHTML(testruns, testfail): # draw the devices for this phase phaselist = data.dmesg[b]['list'] for d in sorted(data.tdevlist[b]): - name = d - drv = '' - dev = phaselist[d] - xtraclass = '' - xtrainfo = '' - xtrastyle = '' + dname = d if '[' not in d else d.split('[')[0] + name, dev = dname, phaselist[d] + drv = xtraclass = xtrainfo = xtrastyle = '' if 'htmlclass' in dev: xtraclass = dev['htmlclass'] if 'color' in dev: @@ -4553,7 +4588,7 @@ def createHTML(testruns, testfail): title += b devtl.html += devtl.html_device.format(dev['id'], \ title, left, top, '%.3f'%rowheight, width, \ - d+drv, xtraclass, xtrastyle) + dname+drv, xtraclass, xtrastyle) if('cpuexec' in dev): for t in sorted(dev['cpuexec']): start, end = t @@ -4571,6 +4606,8 @@ def createHTML(testruns, testfail): continue # draw any trace events for this device for e in dev['src']: + if e.length == 0: + continue height = '%.3f' % devtl.rowH top = '%.3f' % (rowtop + devtl.scaleH + (e.row*devtl.rowH)) left = '%f' % (((e.time-m0)*100)/mTotal) @@ -5876,7 +5913,7 @@ def getArgFloat(name, args, min, max, main=True): def processData(live=False, quiet=False): if not quiet: - pprint('PROCESSING DATA') + pprint('PROCESSING: %s' % sysvals.htmlfile) sysvals.vprint('usetraceevents=%s, usetracemarkers=%s, usekprobes=%s' % \ (sysvals.usetraceevents, sysvals.usetracemarkers, sysvals.usekprobes)) error = '' @@ -5928,7 +5965,7 @@ def processData(live=False, quiet=False): sysvals.vprint('Creating the html timeline (%s)...' % sysvals.htmlfile) createHTML(testruns, error) if not quiet: - pprint('DONE') + pprint('DONE: %s' % sysvals.htmlfile) data = testruns[0] stamp = data.stamp stamp['suspend'], stamp['resume'] = data.getTimeValues() @@ -5984,25 +6021,27 @@ def runTest(n=0, quiet=False): return 0 def find_in_html(html, start, end, firstonly=True): - n, cnt, out = 0, len(html), [] - while n < cnt: - e = cnt if (n + 10000 > cnt or n == 0) else n + 10000 - m = re.search(start, html[n:e]) - if not m: - break - i = m.end() - m = re.search(end, html[n+i:e]) + cnt, out, list = len(html), [], [] + if firstonly: + m = re.search(start, html) + if m: + list.append(m) + else: + list = re.finditer(start, html) + for match in list: + s = match.end() + e = cnt if (len(out) < 1 or s + 10000 > cnt) else s + 10000 + m = re.search(end, html[s:e]) if not m: break - j = m.start() - str = html[n+i:n+i+j] + e = s + m.start() + str = html[s:e] if end == 'ms': num = re.search(r'[-+]?\d*\.\d+|\d+', str) str = num.group() if num else 'NaN' if firstonly: return str out.append(str) - n += i+j if firstonly: return '' return out @@ -6034,7 +6073,7 @@ def data_from_html(file, outpath, issues, fulldetail=False): else: result = 'pass' # extract error info - ilist = [] + tp, ilist = False, [] extra = dict() log = find_in_html(html, '<div id="dmesglog" style="display:none;">', '</div>').strip() @@ -6042,8 +6081,8 @@ def data_from_html(file, outpath, issues, fulldetail=False): d = Data(0) d.end = 999999999 d.dmesgtext = log.split('\n') - msglist = d.extractErrorInfo() - for msg in msglist: + tp = d.extractErrorInfo() + for msg in tp.msglist: sysvals.errorSummary(issues, msg) if stmp[2] == 'freeze': extra = d.turbostatInfo() @@ -6059,8 +6098,8 @@ def data_from_html(file, outpath, issues, fulldetail=False): if wifi: extra['wifi'] = wifi low = find_in_html(html, 'freeze time: <b>', ' ms</b>') - if low and '|' in low: - issue = 'FREEZEx%d' % len(low.split('|')) + if low and 'waking' in low: + issue = 'FREEZEWAKE' match = [i for i in issues if i['match'] == issue] if len(match) > 0: match[0]['count'] += 1 @@ -6126,6 +6165,11 @@ def data_from_html(file, outpath, issues, fulldetail=False): data[key] = extra[key] if fulldetail: data['funclist'] = find_in_html(html, '<div title="', '" class="traceevent"', False) + if tp: + for arg in ['-multi ', '-info ']: + if arg in tp.cmdline: + data['target'] = tp.cmdline[tp.cmdline.find(arg):].split()[1] + break return data def genHtml(subdir, force=False): @@ -6155,8 +6199,7 @@ def runSummary(subdir, local=True, genhtml=False): pprint('Generating a summary of folder:\n %s' % inpath) if genhtml: genHtml(subdir) - issues = [] - testruns = [] + target, issues, testruns = '', [], [] desc = {'host':[],'mode':[],'kernel':[]} for dirname, dirnames, filenames in os.walk(subdir): for filename in filenames: @@ -6165,6 +6208,8 @@ def runSummary(subdir, local=True, genhtml=False): data = data_from_html(os.path.join(dirname, filename), outpath, issues) if(not data): continue + if 'target' in data: + target = data['target'] testruns.append(data) for key in desc: if data[key] not in desc[key]: @@ -6172,6 +6217,8 @@ def runSummary(subdir, local=True, genhtml=False): pprint('Summary files:') if len(desc['host']) == len(desc['mode']) == len(desc['kernel']) == 1: title = '%s %s %s' % (desc['host'][0], desc['kernel'][0], desc['mode'][0]) + if target: + title += ' %s' % target else: title = inpath createHTMLSummarySimple(testruns, os.path.join(outpath, 'summary.html'), title) diff --git a/tools/power/x86/intel-speed-select/isst-config.c b/tools/power/x86/intel-speed-select/isst-config.c index 9f68f51ca652..9f4b190f1d74 100644 --- a/tools/power/x86/intel-speed-select/isst-config.c +++ b/tools/power/x86/intel-speed-select/isst-config.c @@ -15,7 +15,7 @@ struct process_cmd_struct { int arg; }; -static const char *version_str = "v1.4"; +static const char *version_str = "v1.5"; static const int supported_api_ver = 1; static struct isst_if_platform_info isst_platform_info; static char *progname; @@ -44,6 +44,9 @@ static int force_online_offline; static int auto_mode; static int fact_enable_fail; +static int mbox_delay; +static int mbox_retries = 3; + /* clos related */ static int current_clos = -1; static int clos_epp = -1; @@ -198,7 +201,7 @@ int out_format_is_json(void) static int get_stored_topology_info(int cpu, int *core_id, int *pkg_id, int *die_id) { - const char *pathname = "/tmp/isst_cpu_topology.dat"; + const char *pathname = "/var/run/isst_cpu_topology.dat"; struct cpu_topology cpu_top; FILE *fp; int ret; @@ -230,7 +233,7 @@ err_ret: static void store_cpu_topology(void) { - const char *pathname = "/tmp/isst_cpu_topology.dat"; + const char *pathname = "/var/run/isst_cpu_topology.dat"; FILE *fp; int i; @@ -247,6 +250,8 @@ static void store_cpu_topology(void) return; } + fprintf(stderr, "Caching topology information\n"); + for (i = 0; i < topo_max_cpus; ++i) { struct cpu_topology cpu_top; @@ -734,7 +739,7 @@ int isst_send_mbox_command(unsigned int cpu, unsigned char command, unsigned int req_data, unsigned int *resp) { const char *pathname = "/dev/isst_interface"; - int fd; + int fd, retry; struct isst_if_mbox_cmds mbox_cmds = { 0 }; debug_printf( @@ -786,29 +791,42 @@ int isst_send_mbox_command(unsigned int cpu, unsigned char command, mbox_cmds.mbox_cmd[0].parameter = parameter; mbox_cmds.mbox_cmd[0].req_data = req_data; + if (mbox_delay) + usleep(mbox_delay * 1000); + fd = open(pathname, O_RDWR); if (fd < 0) err(-1, "%s open failed", pathname); - if (ioctl(fd, ISST_IF_MBOX_COMMAND, &mbox_cmds) == -1) { - if (errno == ENOTTY) { - perror("ISST_IF_MBOX_COMMAND\n"); - fprintf(stderr, "Check presence of kernel modules: isst_if_mbox_pci or isst_if_mbox_msr\n"); - exit(0); + retry = mbox_retries; + + do { + if (ioctl(fd, ISST_IF_MBOX_COMMAND, &mbox_cmds) == -1) { + if (errno == ENOTTY) { + perror("ISST_IF_MBOX_COMMAND\n"); + fprintf(stderr, "Check presence of kernel modules: isst_if_mbox_pci or isst_if_mbox_msr\n"); + exit(0); + } + debug_printf( + "Error: mbox_cmd cpu:%d command:%x sub_command:%x parameter:%x req_data:%x errorno:%d\n", + cpu, command, sub_command, parameter, req_data, errno); + --retry; + } else { + *resp = mbox_cmds.mbox_cmd[0].resp_data; + debug_printf( + "mbox_cmd response: cpu:%d command:%x sub_command:%x parameter:%x req_data:%x resp:%x\n", + cpu, command, sub_command, parameter, req_data, *resp); + break; } - debug_printf( - "Error: mbox_cmd cpu:%d command:%x sub_command:%x parameter:%x req_data:%x errorno:%d\n", - cpu, command, sub_command, parameter, req_data, errno); - return -1; - } else { - *resp = mbox_cmds.mbox_cmd[0].resp_data; - debug_printf( - "mbox_cmd response: cpu:%d command:%x sub_command:%x parameter:%x req_data:%x resp:%x\n", - cpu, command, sub_command, parameter, req_data, *resp); - } + } while (retry); close(fd); + if (!retry) { + debug_printf("Failed mbox command even after retries\n"); + return -1; + + } return 0; } @@ -1245,7 +1263,11 @@ static void set_tdp_level_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, fprintf(stderr, "Option is set to online/offline\n"); ctdp_level.core_cpumask_size = alloc_cpu_set(&ctdp_level.core_cpumask); - isst_get_coremask_info(cpu, tdp_level, &ctdp_level); + ret = isst_get_coremask_info(cpu, tdp_level, &ctdp_level); + if (ret) { + isst_display_error_info_message(1, "Can't get coremask, online/offline option is ignored", 0, 0); + return; + } if (ctdp_level.cpu_count) { int i, max_cpus = get_topo_max_cpus(); for (i = 0; i < max_cpus; ++i) { @@ -2593,6 +2615,8 @@ static void usage(void) printf("\t[-i|--info] : Print platform information\n"); printf("\t[-o|--out] : Output file\n"); printf("\t\t\tDefault : stderr\n"); + printf("\t[-p|--pause] : Delay between two mail box commands in milliseconds\n"); + printf("\t[-r|--retry] : Retry count for mail box commands on failure, default 3\n"); printf("\t[-v|--version] : Print version\n"); printf("\nResult format\n"); @@ -2624,6 +2648,7 @@ static void print_version(void) static void cmdline(int argc, char **argv) { const char *pathname = "/dev/isst_interface"; + char *ptr; FILE *fp; int opt; int option_index = 0; @@ -2635,7 +2660,9 @@ static void cmdline(int argc, char **argv) { "format", required_argument, 0, 'f' }, { "help", no_argument, 0, 'h' }, { "info", no_argument, 0, 'i' }, + { "pause", required_argument, 0, 'p' }, { "out", required_argument, 0, 'o' }, + { "retry", required_argument, 0, 'r' }, { "version", no_argument, 0, 'v' }, { 0, 0, 0, 0 } }; @@ -2688,6 +2715,20 @@ static void cmdline(int argc, char **argv) fclose(outf); outf = fopen_or_exit(optarg, "w"); break; + case 'p': + ret = strtol(optarg, &ptr, 10); + if (!ret) + fprintf(stderr, "Invalid pause interval, ignore\n"); + else + mbox_delay = ret; + break; + case 'r': + ret = strtol(optarg, &ptr, 10); + if (!ret) + fprintf(stderr, "Invalid retry count, ignore\n"); + else + mbox_retries = ret; + break; case 'v': print_version(); break; diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index f9b769f3437d..425ef40067e7 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -240,12 +240,6 @@ def main(argv, linux=None): if cli_args.subcommand == 'run': if not os.path.exists(cli_args.build_dir): os.mkdir(cli_args.build_dir) - kunit_kernel.kunitconfig_path = os.path.join( - cli_args.build_dir, - kunit_kernel.kunitconfig_path) - - if not os.path.exists(kunit_kernel.kunitconfig_path): - create_default_kunitconfig() if not linux: linux = kunit_kernel.LinuxSourceTree() @@ -263,12 +257,6 @@ def main(argv, linux=None): if cli_args.build_dir: if not os.path.exists(cli_args.build_dir): os.mkdir(cli_args.build_dir) - kunit_kernel.kunitconfig_path = os.path.join( - cli_args.build_dir, - kunit_kernel.kunitconfig_path) - - if not os.path.exists(kunit_kernel.kunitconfig_path): - create_default_kunitconfig() if not linux: linux = kunit_kernel.LinuxSourceTree() @@ -285,12 +273,6 @@ def main(argv, linux=None): if cli_args.build_dir: if not os.path.exists(cli_args.build_dir): os.mkdir(cli_args.build_dir) - kunit_kernel.kunitconfig_path = os.path.join( - cli_args.build_dir, - kunit_kernel.kunitconfig_path) - - if not os.path.exists(kunit_kernel.kunitconfig_path): - create_default_kunitconfig() if not linux: linux = kunit_kernel.LinuxSourceTree() @@ -309,12 +291,6 @@ def main(argv, linux=None): if cli_args.build_dir: if not os.path.exists(cli_args.build_dir): os.mkdir(cli_args.build_dir) - kunit_kernel.kunitconfig_path = os.path.join( - cli_args.build_dir, - kunit_kernel.kunitconfig_path) - - if not os.path.exists(kunit_kernel.kunitconfig_path): - create_default_kunitconfig() if not linux: linux = kunit_kernel.LinuxSourceTree() diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index 63dbda2d029f..e20e2056cb38 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -34,7 +34,7 @@ class LinuxSourceTreeOperations(object): def make_mrproper(self): try: - subprocess.check_output(['make', 'mrproper']) + subprocess.check_output(['make', 'mrproper'], stderr=subprocess.STDOUT) except OSError as e: raise ConfigError('Could not call make command: ' + e) except subprocess.CalledProcessError as e: @@ -47,7 +47,7 @@ class LinuxSourceTreeOperations(object): if build_dir: command += ['O=' + build_dir] try: - subprocess.check_output(command, stderr=subprocess.PIPE) + subprocess.check_output(command, stderr=subprocess.STDOUT) except OSError as e: raise ConfigError('Could not call make command: ' + e) except subprocess.CalledProcessError as e: @@ -77,7 +77,7 @@ class LinuxSourceTreeOperations(object): if build_dir: command += ['O=' + build_dir] try: - subprocess.check_output(command) + subprocess.check_output(command, stderr=subprocess.STDOUT) except OSError as e: raise BuildError('Could not call execute make: ' + e) except subprocess.CalledProcessError as e: diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index f9eeaea94cad..287c74d821c3 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -251,21 +251,21 @@ class KUnitMainTest(unittest.TestCase): pass def test_config_passes_args_pass(self): - kunit.main(['config'], self.linux_source_mock) + kunit.main(['config', '--build_dir=.kunit'], self.linux_source_mock) assert self.linux_source_mock.build_reconfig.call_count == 1 assert self.linux_source_mock.run_kernel.call_count == 0 def test_build_passes_args_pass(self): kunit.main(['build'], self.linux_source_mock) assert self.linux_source_mock.build_reconfig.call_count == 0 - self.linux_source_mock.build_um_kernel.assert_called_once_with(False, 8, '', None) + self.linux_source_mock.build_um_kernel.assert_called_once_with(False, 8, '.kunit', None) assert self.linux_source_mock.run_kernel.call_count == 0 def test_exec_passes_args_pass(self): kunit.main(['exec'], self.linux_source_mock) assert self.linux_source_mock.build_reconfig.call_count == 0 assert self.linux_source_mock.run_kernel.call_count == 1 - self.linux_source_mock.run_kernel.assert_called_once_with(build_dir='', timeout=300) + self.linux_source_mock.run_kernel.assert_called_once_with(build_dir='.kunit', timeout=300) self.print_mock.assert_any_call(StrContains('Testing complete.')) def test_run_passes_args_pass(self): @@ -273,7 +273,7 @@ class KUnitMainTest(unittest.TestCase): assert self.linux_source_mock.build_reconfig.call_count == 1 assert self.linux_source_mock.run_kernel.call_count == 1 self.linux_source_mock.run_kernel.assert_called_once_with( - build_dir='', timeout=300) + build_dir='.kunit', timeout=300) self.print_mock.assert_any_call(StrContains('Testing complete.')) def test_exec_passes_args_fail(self): @@ -313,7 +313,7 @@ class KUnitMainTest(unittest.TestCase): def test_exec_timeout(self): timeout = 3453 kunit.main(['exec', '--timeout', str(timeout)], self.linux_source_mock) - self.linux_source_mock.run_kernel.assert_called_once_with(build_dir='', timeout=timeout) + self.linux_source_mock.run_kernel.assert_called_once_with(build_dir='.kunit', timeout=timeout) self.print_mock.assert_any_call(StrContains('Testing complete.')) def test_run_timeout(self): @@ -321,12 +321,12 @@ class KUnitMainTest(unittest.TestCase): kunit.main(['run', '--timeout', str(timeout)], self.linux_source_mock) assert self.linux_source_mock.build_reconfig.call_count == 1 self.linux_source_mock.run_kernel.assert_called_once_with( - build_dir='', timeout=timeout) + build_dir='.kunit', timeout=timeout) self.print_mock.assert_any_call(StrContains('Testing complete.')) def test_run_builddir(self): build_dir = '.kunit' - kunit.main(['run', '--build_dir', build_dir], self.linux_source_mock) + kunit.main(['run', '--build_dir=.kunit'], self.linux_source_mock) assert self.linux_source_mock.build_reconfig.call_count == 1 self.linux_source_mock.run_kernel.assert_called_once_with( build_dir=build_dir, timeout=300) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index f4522e0a2cab..e03bc15ce731 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -6,6 +6,7 @@ TARGETS += breakpoints TARGETS += capabilities TARGETS += cgroup TARGETS += clone3 +TARGETS += core TARGETS += cpufreq TARGETS += cpu-hotplug TARGETS += drivers/dma-buf @@ -15,6 +16,7 @@ TARGETS += filesystems TARGETS += filesystems/binderfs TARGETS += filesystems/epoll TARGETS += firmware +TARGETS += fpu TARGETS += ftrace TARGETS += futex TARGETS += gpio diff --git a/tools/testing/selftests/breakpoints/step_after_suspend_test.c b/tools/testing/selftests/breakpoints/step_after_suspend_test.c index b3ead29c6089..2cf6f10ab7c4 100644 --- a/tools/testing/selftests/breakpoints/step_after_suspend_test.c +++ b/tools/testing/selftests/breakpoints/step_after_suspend_test.c @@ -47,7 +47,7 @@ void child(int cpu) _exit(0); } -bool run_test(int cpu) +int run_test(int cpu) { int status; pid_t pid = fork(); @@ -55,7 +55,7 @@ bool run_test(int cpu) if (pid < 0) { ksft_print_msg("fork() failed: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (pid == 0) child(cpu); @@ -63,67 +63,68 @@ bool run_test(int cpu) wpid = waitpid(pid, &status, __WALL); if (wpid != pid) { ksft_print_msg("waitpid() failed: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (!WIFSTOPPED(status)) { ksft_print_msg("child did not stop: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (WSTOPSIG(status) != SIGSTOP) { ksft_print_msg("child did not stop with SIGSTOP: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (ptrace(PTRACE_SINGLESTEP, pid, NULL, NULL) < 0) { if (errno == EIO) { - ksft_exit_skip( + ksft_print_msg( "ptrace(PTRACE_SINGLESTEP) not supported on this architecture: %s\n", strerror(errno)); + return KSFT_SKIP; } ksft_print_msg("ptrace(PTRACE_SINGLESTEP) failed: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } wpid = waitpid(pid, &status, __WALL); if (wpid != pid) { ksft_print_msg("waitpid() failed: $s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (WIFEXITED(status)) { ksft_print_msg("child did not single-step: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (!WIFSTOPPED(status)) { ksft_print_msg("child did not