@@ -231,8 +231,18 @@ static void flush_all_zero_pkmaps(void)
set_page_address(page, NULL);
need_flush = 1;
}
- if (need_flush)
+ if (need_flush) {
+ /*
+ * In multi-core system one CPU holds the kmap_lock, waiting
+ * for other CPUs respond to IPI. But other CPUS has disabled
+ * irqs, waiting for kmap_lock, cannot answer the IPI. Release
+ * kmap_lock before call flush_tlb_kernel_range, avoid kmap_lock
+ * deadlock.
+ */
+ unlock_kmap();
flush_tlb_kernel_range(PKMAP_ADDR(0), PKMAP_ADDR(LAST_PKMAP));
+ lock_kmap();
+ }
}
void __kmap_flush_unused(void)
CPU 0: CPU 1: kmap_high(){ kmap_xxx() { ... irq_disable(); spin_lock(&kmap_lock) ... map_new_virtual ... flush_all_zero_pkmaps flush_tlb_kernel_range /* CPU0 holds the kmap_lock */ smp_call_function_many spin_lock(&kmap_lock) ... .... spin_unlock(&kmap_lock) ... CPU 0 holds the kmap_lock, waiting for CPU 1 respond to IPI. But CPU 1 has disabled irqs, waiting for kmap_lock, cannot answer the IPI. Fix this by releasing kmap_lock before call flush_tlb_kernel_range, avoid kmap_lock deadlock. if (need_flush) { unlock_kmap(); flush_tlb_kernel_range(PKMAP_ADDR(0), PKMAP_ADDR(LAST_PKMAP)); lock_kmap(); } Dropping the lock like this is safe. kmap_lock is used to protect pkmap_count, pkmap_page_table and last_pkmap_nr(static variable). When call flush_tlb_kernel_range(PKMAP_ADDR(0), PKMAP_ADDR(LAST_PKMAP)), flush_tlb_kernel_range will neither modify nor read these variables. Leave that data unprotected here is safe. map_new_virtual aims to find an usable entry pkmap_count[last_pkmap_nr]. When read and modify the pkmap_count[last_pkmap_nr], the kmap_lock is not dropped. "if (!pkmap_count[last_pkmap_nr])" determine pkmap_count[last_pkmap_nr] is usable or not. If unusable, try agin. Furthermore, the value of static variable last_pkmap_nr is stored in a local variable last_pkmap_nr, when kmap_lock is acquired, this is thread-safe. In an extreme case, if Thread A and Thread B access the same last_pkmap_nr, Thread A calls function flush_tlb_kernel_range and release the kmap_lock, and Thread B then acquires the kmap_lock and modifies the variable pkmap_count[last_pkmap_nr]. After Thread A completes the execution of function the variable pkmap_count[last_pkmap_nr]. After Thread A completes the execution of function flush_tlb_kernel_range, it will check the variable pkmap_count[last_pkmap_nr]. static inline unsigned long map_new_virtual(struct page *page) { unsigned long vaddr; int count; unsigned int last_pkmap_nr; // local variable to store static variable last_pkmap_nr unsigned int color = get_pkmap_color(page); start: ... flush_all_zero_pkmaps();// release kmap_lock, then acquire it count = get_pkmap_entries_count(color); } ... if (!pkmap_count[last_pkmap_nr]) // pkmap_count[last_pkmap_nr] is used or not break; /* Found a usable entry */ if (--count) continue; ... vaddr = PKMAP_ADDR(last_pkmap_nr); set_pte_at(&init_mm, vaddr, &(pkmap_page_table[last_pkmap_nr]), mk_pte(page, kmap_prot)); pkmap_count[last_pkmap_nr] = 1; ... return vaddr; } Fixes: 3297e760776a ("highmem: atomic highmem kmap page pinning") Signed-off-by: zhangchun <zhang.chuna@h3c.com> Co-developed-by: zhangzhansheng <zhang.zhansheng@h3c.com> Signed-off-by: zhangzhansheng <zhang.zhansheng@h3c.com> Suggested-by: Matthew Wilcox <willy@infradead.org> Reviewed-by: zhangzhengming <zhang.zhengming@h3c.com> --- mm/highmem.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-)