5.4.69-rc1 review

From: Christophe JAILLET <[email protected]>

[ Upstream commit 547a7348633b1f9923551f94ac3157a613d2c9f2 ]

'exynos_dsi_parse_dt()' takes a reference to 'dsi->in_bridge_node'. This must be released in the error handling path.

In order to do that, add an error handling path and move the 'exynos_dsi_parse_dt()' call from the beginning to the end of the probe function to ease the error handling path.
This function only sets some variables which are used only in the 'transfer' function.

The call chain is:
.transfer

    --> exynos_dsi_host_transfer
      --> exynos_dsi_init
        --> exynos_dsi_enable_clock  (use burst_clk_rate and esc_clk_rate)
          --> exynos_dsi_set_pll     (use pll_clk_rate)

While at it, also handle cases where 'component_add()' fails.

This patch is similar to commit 70505c2ef94b ("drm/exynos: dsi: Remove bridge node reference in removal") which fixed the issue in the remove function.

---
 drivers/gpu/drm/exynos/exynos_drm_dsi.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

index 8ed94c9948008..b83acd696774b 100644
@@ -1741,10 +1741,6 @@ static int exynos_dsi_probe(struct platform_device *pdev)
 	dsi->dev = dev;
 	dsi->driver_data = of_device_get_match_data(dev);
 
-	ret = exynos_dsi_parse_dt(dsi);
-	if (ret)
-		return ret;
-
 	dsi->supplies[0].supply = "vddcore";
 	dsi->supplies[1].supply = "vddio";
 	ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(dsi->supplies),

@@ -1805,11 +1801,25 @@ static int exynos_dsi_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	ret = exynos_dsi_parse_dt(dsi);
+	if (ret)
+		return ret;
+
 	platform_set_drvdata(pdev, &dsi->encoder);
 
 	pm_runtime_enable(dev);
 
-	return component_add(dev, &exynos_dsi_component_ops);
+	ret = component_add(dev, &exynos_dsi_component_ops);
+	if (ret)
+		goto err_disable_runtime;
+
+	return 0;
+
+err_disable_runtime:
+	pm_runtime_disable(dev);
+	of_node_put(dsi->in_bridge_node);
+
+	return ret;
 }
 
 static int exynos_dsi_remove(struct platform_device *pdev)

2.25.1

From: Tang Bin <[email protected]>

[ Upstream commit 49826937e7c7917140515aaf10c17bedcc4acaad ]

If the function platform_get_irq() failed, the negative value returned will not be detected here. So fix error handling in bt_bmc_config_irq(). And in the function bt_bmc_probe(), when get irq failed, it will print error message. So use platform_get_irq_optional() to simplify code. Finally in the function bt_bmc_remove() should make the right status check if get irq failed.

Message-Id: <[email protected]>

---
 drivers/char/ipmi/bt-bmc.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

index 40b9927c072c9..89a8faa9b6cfa 100644
@@ -399,15 +399,15 @@ static int bt_bmc_config_irq(struct bt_bmc *bt_bmc,
 	struct device *dev = &pdev->dev;
 	int rc;
 
-	bt_bmc->irq = platform_get_irq(pdev, 0);
-	if (!bt_bmc->irq)
-		return -ENODEV;
+	bt_bmc->irq = platform_get_irq_optional(pdev, 0);
+	if (bt_bmc->irq < 0)
+		return bt_bmc->irq;
 
 	rc = devm_request_irq(dev, bt_bmc->irq, bt_bmc_irq, IRQF_SHARED,
 			      DEVICE_NAME, bt_bmc);
 	if (rc < 0) {
 		dev_warn(dev, "Unable to request IRQ %d\n", bt_bmc->irq);
-		bt_bmc->irq = 0;
+		bt_bmc->irq = rc;
 		return rc;
 	}
 

@@ -479,7 +479,7 @@ static int bt_bmc_probe(struct platform_device *pdev)
 
 	bt_bmc_config_irq(bt_bmc, pdev);
 
-	if (bt_bmc->irq) {
+	if (bt_bmc->irq >= 0) {
 		dev_info(dev, "Using IRQ %d\n", bt_bmc->irq);
 	} else {
 		dev_info(dev, "No IRQ; using timer\n");

@@ -505,7 +505,7 @@ static int bt_bmc_remove(struct platform_device *pdev)
 	struct bt_bmc *bt_bmc = dev_get_drvdata(&pdev->dev);
 
 	misc_deregister(&bt_bmc->miscdev);
-	if (!bt_bmc->irq)
+	if (bt_bmc->irq < 0)
 		del_timer_sync(&bt_bmc->poll_timer);
 	return 0;
 }

2.25.1

From: Nicholas Piggin <[email protected]>

[ Upstream commit 265d6e588d87194c2fe2d6c240247f0264e0c19b ]

System Reset and Machine Check interrupts that are not recoverable due to being nested or interrupting when RI=0 currently panic. This is not necessary, and can often just kill the current context and recover.

---
 arch/powerpc/kernel/traps.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

index 014ff0701f245..9432fc6af28a5 100644
@@ -510,11 +510,11 @@ out:
 #ifdef CONFIG_PPC_BOOK3S_64
 	BUG_ON(get_paca()->in_nmi == 0);
 	if (get_paca()->in_nmi > 1)
-		nmi_panic(regs, "Unrecoverable nested System Reset");
+		die("Unrecoverable nested System Reset", regs, SIGABRT);
 #endif
 	/* Must die if the interrupt is not recoverable */
 	if (!(regs->msr & MSR_RI))
-		nmi_panic(regs, "Unrecoverable System Reset");
+		die("Unrecoverable System Reset", regs, SIGABRT);
 
 	if (saved_hsrrs) {
 		mtspr(SPRN_HSRR0, hsrr0);

@@ -858,7 +858,7 @@ void machine_check_exception(struct pt_regs *regs)
 
 	/* Must die if the interrupt is not recoverable */
 	if (!(regs->msr & MSR_RI))
-		nmi_panic(regs, "Unrecoverable Machine check");
+		die("Unrecoverable Machine check", regs, SIGBUS);
 
 	return;
 

2.25.1

From: Chuck Lever <[email protected]>

[ Upstream commit ea740bd5f58e2912e74f401fd01a9d6aa985ca05 ]

Way back when I was writing the RPC/RDMA server-side backchannel code, I misread the TCP backchannel reply handler logic. When svc_tcp_recvfrom() successfully receives a backchannel reply, it does not return -EAGAIN. It sets XPT_DATA and returns zero.

Update svc_rdma_recvfrom() to return zero. Here, XPT_DATA doesn't need to be set again: it is set whenever a new message is received, behind a spin lock in a single threaded context.

Also, if handling the cb reply is not successful, the message is simply dropped. There's no special message framing to deal with as there is in the TCP case.

Now that the handle_bc_reply() return value is ignored, I've removed the dprintk call sites in the error exit of handle_bc_reply() in favor of trace points in other areas that already report the error cases.

---
 include/linux/sunrpc/svc_rdma.h            |  5 ++-
 net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 38 ++++++----------------
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c    | 11 +++----
 3 files changed, 17 insertions(+), 37 deletions(-)

index 26f282e5e0822..77589ed787f5c 100644
@@ -154,9 +154,8 @@ struct svc_rdma_send_ctxt {
 };
 
 /* svc_rdma_backchannel.c */
-extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt,
-				    __be32 *rdma_resp,
-				    struct xdr_buf *rcvbuf);
+extern void svc_rdma_handle_bc_reply(struct svc_rqst *rqstp,
+				     struct svc_rdma_recv_ctxt *rctxt);
 
 /* svc_rdma_recvfrom.c */
 extern void svc_rdma_recv_ctxts_destroy(struct svcxprt_rdma *rdma);

index 325eef1f85824..68d2dcf0a1be1 100644
@@ -15,26 +15,25 @@
 #undef SVCRDMA_BACKCHANNEL_DEBUG
 
 /**
- * svc_rdma_handle_bc_reply - Process incoming backchannel reply
- * @xprt: controlling backchannel transport
- * @rdma_resp: pointer to incoming transport header
- * @rcvbuf: XDR buffer into which to decode the reply
+ * svc_rdma_handle_bc_reply - Process incoming backchannel Reply
+ * @rqstp: resources for handling the Reply
+ * @rctxt: Received message
  *
- * Returns:
- *	%0 if @rcvbuf is filled in, xprt_complete_rqst called,
- *	%-EAGAIN if server should call ->recvfrom again.
  */
-int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp,
-			     struct xdr_buf *rcvbuf)
+void svc_rdma_handle_bc_reply(struct svc_rqst *rqstp,
+			      struct svc_rdma_recv_ctxt *rctxt)
 {
+	struct svc_xprt *sxprt = rqstp->rq_xprt;
+	struct rpc_xprt *xprt = sxprt->xpt_bc_xprt;
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
+	struct xdr_buf *rcvbuf = &rqstp->rq_arg;
 	struct kvec *dst, *src = &rcvbuf->head[0];
+	__be32 *rdma_resp = rctxt->rc_recv_buf;
 	struct rpc_rqst *req;
 	u32 credits;
 	size_t len;
 	__be32 xid;
 	__be32 *p;
-	int ret;
 
 	p = (__be32 *)src->iov_base;
 	len = src->iov_len;

@@ -49,14 +48,10 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp,
 		__func__, (int)len, p);
 #endif
 
-	ret = -EAGAIN;
-	if (src->iov_len < 24)
-		goto out_shortreply;
-
 	spin_lock(&xprt->queue_lock);
 	req = xprt_lookup_rqst(xprt, xid);
 	if (!req)
-		goto out_notfound;
+		goto out_unlock;
 
 	dst = &req->rq_private_buf.head[0];
 	memcpy(&req->rq_private_buf, &req->rq_rcv_buf, sizeof(struct xdr_buf));

@@ -77,25 +72,12 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp,
 	spin_unlock(&xprt->transport_lock);
 
 	spin_lock(&xprt->queue_lock);
-	ret = 0;
 	xprt_complete_rqst(req->rq_task, rcvbuf->len);
 	xprt_unpin_rqst(req);
 	rcvbuf->len = 0;
 
 out_unlock:
 	spin_unlock(&xprt->queue_lock);
-out:
-	return ret;
-
-out_shortreply:
-	dprintk("svcrdma: short bc reply: xprt=%p, len=%zu\n",
-		xprt, src->iov_len);
-	goto out;
-
-out_notfound:
-	dprintk("svcrdma: unrecognized bc reply: xprt=%p, xid=%08x\n",
-		xprt, be32_to_cpu(xid));
-	goto out_unlock;
 }
 
 /* Send a backwards direction RPC call.

index d803d814a03ad..fd5c1f1bb9885 100644
@@ -817,12 +817,9 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 		goto out_drop;
 	rqstp->rq_xprt_hlen = ret;
 
-	if (svc_rdma_is_backchannel_reply(xprt, p)) {
-		ret = svc_rdma_handle_bc_reply(xprt->xpt_bc_xprt, p,
-					       &rqstp->rq_arg);
-		svc_rdma_recv_ctxt_put(rdma_xprt, ctxt);
-		return ret;
-	}
+	if (svc_rdma_is_backchannel_reply(xprt, p))
+		goto out_backchannel;
+
 	svc_rdma_get_inv_rkey(rdma_xprt, ctxt);
 
 	p += rpcrdma_fixed_maxsz;

@@ -852,6 +849,8 @@ out_postfail:
 	svc_rdma_recv_ctxt_put(rdma_xprt, ctxt);
 	return ret;
 
+out_backchannel:
+	svc_rdma_handle_bc_reply(rqstp, ctxt);
 out_drop:
 	svc_rdma_recv_ctxt_put(rdma_xprt, ctxt);
 	return 0;

2.25.1

From: Miklos Szeredi <[email protected]>

[ Upstream commit 32f98877c57bee6bc27f443a96f49678a2cd6a50 ]

page_count() is unstable. Unless there has been an RCU grace period between when the page was removed from the page cache and now, a speculative reference may exist from the page cache.

---
 fs/fuse/dev.c | 1 -
 1 file changed, 1 deletion(-)

index 06dd38e76c62a..f9022b7028754 100644
@@ -764,7 +764,6 @@ static int fuse_check_page(struct page *page)
 {
 	if (page_mapcount(page) ||
 	    page->mapping != NULL ||
-	    page_count(page) != 1 ||
 	    (page->flags & PAGE_FLAGS_CHECK_AT_PREP &
 	     ~(1 << PG_locked |
 	       1 << PG_referenced |

2.25.1

From: Miklos Szeredi <[email protected]>

[ Upstream commit 5ddd9ced9aef6cfa76af27d384c17c9e2d610ce8 ]

A GETATTR request can race with FUSE_NOTIFY_INVAL_INODE, resulting in the attribute cache being updated with stale information after the invalidation.

Fix this by bumping the attribute version in fuse_reverse_inval_inode().

---
 fs/fuse/inode.c | 7 +++++++
 1 file changed, 7 insertions(+)

index 5dca643a257c9..f58ab84b09fb3 100644
@@ -323,6 +323,8 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
 int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid,
 			     loff_t offset, loff_t len)
 {
+	struct fuse_conn *fc = get_fuse_conn_super(sb);
+	struct fuse_inode *fi;
 	struct inode *inode;
 	pgoff_t pg_start;
 	pgoff_t pg_end;

@@ -331,6 +333,11 @@ int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid,
 	if (!inode)
 		return -ENOENT;
 
+	fi = get_fuse_inode(inode);
+	spin_lock(&fi->lock);
+	fi->attr_version = atomic64_inc_return(&fc->attr_version);
+	spin_unlock(&fi->lock);
+
 	fuse_invalidate_attr(inode);
 	forget_all_cached_acls(inode);
 	if (offset >= 0) {

2.25.1

From: Colin Ian King <[email protected]>

[ Upstream commit a7f40c233a6b0540d28743267560df9cfb571ca9 ]

The comparison of hcd->irq to less than zero for an error check will never be true because hcd->irq is an unsigned int. Fix this by assigning the int retval to the return of platform_get_irq and checking this for the -ve error condition and assigning hcd->irq to retval.