stop: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (WSTOPSIG(status) != SIGTRAP) { ksft_print_msg("child did not stop with SIGTRAP: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (ptrace(PTRACE_CONT, pid, NULL, NULL) < 0) { ksft_print_msg("ptrace(PTRACE_CONT) failed: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } wpid = waitpid(pid, &status, __WALL); if (wpid != pid) { ksft_print_msg("waitpid() failed: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } if (!WIFEXITED(status)) { ksft_print_msg("child did not exit after PTRACE_CONT: %s\n", strerror(errno)); - return false; + return KSFT_FAIL; } - return true; + return KSFT_PASS; } void suspend(void) @@ -183,32 +184,38 @@ int main(int argc, char **argv) } } + err = sched_getaffinity(0, sizeof(available_cpus), &available_cpus); + if (err < 0) + ksft_exit_fail_msg("sched_getaffinity() failed\n"); + for (cpu = 0; cpu < CPU_SETSIZE; cpu++) { if (!CPU_ISSET(cpu, &available_cpus)) continue; tests++; } - ksft_set_plan(tests); if (do_suspend) suspend(); - err = sched_getaffinity(0, sizeof(available_cpus), &available_cpus); - if (err < 0) - ksft_exit_fail_msg("sched_getaffinity() failed\n"); - + ksft_set_plan(tests); for (cpu = 0; cpu < CPU_SETSIZE; cpu++) { - bool test_success; + int test_success; if (!CPU_ISSET(cpu, &available_cpus)) continue; test_success = run_test(cpu); - if (test_success) { + switch (test_success) { + case KSFT_PASS: ksft_test_result_pass("CPU %d\n", cpu); - } else { + break; + case KSFT_SKIP: + ksft_test_result_skip("CPU %d\n", cpu); + break; + case KSFT_FAIL: ksft_test_result_fail("CPU %d\n", cpu); succeeded = false; + break; } } diff --git a/tools/testing/selftests/clone3/.gitignore b/tools/testing/selftests/clone3/.gitignore index a81085742d40..83c0f6246055 100644 --- a/tools/testing/selftests/clone3/.gitignore +++ b/tools/testing/selftests/clone3/.gitignore @@ -2,3 +2,4 @@ clone3 clone3_clear_sighand clone3_set_tid +clone3_cap_checkpoint_restore diff --git a/tools/testing/selftests/clone3/Makefile b/tools/testing/selftests/clone3/Makefile index cf976c732906..ef7564cb7abe 100644 --- a/tools/testing/selftests/clone3/Makefile +++ b/tools/testing/selftests/clone3/Makefile @@ -1,6 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -g -I../../../../usr/include/ +LDLIBS += -lcap -TEST_GEN_PROGS := clone3 clone3_clear_sighand clone3_set_tid +TEST_GEN_PROGS := clone3 clone3_clear_sighand clone3_set_tid \ + clone3_cap_checkpoint_restore include ../lib.mk diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c index f14c269a5a18..b7e6dec36173 100644 --- a/tools/testing/selftests/clone3/clone3.c +++ b/tools/testing/selftests/clone3/clone3.c @@ -131,9 +131,9 @@ int main(int argc, char *argv[]) uid_t uid = getuid(); - test_clone3_supported(); ksft_print_header(); ksft_set_plan(17); + test_clone3_supported(); /* Just a simple clone3() should return 0.*/ test_clone3(0, 0, 0, CLONE3_ARGS_NO_TEST); diff --git a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c new file mode 100644 index 000000000000..9562425aa0a9 --- /dev/null +++ b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c @@ -0,0 +1,182 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Based on Christian Brauner's clone3() example. + * These tests are assuming to be running in the host's + * PID namespace. + */ + +/* capabilities related code based on selftests/bpf/test_verifier.c */ + +#define _GNU_SOURCE +#include <errno.h> +#include <linux/types.h> +#include <linux/sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <sys/capability.h> +#include <sys/prctl.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <sys/un.h> +#include <sys/wait.h> +#include <unistd.h> +#include <sched.h> + +#include "../kselftest_harness.h" +#include "clone3_selftests.h" + +#ifndef MAX_PID_NS_LEVEL +#define MAX_PID_NS_LEVEL 32 +#endif + +static void child_exit(int ret) +{ + fflush(stdout); + fflush(stderr); + _exit(ret); +} + +static int call_clone3_set_tid(struct __test_metadata *_metadata, + pid_t *set_tid, size_t set_tid_size) +{ + int status; + pid_t pid = -1; + + struct clone_args args = { + .exit_signal = SIGCHLD, + .set_tid = ptr_to_u64(set_tid), + .set_tid_size = set_tid_size, + }; + + pid = sys_clone3(&args, sizeof(struct clone_args)); + if (pid < 0) { + TH_LOG("%s - Failed to create new process", strerror(errno)); + return -errno; + } + + if (pid == 0) { + int ret; + char tmp = 0; + + TH_LOG("I am the child, my PID is %d (expected %d)", getpid(), set_tid[0]); + + if (set_tid[0] != getpid()) + child_exit(EXIT_FAILURE); + child_exit(EXIT_SUCCESS); + } + + TH_LOG("I am the parent (%d). My child's pid is %d", getpid(), pid); + + if (waitpid(pid, &status, 0) < 0) { + TH_LOG("Child returned %s", strerror(errno)); + return -errno; + } + + if (!WIFEXITED(status)) + return -1; + + return WEXITSTATUS(status); +} + +static int test_clone3_set_tid(struct __test_metadata *_metadata, + pid_t *set_tid, size_t set_tid_size) +{ + int ret; + + TH_LOG("[%d] Trying clone3() with CLONE_SET_TID to %d", getpid(), set_tid[0]); + ret = call_clone3_set_tid(_metadata, set_tid, set_tid_size); + TH_LOG("[%d] clone3() with CLONE_SET_TID %d says:%d", getpid(), set_tid[0], ret); + return ret; +} + +struct libcap { + struct __user_cap_header_struct hdr; + struct __user_cap_data_struct data[2]; +}; + +static int set_capability(void) +{ + cap_value_t cap_values[] = { CAP_SETUID, CAP_SETGID }; + struct libcap *cap; + int ret = -1; + cap_t caps; + + caps = cap_get_proc(); + if (!caps) { + perror("cap_get_proc"); + return -1; + } + + /* Drop all capabilities */ + if (cap_clear(caps)) { + perror("cap_clear"); + goto out; + } + + cap_set_flag(caps, CAP_EFFECTIVE, 2, cap_values, CAP_SET); + cap_set_flag(caps, CAP_PERMITTED, 2, cap_values, CAP_SET); + + cap = (struct libcap *) caps; + + /* 40 -> CAP_CHECKPOINT_RESTORE */ + cap->data[1].effective |= 1 << (40 - 32); + cap->data[1].permitted |= 1 << (40 - 32); + + if (cap_set_proc(caps)) { + perror("cap_set_proc"); + goto out; + } + ret = 0; +out: + if (cap_free(caps)) + perror("cap_free"); + return ret; +} + +TEST(clone3_cap_checkpoint_restore) +{ + pid_t pid; + int status; + int ret = 0; + pid_t set_tid[1]; + + test_clone3_supported(); + + EXPECT_EQ(getuid(), 0) + XFAIL(return, "Skipping all tests as non-root\n"); + + memset(&set_tid, 0, sizeof(set_tid)); + + /* Find the current active PID */ + pid = fork(); + if (pid == 0) { + TH_LOG("Child has PID %d", getpid()); + child_exit(EXIT_SUCCESS); + } + ASSERT_GT(waitpid(pid, &status, 0), 0) + TH_LOG("Waiting for child %d failed", pid); + + /* After the child has finished, its PID should be free. */ + set_tid[0] = pid; + + ASSERT_EQ(set_capability(), 0) + TH_LOG("Could not set CAP_CHECKPOINT_RESTORE"); + + ASSERT_EQ(prctl(PR_SET_KEEPCAPS, 1, 0, 0, 0), 0); + + EXPECT_EQ(setgid(65534), 0) + TH_LOG("Failed to setgid(65534)"); + ASSERT_EQ(setuid(65534), 0); + + set_tid[0] = pid; + /* This would fail without CAP_CHECKPOINT_RESTORE */ + ASSERT_EQ(test_clone3_set_tid(_metadata, set_tid, 1), -EPERM); + ASSERT_EQ(set_capability(), 0) + TH_LOG("Could not set CAP_CHECKPOINT_RESTORE"); + /* This should work as we have CAP_CHECKPOINT_RESTORE as non-root */ + ASSERT_EQ(test_clone3_set_tid(_metadata, set_tid, 1), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/clone3/clone3_clear_sighand.c b/tools/testing/selftests/clone3/clone3_clear_sighand.c index 9e1af8aa7698..db5fc9c5edcf 100644 --- a/tools/testing/selftests/clone3/clone3_clear_sighand.c +++ b/tools/testing/selftests/clone3/clone3_clear_sighand.c @@ -119,9 +119,8 @@ static void test_clone3_clear_sighand(void) int main(int argc, char **argv) { ksft_print_header(); - test_clone3_supported(); - ksft_set_plan(1); + test_clone3_supported(); test_clone3_clear_sighand(); diff --git a/tools/testing/selftests/clone3/clone3_set_tid.c b/tools/testing/selftests/clone3/clone3_set_tid.c index 25beb22f35b5..5831c1082d6d 100644 --- a/tools/testing/selftests/clone3/clone3_set_tid.c +++ b/tools/testing/selftests/clone3/clone3_set_tid.c @@ -157,8 +157,8 @@ int main(int argc, char *argv[]) pid_t set_tid[MAX_PID_NS_LEVEL * 2]; ksft_print_header(); - test_clone3_supported(); ksft_set_plan(29); + test_clone3_supported(); if (pipe(pipe_1) < 0 || pipe(pipe_2) < 0) ksft_exit_fail_msg("pipe() failed\n"); diff --git a/tools/testing/selftests/core/.gitignore b/tools/testing/selftests/core/.gitignore new file mode 100644 index 000000000000..6e6712ce5817 --- /dev/null +++ b/tools/testing/selftests/core/.gitignore @@ -0,0 +1 @@ +close_range_test diff --git a/tools/testing/selftests/core/Makefile b/tools/testing/selftests/core/Makefile new file mode 100644 index 000000000000..f6f2d6f473c6 --- /dev/null +++ b/tools/testing/selftests/core/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0-only +CFLAGS += -g -I../../../../usr/include/ + +TEST_GEN_PROGS := close_range_test + +include ../lib.mk + diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c new file mode 100644 index 000000000000..c99b98b0d461 --- /dev/null +++ b/tools/testing/selftests/core/close_range_test.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <linux/kernel.h> +#include <limits.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <syscall.h> +#include <unistd.h> + +#include "../kselftest_harness.h" +#include "../clone3/clone3_selftests.h" + +#ifndef __NR_close_range +#define __NR_close_range -1 +#endif + +#ifndef CLOSE_RANGE_UNSHARE +#define CLOSE_RANGE_UNSHARE (1U << 1) +#endif + +static inline int sys_close_range(unsigned int fd, unsigned int max_fd, + unsigned int flags) +{ + return syscall(__NR_close_range, fd, max_fd, flags); +} + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +TEST(close_range) +{ + int i, ret; + int open_fds[101]; + + for (i = 0; i < ARRAY_SIZE(open_fds); i++) { + int fd; + + fd = open("/dev/null", O_RDONLY | O_CLOEXEC); + ASSERT_GE(fd, 0) { + if (errno == ENOENT) + XFAIL(return, "Skipping test since /dev/null does not exist"); + } + + open_fds[i] = fd; + } + + EXPECT_EQ(-1, sys_close_range(open_fds[0], open_fds[100], -1)) { + if (errno == ENOSYS) + XFAIL(return, "close_range() syscall not supported"); + } + + EXPECT_EQ(0, sys_close_range(open_fds[0], open_fds[50], 0)); + + for (i = 0; i <= 50; i++) + EXPECT_EQ(-1, fcntl(open_fds[i], F_GETFL)); + + for (i = 51; i <= 100; i++) + EXPECT_GT(fcntl(open_fds[i], F_GETFL), -1); + + /* create a couple of gaps */ + close(57); + close(78); + close(81); + close(82); + close(84); + close(90); + + EXPECT_EQ(0, sys_close_range(open_fds[51], open_fds[92], 0)); + + for (i = 51; i <= 92; i++) + EXPECT_EQ(-1, fcntl(open_fds[i], F_GETFL)); + + for (i = 93; i <= 100; i++) + EXPECT_GT(fcntl(open_fds[i], F_GETFL), -1); + + /* test that the kernel caps and still closes all fds */ + EXPECT_EQ(0, sys_close_range(open_fds[93], open_fds[99], 0)); + + for (i = 93; i <= 99; i++) + EXPECT_EQ(-1, fcntl(open_fds[i], F_GETFL)); + + EXPECT_GT(fcntl(open_fds[i], F_GETFL), -1); + + EXPECT_EQ(0, sys_close_range(open_fds[100], open_fds[100], 0)); + + EXPECT_EQ(-1, fcntl(open_fds[100], F_GETFL)); +} + +TEST(close_range_unshare) +{ + int i, ret, status; + pid_t pid; + int open_fds[101]; + struct clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + for (i = 0; i < ARRAY_SIZE(open_fds); i++) { + int fd; + + fd = open("/dev/null", O_RDONLY | O_CLOEXEC); + ASSERT_GE(fd, 0) { + if (errno == ENOENT) + XFAIL(return, "Skipping test since /dev/null does not exist"); + } + + open_fds[i] = fd; + } + + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + ret = sys_close_range(open_fds[0], open_fds[50], + CLOSE_RANGE_UNSHARE); + if (ret) + exit(EXIT_FAILURE); + + for (i = 0; i <= 50; i++) + if (fcntl(open_fds[i], F_GETFL) != -1) + exit(EXIT_FAILURE); + + for (i = 51; i <= 100; i++) + if (fcntl(open_fds[i], F_GETFL) == -1) + exit(EXIT_FAILURE); + + /* create a couple of gaps */ + close(57); + close(78); + close(81); + close(82); + close(84); + close(90); + + ret = sys_close_range(open_fds[51], open_fds[92], + CLOSE_RANGE_UNSHARE); + if (ret) + exit(EXIT_FAILURE); + + for (i = 51; i <= 92; i++) + if (fcntl(open_fds[i], F_GETFL) != -1) + exit(EXIT_FAILURE); + + for (i = 93; i <= 100; i++) + if (fcntl(open_fds[i], F_GETFL) == -1) + exit(EXIT_FAILURE); + + /* test that the kernel caps and still closes all fds */ + ret = sys_close_range(open_fds[93], open_fds[99], + CLOSE_RANGE_UNSHARE); + if (ret) + exit(EXIT_FAILURE); + + for (i = 93; i <= 99; i++) + if (fcntl(open_fds[i], F_GETFL) != -1) + exit(EXIT_FAILURE); + + if (fcntl(open_fds[100], F_GETFL) == -1) + exit(EXIT_FAILURE); + + ret = sys_close_range(open_fds[100], open_fds[100], + CLOSE_RANGE_UNSHARE); + if (ret) + exit(EXIT_FAILURE); + + if (fcntl(open_fds[100], F_GETFL) != -1) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); +} + +TEST(close_range_unshare_capped) +{ + int i, ret, status; + pid_t pid; + int open_fds[101]; + struct clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + for (i = 0; i < ARRAY_SIZE(open_fds); i++) { + int fd; + + fd = open("/dev/null", O_RDONLY | O_CLOEXEC); + ASSERT_GE(fd, 0) { + if (errno == ENOENT) + XFAIL(return, "Skipping test since /dev/null does not exist"); + } + + open_fds[i] = fd; + } + + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + ret = sys_close_range(open_fds[0], UINT_MAX, + CLOSE_RANGE_UNSHARE); + if (ret) + exit(EXIT_FAILURE); + + for (i = 0; i <= 100; i++) + if (fcntl(open_fds[i], F_GETFL) != -1) + exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c index 8a6b507e34a8..1d27f52c61e6 100644 --- a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c +++ b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c @@ -21,7 +21,6 @@ #include <linux/android/binder.h> #include <linux/android/binderfs.h> -#include "../../kselftest.h" #include "../../kselftest_harness.h" #define DEFAULT_THREADS 4 @@ -37,37 +36,26 @@ fd = -EBADF; \ } -#define log_exit(format, ...) \ - ({ \ - fprintf(stderr, format "\n", ##__VA_ARGS__); \ - exit(EXIT_FAILURE); \ - }) - -static void change_mountns(void) +static void change_mountns(struct __test_metadata *_metadata) { int ret; ret = unshare(CLONE_NEWNS); - if (ret < 0) - ksft_exit_fail_msg("%s - Failed to unshare mount namespace\n", - strerror(errno)); + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to unshare mount namespace", + strerror(errno)); + } ret = mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0); - if (ret < 0) - ksft_exit_fail_msg("%s - Failed to mount / as private\n", - strerror(errno)); -} - -static void rmdir_protect_errno(const char *dir) -{ - int saved_errno = errno; - (void)rmdir(dir); - errno = saved_errno; + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to mount / as private", + strerror(errno)); + } } -static int __do_binderfs_test(void) +static int __do_binderfs_test(struct __test_metadata *_metadata) { - int fd, ret, saved_errno; + int fd, ret, saved_errno, result = 1; size_t len; ssize_t wret; struct binderfs_device device = { 0 }; @@ -75,113 +63,107 @@ static int __do_binderfs_test(void) char binderfs_mntpt[] = P_tmpdir "/binderfs_XXXXXX", device_path[sizeof(P_tmpdir "/binderfs_XXXXXX/") + BINDERFS_MAX_NAME]; - change_mountns(); + change_mountns(_metadata); - if (!mkdtemp(binderfs_mntpt)) - ksft_exit_fail_msg( - "%s - Failed to create binderfs mountpoint\n", + EXPECT_NE(mkdtemp(binderfs_mntpt), NULL) { + TH_LOG("%s - Failed to create binderfs mountpoint", strerror(errno)); + goto out; + } ret = mount(NULL, binderfs_mntpt, "binder", 0, 0); - if (ret < 0) { - if (errno != ENODEV) - ksft_exit_fail_msg("%s - Failed to mount binderfs\n", - strerror(errno)); - - rmdir_protect_errno(binderfs_mntpt); - return 1; + EXPECT_EQ(ret, 0) { + if (errno == ENODEV) + XFAIL(goto out, "binderfs missing"); + TH_LOG("%s - Failed to mount binderfs", strerror(errno)); + goto rmdir; } - /* binderfs mount test passed */ - ksft_inc_pass_cnt(); + /* success: binderfs mounted */ memcpy(device.name, "my-binder", strlen("my-binder")); snprintf(device_path, sizeof(device_path), "%s/binder-control", binderfs_mntpt); fd = open(device_path, O_RDONLY | O_CLOEXEC); - if (fd < 0) - ksft_exit_fail_msg( - "%s - Failed to open binder-control device\n", + EXPECT_GE(fd, 0) { + TH_LOG("%s - Failed to open binder-control device", strerror(errno)); + goto umount; + } ret = ioctl(fd, BINDER_CTL_ADD, &device); saved_errno = errno; close(fd); errno = saved_errno; - if (ret < 0) { - rmdir_protect_errno(binderfs_mntpt); - ksft_exit_fail_msg( - "%s - Failed to allocate new binder device\n", + EXPECT_GE(ret, 0) { + TH_LOG("%s - Failed to allocate new binder device", strerror(errno)); + goto umount; } - ksft_print_msg( - "Allocated new binder device with major %d, minor %d, and name %s\n", + TH_LOG("Allocated new binder device with major %d, minor %d, and name %s", device.major, device.minor, device.name); - /* binder device allocation test passed */ - ksft_inc_pass_cnt(); + /* success: binder device allocation */ snprintf(device_path, sizeof(device_path), "%s/my-binder", binderfs_mntpt); fd = open(device_path, O_CLOEXEC | O_RDONLY); - if (fd < 0) { - rmdir_protect_errno(binderfs_mntpt); - ksft_exit_fail_msg("%s - Failed to open my-binder device\n", - strerror(errno)); + EXPECT_GE(fd, 0) { + TH_LOG("%s - Failed to open my-binder device", + strerror(errno)); + goto umount; } ret = ioctl(fd, BINDER_VERSION, &version); saved_errno = errno; close(fd); errno = saved_errno; - if (ret < 0) { - rmdir_protect_errno(binderfs_mntpt); - ksft_exit_fail_msg( - "%s - Failed to open perform BINDER_VERSION request\n", + EXPECT_GE(ret, 0) { + TH_LOG("%s - Failed to open perform BINDER_VERSION request", strerror(errno)); + goto umount; } - ksft_print_msg("Detected binder version: %d\n", - version.protocol_version); + TH_LOG("Detected binder version: %d", version.protocol_version); - /* binder transaction with binderfs binder device passed */ - ksft_inc_pass_cnt(); + /* success: binder transaction with binderfs binder device */ ret = unlink(device_path); - if (ret < 0) { - rmdir_protect_errno(binderfs_mntpt); - ksft_exit_fail_msg("%s - Failed to delete binder device\n", - strerror(errno)); + EXPECT_EQ(ret, 0) { + TH_LOG("%s - Failed to delete binder device", + strerror(errno)); + goto umount; } - /* binder device removal passed */ - ksft_inc_pass_cnt(); + /* success: binder device removal */ snprintf(device_path, sizeof(device_path), "%s/binder-control", binderfs_mntpt); ret = unlink(device_path); - if (!ret) { - rmdir_protect_errno(binderfs_mntpt); - ksft_exit_fail_msg("Managed to delete binder-control device\n"); - } else if (errno != EPERM) { - rmdir_protect_errno(binderfs_mntpt); - ksft_exit_fail_msg( - "%s - Failed to delete binder-control device but exited with unexpected error code\n", + EXPECT_NE(ret, 0) { + TH_LOG("Managed to delete binder-control device"); + goto umount; + } + EXPECT_EQ(errno, EPERM) { + TH_LOG("%s - Failed to delete binder-control device but exited with unexpected error code", strerror(errno)); + goto umount; } - /* binder-control device removal failed as expected */ - ksft_inc_xfail_cnt(); + /* success: binder-control device removal failed as expected */ + result = 0; -on_error: +umount: ret = umount2(binderfs_mntpt, MNT_DETACH); - rmdir_protect_errno(binderfs_mntpt); - if (ret < 0) - ksft_exit_fail_msg("%s - Failed to unmount binderfs\n", - strerror(errno)); - - /* binderfs unmount test passed */ - ksft_inc_pass_cnt(); - return 0; + EXPECT_EQ(ret, 0) { + TH_LOG("%s - Failed to unmount binderfs", strerror(errno)); + } +rmdir: + ret = rmdir(binderfs_mntpt); + EXPECT_EQ(ret, 0) { + TH_LOG("%s - Failed to rmdir binderfs mount", strerror(errno)); + } +out: + return result; } static int wait_for_pid(pid_t pid) @@ -291,7 +273,7 @@ static int write_id_mapping(enum idmap_type type, pid_t pid, const char *buf, return 0; } -static void change_userns(int syncfds[2]) +static void change_userns(struct __test_metadata *_metadata, int syncfds[2]) { int ret; char buf; @@ -299,25 +281,29 @@ static void change_userns(int syncfds[2]) close_prot_errno_disarm(syncfds[1]); ret = unshare(CLONE_NEWUSER); - if (ret < 0) - ksft_exit_fail_msg("%s - Failed to unshare user namespace\n", - strerror(errno)); + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to unshare user namespace", + strerror(errno)); + } ret = write_nointr(syncfds[0], "1", 1); - if (ret != 1) - ksft_exit_fail_msg("write_nointr() failed\n"); + ASSERT_EQ(ret, 1) { + TH_LOG("write_nointr() failed"); + } ret = read_nointr(syncfds[0], &buf, 1); - if (ret != 1) - ksft_exit_fail_msg("read_nointr() failed\n"); + ASSERT_EQ(ret, 1) { + TH_LOG("read_nointr() failed"); + } close_prot_errno_disarm(syncfds[0]); - if (setid_userns_root()) - ksft_exit_fail_msg("setid_userns_root() failed"); + ASSERT_EQ(setid_userns_root(), 0) { + TH_LOG("setid_userns_root() failed"); + } } -static void change_idmaps(int syncfds[2], pid_t pid) +static void change_idmaps(struct __test_metadata *_metadata, int syncfds[2], pid_t pid) { int ret; char buf; @@ -326,35 +312,42 @@ static void change_idmaps(int syncfds[2], pid_t pid) close_prot_errno_disarm(syncfds[0]); ret = read_nointr(syncfds[1], &buf, 1); - if (ret != 1) - ksft_exit_fail_msg("read_nointr() failed\n"); + ASSERT_EQ(ret, 1) { + TH_LOG("read_nointr() failed"); + } snprintf(id_map, sizeof(id_map), "0 %d 1\n", getuid()); ret = write_id_mapping(UID_MAP, pid, id_map, strlen(id_map)); - if (ret) - ksft_exit_fail_msg("write_id_mapping(UID_MAP) failed"); + ASSERT_EQ(ret, 0) { + TH_LOG("write_id_mapping(UID_MAP) failed"); + } snprintf(id_map, sizeof(id_map), "0 %d 1\n", getgid()); ret = write_id_mapping(GID_MAP, pid, id_map, strlen(id_map)); - if (ret) - ksft_exit_fail_msg("write_id_mapping(GID_MAP) failed"); + ASSERT_EQ(ret, 0) { + TH_LOG("write_id_mapping(GID_MAP) failed"); + } ret = write_nointr(syncfds[1], "1", 1); - if (ret != 1) - ksft_exit_fail_msg("write_nointr() failed"); + ASSERT_EQ(ret, 1) { + TH_LOG("write_nointr() failed"); + } close_prot_errno_disarm(syncfds[1]); } +struct __test_metadata *_thread_metadata; static void *binder_version_thread(void *data) { + struct __test_metadata *_metadata = _thread_metadata; int fd = PTR_TO_INT(data); struct binder_version version = { 0 }; int ret; ret = ioctl(fd, BINDER_VERSION, &version); if (ret < 0) - ksft_print_msg("%s - Failed to open perform BINDER_VERSION request\n", strerror(errno)); + TH_LOG("%s - Failed to open perform BINDER_VERSION request\n", + strerror(errno)); pthread_exit(data); } @@ -377,68 +370,79 @@ TEST(binderfs_stress) device_path[sizeof(P_tmpdir "/binderfs_XXXXXX/") + BINDERFS_MAX_NAME]; ret = socketpair(PF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, syncfds); - if (ret < 0) - ksft_exit_fail_msg("%s - Failed to create socket pair", strerror(errno)); + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to create socket pair", strerror(errno)); + } pid = fork(); - if (pid < 0) { + ASSERT_GE(pid, 0) { + TH_LOG("%s - Failed to fork", strerror(errno)); close_prot_errno_disarm(syncfds[0]); close_prot_errno_disarm(syncfds[1]); - ksft_exit_fail_msg("%s - Failed to fork", strerror(errno)); } if (pid == 0) { int i, j, k, nthreads; pthread_attr_t attr; pthread_t threads[DEFAULT_THREADS]; - change_userns(syncfds); - change_mountns(); + change_userns(_metadata, syncfds); + change_mountns(_metadata); - if (!mkdtemp(binderfs_mntpt)) - log_exit("%s - Failed to create binderfs mountpoint\n", - strerror(errno)); + ASSERT_NE(mkdtemp(binderfs_mntpt), NULL) { + TH_LOG("%s - Failed to create binderfs mountpoint", + strerror(errno)); + } ret = mount(NULL, binderfs_mntpt, "binder", 0, 0); - if (ret < 0) - log_exit("%s - Failed to mount binderfs\n", strerror(errno)); + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to mount binderfs", strerror(errno)); + } for (int i = 0; i < ARRAY_SIZE(fds); i++) { snprintf(device_path, sizeof(device_path), "%s/binder-control", binderfs_mntpt); fd = open(device_path, O_RDONLY | O_CLOEXEC); - if (fd < 0) - log_exit("%s - Failed to open binder-control device\n", strerror(errno)); + ASSERT_GE(fd, 0) { + TH_LOG("%s - Failed to open binder-control device", + strerror(errno)); + } memset(&device, 0, sizeof(device)); snprintf(device.name, sizeof(device.name), "%d", i); ret = ioctl(fd, BINDER_CTL_ADD, &device); close_prot_errno_disarm(fd); - if (ret < 0) - log_exit("%s - Failed to allocate new binder device\n", strerror(errno)); + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to allocate new binder device", + strerror(errno)); + } snprintf(device_path, sizeof(device_path), "%s/%d", binderfs_mntpt, i); fds[i] = open(device_path, O_RDONLY | O_CLOEXEC); - if (fds[i] < 0) - log_exit("%s - Failed to open binder device\n", strerror(errno)); + ASSERT_GE(fds[i], 0) { + TH_LOG("%s - Failed to open binder device", strerror(errno)); + } } ret = umount2(binderfs_mntpt, MNT_DETACH); - rmdir_protect_errno(binderfs_mntpt); - if (ret < 0) - log_exit("%s - Failed to unmount binderfs\n", strerror(errno)); + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to unmount binderfs", strerror(errno)); + rmdir(binderfs_mntpt); + } nthreads = get_nprocs_conf(); if (nthreads > DEFAULT_THREADS) nthreads = DEFAULT_THREADS; + _thread_metadata = _metadata; pthread_attr_init(&attr); for (k = 0; k < ARRAY_SIZE(fds); k++) { for (i = 0; i < nthreads; i++) { ret = pthread_create(&threads[i], &attr, binder_version_thread, INT_TO_PTR(fds[k])); if (ret) { - ksft_print_msg("%s - Failed to create thread %d\n", strerror(errno), i); + TH_LOG("%s - Failed to create thread %d", + strerror(errno), i); break; } } @@ -448,7 +452,8 @@ TEST(binderfs_stress) ret = pthread_join(threads[j], &fdptr); if (ret) - ksft_print_msg("%s - Failed to join thread %d for fd %d\n", strerror(errno), j, PTR_TO_INT(fdptr)); + TH_LOG("%s - Failed to join thread %d for fd %d", + strerror(errno), j, PTR_TO_INT(fdptr)); } } pthread_attr_destroy(&attr); @@ -459,11 +464,12 @@ TEST(binderfs_stress) exit(EXIT_SUCCESS); } - change_idmaps(syncfds, pid); + change_idmaps(_metadata, syncfds, pid); ret = wait_for_pid(pid); - if (ret) - ksft_exit_fail_msg("wait_for_pid() failed"); + ASSERT_EQ(ret, 0) { + TH_LOG("wait_for_pid() failed"); + } } TEST(binderfs_test_privileged) @@ -471,7 +477,7 @@ TEST(binderfs_test_privileged) if (geteuid() != 0) XFAIL(return, "Tests are not run as root. Skipping privileged tests"); - if (__do_binderfs_test() == 1) + if (__do_binderfs_test(_metadata)) XFAIL(return, "The Android binderfs filesystem is not available"); } @@ -482,31 +488,33 @@ TEST(binderfs_test_unprivileged) pid_t pid; ret = socketpair(PF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, syncfds); - if (ret < 0) - ksft_exit_fail_msg("%s - Failed to create socket pair", strerror(errno)); + ASSERT_EQ(ret, 0) { + TH_LOG("%s - Failed to create socket pair", strerror(errno)); + } pid = fork(); - if (pid < 0) { + ASSERT_GE(pid, 0) { close_prot_errno_disarm(syncfds[0]); close_prot_errno_disarm(syncfds[1]); - ksft_exit_fail_msg("%s - Failed to fork", strerror(errno)); + TH_LOG("%s - Failed to fork", strerror(errno)); } if (pid == 0) { - change_userns(syncfds); - if (__do_binderfs_test() == 1) + change_userns(_metadata, syncfds); + if (__do_binderfs_test(_metadata)) exit(2); exit(EXIT_SUCCESS); } - change_idmaps(syncfds, pid); + change_idmaps(_metadata, syncfds, pid); ret = wait_for_pid(pid); if (ret) { if (ret == 2) XFAIL(return, "The Android binderfs filesystem is not available"); - else - ksft_exit_fail_msg("wait_for_pid() failed"); + ASSERT_EQ(ret, 0) { + TH_LOG("wait_for_pid() failed"); + } } } diff --git a/tools/testing/selftests/firmware/settings b/tools/testing/selftests/firmware/settings new file mode 100644 index 000000000000..085e664ee093 --- /dev/null +++ b/tools/testing/selftests/firmware/settings @@ -0,0 +1,8 @@ +# The async firmware timeout is set to 1 second (but ends up being effectively +# 2 seconds). There are 3 test configs, each done with and without firmware +# present, each with 2 "nowait" functions tested 5 times. Expected time for a +# normal execution should be 2 * 3 * 2 * 2 * 5 = 120 seconds for those alone. +# Additionally, fw_fallback may take 5 seconds for internal timeouts in each +# of the 3 configs, so at least another 15 seconds are needed. Add another +# 10 seconds for each testing config: 120 + 15 + 30 +timeout=165 diff --git a/tools/testing/selftests/fpu/.gitignore b/tools/testing/selftests/fpu/.gitignore new file mode 100644 index 000000000000..d6d12ac1d9c3 --- /dev/null +++ b/tools/testing/selftests/fpu/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0+ +test_fpu diff --git a/tools/testing/selftests/fpu/Makefile b/tools/testing/selftests/fpu/Makefile new file mode 100644 index 000000000000..ea62c176ede7 --- /dev/null +++ b/tools/testing/selftests/fpu/Makefile @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0+ + +LDLIBS := -lm + +TEST_GEN_PROGS := test_fpu + +TEST_PROGS := run_test_fpu.sh + +include ../lib.mk diff --git a/tools/testing/selftests/fpu/run_test_fpu.sh b/tools/testing/selftests/fpu/run_test_fpu.sh new file mode 100755 index 000000000000..d77be93ec139 --- /dev/null +++ b/tools/testing/selftests/fpu/run_test_fpu.sh @@ -0,0 +1,46 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Load kernel module for FPU tests + +uid=$(id -u) +if [ $uid -ne 0 ]; then + echo "$0: Must be run as root" + exit 1 +fi + +if ! which modprobe > /dev/null 2>&1; then + echo "$0: You need modprobe installed" + exit 4 +fi + +if ! modinfo test_fpu > /dev/null 2>&1; then + echo "$0: You must have the following enabled in your kernel:" + echo "CONFIG_TEST_FPU=m" + exit 4 +fi + +NR_CPUS=$(getconf _NPROCESSORS_ONLN) +if [ ! $NR_CPUS ]; then + NR_CPUS=1 +fi + +modprobe test_fpu + +if [ ! -e /sys/kernel/debug/selftest_helpers/test_fpu ]; then + mount -t debugfs none /sys/kernel/debug + + if [ ! -e /sys/kernel/debug/selftest_helpers/test_fpu ]; then + echo "$0: Error mounting debugfs" + exit 4 + fi +fi + +echo "Running 1000 iterations on all CPUs... " +for i in $(seq 1 1000); do + for c in $(seq 1 $NR_CPUS); do + ./test_fpu & + done +done + +rmmod test_fpu diff --git a/tools/testing/selftests/fpu/test_fpu.c b/tools/testing/selftests/fpu/test_fpu.c new file mode 100644 index 000000000000..200238522a9d --- /dev/null +++ b/tools/testing/selftests/fpu/test_fpu.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* This testcase operates with the test_fpu kernel driver. + * It modifies the FPU control register in user mode and calls the kernel + * module to perform floating point operations in the kernel. The control + * register value should be independent between kernel and user mode. + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <errno.h> +#include <string.h> +#include <fenv.h> +#include <unistd.h> +#include <fcntl.h> + +const char *test_fpu_path = "/sys/kernel/debug/selftest_helpers/test_fpu"; + +int main(void) +{ + char dummy[1]; + int fd = open(test_fpu_path, O_RDONLY); + + if (fd < 0) { + printf("[SKIP]\tcan't access %s: %s\n", + test_fpu_path, strerror(errno)); + return 0; + } + + if (read(fd, dummy, 1) < 0) { + printf("[FAIL]\taccess with default rounding mode failed\n"); + return 1; + } + + fesetround(FE_DOWNWARD); + if (read(fd, dummy, 1) < 0) { + printf("[FAIL]\taccess with downward rounding mode failed\n"); + return 2; + } + if (fegetround() != FE_DOWNWARD) { + printf("[FAIL]\tusermode rounding mode clobbered\n"); + return 3; + } + + /* Note: the tests up to this point are quite safe and will only return + * an error. But the exception mask setting can cause misbehaving kernel + * to crash. + */ + feclearexcept(FE_ALL_EXCEPT); + feenableexcept(FE_ALL_EXCEPT); + if (read(fd, dummy, 1) < 0) { + printf("[FAIL]\taccess with fpu exceptions unmasked failed\n"); + return 4; + } + if (fegetexcept() != FE_ALL_EXCEPT) { + printf("[FAIL]\tusermode fpu exception mask clobbered\n"); + return 5; + } + + printf("[OK]\ttest_fpu\n"); + return 0; +} diff --git a/tools/testing/selftests/kmod/kmod.sh b/tools/testing/selftests/kmod/kmod.sh index c82aa77958e5..ea2147248ebe 100755 --- a/tools/testing/selftests/kmod/kmod.sh +++ b/tools/testing/selftests/kmod/kmod.sh @@ -130,7 +130,7 @@ test_reqs() if [[ $KMOD_VERSION -le 19 ]]; then echo "$0: You need at least kmod 20" >&2 echo "kmod <= 19 is buggy, for details see:" >&2 - echo "http://git.kernel.org/cgit/utils/kernel/kmod/kmod.git/commit/libkmod/libkmod-module.c?id=fd44a98ae2eb5eb32161088954ab21e58e19dfc4" >&2 + echo "https://git.kernel.org/cgit/utils/kernel/kmod/kmod.git/commit/libkmod/libkmod-module.c?id=fd44a98ae2eb5eb32161088954ab21e58e19dfc4" >&2 exit $ksft_skip fi diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 862eee734553..8d50483fe204 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -1,11 +1,43 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * kselftest.h: kselftest framework return codes to include from - * selftests. + * kselftest.h: low-level kselftest framework to include from + * selftest programs. When possible, please use + * kselftest_harness.h instead. * * Copyright (c) 2014 Shuah Khan <shuahkh@osg.samsung.com> * Copyright (c) 2014 Samsung Electronics Co., Ltd. * + * Using this API consists of first counting how many tests your code + * has to run, and then starting up the reporting: + * + * ksft_print_header(); + * ksft_set_plan(total_number_of_tests); + * + * For each test, report any progress, debugging, etc with: + * + * ksft_print_msg(fmt, ...); + * + * and finally report the pass/fail/skip/xfail state of the test with one of: + * + * ksft_test_result(condition, fmt, ...); + * ksft_test_result_pass(fmt, ...); + * ksft_test_result_fail(fmt, ...); + * ksft_test_result_skip(fmt, ...); + * ksft_test_result_xfail(fmt, ...); + * ksft_test_result_error(fmt, ...); + * + * When all tests are finished, clean up and exit the program with one of: + * + * ksft_exit(condition); + * ksft_exit_pass(); + * ksft_exit_fail(); + * + * If the program wants to report details on why the entire program has + * failed, it can instead exit with a message (this is usually done when + * the program is aborting before finishing all tests): + * + * ksft_exit_fail_msg(fmt, ...); + * */ #ifndef __KSELFTEST_H #define __KSELFTEST_H @@ -74,7 +106,7 @@ static inline void ksft_print_cnts(void) if (ksft_plan != ksft_test_num()) printf("# Planned tests != run tests (%u != %u)\n", ksft_plan, ksft_test_num()); - printf("# Pass %d Fail %d Xfail %d Xpass %d Skip %d Error %d\n", + printf("# Totals: pass:%d fail:%d xfail:%d xpass:%d skip:%d error:%d\n", ksft_cnt.ksft_pass, ksft_cnt.ksft_fail, ksft_cnt.ksft_xfail, ksft_cnt.ksft_xpass, ksft_cnt.ksft_xskip, ksft_cnt.ksft_error); @@ -120,6 +152,32 @@ static inline void ksft_test_result_fail(const char *msg, ...) va_end(args); } +/** + * ksft_test_result() - Report test success based on truth of condition + * + * @condition: if true, report test success, otherwise failure. + */ +#define ksft_test_result(condition, fmt, ...) do { \ + if (!!(condition)) \ + ksft_test_result_pass(fmt, ##__VA_ARGS__);\ + else \ + ksft_test_result_fail(fmt, ##__VA_ARGS__);\ + } while (0) + +static inline void ksft_test_result_xfail(const char *msg, ...) +{ + int saved_errno = errno; + va_list args; + + ksft_cnt.ksft_xfail++; + + va_start(args, msg); + printf("ok %d # XFAIL ", ksft_test_num()); + errno = saved_errno; + vprintf(msg, args); + va_end(args); +} + static inline void ksft_test_result_skip(const char *msg, ...) { int saved_errno = errno; @@ -128,12 +186,13 @@ static inline void ksft_test_result_skip(const char *msg, ...) ksft_cnt.ksft_xskip++; va_start(args, msg); - printf("not ok %d # SKIP ", ksft_test_num()); + printf("ok %d # SKIP ", ksft_test_num()); errno = saved_errno; vprintf(msg, args); va_end(args); } +/* TODO: how does "error" differ from "fail" or "skip"? */ static inline void ksft_test_result_error(const char *msg, ...) { int saved_errno = errno; @@ -156,11 +215,22 @@ static inline int ksft_exit_pass(void) static inline int ksft_exit_fail(void) { - printf("Bail out!\n"); ksft_print_cnts(); exit(KSFT_FAIL); } +/** + * ksft_exit() - Exit selftest based on truth of condition + * + * @condition: if true, exit self test with success, otherwise fail. + */ +#define ksft_exit(condition) do { \ + if (!!