diff options
| -rw-r--r-- | arch/x86/events/core.c | 63 | ||||
| -rw-r--r-- | arch/x86/events/intel/bts.c | 3 | ||||
| -rw-r--r-- | arch/x86/events/intel/pt.c | 29 | ||||
| -rw-r--r-- | arch/x86/events/intel/uncore.c | 9 | ||||
| -rw-r--r-- | arch/x86/events/intel/uncore.h | 2 | ||||
| -rw-r--r-- | arch/x86/events/intel/uncore_snb.c | 185 | ||||
| -rw-r--r-- | include/linux/perf_event.h | 11 | ||||
| -rw-r--r-- | include/linux/uprobes.h | 24 | ||||
| -rw-r--r-- | kernel/events/core.c | 402 | ||||
| -rw-r--r-- | kernel/events/uprobes.c | 139 | ||||
| -rw-r--r-- | kernel/trace/bpf_trace.c | 25 | ||||
| -rw-r--r-- | kernel/trace/trace_uprobe.c | 31 | ||||
| -rw-r--r-- | tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c | 26 |
13 files changed, 619 insertions, 330 deletions
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index be01823b1bb4..65ab6460aed4 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -41,6 +41,8 @@ #include <asm/desc.h> #include <asm/ldt.h> #include <asm/unwind.h> +#include <asm/uprobes.h> +#include <asm/ibt.h> #include "perf_event.h" @@ -2816,6 +2818,46 @@ static unsigned long get_segment_base(unsigned int segment) return get_desc_base(desc); } +#ifdef CONFIG_UPROBES +/* + * Heuristic-based check if uprobe is installed at the function entry. + * + * Under assumption of user code being compiled with frame pointers, + * `push %rbp/%ebp` is a good indicator that we indeed are. + * + * Similarly, `endbr64` (assuming 64-bit mode) is also a common pattern. + * If we get this wrong, captured stack trace might have one extra bogus + * entry, but the rest of stack trace will still be meaningful. + */ +static bool is_uprobe_at_func_entry(struct pt_regs *regs) +{ + struct arch_uprobe *auprobe; + + if (!current->utask) + return false; + + auprobe = current->utask->auprobe; + if (!auprobe) + return false; + + /* push %rbp/%ebp */ + if (auprobe->insn[0] == 0x55) + return true; + + /* endbr64 (64-bit only) */ + if (user_64bit_mode(regs) && is_endbr(*(u32 *)auprobe->insn)) + return true; + + return false; +} + +#else +static bool is_uprobe_at_func_entry(struct pt_regs *regs) +{ + return false; +} +#endif /* CONFIG_UPROBES */ + #ifdef CONFIG_IA32_EMULATION #include <linux/compat.h> @@ -2827,6 +2869,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent unsigned long ss_base, cs_base; struct stack_frame_ia32 frame; const struct stack_frame_ia32 __user *fp; + u32 ret_addr; if (user_64bit_mode(regs)) return 0; @@ -2836,6 +2879,12 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent fp = compat_ptr(ss_base + regs->bp); pagefault_disable(); + + /* see perf_callchain_user() below for why we do this */ + if (is_uprobe_at_func_entry(regs) && + !get_user(ret_addr, (const u32 __user *)regs->sp)) + perf_callchain_store(entry, ret_addr); + while (entry->nr < entry->max_stack) { if (!valid_user_frame(fp, sizeof(frame))) break; @@ -2864,6 +2913,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs { struct stack_frame frame; const struct stack_frame __user *fp; + unsigned long ret_addr; if (perf_guest_state()) { /* TODO: We don't support guest os callchain now */ @@ -2887,6 +2937,19 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs return; pagefault_disable(); + + /* + * If we are called from uprobe handler, and we are indeed at the very + * entry to user function (which is normally a `push %rbp` instruction, + * under assumption of application being compiled with frame pointers), + * we should read return address from *regs->sp before proceeding + * to follow frame pointers, otherwise we'll skip immediate caller + * as %rbp is not yet setup. + */ + if (is_uprobe_at_func_entry(regs) && + !get_user(ret_addr, (const unsigned long __user *)regs->sp)) + perf_callchain_store(entry, ret_addr); + while (entry->nr < entry->max_stack) { if (!valid_user_frame(fp, sizeof(frame))) break; diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 974e917e65b2..8f78b0c900ef 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -557,9 +557,6 @@ static int bts_event_init(struct perf_event *event) * disabled, so disallow intel_bts driver for unprivileged * users on paranoid systems since it provides trace data * to the user in a zero-copy fashion. - * - * Note that the default paranoia setting permits unprivileged - * users to profile the kernel. */ if (event->attr.exclude_kernel) { ret = perf_allow_kernel(&event->attr); diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index b4aa8daa4773..fd4670a6694e 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -416,7 +416,7 @@ static bool pt_event_valid(struct perf_event *event) static void pt_config_start(struct perf_event *event) { struct pt *pt = this_cpu_ptr(&pt_ctx); - u64 ctl = event->hw.config; + u64 ctl = event->hw.aux_config; ctl |= RTIT_CTL_TRACEEN; if (READ_ONCE(pt->vmx_on)) @@ -424,7 +424,7 @@ static void pt_config_start(struct perf_event *event) else wrmsrl(MSR_IA32_RTIT_CTL, ctl); - WRITE_ONCE(event->hw.config, ctl); + WRITE_ONCE(event->hw.aux_config, ctl); } /* Address ranges and their corresponding msr configuration registers */ @@ -503,7 +503,7 @@ static void pt_config(struct perf_event *event) u64 reg; /* First round: clear STATUS, in particular the PSB byte counter. */ - if (!event->hw.config) { + if (!event->hw.aux_config) { perf_event_itrace_started(event); wrmsrl(MSR_IA32_RTIT_STATUS, 0); } @@ -533,14 +533,14 @@ static void pt_config(struct perf_event *event) reg |= (event->attr.config & PT_CONFIG_MASK); - event->hw.config = reg; + event->hw.aux_config = reg; pt_config_start(event); } static void pt_config_stop(struct perf_event *event) { struct pt *pt = this_cpu_ptr(&pt_ctx); - u64 ctl = READ_ONCE(event->hw.config); + u64 ctl = READ_ONCE(event->hw.aux_config); /* may be already stopped by a PMI */ if (!(ctl & RTIT_CTL_TRACEEN)) @@ -550,7 +550,7 @@ static void pt_config_stop(struct perf_event *event) if (!READ_ONCE(pt->vmx_on)) wrmsrl(MSR_IA32_RTIT_CTL, ctl); - WRITE_ONCE(event->hw.config, ctl); + WRITE_ONCE(event->hw.aux_config, ctl); /* * A wrmsr that disables trace generation serializes other PT @@ -1557,7 +1557,7 @@ void intel_pt_handle_vmx(int on) /* Turn PTs back on */ if (!on && event) - wrmsrl(MSR_IA32_RTIT_CTL, event->hw.config); + wrmsrl(MSR_IA32_RTIT_CTL, event->hw.aux_config); local_irq_restore(flags); } @@ -1606,6 +1606,7 @@ static void pt_event_stop(struct perf_event *event, int mode) * see comment in intel_pt_interrupt(). */ WRITE_ONCE(pt->handle_nmi, 0); + barrier(); pt_config_stop(event); @@ -1657,11 +1658,10 @@ static long pt_event_snapshot_aux(struct perf_event *event, return 0; /* - * Here, handle_nmi tells us if the tracing is on + * There is no PT interrupt in this mode, so stop the trace and it will + * remain stopped while the buffer is copied. */ - if (READ_ONCE(pt->handle_nmi)) - pt_config_stop(event); - + pt_config_stop(event); pt_read_offset(buf); pt_update_head(pt); @@ -1673,11 +1673,10 @@ static long pt_event_snapshot_aux(struct perf_event *event, ret = perf_output_copy_aux(&pt->handle, handle, from, to); /* - * If the tracing was on when we turned up, restart it. - * Compiler barrier not needed as we couldn't have been - * preempted by anything that touches pt->handle_nmi. + * Here, handle_nmi tells us if the tracing was on. + * If the tracing was on, restart it. */ - if (pt->handle_nmi) + if (READ_ONCE(pt->handle_nmi)) pt_config_start(event); return ret; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 64ca8625eb58..d98fac567684 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1816,6 +1816,11 @@ static const struct intel_uncore_init_fun