Addresses-Coverity: ("Unsigned compared against 0")

---
 drivers/usb/host/ehci-mv.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

index 15b2e8910e9b7..b6f196f5e252e 100644
@@ -156,11 +156,10 @@ static int mv_ehci_probe(struct platform_device *pdev)
 	hcd->rsrc_len = resource_size(r);
 	hcd->regs = ehci_mv->op_regs;
 
-	hcd->irq = platform_get_irq(pdev, 0);
-	if (hcd->irq < 0) {
-		retval = hcd->irq;
+	retval = platform_get_irq(pdev, 0);
+	if (retval < 0)
 		goto err_disable_clk;
-	}
+	hcd->irq = retval;
 
 	ehci = hcd_to_ehci(hcd);
 	ehci->caps = (struct ehci_caps *) ehci_mv->cap_regs;

2.25.1

From: Suzuki K Poulose <[email protected]>

[ Upstream commit 3f4943d422c5febbb3c764670011a00eb2a86238 ]

etm probe could be deferred due to the dependency in the trace path chain and may be retried. We need to clear the per-cpu etmdrvdata entry for the etm in case of a failure to avoid use-after-free cases as reported below:

KASAN use-after-free bug in etm4_cpu_pm_notify():

[    8.574566] coresight etm0: CPU0: ETM v4.2 initialized
[    8.581920] BUG: KASAN: use-after-free in etm4_cpu_pm_notify+0x580/0x2024
[    8.581925] Read of size 8 at addr ffffff813304f8c8 by task swapper/3/0
[    8.581927]
[    8.581934] CPU: 3 PID: 0 Comm: swapper/3 Tainted: G S      W         5.4.28 #314
[    8.587775] coresight etm1: CPU1: ETM v4.2 initialized
[    8.594195] Call trace:
[    8.594205]  dump_backtrace+0x0/0x188
[    8.594209]  show_stack+0x20/0x2c
[    8.594216]  dump_stack+0xdc/0x144
[    8.594227]  print_address_description+0x3c/0x494
[    8.594232]  __kasan_report+0x144/0x168
[    8.601598] coresight etm2: CPU2: ETM v4.2 initialized
[    8.602563]  kasan_report+0x10/0x18
[    8.602568]  check_memory_region+0x1a4/0x1b4
[    8.602572]  __kasan_check_read+0x18/0x24
[    8.602577]  etm4_cpu_pm_notify+0x580/0x2024
[    8.665945]  notifier_call_chain+0x5c/0x90
[    8.670166]  __atomic_notifier_call_chain+0x90/0xf8
[    8.675182]  cpu_pm_notify+0x40/0x6c
[    8.678858]  cpu_pm_enter+0x38/0x80
[    8.682451]  psci_enter_idle_state+0x34/0x70
[    8.686844]  cpuidle_enter_state+0xb8/0x20c
[    8.691143]  cpuidle_enter+0x38/0x4c
[    8.694820]  call_cpuidle+0x3c/0x68
[    8.698408]  do_idle+0x1a0/0x280
[    8.701729]  cpu_startup_entry+0x24/0x28
[    8.705768]  secondary_start_kernel+0x15c/0x170
[    8.710423]
[    8.711972] Allocated by task 242:
[    8.715473]  __kasan_kmalloc+0xf0/0x1ac
[    8.719426]  kasan_slab_alloc+0x14/0x1c
[    8.723375]  __kmalloc_track_caller+0x23c/0x388
[    8.728040]  devm_kmalloc+0x38/0x94
[    8.731632]  etm4_probe+0x48/0x3c8
[    8.735140]  amba_probe+0xbc/0x158
[    8.738645]  really_probe+0x144/0x408
[    8.742412]  driver_probe_device+0x70/0x140
[    8.746716]  __device_attach_driver+0x9c/0x110
[    8.751287]  bus_for_each_drv+0x90/0xd8
[    8.755236]  __device_attach+0xb4/0x164
[    8.759188]  device_initial_probe+0x20/0x2c
[    8.763490]  bus_probe_device+0x34/0x94
[    8.767436]  device_add+0x34c/0x3e0
[    8.771029]  amba_device_try_add+0x68/0x440
[    8.775332]  amba_deferred_retry_func+0x48/0xc8
[    8.779997]  process_one_work+0x344/0x648
[    8.784127]  worker_thread+0x2ac/0x47c
[    8.787987]  kthread+0x128/0x138
[    8.791313]  ret_from_fork+0x10/0x18
[    8.794993]
[    8.796532] Freed by task 242:
[    8.799684]  __kasan_slab_free+0x15c/0x22c
[    8.803897]  kasan_slab_free+0x10/0x1c
[    8.807761]  kfree+0x25c/0x4bc
[    8.810913]  release_nodes+0x240/0x2b0
[    8.814767]  devres_release_all+0x3c/0x54
[    8.818887]  really_probe+0x178/0x408
[    8.822661]  driver_probe_device+0x70/0x140
[    8.826963]  __device_attach_driver+0x9c/0x110
[    8.831539]  bus_for_each_drv+0x90/0xd8
[    8.835487]  __device_attach+0xb4/0x164
[    8.839431]  device_initial_probe+0x20/0x2c
[    8.843732]  bus_probe_device+0x34/0x94
[    8.847678]  device_add+0x34c/0x3e0
[    8.851274]  amba_device_try_add+0x68/0x440
[    8.855576]  amba_deferred_retry_func+0x48/0xc8
[    8.860240]  process_one_work+0x344/0x648
[    8.864366]  worker_thread+0x2ac/0x47c
[    8.868228]  kthread+0x128/0x138
[    8.871557]  ret_from_fork+0x10/0x18
[    8.875231]
[    8.876782] The buggy address belongs to the object at ffffff813304f800
[    8.876782]  which belongs to the cache kmalloc-1k of size 1024
[    8.889632] The buggy address is located 200 bytes inside of
[    8.889632]  1024-byte region [ffffff813304f800, ffffff813304fc00)
[    8.901761] The buggy address belongs to the page:
[    8.906695] page:ffffffff04ac1200 refcount:1 mapcount:0 mapping:ffffff8146c03800 index:0x0 compound_mapcount: 0
[    8.917047] flags: 0x4000000000010200(slab|head)
[    8.921799] raw: 4000000000010200 dead000000000100 dead000000000122 ffffff8146c03800
[    8.929753] raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000
[    8.937703] page dumped because: kasan: bad access detected
[    8.943433]
[    8.944974] Memory state around the buggy address:
[    8.949903]  ffffff813304f780: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[    8.957320]  ffffff813304f800: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[    8.964742] >ffffff813304f880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[    8.972157]                                               ^
[    8.977886]  ffffff813304f900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[    8.985298]  ffffff813304f980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[    8.992713] ==================================================================

---
 drivers/hwtracing/coresight/coresight-etm4x.c | 1 +
 1 file changed, 1 insertion(+)

index a128b5063f46c..83dccdeef9069 100644
@@ -1184,6 +1184,7 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 	return 0;
 
 err_arch_supported:
+	etmdrvdata[drvdata->cpu] = NULL;
 	if (--etm4_count == 0) {
 		cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING);
 		if (hp_online)

2.25.1

From: James Morse <[email protected]>

[ Upstream commit 8fcc4ae6faf8b455eeef00bc9ae70744e3b0f462 ]

APEI is unable to do all of its error handling work in nmi-context, so it defers non-fatal work onto the irq_work queue. arch_irq_work_raise() sends an IPI to the calling cpu, but this is not guaranteed to be taken before returning to user-space.

Unless the exception interrupted a context with irqs-masked, irq_work_run() can run immediately. Otherwise return -EINPROGRESS to indicate ghes_notify_sea() found some work to do, but it hasn't finished yet.

With this apei_claim_sea() returning '0' means this external-abort was also notification of a firmware-first RAS error, and that APEI has processed the CPER records.

---
 arch/arm64/kernel/acpi.c | 25 +++++++++++++++++++++++++
 arch/arm64/mm/fault.c    | 12 +++++++-----
 2 files changed, 32 insertions(+), 5 deletions(-)

index a100483b47c42..46ec402e97edc 100644
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
+#include <linux/irq_work.h>
 #include <linux/memblock.h>
 #include <linux/of_fdt.h>
 #include <linux/smp.h>

@@ -269,6 +270,7 @@ pgprot_t __acpi_get_mem_attribute(phys_addr_t addr)
 int apei_claim_sea(struct pt_regs *regs)
 {
 	int err = -ENOENT;
+	bool return_to_irqs_enabled;
 	unsigned long current_flags;
 
 	if (!IS_ENABLED(CONFIG_ACPI_APEI_GHES))

@@ -276,6 +278,12 @@ int apei_claim_sea(struct pt_regs *regs)
 
 	current_flags = local_daif_save_flags();
 
+	/* current_flags isn't useful here as daif doesn't tell us about pNMI */
+	return_to_irqs_enabled = !irqs_disabled_flags(arch_local_save_flags());
+
+	if (regs)
+		return_to_irqs_enabled = interrupts_enabled(regs);
+
 	/*
 	 * SEA can interrupt SError, mask it and describe this as an NMI so
 	 * that APEI defers the handling.

@@ -284,6 +292,23 @@ int apei_claim_sea(struct pt_regs *regs)
 	nmi_enter();
 	err = ghes_notify_sea();
 	nmi_exit();
+
+	/*
+	 * APEI NMI-like notifications are deferred to irq_work. Unless
+	 * we interrupted irqs-masked code, we can do that now.
+	 */
+	if (!err) {
+		if (return_to_irqs_enabled) {
+			local_daif_restore(DAIF_PROCCTX_NOIRQ);
+			__irq_enter();
+			irq_work_run();
+			__irq_exit();
+		} else {
+			pr_warn_ratelimited("APEI work queued but not completed");
+			err = -EINPROGRESS;
+		}
+	}
+
 	local_daif_restore(current_flags);
 
 	return err;

index d26e6cd289539..2a7339aeb1ad4 100644
@@ -654,11 +654,13 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 
 	inf = esr_to_fault_info(esr);
 
-	/*
-	 * Return value ignored as we rely on signal merging.
-	 * Future patches will make this more robust.
-	 */
-	apei_claim_sea(regs);
+	if (user_mode(regs) && apei_claim_sea(regs) == 0) {
+		/*
+		 * APEI claimed this as a firmware-first notification.
+		 * Some processing deferred to task_work before ret_to_user().
+		 */
+		return 0;
+	}
 
 	if (esr & ESR_ELx_FnV)
 		siaddr = NULL;

2.25.1

From: Wei Yongjun <[email protected]>

[ Upstream commit d0b1e4a638d670a09f42017a3e567dc846931ba8 ]

Fix to return negative error code -ENOMEM from create_afu error handling case instead of 0, as done elsewhere in this function.

---
 drivers/scsi/cxlflash/main.c | 1 +
 1 file changed, 1 insertion(+)

index 93ef97af22df4..67d681c53c295 100644
@@ -3746,6 +3746,7 @@ static int cxlflash_probe(struct pci_dev *pdev,
 	cfg->afu_cookie = cfg->ops->create_afu(pdev);
 	if (unlikely(!cfg->afu_cookie)) {
 		dev_err(dev, "%s: create_afu failed\n", __func__);
+		rc = -ENOMEM;
 		goto out_remove;
 	}
 

2.25.1

From: Anshuman Khandual <[email protected]>

[ Upstream commit 1ed1b90a0594c8c9d31e8bb8be25a2b37717dc9e ]

ID_DFR0 based TraceFilt feature should not be exposed to guests. Hence lets drop it.

---
 arch/arm64/kernel/cpufeature.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 1df57ffc9314d..f2ec845404149 100644
@@ -319,7 +319,7 @@ static const struct arm64_ftr_bits ftr_id_pfr0[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_dfr0[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0),
+	/* [31:28] TraceFilt */
 	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0xf),	/* PerfMon */
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0),

2.25.1




_______________________________________________
linux-arm-kernel mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

From: Philip Yang <[email protected]>

[ Upstream commit f7646585a30ed8ef5ab300d4dc3b0c1d6afbe71d ]

In free memory of gpu path, remove bo from validate_list to make sure restore worker don't access the BO any more, then unregister bo MMU interval notifier. Otherwise, the restore worker will crash in the middle of validating BO user pages if MMU interval notifer is gone.

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

index edb561baf8b90..f3fa271e3394c 100644
@@ -1247,15 +1247,15 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 	 * be freed anyway
 	 */
 
-	/* No more MMU notifiers */
-	amdgpu_mn_unregister(mem->bo);
-
 	/* Make sure restore workers don't access the BO any more */
 	bo_list_entry = &mem->validate_list;
 	mutex_lock(&process_info->lock);
 	list_del(&bo_list_entry->head);
 	mutex_unlock(&process_info->lock);
 
+	/* No more MMU notifiers */
+	amdgpu_mn_unregister(mem->bo);
+
 	ret = reserve_bo_and_cond_vms(mem, NULL, BO_VM_ALL, &ctx);
 	if (unlikely(ret))
 		return ret;

2.25.1

From: Alexander Duyck <[email protected]>

[ Upstream commit 49ee3c2ab5234757bfb56a0b3a3cb422f427e3a3 ]

We are seeing a deadlock in e1000 down when NAPI is being disabled. Looking over the kernel function trace of the system it appears that the interface is being closed and then a reset is hitting which deadlocks the interface as the NAPI interface is already disabled.

To prevent this from happening I am disabling the reset task when __E1000_DOWN is already set. In addition code has been added so that we set the __E1000_DOWN while holding the __E1000_RESET flag in e1000_close in order to guarantee that the reset task will not run after we have started the close call.

---
 drivers/net/ethernet/intel/e1000/e1000_main.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

index f93ed70709c65..a2ee28e487a6f 100644
@@ -542,8 +542,13 @@ void e1000_reinit_locked(struct e1000_adapter *adapter)
 	WARN_ON(in_interrupt());
 	while (test_and_set_bit(__E1000_RESETTING, &adapter->flags))
 		msleep(1);
-	e1000_down(adapter);
-	e1000_up(adapter);
+
+	/* only run the task if not already down */
+	if (!test_bit(__E1000_DOWN, &adapter->flags)) {
+		e1000_down(adapter);
+		e1000_up(adapter);
+	}
+
 	clear_bit(__E1000_RESETTING, &adapter->flags);
 }
 

@@ -1433,10 +1438,15 @@ int e1000_close(struct net_device *netdev)
 	struct e1000_hw *hw = &adapter->hw;
 	int count = E1000_CHECK_RESET_COUNT;
 
-	while (test_bit(__E1000_RESETTING, &adapter->flags) && count--)
+	while (test_and_set_bit(__E1000_RESETTING, &adapter->flags) && count--)
 		usleep_range(10000, 20000);
 
-	WARN_ON(test_bit(__E1000_RESETTING, &adapter->flags));
+	WARN_ON(count < 0);
+
+	/* signal that we're down so that the reset task will no longer run */
+	set_bit(__E1000_DOWN, &adapter->flags);
+	clear_bit(__E1000_RESETTING, &adapter->flags);
+
 	e1000_down(adapter);
 	e1000_power_down_phy(adapter);
 	e1000_free_irq(adapter);

2.25.1

From: Dinghao Liu <[email protected]>

[ Upstream commit 00583fbe8031f69bba8b0a9a861efb75fb7131af ]

pm_runtime_get_sync() increments the runtime PM usage counter even the call returns an error code. Thus a pairing decrement is needed on the error handling path to keep the counter balanced.

---
 drivers/gpu/drm/nouveau/nouveau_debugfs.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

index 5c314f135dd10..3b13feca970f7 100644
@@ -183,8 +183,11 @@ nouveau_debugfs_pstate_set(struct file *file, const char __user *ubuf,
 	}
 
 	ret = pm_runtime_get_sync(drm->dev);
-	if (ret < 0 && ret != -EACCES)
+	if (ret < 0 && ret != -EACCES) {
+		pm_runtime_put_autosuspend(drm->dev);
 		return ret;
+	}
+
 	ret = nvif_mthd(ctrl, NVIF_CONTROL_PSTATE_USER, &args, sizeof(args));
 	pm_runtime_put_autosuspend(drm->dev);
 	if (ret < 0)

2.25.1

From: Dinghao Liu <[email protected]>

[ Upstream commit d7372dfb3f7f1602b87e0663e8b8646da23ebca7 ]

pm_runtime_get_sync() increments the runtime PM usage counter even the call returns an error code. Thus a pairing decrement is needed on the error handling path to keep the counter balanced.