(condition)) \ + ksft_exit_pass(); \ + else \ + ksft_exit_fail(); \ + } while (0) + static inline int ksft_exit_fail_msg(const char *msg, ...) { int saved_errno = errno; @@ -190,18 +260,30 @@ static inline int ksft_exit_xpass(void) static inline int ksft_exit_skip(const char *msg, ...) { - if (msg) { - int saved_errno = errno; - va_list args; + int saved_errno = errno; + va_list args; + + va_start(args, msg); - va_start(args, msg); - printf("not ok %d # SKIP ", 1 + ksft_test_num()); + /* + * FIXME: several tests misuse ksft_exit_skip so produce + * something sensible if some tests have already been run + * or a plan has been printed. Those tests should use + * ksft_test_result_skip or ksft_exit_fail_msg instead. + */ + if (ksft_plan || ksft_test_num()) { + ksft_cnt.ksft_xskip++; + printf("ok %d # SKIP ", 1 + ksft_test_num()); + } else { + printf("1..0 # SKIP "); + } + if (msg) { errno = saved_errno; vprintf(msg, args); va_end(args); - } else { - ksft_print_cnts(); } + if (ksft_test_num()) + ksft_print_cnts(); exit(KSFT_SKIP); } diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index 676b3a8b114d..cc9c846585f0 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -53,6 +53,10 @@ run_one() settings="$BASE_DIR/$DIR/settings" if [ -r "$settings" ] ; then while read line ; do + # Skip comments. + if echo "$line" | grep -q '^#'; then + continue + fi field=$(echo "$line" | cut -d= -f1) value=$(echo "$line" | cut -d= -f2-) eval "kselftest_$field"="$value" @@ -77,10 +81,10 @@ run_one() echo "ok $test_num $TEST_HDR_MSG") || (rc=$?; \ if [ $rc -eq $skip_rc ]; then \ - echo "not ok $test_num $TEST_HDR_MSG # SKIP" + echo "ok $test_num $TEST_HDR_MSG # SKIP" elif [ $rc -eq $timeout_rc ]; then \ echo "#" - echo "not ok $test_num $TEST_HDR_MSG # TIMEOUT" + echo "not ok $test_num $TEST_HDR_MSG # TIMEOUT $kselftest_timeout seconds" else echo "not ok $test_num $TEST_HDR_MSG # exit=$rc" fi) diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index c9f03ef93338..4f78e4805633 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -50,7 +50,9 @@ #ifndef __KSELFTEST_HARNESS_H #define __KSELFTEST_HARNESS_H +#ifndef _GNU_SOURCE #define _GNU_SOURCE +#endif #include <asm/types.h> #include <errno.h> #include <stdbool.h> @@ -58,10 +60,13 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <sys/mman.h> #include <sys/types.h> #include <sys/wait.h> #include <unistd.h> +#include "kselftest.h" + #define TEST_TIMEOUT_DEFAULT 30 /* Utilities exposed to the test definitions */ @@ -104,26 +109,28 @@ /* Unconditional logger for internal use. */ #define __TH_LOG(fmt, ...) \ - fprintf(TH_LOG_STREAM, "%s:%d:%s:" fmt "\n", \ + fprintf(TH_LOG_STREAM, "# %s:%d:%s:" fmt "\n", \ __FILE__, __LINE__, _metadata->name, ##__VA_ARGS__) /** - * XFAIL(statement, fmt, ...) + * SKIP(statement, fmt, ...) * - * @statement: statement to run after reporting XFAIL + * @statement: statement to run after reporting SKIP * @fmt: format string * @...: optional arguments * - * This forces a "pass" after reporting a failure with an XFAIL prefix, + * This forces a "pass" after reporting why something is being skipped * and runs "statement", which is usually "return" or "goto skip". */ -#define XFAIL(statement, fmt, ...) do { \ +#define SKIP(statement, fmt, ...) do { \ + snprintf(_metadata->results->reason, \ + sizeof(_metadata->results->reason), fmt, ##__VA_ARGS__); \ if (TH_LOG_ENABLED) { \ - fprintf(TH_LOG_STREAM, "[ XFAIL! ] " fmt "\n", \ - ##__VA_ARGS__); \ + fprintf(TH_LOG_STREAM, "# SKIP %s\n", \ + _metadata->results->reason); \ } \ - /* TODO: find a way to pass xfail to test runner process. */ \ _metadata->passed = 1; \ + _metadata->skip = 1; \ _metadata->trigger = 0; \ statement; \ } while (0) @@ -195,8 +202,9 @@ * * .. code-block:: c * - * FIXTURE_DATA(datatype name) + * FIXTURE_DATA(datatype_name) * + * Almost always, you want just FIXTURE() instead (see below). * This call may be used when the type of the fixture data * is needed. In general, this should not be needed unless * the *self* is being passed to a helper directly. @@ -211,7 +219,7 @@ * * .. code-block:: c * - * FIXTURE(datatype name) { + * FIXTURE(fixture_name) { * type property1; * ... * }; @@ -238,7 +246,7 @@ * * .. code-block:: c * - * FIXTURE_SETUP(fixture name) { implementation } + * FIXTURE_SETUP(fixture_name) { implementation } * * Populates the required "setup" function for a fixture. An instance of the * datatype defined with FIXTURE_DATA() will be exposed as *self* for the @@ -264,7 +272,7 @@ * * .. code-block:: c * - * FIXTURE_TEARDOWN(fixture name) { implementation } + * FIXTURE_TEARDOWN(fixture_name) { implementation } * * Populates the required "teardown" function for a fixture. An instance of the * datatype defined with FIXTURE_DATA() will be exposed as *self* for the @@ -285,7 +293,7 @@ * * .. code-block:: c * - * FIXTURE_VARIANT(datatype name) { + * FIXTURE_VARIANT(fixture_name) { * type property1; * ... * }; @@ -305,8 +313,8 @@ * * .. code-block:: c * - * FIXTURE_ADD(datatype name) { - * .property1 = val1; + * FIXTURE_VARIANT_ADD(fixture_name, variant_name) { + * .property1 = val1, * ... * }; * @@ -672,20 +680,53 @@ __bail(_assert, _metadata->no_print, _metadata->step)) #define __INC_STEP(_metadata) \ - if (_metadata->passed && _metadata->step < 255) \ + /* Keep "step" below 255 (which is used for "SKIP" reporting). */ \ + if (_metadata->passed && _metadata->step < 253) \ _metadata->step++; +#define is_signed_type(var) (!!(((__typeof__(var))(-1)) < (__typeof__(var))1)) + #define __EXPECT(_expected, _expected_str, _seen, _seen_str, _t, _assert) do { \ /* Avoid multiple evaluation of the cases */ \ __typeof__(_expected) __exp = (_expected); \ __typeof__(_seen) __seen = (_seen); \ if (_assert) __INC_STEP(_metadata); \ if (!(__exp _t __seen)) { \ - unsigned long long __exp_print = (uintptr_t)__exp; \ - unsigned long long __seen_print = (uintptr_t)__seen; \ - __TH_LOG("Expected %s (%llu) %s %s (%llu)", \ - _expected_str, __exp_print, #_t, \ - _seen_str, __seen_print); \ + /* Report with actual signedness to avoid weird output. */ \ + switch (is_signed_type(__exp) * 2 + is_signed_type(__seen)) { \ + case 0: { \ + unsigned long long __exp_print = (uintptr_t)__exp; \ + unsigned long long __seen_print = (uintptr_t)__seen; \ + __TH_LOG("Expected %s (%llu) %s %s (%llu)", \ + _expected_str, __exp_print, #_t, \ + _seen_str, __seen_print); \ + break; \ + } \ + case 1: { \ + unsigned long long __exp_print = (uintptr_t)__exp; \ + long long __seen_print = (intptr_t)__seen; \ + __TH_LOG("Expected %s (%llu) %s %s (%lld)", \ + _expected_str, __exp_print, #_t, \ + _seen_str, __seen_print); \ + break; \ + } \ + case 2: { \ + long long __exp_print = (intptr_t)__exp; \ + unsigned long long __seen_print = (uintptr_t)__seen; \ + __TH_LOG("Expected %s (%lld) %s %s (%llu)", \ + _expected_str, __exp_print, #_t, \ + _seen_str, __seen_print); \ + break; \ + } \ + case 3: { \ + long long __exp_print = (intptr_t)__exp; \ + long long __seen_print = (intptr_t)__seen; \ + __TH_LOG("Expected %s (%lld) %s %s (%lld)", \ + _expected_str, __exp_print, #_t, \ + _seen_str, __seen_print); \ + break; \ + } \ + } \ _metadata->passed = 0; \ /* Ensure the optional handler is triggered */ \ _metadata->trigger = 1; \ @@ -726,6 +767,10 @@ } \ } +struct __test_results { + char reason[1024]; /* Reason for test result */ +}; + struct __test_metadata; struct __fixture_variant_metadata; @@ -773,11 +818,13 @@ struct __test_metadata { struct __fixture_metadata *fixture; int termsig; int passed; + int skip; /* did SKIP get used? */ int trigger; /* extra handler after the evaluation */ int timeout; /* seconds to wait for test timeout */ bool timed_out; /* did this test timeout instead of exiting? */ __u8 step; bool no_print; /* manual trigger when TH_LOG_STREAM is not available */ + struct __test_results *results; struct __test_metadata *prev, *next; }; @@ -813,12 +860,12 @@ static void __timeout_handler(int sig, siginfo_t *info, void *ucontext) /* Sanity check handler execution environment. */ if (!t) { fprintf(TH_LOG_STREAM, - "no active test in SIGALRM handler!?\n"); + "# no active test in SIGALRM handler!?\n"); abort(); } if (sig != SIGALRM || sig != info->si_signo) { fprintf(TH_LOG_STREAM, - "%s: SIGALRM handler caught signal %d!?\n", + "# %s: SIGALRM handler caught signal %d!?\n", t->name, sig != SIGALRM ? sig : info->si_signo); abort(); } @@ -839,7 +886,7 @@ void __wait_for_test(struct __test_metadata *t) if (sigaction(SIGALRM, &action, &saved_action)) { t->passed = 0; fprintf(TH_LOG_STREAM, - "%s: unable to install SIGALRM handler\n", + "# %s: unable to install SIGALRM handler\n", t->name); return; } @@ -851,7 +898,7 @@ void __wait_for_test(struct __test_metadata *t) if (sigaction(SIGALRM, &saved_action, NULL)) { t->passed = 0; fprintf(TH_LOG_STREAM, - "%s: unable to uninstall SIGALRM handler\n", + "# %s: unable to uninstall SIGALRM handler\n", t->name); return; } @@ -860,39 +907,51 @@ void __wait_for_test(struct __test_metadata *t) if (t->timed_out) { t->passed = 0; fprintf(TH_LOG_STREAM, - "%s: Test terminated by timeout\n", t->name); + "# %s: Test terminated by timeout\n", t->name); } else if (WIFEXITED(status)) { - t->passed = t->termsig == -1 ? !WEXITSTATUS(status) : 0; if (t->termsig != -1) { + t->passed = 0; fprintf(TH_LOG_STREAM, - "%s: Test exited normally " - "instead of by signal (code: %d)\n", - t->name, - WEXITSTATUS(status)); - } else if (!t->passed) { - fprintf(TH_LOG_STREAM, - "%s: Test failed at step #%d\n", + "# %s: Test exited normally instead of by signal (code: %d)\n", t->name, WEXITSTATUS(status)); + } else { + switch (WEXITSTATUS(status)) { + /* Success */ + case 0: + t->passed = 1; + break; + /* SKIP */ + case 255: + t->passed = 1; + t->skip = 1; + break; + /* Other failure, assume step report. */ + default: + t->passed = 0; + fprintf(TH_LOG_STREAM, + "# %s: Test failed at step #%d\n", + t->name, + WEXITSTATUS(status)); + } } } else if (WIFSIGNALED(status)) { t->passed = 0; if (WTERMSIG(status) == SIGABRT) { fprintf(TH_LOG_STREAM, - "%s: Test terminated by assertion\n", + "# %s: Test terminated by assertion\n", t->name); } else if (WTERMSIG(status) == t->termsig) { t->passed = 1; } else { fprintf(TH_LOG_STREAM, - "%s: Test terminated unexpectedly " - "by signal %d\n", + "# %s: Test terminated unexpectedly by signal %d\n", t->name, WTERMSIG(status)); } } else { fprintf(TH_LOG_STREAM, - "%s: Test ended in some other way [%u]\n", + "# %s: Test ended in some other way [%u]\n", t->name, status); } @@ -904,25 +963,39 @@ void __run_test(struct __fixture_metadata *f, { /* reset test struct */ t->passed = 1; + t->skip = 0; t->trigger = 0; t->step = 0; t->no_print = 0; + memset(t->results->reason, 0, sizeof(t->results->reason)); - printf("[ RUN ] %s%s%s.%s\n", + ksft_print_msg(" RUN %s%s%s.%s ...\n", f->name, variant->name[0] ? "." : "", variant->name, t->name); t->pid = fork(); if (t->pid < 0) { - printf("ERROR SPAWNING TEST CHILD\n"); + ksft_print_msg("ERROR SPAWNING TEST CHILD\n"); t->passed = 0; } else if (t->pid == 0) { t->fn(t, variant); - /* return the step that failed or 0 */ - _exit(t->passed ? 0 : t->step); + if (t->skip) + _exit(255); + /* Pass is exit 0 */ + if (t->passed) + _exit(0); + /* Something else happened, report the step. */ + _exit(t->step); } else { __wait_for_test(t); } - printf("[ %4s ] %s%s%s.%s\n", (t->passed ? "OK" : "FAIL"), + ksft_print_msg(" %4s %s%s%s.%s\n", t->passed ? "OK" : "FAIL", f->name, variant->name[0] ? "." : "", variant->name, t->name); + + if (t->skip) + ksft_test_result_skip("%s\n", t->results->reason[0] ? + t->results->reason : "unknown"); + else + ksft_test_result(t->passed, "%s%s%s.%s\n", + f->name, variant->name[0] ? "." : "", variant->name, t->name); } static int test_harness_run(int __attribute__((unused)) argc, @@ -931,6 +1004,7 @@ static int test_harness_run(int __attribute__((unused)) argc, struct __fixture_variant_metadata no_variant = { .name = "", }; struct __fixture_variant_metadata *v; struct __fixture_metadata *f; + struct __test_results *results; struct __test_metadata *t; int ret = 0; unsigned int case_count = 0, test_count = 0; @@ -945,14 +1019,20 @@ static int test_harness_run(int __attribute__((unused)) argc, } } - /* TODO(wad) add optional arguments similar to gtest. */ - printf("[==========] Running %u tests from %u test cases.\n", + results = mmap(NULL, sizeof(*results), PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + + ksft_print_header(); + ksft_set_plan(test_count); + ksft_print_msg("Starting %u tests from %u test cases.\n", test_count, case_count); for (f = __fixture_list; f; f = f->next) { for (v = f->variant ?: &no_variant; v; v = v->next) { for (t = f->tests; t; t = t->next) { count++; + t->results = results; __run_test(f, v, t); + t->results = NULL; if (t->passed) pass_count++; else @@ -960,9 +1040,14 @@ static int test_harness_run(int __attribute__((unused)) argc, } } } - printf("[==========] %u / %u tests passed.\n", pass_count, count); - printf("[ %s ]\n", (ret ? "FAILED" : "PASSED")); - return ret; + munmap(results, sizeof(*results)); + + ksft_print_msg("%s: %u / %u tests passed.\n", ret ? "FAILED" : "PASSED", + pass_count, count); + ksft_exit(ret == 0); + + /* unreachable */ + return KSFT_FAIL; } static void __attribute__((constructor)) __constructor_order_first(void) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c index 54cdefdfb49d..d59f3eb67c8f 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c @@ -76,10 +76,8 @@ void set_default_state(struct kvm_nested_state *state) void set_default_vmx_state(struct kvm_nested_state *state, int size) { memset(state, 0, size); - state->flags = KVM_STATE_NESTED_GUEST_MODE | - KVM_STATE_NESTED_RUN_PENDING; if (have_evmcs) - state->flags |= KVM_STATE_NESTED_EVMCS; + state->flags = KVM_STATE_NESTED_EVMCS; state->format = 0; state->size = size; state->hdr.vmx.vmxon_pa = 0x1000; @@ -148,6 +146,11 @@ void test_vmx_nested_state(struct kvm_vm *vm) state->hdr.vmx.smm.flags = 1; test_nested_state_expect_einval(vm, state); + /* Invalid flags are rejected. */ + set_default_vmx_state(state, state_sz); + state->hdr.vmx.flags = ~0; + test_nested_state_expect_einval(vm, state); + /* It is invalid to have vmxon_pa == -1ull and vmcs_pa != -1ull. */ set_default_vmx_state(state, state_sz); state->hdr.vmx.vmxon_pa = -1ull; @@ -185,20 +188,41 @@ void test_vmx_nested_state(struct kvm_vm *vm) state->hdr.vmx.smm.flags = KVM_STATE_NESTED_SMM_GUEST_MODE; test_nested_state_expect_einval(vm, state); - /* Size must be large enough to fit kvm_nested_state and vmcs12. */ + /* + * Size must be large enough to fit kvm_nested_state and vmcs12 + * if VMCS12 physical address is set + */ set_default_vmx_state(state, state_sz); state->size = sizeof(*state); + state->flags = 0; + test_nested_state_expect_einval(vm, state); + + set_default_vmx_state(state, state_sz); + state->size = sizeof(*state); + state->flags = 0; + state->hdr.vmx.vmcs12_pa = -1; test_nested_state(vm, state); - /* vmxon_pa cannot be the same address as vmcs_pa. */ + /* + * KVM_SET_NESTED_STATE succeeds with invalid VMCS + * contents but L2 not running. + */ set_default_vmx_state(state, state_sz); - state->hdr.vmx.vmxon_pa = 0; - state->hdr.vmx.vmcs12_pa = 0; + state->flags = 0; + test_nested_state(vm, state); + + /* Invalid flags are rejected, even if no VMCS loaded. */ + set_default_vmx_state(state, state_sz); + state->size = sizeof(*state); + state->flags = 0; + state->hdr.vmx.vmcs12_pa = -1; + state->hdr.vmx.flags = ~0; test_nested_state_expect_einval(vm, state); - /* The revision id for vmcs12 must be VMCS12_REVISION. */ + /* vmxon_pa cannot be the same address as vmcs_pa. */ set_default_vmx_state(state, state_sz); - set_revision_id_for_vmcs12(state, 0); + state->hdr.vmx.vmxon_pa = 0; + state->hdr.vmx.vmcs12_pa = 0; test_nested_state_expect_einval(vm, state); /* diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index b0556c752443..7a17ea815736 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -59,9 +59,8 @@ else all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) endif -.ONESHELL: define RUN_TESTS - @BASE_DIR="$(selfdir)"; \ + BASE_DIR="$(selfdir)"; \ . $(selfdir)/kselftest/runner.sh; \ if [ "X$(summary)" != "X" ]; then \ per_test_logging=1; \ @@ -71,22 +70,21 @@ endef run_tests: all ifdef building_out_of_srctree - @if [ "X$(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)" != "X" ]; then - @rsync -aq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT) + @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ + rsync -aq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT); \ fi - @if [ "X$(TEST_PROGS)" != "X" ]; then - $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(OUTPUT)/$(TEST_PROGS)) - else - $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS)) + @if [ "X$(TEST_PROGS)" != "X" ]; then \ + $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(OUTPUT)/$(TEST_PROGS)) ; \ + else \ + $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS)); \ fi else - $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS)) + @$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS)) endif define INSTALL_SINGLE_RULE $(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH)) - $(if $(INSTALL_LIST),@echo rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/) - $(if $(INSTALL_LIST),@rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/) + $(if $(INSTALL_LIST),rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/) endef define INSTALL_RULE diff --git a/tools/testing/selftests/lkdtm/run.sh b/tools/testing/selftests/lkdtm/run.sh index ee64ff8df8f4..8383eb89d88a 100755 --- a/tools/testing/selftests/lkdtm/run.sh +++ b/tools/testing/selftests/lkdtm/run.sh @@ -8,6 +8,7 @@ # set -e TRIGGER=/sys/kernel/debug/provoke-crash/DIRECT +CLEAR_ONCE=/sys/kernel/debug/clear_warn_once KSELFTEST_SKIP_TEST=4 # Verify we have LKDTM available in the kernel. @@ -67,6 +68,11 @@ cleanup() { } trap cleanup EXIT +# Reset WARN_ONCE counters so we trip it each time this runs. +if [ -w $CLEAR_ONCE ] ; then + echo 1 > $CLEAR_ONCE +fi + # Save existing dmesg so we can detect new content below dmesg > "$DMESG" diff --git a/tools/testing/selftests/lkdtm/tests.txt b/tools/testing/selftests/lkdtm/tests.txt index 92ca32143ae5..9d266e79c6a2 100644 --- a/tools/testing/selftests/lkdtm/tests.txt +++ b/tools/testing/selftests/lkdtm/tests.txt @@ -14,6 +14,7 @@ STACK_GUARD_PAGE_LEADING STACK_GUARD_PAGE_TRAILING UNSET_SMEP CR4 bits went missing DOUBLE_FAULT +CORRUPT_PAC UNALIGNED_LOAD_STORE_WRITE #OVERWRITE_ALLOCATION Corrupts memory on failure #WRITE_AFTER_FREE Corrupts memory on failure diff --git a/tools/testing/selftests/pid_namespace/regression_enomem.c b/tools/testing/selftests/pid_namespace/regression_enomem.c index 73d532556d17..7d84097ad45c 100644 --- a/tools/testing/selftests/pid_namespace/regression_enomem.c +++ b/tools/testing/selftests/pid_namespace/regression_enomem.c @@ -11,7 +11,6 @@ #include <syscall.h> #include <sys/wait.h> -#include "../kselftest.h" #include "../kselftest_harness.h" #include "../pidfd/pidfd.h" diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h index 