diff options
Diffstat (limited to 'tools')
54 files changed, 1352 insertions, 401 deletions
diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile index 6df1850f8353..8a69258fd8aa 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/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/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 5b36c589a029..ba4f33804af1 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -2861,6 +2861,7 @@ process_dynamic_array_len(struct tep_event *event, struct tep_print_arg *arg, if (read_expected(TEP_EVENT_DELIM, ")") < 0) goto out_err; + free_token(token); type = read_token(&token); *tok = token; diff --git a/tools/lib/traceevent/plugins/Makefile b/tools/lib/traceevent/plugins/Makefile index 349bb81482ab..680d883efe05 100644 --- a/tools/lib/traceevent/plugins/Makefile +++ b/tools/lib/traceevent/plugins/Makefile @@ -197,7 +197,7 @@ define do_generate_dynamic_list_file xargs echo "U w W" | tr 'w ' 'W\n' | sort -u | xargs echo`;\ if [ "$$symbol_type" = "U W" ];then \ (echo '{'; \ - $(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\ + $(NM) -u -D $1 | awk 'NF>1 {sub("@.*", "", $$2); print "\t"$$2";"}' | sort -u;\ echo '};'; \ ) > $2; \ else \ 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/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c index 0a6e75b8777a..28a5d0c18b1d 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -56,7 +56,7 @@ struct auxtrace_record struct perf_pmu *cs_etm_pmu; struct evsel *evsel; bool found_etm = false; - bool found_spe = false; + struct perf_pmu *found_spe = NULL; static struct perf_pmu **arm_spe_pmus = NULL; static int nr_spes = 0; int i = 0; @@ -74,12 +74,12 @@ struct auxtrace_record evsel->core.attr.type == cs_etm_pmu->type) found_etm = true; - if (!nr_spes) + if (!nr_spes || found_spe) continue; for (i = 0; i < nr_spes; i++) { if (evsel->core.attr.type == arm_spe_pmus[i]->type) { - found_spe = true; + found_spe = arm_spe_pmus[i]; break; } } @@ -96,7 +96,7 @@ struct auxtrace_record #if defined(__aarch64__) if (found_spe) - return arm_spe_recording_init(err, arm_spe_pmus[i]); + return arm_spe_recording_init(err, found_spe); #endif /* diff --git a/tools/perf/tests/shell/record+zstd_comp_decomp.sh b/tools/perf/tests/shell/record+zstd_comp_decomp.sh index 63a91ec473bb..045723b3d992 100755 --- a/tools/perf/tests/shell/record+zstd_comp_decomp.sh +++ b/tools/perf/tests/shell/record+zstd_comp_decomp.sh @@ -12,7 +12,8 @@ skip_if_no_z_record() { collect_z_record() { echo "Collecting compressed record file:" - $perf_tool record -o $trace_file -g -z -F 5000 -- \ + [[ "$(uname -m)" != s390x ]] && gflag='-g' + $perf_tool record -o $trace_file $gflag -z -F 5000 -- \ dd count=500 if=/dev/urandom of=/dev/null } 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/selftests/Makefile b/tools/testing/selftests/Makefile index 1195bd85af38..227ca78a5b7f 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -15,6 +15,7 @@ TARGETS += filesystems TARGETS += filesystems/binderfs TARGETS += filesystems/epoll TARGETS += firmware +TARGETS += fpu TARGETS += ftrace TARGETS += futex TARGETS += gpio diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c index f7ee8fa377ad..6ccecbd39476 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c @@ -5,10 +5,60 @@ #include "test_btf_map_in_map.skel.h" +static int duration; + +static __u32 bpf_map_id(struct bpf_map *map) +{ + struct bpf_map_info info; + __u32 info_len = sizeof(info); + int err; + + memset(&info, 0, info_len); + err = bpf_obj_get_info_by_fd(bpf_map__fd(map), &info, &info_len); + if (err) + return 0; + return info.id; +} + +/* + * Trigger synchronize_rcu() in kernel. + * + * ARRAY_OF_MAPS/HASH_OF_MAPS lookup/update operations trigger synchronize_rcu() + * if looking up an existing non-NULL element or updating the map with a valid + * inner map FD. Use this fact to trigger synchronize_rcu(): create map-in-map, + * create a trivial ARRAY map, update map-in-map with ARRAY inner map. Then + * cleanup. At the end, at least one synchronize_rcu() would be called. + */ +static int kern_sync_rcu(void) +{ + int inner_map_fd, outer_map_fd, err, zero = 0; + + inner_map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 4, 1, 0); + if (CHECK(inner_map_fd < 0, "inner_map_create", "failed %d\n", -errno)) + return -1; + + outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL, + sizeof(int), inner_map_fd, 1, 0); + if (CHECK(outer_map_fd < 0, "outer_map_create", "failed %d\n", -errno)) { + close(inner_map_fd); + return -1; + } + + err = bpf_map_update_elem(outer_map_fd, &zero, &inner_map_fd, 0); + if (err) + err = -errno; + CHECK(err, "outer_map_update", "failed %d\n", err); + close(inner_map_fd); + close(outer_map_fd); + return err; +} + void test_btf_map_in_map(void) { - int duration = 0, err, key = 0, val; - struct test_btf_map_in_map* skel; + int err, key = 0, val, i; + struct test_btf_map_in_map *skel; + int outer_arr_fd, outer_hash_fd; + int fd, map1_fd, map2_fd, map1_id, map2_id; skel = test_btf_map_in_map__open_and_load(); if (CHECK(!skel, "skel_open", "failed to open&load skeleton\n")) @@ -18,32 +68,78 @@ void test_btf_map_in_map(void) if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) goto cleanup; + map1_fd = bpf_map__fd(skel->maps.inner_map1); + map2_fd = bpf_map__fd(skel->maps.inner_map2); + outer_arr_fd = bpf_map__fd(skel->maps.outer_arr); + outer_hash_fd = bpf_map__fd(skel->maps.outer_hash); + /* inner1 = input, inner2 = input + 1 */ - val = bpf_map__fd(skel->maps.inner_map1); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0); - val = bpf_map__fd(skel->maps.inner_map2); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0); + map1_fd = bpf_map__fd(skel->maps.inner_map1); + bpf_map_update_elem(outer_arr_fd, &key, &map1_fd, 0); + map2_fd = bpf_map__fd(skel->maps.inner_map2); + bpf_map_update_elem(outer_hash_fd, &key, &map2_fd, 0); skel->bss->input = 1; usleep(1); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val); + bpf_map_lookup_elem(map1_fd, &key, &val); CHECK(val != 1, "inner1", "got %d != exp %d\n", val, 1); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val); + bpf_map_lookup_elem(map2_fd, &key, &val); CHECK(val != 2, "inner2", "got %d != exp %d\n", val, 2); /* inner1 = input + 1, inner2 = input */ - val = bpf_map__fd(skel->maps.inner_map2); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_arr), &key, &val, 0); - val = bpf_map__fd(skel->maps.inner_map1); - bpf_map_update_elem(bpf_map__fd(skel->maps.outer_hash), &key, &val, 0); + bpf_map_update_elem(outer_arr_fd, &key, &map2_fd, 0); + bpf_map_update_elem(outer_hash_fd, &key, &map1_fd, 0); skel->bss->input = 3; usleep(1); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map1), &key, &val); + bpf_map_lookup_elem(map1_fd, &key, &val); CHECK(val != 4, "inner1", "got %d != exp %d\n", val, 4); - bpf_map_lookup_elem(bpf_map__fd(skel->maps.inner_map2), &key, &val); + bpf_map_lookup_elem(map2_fd, &key, &val); CHECK(val != 3, "inner2", "got %d != exp %d\n", val, 3); + for (i = 0; i < 5; i++) { + val = i % 2 ? map1_fd : map2_fd; + err = bpf_map_update_elem(outer_hash_fd, &key, &val, 0); + if (CHECK_FAIL(err)) { + printf("failed to update hash_of_maps on iter #%d\n", i); + goto cleanup; + } + err = bpf_map_update_elem(outer_arr_fd, &key, &val, 0); + if (CHECK_FAIL(err)) { + printf("failed to update hash_of_maps on iter #%d\n", i); + goto cleanup; + } + } + + map1_id = bpf_map_id(skel->maps.inner_map1); + map2_id = bpf_map_id(skel->maps.inner_map2); + CHECK(map1_id == 0, "map1_id", "failed to get ID 1\n"); + CHECK(map2_id == 0, "map2_id", "failed to get ID 2\n"); + + test_btf_map_in_map__destroy(skel); + skel = NULL; + + /* we need to either wait for or force synchronize_rcu(), before + * checking for "still exists" condition, otherwise map could still be + * resolvable by ID, causing false positives. + * + * Older kernels (5.8 and earlier) freed map only after two + * synchronize_rcu()s, so trigger two, to be entirely sure. + */ + CHECK(kern_sync_rcu(), "sync_rcu", "failed\n"); + CHECK(kern_sync_rcu(), "sync_rcu", "failed\n"); + + fd = bpf_map_get_fd_by_id(map1_id); + if (CHECK(fd >= 0, "map1_leak", "inner_map1 leaked!