---
 drivers/gpu/drm/nouveau/nouveau_gem.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index fbfe254227740..7d39d4949ee77 100644
@@ -78,8 +78,10 @@ nouveau_gem_object_open(struct drm_gem_object *gem, struct drm_file *file_priv)
 		return ret;
 
 	ret = pm_runtime_get_sync(dev);
-	if (ret < 0 && ret != -EACCES)
+	if (ret < 0 && ret != -EACCES) {
+		pm_runtime_put_autosuspend(dev);
 		goto out;
+	}
 
 	ret = nouveau_vma_new(nvbo, vmm, &vma);
 	pm_runtime_mark_last_busy(dev);

2.25.1

From: Dinghao Liu <[email protected]>

[ Upstream commit dc455f4c888365595c0a13da445e092422d55b8d ]

pm_runtime_get_sync() increments the runtime PM usage counter even the call returns an error code. Thus a pairing decrement is needed on the error handling path to keep the counter balanced.

---
 drivers/gpu/drm/nouveau/dispnv50/disp.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index 419a02260bfa7..ee2b1e1199e09 100644
@@ -1032,8 +1032,10 @@ nv50_mstc_detect(struct drm_connector *connector, bool force)
 		return connector_status_disconnected;
 
 	ret = pm_runtime_get_sync(connector->dev->dev);
-	if (ret < 0 && ret != -EACCES)
+	if (ret < 0 && ret != -EACCES) {
+		pm_runtime_put_autosuspend(connector->dev->dev);
 		return connector_status_disconnected;
+	}
 
 	conn_status = drm_dp_mst_detect_port(connector, mstc->port->mgr,
 					     mstc->port);

2.25.1

From: Shreyas Joshi <[email protected]>

[ Upstream commit 48021f98130880dd74286459a1ef48b5e9bc374f ]

If uboot passes a blank string to console_setup then it results in a trashed memory. Ultimately, the kernel crashes during freeing up the memory.

This fix checks if there is a blank parameter being passed to console_setup from uboot. In case it detects that the console parameter is blank then it doesn't setup the serial device and it gracefully exits.

---
 kernel/printk/printk.c | 3 +++
 1 file changed, 3 insertions(+)

index 971197f5d8ee5..5569ef6bc1839 100644
@@ -2193,6 +2193,9 @@ static int __init console_setup(char *str)
 	char *s, *options, *brl_options = NULL;
 	int idx;
 
+	if (str[0] == 0)
+		return 1;
+
 	if (_braille_console_setup(&str, &brl_options))
 		return 1;
 

2.25.1

From: Yu Chen <[email protected]>

[ Upstream commit 1c0e69ae1b9f9004fd72978612ae3463791edc56 ]

If the SS PHY is in P3, there is no pipe_clk, HW may use suspend_clk for function, as suspend_clk is slow so EP command need more time to complete, e.g, imx8M suspend_clk is 32K, set ep configuration will take about 380us per below trace time stamp(44.286278 - 44.285897 = 0.000381):

configfs_acm.sh-822 [000] d..1 44.285896: dwc3_writel: addr
000000006d59aae1 value 00000401
configfs_acm.sh-822 [000] d..1 44.285897: dwc3_readl: addr
000000006d59aae1 value 00000401
... ...
configfs_acm.sh-822 [000] d..1 44.286278: dwc3_readl: addr
000000006d59aae1 value 00000001
configfs_acm.sh-822 [000] d..1 44.286279: dwc3_gadget_ep_cmd:
ep0out: cmd 'Set Endpoint Configuration' [401] params 00001000 00000500 00000000 --> status: Successful

This was originally found on Hisilicon Kirin Soc that need more time for the device controller to clear the CmdAct of DEPCMD.

---
 drivers/usb/dwc3/gadget.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 4225544342519..809103254fc64 100644
@@ -270,7 +270,7 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned cmd,
 {
 	const struct usb_endpoint_descriptor *desc = dep->endpoint.desc;
 	struct dwc3		*dwc = dep->dwc;
-	u32			timeout = 1000;
+	u32			timeout = 5000;
 	u32			saved_config = 0;
 	u32			reg;
 

2.25.1

From: David Sterba <[email protected]>

[ Upstream commit 7c09c03091ac562ddca2b393e5d65c1d37da79f1 ]

Deleting a subvolume on a full filesystem leads to ENOSPC followed by a forced read-only. This is not a transaction abort and the filesystem is otherwise ok, so the error should be just propagated to the callers.

This is caused by unnecessary call to btrfs_handle_fs_error for all errors, except EAGAIN. This does not make sense as the standard transaction abort mechanism is in btrfs_drop_snapshot so all relevant failures are handled.

Originally in commit cb1b69f4508a ("Btrfs: forced readonly when btrfs_drop_snapshot() fails") there was no return value at all, so the btrfs_std_error made some sense but once the error handling and propagation has been implemented we don't need it anymore.

---
 fs/btrfs/extent-tree.c | 2 --
 1 file changed, 2 deletions(-)

index 31c1ed554d26d..7658f3193175b 100644
@@ -5428,8 +5428,6 @@ out:
 	 */
 	if (!for_reloc && !root_dropped)
 		btrfs_add_dead_root(root);
-	if (err && err != -EAGAIN)
-		btrfs_handle_fs_error(fs_info, err, NULL);
 	return err;
 }
 

2.25.1

From: Omar Sandoval <[email protected]>

[ Upstream commit c36cac28cb94e58f7e21ff43bdc6064346dab32c ]

In btrfs_submit_direct(), if we fail to allocate the btrfs_dio_private, we complete the ordered extent range. However, we don't mark that the range doesn't need to be cleaned up from btrfs_direct_IO() until later. Therefore, if we fail to allocate the btrfs_dio_private, we complete the ordered extent range twice. We could fix this by updating unsubmitted_oe_range earlier, but it's cleaner to reorganize the code so that creating the btrfs_dio_private and submitting the bios are separate, and once the btrfs_dio_private is created, cleanup always happens through the btrfs_dio_private.

The logic around unsubmitted_oe_range_end and unsubmitted_oe_range_start is really subtle. We have the following:

1. btrfs_direct_IO sets those two to the same value.

2. When we call __blockdev_direct_IO unless btrfs_get_blocks_direct->btrfs_get_blocks_direct_write is called to modify unsubmitted_oe_range_start so that start < end. Cleanup won't happen.

3. We come into btrfs_submit_direct - if it dip allocation fails we'd return with oe_range_end now modified so cleanup will happen.

4. If we manage to allocate the dip we reset the unsubmitted range members to be equal so that cleanup happens from btrfs_endio_direct_write.

This 4-step logic is not really obvious, especially given it's scattered across 3 functions.

---
 fs/btrfs/inode.c | 178 +++++++++++++++++++----------------------------
 1 file changed, 70 insertions(+), 108 deletions(-)

index 9ac40991a6405..e9787b7b943a2 100644
@@ -8586,14 +8586,64 @@ err:
 	return ret;
 }
 
-static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip)
+/*
+ * If this succeeds, the btrfs_dio_private is responsible for cleaning up locked
+ * or ordered extents whether or not we submit any bios.
+ */
+static struct btrfs_dio_private *btrfs_create_dio_private(struct bio *dio_bio,
+							  struct inode *inode,
+							  loff_t file_offset)
 {
-	struct inode *inode = dip->inode;
+	const bool write = (bio_op(dio_bio) == REQ_OP_WRITE);
+	struct btrfs_dio_private *dip;
+	struct bio *bio;
+
+	dip = kzalloc(sizeof(*dip), GFP_NOFS);
+	if (!dip)
+		return NULL;
+
+	bio = btrfs_bio_clone(dio_bio);
+	bio->bi_private = dip;
+	btrfs_io_bio(bio)->logical = file_offset;
+
+	dip->private = dio_bio->bi_private;
+	dip->inode = inode;
+	dip->logical_offset = file_offset;
+	dip->bytes = dio_bio->bi_iter.bi_size;
+	dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9;
+	dip->orig_bio = bio;
+	dip->dio_bio = dio_bio;
+	atomic_set(&dip->pending_bios, 1);
+
+	if (write) {
+		struct btrfs_dio_data *dio_data = current->journal_info;
+
+		/*
+		 * Setting range start and end to the same value means that
+		 * no cleanup will happen in btrfs_direct_IO
+		 */
+		dio_data->unsubmitted_oe_range_end = dip->logical_offset +
+			dip->bytes;
+		dio_data->unsubmitted_oe_range_start =
+			dio_data->unsubmitted_oe_range_end;
+
+		bio->bi_end_io = btrfs_endio_direct_write;
+	} else {
+		bio->bi_end_io = btrfs_endio_direct_read;
+		dip->subio_endio = btrfs_subio_endio_read;
+	}
+	return dip;
+}
+
+static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
+				loff_t file_offset)
+{
+	const bool write = (bio_op(dio_bio) == REQ_OP_WRITE);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_dio_private *dip;
 	struct bio *bio;
-	struct bio *orig_bio = dip->orig_bio;
-	u64 start_sector = orig_bio->bi_iter.bi_sector;
-	u64 file_offset = dip->logical_offset;
+	struct bio *orig_bio;
+	u64 start_sector;
 	int async_submit = 0;
 	u64 submit_len;
 	int clone_offset = 0;

@@ -8602,11 +8652,24 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip)
 	blk_status_t status;
 	struct btrfs_io_geometry geom;
 
+	dip = btrfs_create_dio_private(dio_bio, inode, file_offset);
+	if (!dip) {
+		if (!write) {
+			unlock_extent(&BTRFS_I(inode)->io_tree, file_offset,
+				file_offset + dio_bio->bi_iter.bi_size - 1);
+		}
+		dio_bio->bi_status = BLK_STS_RESOURCE;
+		dio_end_io(dio_bio);
+		return;
+	}
+
+	orig_bio = dip->orig_bio;
+	start_sector = orig_bio->bi_iter.bi_sector;
 	submit_len = orig_bio->bi_iter.bi_size;
 	ret = btrfs_get_io_geometry(fs_info, btrfs_op(orig_bio),
 				    start_sector << 9, submit_len, &geom);
 	if (ret)
-		return -EIO;
+		goto out_err;
 
 	if (geom.len >= submit_len) {
 		bio = orig_bio;

@@ -8669,7 +8732,7 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip)
 submit:
 	status = btrfs_submit_dio_bio(bio, inode, file_offset, async_submit);
 	if (!status)
-		return 0;
+		return;
 
 	if (bio != orig_bio)
 		bio_put(bio);

@@ -8683,107 +8746,6 @@ out_err:
 	 */
 	if (atomic_dec_and_test(&dip->pending_bios))
 		bio_io_error(dip->orig_bio);
-
-	/* bio_end_io() will handle error, so we needn't return it */
-	return 0;
-}
-
-static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
-				loff_t file_offset)
-{
-	struct btrfs_dio_private *dip = NULL;
-	struct bio *bio = NULL;
-	struct btrfs_io_bio *io_bio;
-	bool write = (bio_op(dio_bio) == REQ_OP_WRITE);
-	int ret = 0;
-
-	bio = btrfs_bio_clone(dio_bio);
-
-	dip = kzalloc(sizeof(*dip), GFP_NOFS);
-	if (!dip) {
-		ret = -ENOMEM;
-		goto free_ordered;
-	}
-
-	dip->private = dio_bio->bi_private;
-	dip->inode = inode;
-	dip->logical_offset = file_offset;
-	dip->bytes = dio_bio->bi_iter.bi_size;
-	dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9;
-	bio->bi_private = dip;
-	dip->orig_bio = bio;
-	dip->dio_bio = dio_bio;
-	atomic_set(&dip->pending_bios, 1);
-	io_bio = btrfs_io_bio(bio);
-	io_bio->logical = file_offset;
-
-	if (write) {
-		bio->bi_end_io = btrfs_endio_direct_write;
-	} else {
-		bio->bi_end_io = btrfs_endio_direct_read;
-		dip->subio_endio = btrfs_subio_endio_read;
-	}
-
-	/*
-	 * Reset the range for unsubmitted ordered extents (to a 0 length range)
-	 * even if we fail to submit a bio, because in such case we do the
-	 * corresponding error handling below and it must not be done a second
-	 * time by btrfs_direct_IO().
-	 */
-	if (write) {
-		struct btrfs_dio_data *dio_data = current->journal_info;
-
-		dio_data->unsubmitted_oe_range_end = dip->logical_offset +
-			dip->bytes;
-		dio_data->unsubmitted_oe_range_start =
-			dio_data->unsubmitted_oe_range_end;
-	}
-
-	ret = btrfs_submit_direct_hook(dip);
-	if (!ret)
-		return;
-
-	btrfs_io_bio_free_csum(io_bio);
-
-free_ordered:
-	/*
-	 * If we arrived here it means either we failed to submit the dip
-	 * or we either failed to clone the dio_bio or failed to allocate the
-	 * dip. If we cloned the dio_bio and allocated the dip, we can just
-	 * call bio_endio against our io_bio so that we get proper resource
-	 * cleanup if we fail to submit the dip, otherwise, we must do the
-	 * same as btrfs_endio_direct_[write|read] because we can't call these
-	 * callbacks - they require an allocated dip and a clone of dio_bio.
-	 */
-	if (bio && dip) {
-		bio_io_error(bio);
-		/*
-		 * The end io callbacks free our dip, do the final put on bio
-		 * and all the cleanup and final put for dio_bio (through
-		 * dio_end_io()).
-		 */
-		dip = NULL;
-		bio = NULL;
-	} else {
-		if (write)
-			__endio_write_update_ordered(inode,
-						file_offset,
-						dio_bio->bi_iter.bi_size,
-						false);
-		else
-			unlock_extent(&BTRFS_I(inode)->io_tree, file_offset,
-			      file_offset + dio_bio->bi_iter.bi_size - 1);
-
-		dio_bio->bi_status = BLK_STS_IOERR;
-		/*
-		 * Releases and cleans up our dio_bio, no need to bio_put()
-		 * nor bio_endio()/bio_io_error() against dio_bio.
-		 */
-		dio_end_io(dio_bio);
-	}
-	if (bio)
-		bio_put(bio);
-	kfree(dip);
 }
 
 static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info,

2.25.1

From: Dinghao Liu <[email protected]>

[ Upstream commit 6f8cd246411575703d9312888b70705c396b53a9 ]

pm_runtime_get_sync() increments the runtime PM usage counter even when it returns an error code. Thus a pairing decrement is needed on the error handling path to keep the counter balanced.

