mirror of https://github.com/torvalds/linux.git
f51e2f1911
Currently instruction_pointer() returns pt_regs->ret and so return value is of type "long", which implicitly stands for "signed long". While that's perfectly fine when dealing with 32-bit values if return value of instruction_pointer() gets assigned to 64-bit variable sign extension may happen. And at least in one real use-case it happens already. In perf_prepare_sample() return value of perf_instruction_pointer() (which is an alias to instruction_pointer() in case of ARC) is assigned to (struct perf_sample_data)->ip (which type is "u64"). And what we see if instuction pointer points to user-space application that in case of ARC lays below 0x8000_0000 "ip" gets set properly with leading 32 zeros. But if instruction pointer points to kernel address space that starts from 0x8000_0000 then "ip" is set with 32 leadig "f"-s. I.e. id instruction_pointer() returns 0x8100_0000, "ip" will be assigned with 0xffff_ffff__8100_0000. Which is obviously wrong. In particular that issuse broke output of perf, because perf was unable to associate addresses like 0xffff_ffff__8100_0000 with anything from /proc/kallsyms. That's what we used to see: ----------->8---------- 6.27% ls [unknown] [k] 0xffffffff8046c5cc 2.96% ls libuClibc-0.9.34-git.so [.] memcpy 2.25% ls libuClibc-0.9.34-git.so [.] memset 1.66% ls [unknown] [k] 0xffffffff80666536 1.54% ls libuClibc-0.9.34-git.so [.] 0x000224d6 1.18% ls libuClibc-0.9.34-git.so [.] 0x00022472 ----------->8---------- With that change perf output looks much better now: ----------->8---------- 8.21% ls [kernel.kallsyms] [k] memset 3.52% ls libuClibc-0.9.34-git.so [.] memcpy 2.11% ls libuClibc-0.9.34-git.so [.] malloc 1.88% ls libuClibc-0.9.34-git.so [.] memset 1.64% ls [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 1.41% ls [kernel.kallsyms] [k] __d_lookup_rcu ----------->8---------- Signed-off-by: Alexey Brodkin <abrodkin@synopsys.com> Cc: arc-linux-dev@synopsys.com Cc: stable@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Vineet Gupta <vgupta@synopsys.com> |
||
|---|---|---|
| .. | ||
| Kbuild | ||
| arcregs.h | ||
| asm-offsets.h | ||
| atomic.h | ||
| barrier.h | ||
| bitops.h | ||
| bug.h | ||
| cache.h | ||
| cacheflush.h | ||
| checksum.h | ||
| clk.h | ||
| cmpxchg.h | ||
| current.h | ||
| delay.h | ||
| disasm.h | ||
| dma-mapping.h | ||
| dma.h | ||
| elf.h | ||
| entry-arcv2.h | ||
| entry-compact.h | ||
| entry.h | ||
| exec.h | ||
| futex.h | ||
| io.h | ||
| irq.h | ||
| irqflags-arcv2.h | ||
| irqflags-compact.h | ||
| irqflags.h | ||
| kdebug.h | ||
| kgdb.h | ||
| kprobes.h | ||
| linkage.h | ||
| mach_desc.h | ||
| mcip.h | ||
| mm-arch-hooks.h | ||
| mmu.h | ||
| mmu_context.h | ||
| module.h | ||
| mutex.h | ||
| page.h | ||
| perf_event.h | ||
| pgalloc.h | ||
| pgtable.h | ||
| processor.h | ||
| ptrace.h | ||
| sections.h | ||
| segment.h | ||
| serial.h | ||
| setup.h | ||
| shmparam.h | ||
| smp.h | ||
| spinlock.h | ||
| spinlock_types.h | ||
| stacktrace.h | ||
| string.h | ||
| switch_to.h | ||
| syscall.h | ||
| syscalls.h | ||
| thread_info.h | ||
| timex.h | ||
| tlb-mmu1.h | ||
| tlb.h | ||
| tlbflush.h | ||
| uaccess.h | ||
| unaligned.h | ||
| unwind.h | ||