Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Zheng Wang <zyytlz.wz@163.com>
To:     gregkh@linuxfoundation.org
Cc:     zhengyejian1@huawei.com, dimitri.sivanich@hpe.com, arnd@arndb.de,
        linux-kernel@vger.kernel.org, hackerzheng666@gmail.com,
        alex000young@gmail.com, security@kernel.org, sivanich@hpe.com,
        Zheng Wang <zyytlz.wz@163.com>
Subject: [PATCH v5] misc: sgi-gru: fix use-after-free error in  gru_set_context_option, gru_fault and gru_handle_user_call_os
Date:   Thu, 27 Oct 2022 12:04:55 +0800
Message-Id: <20221027040455.115035-1-zyytlz.wz@163.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Gts may be freed in gru_check_chiplet_assignment.
The caller still use it after that, UAF happens.

Fix it by introducing a return value to see if it's in error path or not.
Free the gts in caller if gru_check_chiplet_assignment check failed.

Fixes: 55484c45dbec ("gru: allow users to specify gru chiplet 2")
Reported-by: Zheng Wang <hackerzheng666@gmail.com>
Signed-off-by: Zheng Wang <zyytlz.wz@163.com>
---
v5:
- fix logical issue and remove unnecessary variable suggested by Dimitri Sivanich

v4:
- use VM_FAULT_NOPAGE as failure code in gru_fault and -EINVAL in other functions suggested by Yejian

v3:
- add preempt_enable and use VM_FAULT_NOPAGE as failure code suggested by Yejian

v2:
- commit message changes suggested by Greg

v1: https://lore.kernel.org/lkml/CAJedcCzY72jqgF-pCPtx66vXXwdPn-KMagZnqrxcpWw1NxTLaA@mail.gmail.com/
---
 drivers/misc/sgi-gru/grufault.c  | 14 ++++++++++++--
 drivers/misc/sgi-gru/grumain.c   | 17 +++++++++++++----
 drivers/misc/sgi-gru/grutables.h |  2 +-
 3 files changed, 26 insertions(+), 7 deletions(-)

diff --git a/drivers/misc/sgi-gru/grufault.c b/drivers/misc/sgi-gru/grufault.c
index d7ef61e602ed..bdd515d33225 100644
--- a/drivers/misc/sgi-gru/grufault.c
+++ b/drivers/misc/sgi-gru/grufault.c
@@ -656,7 +656,9 @@ int gru_handle_user_call_os(unsigned long cb)
 	if (ucbnum >= gts->ts_cbr_au_count * GRU_CBR_AU_SIZE)
 		goto exit;
 
-	gru_check_context_placement(gts);
+	ret = gru_check_context_placement(gts);
+	if (ret)
+		goto err;
 
 	/*
 	 * CCH may contain stale data if ts_force_cch_reload is set.
@@ -677,6 +679,10 @@ int gru_handle_user_call_os(unsigned long cb)
 exit:
 	gru_unlock_gts(gts);
 	return ret;
+err:
+	gru_unlock_gts(gts);
+	gru_unload_context(gts, 1);
+	return -EINVAL;
 }
 
 /*
@@ -874,7 +880,11 @@ int gru_set_context_option(unsigned long arg)
 		} else {
 			gts->ts_user_blade_id = req.val1;
 			gts->ts_user_chiplet_id = req.val0;
-			gru_check_context_placement(gts);
+			if (gru_check_context_placement(gts)) {
+				gru_unlock_gts(gts);
+				gru_unload_context(gts, 1);
+				return -EINVAL;
+			}
 		}
 		break;
 	case sco_gseg_owner:
diff --git a/drivers/misc/sgi-gru/grumain.c b/drivers/misc/sgi-gru/grumain.c
index 9afda47efbf2..8c9f7055068d 100644
--- a/drivers/misc/sgi-gru/grumain.c
+++ b/drivers/misc/sgi-gru/grumain.c
@@ -716,9 +716,10 @@ static int gru_check_chiplet_assignment(struct gru_state *gru,
  * chiplet. Misassignment can occur if the process migrates to a different
  * blade or if the user changes the selected blade/chiplet.
  */
-void gru_check_context_placement(struct gru_thread_state *gts)
+int gru_check_context_placement(struct gru_thread_state *gts)
 {
 	struct gru_state *gru;
+	int ret = 0;
 
 	/*
 	 * If the current task is the context owner, verify that the
@@ -727,14 +728,16 @@ void gru_check_context_placement(struct gru_thread_state *gts)
 	 */
 	gru = gts->ts_gru;
 	if (!gru || gts->ts_tgid_owner != current->tgid)
-		return;
+		return ret;
 
 	if (!gru_check_chiplet_assignment(gru, gts)) {
 		STAT(check_context_unload);
-		gru_unload_context(gts, 1);
+		ret = -EINVAL;
 	} else if (gru_retarget_intr(gts)) {
 		STAT(check_context_retarget_intr);
 	}
+
+	return ret;
 }
 
 
@@ -919,6 +922,7 @@ vm_fault_t gru_fault(struct vm_fault *vmf)
 	struct gru_thread_state *gts;
 	unsigned long paddr, vaddr;
 	unsigned long expires;
+	int ret;
 
 	vaddr = vmf->address;
 	gru_dbg(grudev, "vma %p, vaddr 0x%lx (0x%lx)\n",
@@ -934,7 +938,12 @@ vm_fault_t gru_fault(struct vm_fault *vmf)
 	mutex_lock(&gts->ts_ctxlock);
 	preempt_disable();
 
-	gru_check_context_placement(gts);
+	if (gru_check_context_placement(gts)) {
+		preempt_enable();
+		mutex_unlock(&gts->ts_ctxlock);
+		gru_unload_context(gts, 1);
+		return VM_FAULT_NOPAGE;
+	}
 
 	if (!gts->ts_gru) {
 		STAT(load_user_context);
diff --git a/drivers/misc/sgi-gru/grutables.h b/drivers/misc/sgi-gru/grutables.h
index 5efc869fe59a..f4a5a787685f 100644
--- a/drivers/misc/sgi-gru/grutables.h
+++ b/drivers/misc/sgi-gru/grutables.h
@@ -632,7 +632,7 @@ extern int gru_user_flush_tlb(unsigned long arg);
 extern int gru_user_unload_context(unsigned long arg);
 extern int gru_get_exception_detail(unsigned long arg);
 extern int gru_set_context_option(unsigned long address);
-extern void gru_check_context_placement(struct gru_thread_state *gts);
+extern int gru_check_context_placement(struct gru_thread_state *gts);
 extern int gru_cpu_fault_map_id(void);
 extern struct vm_area_struct *gru_find_vma(unsigned long vaddr);
 extern void gru_flush_all_tlb(struct gru_state *gru);
-- 
2.25.1