---
 drivers/gpio/gpio-rcar.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index 187984d26f47a..f0b6c68e848e3 100644
@@ -250,8 +250,10 @@ static int gpio_rcar_request(struct gpio_chip *chip, unsigned offset)
 	int error;
 
 	error = pm_runtime_get_sync(p->dev);
-	if (error < 0)
+	if (error < 0) {
+		pm_runtime_put(p->dev);
 		return error;
+	}
 
 	error = pinctrl_gpio_request(chip->base + offset);
 	if (error)

2.25.1

From: Qian Cai <[email protected]>

[ Upstream commit 1518ac272e789cae8c555d69951b032a275b7602 ]

Finished a qemu-kvm (-device vfio-pci,host=0001:01:00.0) triggers a few memory leaks after a while because vfio_pci_set_ctx_trigger_single() calls eventfd_ctx_fdget() without the matching eventfd_ctx_put() later. Fix it by calling eventfd_ctx_put() for those memory in vfio_pci_release() before vfio_device_release().

unreferenced object 0xebff008981cc2b00 (size 128):
comm "qemu-kvm", pid 4043, jiffies 4294994816 (age 9796.310s) hex dump (first 32 bytes):
01 00 00 00 6b 6b 6b 6b 00 00 00 00 ad 4e ad de ....kkkk.....N.. ff ff ff ff 6b 6b 6b 6b ff ff ff ff ff ff ff ff ....kkkk........
backtrace:

    [<00000000917e8f8d>] slab_post_alloc_hook+0x74/0x9c
    [<00000000df0f2aa2>] kmem_cache_alloc_trace+0x2b4/0x3d4
    [<000000005fcec025>] do_eventfd+0x54/0x1ac
    [<0000000082791a69>] __arm64_sys_eventfd2+0x34/0x44
    [<00000000b819758c>] do_el0_svc+0x128/0x1dc
    [<00000000b244e810>] el0_sync_handler+0xd0/0x268
    [<00000000d495ef94>] el0_sync+0x164/0x180

unreferenced object 0x29ff008981cc4180 (size 128):
comm "qemu-kvm", pid 4043, jiffies 4294994818 (age 9796.290s) hex dump (first 32 bytes):
01 00 00 00 6b 6b 6b 6b 00 00 00 00 ad 4e ad de ....kkkk.....N.. ff ff ff ff 6b 6b 6b 6b ff ff ff ff ff ff ff ff ....kkkk........
backtrace:

    [<00000000917e8f8d>] slab_post_alloc_hook+0x74/0x9c
    [<00000000df0f2aa2>] kmem_cache_alloc_trace+0x2b4/0x3d4
    [<000000005fcec025>] do_eventfd+0x54/0x1ac
    [<0000000082791a69>] __arm64_sys_eventfd2+0x34/0x44
    [<00000000b819758c>] do_el0_svc+0x128/0x1dc
    [<00000000b244e810>] el0_sync_handler+0xd0/0x268
    [<00000000d495ef94>] el0_sync+0x164/0x180

---
 drivers/vfio/pci/vfio_pci.c | 4 ++++
 1 file changed, 4 insertions(+)

index 0d16f9806655f..12f7691e8b6ca 100644
@@ -474,6 +474,10 @@ static void vfio_pci_release(void *device_data)
 	if (!(--vdev->refcnt)) {
 		vfio_spapr_pci_eeh_release(vdev->pdev);
 		vfio_pci_disable(vdev);
+		if (vdev->err_trigger)
+			eventfd_ctx_put(vdev->err_trigger);
+		if (vdev->req_trigger)
+			eventfd_ctx_put(vdev->req_trigger);
 	}
 
 	mutex_unlock(&vdev->reflck->lock);

2.25.1

From: Paul Mackerras <[email protected]>

[ Upstream commit 11362b1befeadaae4d159a8cddcdaf6b8afe08f9 ]

There is a potential race condition between hypervisor page faults and flushing a memslot. It is possible for a page fault to read the memslot before a memslot is updated and then write a PTE to the partition-scoped page tables after kvmppc_radix_flush_memslot has completed. (Note that this race has never been explicitly observed.)

To close this race, it is sufficient to increment the MMU sequence number while the kvm->mmu_lock is held. That will cause mmu_notifier_retry() to return true, and the page fault will then return to the guest without inserting a PTE.

---
 arch/powerpc/kvm/book3s_64_mmu_radix.c | 5 +++++
 1 file changed, 5 insertions(+)

index da8375437d161..9d73448354698 100644
@@ -1104,6 +1104,11 @@ void kvmppc_radix_flush_memslot(struct kvm *kvm,
 					 kvm->arch.lpid);
 		gpa += PAGE_SIZE;
 	}
+	/*
+	 * Increase the mmu notifier sequence number to prevent any page
+	 * fault that read the memslot earlier from writing a PTE.
+	 */
+	kvm->mmu_notifier_seq++;
 	spin_unlock(&kvm->mmu_lock);
 }
 

2.25.1

From: Ian Rogers <[email protected]>

[ Upstream commit 3efc899d9afb3d03604f191a0be9669eabbfc4aa ]

If allocated, perf_pkg_mask and metric_events need freeing.

---
 tools/perf/util/evsel.c | 2 ++
 1 file changed, 2 insertions(+)

index 12b1755b136d3..9dd9e3f4ef591 100644
@@ -1255,6 +1255,8 @@ void perf_evsel__exit(struct evsel *evsel)
 	zfree(&evsel->group_name);
 	zfree(&evsel->name);
 	zfree(&evsel->pmu_name);
+	zfree(&evsel->per_pkg_mask);
+	zfree(&evsel->metric_events);
 	perf_evsel__object.fini(evsel);
 }
 

2.25.1

From: Ian Rogers <[email protected]>

[ Upstream commit 7597ce89b3ed239f7a3408b930d2a6c7a4c938a1 ]

Make the architecture test directory agree with the code comment.

Committer notes:

This was split from a larger patch.

The code was assuming the developer always worked from tools/perf/, so make sure we do the test -d having $toolsdir/perf/arch/$arch, to match the intent expressed in the comment, just above that loop.

---
 tools/perf/trace/beauty/arch_errno_names.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 22c9fc900c847..f8c44a85650be 100755
@@ -91,7 +91,7 @@ EoHEADER
 # in tools/perf/arch
 archlist=""
 for arch in $(find $toolsdir/arch -maxdepth 1 -mindepth 1 -type d -printf "%f\n" | grep -v x86 | sort); do
-	test -d arch/$arch && archlist="$archlist $arch"
+	test -d $toolsdir/perf/arch/$arch && archlist="$archlist $arch"
 done
 
 for arch in x86 $archlist generic; do

2.25.1

From: Jiri Olsa <[email protected]>

[ Upstream commit ea9eb1f456a08c18feb485894185f7a4e31cc8a4 ]

Joakim reported wrong duration_time value for interval bigger than 4000 [1].

The problem is in the interval value we pass to update_stats function, which is typed as 'unsigned int' and overflows when we get over 2^32 (happens between intervals 4000 and 5000).

Retyping the passed value to unsigned long long.

[1] https://www.spinics.net/lists/linux-perf-users/msg11777.html

---
 tools/perf/builtin-stat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 468fc49420ce1..ac2feddc75fdd 100644
@@ -351,7 +351,7 @@ static void process_interval(void)
 	}
 
 	init_stats(&walltime_nsecs_stats);
-	update_stats(&walltime_nsecs_stats, stat_config.interval * 1000000);
+	update_stats(&walltime_nsecs_stats, stat_config.interval * 1000000ULL);
 	print_counters(&rs, 0, NULL);
 }
 

2.25.1

From: Xie XiuQi <[email protected]>

[ Upstream commit 07e9a6f538cbeecaf5c55b6f2991416f873cdcbd ]

Need to free "str" before return when asprintf() failed to avoid memory leak.

---
 tools/perf/util/sort.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 43d1d410854a3..4027906fd3e38 100644
@@ -2788,7 +2788,7 @@ static char *prefix_if_not_in(const char *pre, char *str)
 		return str;
 
 	if (asprintf(&n, "%s,%s", pre, str) < 0)
-		return NULL;
+		n = NULL;
 
 	free(str);
 	return n;

2.25.1

From: Ian Rogers <[email protected]>

[ Upstream commit a159e2fe89b4d1f9fb54b0ae418b961e239bf617 ]

Avoid a simple memory leak.

---
 tools/perf/util/metricgroup.c | 3 +++
 1 file changed, 3 insertions(+)

index 940a6e7a68549..7753c3091478a 100644
@@ -174,6 +174,7 @@ static int metricgroup__setup_events(struct list_head *groups,
 		if (!evsel) {
 			pr_debug("Cannot resolve %s: %s\n",
 					eg->metric_name, eg->metric_expr);
+			free(metric_events);
 			continue;
 		}
 		for (i = 0; i < eg->idnum; i++)

@@ -181,11 +182,13 @@ static int metricgroup__setup_events(struct list_head *groups,
 		me = metricgroup__lookup(metric_events_list, evsel, true);
 		if (!me) {
 			ret = -ENOMEM;
+			free(metric_events);
 			break;
 		}
 		expr = malloc(sizeof(struct metric_expr));
 		if (!expr) {
 			ret = -ENOMEM;
+			free(metric_events);
 			break;
 		}
 		expr->metric_expr = eg->metric_expr;

2.25.1

From: Adrian Hunter <[email protected]>

[ Upstream commit 61f82e3fb697a8e85f22fdec786528af73dc36d1 ]

In the absence of any modules, no "modules" map is created, but there are other executable pages to map, due to eBPF JIT, kprobe or ftrace. Map them by recognizing that the first "module" symbol is not necessarily from a module, and adjust the map accordingly.

---
 tools/perf/util/symbol-elf.c | 7 +++++++
 1 file changed, 7 insertions(+)

index 66f4be1df573e..2ec0a32da5793 100644
@@ -1449,6 +1449,7 @@ struct kcore_copy_info {
 	u64 first_symbol;
 	u64 last_symbol;
 	u64 first_module;
+	u64 first_module_symbol;
 	u64 last_module_symbol;
 	size_t phnum;
 	struct list_head phdrs;

@@ -1525,6 +1526,8 @@ static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,
 		return 0;
 
 	if (strchr(name, '[')) {
+		if (!kci->first_module_symbol || start < kci->first_module_symbol)
+			kci->first_module_symbol = start;
 		if (start > kci->last_module_symbol)
 			kci->last_module_symbol = start;
 		return 0;

@@ -1722,6 +1725,10 @@ static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir,
 		kci->etext += page_size;
 	}
 
+	if (kci->first_module_symbol &&
+	    (!kci->first_module || kci->first_module_symbol < kci->first_module))
+		kci->first_module = kci->first_module_symbol;
+
 	kci->first_module = round_down(kci->first_module, page_size);
 
 	if (kci->last_module_symbol) {

2.25.1

From: Dinghao Liu <[email protected]>

[ Upstream commit 1c1dbb2c02623db18a50c61b175f19aead800b4e ]

pm_runtime_get_sync() increments the runtime PM usage counter even when it returns an error code. Thus a pairing decrement is needed on the error handling path to keep the counter balanced.

---
 drivers/pci/controller/dwc/pcie-tegra194.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

index f89f5acee72d4..c06b05ab9f787 100644
@@ -1395,7 +1395,7 @@ static int tegra_pcie_config_rp(struct tegra_pcie_dw *pcie)
 	ret = pinctrl_pm_select_default_state(dev);
 	if (ret < 0) {
 		dev_err(dev, "Failed to configure sideband pins: %d\n", ret);
-		goto fail_pinctrl;
+		goto fail_pm_get_sync;
 	}
 
 	tegra_pcie_init_controller(pcie);

@@ -1422,9 +1422,8 @@ static int tegra_pcie_config_rp(struct tegra_pcie_dw *pcie)
 
 fail_host_init:
 	tegra_pcie_deinit_controller(pcie);
-fail_pinctrl:
-	pm_runtime_put_sync(dev);
 fail_pm_get_sync:
+	pm_runtime_put_sync(dev);
 	pm_runtime_disable(dev);
 	return ret;
 }

2.25.1

From: Dinghao Liu <[email protected]>

[ Upstream commit 65bd91dd6957390c42a0491b9622cf31a2cdb140 ]

pm_runtime_get_sync() increments the runtime PM usage counter even the call returns an error code. Thus a pairing decrement is needed on the error handling path to keep the counter balanced.

---
 sound/soc/img/img-i2s-out.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

index 4b18534096336..9c4212f2f7269 100644
@@ -347,8 +347,10 @@ static int img_i2s_out_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	chan_control_mask = IMG_I2S_OUT_CHAN_CTL_CLKT_MASK;
 
 	ret = pm_runtime_get_sync(i2s->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_noidle(i2s->dev);
 		return ret;
+	}
 
 	img_i2s_out_disable(i2s);
 

@@ -488,8 +490,10 @@ static int img_i2s_out_probe(struct platform_device *pdev)
 			goto err_pm_disable;
 	}
 	ret = pm_runtime_get_sync(&pdev->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_noidle(&pdev->dev);
 		goto err_suspend;
+	}
 
 	reg = IMG_I2S_OUT_CTL_FRM_SIZE_MASK;
 	img_i2s_out_writel(i2s, reg, IMG_I2S_OUT_CTL);

2.25.1

From: Dinghao Liu <[email protected]>

[ Upstream commit 9604617e998b49f7695fea1479ed82421ef8c9f0 ]

There are two error handling paths in this functon. When wlcore_tx_work_locked() returns an error code, we should decrease the runtime PM usage counter the same way as the error handling path beginning from pm_runtime_get_sync().

---
 drivers/net/wireless/ti/wlcore/tx.c | 1 +
 1 file changed, 1 insertion(+)

index 90e56d4c3df3b..e20e18cd04aed 100644
@@ -863,6 +863,7 @@ void wl1271_tx_work(struct work_struct *work)
 
 	ret = wlcore_tx_work_locked(wl);
 	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		wl12xx_queue_recovery_work(wl);
 		goto out;
 	}

2.25.1

From: Dinghao Liu <[email protected]>

[ Upstream commit 282a04bf1d8029eb98585cb5db3fd70fe8bc91f7 ]

pm_runtime_get_sync() increments the runtime PM usage counter even the call returns an error code. Thus a pairing decrement is needed on the error handling path to keep the counter balanced.

---
 drivers/net/wireless/ti/wlcore/main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index 547ad538d8b66..5f74cf821068d 100644
@@ -3658,8 +3658,10 @@ void wlcore_regdomain_config(struct wl1271 *wl)
 		goto out;
 
 	ret = pm_runtime_get_sync(wl->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_autosuspend(wl->dev);
 		goto out;
+	}
 
 	ret = wlcore_cmd_regdomain_config_locked(wl);
 	if (ret < 0) {

2.25.1

From: Dinghao Liu <[email protected]>

[ Upstream commit 550e68ea36a6671a96576c0531685ce6e6c0d19d ]

pm_runtime_get_sync() increments the runtime PM usage counter even when it returns an error code. Thus a pairing decrement is needed on the error handling path to keep the counter balanced.

---
 drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index b9d5d55a5edb9..ef89947ee3191 100644
@@ -540,8 +540,10 @@ static int bch_set_geometry(struct gpmi_nand_data *this)
 		return ret;
 
 	ret = pm_runtime_get_sync(this->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_autosuspend(this->dev);
 		return ret;
+	}
 
 	/*
 	* Due to erratum #2847 of the MX23, the BCH cannot be soft reset on this

2.25.1

From: Dinghao Liu <[email protected]>

[ Upstream commit 37f7212148cf1d796135cdf8d0c7fee13067674b ]

pm_runtime_get_sync() increments the runtime PM usage counter even when it returns an error code. Thus a pairing decrement is needed on the error handling path to keep the counter balanced.

---
 drivers/mtd/nand/raw/omap_elm.c | 1 +
 1 file changed, 1 insertion(+)

index 5502ffbdd1e6d..6e0e31eab7cce 100644
@@ -411,6 +411,7 @@ static int elm_probe(struct platform_device *pdev)
 	pm_runtime_enable(&pdev->dev);
 	if (pm_runtime_get_sync(&pdev->dev) < 0) {
 		ret = -EINVAL;
+		pm_runtime_put_sync(&pdev->dev);
 		pm_runtime_disable(&pdev->dev);
 		dev_err(&pdev->dev, "can't enable clock\n");
 		return ret;

2.25.1

From: Dinghao Liu <[email protected]>

[ Upstream commit fcee90cdf6f3a3a371add04d41528d5ba9c3b411 ]

pm_runtime_get_sync() increments the runtime PM usage counter even when it returns an error code. Thus a pairing decrement is needed on the error handling path to keep the counter balanced.