\n")) { + close(fd); + goto cleanup; + } + fd = bpf_map_get_fd_by_id(map2_id); + if (CHECK(fd >= 0, "map2_leak", "inner_map2 leaked!\n")) { + close(fd); + goto cleanup; + } + cleanup: test_btf_map_in_map__destroy(skel); } diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index 8294ae3ffb3c..43c9cda199b8 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -318,6 +318,9 @@ class DebugfsDir: continue if os.path.isfile(p): + # We need to init trap_flow_action_cookie before read it + if f == "trap_flow_action_cookie": + cmd('echo deadbeef > %s/%s' % (path, f)) _, out = cmd('cat %s/%s' % (path, f)) dfs[f] = out.strip() elif os.path.isdir(p): diff --git a/tools/testing/selftests/bpf/verifier/event_output.c b/tools/testing/selftests/bpf/verifier/event_output.c index 99f8f582c02b..c5e805980409 100644 --- a/tools/testing/selftests/bpf/verifier/event_output.c +++ b/tools/testing/selftests/bpf/verifier/event_output.c @@ -112,6 +112,7 @@ "perfevent for cgroup sockopt", .insns = { __PERF_EVENT_INSNS__ }, .prog_type = BPF_PROG_TYPE_CGROUP_SOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, .fixup_map_event_output = { 4 }, .result = ACCEPT, .retval = 1, 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/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/net/forwarding/ethtool.sh b/tools/testing/selftests/net/forwarding/ethtool.sh index eb8e2a23bbb4..43a948feed26 100755 --- a/tools/testing/selftests/net/forwarding/ethtool.sh +++ b/tools/testing/selftests/net/forwarding/ethtool.sh @@ -252,8 +252,6 @@ check_highest_speed_is_chosen() fi local -a speeds_arr=($(common_speeds_get $h1 $h2 0 1)) - # Remove the first speed, h1 does not advertise this speed. - unset speeds_arr[0] max_speed=${speeds_arr[0]} for current in ${speeds_arr[@]}; do diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index 8c8c7d79c38d..2c522f7a0aec 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -350,7 +350,8 @@ static int test_datapath(uint16_t typeflags, int port_off, int fds[2], fds_udp[2][2], ret; fprintf(stderr, "\ntest: datapath 0x%hx ports %hu,%hu\n", - typeflags, PORT_BASE, PORT_BASE + port_off); + typeflags, (uint16_t)PORT_BASE, + (uint16_t)(PORT_BASE + port_off)); fds[0] = sock_fanout_open(typeflags, 0); fds[1] = sock_fanout_open(typeflags, 0); diff --git a/tools/testing/selftests/net/rxtimestamp.c b/tools/testing/selftests/net/rxtimestamp.c index 422e7761254d..bcb79ba1f214 100644 --- a/tools/testing/selftests/net/rxtimestamp.c +++ b/tools/testing/selftests/net/rxtimestamp.c @@ -329,8 +329,7 @@ int main(int argc, char **argv) bool all_tests = true; int arg_index = 0; int failures = 0; - int s, t; - char opt; + int s, t, opt; while ((opt = getopt_long(argc, argv, "", long_options, &arg_index)) != -1) { diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c index ceaad78e9667..3155fbbf644b 100644 --- a/tools/testing/selftests/net/so_txtime.c +++ b/tools/testing/selftests/net/so_txtime.c @@ -121,7 +121,7 @@ static bool do_recv_one(int fdr, struct timed_send *ts) if (rbuf[0] != ts->data) error(1, 0, "payload mismatch. expected %c", ts->data); - if (labs(tstop - texpect) > cfg_variance_us) + if (llabs(tstop - texpect) > cfg_variance_us) error(1, 0, "exceeds variance (%d us)", cfg_variance_us); return false; diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index 4555f88252ba..a61b7b3da549 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -344,7 +344,7 @@ int main(int argc, char *argv[]) { struct sockaddr_storage listenaddr, addr; unsigned int max_pacing_rate = 0; - size_t total = 0; + uint64_t total = 0; char *host = NULL; int fd, c, on = 1; char *buffer; @@ -473,12 +473,12 @@ int main(int argc, char *argv[]) zflg = 0; } while (total < FILE_SZ) { - ssize_t wr = FILE_SZ - total; + int64_t wr = FILE_SZ - total; if (wr > chunk_size) wr = chunk_size; /* Note : we just want to fill the pipe with 0 bytes */ - wr = send(fd, buffer, wr, zflg ? MSG_ZEROCOPY : 0); + wr = send(fd, buffer, (size_t)wr, zflg ? MSG_ZEROCOPY : 0); if (wr <= 0) break; total += wr; 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 +} |