8d728eda783d..a2c80914e3dc 100644 --- a/tools/testing/selftests/pidfd/pidfd.h +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -22,6 +22,10 @@ #define P_PIDFD 3 #endif +#ifndef CLONE_NEWTIME +#define CLONE_NEWTIME 0x00000080 +#endif + #ifndef CLONE_PIDFD #define CLONE_PIDFD 0x00001000 #endif diff --git a/tools/testing/selftests/pidfd/pidfd_getfd_test.c b/tools/testing/selftests/pidfd/pidfd_getfd_test.c index 84b65ecccb04..7758c98be015 100644 --- a/tools/testing/selftests/pidfd/pidfd_getfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_getfd_test.c @@ -18,7 +18,6 @@ #include <linux/kcmp.h> #include "pidfd.h" -#include "../kselftest.h" #include "../kselftest_harness.h" /* diff --git a/tools/testing/selftests/pidfd/pidfd_setns_test.c b/tools/testing/selftests/pidfd/pidfd_setns_test.c index 9418108eae13..7dca1aa4672d 100644 --- a/tools/testing/selftests/pidfd/pidfd_setns_test.c +++ b/tools/testing/selftests/pidfd/pidfd_setns_test.c @@ -20,7 +20,6 @@ #include "pidfd.h" #include "../clone3/clone3_selftests.h" -#include "../kselftest.h" #include "../kselftest_harness.h" enum { @@ -32,6 +31,7 @@ enum { PIDFD_NS_NET, PIDFD_NS_CGROUP, PIDFD_NS_PIDCLD, + PIDFD_NS_TIME, PIDFD_NS_MAX }; @@ -47,6 +47,7 @@ const struct ns_info { [PIDFD_NS_NET] = { "net", CLONE_NEWNET, }, [PIDFD_NS_CGROUP] = { "cgroup", CLONE_NEWCGROUP, }, [PIDFD_NS_PIDCLD] = { "pid_for_children", 0, }, + [PIDFD_NS_TIME] = { "time", CLONE_NEWTIME, }, }; FIXTURE(current_nsset) @@ -83,9 +84,49 @@ pid_t create_child(int *pidfd, unsigned flags) return sys_clone3(&args, sizeof(struct clone_args)); } +static bool switch_timens(void) +{ + int fd, ret; + + if (unshare(CLONE_NEWTIME)) + return false; + + fd = open("/proc/self/ns/time_for_children", O_RDONLY | O_CLOEXEC); + if (fd < 0) + return false; + + ret = setns(fd, CLONE_NEWTIME); + close(fd); + return ret == 0; +} + +static ssize_t read_nointr(int fd, void *buf, size_t count) +{ + ssize_t ret; + + do { + ret = read(fd, buf, count); + } while (ret < 0 && errno == EINTR); + + return ret; +} + +static ssize_t write_nointr(int fd, const void *buf, size_t count) +{ + ssize_t ret; + + do { + ret = write(fd, buf, count); + } while (ret < 0 && errno == EINTR); + + return ret; +} + FIXTURE_SETUP(current_nsset) { int i, proc_fd, ret; + int ipc_sockets[2]; + char c; for (i = 0; i < PIDFD_NS_MAX; i++) { self->nsfds[i] = -EBADF; @@ -130,6 +171,9 @@ FIXTURE_SETUP(current_nsset) TH_LOG("%m - Failed to open pidfd for process %d", self->pid); } + ret = socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + EXPECT_EQ(ret, 0); + /* Create tasks that will be stopped. */ self->child_pid1 = create_child(&self->child_pidfd1, CLONE_NEWUSER | CLONE_NEWNS | @@ -139,10 +183,27 @@ FIXTURE_SETUP(current_nsset) EXPECT_GE(self->child_pid1, 0); if (self->child_pid1 == 0) { + close(ipc_sockets[0]); + + if (!switch_timens()) + _exit(EXIT_FAILURE); + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + _exit(EXIT_FAILURE); + + close(ipc_sockets[1]); + pause(); _exit(EXIT_SUCCESS); } + close(ipc_sockets[1]); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + close(ipc_sockets[0]); + + ret = socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + EXPECT_EQ(ret, 0); + self->child_pid2 = create_child(&self->child_pidfd2, CLONE_NEWUSER | CLONE_NEWNS | CLONE_NEWCGROUP | CLONE_NEWIPC | @@ -151,10 +212,24 @@ FIXTURE_SETUP(current_nsset) EXPECT_GE(self->child_pid2, 0); if (self->child_pid2 == 0) { + close(ipc_sockets[0]); + + if (!switch_timens()) + _exit(EXIT_FAILURE); + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) + _exit(EXIT_FAILURE); + + close(ipc_sockets[1]); + pause(); _exit(EXIT_SUCCESS); } + close(ipc_sockets[1]); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + close(ipc_sockets[0]); + for (i = 0; i < PIDFD_NS_MAX; i++) { char p[100]; diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index 7aff2d3b42c0..c585aaa2acd8 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -8,6 +8,7 @@ #include <sched.h> #include <signal.h> #include <stdio.h> +#include <stdbool.h> #include <stdlib.h> #include <string.h> #include <syscall.h> @@ -27,6 +28,8 @@ #define MAX_EVENTS 5 +static bool have_pidfd_send_signal; + static pid_t pidfd_clone(int flags, int *pidfd, int (*fn)(void *)) { size_t stack_size = 1024; @@ -56,6 +59,13 @@ static int test_pidfd_send_signal_simple_success(void) int pidfd, ret; const char *test_name = "pidfd_send_signal send SIGUSR1"; + if (!have_pidfd_send_signal) { + ksft_test_result_skip( + "%s test: pidfd_send_signal() syscall not supported\n", + test_name); + return 0; + } + pidfd = open("/proc/self", O_DIRECTORY | O_CLOEXEC); if (pidfd < 0) ksft_exit_fail_msg( @@ -86,6 +96,13 @@ static int test_pidfd_send_signal_exited_fail(void) pid_t pid; const char *test_name = "pidfd_send_signal signal exited process"; + if (!have_pidfd_send_signal) { + ksft_test_result_skip( + "%s test: pidfd_send_signal() syscall not supported\n", + test_name); + return 0; + } + pid = fork(); if (pid < 0) ksft_exit_fail_msg("%s test: Failed to create new process\n", @@ -137,16 +154,34 @@ static int test_pidfd_send_signal_recycled_pid_fail(void) pid_t pid1; const char *test_name = "pidfd_send_signal signal recycled pid"; + if (!have_pidfd_send_signal) { + ksft_test_result_skip( + "%s test: pidfd_send_signal() syscall not supported\n", + test_name); + return 0; + } + ret = unshare(CLONE_NEWPID); - if (ret < 0) + if (ret < 0) { + if (errno == EPERM) { + ksft_test_result_skip("%s test: Unsharing pid namespace not permitted\n", + test_name); + return 0; + } ksft_exit_fail_msg("%s test: Failed to unshare pid namespace\n", test_name); + } ret = unshare(CLONE_NEWNS); - if (ret < 0) - ksft_exit_fail_msg( - "%s test: Failed to unshare mount namespace\n", - test_name); + if (ret < 0) { + if (errno == EPERM) { + ksft_test_result_skip("%s test: Unsharing mount namespace not permitted\n", + test_name); + return 0; + } + ksft_exit_fail_msg("%s test: Failed to unshare mount namespace\n", + test_name); + } ret = mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0); if (ret < 0) @@ -325,15 +360,17 @@ static int test_pidfd_send_signal_syscall_support(void) ret = sys_pidfd_send_signal(pidfd, 0, NULL, 0); if (ret < 0) { - if (errno == ENOSYS) - ksft_exit_skip( + if (errno == ENOSYS) { + ksft_test_result_skip( "%s test: pidfd_send_signal() syscall not supported\n", test_name); - + return 0; + } ksft_exit_fail_msg("%s test: Failed to send signal\n", test_name); } + have_pidfd_send_signal = true; close(pidfd); ksft_test_result_pass( "%s test: pidfd_send_signal() syscall is supported. Tests can be executed\n", @@ -521,7 +558,7 @@ static void test_pidfd_poll_leader_exit(int use_waitpid) int main(int argc, char **argv) { ksft_print_header(); - ksft_set_plan(4); + ksft_set_plan(8); test_pidfd_poll_exec(0); test_pidfd_poll_exec(1); diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh index 93e80a42249a..d6e5ce084b1c 100755 --- a/tools/testing/selftests/rcutorture/bin/configinit.sh +++ b/tools/testing/selftests/rcutorture/bin/configinit.sh @@ -32,11 +32,11 @@ if test -z "$TORTURE_TRUST_MAKE" then make clean > $resdir/Make.clean 2>&1 fi -make $TORTURE_DEFCONFIG > $resdir/Make.defconfig.out 2>&1 +make $TORTURE_KMAKE_ARG $TORTURE_DEFCONFIG > $resdir/Make.defconfig.out 2>&1 mv .config .config.sav sh $T/upd.sh < .config.sav > .config cp .config .config.new -yes '' | make oldconfig > $resdir/Make.oldconfig.out 2> $resdir/Make.oldconfig.err +yes '' | make $TORTURE_KMAKE_ARG oldconfig > $resdir/Make.oldconfig.out 2> $resdir/Make.oldconfig.err # verify new config matches specification. configcheck.sh .config $c diff --git a/tools/testing/selftests/rcutorture/bin/console-badness.sh b/tools/testing/selftests/rcutorture/bin/console-badness.sh new file mode 100755 index 000000000000..0e4c0b2eb7f0 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/console-badness.sh @@ -0,0 +1,16 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Scan standard input for error messages, dumping any found to standard +# output. +# +# Usage: console-badness.sh +# +# Copyright (C) 2020 Facebook, Inc. +# +# Authors: Paul E. McKenney <paulmck@kernel.org> + +egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for|!!!' | +grep -v 'ODEBUG: ' | +grep -v 'This means that this is a DEBUG kernel and it is' | +grep -v 'Warning: unable to open an initial console' diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh index 12810229fddc..51f3464b96d3 100644 --- a/tools/testing/selftests/rcutorture/bin/functions.sh +++ b/tools/testing/selftests/rcutorture/bin/functions.sh @@ -215,9 +215,6 @@ identify_qemu_args () { then echo -device spapr-vlan,netdev=net0,mac=$TORTURE_QEMU_MAC echo -netdev bridge,br=br0,id=net0 - elif test -n "$TORTURE_QEMU_INTERACTIVE" - then - echo -net nic -net user fi ;; esac @@ -234,7 +231,7 @@ identify_qemu_args () { # Returns the number of virtual CPUs available to the aggregate of the # guest OSes. identify_qemu_vcpus () { - lscpu | grep '^CPU(s):' | sed -e 's/CPU(s)://' + lscpu | grep '^CPU(s):' | sed -e 's/CPU(s)://' -e 's/[ ]*//g' } # print_bug @@ -275,3 +272,21 @@ specify_qemu_cpus () { esac fi } + +# specify_qemu_net qemu-args +# +# Appends a string containing "-net none" to qemu-args, unless the incoming +# qemu-args already contains "-smp" or unless the TORTURE_QEMU_INTERACTIVE +# environment variable is set, in which case the string that is be added is +# instead "-net nic -net user". +specify_qemu_net () { + if echo $1 | grep -q -e -net + then + echo $1 + elif test -n "$TORTURE_QEMU_INTERACTIVE" + then + echo $1 -net nic -net user + else + echo $1 -net none + fi +} diff --git a/tools/testing/selftests/rcutorture/bin/jitter.sh b/tools/testing/selftests/rcutorture/bin/jitter.sh index 30cb5b27d32e..188b864bc4bf 100755 --- a/tools/testing/selftests/rcutorture/bin/jitter.sh +++ b/tools/testing/selftests/rcutorture/bin/jitter.sh @@ -46,6 +46,12 @@ do exit 0; fi + # Check for stop request. + if test -f "$TORTURE_STOPFILE" + then + exit 1; + fi + # Set affinity to randomly selected online CPU if cpus=`grep 1 /sys/devices/system/cpu/*/online 2>&1 | sed -e 's,/[^/]*$,,' -e 's/^[^0-9]*//'` diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh index 18d6518504ee..115e1822b26f 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh @@ -9,6 +9,12 @@ # # Authors: Paul E. McKenney <paulmck@linux.ibm.com> +if test -f "$TORTURE_STOPFILE" +then + echo "kvm-build.sh early exit due to run STOP request" + exit 1 +fi + config_template=${1} if test -z "$config_template" -o ! -f "$config_template" -o ! -r "$config_template" then diff --git a/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh new file mode 100755 index 000000000000..6e65c134e5f1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh @@ -0,0 +1,108 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0+ +# +# Run a group of kvm.sh tests on the specified commits. This currently +# unconditionally does three-minute runs on each scenario in CFLIST, +# taking advantage of all available CPUs and trusting the "make" utility. +# In the short term, adjustments can be made by editing this script and +# CFLIST. If some adjustments appear to have ongoing value, this script +# might grow some command-line arguments. +# +# Usage: kvm-check-branches.sh commit1 commit2..commit3 commit4 ... +# +# This script considers its arguments one at a time. If more elaborate +# specification of commits is needed, please use "git rev-list" to +# produce something that this simple script can understand. The reason +# for retaining the simplicity is that it allows the user to more easily +# see which commit came from which branch. +# +# This script creates a yyyy.mm.dd-hh.mm.ss-group entry in the "res" +# directory. The calls to kvm.sh create the usual entries, but this script +# moves them under the yyyy.mm.dd-hh.mm.ss-group entry, each in its own +# directory numbered in run order, that is, "0001", "0002", and so on. +# For successful runs, the large build artifacts are removed. Doing this +# reduces the disk space required by about two orders of magnitude for +# successful runs. +# +# Copyright (C) Facebook, 2020 +# +# Authors: Paul E. McKenney <paulmck@kernel.org> + +if ! git status > /dev/null 2>&1 +then + echo '!!!' This script needs to run in a git archive. 1>&2 + echo '!!!' Giving up. 1>&2 + exit 1 +fi + +# Remember where we started so that we can get back and the end. +curcommit="`git status | head -1 | awk '{ print $NF }'`" + +nfail=0 +ntry=0 +resdir="tools/testing/selftests/rcutorture/res" +ds="`date +%Y.%m.%d-%H.%M.%S`-group" +if ! test -e $resdir +then + mkdir $resdir || : +fi +mkdir $resdir/$ds +echo Results directory: $resdir/$ds + +KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM +PATH=${KVM}/bin:$PATH; export PATH +. functions.sh +cpus="`identify_qemu_vcpus`" +echo Using up to $cpus CPUs. + +# Each pass through this loop does one command-line argument. +for gitbr in $@ +do + echo ' --- git branch ' $gitbr + + # Each pass through this loop tests one commit. + for i in `git rev-list "$gitbr"` + do + ntry=`expr $ntry + 1` + idir=`awk -v ntry="$ntry" 'END { printf "%04d", ntry; }' < /dev/null` + echo ' --- commit ' $i from branch $gitbr + date + mkdir $resdir/$ds/$idir + echo $gitbr > $resdir/$ds/$idir/gitbr + echo $i >> $resdir/$ds/$idir/gitbr + + # Test the specified commit. + git checkout $i > $resdir/$ds/$idir/git-checkout.out 2>&1 + echo git checkout return code: $? "(Commit $ntry: $i)" + kvm.sh --cpus $cpus --duration 3 --trust-make > $resdir/$ds/$idir/kvm.sh.out 2>&1 + ret=$? + echo kvm.sh return code $ret for commit $i from branch $gitbr + + # Move the build products to their resting place. + runresdir="`grep -m 1 '^Results directory:' < $resdir/$ds/$idir/kvm.sh.out | sed -e 's/^Results directory://'`" + mv $runresdir $resdir/$ds/$idir + rrd="`echo $runresdir | sed -e 's,^.*/,,'`" + echo Run results: $resdir/$ds/$idir/$rrd + if test "$ret" -ne 0 + then + # Failure, so leave all evidence intact. + nfail=`expr $nfail + 1` + else + # Success, so remove large files to save about 1GB. + ( cd $resdir/$ds/$idir/$rrd; rm -f */vmlinux */bzImage */System.map */Module.symvers ) + fi + done +done +date + +# Go back to the original commit. +git checkout "$curcommit" + +if test $nfail -ne 0 +then + echo '!!! ' $nfail failures in $ntry 'runs!!!' + exit 1 +else + echo No failures in $ntry runs. + exit 0 +fi diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-refscale.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-refscale.sh new file mode 100755 index 000000000000..35a463dddffe --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-refscale.sh @@ -0,0 +1,71 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Analyze a given results directory for refscale performance measurements. +# +# Usage: kvm-recheck-refscale.sh resdir +# +# Copyright (C) IBM Corporation, 2016 +# +# Authors: Paul E. McKenney <paulmck@linux.ibm.com> + +i="$1" +if test -d "$i" -a -r "$i" +then + : +else + echo Unreadable results directory: $i + exit 1 +fi +PATH=`pwd`/tools/testing/selftests/rcutorture/bin:$PATH; export PATH +. functions.sh + +configfile=`echo $i | sed -e 's/^.*\///'` + +sed -e 's/^\[[^]]*]//' < $i/console.log | tr -d '\015' | +awk -v configfile="$configfile" ' +/^[ ]*Runs Time\(ns\) *$/ { + if (dataphase + 0 == 0) { + dataphase = 1; + # print configfile, $0; + } + next; +} + +/[^ ]*[0-9][0-9]* [0-9][0-9]*\.[0-9][0-9]*$/ { + if (dataphase == 1) { + # print $0; + readertimes[++n] = $2; + sum += $2; + } + next; +} + +{ + if (dataphase == 1) + dataphase == 2; + next; +} + +END { + print configfile " results:"; + newNR = asort(readertimes); + if (newNR <= 0) { + print "No refscale records found???" + exit; + } + medianidx = int(newNR / 2); + if (newNR == medianidx * 2) + medianvalue = (readertimes[medianidx - 1] + readertimes[medianidx]) / 2; + else + medianvalue = readertimes[medianidx]; + points = "Points:"; + for (i = 1; i <= newNR; i++) + points = points " " readertimes[i]; + print points; + print "Average reader duration: " sum / newNR " nanoseconds"; + print "Minimum reader duration: " readertimes[1]; + print "Median reader duration: " medianvalue; + print "Maximum reader duration: " readertimes[newNR]; + print "Computed from refscale printk output."; +}' diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh index 736f04749b90..840a4679a0d7 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh @@ -31,6 +31,7 @@ do head -1 $resdir/log fi TORTURE_SUITE="`cat $i/../TORTURE_SUITE`" + configfile=`echo $i | sed -e 's,^.*/,,'` rm -f $i/console.log.