Also, call pm_runtime_disable() when pm_runtime_get_sync() returns an error code.

---
 drivers/pci/controller/pci-tegra.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

index b71e753419c2d..cfa3c83d6cc74 100644
@@ -2768,7 +2768,7 @@ static int tegra_pcie_probe(struct platform_device *pdev)
 	err = pm_runtime_get_sync(pcie->dev);
 	if (err < 0) {
 		dev_err(dev, "fail to enable pcie controller: %d\n", err);
-		goto teardown_msi;
+		goto pm_runtime_put;
 	}
 
 	err = tegra_pcie_request_resources(pcie);

@@ -2808,7 +2808,6 @@ free_resources:
 pm_runtime_put:
 	pm_runtime_put_sync(pcie->dev);
 	pm_runtime_disable(pcie->dev);
-teardown_msi:
 	tegra_pcie_msi_teardown(pcie);
 put_resources:
 	tegra_pcie_put_resources(pcie);

2.25.1

From: Jeff Layton <[email protected]>

[ Upstream commit dc3da0461cc4b76f2d0c5b12247fcb3b520edbbf ]

Nothing ensures that session will still be valid by the time we dereference the pointer. Take and put a reference.

In principle, we should always be able to get a reference here, but throw a warning if that's ever not the case.

---
 fs/ceph/caps.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

index b2695919435e8..af563d73d252c 100644
@@ -2013,12 +2013,24 @@ ack:
 			if (mutex_trylock(&session->s_mutex) == 0) {
 				dout("inverting session/ino locks on %p\n",
 				     session);
+				session = ceph_get_mds_session(session);
 				spin_unlock(&ci->i_ceph_lock);
 				if (took_snap_rwsem) {
 					up_read(&mdsc->snap_rwsem);
 					took_snap_rwsem = 0;
 				}
-				mutex_lock(&session->s_mutex);
+				if (session) {
+					mutex_lock(&session->s_mutex);
+					ceph_put_mds_session(session);
+				} else {
+					/*
+					 * Because we take the reference while
+					 * holding the i_ceph_lock, it should
+					 * never be NULL. Throw a warning if it
+					 * ever is.
+					 */
+					WARN_ON_ONCE(true);
+				}
 				goto retry;
 			}
 		}

2.25.1

From: Qian Cai <[email protected]>

[ Upstream commit d6c1f098f2a7ba62627c9bc17cda28f534ef9e4a ]

"prev_offset" is a static variable in swapin_nr_pages() that can be accessed concurrently with only mmap_sem held in read mode as noticed by KCSAN,

 BUG: KCSAN: data-race in swap_cluster_readahead / swap_cluster_readahead

write to 0xffffffff92763830 of 8 bytes by task 14795 on cpu 17:

  swap_cluster_readahead+0x2a6/0x5e0
  swapin_readahead+0x92/0x8dc
  do_swap_page+0x49b/0xf20
  __handle_mm_fault+0xcfb/0xd70
  handle_mm_fault+0xfc/0x2f0
  do_page_fault+0x263/0x715
  page_fault+0x34/0x40

1 lock held by (dnf)/14795:
#0: ffff897bd2e98858 (&mm->mmap_sem#2){++++}-{3:3}, at: do_page_fault+0x143/0x715 do_user_addr_fault at arch/x86/mm/fault.c:1405
(inlined by) do_page_fault at arch/x86/mm/fault.c:1535

 irq event stamp: 83493
 count_memcg_event_mm+0x1a6/0x270
 count_memcg_event_mm+0x119/0x270
 __do_softirq+0x365/0x589
 irq_exit+0xa2/0xc0

read to 0xffffffff92763830 of 8 bytes by task 1 on cpu 22:

  swap_cluster_readahead+0xfd/0x5e0
  swapin_readahead+0x92/0x8dc
  do_swap_page+0x49b/0xf20
  __handle_mm_fault+0xcfb/0xd70
  handle_mm_fault+0xfc/0x2f0
  do_page_fault+0x263/0x715
  page_fault+0x34/0x40

1 lock held by systemd/1:
#0: ffff897c38f14858 (&mm->mmap_sem#2){++++}-{3:3}, at: do_page_fault+0x143/0x715

 irq event stamp: 43530289
 count_memcg_event_mm+0x1a6/0x270
 count_memcg_event_mm+0x119/0x270
 __do_softirq+0x365/0x589
 irq_exit+0xa2/0xc0

---
 mm/swap_state.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

index 4ce014dc4571a..7c434fcfff0dd 100644
@@ -511,10 +511,11 @@ static unsigned long swapin_nr_pages(unsigned long offset)
 		return 1;
 
 	hits = atomic_xchg(&swapin_readahead_hits, 0);
-	pages = __swapin_nr_pages(prev_offset, offset, hits, max_pages,
+	pages = __swapin_nr_pages(READ_ONCE(prev_offset), offset, hits,
+				  max_pages,
 				  atomic_read(&last_readahead_pages));
 	if (!hits)
-		prev_offset = offset;
+		WRITE_ONCE(prev_offset, offset);
 	atomic_set(&last_readahead_pages, pages);
 
 	return pages;

2.25.1

From: Johannes Weiner <[email protected]>

[ Upstream commit abb242f57196dbaa108271575353a0453f6834ef ]

The move_lock is a per-memcg lock, but the VM accounting code that needs to acquire it comes from the page and follows page->mem_cgroup under RCU protection. That means that the page becomes unlocked not when we drop the move_lock, but when we update page->mem_cgroup. And that assignment doesn't imply any memory ordering. If that pointer write gets reordered against the reads of the page state - page_mapped, PageDirty etc. the state may change while we rely on it being stable and we can end up corrupting the counters.

Place an SMP memory barrier to make sure we're done with all page state by the time the new page->mem_cgroup becomes visible.

Also replace the open-coded move_lock with a lock_page_memcg() to make it more obvious what we're serializing against.

---
 mm/memcontrol.c | 26 ++++++++++++++------------
 1 file changed, 14 insertions(+), 12 deletions(-)

index 402c8bc65e08d..ca1632850fb76 100644
@@ -5489,7 +5489,6 @@ static int mem_cgroup_move_account(struct page *page,
 {
 	struct lruvec *from_vec, *to_vec;
 	struct pglist_data *pgdat;
-	unsigned long flags;
 	unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1;
 	int ret;
 	bool anon;

@@ -5516,18 +5515,13 @@ static int mem_cgroup_move_account(struct page *page,
 	from_vec = mem_cgroup_lruvec(pgdat, from);
 	to_vec = mem_cgroup_lruvec(pgdat, to);
 
-	spin_lock_irqsave(&from->move_lock, flags);
+	lock_page_memcg(page);
 
 	if (!anon && page_mapped(page)) {
 		__mod_lruvec_state(from_vec, NR_FILE_MAPPED, -nr_pages);
 		__mod_lruvec_state(to_vec, NR_FILE_MAPPED, nr_pages);
 	}
 
-	/*
-	 * move_lock grabbed above and caller set from->moving_account, so
-	 * mod_memcg_page_state will serialize updates to PageDirty.
-	 * So mapping should be stable for dirty pages.
-	 */
 	if (!anon && PageDirty(page)) {
 		struct address_space *mapping = page_mapping(page);
 

@@ -5543,15 +5537,23 @@ static int mem_cgroup_move_account(struct page *page,
 	}
 
 	/*
+	 * All state has been migrated, let's switch to the new memcg.
+	 *
 	 * It is safe to change page->mem_cgroup here because the page
-	 * is referenced, charged, and isolated - we can't race with
-	 * uncharging, charging, migration, or LRU putback.
+	 * is referenced, charged, isolated, and locked: we can't race
+	 * with (un)charging, migration, LRU putback, or anything else
+	 * that would rely on a stable page->mem_cgroup.
+	 *
+	 * Note that lock_page_memcg is a memcg lock, not a page lock,
+	 * to save space. As soon as we switch page->mem_cgroup to a
+	 * new memcg that isn't locked, the above state can change
+	 * concurrently again. Make sure we're truly done with it.
 	 */
+	smp_mb();
 
-	/* caller should have done css_get */
-	page->mem_cgroup = to;
+	page->mem_cgroup = to; 	/* caller should have done css_get */
 
-	spin_unlock_irqrestore(&from->move_lock, flags);
+	__unlock_page_memcg(from);
 
 	ret = 0;
 

2.25.1

From: Madhuparna Bhowmik <[email protected]>

[ Upstream commit e1c3cdb26ab881b77486dc50370356a349077c74 ]

Fields of md(mport_dev) are set after cdev_device_add(). However, the file operation callbacks can be called after cdev_device_add() and therefore accesses to fields of md in the callbacks can race with the rest of the mport_cdev_add() function.

One such example is INIT_LIST_HEAD(&md->portwrites) in mport_cdev_add(), the list is initialised after cdev_device_add(). This can race with list_add_tail(&pw_filter->md_node,&md->portwrites) in rio_mport_add_pw_filter() which is called by unlocked_ioctl.

To avoid such data races use cdev_device_add() after initializing md.

Found by Linux Driver Verification project (linuxtesting.org).

---
 drivers/rapidio/devices/rio_mport_cdev.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

index 10af330153b5e..0b85a80ae7ef6 100644
@@ -2384,13 +2384,6 @@ static struct mport_dev *mport_cdev_add(struct rio_mport *mport)
 	cdev_init(&md->cdev, &mport_fops);
 	md->cdev.owner = THIS_MODULE;
 
-	ret = cdev_device_add(&md->cdev, &md->dev);
-	if (ret) {
-		rmcd_error("Failed to register mport %d (err=%d)",
-		       mport->id, ret);
-		goto err_cdev;
-	}
-
 	INIT_LIST_HEAD(&md->doorbells);
 	spin_lock_init(&md->db_lock);
 	INIT_LIST_HEAD(&md->portwrites);

@@ -2410,6 +2403,13 @@ static struct mport_dev *mport_cdev_add(struct rio_mport *mport)
 #else
 	md->properties.transfer_mode |= RIO_TRANSFER_MODE_TRANSFER;
 #endif
+
+	ret = cdev_device_add(&md->cdev, &md->dev);
+	if (ret) {
+		rmcd_error("Failed to register mport %d (err=%d)",
+		       mport->id, ret);
+		goto err_cdev;
+	}
 	ret = rio_query_mport(mport, &attr);
 	if (!ret) {
 		md->properties.flags = attr.flags;

2.25.1

From: Boris Brezillon <[email protected]>

[ Upstream commit eb13fa0227417e84aecc3bd9c029d376e33474d3 ]

Looks like some drivers define MTD names with a colon in it, thus making mtdpart= parsing impossible. Let's fix the parser to gracefully handle that case: the last ':' in a partition definition sequence is considered instead of the first one.

---
 drivers/mtd/parsers/cmdlinepart.c | 23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)

index c86f2db8c882d..0625b25620ca7 100644
@@ -218,12 +218,29 @@ static int mtdpart_setup_real(char *s)
 		struct cmdline_mtd_partition *this_mtd;
 		struct mtd_partition *parts;
 		int mtd_id_len, num_parts;
-		char *p, *mtd_id;
+		char *p, *mtd_id, *semicol;
+
+		/*
+		 * Replace the first ';' by a NULL char so strrchr can work
+		 * properly.
+		 */
+		semicol = strchr(s, ';');
+		if (semicol)
+			*semicol = '\0';
 
 		mtd_id = s;
 
-		/* fetch <mtd-id> */
-		p = strchr(s, ':');
+		/*
+		 * fetch <mtd-id>. We use strrchr to ignore all ':' that could
+		 * be present in the MTD name, only the last one is interpreted
+		 * as an <mtd-id>/<part-definition> separator.
+		 */
+		p = strrchr(s, ':');
+
+		/* Restore the ';' now. */
+		if (semicol)
+			*semicol = ';';
+
 		if (!p) {
 			pr_err("no mtd-id\n");
 			return -EINVAL;

2.25.1

From: Thomas Gleixner <[email protected]>

[ Upstream commit a7ef9ba986b5fae9d80f8a7b31db0423687efe4e ]

Prevent the compiler from uninlining and creating traceable/probable functions as this is invoked _after_ context tracking switched to CONTEXT_USER and rcu idle.

---
 arch/x86/include/asm/nospec-branch.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index 5c24a7b351665..b222a35959467 100644
@@ -320,7 +320,7 @@ DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
  * combination with microcode which triggers a CPU buffer flush when the
  * instruction is executed.
  */
-static inline void mds_clear_cpu_buffers(void)
+static __always_inline void mds_clear_cpu_buffers(void)
 {
 	static const u16 ds = __KERNEL_DS;
 

@@ -341,7 +341,7 @@ static inline void mds_clear_cpu_buffers(void)
  *
  * Clear CPU buffers if the corresponding static key is enabled
  */
-static inline void mds_user_clear_cpu_buffers(void)
+static __always_inline void mds_user_clear_cpu_buffers(void)
 {
 	if (static_branch_likely(&mds_user_clear))
 		mds_clear_cpu_buffers();

2.25.1

From: Chuck Lever <[email protected]>

[ Upstream commit 5be5945864ea143fda628e8179c8474457af1f43 ]

When sunrpc trace points are not enabled, the recorded task ID information alone is not helpful.

---
 fs/nfs/nfstrace.h | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

index 361cc10d6f95d..c8081d2b4166a 100644
@@ -1147,7 +1147,12 @@ TRACE_EVENT(nfs_xdr_status,
 			__field(unsigned int, task_id)
 			__field(unsigned int, client_id)
 			__field(u32, xid)
+			__field(int, version)
 			__field(unsigned long, error)
+			__string(program,
+				 xdr->rqst->rq_task->tk_client->cl_program->name)
+			__string(procedure,
+				 xdr->rqst->rq_task->tk_msg.rpc_proc->p_name)
 		),
 
 		TP_fast_assign(

@@ -1157,13 +1162,19 @@ TRACE_EVENT(nfs_xdr_status,
 			__entry->task_id = task->tk_pid;
 			__entry->client_id = task->tk_client->cl_clid;
 			__entry->xid = be32_to_cpu(rqstp->rq_xid);
+			__entry->version = task->tk_client->cl_vers;
 			__entry->error = error;
+			__assign_str(program,
+				     task->tk_client->cl_program->name)
+			__assign_str(procedure, task->tk_msg.rpc_proc->p_name)
 		),
 
 		TP_printk(
-			"task:%u@%d xid=0x%08x error=%ld (%s)",
+			"task:%u@%d xid=0x%08x %sv%d %s error=%ld (%s)",
 			__entry->task_id, __entry->client_id, __entry->xid,
-			-__entry->error, nfs_show_status(__entry->error)
+			__get_str(program), __entry->version,
+			__get_str(procedure), -__entry->error,
+			nfs_show_status(__entry->error)
 		)
 );
 

2.25.1

From: Alex Williamson <[email protected]>

[ Upstream commit 5c5866c593bbd444d0339ede6a8fb5f14ff66d72 ]

The next use of the device will generate an underflow from the stale reference.