mtl_uncore_init __initconst = { .mmio_init = adl_uncore_mmio_init, }; +static const struct intel_uncore_init_fun lnl_uncore_init __initconst = { + .cpu_init = lnl_uncore_cpu_init, + .mmio_init = lnl_uncore_mmio_init, +}; + static const struct intel_uncore_init_fun icx_uncore_init __initconst = { .cpu_init = icx_uncore_cpu_init, .pci_init = icx_uncore_pci_init, @@ -1893,6 +1898,10 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_VFM(INTEL_RAPTORLAKE_S, &adl_uncore_init), X86_MATCH_VFM(INTEL_METEORLAKE, &mtl_uncore_init), X86_MATCH_VFM(INTEL_METEORLAKE_L, &mtl_uncore_init), + X86_MATCH_VFM(INTEL_ARROWLAKE, &mtl_uncore_init), + X86_MATCH_VFM(INTEL_ARROWLAKE_U, &mtl_uncore_init), + X86_MATCH_VFM(INTEL_ARROWLAKE_H, &mtl_uncore_init), + X86_MATCH_VFM(INTEL_LUNARLAKE_M, &lnl_uncore_init), X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, &spr_uncore_init), X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, &spr_uncore_init), X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, &gnr_uncore_init), diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index 027ef292c602..79ff32e13dcc 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -611,10 +611,12 @@ void skl_uncore_cpu_init(void); void icl_uncore_cpu_init(void); void tgl_uncore_cpu_init(void); void adl_uncore_cpu_init(void); +void lnl_uncore_cpu_init(void); void mtl_uncore_cpu_init(void); void tgl_uncore_mmio_init(void); void tgl_l_uncore_mmio_init(void); void adl_uncore_mmio_init(void); +void lnl_uncore_mmio_init(void); int snb_pci2phy_map_init(int devid); /* uncore_snbep.c */ diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 9462fd9f3b7a..3934e1e4e3b1 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -252,6 +252,7 @@ DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28"); DEFINE_UNCORE_FORMAT_ATTR(cmask8, cmask, "config:24-31"); DEFINE_UNCORE_FORMAT_ATTR(threshold, threshold, "config:24-29"); +DEFINE_UNCORE_FORMAT_ATTR(threshold2, threshold, "config:24-31"); /* Sandy Bridge uncore support */ static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) @@ -746,6 +747,34 @@ void mtl_uncore_cpu_init(void) uncore_msr_uncores = mtl_msr_uncores; } +static struct intel_uncore_type *lnl_msr_uncores[] = { + &mtl_uncore_cbox, + &mtl_uncore_arb, + NULL +}; + +#define LNL_UNC_MSR_GLOBAL_CTL 0x240e + +static void lnl_uncore_msr_init_box(struct intel_uncore_box *box) +{ + if (box->pmu->pmu_idx == 0) + wrmsrl(LNL_UNC_MSR_GLOBAL_CTL, SNB_UNC_GLOBAL_CTL_EN); +} + +static struct intel_uncore_ops lnl_uncore_msr_ops = { + .init_box = lnl_uncore_msr_init_box, + .disable_event = snb_uncore_msr_disable_event, + .enable_event = snb_uncore_msr_enable_event, + .read_counter = uncore_msr_read_counter, +}; + +void lnl_uncore_cpu_init(void) +{ + mtl_uncore_cbox.num_boxes = 4; + mtl_uncore_cbox.ops = &lnl_uncore_msr_ops; + uncore_msr_uncores = lnl_msr_uncores; +} + enum { SNB_PCI_UNCORE_IMC, }; @@ -1475,39 +1504,45 @@ static struct pci_dev *tgl_uncore_get_mc_dev(void) ids++; } + /* Just try to grab 00:00.0 device */ + if (!mc_dev) + mc_dev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(0, 0)); + return mc_dev; } #define TGL_UNCORE_MMIO_IMC_MEM_OFFSET 0x10000 #define TGL_UNCORE_PCI_IMC_MAP_SIZE 0xe000 -static void __uncore_imc_init_box(struct intel_uncore_box *box, - unsigned int base_offset) +static void +uncore_get_box_mmio_addr(struct intel_uncore_box *box, + unsigned int base_offset, + int bar_offset, int step) { struct pci_dev *pdev = tgl_uncore_get_mc_dev(); struct intel_uncore_pmu *pmu = box->pmu; struct intel_uncore_type *type = pmu->type; resource_size_t addr; - u32 mch_bar; + u32 bar; if (!pdev) { pr_warn("perf uncore: Cannot find matched IMC device.\n"); return; } - pci_read_config_dword(pdev, SNB_UNCORE_PCI_IMC_BAR_OFFSET, &mch_bar); - /* MCHBAR is disabled */ - if (!(mch_bar & BIT(0))) { - pr_warn("perf uncore: MCHBAR is disabled. Failed to map IMC free-running counters.\n"); + pci_read_config_dword(pdev, bar_offset, &bar); + if (!(bar & BIT(0))) { + pr_warn("perf uncore: BAR 0x%x is disabled. Failed to map %s counters.\n", + bar_offset, type->name); pci_dev_put(pdev); return; } - mch_bar &= ~BIT(0); - addr = (resource_size_t)(mch_bar + TGL_UNCORE_MMIO_IMC_MEM_OFFSET * pmu->pmu_idx); + bar &= ~BIT(0); + addr = (resource_size_t)(bar + step * pmu->pmu_idx); #ifdef CONFIG_PHYS_ADDR_T_64BIT - pci_read_config_dword(pdev, SNB_UNCORE_PCI_IMC_BAR_OFFSET + 4, &mch_bar); - addr |= ((resource_size_t)mch_bar << 32); + pci_read_config_dword(pdev, bar_offset + 4, &bar); + addr |= ((resource_size_t)bar << 32); #endif addr += base_offset; @@ -1518,6 +1553,14 @@ static void __uncore_imc_init_box(struct intel_uncore_box *box, pci_dev_put(pdev); } +static void __uncore_imc_init_box(struct intel_uncore_box *box, + unsigned int base_offset) +{ + uncore_get_box_mmio_addr(box, base_offset, + SNB_UNCORE_PCI_IMC_BAR_OFFSET, + TGL_UNCORE_MMIO_IMC_MEM_OFFSET); +} + static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) { __uncore_imc_init_box(box, 0); @@ -1612,14 +1655,17 @@ static void adl_uncore_mmio_enable_box(struct intel_uncore_box *box) writel(0, box->io_addr + uncore_mmio_box_ctl(box)); } +#define MMIO_UNCORE_COMMON_OPS() \ + .exit_box = uncore_mmio_exit_box, \ + .disable_box = adl_uncore_mmio_disable_box, \ + .enable_box = adl_uncore_mmio_enable_box, \ + .disable_event = intel_generic_uncore_mmio_disable_event, \ + .enable_event = intel_generic_uncore_mmio_enable_event, \ + .read_counter = uncore_mmio_read_counter, + static struct intel_uncore_ops adl_uncore_mmio_ops = { .init_box = adl_uncore_imc_init_box, - .exit_box = uncore_mmio_exit_box, - .disable_box = adl_uncore_mmio_disable_box, - .enable_box = adl_uncore_mmio_enable_box, - .disable_event = intel_generic_uncore_mmio_disable_event, - .enable_event = intel_generic_uncore_mmio_enable_event, - .read_counter = uncore_mmio_read_counter, + MMIO_UNCORE_COMMON_OPS() }; #define ADL_UNC_CTL_CHMASK_MASK 0x00000f00 @@ -1703,3 +1749,108 @@ void adl_uncore_mmio_init(void) } /* end of Alder Lake MMIO uncore support */ + +/* Lunar Lake MMIO uncore support */ +#define LNL_UNCORE_PCI_SAFBAR_OFFSET 0x68 +#define LNL_UNCORE_MAP_SIZE 0x1000 +#define LNL_UNCORE_SNCU_BASE 0xE4B000 +#define LNL_UNCORE_SNCU_CTR 0x390 +#define LNL_UNCORE_SNCU_CTRL 0x398 +#define LNL_UNCORE_SNCU_BOX_CTL 0x380 +#define LNL_UNCORE_GLOBAL_CTL 0x700 +#define LNL_UNCORE_HBO_BASE 0xE54000 +#define LNL_UNCORE_HBO_OFFSET -4096 +#define LNL_UNCORE_HBO_CTR 0x570 +#define LNL_UNCORE_HBO_CTRL 0x550 +#define LNL_UNCORE_HBO_BOX_CTL 0x548 + +#define LNL_UNC_CTL_THRESHOLD 0xff000000 +#define LNL_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \ + SNB_UNC_CTL_UMASK_MASK | \ + SNB_UNC_CTL_EDGE_DET | \ + SNB_UNC_CTL_INVERT | \ + LNL_UNC_CTL_THRESHOLD) + +static struct attribute *lnl_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_threshold2.attr, + NULL +}; + +static const struct attribute_group lnl_uncore_format_group = { + .name = "format", + .attrs = lnl_uncore_formats_attr, +}; + +static void lnl_uncore_hbo_init_box(struct intel_uncore_box *box) +{ + uncore_get_box_mmio_addr(box, LNL_UNCORE_HBO_BASE, + LNL_UNCORE_PCI_SAFBAR_OFFSET, + LNL_UNCORE_HBO_OFFSET); +} + +static struct intel_uncore_ops lnl_uncore_hbo_ops = { + .init_box = lnl_uncore_hbo_init_box, + MMIO_UNCORE_COMMON_OPS() +}; + +static struct intel_uncore_type lnl_uncore_hbo = { + .name = "hbo", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 64, + .perf_ctr = LNL_UNCORE_HBO_CTR, + .event_ctl = LNL_UNCORE_HBO_CTRL, + .event_mask = LNL_UNC_RAW_EVENT_MASK, + .box_ctl = LNL_UNCORE_HBO_BOX_CTL, + .mmio_map_size = LNL_UNCORE_MAP_SIZE, + .ops = &lnl_uncore_hbo_ops, + .format_group = &lnl_uncore_format_group, +}; + +static void lnl_uncore_sncu_init_box(struct intel_uncore_box *box) +{ + uncore_get_box_mmio_addr(box, LNL_UNCORE_SNCU_BASE, + LNL_UNCORE_PCI_SAFBAR_OFFSET, + 0); + + if (box->io_addr) + writel(ADL_UNCORE_IMC_CTL_INT, box->io_addr + LNL_UNCORE_GLOBAL_CTL); +} + +static struct intel_uncore_ops lnl_uncore_sncu_ops = { + .init_box = lnl_uncore_sncu_init_box, + MMIO_UNCORE_COMMON_OPS() +}; + +static struct intel_uncore_type lnl_uncore_sncu = { + .name = "sncu", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 64, + .perf_ctr = LNL_UNCORE_SNCU_CTR, + .event_ctl = LNL_UNCORE_SNCU_CTRL, + .event_mask = LNL_UNC_RAW_EVENT_MASK, + .box_ctl = LNL_UNCORE_SNCU_BOX_CTL, + .mmio_map_size = LNL_UNCORE_MAP_SIZE, + .ops = &lnl_uncore_sncu_ops, + .format_group = &lnl_uncore_format_group, +}; + +static struct intel_uncore_type *lnl_mmio_uncores[] = { + &adl_uncore_imc, + &lnl_uncore_hbo, + &lnl_uncore_sncu, + &adl_uncore_imc_free_running, + NULL +}; + +void lnl_uncore_mmio_init(void) +{ + uncore_mmio_uncores = lnl_mmio_uncores; +} + +/* end of Lunar Lake MMIO uncore support */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1a8942277dda..701549967c18 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -168,6 +168,9 @@ struct hw_perf_event { struct hw_perf_event_extra extra_reg; struct hw_perf_event_extra branch_reg; }; + struct { /* aux / Intel-PT */ + u64 aux_config; + }; struct { /* software */ struct hrtimer hrtimer; }; @@ -963,12 +966,16 @@ struct perf_event_context { struct rcu_head rcu_head; /* - * Sum (event->pending_work + event->pending_work) + * The count of events for which using the switch-out fast path + * should be avoided. + * + * Sum (event->pending_work + events with + * (attr->inherit && (attr->sample_type & PERF_SAMPLE_READ))) * * The SIGTRAP is targeted at ctx->task, as such it won't do changing * that until the signal is delivered. */ - local_t nr_pending; + local_t nr_no_switch_fast; }; struct perf_cpu_pmu_context { diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index b503fafb7fb3..f50df1fa93e7 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -16,6 +16,7 @@ #include <linux/types.h> #include <linux/wait.h> +struct uprobe; struct vm_area_struct; struct mm_struct; struct inode; @@ -76,6 +77,8 @@ struct uprobe_task { struct uprobe *active_uprobe; unsigned long xol_vaddr; + struct arch_uprobe *auprobe; + struct return_instance *return_instances; unsigned int depth; }; @@ -110,10 +113,9 @@ extern bool is_trap_insn(uprobe_opcode_t *insn); extern unsigned long uprobe_get_swbp_addr(struct pt_regs *regs); extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs); extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t); -extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); -extern int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc); -extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool); -extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); +extern struct uprobe *uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc); +extern int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool); +extern void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc); extern int uprobe_mmap(struct vm_area_struct *vma); extern void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void uprobe_start_dup_mmap(void); @@ -151,22 +153,18 @@ static inline void uprobes_init(void) #define uprobe_get_trap_addr(regs) instruction_pointer(regs) -static inline int -uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) -{ - return -ENOSYS; -} -static inline int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc) +static inline struct uprobe * +uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc) { - return -ENOSYS; + return ERR_PTR(-ENOSYS); } static inline int -uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool add) +uprobe_apply(struct uprobe* uprobe, struct uprobe_consumer *uc, bool add) { return -ENOSYS; } static inline void -uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) +uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc) { } static inline int uprobe_mmap(struct vm_area_struct *vma) diff --git a/kernel/events/core.c b/kernel/events/core.c index 8a6c6bbcd658..4acec97e5448 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -155,20 +155,55 @@ static int cpu_function_call(int cpu, remote_function_f func, void *info) return data.ret; } +enum event_type_t { + EVENT_FLEXIBLE = 0x01, + EVENT_PINNED = 0x02, + EVENT_TIME = 0x04, + EVENT_FROZEN = 0x08, + /* see ctx_resched() for details */ + EVENT_CPU = 0x10, + EVENT_CGROUP = 0x20, + + /* compound helpers */ + EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED, + EVENT_TIME_FROZEN = EVENT_TIME | EVENT_FROZEN, +}; + +static inline void __perf_ctx_lock(struct perf_event_context *ctx) +{ + raw_spin_lock(&ctx->lock); + WARN_ON_ONCE(ctx->is_active & EVENT_FROZEN); +} + static void perf_ctx_lock(struct perf_cpu_context *cpuctx, struct perf_event_context *ctx) { - raw_spin_lock(&cpuctx->ctx.lock); + __perf_ctx_lock(&cpuctx->ctx); if (ctx) - raw_spin_lock(&ctx->lock); + __perf_ctx_lock(ctx); +} + +static inline void __perf_ctx_unlock(struct perf_event_context *ctx) +{ + /* + * If ctx_sched_in() didn't again set any ALL flags, clean up + * after ctx_sched_out() by clearing is_active. + */ + if (ctx->is_active & EVENT_FROZEN) { + if (!(ctx->is_active & EVENT_ALL)) + ctx->is_active = 0; + else + ctx->is_active &= ~EVENT_FROZEN; + } + raw_spin_unlock(&ctx->lock); } static void perf_ctx_unlock(struct perf_cpu_context *cpuctx, struct perf_event_context *ctx) { if (ctx) - raw_spin_unlock(&ctx->lock); - raw_spin_unlock(&cpuctx->ctx.lock); + __perf_ctx_unlock(ctx); + __perf_ctx_unlock(&cpuctx->ctx); } #define TASK_TOMBSTONE ((void *)-1L) @@ -264,6 +299,7 @@ static void event_function_call(struct perf_event *event, event_f func, void *da { struct perf_event_context *ctx = event->ctx; struct task_struct *task = READ_ONCE(ctx->task); /* verified in event_function */ + struct perf_cpu_context *cpuctx; struct event_function_struct efs = { .event = event, .func = func, @@ -291,22 +327,25 @@ again: if (!task_function_call(task, event_function, &efs)) return; - raw_spin_lock_irq(&ctx->lock); + local_irq_disable(); + cpuctx = this_cpu_ptr(&perf_cpu_context); + perf_ctx_lock(cpuctx, ctx); /* * Reload the task pointer, it might have been changed by * a concurrent perf_event_context_sched_out(). */ task = ctx->task; - if (task == TASK_TOMBSTONE) { - raw_spin_unlock_irq(&ctx->lock); - return; - } + if (task == TASK_TOMBSTONE) + goto unlock; if (ctx->is_active) { - raw_spin_unlock_irq(&ctx->lock); + perf_ctx_unlock(cpuctx, ctx); + local_irq_enable(); goto again; } func(event, NULL, ctx, data); - raw_spin_unlock_irq(&ctx->lock); +unlock: + perf_ctx_unlock(cpuctx, ctx); + local_irq_enable(); } /* @@ -369,16 +408,6 @@ unlock: (PERF_SAMPLE_BRANCH_KERNEL |\ PERF_SAMPLE_BRANCH_HV) -enum event_type_t { - EVENT_FLEXIBLE = 0x1, - EVENT_PINNED = 0x2, - EVENT_TIME = 0x4, - /* see ctx_resched() for details */ - EVENT_CPU = 0x8, - EVENT_CGROUP = 0x10, - EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED, -}; - /* * perf_sched_events : >0 events exist */ @@ -685,30 +714,32 @@ do { \ ___p; \ }) +#define for_each_epc(_epc, _ctx, _pmu, _cgroup) \ + list_for_each_entry(_epc, &((_ctx)->pmu_ctx_list), pmu_ctx_entry) \ + if (_cgroup && !