Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1161094AbaDTC2e (ORCPT ); Sat, 19 Apr 2014 22:28:34 -0400 Received: from g2t2353.austin.hp.com ([15.217.128.52]:57927 "EHLO g2t2353.austin.hp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755235AbaDTC0w (ORCPT ); Sat, 19 Apr 2014 22:26:52 -0400 From: Davidlohr Bueso To: akpm@linux-foundation.org Cc: zeus@gnu.org, aswin@hp.com, davidlohr@hp.com, linux-mm@kvack.org, linux-kernel@vger.kernel.org, Dimitri@domain.invalid, "Sivanich X-Mailer: git-send-email 1.8.1.4 In-Reply-To: <1397960791-16320-1-git-send-email-davidlohr@hp.com> References: <1397960791-16320-1-git-send-email-davidlohr@hp.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Jonathan Gonzalez V Performing vma lookups without taking the mm->mmap_sem is asking for trouble. While doing the search, the vma in question can be modified or even removed before returning to the caller. Take the lock in order to avoid races while iterating through the vmacache and/or rbtree. This patch is completely *untested*. Signed-off-by: Jonathan Gonzalez V Signed-off-by: Davidlohr Bueso Cc: Dimitri Sivanich mmap_sem); vma = find_vma(mm, vaddr); if (!vma) goto inval; @@ -277,22 +278,26 @@ static int gru_vtop(struct gru_thread_state *gts, unsigned long vaddr, rmb(); /* Must/check ms_range_active before loading PTEs */ ret = atomic_pte_lookup(vma, vaddr, write, &paddr, &ps); if (ret) { - if (atomic) - goto upm; + if (atomic) { + up_write(&mm->mmap_sem); + return VTOP_RETRY; + } if (non_atomic_pte_lookup(vma, vaddr, write, &paddr, &ps)) goto inval; } if (is_gru_paddr(paddr)) goto inval; + + up_write(&mm->mmap_sem); + paddr = paddr & ~((1UL << ps) - 1); *gpa = uv_soc_phys_ram_to_gpa(paddr); *pageshift = ps; return VTOP_SUCCESS; inval: + up_write(&mm->mmap_sem); return VTOP_INVALID; -upm: - return VTOP_RETRY; } -- 1.8.1.4 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/