---
 drivers/vfio/pci/vfio_pci.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

index 12f7691e8b6ca..b669be5a20066 100644
@@ -474,10 +474,14 @@ static void vfio_pci_release(void *device_data)
 	if (!(--vdev->refcnt)) {
 		vfio_spapr_pci_eeh_release(vdev->pdev);
 		vfio_pci_disable(vdev);
-		if (vdev->err_trigger)
+		if (vdev->err_trigger) {
 			eventfd_ctx_put(vdev->err_trigger);
-		if (vdev->req_trigger)
+			vdev->err_trigger = NULL;
+		}
+		if (vdev->req_trigger) {
 			eventfd_ctx_put(vdev->req_trigger);
+			vdev->req_trigger = NULL;
+		}
 	}
 
 	mutex_unlock(&vdev->reflck->lock);

2.25.1

From: Zhang Xiaoxu <[email protected]>

[ Upstream commit 95a3d8f3af9b0d63b43f221b630beaab9739d13a ]

When xfstests generic/451, there is an BUG at mm/memcontrol.c:
page:ffffea000560f2c0 refcount:2 mapcount:0 mapping:000000008544e0ea

       index:0xf
  mapping->aops:cifs_addr_ops dentry name:"tst-aio-dio-cycle-write.451"
  flags: 0x2fffff80000001(locked)
  raw: 002fffff80000001 ffffc90002023c50 ffffea0005280088 ffff88815cda0210
  raw: 000000000000000f 0000000000000000 00000002ffffffff ffff88817287d000
  page dumped because: VM_BUG_ON_PAGE(page->mem_cgroup)
  page->mem_cgroup:ffff88817287d000
  ------------[ cut here ]------------
  kernel BUG at mm/memcontrol.c:2659!
  invalid opcode: 0000 [#1] SMP
  CPU: 2 PID: 2038 Comm: xfs_io Not tainted 5.8.0-rc1 #44
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ?-20190727_
    073836-buildvm-ppc64le-16.ppc.4
  RIP: 0010:commit_charge+0x35/0x50
  Code: 0d 48 83 05 54 b2 02 05 01 48 89 77 38 c3 48 c7
        c6 78 4a ea ba 48 83 05 38 b2 02 05 01 e8 63 0d9
  RSP: 0018:ffffc90002023a50 EFLAGS: 00010202
  RAX: 0000000000000000 RBX: ffff88817287d000 RCX: 0000000000000000
  RDX: 0000000000000000 RSI: ffff88817ac97ea0 RDI: ffff88817ac97ea0
  RBP: ffffea000560f2c0 R08: 0000000000000203 R09: 0000000000000005
  R10: 0000000000000030 R11: ffffc900020237a8 R12: 0000000000000000
  R13: 0000000000000001 R14: 0000000000000001 R15: ffff88815a1272c0
  FS:  00007f5071ab0800(0000) GS:ffff88817ac80000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 000055efcd5ca000 CR3: 000000015d312000 CR4: 00000000000006e0
  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
  Call Trace:
   mem_cgroup_charge+0x166/0x4f0
   __add_to_page_cache_locked+0x4a9/0x710
   add_to_page_cache_locked+0x15/0x20
   cifs_readpages+0x217/0x1270
   read_pages+0x29a/0x670
   page_cache_readahead_unbounded+0x24f/0x390
   __do_page_cache_readahead+0x3f/0x60
   ondemand_readahead+0x1f1/0x470
   page_cache_async_readahead+0x14c/0x170
   generic_file_buffered_read+0x5df/0x1100
   generic_file_read_iter+0x10c/0x1d0
   cifs_strict_readv+0x139/0x170
   new_sync_read+0x164/0x250
   __vfs_read+0x39/0x60
   vfs_read+0xb5/0x1e0
   ksys_pread64+0x85/0xf0
   __x64_sys_pread64+0x22/0x30
   do_syscall_64+0x69/0x150
   entry_SYSCALL_64_after_hwframe+0x44/0xa9
  RIP: 0033:0x7f5071fcb1af
  Code: Bad RIP value.
  RSP: 002b:00007ffde2cdb8e0 EFLAGS: 00000293 ORIG_RAX: 0000000000000011
  RAX: ffffffffffffffda RBX: 00007ffde2cdb990 RCX: 00007f5071fcb1af
  RDX: 0000000000001000 RSI: 000055efcd5ca000 RDI: 0000000000000003
  RBP: 0000000000000003 R08: 0000000000000000 R09: 0000000000000000
  R10: 0000000000001000 R11: 0000000000000293 R12: 0000000000000001
  R13: 000000000009f000 R14: 0000000000000000 R15: 0000000000001000
  Modules linked in:
  ---[ end trace 725fa14a3e1af65c ]---

Since commit 3fea5a499d57 ("mm: memcontrol: convert page cache to a new mem_cgroup_charge() API") not cancel the page charge, the pages maybe double add to pagecache:
thread1 | thread2
cifs_readpages
readpages_get_pages
add_to_page_cache_locked(head,index=n)=0

                              | readpages_get_pages
                              | add_to_page_cache_locked(head,index=n+1)=0

add_to_page_cache_locked(head, index=n+1)=-EEXIST then, will next loop with list head page's index=n+1 and the page->mapping not NULL
readpages_get_pages add_to_page_cache_locked(head, index=n+1)
commit_charge
VM_BUG_ON_PAGE

So, we should not do the next loop when any page add to page cache failed.

---
 fs/cifs/file.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

index 14ae341755d47..31d578739341b 100644
@@ -4269,7 +4269,8 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
 			break;
 
 		__SetPageLocked(page);
-		if (add_to_page_cache_locked(page, mapping, page->index, gfp)) {
+		rc = add_to_page_cache_locked(page, mapping, page->index, gfp);
+		if (rc) {
 			__ClearPageLocked(page);
 			break;
 		}

@@ -4285,6 +4286,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 	struct list_head *page_list, unsigned num_pages)
 {
 	int rc;
+	int err = 0;
 	struct list_head tmplist;
 	struct cifsFileInfo *open_file = file->private_data;
 	struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);

@@ -4329,7 +4331,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 	 * the order of declining indexes. When we put the pages in
 	 * the rdata->pages, then we want them in increasing order.
 	 */
-	while (!list_empty(page_list)) {
+	while (!list_empty(page_list) && !err) {
 		unsigned int i, nr_pages, bytes, rsize;
 		loff_t offset;
 		struct page *page, *tpage;

@@ -4362,9 +4364,10 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 			return 0;
 		}
 
-		rc = readpages_get_pages(mapping, page_list, rsize, &tmplist,
+		nr_pages = 0;
+		err = readpages_get_pages(mapping, page_list, rsize, &tmplist,
 					 &nr_pages, &offset, &bytes);
-		if (rc) {
+		if (!nr_pages) {
 			add_credits_and_wake_if(server, credits, 0);
 			break;
 		}

2.25.1

From: Sagi Grimberg <[email protected]>

[ Upstream commit 3b4b19721ec652ad2c4fe51dfbe5124212b5f581 ]

Revert fab7772bfbcf ("nvme-multipath: revalidate nvme_ns_head gendisk in nvme_validate_ns")

When adding a new namespace to the head disk (via nvme_mpath_set_live) we will see partition scan which triggers I/O on the mpath device node. This process will usually be triggered from the scan_work which holds the scan_lock. If I/O blocks (if we got ana change currently have only available paths but none are accessible) this can deadlock on the head disk bd_mutex as both partition scan I/O takes it, and head disk revalidation takes it to check for resize (also triggered from scan_work on a different path). See trace [1].

The mpath disk revalidation was originally added to detect online disk size change, but this is no longer needed since commit cb224c3af4df ("nvme: Convert to use set_capacity_revalidate_and_notify") which already updates resize info without unnecessarily revalidating the disk (the mpath disk doesn't even implement .revalidate_disk fop).

[1]:
--

kernel: INFO: task kworker/u65:9:494 blocked for more than 241 seconds.
kernel:       Tainted: G           OE     5.3.5-050305-generic #201910071830
kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
kernel: kworker/u65:9   D    0   494      2 0x80004000
kernel: Workqueue: nvme-wq nvme_scan_work [nvme_core]
kernel: Call Trace:
kernel:  __schedule+0x2b9/0x6c0
kernel:  schedule+0x42/0xb0
kernel:  schedule_preempt_disabled+0xe/0x10
kernel:  __mutex_lock.isra.0+0x182/0x4f0
kernel:  __mutex_lock_slowpath+0x13/0x20
kernel:  mutex_lock+0x2e/0x40
kernel:  revalidate_disk+0x63/0xa0
kernel:  __nvme_revalidate_disk+0xfe/0x110 [nvme_core]
kernel:  nvme_revalidate_disk+0xa4/0x160 [nvme_core]
kernel:  ? evict+0x14c/0x1b0
kernel:  revalidate_disk+0x2b/0xa0
kernel:  nvme_validate_ns+0x49/0x940 [nvme_core]
kernel:  ? blk_mq_free_request+0xd2/0x100
kernel:  ? __nvme_submit_sync_cmd+0xbe/0x1e0 [nvme_core]
kernel:  nvme_scan_work+0x24f/0x380 [nvme_core]
kernel:  process_one_work+0x1db/0x380
kernel:  worker_thread+0x249/0x400
kernel:  kthread+0x104/0x140
kernel:  ? process_one_work+0x380/0x380
kernel:  ? kthread_park+0x80/0x80
kernel:  ret_from_fork+0x1f/0x40
...
kernel: INFO: task kworker/u65:1:2630 blocked for more than 241 seconds.
kernel:       Tainted: G           OE     5.3.5-050305-generic #201910071830
kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
kernel: kworker/u65:1   D    0  2630      2 0x80004000
kernel: Workqueue: nvme-wq nvme_scan_work [nvme_core]
kernel: Call Trace:
kernel:  __schedule+0x2b9/0x6c0
kernel:  schedule+0x42/0xb0
kernel:  io_schedule+0x16/0x40
kernel:  do_read_cache_page+0x438/0x830
kernel:  ? __switch_to_asm+0x34/0x70
kernel:  ? file_fdatawait_range+0x30/0x30
kernel:  read_cache_page+0x12/0x20
kernel:  read_dev_sector+0x27/0xc0
kernel:  read_lba+0xc1/0x220
kernel:  ? kmem_cache_alloc_trace+0x19c/0x230
kernel:  efi_partition+0x1e6/0x708
kernel:  ? vsnprintf+0x39e/0x4e0
kernel:  ? snprintf+0x49/0x60
kernel:  check_partition+0x154/0x244
kernel:  rescan_partitions+0xae/0x280
kernel:  __blkdev_get+0x40f/0x560
kernel:  blkdev_get+0x3d/0x140
kernel:  __device_add_disk+0x388/0x480
kernel:  device_add_disk+0x13/0x20
kernel:  nvme_mpath_set_live+0x119/0x140 [nvme_core]
kernel:  nvme_update_ns_ana_state+0x5c/0x60 [nvme_core]
kernel:  nvme_set_ns_ana_state+0x1e/0x30 [nvme_core]
kernel:  nvme_parse_ana_log+0xa1/0x180 [nvme_core]
kernel:  ? nvme_update_ns_ana_state+0x60/0x60 [nvme_core]
kernel:  nvme_mpath_add_disk+0x47/0x90 [nvme_core]
kernel:  nvme_validate_ns+0x396/0x940 [nvme_core]
kernel:  ? blk_mq_free_request+0xd2/0x100
kernel:  nvme_scan_work+0x24f/0x380 [nvme_core]
kernel:  process_one_work+0x1db/0x380
kernel:  worker_thread+0x249/0x400
kernel:  kthread+0x104/0x140
kernel:  ? process_one_work+0x380/0x380
kernel:  ? kthread_park+0x80/0x80
kernel:  ret_from_fork+0x1f/0x40

--

in nvme_validate_ns")

---
 drivers/nvme/host/core.c | 1 -
 1 file changed, 1 deletion(-)

index 438a03fc4bd94..5702bc59c569c 100644
@@ -1864,7 +1864,6 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 	if (ns->head->disk) {
 		nvme_update_disk_info(ns->head->disk, ns, id);
 		blk_queue_stack_limits(ns->head->disk->queue, ns->queue);
-		revalidate_disk(ns->head->disk);
 	}
 #endif
 }

2.25.1

From: Markus Theil <[email protected]>

[ Upstream commit 5af7fef39d7952c0f5551afa7b821ee7b6c9dd3d ]

When using 802.1X over mesh networks, at first an ordinary mesh peering is established, then the 802.1X EAPOL dialog happens, afterwards an authenticated mesh peering exchange (AMPE) happens, finally the peering is complete and we can set the STA authorized flag.

As 802.1X is an intermediate step here and key material is not yet exchanged for stations we have to skip mesh path lookup for these EAPOL frames. Otherwise the already configure mesh group encryption key would be used to send a mesh path request which no one can decipher, because we didn't already establish key material on both peers, like with SAE and directly using AMPE.

[remove pointless braces, remove unnecessary local variable,
the list can only process one such frame (or its fragments)]

---
 net/mac80211/tx.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

index 30201aeb426cf..f029e75ec815a 100644
@@ -3913,6 +3913,9 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb,
 		skb->prev = NULL;
 		skb->next = NULL;
 
+		if (skb->protocol == sdata->control_port_protocol)
+			ctrl_flags |= IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP;
+
 		skb = ieee80211_build_hdr(sdata, skb, info_flags,
 					  sta, ctrl_flags);
 		if (IS_ERR(skb))

@@ -5096,7 +5099,8 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev,
 		return -EINVAL;
 
 	if (proto == sdata->control_port_protocol)
-		ctrl_flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO;
+		ctrl_flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO |
+			      IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP;
 
 	if (unencrypted)
 		flags = IEEE80211_TX_INTFL_DONT_ENCRYPT;

2.25.1

From: Javed Hasan <[email protected]>

[ Upstream commit 71f2bf85e90d938d4a9ef9dd9bfa8d9b0b6a03f7 ]

Handling of extra kref which is done by lookup table in case rdata is already present in list.

This issue was leading to memory leak. Trace from KMEMLEAK tool:

unreferenced object 0xffff8888259e8780 (size 512):

    comm "kworker/2:1", pid 182614, jiffies 4433237386 (age 113021.971s)
    hex dump (first 32 bytes):
    58 0a ec cf 83 88 ff ff 00 00 00 00 00 00 00 00
    01 00 00 00 08 00 00 00 13 7d f0 1e 0e 00 00 10
  backtrace:
	[<000000006b25760f>] fc_rport_recv_req+0x3c6/0x18f0 [libfc]
	[<00000000f208d994>] fc_lport_recv_els_req+0x120/0x8a0 [libfc]
	[<00000000a9c437b8>] fc_lport_recv+0xb9/0x130 [libfc]
	[<00000000ad5be37b>] qedf_ll2_process_skb+0x73d/0xad0 [qedf]
	[<00000000e0eb6893>] process_one_work+0x382/0x6c0
	[<000000002dfd9e21>] worker_thread+0x57/0x5c0
	[<00000000b648204f>] kthread+0x1a0/0x1c0
	[<0000000072f5ab20>] ret_from_fork+0x35/0x40
	[<000000001d5c05d8>] 0xffffffffffffffff

Below is the log sequence which leads to memory leak. Here we get the nested "Received PLOGI request" for same port and this request leads to call the fc_rport_create() twice for the same rport.

kernel: host1: rport fffce5: Received PLOGI request
kernel: host1: rport fffce5: Received PLOGI in INIT state
kernel: host1: rport fffce5: Port is Ready
kernel: host1: rport fffce5: Received PRLI request while in state Ready
kernel: host1: rport fffce5: PRLI rspp type 8 active 1 passive 0
kernel: host1: rport fffce5: Received LOGO request while in state Ready
kernel: host1: rport fffce5: Delete port
kernel: host1: rport fffce5: Received PLOGI request
kernel: host1: rport fffce5: Received PLOGI in state Delete - send busy

---
 drivers/scsi/libfc/fc_rport.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index 6bb8917b99a19..aabf51df3c02f 100644
@@ -133,8 +133,10 @@ struct fc_rport_priv *fc_rport_create(struct fc_lport *lport, u32 port_id)
 	lockdep_assert_held(&lport->disc.disc_mutex);
 
 	rdata = fc_rport_lookup(lport, port_id);
-	if (rdata)
+	if (rdata) {
+		kref_put(&rdata->kref, fc_rport_destroy);
 		return rdata;
+	}
 
 	if (lport->rport_priv_size > 0)
 		rport_priv_size = lport->rport_priv_size;

2.25.1

From: Javed Hasan <[email protected]>

[ Upstream commit 823a65409c8990f64c5693af98ce0e7819975cba ]

When an rport event (RPORT_EV_READY) is updated without work being queued, avoid taking an additional reference.