_epc->nr_cgroups) \ + continue; \ + else if (_pmu && _epc->pmu != _pmu) \ + continue; \ + else + static void perf_ctx_disable(struct perf_event_context *ctx, bool cgroup) { struct perf_event_pmu_context *pmu_ctx; - list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) { - if (cgroup && !pmu_ctx->nr_cgroups) - continue; + for_each_epc(pmu_ctx, ctx, NULL, cgroup) perf_pmu_disable(pmu_ctx->pmu); - } } static void perf_ctx_enable(struct perf_event_context *ctx, bool cgroup) { struct perf_event_pmu_context *pmu_ctx; - list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) { - if (cgroup && !pmu_ctx->nr_cgroups) - continue; + for_each_epc(pmu_ctx, ctx, NULL, cgroup) perf_pmu_enable(pmu_ctx->pmu); - } } -static void ctx_sched_out(struct perf_event_context *ctx, enum event_type_t event_type); -static void ctx_sched_in(struct perf_event_context *ctx, enum event_type_t event_type); +static void ctx_sched_out(struct perf_event_context *ctx, struct pmu *pmu, enum event_type_t event_type); +static void ctx_sched_in(struct perf_event_context *ctx, struct pmu *pmu, enum event_type_t event_type); #ifdef CONFIG_CGROUP_PERF @@ -865,7 +896,7 @@ static void perf_cgroup_switch(struct task_struct *task) perf_ctx_lock(cpuctx, cpuctx->task_ctx); perf_ctx_disable(&cpuctx->ctx, true); - ctx_sched_out(&cpuctx->ctx, EVENT_ALL|EVENT_CGROUP); + ctx_sched_out(&cpuctx->ctx, NULL, EVENT_ALL|EVENT_CGROUP); /* * must not be done before ctxswout due * to update_cgrp_time_from_cpuctx() in @@ -877,7 +908,7 @@ static void perf_cgroup_switch(struct task_struct *task) * perf_cgroup_set_timestamp() in ctx_sched_in() * to not have to pass task around */ - ctx_sched_in(&cpuctx->ctx, EVENT_ALL|EVENT_CGROUP); + ctx_sched_in(&cpuctx->ctx, NULL, EVENT_ALL|EVENT_CGROUP); perf_ctx_enable(&cpuctx->ctx, true); perf_ctx_unlock(cpuctx, cpuctx->task_ctx); @@ -1769,6 +1800,14 @@ perf_event_groups_next(struct perf_event *event, struct pmu *pmu) typeof(*event), group_node)) /* + * Does the event attribute request inherit with PERF_SAMPLE_READ + */ +static inline bool has_inherit_and_sample_read(struct perf_event_attr *attr) +{ + return attr->inherit && (attr->sample_type & PERF_SAMPLE_READ); +} + +/* * Add an event from the lists for its context. * Must be called with ctx->mutex and ctx->lock held. */ @@ -1798,6 +1837,8 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx) ctx->nr_user++; if (event->attr.inherit_stat) ctx->nr_stat++; + if (has_inherit_and_sample_read(&event->attr)) + local_inc(&ctx->nr_no_switch_fast); if (event->state > PERF_EVENT_STATE_OFF) perf_cgroup_event_enable(event, ctx); @@ -2022,6 +2063,8 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx) ctx->nr_user--; if (event->attr.inherit_stat) ctx->nr_stat--; + if (has_inherit_and_sample_read(&event->attr)) + local_dec(&ctx->nr_no_switch_fast); list_del_rcu(&event->event_entry); @@ -2317,6 +2360,45 @@ group_sched_out(struct perf_event *group_event, struct perf_event_context *ctx) event_sched_out(event, ctx); } +static inline void +__ctx_time_update(struct perf_cpu_context *cpuctx, struct perf_event_context *ctx, bool final) +{ + if (ctx->is_active & EVENT_TIME) { + if (ctx->is_active & EVENT_FROZEN) + return; + update_context_time(ctx); + update_cgrp_time_from_cpuctx(cpuctx, final); + } +} + +static inline void +ctx_time_update(struct perf_cpu_context *cpuctx, struct perf_event_context *ctx) +{ + __ctx_time_update(cpuctx, ctx, false); +} + +/* + * To be used inside perf_ctx_lock() / perf_ctx_unlock(). Lasts until perf_ctx_unlock(). + */ +static inline void +ctx_time_freeze(struct perf_cpu_context *cpuctx, struct perf_event_context *ctx) +{ + ctx_time_update(cpuctx, ctx); + if (ctx->is_active & EVENT_TIME) + ctx->is_active |= EVENT_FROZEN; +} + +static inline void +ctx_time_update_event(struct perf_event_context *ctx, struct perf_event *event) +{ + if (ctx->is_active & EVENT_TIME) { + if (ctx->is_active & EVENT_FROZEN) + return; + update_context_time(ctx); + update_cgrp_time_from_event(event); + } +} + #define DETACH_GROUP 0x01UL #define DETACH_CHILD 0x02UL #define DETACH_DEAD 0x04UL @@ -2336,10 +2418,7 @@ __perf_remove_from_context(struct perf_event *event, struct perf_event_pmu_context *pmu_ctx = event->pmu_ctx; unsigned long flags = (unsigned long)info; - if (ctx->is_active & EVENT_TIME) { - update_context_time(ctx); - update_cgrp_time_from_cpuctx(cpuctx, false); - } + ctx_time_update(cpuctx, ctx); /* * Ensure event_sched_out() switches to OFF, at the very least @@ -2424,12 +2503,8 @@ static void __perf_event_disable(struct perf_event *event, if (event->state < PERF_EVENT_STATE_INACTIVE) return; - if (ctx->is_active & EVENT_TIME) { - update_context_time(ctx); - update_cgrp_time_from_event(event); - } - perf_pmu_disable(event->pmu_ctx->pmu); + ctx_time_update_event(ctx, event); if (event == event->group_leader) group_sched_out(event, ctx); @@ -2645,7 +2720,8 @@ static void add_event_to_ctx(struct perf_event *event, } static void task_ctx_sched_out(struct perf_event_context *ctx, - enum event_type_t event_type) + struct pmu *pmu, + enum event_type_t event_type) { struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); @@ -2655,18 +2731,19 @@ static void task_ctx_sched_out(struct perf_event_context *ctx, if (WARN_ON_ONCE(ctx != cpuctx->task_ctx)) return; - ctx_sched_out(ctx, event_type); + ctx_sched_out(ctx, pmu, event_type); } static void perf_event_sched_in(struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx) + struct perf_event_context *ctx, + struct pmu *pmu) { - ctx_sched_in(&cpuctx->ctx, EVENT_PINNED); + ctx_sched_in(&cpuctx->ctx, pmu, EVENT_PINNED); if (ctx) - ctx_sched_in(ctx, EVENT_PINNED); - ctx_sched_in(&cpuctx->ctx, EVENT_FLEXIBLE); + ctx_sched_in(ctx, pmu, EVENT_PINNED); + ctx_sched_in(&cpuctx->ctx, pmu, EVENT_FLEXIBLE); if (ctx) - ctx_sched_in(ctx, EVENT_FLEXIBLE); + ctx_sched_in(ctx, pmu, EVENT_FLEXIBLE); } /* @@ -2684,16 +2761,12 @@ static void perf_event_sched_in(struct perf_cpu_context *cpuctx, * event_type is a bit mask of the types of events involved. For CPU events, * event_type is only either EVENT_PINNED or EVENT_FLEXIBLE. */ -/* - * XXX: ctx_resched() reschedule entire perf_event_context while adding new - * event to the context or enabling existing event in the context. We can - * probably optimize it by rescheduling only affected pmu_ctx. - */ static void ctx_resched(struct perf_cpu_context *cpuctx, struct perf_event_context *task_ctx, - enum event_type_t event_type) + struct pmu *pmu, enum event_type_t event_type) { bool cpu_event = !!(event_type & EVENT_CPU); + struct perf_event_pmu_context *epc; /* * If pinned groups are involved, flexible groups also need to be @@ -2704,10 +2777,14 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, event_type &= EVENT_ALL; - perf_ctx_disable(&cpuctx->ctx, false); + for_each_epc(epc, &cpuctx->ctx, pmu, false) + perf_pmu_disable(epc->pmu); + if (task_ctx) { - perf_ctx_disable(task_ctx, false); - task_ctx_sched_out(task_ctx, event_type); + for_each_epc(epc, task_ctx, pmu, false) + perf_pmu_disable(epc->pmu); + + task_ctx_sched_out(task_ctx, pmu, event_type); } /* @@ -2718,15 +2795,19 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, * - otherwise, do nothing more. */ if (cpu_event) - ctx_sched_out(&cpuctx->ctx, event_type); + ctx_sched_out(&cpuctx->ctx, pmu, event_type); else if (event_type & EVENT_PINNED) - ctx_sched_out(&cpuctx->ctx, EVENT_FLEXIBLE); + ctx_sched_out(&cpuctx->ctx, pmu, EVENT_FLEXIBLE); + + perf_event_sched_in(cpuctx, task_ctx, pmu); - perf_event_sched_in(cpuctx, task_ctx); + for_each_epc(epc, &cpuctx->ctx, pmu, false) + perf_pmu_enable(epc->pmu); - perf_ctx_enable(&cpuctx->ctx, false); - if (task_ctx) - perf_ctx_enable(task_ctx, false); + if (task_ctx) { + for_each_epc(epc, task_ctx, pmu, false) + perf_pmu_enable(epc->pmu); + } } void perf_pmu_resched(struct pmu *pmu) @@ -2735,7 +2816,7 @@ void perf_pmu_resched(struct pmu *pmu) struct perf_event_context *task_ctx = cpuctx->task_ctx; perf_ctx_lock(cpuctx, task_ctx); - ctx_resched(cpuctx, task_ctx, EVENT_ALL|EVENT_CPU); + ctx_resched(cpuctx, task_ctx, pmu, EVENT_ALL|EVENT_CPU); perf_ctx_unlock(cpuctx, task_ctx); } @@ -2791,9 +2872,10 @@ static int __perf_install_in_context(void *info) #endif if (reprogram) { - ctx_sched_out(ctx, EVENT_TIME); + ctx_time_freeze(cpuctx, ctx); add_event_to_ctx(event, ctx); - ctx_resched(cpuctx, task_ctx, get_event_type(event)); + ctx_resched(cpuctx, task_ctx, event->pmu_ctx->pmu, + get_event_type(event)); } else { add_event_to_ctx(event, ctx); } @@ -2936,8 +3018,7 @@ static void __perf_event_enable(struct perf_event *event, event->state <= PERF_EVENT_STATE_ERROR) return; - if (ctx->is_active) - ctx_sched_out(ctx, EVENT_TIME); + ctx_time_freeze(cpuctx, ctx); perf_event_set_state(event, PERF_EVENT_STATE_INACTIVE); perf_cgroup_event_enable(event, ctx); @@ -2945,25 +3026,21 @@ static void __perf_event_enable(struct perf_event *event, if (!ctx->is_active) return; - if (!event_filter_match(event)) { - ctx_sched_in(ctx, EVENT_TIME); + if (!event_filter_match(event)) return; - } /* * If the event is in a group and isn't the group leader, * then don't put it on unless the group is on. */ - if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) { - ctx_sched_in(ctx, EVENT_TIME); + if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) return; - } task_ctx = cpuctx->task_ctx; if (ctx->task) WARN_ON_ONCE(task_ctx != ctx); - ctx_resched(cpuctx, task_ctx, get_event_type(event)); + ctx_resched(cpuctx, task_ctx, event->pmu_ctx->pmu, get_event_type(event)); } /* @@ -3231,7 +3308,7 @@ static void __pmu_ctx_sched_out(struct perf_event_pmu_context *pmu_ctx, struct perf_event *event, *tmp; struct pmu *pmu = pmu_ctx->pmu; - if (ctx->task && !ctx->is_active) { + if (ctx->task && !(ctx->is_active & EVENT_ALL)) { struct perf_cpu_pmu_context *cpc; cpc = this_cpu_ptr(pmu->cpu_pmu_context); @@ -3239,7 +3316,7 @@ static void __pmu_ctx_sched_out(struct perf_event_pmu_context *pmu_ctx, cpc->task_epc = NULL; } - if (!event_type) + if (!(event_type & EVENT_ALL)) return; perf_pmu_disable(pmu); @@ -3265,8 +3342,17 @@ static void __pmu_ctx_sched_out(struct perf_event_pmu_context *pmu_ctx, perf_pmu_enable(pmu); } +/* + * Be very careful with the @pmu argument since this will change ctx state. + * The @pmu argument works for ctx_resched(), because that is symmetric in + * ctx_sched_out() / ctx_sched_in() usage and the ctx state ends up invariant. + * + * However, if you were to be asymmetrical, you could end up with messed up + * state, eg. ctx->is_active cleared even though most EPCs would still actually + * be active. + */ static void -ctx_sched_out(struct perf_event_context *ctx, enum event_type_t event_type) +ctx_sched_out(struct perf_event_context *ctx, struct pmu *pmu, enum event_type_t event_type) { struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); struct perf_event_pmu_context *pmu_ctx; @@ -3297,34 +3383,36 @@ ctx_sched_out(struct perf_event_context *ctx, enum event_type_t event_type) * * would only update time for the pinned events. */ - if (is_active & EVENT_TIME) { - /* update (and stop) ctx time */ - update_context_time(ctx); - update_cgrp_time_from_cpuctx(cpuctx, ctx == &cpuctx->ctx); + __ctx_time_update(cpuctx, ctx, ctx == &cpuctx->ctx); + + /* + * CPU-release for the below ->is_active store, + * see __load_acquire() in perf_event_time_now() + */ + barrier(); + ctx->is_active &= ~event_type; + + if (!(ctx->is_active & EVENT_ALL)) { /* - * CPU-release for the below ->is_active store, - * see __load_acquire() in perf_event_time_now() + * For FROZEN, preserve TIME|FROZEN such that perf_event_time_now() + * does not observe a hole. perf_ctx_unlock() will clean up. */ - barrier(); + if (ctx->is_active & EVENT_FROZEN) + ctx->is_active &= EVENT_TIME_FROZEN; + else + ctx->is_active = 0; } - ctx->is_active &= ~event_type; - if (!(ctx->is_active & EVENT_ALL)) - ctx->is_active = 0; - if (ctx->task) { WARN_ON_ONCE(cpuctx->task_ctx != ctx); - if (!ctx->is_active) + if (!(ctx->is_active & EVENT_ALL)) cpuctx->task_ctx = NULL; } is_active ^= ctx->is_active; /* changed bits */ - list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) { - if (cgroup && !pmu_ctx->nr_cgroups) - continue; + for_each_epc(pmu_ctx, ctx, pmu, cgroup) __pmu_ctx_sched_out(pmu_ctx, is_active); - } } /* @@ -3517,12 +3605,17 @@ perf_event_context_sched_out(struct task_struct *task, struct task_struct *next) perf_ctx_disable(ctx, false); - /* PMIs are disabled; ctx->nr_pending is stable. */ - if (local_read(&ctx->nr_pending) || - local_read(&next_ctx->nr_pending)) { + /* PMIs are disabled; ctx->nr_no_switch_fast is stable. */ + if (local_read(&ctx->nr_no_switch_fast) || + local_read(&next_ctx->nr_no_switch_fast)) { /* * Must not swap out ctx when there's pending * events that rely on the ctx->task relation. + * + * Likewise, when a context contains inherit + + * SAMPLE_READ events they should be switched + * out using the slow path so that they are + * treated as if they were distinct contexts. */ raw_spin_unlock(&next_ctx->lock); rcu_read_unlock(); @@ -3563,7 +3656,7 @@ unlock: inside_switch: perf_ctx_sched_task_cb(ctx, false); - task_ctx_sched_out(ctx, EVENT_ALL); + task_ctx_sched_out(ctx, NULL, EVENT_ALL); perf_ctx_enable(ctx, false); raw_spin_unlock(&ctx->lock); @@ -3861,29 +3954,22 @@ static void pmu_groups_sched_in(struct perf_event_context *ctx, merge_sched_in, &can_add_hw); } -static void ctx_groups_sched_in(struct perf_event_context *ctx, - struct perf_event_groups *groups, - bool cgroup) +static void __pmu_ctx_sched_in(struct perf_event_pmu_context *pmu_ctx, + enum event_type_t event_type) { - struct perf_event_pmu_context *pmu_ctx; - - list_for_each_entry(pmu_ctx, &ctx->pmu_ctx_list, pmu_ctx_entry) { - if (cgroup && !pmu_ctx->nr_cgroups) - continue; - pmu_groups_sched_in(ctx, groups, pmu_ctx->pmu); - } -} + struct perf_event_context *ctx = pmu_ctx->ctx; -static void __pmu_ctx_sched_in(struct perf_event_context *ctx, - struct pmu *pmu) -{ - pmu_groups_sched_in(ctx, &ctx->flexible_groups, pmu); + if (event_type & EVENT_PINNED) + pmu_groups_sched_in(ctx, &ctx->pinned_groups, pmu_ctx->pmu); + if (event_type & EVENT_FLEXIBLE) + pmu_groups_sched_in(ctx, &ctx->flexible_groups, pmu_ctx->pmu); } static void -ctx_sched_in(struct perf_event_context *ctx, enum event_type_t event_type) +ctx_sched_in(struct perf_event_context *ctx, struct pmu *pmu, enum event_type_t event_type) { struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context); + struct perf_event_pmu_context *pmu_ctx; int is_active = ctx->is_active; bool cgroup = event_type & EVENT_CGROUP; @@ -3907,7 +3993,7 @@ ctx_sched_in(struct perf_event_context *ctx, enum event_type_t event_type) ctx->is_active |= (event_type | EVENT_TIME); if (ctx->task) { - if (!is_active) + if (!