When an interrupt (such as a perf counter interrupt) is delivered while executing in user space, the trap entry code puts ASI_AIUS in %asi so that copy_from_user() and copy_to_user() will access the correct memory. But if a perf counter interrupt is delivered while the cpu is already executing in kernel space, then the trap entry code will put ASI_P in %asi, and this will prevent copy_from_user() from reading any useful stack data in either of the perf_callchain_user_X functions, and thus no user callgraph data will be collected for this sample period. An additional problem is that a fault is guaranteed to occur, and though it will be silently covered up, it wastes time and could perturb state. In perf_callchain_user(), we ensure that %asi contains ASI_AIUS because we know for a fact that the subsequent calls to copy_from_user() are intended to read the user's stack. [ Use get_fs()/set_fs() -DaveM ]
Unified · Split
| @@ -1828,11 +1828,16 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry, · 1827 unmodified lines | ||
| 1828 | 1828 | void |
| 1829 | 1829 | perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) |
| 1830 | 1830 | { |
| 1831 | + mm_segment_t old_fs; | |
| 1832 | + | |
| 1831 | 1833 | perf_callchain_store(entry, regs->tpc); |
| 1832 | 1834 | |
| 1833 | 1835 | if (!current->mm) |
| 1834 | 1836 | return; |
| 1835 | 1837 | |
| 1838 | + old_fs = get_fs(); | |
| 1839 | + set_fs(USER_DS); | |
| 1840 | + | |
| 1836 | 1841 | flushw_user(); |
| 1837 | 1842 | |
| 1838 | 1843 | pagefault_disable(); |
| @@ -1843,4 +1848,6 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) · 4 unmodified lines | ||
| 1843 | 1848 | perf_callchain_user_64(entry, regs); |
| 1844 | 1849 | |
| 1845 | 1850 | pagefault_enable(); |
| 1851 | + | |
| 1852 | + set_fs(old_fs); | |
| 1846 | 1853 | } |