*.diags kvm-recheck-${TORTURE_SUITE}.sh $i if test -f "$i/qemu-retval" && test "`cat $i/qemu-retval`" -ne 0 && test "`cat $i/qemu-retval`" -ne 137 @@ -43,7 +44,8 @@ do then echo QEMU killed fi - configcheck.sh $i/.config $i/ConfigFragment + configcheck.sh $i/.config $i/ConfigFragment > $T 2>&1 + cat $T if test -r $i/Make.oldconfig.err then cat $i/Make.oldconfig.err @@ -55,15 +57,15 @@ do cat $i/Warnings fi else - if test -f "$i/qemu-cmd" - then - print_bug qemu failed - echo " $i" - elif test -f "$i/buildonly" + if test -f "$i/buildonly" then echo Build-only run, no boot/test configcheck.sh $i/.config $i/ConfigFragment parse-build.sh $i/Make.out $configfile + elif test -f "$i/qemu-cmd" + then + print_bug qemu failed + echo " $i" else print_bug Build failed echo " $i" @@ -72,7 +74,11 @@ do done if test -f "$rd/kcsan.sum" then - if test -s "$rd/kcsan.sum" + if grep -q CONFIG_KCSAN=y $T + then + echo "Compiler or architecture does not support KCSAN!" + echo Did you forget to switch your compiler with '--kmake-arg CC=<cc-that-supports-kcsan>'? + elif test -s "$rd/kcsan.sum" then echo KCSAN summary in $rd/kcsan.sum else diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index 6ff611c630d1..e07779a62634 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -124,7 +124,6 @@ seconds=$4 qemu_args=$5 boot_args=$6 -cd $KVM kstarttime=`gawk 'BEGIN { print systime() }' < /dev/null` if test -z "$TORTURE_BUILDONLY" then @@ -141,6 +140,7 @@ then cpu_count=$TORTURE_ALLOTED_CPUS fi qemu_args="`specify_qemu_cpus "$QEMU" "$qemu_args" "$cpu_count"`" +qemu_args="`specify_qemu_net "$qemu_args"`" # Generate architecture-specific and interaction-specific qemu arguments qemu_args="$qemu_args `identify_qemu_args "$QEMU" "$resdir/console.log"`" @@ -152,6 +152,7 @@ qemu_append="`identify_qemu_append "$QEMU"`" boot_args="`configfrag_boot_params "$boot_args" "$config_template"`" # Generate kernel-version-specific boot parameters boot_args="`per_version_boot_params "$boot_args" $resdir/.config $seconds`" +echo $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd if test -n "$TORTURE_BUILDONLY" then @@ -159,9 +160,16 @@ then touch $resdir/buildonly exit 0 fi + +# Decorate qemu-cmd with redirection, backgrounding, and PID capture +sed -e 's/$/ 2>\&1 \&/' < $resdir/qemu-cmd > $T/qemu-cmd +echo 'echo $! > $resdir/qemu_pid' >> $T/qemu-cmd + +# In case qemu refuses to run... echo "NOTE: $QEMU either did not run or was interactive" > $resdir/console.log -echo $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd -( $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append "$qemu_append $boot_args" > $resdir/qemu-output 2>&1 & echo $! > $resdir/qemu_pid; wait `cat $resdir/qemu_pid`; echo $? > $resdir/qemu-retval ) & + +# Attempt to run qemu +( . $T/qemu-cmd; wait `cat $resdir/qemu_pid`; echo $? > $resdir/qemu-retval ) & commandcompleted=0 sleep 10 # Give qemu's pid a chance to reach the file if test -s "$resdir/qemu_pid" @@ -181,7 +189,7 @@ do kruntime=`gawk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null` if test -z "$qemu_pid" || kill -0 "$qemu_pid" > /dev/null 2>&1 then - if test $kruntime -ge $seconds + if test $kruntime -ge $seconds -o -f "$TORTURE_STOPFILE" then break; fi @@ -210,10 +218,19 @@ then fi if test $commandcompleted -eq 0 -a -n "$qemu_pid" then - echo Grace period for qemu job at pid $qemu_pid + if ! test -f "$TORTURE_STOPFILE" + then + echo Grace period for qemu job at pid $qemu_pid + fi oldline="`tail $resdir/console.log`" while : do + if test -f "$TORTURE_STOPFILE" + then + echo "PID $qemu_pid killed due to run STOP request" >> $resdir/Warnings 2>&1 + kill -KILL $qemu_pid + break + fi kruntime=`gawk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null` if kill -0 $qemu_pid > /dev/null 2>&1 then diff --git a/tools/testing/selftests/rcutorture/bin/kvm-transform.sh b/tools/testing/selftests/rcutorture/bin/kvm-transform.sh new file mode 100755 index 000000000000..c45a953ef393 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/kvm-transform.sh @@ -0,0 +1,51 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Transform a qemu-cmd file to allow reuse. +# +# Usage: kvm-transform.sh bzImage console.log < qemu-cmd-in > qemu-cmd-out +# +# bzImage: Kernel and initrd from the same prior kvm.sh run. +# console.log: File into which to place console output. +# +# The original qemu-cmd file is provided on standard input. +# The transformed qemu-cmd file is on standard output. +# The transformation assumes that the qemu command is confined to a +# single line. It also assumes no whitespace in filenames. +# +# Copyright (C) 2020 Facebook, Inc. +# +# Authors: Paul E. McKenney <paulmck@kernel.org> + +image="$1" +if test -z "$image" +then + echo Need kernel image file. + exit 1 +fi +consolelog="$2" +if test -z "$consolelog" +then + echo "Need console log file name." + exit 1 +fi + +awk -v image="$image" -v consolelog="$consolelog" ' +{ + line = ""; + for (i = 1; i <= NF; i++) { + if (line == "") + line = $i; + else + line = line " " $i; + if ($i == "-serial") { + i++; + line = line " file:" consolelog; + } + if ($i == "-kernel") { + i++; + line = line " " image; + } + } + print line; +}' diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index c279cf9cb010..e655983b7429 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -73,6 +73,10 @@ usage () { while test $# -gt 0 do case "$1" in + --allcpus) + cpus=$TORTURE_ALLOTED_CPUS + max_cpus=$TORTURE_ALLOTED_CPUS + ;; --bootargs|--bootarg) checkarg --bootargs "(list of kernel boot arguments)" "$#" "$2" '.*' '^--' TORTURE_BOOTARGS="$2" @@ -180,13 +184,14 @@ do shift ;; --torture) - checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuperf\)$' '^--' + checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuperf\|refscale\)$' '^--' TORTURE_SUITE=$2 shift - if test "$TORTURE_SUITE" = rcuperf + if test "$TORTURE_SUITE" = rcuperf || test "$TORTURE_SUITE" = refscale then - # If you really want jitter for rcuperf, specify - # it after specifying rcuperf. (But why?) + # If you really want jitter for refscale or + # rcuperf, specify it after specifying the rcuperf + # or the refscale. (But why jitter in these cases?) jitter=0 fi ;; @@ -333,6 +338,8 @@ then mkdir -p "$resdir" || : fi mkdir $resdir/$ds +TORTURE_RESDIR="$resdir/$ds"; export TORTURE_RESDIR +TORTURE_STOPFILE="$resdir/$ds/STOP"; export TORTURE_STOPFILE echo Results directory: $resdir/$ds echo $scriptname $args touch $resdir/$ds/log @@ -497,3 +504,7 @@ fi # Tracing: trace_event=rcu:rcu_grace_period,rcu:rcu_future_grace_period,rcu:rcu_grace_period_init,rcu:rcu_nocb_wake,rcu:rcu_preempt_task,rcu:rcu_unlock_preempted_task,rcu:rcu_quiescent_state_report,rcu:rcu_fqs,rcu:rcu_callback,rcu:rcu_kfree_callback,rcu:rcu_batch_start,rcu:rcu_invoke_callback,rcu:rcu_invoke_kfree_callback,rcu:rcu_batch_end,rcu:rcu_torture_read,rcu:rcu_barrier # Function-graph tracing: ftrace=function_graph ftrace_graph_filter=sched_setaffinity,migration_cpu_stop # Also --kconfig "CONFIG_FUNCTION_TRACER=y CONFIG_FUNCTION_GRAPH_TRACER=y" +# Control buffer size: --bootargs trace_buf_size=3k +# Get trace-buffer dumps on all oopses: --bootargs ftrace_dump_on_oops +# Ditto, but dump only the oopsing CPU: --bootargs ftrace_dump_on_oops=orig_cpu +# Heavy-handed way to also dump on warnings: --bootargs panic_on_warn diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh index 4bf62d7b1cbc..71a9f43a3918 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-console.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh @@ -33,8 +33,8 @@ then fi cat /dev/null > $file.diags -# Check for proper termination, except that rcuperf runs don't indicate this. -if test "$TORTURE_SUITE" != rcuperf +# Check for proper termination, except for rcuperf and refscale. +if test "$TORTURE_SUITE" != rcuperf && test "$TORTURE_SUITE" != refscale then # check for abject failure @@ -44,11 +44,23 @@ then tail -1 | awk ' { - for (i=NF-8;i<=NF;i++) + normalexit = 1; + for (i=NF-8;i<=NF;i++) { + if (i <= 0 || i !~ /^[0-9]*$/) { + bangstring = $0; + gsub(/^\[[^]]*] /, "", bangstring); + print bangstring; + normalexit = 0; + exit 0; + } sum+=$i; + } } - END { print sum }'` - print_bug $title FAILURE, $nerrs instances + END { + if (normalexit) + print sum " instances" + }'` + print_bug $title FAILURE, $nerrs exit fi @@ -104,10 +116,7 @@ then fi fi | tee -a $file.diags -egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for' < $file | -grep -v 'ODEBUG: ' | -grep -v 'This means that this is a DEBUG kernel and it is' | -grep -v 'Warning: unable to open an initial console' > $T.diags +console-badness.sh < $file > $T.diags if test -s $T.diags then print_warning "Assertion failure in $file $title" diff --git a/tools/testing/selftests/rcutorture/configs/refscale/CFLIST b/tools/testing/selftests/rcutorture/configs/refscale/CFLIST new file mode 100644 index 000000000000..4d62eb4a39f9 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/CFLIST @@ -0,0 +1,2 @@ +NOPREEMPT +PREEMPT diff --git a/tools/testing/selftests/rcutorture/configs/refscale/CFcommon b/tools/testing/selftests/rcutorture/configs/refscale/CFcommon new file mode 100644 index 000000000000..a98b58b54bb1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/CFcommon @@ -0,0 +1,2 @@ +CONFIG_RCU_REF_SCALE_TEST=y +CONFIG_PRINTK_TIME=y diff --git a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT new file mode 100644 index 000000000000..1cd25b7314e3 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT @@ -0,0 +1,18 @@ +CONFIG_SMP=y +CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=n +#CHECK#CONFIG_PREEMPT_RCU=n +CONFIG_HZ_PERIODIC=n +CONFIG_NO_HZ_IDLE=y +CONFIG_NO_HZ_FULL=n +CONFIG_RCU_FAST_NO_HZ=n +CONFIG_HOTPLUG_CPU=n +CONFIG_SUSPEND=n +CONFIG_HIBERNATION=n +CONFIG_RCU_NOCB_CPU=n +CONFIG_DEBUG_LOCK_ALLOC=n +CONFIG_PROVE_LOCKING=n +CONFIG_RCU_BOOST=n +CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT new file mode 100644 index 000000000000..d10bc694f42c --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/PREEMPT @@ -0,0 +1,18 @@ +CONFIG_SMP=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y +#CHECK#CONFIG_PREEMPT_RCU=y +CONFIG_HZ_PERIODIC=n +CONFIG_NO_HZ_IDLE=y +CONFIG_NO_HZ_FULL=n +CONFIG_RCU_FAST_NO_HZ=n +CONFIG_HOTPLUG_CPU=n +CONFIG_SUSPEND=n +CONFIG_HIBERNATION=n +CONFIG_RCU_NOCB_CPU=n +CONFIG_DEBUG_LOCK_ALLOC=n +CONFIG_PROVE_LOCKING=n +CONFIG_RCU_BOOST=n +CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_RCU_EXPERT=y diff --git a/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh new file mode 100644 index 000000000000..321e82641287 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/refscale/ver_functions.sh @@ -0,0 +1,16 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Torture-suite-dependent shell functions for the rest of the scripts. +# +# Copyright (C) IBM Corporation, 2015 +# +# Authors: Paul E. McKenney <paulmck@linux.ibm.com> + +# per_version_boot_params bootparam-string config-file seconds +# +# Adds per-version torture-module parameters to kernels supporting them. +per_version_boot_params () { + echo $1 refscale.shutdown=1 \ + refscale.verbose=1 +} diff --git a/tools/testing/selftests/seccomp/config b/tools/testing/selftests/seccomp/config index db1e11b08c8a..64c19d8eba79 100644 --- a/tools/testing/selftests/seccomp/config +++ b/tools/testing/selftests/seccomp/config @@ -1,2 +1,3 @@ CONFIG_SECCOMP=y CONFIG_SECCOMP_FILTER=y +CONFIG_USER_NS=y diff --git a/tools/testing/selftests/seccomp/seccomp_benchmark.c b/tools/testing/selftests/seccomp/seccomp_benchmark.c index 5838c8697ec3..91f5a89cadac 100644 --- a/tools/testing/selftests/seccomp/seccomp_benchmark.c +++ b/tools/testing/selftests/seccomp/seccomp_benchmark.c @@ -18,9 +18,9 @@ unsigned long long timing(clockid_t clk_id, unsigned long long samples) { - pid_t pid, ret; - unsigned long long i; struct timespec start, finish; + unsigned long long i; + pid_t pid, ret; pid = getpid(); assert(clock_gettime(clk_id, &start) == 0); @@ -31,30 +31,43 @@ unsigned long long timing(clockid_t clk_id, unsigned long long samples) assert(clock_gettime(clk_id, &finish) == 0); i = finish.tv_sec - start.tv_sec; - i *= 1000000000; + i *= 1000000000ULL; i += finish.tv_nsec - start.tv_nsec; - printf("%lu.%09lu - %lu.%09lu = %llu\n", + printf("%lu.%09lu - %lu.%09lu = %llu (%.1fs)\n", finish.tv_sec, finish.tv_nsec, start.tv_sec, start.tv_nsec, - i); + i, (double)i / 1000000000.0); return i; } unsigned long long calibrate(void) { - unsigned long long i; - - printf("Calibrating reasonable sample size...\n"); + struct timespec start, finish; + unsigned long long i, samples, step = 9973; + pid_t pid, ret; + int seconds = 15; - for (i = 5; ; i++) { - unsigned long long samples = 1 << i; + printf("Calibrating sample size for %d seconds worth of syscalls ...\n", seconds); - /* Find something that takes more than 5 seconds to run. */ - if (timing(CLOCK_REALTIME, samples) / 1000000000ULL > 5) - return samples; - } + samples = 0; + pid = getpid(); + assert(clock_gettime(CLOCK_MONOTONIC, &start) == 0); + do { + for (i = 0; i < step; i++) { + ret = syscall(__NR_getpid); + assert(pid == ret); + } + assert(clock_gettime(CLOCK_MONOTONIC, &finish) == 0); + + samples += step; + i = finish.tv_sec - start.tv_sec; + i *= 1000000000ULL; + i += finish.tv_nsec - start.tv_nsec; + } while (i < 1000000000ULL); + + return samples * seconds; } int main(int argc, char *argv[]) @@ -68,32 +81,55 @@ int main(int argc, char *argv[]) }; long ret; unsigned long long samples; - unsigned long long native, filtered; + unsigned long long native, filter1, filter2; + + printf("Current BPF sysctl settings:\n"); + system("sysctl net.core.bpf_jit_enable"); + system("sysctl net.core.bpf_jit_harden"); if (argc > 1) samples = strtoull(argv[1], NULL, 0); else samples = calibrate(); - printf("Benchmarking %llu samples...\n", samples); + printf("Benchmarking %llu syscalls...\n", samples); + /* Native call */ native = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; printf("getpid native: %llu ns\n", native); ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); assert(ret == 0); + /* One filter */ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog); assert(ret == 0); - filtered = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; - printf("getpid RET_ALLOW: %llu ns\n", filtered); + filter1 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; + printf("getpid RET_ALLOW 1 filter: %llu ns\n", filter1); + + if (filter1 == native) + printf("No overhead measured!? Try running again with more samples.\n"); + + /* Two filters */ + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog); + assert(ret == 0); + + filter2 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; + printf("getpid RET_ALLOW 2 filters: %llu ns\n", filter2); + + /* Calculations */ + printf("Estimated total seccomp overhead for 1 filter: %llu ns\n", + filter1 - native); + + printf("Estimated total seccomp overhead for 2 filters: %llu ns\n", + filter2 - native); - printf("Estimated seccomp overhead per syscall: %llu ns\n", - filtered - native); + printf("Estimated seccomp per-filter overhead: %llu ns\n", + filter2 - filter1); - if (filtered == native) - printf("Trying running again with more samples.\n"); + printf("Estimated seccomp entry overhead: %llu ns\n", + filter1 - native - (filter2 - filter1)); return 0; } diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 252140a52553..5267b9fb7c0f 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -45,12 +45,19 @@ #include <sys/socket.h> #include <sys/ioctl.h> #include <linux/kcmp.h> +#include <sys/resource.h> #include <unistd.h> #include <sys/syscall.h> #include <poll.h> #include "../kselftest_harness.h" +#include "../clone3/clone3_selftests.h" + +/* Attempt to de-conflict with the selftests tree. */ +#ifndef SKIP +#define SKIP(s, ...) XFAIL(s, ##__VA_ARGS__) +#endif #ifndef PR_SET_PTRACER # define PR_SET_PTRACER 0x59616d61 @@ -167,7 +174,9 @@ struct seccomp_metadata { #ifndef SECCOMP_FILTER_FLAG_NEW_LISTENER #define SECCOMP_FILTER_FLAG_NEW_LISTENER (1UL << 3) +#endif +#ifndef SECCOMP_RET_USER_NOTIF #define SECCOMP_RET_USER_NOTIF 0x7fc00000U #define SECCOMP_IOC_MAGIC '!' @@ -180,7 +189,7 @@ struct seccomp_metadata { #define SECCOMP_IOCTL_NOTIF_RECV SECCOMP_IOWR(0, struct seccomp_notif) #define SECCOMP_IOCTL_NOTIF_SEND SECCOMP_IOWR(1, \ struct seccomp_notif_resp) -#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOR(2, __u64) +#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOW(2, __u64) struct seccomp_notif { __u64 id; @@ -203,6 +212,39 @@ struct seccomp_notif_sizes { }; #endif +#ifndef SECCOMP_IOCTL_NOTIF_ADDFD +/* On success, the return value is the remote process's added fd number */ +#define SECCOMP_IOCTL_NOTIF_ADDFD SECCOMP_IOW(3, \ + struct seccomp_notif_addfd) + +/* valid flags for seccomp_notif_addfd */ +#define SECCOMP_ADDFD_FLAG_SETFD (1UL << 0) /* Specify remote fd */ + +struct seccomp_notif_addfd { + __u64 id; + __u32 flags; + __u32 srcfd; + __u32 newfd; + __u32 newfd_flags; +}; +#endif + +struct seccomp_notif_addfd_small { + __u64 id; + char weird[4]; +}; +#define SECCOMP_IOCTL_NOTIF_ADDFD_SMALL \ + SECCOMP_IOW(3, struct seccomp_notif_addfd_small) + +struct seccomp_notif_addfd_big { + union { + struct seccomp_notif_addfd addfd; + char buf[sizeof(struct seccomp_notif_addfd) + 8]; + }; +}; +#define SECCOMP_IOCTL_NOTIF_ADDFD_BIG \ + SECCOMP_IOWR(3, struct seccomp_notif_addfd_big) + #ifndef PTRACE_EVENTMSG_SYSCALL_ENTRY #define PTRACE_EVENTMSG_SYSCALL_ENTRY 1 #define PTRACE_EVENTMSG_SYSCALL_EXIT 2 @@ -236,6 +278,40 @@ int seccomp(unsigned int op, unsigned int flags, void *args) #define SIBLING_EXIT_FAILURE 0xbadface #define SIBLING_EXIT_NEWPRIVS 0xbadfeed +static int __filecmp(pid_t pid1, pid_t pid2, int fd1, int fd2) +{ +#ifdef __NR_kcmp + errno = 0; + return syscall(__NR_kcmp, pid1, pid2, KCMP_FILE, fd1, fd2); +#else + errno = ENOSYS; + return -1; +#endif +} + +/* Have TH_LOG report actual location filecmp() is used. */ +#define filecmp(pid1, pid2, fd1, fd2) ({ \ + int _ret; \ + \ + _ret = __filecmp(pid1, pid2, fd1, fd2); \ + if (_ret != 0) { \ + if (_ret < 0 && errno == ENOSYS) { \ + TH_LOG("kcmp() syscall missing (test is less accurate)");\ + _ret = 0; \ + } \ + } \ + _ret; }) + +TEST(kcmp) +{ + int ret; + + ret = __filecmp(getpid(), getpid(), 1, 1); + EXPECT_EQ(ret, 0); + if (ret != 0 && errno == ENOSYS) + SKIP(return, "Kernel does not support kcmp() (missing CONFIG_CHECKPOINT_RESTORE?)"); +} + TEST(mode_strict_support) { long ret; @@ -1470,6 +1546,7 @@ pid_t setup_trace_fixture(struct __test_metadata *_metadata, return tracer_pid; } + void teardown_trace_fixture(struct __test_metadata *_metadata, pid_t tracer) { @@ -1750,7 +1827,7 @@ void change_syscall(struct __test_metadata *_metadata, EXPECT_EQ(0, ret); } -void tracer_syscall(struct __test_metadata *_metadata, pid_t tracee, +void tracer_seccomp(struct __test_metadata *_metadata, pid_t tracee, int status, void *args) { int ret; @@ -1827,6 +1904,24 @@ FIXTURE(TRACE_syscall) { pid_t tracer, mytid, mypid, parent; }; +FIXTURE_VARIANT(TRACE_syscall) { + /* + * All of the SECCOMP_RET_TRACE behaviors can be tested with either + * SECCOMP_RET_TRACE+PTRACE_CONT or plain ptrace()+PTRACE_SYSCALL. + * This indicates if we should use SECCOMP_RET_TRACE (false), or + * ptrace (true). + */ + bool use_ptrace; +}; + +FIXTURE_VARIANT_ADD(TRACE_syscall, ptrace) { + .use_ptrace = true, +}; + +FIXTURE_VARIANT_ADD(TRACE_syscall, seccomp) { + .use_ptrace = false, +}; + FIXTURE_SETUP(TRACE_syscall) { struct sock_filter filter[] = { @@ -1842,12 +1937,11 @@ FIXTURE_SETUP(TRACE_syscall) BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1005), BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), }; - - memset(&self->prog, 0, sizeof(self->prog)); - self->prog.filter = malloc(sizeof(filter)); - ASSERT_NE(NULL, self->prog.filter); - memcpy(self->prog.filter, filter, sizeof(filter)); - self->prog.len = (unsigned short)ARRAY_SIZE(filter); + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + long ret; /* Prepare some testable syscall results. */ self->mytid = syscall(__NR_gettid); @@ -1865,60 +1959,48 @@ FIXTURE_SETUP(TRACE_syscall) ASSERT_NE(self->parent, self->mypid); /* Launch tracer. */ - self->tracer = setup_trace_fixture(_metadata, tracer_syscall, NULL, - false); -} + self->tracer = setup_trace_fixture(_metadata, + variant->use_ptrace ? tracer_ptrace + : tracer_seccomp, + NULL, variant->use_ptrace); -FIXTURE_TEARDOWN(TRACE_syscall) -{ - teardown_trace_fixture(_metadata, self->tracer); - if (self->prog.filter) - free(self->prog.filter); -} + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); -TEST_F(TRACE_syscall, ptrace_syscall_redirected) -{ - /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ - teardown_trace_fixture(_metadata, self->tracer); - self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, - true); + if (variant->use_ptrace) + return; - /* Tracer will redirect getpid to getppid. */ - EXPECT_NE(self->mypid, syscall(__NR_getpid)); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); + ASSERT_EQ(0, ret); } -TEST_F(TRACE_syscall, ptrace_syscall_errno) +FIXTURE_TEARDOWN(TRACE_syscall) { - /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ teardown_trace_fixture(_metadata, self->tracer); - self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, - true); - - /* Tracer should skip the open syscall, resulting in ESRCH. */ - EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat)); } -TEST_F(TRACE_syscall, ptrace_syscall_faked) +TEST(negative_ENOSYS) { - /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ - teardown_trace_fixture(_metadata, self->tracer); - self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, - true); + /* + * There should be no difference between an "internal" skip + * and userspace asking for syscall "-1". + */ + errno = 0; + EXPECT_EQ(-1, syscall(-1)); + EXPECT_EQ(errno, ENOSYS); + /* And no difference for "still not valid but not -1". */ + errno = 0; + EXPECT_EQ(-1, syscall(-101)); + EXPECT_EQ(errno, ENOSYS); +} - /* Tracer should skip the gettid syscall, resulting fake pid. */ - EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid)); +TEST_F(TRACE_syscall, negative_ENOSYS) +{ + negative_ENOSYS(_metadata); } TEST_F(TRACE_syscall, syscall_allowed) { - long ret; - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - /* getppid works as expected (no changes). */ EXPECT_EQ(self->parent, syscall(__NR_getppid)); EXPECT_NE(self->mypid, syscall(__NR_getppid)); @@ -1926,14 +2008,6 @@ TEST_F(TRACE_syscall, syscall_allowed) TEST_F(TRACE_syscall, syscall_redirected) { - long ret; - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - /* getpid has been redirected to getppid as expected. */ EXPECT_EQ(self->parent, syscall(__NR_getpid)); EXPECT_NE(self->mypid, syscall(__NR_getpid)); @@ -1941,33 +2015,17 @@ TEST_F(TRACE_syscall, syscall_redirected) TEST_F(TRACE_syscall, syscall_errno) { - long ret; - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - - /* openat has been skipped and an errno return. */ + /* Tracer should skip the open syscall, resulting in ESRCH. */ EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat)); } TEST_F(TRACE_syscall, syscall_faked) { - long ret; - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - - /* gettid has been skipped and an altered return value stored. */ + /* Tracer skips the gettid syscall and store altered return value. */ EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid)); } -TEST_F(TRACE_syscall, skip_after_RET_TRACE) +TEST_F(TRACE_syscall, skip_after) { struct sock_filter filter[] = { BPF_STMT(BPF_LD|BPF_W|BPF_ABS, @@ -1982,14 +2040,7 @@ TEST_F(TRACE_syscall, skip_after_RET_TRACE) }; long ret; - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - /* Install fixture filter. */ - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - - /* Install "errno on getppid" filter. */ + /* Install additional "errno on getppid" filter. */ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); ASSERT_EQ(0, ret); @@ -1999,69 +2050,7 @@ TEST_F(TRACE_syscall, skip_after_RET_TRACE) EXPECT_EQ(EPERM, errno); } -TEST_F_SIGNAL(TRACE_syscall, kill_after_RET_TRACE, SIGSYS) -{ - struct sock_filter filter[] = { - BPF_STMT(BPF_LD|BPF_W|BPF_ABS, - offsetof(struct seccomp_data, nr)), - BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), - }; - struct sock_fprog prog = { - .len = (unsigned short)ARRAY_SIZE(filter), - .filter = filter, - }; - long ret; - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - /* Install fixture filter. */ - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); - ASSERT_EQ(0, ret); - - /* Install "death on getppid" filter. */ - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); - ASSERT_EQ(0, ret); - - /* Tracer will redirect getpid to getppid, and we should die. */ - EXPECT_NE(self->mypid, syscall(__NR_getpid)); -} - -TEST_F(TRACE_syscall, skip_after_ptrace) -{ - struct sock_filter filter[] = { - BPF_STMT(BPF_LD|BPF_W|BPF_ABS, - offsetof(struct seccomp_data, nr)), - BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | EPERM), - BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), - }; - struct sock_fprog prog = { - .len = (unsigned short)ARRAY_SIZE(filter), - .filter = filter, - }; - long ret; - - /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ - teardown_trace_fixture(_metadata, self->tracer); - self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, - true); - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - /* Install "errno on getppid" filter. */ - ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); - ASSERT_EQ(0, ret); - - /* Tracer will redirect getpid to getppid, and we should see EPERM. */ - EXPECT_EQ(-1, syscall(__NR_getpid)); - EXPECT_EQ(EPERM, errno); -} - -TEST_F_SIGNAL(TRACE_syscall, kill_after_ptrace, SIGSYS) +TEST_F_SIGNAL(TRACE_syscall, kill_after, SIGSYS) { struct sock_filter filter[] = { BPF_STMT(BPF_LD|BPF_W|BPF_ABS, @@ -2076,15 +2065,7 @@ TEST_F_SIGNAL(TRACE_syscall, kill_after_ptrace, SIGSYS) }; long ret; - /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ - teardown_trace_fixture(_metadata, self->tracer); - self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, - true); - - ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); - ASSERT_EQ(0, ret); - - /* Install "death on getppid" filter. */ + /* Install additional "death on getppid" filter. */ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); ASSERT_EQ(0, ret); @@ -3069,7 +3050,7 @@ TEST(get_metadata) /* Only real root can get metadata. */ if (geteuid()) { - XFAIL(return, "get_metadata requires real root"); + SKIP(return, "get_metadata requires real root"); return; } @@ -3112,7 +3093,7 @@ TEST(get_metadata) ret = ptrace(PTRACE_SECCOMP_GET_METADATA, pid, sizeof(md), &md); EXPECT_EQ(sizeof(md), ret) { if (errno == EINVAL) - XFAIL(goto skip, "Kernel does not support PTRACE_SECCOMP_GET_METADATA (missing CONFIG_CHECKPOINT_RESTORE?)"); + SKIP(goto skip, "Kernel does not support PTRACE_SECCOMP_GET_METADATA (missing CONFIG_CHECKPOINT_RESTORE?)"); } EXPECT_EQ(md.flags, SECCOMP_FILTER_FLAG_LOG); @@ -3128,7 +3109,7 @@ skip: ASSERT_EQ(0, kill(pid, SIGKILL)); } -static int user_trap_syscall(int nr, unsigned int flags) +static int user_notif_syscall(int nr, unsigned int flags) { struct sock_filter filter[] = { BPF_STMT(BPF_LD+BPF_W+BPF_ABS, @@ -3174,7 +3155,7 @@ TEST(user_notification_basic) /* Check that we get -ENOSYS with no listener attached */ if (pid == 0) { - if (user_trap_syscall(__NR_getppid, 0) < 0) + if (user_notif_syscall(__NR_getppid, 0) < 0) exit(1); ret = syscall(__NR_getppid); exit(ret >= 0 || errno != ENOSYS); @@ -3191,13 +3172,13 @@ TEST(user_notification_basic) EXPECT_EQ(seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog), 0); /* Check that the basic notification machinery works */ - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); /* Installing a second listener in the chain should EBUSY */ - EXPECT_EQ(user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER), + EXPECT_EQ(user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER), -1); EXPECT_EQ(errno, EBUSY); @@ -3258,15 +3239,20 @@ TEST(user_notification_with_tsync) int ret; unsigned int flags; + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + /* these were exclusive */ flags = SECCOMP_FILTER_FLAG_NEW_LISTENER | SECCOMP_FILTER_FLAG_TSYNC; - ASSERT_EQ(-1, user_trap_syscall(__NR_getppid, flags)); + ASSERT_EQ(-1, user_notif_syscall(__NR_getppid, flags)); ASSERT_EQ(EINVAL, errno); /* but now they're not */ flags |= SECCOMP_FILTER_FLAG_TSYNC_ESRCH; - ret = user_trap_syscall(__NR_getppid, flags); + ret = user_notif_syscall(__NR_getppid, flags); close(ret); ASSERT_LE(0, ret); } @@ -3284,8 +3270,8 @@ TEST(user_notification_kill_in_middle) TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); } - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); /* @@ -3338,8 +3324,8 @@ TEST(user_notification_signal) ASSERT_EQ(socketpair(PF_LOCAL, SOCK_SEQPACKET, 0, sk_pair), 0); - listener = user_trap_syscall(__NR_gettid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_gettid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); pid = fork(); @@ -3408,8 +3394,8 @@ TEST(user_notification_closed_listener) TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); } - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); /* @@ -3440,10 +3426,13 @@ TEST(user_notification_child_pid_ns) struct seccomp_notif req = {}; struct seccomp_notif_resp resp = {}; - ASSERT_EQ(unshare(CLONE_NEWUSER | CLONE_NEWPID), 0); + ASSERT_EQ(unshare(CLONE_NEWUSER | CLONE_NEWPID), 0) { + if (errno == EINVAL) + SKIP(return, "kernel missing CLONE_NEWUSER support"); + }; - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); pid = fork(); @@ -3482,8 +3471,8 @@ TEST(user_notification_sibling_pid_ns) TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); } - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); pid = fork(); @@ -3505,7 +3494,10 @@ TEST(user_notification_sibling_pid_ns) } /* Create the sibling ns, and sibling in it. */ - ASSERT_EQ(unshare(CLONE_NEWPID), 0); + ASSERT_EQ(unshare(CLONE_NEWPID), 0) { + if (errno == EPERM) + SKIP(return, "CLONE_NEWPID requires CAP_SYS_ADMIN"); + } ASSERT_EQ(errno, 0); pid2 = fork(); @@ -3547,8 +3539,8 @@ TEST(user_notification_fault_recv) ASSERT_EQ(unshare(CLONE_NEWUSER), 0); - listener = user_trap_syscall(__NR_getppid, - SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); pid = fork(); @@ -3585,16 +3577,6 @@ TEST(seccomp_get_notif_sizes) EXPECT_EQ(sizes.seccomp_notif_resp, sizeof(struct seccomp_notif_resp)); } -static int filecmp(pid_t pid1, pid_t pid2, int fd1, int fd2) -{ -#ifdef __NR_kcmp - return syscall(__NR_kcmp, pid1, pid2, KCMP_FILE, fd1, fd2); -#else - errno = ENOSYS; - return -1; -#endif -} - TEST(user_notification_continue) { pid_t pid; @@ -3609,7 +3591,7 @@ TEST(user_notification_continue) TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); } - listener = user_trap_syscall(__NR_dup, SECCOMP_FILTER_FLAG_NEW_LISTENER); + listener = user_notif_syscall(__NR_dup, SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); pid = fork(); @@ -3619,20 +3601,14 @@ TEST(user_notification_continue) int dup_fd, pipe_fds[2]; pid_t self; - ret = pipe(pipe_fds); - if (ret < 0) - exit(1); + ASSERT_GE(pipe(pipe_fds), 0); dup_fd = dup(pipe_fds[0]); - if (dup_fd < 0) - exit(1); + ASSERT_GE(dup_fd, 0); + EXPECT_NE(pipe_fds[0], dup_fd); self = getpid(); - - ret = filecmp(self, self, pipe_fds[0], dup_fd); - if (ret) - exit(2); - + ASSERT_EQ(filecmp(self, self, pipe_fds[0], dup_fd), 0); exit(0); } @@ -3673,7 +3649,7 @@ TEST(user_notification_continue) resp.val = 0; EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0) { if (errno == EINVAL) - XFAIL(goto skip, "Kernel does not support SECCOMP_USER_NOTIF_FLAG_CONTINUE"); + SKIP(goto skip, "Kernel does not support SECCOMP_USER_NOTIF_FLAG_CONTINUE"); } skip: @@ -3681,15 +3657,342 @@ skip: EXPECT_EQ(true, WIFEXITED(status)); EXPECT_EQ(0, WEXITSTATUS(status)) { if (WEXITSTATUS(status) == 2) { - XFAIL(return, "Kernel does not support kcmp() syscall"); + SKIP(return, "Kernel does not support kcmp() syscall"); return; } } } +TEST(user_notification_filter_empty) +{ + pid_t pid; + long ret; + int status; + struct pollfd pollfd; + struct clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + int listener; + + listener = user_notif_syscall(__NR_mknod, SECCOMP_FILTER_FLAG_NEW_LISTENER); + if (listener < 0) + _exit(EXIT_FAILURE); + + if (dup2(listener, 200) != 200) + _exit(EXIT_FAILURE); + + close(listener); + + _exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + + /* + * The seccomp filter has become unused so we should be notified once + * the kernel gets around to cleaning up task struct. + */ + pollfd.fd = 200; + pollfd.events = POLLHUP; + + EXPECT_GT(poll(&pollfd, 1, 2000), 0); + EXPECT_GT((pollfd.revents & POLLHUP) ?: 0, 0); +} + +static void *do_thread(void *data) +{ + return NULL; +} + +TEST(user_notification_filter_empty_threaded) +{ + pid_t pid; + long ret; + int status; + struct pollfd pollfd; + struct clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + pid_t pid1, pid2; + int listener, status; + pthread_t thread; + + listener = user_notif_syscall(__NR_dup, SECCOMP_FILTER_FLAG_NEW_LISTENER); + if (listener < 0) + _exit(EXIT_FAILURE); + + if (dup2(listener, 200) != 200) + _exit(EXIT_FAILURE); + + close(listener); + + pid1 = fork(); + if (pid1 < 0) + _exit(EXIT_FAILURE); + + if (pid1 == 0) + _exit(EXIT_SUCCESS); + + pid2 = fork(); + if (pid2 < 0) + _exit(EXIT_FAILURE); + + if (pid2 == 0) + _exit(EXIT_SUCCESS); + + if (pthread_create(&thread, NULL, do_thread, NULL) || + pthread_join(thread, NULL)) + _exit(EXIT_FAILURE); + + if (pthread_create(&thread, NULL, do_thread, NULL) || + pthread_join(thread, NULL)) + _exit(EXIT_FAILURE); + + if (waitpid(pid1, &status, 0) != pid1 || !WIFEXITED(status) || + WEXITSTATUS(status)) + _exit(EXIT_FAILURE); + + if (waitpid(pid2, &status, 0) != pid2 || !WIFEXITED(status) || + WEXITSTATUS(status)) + _exit(EXIT_FAILURE); + + exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + + /* + * The seccomp filter has become unused so we should be notified once + * the kernel gets around to cleaning up task struct. + */ + pollfd.fd = 200; + pollfd.events = POLLHUP; + + EXPECT_GT(poll(&pollfd, 1, 2000), 0); + EXPECT_GT((pollfd.revents & POLLHUP) ?: 0, 0); +} + +TEST(user_notification_addfd) +{ + pid_t pid; + long ret; + int status, listener, memfd, fd; + struct seccomp_notif_addfd addfd = {}; + struct seccomp_notif_addfd_small small = {}; + struct seccomp_notif_addfd_big big = {}; + struct seccomp_notif req = {}; + struct seccomp_notif_resp resp = {}; + /* 100 ms */ + struct timespec delay = { .tv_nsec = 100000000 }; + + memfd = memfd_create("test", 0); + ASSERT_GE(memfd, 0); + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + /* Check that the basic notification machinery works */ + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); + ASSERT_GE(listener, 0); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + if (syscall(__NR_getppid) != USER_NOTIF_MAGIC) + exit(1); + exit(syscall(__NR_getppid) != USER_NOTIF_MAGIC); + } + + ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + + addfd.srcfd = memfd; + addfd.newfd = 0; + addfd.id = req.id; + addfd.flags = 0x0; + + /* Verify bad newfd_flags cannot be set */ + addfd.newfd_flags = ~O_CLOEXEC; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1); + EXPECT_EQ(errno, EINVAL); + addfd.newfd_flags = O_CLOEXEC; + + /* Verify bad flags cannot be set */ + addfd.flags = 0xff; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1); + EXPECT_EQ(errno, EINVAL); + addfd.flags = 0; + + /* Verify that remote_fd cannot be set without setting flags */ + addfd.newfd = 1; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1); + EXPECT_EQ(errno, EINVAL); + addfd.newfd = 0; + + /* Verify small size cannot be set */ + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD_SMALL, &small), -1); + EXPECT_EQ(errno, EINVAL); + + /* Verify we can't send bits filled in unknown buffer area */ + memset(&big, 0xAA, sizeof(big)); + big.addfd = addfd; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD_BIG, &big), -1); + EXPECT_EQ(errno, E2BIG); + + + /* Verify we can set an arbitrary remote fd */ + fd = ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd); + /* + * The child has fds 0(stdin), 1(stdout), 2(stderr), 3(memfd), + * 4(listener), so the newly allocated fd should be 5. + */ + EXPECT_EQ(fd, 5); + EXPECT_EQ(filecmp(getpid(), pid, memfd, fd), 0); + + /* Verify we can set an arbitrary remote fd with large size */ + memset(&big, 0x0, sizeof(big)); + big.addfd = addfd; + fd = ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD_BIG, &big); + EXPECT_EQ(fd, 6); + + /* Verify we can set a specific remote fd */ + addfd.newfd = 42; + addfd.flags = SECCOMP_ADDFD_FLAG_SETFD; + fd = ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd); + EXPECT_EQ(fd, 42); + EXPECT_EQ(filecmp(getpid(), pid, memfd, fd), 0); + + /* Resume syscall */ + resp.id = req.id; + resp.error = 0; + resp.val = USER_NOTIF_MAGIC; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0); + + /* + * This sets the ID of the ADD FD to the last request plus 1. The + * notification ID increments 1 per notification. + */ + addfd.id = req.id + 1; + + /* This spins until the underlying notification is generated */ + while (ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd) != -1 && + errno != -EINPROGRESS) + nanosleep(&delay, NULL); + + memset(&req, 0, sizeof(req)); + ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + ASSERT_EQ(addfd.id, req.id); + + resp.id = req.id; + resp.error = 0; + resp.val = USER_NOTIF_MAGIC; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0); + + /* Wait for child to finish. */ + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + + close(memfd); +} + +TEST(user_notification_addfd_rlimit) +{ + pid_t pid; + long ret; + int status, listener, memfd; + struct seccomp_notif_addfd addfd = {}; + struct seccomp_notif req = {}; + struct seccomp_notif_resp resp = {}; + const struct rlimit lim = { + .rlim_cur = 0, + .rlim_max = 0, + }; + + memfd = memfd_create("test", 0); + ASSERT_GE(memfd, 0); + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret) { + TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); + } + + /* Check that the basic notification machinery works */ + listener = user_notif_syscall(__NR_getppid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); + ASSERT_GE(listener, 0); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) + exit(syscall(__NR_getppid) != USER_NOTIF_MAGIC); + + + ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + + ASSERT_EQ(prlimit(pid, RLIMIT_NOFILE, &lim, NULL), 0); + + addfd.srcfd = memfd; + addfd.newfd_flags = O_CLOEXEC; + addfd.newfd = 0; + addfd.id = req.id; + addfd.flags = 0; + + /* Should probably spot check /proc/sys/fs/file-nr */ + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1); + EXPECT_EQ(errno, EMFILE); + + addfd.newfd = 100; + addfd.flags = SECCOMP_ADDFD_FLAG_SETFD; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1); + EXPECT_EQ(errno, EBADF); + + resp.id = req.id; + resp.error = 0; + resp.val = USER_NOTIF_MAGIC; + + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0); + + /* Wait for child to finish. */ + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + + close(memfd); +} + /* * TODO: - * - add microbenchmarks * - expand NNP testing * - better arch-specific TRACE and TRAP handlers. * - endianness checking when appropriate @@ -3697,7 +4000,6 @@ skip: * - arch value testing (x86 modes especially) * - verify that FILTER_FLAG_LOG filters generate log messages * - verify that RET_LOG generates log messages - * - ... */ TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/seccomp/settings b/tools/testing/selftests/seccomp/settings new file mode 100644 index 000000000000..ba4d85f74cd6 --- /dev/null +++ b/tools/testing/selftests/seccomp/settings @@ -0,0 +1 @@ +timeout=90 diff --git a/tools/testing/selftests/sigaltstack/sas.c b/tools/testing/selftests/sigaltstack/sas.c index ad0f8df2ca0a..8934a3766d20 100644 --- a/tools/testing/selftests/sigaltstack/sas.c +++ b/tools/testing/selftests/sigaltstack/sas.c @@ -71,7 +71,7 @@ void my_usr1(int sig, siginfo_t *si, void *u) swapcontext(&sc, &uc); ksft_print_msg("%s\n", p->msg); if (!p->flag) { - ksft_exit_skip("[RUN]\tAborting\n"); + ksft_exit_fail_msg("[RUN]\tAborting\n"); exit(EXIT_FAILURE); } } @@ -144,7 +144,7 @@ int main(void) err = sigaltstack(&stk, NULL); if (err) { if (errno == EINVAL) { - ksft_exit_skip( + ksft_test_result_skip( "[NOTE]\tThe running kernel doesn't support SS_AUTODISARM\n"); /* * If test cases for the !SS_AUTODISARM variant were diff --git a/tools/testing/selftests/sync/sync_test.c b/tools/testing/selftests/sync/sync_test.c index 3824b66f41a0..414a617db993 100644 --- a/tools/testing/selftests/sync/sync_test.c +++ b/tools/testing/selftests/sync/sync_test.c @@ -86,9 +86,9 @@ int main(void) int err; ksft_print_header(); - ksft_set_plan(3 + 7); sync_api_supported(); + ksft_set_plan(3 + 7); ksft_print_msg("[RUN]\tTesting sync framework\n"); diff --git a/tools/testing/selftests/uevent/uevent_filtering.c b/tools/testing/selftests/uevent/uevent_filtering.c index f83391aa42cf..5cebfb356345 100644 --- a/tools/testing/selftests/uevent/uevent_filtering.c +++ b/tools/testing/selftests/uevent/uevent_filtering.c @@ -19,7 +19,6 @@ #include <sys/wait.h> #include <unistd.h> -#include "../kselftest.h" #include "../kselftest_harness.h" #define __DEV_FULL "/sys/devices/virtual/mem/full/uevent" diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c index 79db22604019..91d38a29956b 100644 --- a/tools/testing/selftests/vm/hmm-tests.c +++ b/tools/testing/selftests/vm/hmm-tests.c @@ -881,8 +881,9 @@ TEST_F(hmm, migrate) } /* - * Migrate anonymous memory to device private memory and fault it back to system - * memory. + * Migrate anonymous memory to device private memory and fault some of it back + * to system memory, then try migrating the resulting mix of system and device + * private memory to the device. */ TEST_F(hmm, migrate_fault) { @@ -924,8 +925,17 @@ TEST_F(hmm, migrate_fault) for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) ASSERT_EQ(ptr[i], i); - /* Fault pages back to system memory and check them. */ - for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + /* Fault half the pages back to system memory and check them. */ + for (i = 0, ptr = buffer->ptr; i < size / (2 * sizeof(*ptr)); ++i) + ASSERT_EQ(ptr[i], i); + + /* Migrate memory to the device again. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) ASSERT_EQ(ptr[i], i); hmm_buffer_free(buffer); @@ -1292,6 +1302,82 @@ TEST_F(hmm2, snapshot) } /* + * Test the hmm_range_fault() HMM_PFN_PMD flag for large pages that + * should be mapped by a large page table entry. + */ +TEST_F(hmm, compound) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + int *ptr; + unsigned char *m; + int ret; + long pagesizes[4]; + int n, idx; + unsigned long i; + + /* Skip test if we can't allocate a hugetlbfs page. */ + + n = gethugepagesizes(pagesizes, 4); + if (n <= 0) + return; + for (idx = 0; --n > 0; ) { + if (pagesizes[n] < pagesizes[idx]) + idx = n; + } + size = ALIGN(TWOMEG, pagesizes[idx]); + npages = size >> self->page_shift; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->ptr = get_hugepage_region(size, GHR_STRICT); + if (buffer->ptr == NULL) { + free(buffer); + return; + } + + buffer->size = size; + buffer->mirror = malloc(npages); + ASSERT_NE(buffer->mirror, NULL); + + /* Initialize the pages the device will snapshot in buffer->ptr. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Simulate a device snapshotting CPU pagetables. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device saw. */ + m = buffer->mirror; + for (i = 0; i < npages; ++i) + ASSERT_EQ(m[i], HMM_DMIRROR_PROT_WRITE | + HMM_DMIRROR_PROT_PMD); + + /* Make the region read-only. */ + ret = mprotect(buffer->ptr, size, PROT_READ); + ASSERT_EQ(ret, 0); + + /* Simulate a device snapshotting CPU pagetables. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device saw. */ + m = buffer->mirror; + for (i = 0; i < npages; ++i) + ASSERT_EQ(m[i], HMM_DMIRROR_PROT_READ | + HMM_DMIRROR_PROT_PMD); + + free_hugepage_region(buffer->ptr); + buffer->ptr = NULL; + hmm_buffer_free(buffer); +} + +/* * Test two devices reading the same memory (double mapped). */ TEST_F(hmm2, double_map) diff --git a/tools/testing/selftests/vm/protection_keys.c b/tools/testing/selftests/vm/protection_keys.c index fc19addcb5c8..fdbb602ecf32 100644 --- a/tools/testing/selftests/vm/protection_keys.c +++ b/tools/testing/selftests/vm/protection_keys.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Tests Memory Protection Keys (see Documentation/vm/protection-keys.txt) + * Tests Memory Protection Keys (see Documentation/core-api/protection-keys.rst) * * There are examples in here of: * * how to set protection keys on memory diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index d2796ea98c5a..6703c7906b71 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -13,7 +13,7 @@ CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh $(CC) trivial_program.c -no-pie) TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \ check_initial_reg_state sigreturn iopl ioperm \ test_vdso test_vsyscall mov_ss_trap \ - syscall_arg_fault + syscall_arg_fault fsgsbase_restore TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c index 15a329da59fa..998319553523 100644 --- a/tools/testing/selftests/x86/fsgsbase.c +++ b/tools/testing/selftests/x86/fsgsbase.c @@ -285,7 +285,8 @@ static unsigned short load_gs(void) /* 32-bit set_thread_area */ long ret; asm volatile ("int $0x80" - : "=a" (ret) : "a" (243), "b" (low_desc) + : "=a" (ret), "+m" (*low_desc) + : "a" (243), "b" (low_desc) : "r8", "r9", "r10", "r11"); memcpy(&desc, low_desc, sizeof(desc)); munmap(low_desc, sizeof(desc)); @@ -489,11 +490,28 @@ static void test_ptrace_write_gsbase(void) * selector value is changed or not by the GSBASE write in * a ptracer. */ - if (gs == 0 && base == 0xFF) { - printf("[OK]\tGS was reset as expected\n"); - } else { + if (gs != *shared_scratch) { nerrs++; - printf("[FAIL]\tGS=0x%lx, GSBASE=0x%lx (should be 0, 0xFF)\n", gs, base); + printf("[FAIL]\tGS changed to %lx\n", gs); + + /* + * On older kernels, poking a nonzero value into the + * base would zero the selector. On newer kernels, + * this behavior has changed -- poking the base + * changes only the base and, if FSGSBASE is not + * available, this may have no effect once the tracee + * is resumed. + */ + if (gs == 0) + printf("\tNote: this is expected behavior on older kernels.\n"); + } else if (have_fsgsbase && (base != 0xFF)) { + nerrs++; + printf("[FAIL]\tGSBASE changed to %lx\n", base); + } else { + printf("[OK]\tGS remained 0x%hx", *shared_scratch); + if (have_fsgsbase) + printf(" and GSBASE changed to 0xFF"); + printf("\n"); } } diff --git a/tools/testing/selftests/x86/fsgsbase_restore.c b/tools/testing/selftests/x86/fsgsbase_restore.c new file mode 100644 index 000000000000..6fffadc51579 --- /dev/null +++ b/tools/testing/selftests/x86/fsgsbase_restore.c @@ -0,0 +1,245 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * fsgsbase_restore.c, test ptrace vs fsgsbase + * Copyright (c) 2020 Andy Lutomirski + * + * This test case simulates a tracer redirecting tracee execution to + * a function and then restoring tracee state using PTRACE_GETREGS and + * PTRACE_SETREGS. This is similar to what gdb does when doing + * 'p func()'. The catch is that this test has the called function + * modify a segment register. This makes sure that ptrace correctly + * restores segment state when using PTRACE_SETREGS. + * + * This is not part of fsgsbase.c, because that test is 64-bit only. + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> +#include <sys/syscall.h> +#include <unistd.h> +#include <err.h> +#include <sys/user.h> +#include <asm/prctl.h> +#include <sys/prctl.h> +#include <asm/ldt.h> +#include <sys/mman.h> +#include <stddef.h> +#include <sys/ptrace.h> +#include <sys/wait.h> +#include <stdint.h> + +#define EXPECTED_VALUE 0x1337f00d + +#ifdef __x86_64__ +# define SEG "%gs" +#else +# define SEG "%fs" +#endif + +static unsigned int dereference_seg_base(void) +{ + int ret; + asm volatile ("mov %" SEG ":(0), %0" : "=rm" (ret)); + return ret; +} + +static void init_seg(void) +{ + unsigned int *target = mmap( + NULL, sizeof(unsigned int), + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_32BIT, -1, 0); + if (target == MAP_FAILED) + err(1, "mmap"); + + *target = EXPECTED_VALUE; + + printf("\tsegment base address = 0x%lx\n", (unsigned long)target); + + struct user_desc desc = { + .entry_number = 0, + .base_addr = (unsigned int)(uintptr_t)target, + .limit = sizeof(unsigned int) - 1, + .seg_32bit = 1, + .contents = 0, /* Data, grow-up */ + .read_exec_only = 0, + .limit_in_pages = 0, + .seg_not_present = 0, + .useable = 0 + }; + if (syscall(SYS_modify_ldt, 1, &desc, sizeof(desc)) == 0) { + printf("\tusing LDT slot 0\n"); + asm volatile ("mov %0, %" SEG :: "rm" ((unsigned short)0x7)); + } else { + /* No modify_ldt for us (configured out, perhaps) */ + + struct user_desc *low_desc = mmap( + NULL, sizeof(desc), + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_32BIT, -1, 0); + memcpy(low_desc, &desc, sizeof(desc)); + + low_desc->entry_number = -1; + + /* 32-bit set_thread_area */ + long ret; + asm volatile ("int $0x80" + : "=a" (ret), "+m" (*low_desc) + : "a" (243), "b" (low_desc) +#ifdef __x86_64__ + : "r8", "r9", "r10", "r11" +#endif + ); + memcpy(&desc, low_desc, sizeof(desc)); + munmap(low_desc, sizeof(desc)); + + if (ret != 0) { + printf("[NOTE]\tcould not create a segment -- can't test anything\n"); + exit(0); + } + printf("\tusing GDT slot %d\n", desc.entry_number); + + unsigned short sel = (unsigned short)((desc.entry_number << 3) | 0x3); + asm volatile ("mov %0, %" SEG :: "rm" (sel)); + } +} + +static void tracee_zap_segment(void) +{ + /* + * The tracer will redirect execution here. This is meant to + * work like gdb's 'p func()' feature. The tricky bit is that + * we modify a segment register in order to make sure that ptrace + * can correctly restore segment registers. + */ + printf("\tTracee: in tracee_zap_segment()\n"); + + /* + * Write a nonzero selector with base zero to the segment register. + * Using a null selector would defeat the test on AMD pre-Zen2 + * CPUs, as such CPUs don't clear the base when loading a null + * selector. + */ + unsigned short sel; + asm volatile ("mov %%ss, %0\n\t" + "mov %0, %" SEG + : "=rm" (sel)); + + pid_t pid = getpid(), tid = syscall(SYS_gettid); + + printf("\tTracee is going back to sleep\n"); + syscall(SYS_tgkill, pid, tid, SIGSTOP); + + /* Should not get here. */ + while (true) { + printf("[FAIL]\tTracee hit unreachable code\n"); + pause(); + } +} + +int main() +{ + printf("\tSetting up a segment\n"); + init_seg(); + + unsigned int val = dereference_seg_base(); + if (val != EXPECTED_VALUE) { + printf("[FAIL]\tseg[0] == %x; should be %x\n", val, EXPECTED_VALUE); + return 1; + } + printf("[OK]\tThe segment points to the right place.\n"); + + pid_t chld = fork(); + if (chld < 0) + err(1, "fork"); + + if (chld == 0) { + prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0, 0); + + if (ptrace(PTRACE_TRACEME, 0, 0, 0) != 0) + err(1, "PTRACE_TRACEME"); + + pid_t pid = getpid(), tid = syscall(SYS_gettid); + + printf("\tTracee will take a nap until signaled\n"); + syscall(SYS_tgkill, pid, tid, SIGSTOP); + + printf("\tTracee was resumed. Will re-check segment.\n"); + + val = dereference_seg_base(); + if (val != EXPECTED_VALUE) { + printf("[FAIL]\tseg[0] == %x; should be %x\n", val, EXPECTED_VALUE); + exit(1); + } + + printf("[OK]\tThe segment points to the right place.\n"); + exit(0); + } + + int status; + + /* Wait for SIGSTOP. */ + if (waitpid(chld, &status, 0) != chld || !WIFSTOPPED(status)) + err(1, "waitpid"); + + struct user_regs_struct regs; + + if (ptrace(PTRACE_GETREGS, chld, NULL, ®s) != 0) + err(1, "PTRACE_GETREGS"); + +#ifdef __x86_64__ + printf("\tChild GS=0x%lx, GSBASE=0x%lx\n", (unsigned long)regs.gs, (unsigned long)regs.gs_base); +#else + printf("\tChild FS=0x%lx\n", (unsigned long)regs.xfs); +#endif + + struct user_regs_struct regs2 = regs; +#ifdef __x86_64__ + regs2.rip = (unsigned long)tracee_zap_segment; + regs2.rsp -= 128; /* Don't clobber the redzone. */ +#else + regs2.eip = (unsigned long)tracee_zap_segment; +#endif + + printf("\tTracer: redirecting tracee to tracee_zap_segment()\n"); + if (ptrace(PTRACE_SETREGS, chld, NULL, ®s2) != 0) + err(1, "PTRACE_GETREGS"); + if (ptrace(PTRACE_CONT, chld, NULL, NULL) != 0) + err(1, "PTRACE_GETREGS"); + + /* Wait for SIGSTOP. */ + if (waitpid(chld, &status, 0) != chld || !WIFSTOPPED(status)) + err(1, "waitpid"); + + printf("\tTracer: restoring tracee state\n"); + if (ptrace(PTRACE_SETREGS, chld, NULL, ®s) != 0) + err(1, "PTRACE_GETREGS"); + if (ptrace(PTRACE_DETACH, chld, NULL, NULL) != 0) + err(1, "PTRACE_GETREGS"); + + /* Wait for SIGSTOP. */ + if (waitpid(chld, &status, 0) != chld) + err(1, "waitpid"); + + if (WIFSIGNALED(status)) { + printf("[FAIL]\tTracee crashed\n"); + return 1; + } + + if (!WIFEXITED(status)) { + printf("[FAIL]\tTracee stopped for an unexpected reason: %d\n", status); + return 1; + } + + int exitcode = WEXITSTATUS(status); + if (exitcode != 0) { + printf("[FAIL]\tTracee reported failure\n"); + return 1; + } + + printf("[OK]\tAll is well.\n"); + return 0; +} diff --git a/tools/testing/selftests/x86/syscall_arg_fault.c b/tools/testing/selftests/x86/syscall_arg_fault.c index 5b7abebbcbb9..bff474b5efc6 100644 --- a/tools/testing/selftests/x86/syscall_arg_fault.c +++ b/tools/testing/selftests/x86/syscall_arg_fault.c @@ -53,6 +53,7 @@ static void sigsegv_or_sigbus(int sig, siginfo_t *info, void *ctx_void) if (ax != -EFAULT && ax != -ENOSYS) { printf("[FAIL]\tAX had the wrong value: 0x%lx\n", (unsigned long)ax); + printf("\tIP = 0x%lx\n", (unsigned long)ctx->uc_mcontext.gregs[REG_IP]); n_errs++; } else { printf("[OK]\tSeems okay\n"); @@ -207,5 +208,30 @@ int main() } set_eflags(get_eflags() & ~X86_EFLAGS_TF); +#ifdef __x86_64__ + printf("[RUN]\tSYSENTER with TF, invalid state, and GSBASE < 0\n"); + + if (sigsetjmp(jmpbuf, 1) == 0) { + sigtrap_consecutive_syscalls = 0; + + asm volatile ("wrgsbase %%rax\n\t" + :: "a" (0xffffffffffff0000UL)); + + set_eflags(get_eflags() | X86_EFLAGS_TF); + asm volatile ( + "movl $-1, %%eax\n\t" + "movl $-1, %%ebx\n\t" + "movl $-1, %%ecx\n\t" + "movl $-1, %%edx\n\t" + "movl $-1, %%esi\n\t" + "movl $-1, %%edi\n\t" + "movl $-1, %%ebp\n\t" + "movl $-1, %%esp\n\t" + "sysenter" + : : : "memory", "flags"); + } + set_eflags(get_eflags() & ~X86_EFLAGS_TF); +#endif + return 0; } diff --git a/tools/usb/usbip/doc/usbip.8 b/tools/usb/usbip/doc/usbip.8 index a6097be25d28..a15d20063b98 100644 --- a/tools/usb/usbip/doc/usbip.8 +++ b/tools/usb/usbip/doc/usbip.8 @@ -83,7 +83,9 @@ List local USB devices. .SH EXAMPLES client:# usbip list --remote=server - - List exportable usb devices on the server. + - List devices exported by remote server. + + client:# modprobe vhci-hcd client:# usbip attach --remote=server --busid=1-2 - Connect the remote USB device. diff --git a/tools/usb/usbip/doc/usbipd.8 b/tools/usb/usbip/doc/usbipd.8 index ac4635db3f03..fb62a756893b 100644 --- a/tools/usb/usbip/doc/usbipd.8 +++ b/tools/usb/usbip/doc/usbipd.8 @@ -73,7 +73,7 @@ USB/IP client can connect and use exported devices. .SH EXAMPLES - server:# modprobe usbip + server:# modprobe usbip-host server:# usbipd -D - Start usbip daemon. diff --git a/tools/usb/usbip/libsrc/usbip_host_common.c b/tools/usb/usbip/libsrc/usbip_host_common.c index d1d8ba2a4a40..ca78aa368476 100644 --- a/tools/usb/usbip/libsrc/usbip_host_common.c +++ b/tools/usb/usbip/libsrc/usbip_host_common.c @@ -23,7 +23,7 @@ #include "list.h" #include "sysfs_utils.h" -struct udev *udev_context; +extern struct udev *udev_context; static int32_t read_attr_usbip_status(struct usbip_usb_device *udev) { diff --git a/tools/usb/usbip/vudc/vudc_server_example.sh b/tools/usb/usbip/vudc/vudc_server_example.sh index 2736be64f203..fed53f51ee01 100755 --- a/tools/usb/usbip/vudc/vudc_server_example.sh +++ b/tools/usb/usbip/vudc/vudc_server_example.sh @@ -24,7 +24,7 @@ # ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR # OTHER DEALINGS IN THE SOFTWARE. # -# For more information, please refer to <http://unlicense.org/> +# For more information, please refer to <https://unlicense.org/> ################################################################################ ################################################################################ diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index caab980211a6..315e85cabeda 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -110,8 +110,6 @@ static inline void free_page(unsigned long addr) const typeof( ((type *)0)->member ) *__mptr = (ptr); \ (type *)( (char *)__mptr - offsetof(type,member) );}) -#define uninitialized_var(x) x = x - # ifndef likely # define likely(x) (__builtin_expect(!!(x), 1)) # endif |