(is_active & EVENT_ALL)) cpuctx->task_ctx = ctx; else WARN_ON_ONCE(cpuctx->task_ctx != ctx); @@ -3919,12 +4005,16 @@ ctx_sched_in(struct perf_event_context *ctx, enum event_type_t event_type) * First go through the list and put on any pinned groups * in order to give them the best chance of going on. */ - if (is_active & EVENT_PINNED) - ctx_groups_sched_in(ctx, &ctx->pinned_groups, cgroup); + if (is_active & EVENT_PINNED) { + for_each_epc(pmu_ctx, ctx, pmu, cgroup) + __pmu_ctx_sched_in(pmu_ctx, EVENT_PINNED); + } /* Then walk through the lower prio flexible groups */ - if (is_active & EVENT_FLEXIBLE) - ctx_groups_sched_in(ctx, &ctx->flexible_groups, cgroup); + if (is_active & EVENT_FLEXIBLE) { + for_each_epc(pmu_ctx, ctx, pmu, cgroup) + __pmu_ctx_sched_in(pmu_ctx, EVENT_FLEXIBLE); + } } static void perf_event_context_sched_in(struct task_struct *task) @@ -3967,10 +4057,10 @@ static void perf_event_context_sched_in(struct task_struct *task) */ if (!RB_EMPTY_ROOT(&ctx->pinned_groups.tree)) { perf_ctx_disable(&cpuctx->ctx, false); - ctx_sched_out(&cpuctx->ctx, EVENT_FLEXIBLE); + ctx_sched_out(&cpuctx->ctx, NULL, EVENT_FLEXIBLE); } - perf_event_sched_in(cpuctx, ctx); + perf_event_sched_in(cpuctx, ctx, NULL); perf_ctx_sched_task_cb(cpuctx->task_ctx, true); @@ -4311,14 +4401,14 @@ static bool perf_rotate_context(struct perf_cpu_pmu_context *cpc) update_context_time(&cpuctx->ctx); __pmu_ctx_sched_out(cpu_epc, EVENT_FLEXIBLE); rotate_ctx(&cpuctx->ctx, cpu_event); - __pmu_ctx_sched_in(&cpuctx->ctx, pmu); + __pmu_ctx_sched_in(cpu_epc, EVENT_FLEXIBLE); } if (task_event) rotate_ctx(task_epc->ctx, task_event); if (task_event || (task_epc && cpu_event)) - __pmu_ctx_sched_in(task_epc->ctx, pmu); + __pmu_ctx_sched_in(task_epc, EVENT_FLEXIBLE); perf_pmu_enable(pmu); perf_ctx_unlock(cpuctx, cpuctx->task_ctx); @@ -4384,7 +4474,7 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx) cpuctx = this_cpu_ptr(&perf_cpu_context); perf_ctx_lock(cpuctx, ctx); - ctx_sched_out(ctx, EVENT_TIME); + ctx_time_freeze(cpuctx, ctx); list_for_each_entry(event, &ctx->event_list, event_entry) { enabled |= event_enable_on_exec(event, ctx); @@ -4396,9 +4486,7 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx) */ if (enabled) { clone_ctx = unclone_ctx(ctx); - ctx_resched(cpuctx, ctx, event_type); - } else { - ctx_sched_in(ctx, EVENT_TIME); + ctx_resched(cpuctx, ctx, NULL, event_type); } perf_ctx_unlock(cpuctx, ctx); @@ -4501,10 +4589,7 @@ static void __perf_event_read(void *info) return; raw_spin_lock(&ctx->lock); - if (ctx->is_active & EVENT_TIME) { - update_context_time(ctx); - update_cgrp_time_from_event(event); - } + ctx_time_update_event(ctx, event); perf_event_update_time(event); if (data->group) @@ -4539,8 +4624,11 @@ unlock: raw_spin_unlock(&ctx->lock); } -static inline u64 perf_event_count(struct perf_event *event) +static inline u64 perf_event_count(struct perf_event *event, bool self) { + if (self) + return local64_read(&event->count); + return local64_read(&event->count) + atomic64_read(&event->child_count); } @@ -4701,10 +4789,7 @@ again: * May read while context is not active (e.g., thread is * blocked), in that case we cannot update context time */ - if (ctx->is_active & EVENT_TIME) { - update_context_time(ctx); - update_cgrp_time_from_event(event); - } + ctx_time_update_event(ctx, event); perf_event_update_time(event); if (group) @@ -5205,7 +5290,7 @@ static void perf_pending_task_sync(struct perf_event *event) */ if (task_work_cancel(current, head)) { event->pending_work = 0; - local_dec(&event->ctx->nr_pending); + local_dec(&event->ctx->nr_no_switch_fast); return; } @@ -5499,7 +5584,7 @@ static u64 __perf_event_read_value(struct perf_event *event, u64 *enabled, u64 * mutex_lock(&event->child_mutex); (void)perf_event_read(event, false); - total += perf_event_count(event); + total += perf_event_count(event, false); *enabled += event->total_time_enabled + atomic64_read(&event->child_total_time_enabled); @@ -5508,7 +5593,7 @@ static u64 __perf_event_read_value(struct perf_event *event, u64 *enabled, u64 * list_for_each_entry(child, &event->child_list, child_list) { (void)perf_event_read(child, false); - total += perf_event_count(child); + total += perf_event_count(child, false); *enabled += child->total_time_enabled; *running += child->total_time_running; } @@ -5590,14 +5675,14 @@ static int __perf_read_group_add(struct perf_event *leader, /* * Write {count,id} tuples for every sibling. */ - values[n++] += perf_event_count(leader); + values[n++] += perf_event_count(leader, false); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(leader); if (read_format & PERF_FORMAT_LOST) values[n++] = atomic64_read(&leader->lost_samples); for_each_sibling_event(sub, leader) { - values[n++] += perf_event_count(sub); + values[n++] += perf_event_count(sub, false); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(sub); if (read_format & PERF_FORMAT_LOST) @@ -6177,7 +6262,7 @@ void perf_event_update_userpage(struct perf_event *event) ++userpg->lock; barrier(); userpg->index = perf_event_index(event); - userpg->offset = perf_event_count(event); + userpg->offset = perf_event_count(event, false); if (userpg->index) userpg->offset -= local64_read(&event->hw.prev_count); @@ -6874,7 +6959,7 @@ static void perf_pending_task(struct callback_head *head) if (event->pending_work) { event->pending_work = 0; perf_sigtrap(event); - local_dec(&event->ctx->nr_pending); + local_dec(&event->ctx->nr_no_switch_fast); rcuwait_wake_up(&event->pending_work_wait); } rcu_read_unlock(); @@ -7256,7 +7341,7 @@ static void perf_output_read_one(struct perf_output_handle *handle, u64 values[5]; int n = 0; - values[n++] = perf_event_count(event); + values[n++] = perf_event_count(event, has_inherit_and_sample_read(&event->attr)); if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { values[n++] = enabled + atomic64_read(&event->child_total_time_enabled); @@ -7274,14 +7359,15 @@ static void perf_output_read_one(struct perf_output_handle *handle, } static void perf_output_read_group(struct perf_output_handle *handle, - struct perf_event *event, - u64 enabled, u64 running) + struct perf_event *event, + u64 enabled, u64 running) { struct perf_event *leader = event->group_leader, *sub; u64 read_format = event->attr.read_format; unsigned long flags; u64 values[6]; int n = 0; + bool self = has_inherit_and_sample_read(&event->attr); /* * Disabling interrupts avoids all counter scheduling @@ -7301,7 +7387,7 @@ static void perf_output_read_group(struct perf_output_handle *handle, (leader->state == PERF_EVENT_STATE_ACTIVE)) leader->pmu->read(leader); - values[n++] = perf_event_count(leader); + values[n++] = perf_event_count(leader, self); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(leader); if (read_format & PERF_FORMAT_LOST) @@ -7316,7 +7402,7 @@ static void perf_output_read_group(struct perf_output_handle *handle, (sub->state == PERF_EVENT_STATE_ACTIVE)) sub->pmu->read(sub); - values[n++] = perf_event_count(sub); + values[n++] = perf_event_count(sub, self); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(sub); if (read_format & PERF_FORMAT_LOST) @@ -7337,6 +7423,10 @@ static void perf_output_read_group(struct perf_output_handle *handle, * The problem is that its both hard and excessively expensive to iterate the * child list, not to mention that its impossible to IPI the children running * on another CPU, from interrupt/NMI context. + * + * Instead the combination of PERF_SAMPLE_READ and inherit will track per-thread + * counts rather than attempting to accumulate some value across all children on + * all cores. */ static void perf_output_read(struct perf_output_handle *handle, struct perf_event *event) @@ -9747,7 +9837,7 @@ static int __perf_event_overflow(struct perf_event *event, if (!event->pending_work && !task_work_add(current, &event->pending_task, notify_mode)) { event->pending_work = pending_id; - local_inc(&event->ctx->nr_pending); + local_inc(&event->ctx->nr_no_switch_fast); event->pending_addr = 0; if (valid_sample && (data->sample_flags & PERF_SAMPLE_ADDR)) @@ -12064,10 +12154,12 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, local64_set(&hwc->period_left, hwc->sample_period); /* - * We currently do not support PERF_SAMPLE_READ on inherited events. + * We do not support PERF_SAMPLE_READ on inherited events unless + * PERF_SAMPLE_TID is also selected, which allows inherited events to + * collect per-thread samples. * See perf_output_read(). */ - if (attr->inherit && (attr->sample_type & PERF_SAMPLE_READ)) + if (has_inherit_and_sample_read(attr) && !