This issue was leading to memory leak. Trace from KMEMLEAK tool:

unreferenced object 0xffff8888259e8780 (size 512):
comm "kworker/2:1", jiffies 4433237386 (age 113021.971s)

    hex dump (first 32 bytes):
	58 0a ec cf 83 88 ff ff 00 00 00 00 00 00 00 00
	01 00 00 00 08 00 00 00 13 7d f0 1e 0e 00 00 10
  backtrace:
  [<000000006b25760f>] fc_rport_recv_req+0x3c6/0x18f0 [libfc]
  [<00000000f208d994>] fc_lport_recv_els_req+0x120/0x8a0 [libfc]
  [<00000000a9c437b8>] fc_lport_recv+0xb9/0x130 [libfc]
  [<00000000a9c437b8>] fc_lport_recv+0xb9/0x130 [libfc]
  [<00000000ad5be37b>] qedf_ll2_process_skb+0x73d/0xad0 [qedf]
  [<00000000e0eb6893>] process_one_work+0x382/0x6c0
  [<000000002dfd9e21>] worker_thread+0x57/0x5c0
  [<00000000b648204f>] kthread+0x1a0/0x1c0
  [<0000000072f5ab20>] ret_from_fork+0x35/0x40
  [<000000001d5c05d8>] 0xffffffffffffffff

Below is the log sequence which leads to memory leak. Here we get the RPORT_EV_READY and RPORT_EV_STOP back to back, which lead to overwrite the event RPORT_EV_READY by event RPORT_EV_STOP. Because of this, kref_count gets incremented by 1.

kernel: host0: rport fffce5: Received PLOGI request
kernel: host0: rport fffce5: Received PLOGI in INIT state
kernel: host0: rport fffce5: Port is Ready
kernel: host0: rport fffce5: Received PRLI request while in state Ready
kernel: host0: rport fffce5: PRLI rspp type 8 active 1 passive 0
kernel: host0: rport fffce5: Received LOGO request while in state Ready
kernel: host0: rport fffce5: Delete port
kernel: host0: rport fffce5: Received PLOGI request
kernel: host0: rport fffce5: Received PLOGI in state Delete - send busy
kernel: host0: rport fffce5: work event 3
kernel: host0: rport fffce5: lld callback ev 3
kernel: host0: rport fffce5: work delete

---
 drivers/scsi/libfc/fc_rport.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

index aabf51df3c02f..64500417c22ea 100644
@@ -483,10 +483,11 @@ static void fc_rport_enter_delete(struct fc_rport_priv *rdata,
 
 	fc_rport_state_enter(rdata, RPORT_ST_DELETE);
 
-	kref_get(&rdata->kref);
-	if (rdata->event == RPORT_EV_NONE &&
-	    !queue_work(rport_event_queue, &rdata->event_work))
-		kref_put(&rdata->kref, fc_rport_destroy);
+	if (rdata->event == RPORT_EV_NONE) {
+		kref_get(&rdata->kref);
+		if (!queue_work(rport_event_queue, &rdata->event_work))
+			kref_put(&rdata->kref, fc_rport_destroy);
+	}
 
 	rdata->event = event;
 }

2.25.1

From: Andy Lutomirski <[email protected]>

[ Upstream commit a61fa2799ef9bf6c4f54cf7295036577cececc72 ]

Clear the weird flags before logging to improve strace output -- logging results while, say, TF is set does no one any favors.

---
 tools/testing/selftests/x86/syscall_nt.c | 1 +
 1 file changed, 1 insertion(+)

index 02309a1950413..a765f62ee7668 100644
@@ -59,6 +59,7 @@ static void do_it(unsigned long extraflags)
 	set_eflags(get_eflags() | extraflags);
 	syscall(SYS_getpid);
 	flags = get_eflags();
+	set_eflags(X86_EFLAGS_IF | X86_EFLAGS_FIXED);
 	if ((flags & extraflags) == extraflags) {
 		printf("[OK]\tThe syscall worked and flags are still set\n");
 	} else {

2.25.1

From: Zeng Tao <[email protected]>

[ Upstream commit b872d0640840018669032b20b6375a478ed1f923 ]

The vfio_pci_release call will free and clear the error and request eventfd ctx while these ctx could be in use at the same time in the function like vfio_pci_request, and it's expected to protect them under the vdev->igate mutex, which is missing in vfio_pci_release.

This issue is introduced since commit 1518ac272e78 ("vfio/pci: fix memory leaks of eventfd ctx"),and since commit 5c5866c593bb ("vfio/pci: Clear error and request eventfd ctx after releasing"), it's very easily to trigger the kernel panic like this:

[ 9513.904346] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008
[ 9513.913091] Mem abort info:
[ 9513.915871]   ESR = 0x96000006
[ 9513.918912]   EC = 0x25: DABT (current EL), IL = 32 bits
[ 9513.924198]   SET = 0, FnV = 0
[ 9513.927238]   EA = 0, S1PTW = 0
[ 9513.930364] Data abort info:
[ 9513.933231]   ISV = 0, ISS = 0x00000006
[ 9513.937048]   CM = 0, WnR = 0
[ 9513.940003] user pgtable: 4k pages, 48-bit VAs, pgdp=0000007ec7d12000
[ 9513.946414] [0000000000000008] pgd=0000007ec7d13003, p4d=0000007ec7d13003, pud=0000007ec728c003, pmd=0000000000000000
[ 9513.956975] Internal error: Oops: 96000006 [#1] PREEMPT SMP
[ 9513.962521] Modules linked in: vfio_pci vfio_virqfd vfio_iommu_type1 vfio hclge hns3 hnae3 [last unloaded: vfio_pci]
[ 9513.972998] CPU: 4 PID: 1327 Comm: bash Tainted: G        W         5.8.0-rc4+ #3
[ 9513.980443] Hardware name: Huawei TaiShan 2280 V2/BC82AMDC, BIOS 2280-V2 CS V3.B270.01 05/08/2020
[ 9513.989274] pstate: 80400089 (Nzcv daIf +PAN -UAO BTYPE=--)
[ 9513.994827] pc : _raw_spin_lock_irqsave+0x48/0x88
[ 9513.999515] lr : eventfd_signal+0x6c/0x1b0
[ 9514.003591] sp : ffff800038a0b960
[ 9514.006889] x29: ffff800038a0b960 x28: ffff007ef7f4da10
[ 9514.012175] x27: ffff207eefbbfc80 x26: ffffbb7903457000
[ 9514.017462] x25: ffffbb7912191000 x24: ffff007ef7f4d400
[ 9514.022747] x23: ffff20be6e0e4c00 x22: 0000000000000008
[ 9514.028033] x21: 0000000000000000 x20: 0000000000000000
[ 9514.033321] x19: 0000000000000008 x18: 0000000000000000
[ 9514.038606] x17: 0000000000000000 x16: ffffbb7910029328
[ 9514.043893] x15: 0000000000000000 x14: 0000000000000001
[ 9514.049179] x13: 0000000000000000 x12: 0000000000000002
[ 9514.054466] x11: 0000000000000000 x10: 0000000000000a00
[ 9514.059752] x9 : ffff800038a0b840 x8 : ffff007ef7f4de60
[ 9514.065038] x7 : ffff007fffc96690 x6 : fffffe01faffb748
[ 9514.070324] x5 : 0000000000000000 x4 : 0000000000000000
[ 9514.075609] x3 : 0000000000000000 x2 : 0000000000000001
[ 9514.080895] x1 : ffff007ef7f4d400 x0 : 0000000000000000
[ 9514.086181] Call trace:
[ 9514.088618]  _raw_spin_lock_irqsave+0x48/0x88
[ 9514.092954]  eventfd_signal+0x6c/0x1b0
[ 9514.096691]  vfio_pci_request+0x84/0xd0 [vfio_pci]
[ 9514.101464]  vfio_del_group_dev+0x150/0x290 [vfio]
[ 9514.106234]  vfio_pci_remove+0x30/0x128 [vfio_pci]
[ 9514.111007]  pci_device_remove+0x48/0x108
[ 9514.115001]  device_release_driver_internal+0x100/0x1b8
[ 9514.120200]  device_release_driver+0x28/0x38
[ 9514.124452]  pci_stop_bus_device+0x68/0xa8
[ 9514.128528]  pci_stop_and_remove_bus_device+0x20/0x38
[ 9514.133557]  pci_iov_remove_virtfn+0xb4/0x128
[ 9514.137893]  sriov_disable+0x3c/0x108
[ 9514.141538]  pci_disable_sriov+0x28/0x38
[ 9514.145445]  hns3_pci_sriov_configure+0x48/0xb8 [hns3]
[ 9514.150558]  sriov_numvfs_store+0x110/0x198
[ 9514.154724]  dev_attr_store+0x44/0x60
[ 9514.158373]  sysfs_kf_write+0x5c/0x78
[ 9514.162018]  kernfs_fop_write+0x104/0x210
[ 9514.166010]  __vfs_write+0x48/0x90
[ 9514.169395]  vfs_write+0xbc/0x1c0
[ 9514.172694]  ksys_write+0x74/0x100
[ 9514.176079]  __arm64_sys_write+0x24/0x30
[ 9514.179987]  el0_svc_common.constprop.4+0x110/0x200
[ 9514.184842]  do_el0_svc+0x34/0x98
[ 9514.188144]  el0_svc+0x14/0x40
[ 9514.191185]  el0_sync_handler+0xb0/0x2d0
[ 9514.195088]  el0_sync+0x140/0x180
[ 9514.198389] Code: b9001020 d2800000 52800022 f9800271 (885ffe61)
[ 9514.204455] ---[ end trace 648de00c8406465f ]---
[ 9514.212308] note: bash[1327] exited with preempt_count 1

---
 drivers/vfio/pci/vfio_pci.c | 5 +++++
 1 file changed, 5 insertions(+)

index b669be5a20066..a72fd5309b09f 100644
@@ -474,14 +474,19 @@ static void vfio_pci_release(void *device_data)
 	if (!(--vdev->refcnt)) {
 		vfio_spapr_pci_eeh_release(vdev->pdev);
 		vfio_pci_disable(vdev);
+		mutex_lock(&vdev->igate);
 		if (vdev->err_trigger) {
 			eventfd_ctx_put(vdev->err_trigger);
 			vdev->err_trigger = NULL;
 		}
+		mutex_unlock(&vdev->igate);
+
+		mutex_lock(&vdev->igate);
 		if (vdev->req_trigger) {
 			eventfd_ctx_put(vdev->req_trigger);
 			vdev->req_trigger = NULL;
 		}
+		mutex_unlock(&vdev->igate);
 	}
 
 	mutex_unlock(&vdev->reflck->lock);

2.25.1

From: Qu Wenruo <[email protected]>

[ Upstream commit fa91e4aa1716004ea8096d5185ec0451e206aea0 ]

[BUG]
When running tests like generic/013 on test device with btrfs quota enabled, it can normally lead to data leak, detected at unmount time:

BTRFS warning (device dm-3): qgroup 0/5 has unreleased space, type 0 rsv 4096

  ------------[ cut here ]------------
  WARNING: CPU: 11 PID: 16386 at fs/btrfs/disk-io.c:4142 close_ctree+0x1dc/0x323 [btrfs]
  RIP: 0010:close_ctree+0x1dc/0x323 [btrfs]
  Call Trace:
   btrfs_put_super+0x15/0x17 [btrfs]
   generic_shutdown_super+0x72/0x110
   kill_anon_super+0x18/0x30
   btrfs_kill_super+0x17/0x30 [btrfs]
   deactivate_locked_super+0x3b/0xa0
   deactivate_super+0x40/0x50
   cleanup_mnt+0x135/0x190
   __cleanup_mnt+0x12/0x20
   task_work_run+0x64/0xb0
   __prepare_exit_to_usermode+0x1bc/0x1c0
   __syscall_return_slowpath+0x47/0x230
   do_syscall_64+0x64/0xb0
   entry_SYSCALL_64_after_hwframe+0x44/0xa9
  ---[ end trace caf08beafeca2392 ]---
  BTRFS error (device dm-3): qgroup reserved space leaked

[CAUSE]
In the offending case, the offending operations are:
2/6: writev f2X[269 1 0 0 0 0] [1006997,67,288] 0 2/7: truncate f2X[269 1 0 0 48 1026293] 18388 0

The following sequence of events could happen after the writev():

	CPU1 (writeback)		|		CPU2 (truncate)
-----------------------------------------------------------------
btrfs_writepages()			|
|- extent_write_cache_pages()		|
   |- Got page for 1003520		|
   |  1003520 is Dirty, no writeback	|
   |  So (!clear_page_dirty_for_io())   |
   |  gets called for it		|
   |- Now page 1003520 is Clean.	|
   |					| btrfs_setattr()
   |					| |- btrfs_setsize()
   |					|    |- truncate_setsize()
   |					|       New i_size is 18388
   |- __extent_writepage()		|
   |  |- page_offset() > i_size		|
      |- btrfs_invalidatepage()		|
	 |- Page is clean, so no qgroup |

callback executed

This means, the qgroup reserved data space is not properly released in btrfs_invalidatepage() as the page is Clean.

[FIX]
Instead of checking the dirty bit of a page, call btrfs_qgroup_free_data() unconditionally in btrfs_invalidatepage().

As qgroup rsv are completely bound to the QGROUP_RESERVED bit of io_tree, not bound to page status, thus we won't cause double freeing anyway.

---
 fs/btrfs/inode.c | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)

index e9787b7b943a2..182e93a5b11d5 100644
@@ -9044,20 +9044,17 @@ again:
 	/*
 	 * Qgroup reserved space handler
 	 * Page here will be either
-	 * 1) Already written to disk
-	 *    In this case, its reserved space is released from data rsv map
-	 *    and will be freed by delayed_ref handler finally.
-	 *    So even we call qgroup_free_data(), it won't decrease reserved
-	 *    space.
-	 * 2) Not written to disk
-	 *    This means the reserved space should be freed here. However,
-	 *    if a truncate invalidates the page (by clearing PageDirty)
-	 *    and the page is accounted for while allocating extent
-	 *    in btrfs_check_data_free_space() we let delayed_ref to
-	 *    free the entire extent.
+	 * 1) Already written to disk or ordered extent already submitted
+	 *    Then its QGROUP_RESERVED bit in io_tree is already cleaned.
+	 *    Qgroup will be handled by its qgroup_record then.
+	 *    btrfs_qgroup_free_data() call will do nothing here.
+	 *
+	 * 2) Not written to disk yet
+	 *    Then btrfs_qgroup_free_data() call will clear the QGROUP_RESERVED
+	 *    bit of its io_tree, and free the qgroup reserved data space.
+	 *    Since the IO will never happen for this page.
 	 */
-	if (PageDirty(page))
-		btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE);
+	btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE);
 	if (!inode_evicting) {
 		clear_extent_bit(tree, page_start, page_end, EXTENT_LOCKED |
 				 EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |

2.25.1

From: Thomas Richter <[email protected]>

[ Upstream commit 463538a383a27337cb83ae195e432a839a52d639 ]

Commit 5aa98879efe7 ("s390/cpum_sf: prohibit callchain data collection") prohibits call graph sampling for hardware events on s390. The information recorded is out of context and does not match.