(attr->sample_type & PERF_SAMPLE_TID)) goto err_ns; if (!has_branch_stack(event)) @@ -13091,7 +13183,7 @@ static void sync_child_event(struct perf_event *child_event) perf_event_read_event(child_event, task); } - child_val = perf_event_count(child_event); + child_val = perf_event_count(child_event, false); /* * Add back the child's count to the parent's count: @@ -13182,7 +13274,7 @@ static void perf_event_exit_task_context(struct task_struct *child) * in. */ raw_spin_lock_irq(&child_ctx->lock); - task_ctx_sched_out(child_ctx, EVENT_ALL); + task_ctx_sched_out(child_ctx, NULL, EVENT_ALL); /* * Now that the context is inactive, destroy the task <-> ctx relation @@ -13731,7 +13823,7 @@ static void __perf_event_exit_context(void *__info) struct perf_event *event; raw_spin_lock(&ctx->lock); - ctx_sched_out(ctx, EVENT_TIME); + ctx_sched_out(ctx, NULL, EVENT_TIME); list_for_each_entry(event, &ctx->event_list, event_entry) __perf_remove_from_context(event, cpuctx, ctx, (void *)DETACH_GROUP); raw_spin_unlock(&ctx->lock); diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 50d7949be2b1..cac45ea4c284 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -453,7 +453,7 @@ static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm, * @vaddr: the virtual address to store the opcode. * @opcode: opcode to be written at @vaddr. * - * Called with mm->mmap_lock held for write. + * Called with mm->mmap_lock held for read or write. * Return 0 (success) or a negative errno. */ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, @@ -725,7 +725,7 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset, uprobe = kzalloc(sizeof(struct uprobe), GFP_KERNEL); if (!uprobe) - return NULL; + return ERR_PTR(-ENOMEM); uprobe->inode = inode; uprobe->offset = offset; @@ -939,7 +939,6 @@ static void delete_uprobe(struct uprobe *uprobe) rb_erase(&uprobe->rb_node, &uprobes_tree); write_unlock(&uprobes_treelock); RB_CLEAR_NODE(&uprobe->rb_node); /* for uprobe_is_active() */ - put_uprobe(uprobe); } struct map_info { @@ -1046,7 +1045,13 @@ register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new) if (err && is_register) goto free; - + /* + * We take mmap_lock for writing to avoid the race with + * find_active_uprobe() which takes mmap_lock for reading. + * Thus this install_breakpoint() can not make + * is_trap_at_addr() true right after find_uprobe() + * returns NULL in find_active_uprobe(). + */ mmap_write_lock(mm); vma = find_vma(mm, info->vaddr); if (!vma || !valid_vma(vma, is_register) || @@ -1079,92 +1084,85 @@ register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new) return err; } -static void -__uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc) -{ - int err; - - if (WARN_ON(!consumer_del(uprobe, uc))) - return; - - err = register_for_each_vma(uprobe, NULL); - /* TODO : cant unregister? schedule a worker thread */ - if (!uprobe->consumers && !err) - delete_uprobe(uprobe); -} - -/* +/** * uprobe_unregister - unregister an already registered probe. - * @inode: the file in which the probe has to be removed. - * @offset: offset from the start of the file. + * @uprobe: uprobe to remove * @uc: identify which probe if multiple probes are colocated. */ -void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) +void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc) { - struct uprobe *uprobe; - - uprobe = find_uprobe(inode, offset); - if (WARN_ON(!uprobe)) - return; + int err; down_write(&uprobe->register_rwsem); - __uprobe_unregister(uprobe, uc); + if (WARN_ON(!consumer_del(uprobe, uc))) + err = -ENOENT; + else + err = register_for_each_vma(uprobe, NULL); + + /* TODO : cant unregister? schedule a worker thread */ + if (!err) { + if (!uprobe->consumers) + delete_uprobe(uprobe); + else + err = -EBUSY; + } up_write(&uprobe->register_rwsem); - put_uprobe(uprobe); + + if (!err) + put_uprobe(uprobe); } EXPORT_SYMBOL_GPL(uprobe_unregister); -/* - * __uprobe_register - register a probe +/** + * uprobe_register - register a probe * @inode: the file in which the probe has to be placed. * @offset: offset from the start of the file. + * @ref_ctr_offset: offset of SDT marker / reference counter * @uc: information on howto handle the probe.. * - * Apart from the access refcount, __uprobe_register() takes a creation + * Apart from the access refcount, uprobe_register() takes a creation * refcount (thro alloc_uprobe) if and only if this @uprobe is getting * inserted into the rbtree (i.e first consumer for a @inode:@offset * tuple). Creation refcount stops uprobe_unregister from freeing the * @uprobe even before the register operation is complete. Creation * refcount is released when the last @uc for the @uprobe - * unregisters. Caller of __uprobe_register() is required to keep @inode + * unregisters. Caller of uprobe_register() is required to keep @inode * (and the containing mount) referenced. * - * Return errno if it cannot successully install probes - * else return 0 (success) + * Return: pointer to the new uprobe on success or an ERR_PTR on failure. */ -static int __uprobe_register(struct inode *inode, loff_t offset, - loff_t ref_ctr_offset, struct uprobe_consumer *uc) +struct uprobe *uprobe_register(struct inode *inode, + loff_t offset, loff_t ref_ctr_offset, + struct uprobe_consumer *uc) { struct uprobe *uprobe; int ret; /* Uprobe must have at least one set consumer */ if (!uc->handler && !uc->ret_handler) - return -EINVAL; + return ERR_PTR(-EINVAL); /* copy_insn() uses read_mapping_page() or shmem_read_mapping_page() */ if (!inode->i_mapping->a_ops->read_folio && !shmem_mapping(inode->i_mapping)) - return -EIO; + return ERR_PTR(-EIO); /* Racy, just to catch the obvious mistakes */ if (offset > i_size_read(inode)) - return -EINVAL; + return ERR_PTR(-EINVAL); /* * This ensures that copy_from_page(), copy_to_page() and * __update_ref_ctr() can't cross page boundary. */ if (!IS_ALIGNED(offset, UPROBE_SWBP_INSN_SIZE)) - return -EINVAL; + return ERR_PTR(-EINVAL); if (!IS_ALIGNED(ref_ctr_offset, sizeof(short))) - return -EINVAL; + return ERR_PTR(-EINVAL); retry: uprobe = alloc_uprobe(inode, offset, ref_ctr_offset); - if (!uprobe) - return -ENOMEM; if (IS_ERR(uprobe)) - return PTR_ERR(uprobe); + return uprobe; /* * We can race with uprobe_unregister()->delete_uprobe(). @@ -1175,56 +1173,39 @@ static int __uprobe_register(struct inode *inode, loff_t offset, if (likely(uprobe_is_active(uprobe))) { consumer_add(uprobe, uc); ret = register_for_each_vma(uprobe, uc); - if (ret) - __uprobe_unregister(uprobe, uc); } up_write(&uprobe->register_rwsem); put_uprobe(uprobe); - if (unlikely(ret == -EAGAIN)) - goto retry; - return ret; -} + if (ret) { + if (unlikely(ret == -EAGAIN)) + goto retry; + uprobe_unregister(uprobe, uc); + return ERR_PTR(ret); + } -int uprobe_register(struct inode *inode, loff_t offset, - struct uprobe_consumer *uc) -{ - return __uprobe_register(inode, offset, 0, uc); + return uprobe; } EXPORT_SYMBOL_GPL(uprobe_register); -int uprobe_register_refctr(struct inode *inode, loff_t offset, - loff_t ref_ctr_offset, struct uprobe_consumer *uc) -{ - return __uprobe_register(inode, offset, ref_ctr_offset, uc); -} -EXPORT_SYMBOL_GPL(uprobe_register_refctr); - -/* - * uprobe_apply - unregister an already registered probe. - * @inode: the file in which the probe has to be removed. - * @offset: offset from the start of the file. +/** + * uprobe_apply - add or remove the breakpoints according to @uc->filter + * @uprobe: uprobe which "owns" the breakpoint * @uc: consumer which wants to add more or remove some breakpoints * @add: add or remove the breakpoints + * Return: 0 on success or negative error code. */ -int uprobe_apply(struct inode *inode, loff_t offset, - struct uprobe_consumer *uc, bool add) +int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool add) { - struct uprobe *uprobe; struct uprobe_consumer *con; int ret = -ENOENT; - uprobe = find_uprobe(inode, offset); - if (WARN_ON(!uprobe)) - return ret; - down_write(&uprobe->register_rwsem); for (con = uprobe->consumers; con && con != uc ; con = con->next) ; if (con) ret = register_for_each_vma(uprobe, add ? uc : NULL); up_write(&uprobe->register_rwsem); - put_uprobe(uprobe); return ret; } @@ -2028,13 +2009,7 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr) if (likely(result == 0)) goto out; - /* - * The NULL 'tsk' here ensures that any faults that occur here - * will not be accounted to the task. 'mm' *is* current->mm, - * but we treat this as a 'remote' access since it is - * essentially a kernel access to the memory. - */ - result = get_user_pages_remote(mm, vaddr, 1, FOLL_FORCE, &page, NULL); + result = get_user_pages(vaddr, 1, FOLL_FORCE, &page); if (result < 0) return result; @@ -2081,6 +2056,7 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs) bool need_prep = false; /* prepare return uprobe, when needed */ down_read(&uprobe->register_rwsem); + current->utask->auprobe = &uprobe->arch; for (uc = uprobe->consumers; uc; uc = uc->next) { int rc = 0; @@ -2095,6 +2071,7 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs) remove &= rc; } + current->utask->auprobe = NULL; if (need_prep && !remove) prepare_uretprobe(uprobe, regs); /* put bp at return */ diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index cd098846e251..4e391daafa64 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -3160,6 +3160,7 @@ struct bpf_uprobe { loff_t offset; unsigned long ref_ctr_offset; u64 cookie; + struct uprobe *uprobe; struct uprobe_consumer consumer; }; @@ -3178,15 +3179,12 @@ struct bpf_uprobe_multi_run_ctx { struct bpf_uprobe *uprobe; }; -static void bpf_uprobe_unregister(struct path *path, struct bpf_uprobe *uprobes, - u32 cnt) +static void bpf_uprobe_unregister(struct bpf_uprobe *uprobes, u32 cnt) { u32 i; - for (i = 0; i < cnt; i++) { - uprobe_unregister(d_real_inode(path->dentry), uprobes[i].offset, - &uprobes[i].consumer); - } + for (i = 0; i < cnt; i++) + uprobe_unregister(uprobes[i].uprobe, &uprobes[i].consumer); } static void bpf_uprobe_multi_link_release(struct bpf_link *link) @@ -3194,7 +3192,7 @@ static void bpf_uprobe_multi_link_release(struct bpf_link *link) struct bpf_uprobe_multi_link *umulti_link; umulti_link = container_of(link, struct bpf_uprobe_multi_link, link); - bpf_uprobe_unregister(&umulti_link->path, umulti_link->uprobes, umulti_link->cnt); + bpf_uprobe_unregister(umulti_link->uprobes, umulti_link->cnt); if (umulti_link->task) put_task_struct(umulti_link->task); path_put(&umulti_link->path); @@ -3480,12 +3478,13 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr &bpf_uprobe_multi_link_lops, prog); for (i = 0; i < cnt; i++) { - err = uprobe_register_refctr(d_real_inode(link->path.dentry), - uprobes[i].offset, - uprobes[i].ref_ctr_offset, - &uprobes[i].consumer); - if (err) { - bpf_uprobe_unregister(&path, uprobes, i); + uprobes[i].uprobe = uprobe_register(d_real_inode(link->path.dentry), + uprobes[i].offset, + uprobes[i].ref_ctr_offset, + &uprobes[i].consumer); + if (IS_ERR(uprobes[i].uprobe)) { + err = PTR_ERR(uprobes[i].uprobe); + bpf_uprobe_unregister(uprobes, i); goto error_free; } } diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index c98e3b3386ba..52e76a73fa7c 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -58,8 +58,8 @@ struct trace_uprobe { struct dyn_event devent; struct uprobe_consumer consumer; struct path path; - struct inode *inode; char *filename; + struct uprobe *uprobe; unsigned long offset; unsigned long ref_ctr_offset; unsigned long nhit; @@ -1084,21 +1084,16 @@ typedef bool (*filter_func_t)(struct uprobe_consumer *self, static int trace_uprobe_enable(struct trace_uprobe *tu, filter_func_t filter) { - int ret; + struct inode *inode = d_real_inode(tu->path.dentry); + struct uprobe *uprobe; tu->consumer.filter = filter; - tu->inode = d_real_inode(tu->path.dentry); - - if (tu->ref_ctr_offset) - ret = uprobe_register_refctr(tu->inode, tu->offset, - tu->ref_ctr_offset, &tu->consumer); - else - ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); + uprobe = uprobe_register(inode, tu->offset, tu->ref_ctr_offset, &tu->consumer); + if (IS_ERR(uprobe)) + return PTR_ERR(uprobe); - if (ret) - tu->inode = NULL; - - return ret; + tu->uprobe = uprobe; + return 0; } static void __probe_event_disable(struct trace_probe *tp) @@ -1109,11 +1104,11 @@ static void __probe_event_disable(struct trace_probe *tp) WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) { - if (!tu->inode) + if (!tu->uprobe) continue; - uprobe_unregister(tu->inode, tu->offset, &tu->consumer); - tu->inode = NULL; + uprobe_unregister(tu->uprobe, &tu->consumer); + tu->uprobe = NULL; } } @@ -1310,7 +1305,7 @@ static int uprobe_perf_close(struct trace_event_call *call, return 0; list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) { - ret = uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); + ret = uprobe_apply(tu->uprobe, &tu->consumer, false); if (ret) break; } @@ -1334,7 +1329,7 @@ static int uprobe_perf_open(struct trace_event_call *call, return 0; list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) { - err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); + err = uprobe_apply(tu->uprobe, &tu->consumer, true); if (err) { uprobe_perf_close(call, event); break; diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index fd28c1157bd3..3c0515a27842 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -432,7 +432,7 @@ uprobe_ret_handler(struct uprobe_consumer *self, unsigned long func, struct testmod_uprobe { struct path path; - loff_t offset; + struct uprobe *uprobe; struct uprobe_consumer consumer; }; @@ -446,25 +446,25 @@ static int testmod_register_uprobe(loff_t offset) { int err = -EBUSY; - if (uprobe.offset) + if (uprobe.uprobe) return -EBUSY; mutex_lock(&testmod_uprobe_mutex); - if (uprobe.offset) + if (uprobe.uprobe) goto out; err = kern_path("/proc/self/exe", LOOKUP_FOLLOW, &uprobe.path); if (err) goto out; - err = uprobe_register_refctr(d_real_inode(uprobe.path.dentry), - offset, 0, &uprobe.consumer); - if (err) + uprobe.uprobe = uprobe_register(d_real_inode(uprobe.path.dentry), + offset, 0, &uprobe.consumer); + if (IS_ERR(uprobe.uprobe)) { + err = PTR_ERR(uprobe.uprobe); path_put(&uprobe.path); - else - uprobe.offset = offset; - + uprobe.uprobe = NULL; + } out: mutex_unlock(&testmod_uprobe_mutex); return err; @@ -474,10 +474,10 @@ static void testmod_unregister_uprobe(void) { mutex_lock(&testmod_uprobe_mutex); - if (uprobe.offset) { - uprobe_unregister(d_real_inode(uprobe.path.dentry), - uprobe.offset, &uprobe.consumer); - uprobe.offset = 0; + if (uprobe.uprobe) { + uprobe_unregister(uprobe.uprobe, &uprobe.consumer); + path_put(&uprobe.path); + uprobe.uprobe = NULL; } mutex_unlock(&testmod_uprobe_mutex); |