On s390 this commit now breaks test case 68 Zstd perf.data compression/decompression.

Therefore omit call graph sampling on s390 in this test.

Output before:
[root@t35lp46 perf]# ./perf test -Fv 68
68: Zstd perf.data compression/decompression :
--- start ---
Collecting compressed record file:
Error:
cycles: PMU Hardware doesn't support sampling/overflow-interrupts.
Try 'perf stat'
---- end ----
Zstd perf.data compression/decompression: FAILED! [root@t35lp46 perf]#

Output after:
[root@t35lp46 perf]# ./perf test -Fv 68
68: Zstd perf.data compression/decompression :
--- start ---
Collecting compressed record file:
500+0 records in
500+0 records out
256000 bytes (256 kB, 250 KiB) copied, 0.00615638 s, 41.6 MB/s [ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.004 MB /tmp/perf.data.X3M,

                        compressed (original 0.002 MB, ratio is 3.609) ]
  Checking compressed events stats:
  # compressed : Zstd, level = 1, ratio = 4
        COMPRESSED events:          1
  2ELIFREPh---- end ----
  Zstd perf.data compression/decompression: Ok
  [root@t35lp46 perf]#

---
 tools/perf/tests/shell/record+zstd_comp_decomp.sh | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

index 63a91ec473bb5..045723b3d9928 100755
@@ -12,7 +12,8 @@ skip_if_no_z_record() {
 
 collect_z_record() {
 	echo "Collecting compressed record file:"
-	$perf_tool record -o $trace_file -g -z -F 5000 -- \
+	[[ "$(uname -m)" != s390x ]] && gflag='-g'
+	$perf_tool record -o $trace_file $gflag -z -F 5000 -- \
 		dd count=500 if=/dev/urandom of=/dev/null
 }
 

2.25.1

From: Quinn Tran <[email protected]>

[ Upstream commit 983f127603fac650fa34ee69db363e4615eaf9e7 ]

Current code will send PRLI with FC-NVMe bit set for the targets which support only FCP. This may result into issue with targets which do not understand NVMe and will go into a strange state. This patch would restart the login process by going back to PLOGI state. The PLOGI state will force the target to respond to correct PRLI request.

---
 drivers/scsi/qla2xxx/qla_init.c | 28 ++++------------------------
 drivers/scsi/qla2xxx/qla_iocb.c |  6 +++++-
 2 files changed, 9 insertions(+), 25 deletions(-)

index 2f2e059f4575e..62d2ee825c97a 100644
@@ -1911,33 +1911,13 @@ qla24xx_handle_prli_done_event(struct scsi_qla_host *vha, struct event_arg *ea)
 				"%s %d %8phC post fc4 prli\n",
 				__func__, __LINE__, ea->fcport->port_name);
 			ea->fcport->fc4f_nvme = 0;
-			qla24xx_post_prli_work(vha, ea->fcport);
 			return;
 		}
 
-		/* at this point both PRLI NVME & PRLI FCP failed */
-		if (N2N_TOPO(vha->hw)) {
-			if (ea->fcport->n2n_link_reset_cnt < 3) {
-				ea->fcport->n2n_link_reset_cnt++;
-				/*
-				 * remote port is not sending Plogi. Reset
-				 * link to kick start his state machine
-				 */
-				set_bit(N2N_LINK_RESET, &vha->dpc_flags);
-			} else {
-				ql_log(ql_log_warn, vha, 0x2119,
-				    "%s %d %8phC Unable to reconnect\n",
-				    __func__, __LINE__, ea->fcport->port_name);
-			}
-		} else {
-			/*
-			 * switch connect. login failed. Take connection
-			 * down and allow relogin to retrigger
-			 */
-			ea->fcport->flags &= ~FCF_ASYNC_SENT;
-			ea->fcport->keep_nport_handle = 0;
-			qlt_schedule_sess_for_deletion(ea->fcport);
-		}
+		ea->fcport->flags &= ~FCF_ASYNC_SENT;
+		ea->fcport->keep_nport_handle = 0;
+		ea->fcport->logout_on_delete = 1;
+		qlt_schedule_sess_for_deletion(ea->fcport);
 		break;
 	}
 }

index 2e272fc858ed1..aed4ce66e6cf9 100644
@@ -2773,6 +2773,7 @@ static void qla2x00_els_dcmd2_sp_done(srb_t *sp, int res)
 			ea.sp = sp;
 			qla24xx_handle_plogi_done_event(vha, &ea);
 			break;
+
 		case CS_IOCB_ERROR:
 			switch (fw_status[1]) {
 			case LSC_SCODE_PORTID_USED:

@@ -2843,6 +2844,7 @@ static void qla2x00_els_dcmd2_sp_done(srb_t *sp, int res)
 				    fw_status[0], fw_status[1], fw_status[2]);
 
 				fcport->flags &= ~FCF_ASYNC_SENT;
+				fcport->disc_state = DSC_LOGIN_FAILED;
 				set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
 				break;
 			}

@@ -2855,6 +2857,7 @@ static void qla2x00_els_dcmd2_sp_done(srb_t *sp, int res)
 			    fw_status[0], fw_status[1], fw_status[2]);
 
 			sp->fcport->flags &= ~FCF_ASYNC_SENT;
+			sp->fcport->disc_state = DSC_LOGIN_FAILED;
 			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
 			break;
 		}

@@ -2890,11 +2893,12 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,
 		return -ENOMEM;
 	}
 
+	fcport->flags |= FCF_ASYNC_SENT;
+	fcport->disc_state = DSC_LOGIN_PEND;
 	elsio = &sp->u.iocb_cmd;
 	ql_dbg(ql_dbg_io, vha, 0x3073,
 	    "Enter: PLOGI portid=%06x\n", fcport->d_id.b24);
 
-	fcport->flags |= FCF_ASYNC_SENT;
 	sp->type = SRB_ELS_DCMD;
 	sp->name = "ELS_DCMD";
 	sp->fcport = fcport;

2.25.1

From: Hou Tao <[email protected]>

[ Upstream commit c16f39d14a7e0ec59881fbdb22ae494907534384 ]

When CONFIG_MTD_UBI_FASTMAP is enabled, fm_anchor will be assigned a free PEB during ubi_wl_init() or ubi_update_fastmap(). However if fastmap is not used or disabled on the MTD device, ubi_wl_entry related with the PEB will not be freed during detach.

So Fix it by freeing the unused fastmap anchor during detach.

---
 drivers/mtd/ubi/fastmap-wl.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

index 426820ab9afe1..b486250923c5a 100644
@@ -39,6 +39,13 @@ static struct ubi_wl_entry *find_anchor_wl_entry(struct rb_root *root)
 	return victim;
 }
 
+static inline void return_unused_peb(struct ubi_device *ubi,
+				     struct ubi_wl_entry *e)
+{
+	wl_tree_add(e, &ubi->free);
+	ubi->free_count++;
+}
+
 /**
  * return_unused_pool_pebs - returns unused PEB to the free tree.
  * @ubi: UBI device description object

@@ -52,8 +59,7 @@ static void return_unused_pool_pebs(struct ubi_device *ubi,
 
 	for (i = pool->used; i < pool->size; i++) {
 		e = ubi->lookuptbl[pool->pebs[i]];
-		wl_tree_add(e, &ubi->free);
-		ubi->free_count++;
+		return_unused_peb(ubi, e);
 	}
 }
 

@@ -361,6 +367,11 @@ static void ubi_fastmap_close(struct ubi_device *ubi)
 	return_unused_pool_pebs(ubi, &ubi->fm_pool);
 	return_unused_pool_pebs(ubi, &ubi->fm_wl_pool);
 
+	if (ubi->fm_anchor) {
+		return_unused_peb(ubi, ubi->fm_anchor);
+		ubi->fm_anchor = NULL;
+	}
+
 	if (ubi->fm) {
 		for (i = 0; i < ubi->fm->used_blocks; i++)
 			kfree(ubi->fm->e[i]);

2.25.1

From: Arnd Bergmann <[email protected]>

[ Upstream commit d68f4e43a46ff1f772ff73085f96d44eb4163e9d ]

The mt76_led_cleanup() function is called unconditionally, which leads to a link error when CONFIG_LEDS is a loadable module or disabled but mt76 is built-in:

drivers/net/wireless/mediatek/mt76/mac80211.o: In function `mt76_unregister_device':
mac80211.c:(.text+0x2ac): undefined reference to `led_classdev_unregister'

Use the same trick that is guarding the registration, using an IS_ENABLED() check for the CONFIG_MT76_LEDS symbol that indicates whether LEDs can be used or not.

---
 drivers/net/wireless/mediatek/mt76/mac80211.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

index 7be5806a1c398..8bd191347b9fb 100644
@@ -368,7 +368,8 @@ void mt76_unregister_device(struct mt76_dev *dev)
 {
 	struct ieee80211_hw *hw = dev->hw;
 
-	mt76_led_cleanup(dev);
+	if (IS_ENABLED(CONFIG_MT76_LEDS))
+		mt76_led_cleanup(dev);
 	mt76_tx_status_check(dev, NULL, true);
 	ieee80211_unregister_hw(hw);
 }

2.25.1

From: Walter Lozano <[email protected]>

[ Upstream commit 6544abc520f0fff701e9da382110dc29676c683a ]

Currently, when using _of_add_opp_table_v2 parsed_static_opps is increased and this value is used in _opp_remove_all_static() to check if there are static opp entries that need to be freed. Unfortunately this does not happen when using _of_add_opp_table_v1(), which leads to warnings.

This patch increases parsed_static_opps in _of_add_opp_table_v1() in a similar way as in _of_add_opp_table_v2().

[ Viresh: Do the operation with lock held and set the value to 1 instead
of incrementing it ]

---
 drivers/opp/of.c | 4 ++++
 1 file changed, 4 insertions(+)

index 9cd8f0adacae4..249738e1e0b7a 100644
@@ -733,6 +733,10 @@ static int _of_add_opp_table_v1(struct device *dev, struct opp_table *opp_table)
 		return -EINVAL;
 	}
 
+	mutex_lock(&opp_table->lock);
+	opp_table->parsed_static_opps = 1;
+	mutex_unlock(&opp_table->lock);
+
 	val = prop->value;
 	while (nr) {
 		unsigned long freq = be32_to_cpup(val++) * 1000;

2.25.1

From: Jin Yao <[email protected]>

[ Upstream commit 8510895bafdbf7c4dd24c22946d925691135c2b2 ]

A big uncore event group is split into multiple small groups which only include the uncore events from the same PMU. This has been supported in the commit 3cdc5c2cb924a ("perf parse-events: Handle uncore event aliases in small groups properly").

If the event's PMU name starts to repeat, it must be a new event. That can be used to distinguish the leader from other members. But now it only compares the pointer of pmu_name (leader->pmu_name == evsel->pmu_name).

If we use "perf stat -M LLC_MISSES.PCIE_WRITE -a" on cascadelakex, the event list is:

evsel->name evsel->pmu_name
---------------------------------------------------------------
unc_iio_data_req_of_cpu.mem_write.part0 uncore_iio_4 (as leader)
unc_iio_data_req_of_cpu.mem_write.part0 uncore_iio_2
unc_iio_data_req_of_cpu.mem_write.part0 uncore_iio_0
unc_iio_data_req_of_cpu.mem_write.part0 uncore_iio_5
unc_iio_data_req_of_cpu.mem_write.part0 uncore_iio_3
unc_iio_data_req_of_cpu.mem_write.part0 uncore_iio_1
unc_iio_data_req_of_cpu.mem_write.part1 uncore_iio_4
......

For the event "unc_iio_data_req_of_cpu.mem_write.part1" with "uncore_iio_4", it should be the event from PMU "uncore_iio_4". It's not a new leader for this PMU.

But if we use "(leader->pmu_name == evsel->pmu_name)", the check would be failed and the event is stored to leaders[] as a new PMU leader.

So this patch uses strcmp to compare the PMU name between events.

---
 tools/perf/util/parse-events.c |    5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

@@ -1505,12 +1505,11 @@ parse_events__set_leader_for_uncore_alia
 		 * event. That can be used to distinguish the leader from
 		 * other members, even they have the same event name.
 		 */
-		if ((leader != evsel) && (leader->pmu_name == evsel->pmu_name)) {
+		if ((leader != evsel) &&
+		    !strcmp(leader->pmu_name, evsel->pmu_name)) {
 			is_leader = false;
 			continue;
 		}
-		/* The name is always alias name */
-		WARN_ON(strcmp(leader->name, evsel->name));
 
 		/* Store the leader event for each PMU */
 		leaders[nr_pmu++] = (uintptr_t) evsel;

From: Takashi Iwai <[email protected]>

[ Upstream commit 8d6762af302d69f76fa788a277a56a9d9cd275d5 ]

HD-audio codec driver applies a tricky procedure to forcibly perform the runtime resume by mimicking the usage count even if the device has been runtime-suspended beforehand. This was needed to assure to trigger the jack detection update after the system resume.

And recently we also applied the similar logic to the HD-audio controller side. However this seems leading to some inconsistency, and eventually PCI controller gets screwed up.

This patch is an attempt to fix and clean up those behavior: instead of the tricky runtime resume procedure, the existing jackpoll work is scheduled when such a forced codec resume is required. The jackpoll work will power up the codec, and this alone should suffice for the jack status update in usual cases. If the extra polling is requested (by checking codec->jackpoll_interval), the manual update is invoked after that, and the codec is powered down again.

Also, we filter the spurious wake up of the codec from the controller runtime resume by checking codec->relaxed_resume flag. If this flag is set, basically we don't need to wake up explicitly, but it's supposed to be done via the audio component notifier.

---
 sound/pci/hda/hda_codec.c | 28 +++++++++++++++++-----------
 sound/pci/hda/hda_intel.c | 17 ++---------------
 2 files changed, 19 insertions(+), 26 deletions(-)

index 12da263fb02ba..6da296def283e 100644
@@ -641,8 +641,18 @@ static void hda_jackpoll_work(struct work_struct *work)
 	struct hda_codec *codec =
 		container_of(work, struct hda_codec, jackpoll_work.work);
 
-	snd_hda_jack_set_dirty_all(codec);
-	snd_hda_jack_poll_all(codec);
+	/* for non-polling trigger: we need nothing if already powered on */
+	if (!codec->jackpoll_interval && snd_hdac_is_power_on(&codec->core))
+		return;
+
+	/* the power-up/down sequence triggers the runtime resume */
+	snd_hda_power_up_pm(codec);
+	/* update jacks manually if polling is required, too */
+	if (codec->jackpoll_interval) {
+		snd_hda_jack_set_dirty_all(codec);
+		snd_hda_jack_poll_all(codec);
+	}
+	snd_hda_power_down_pm(codec);
 
 	if (!codec->jackpoll_interval)
 		return;

@@ -2958,18 +2968,14 @@ static int hda_codec_runtime_resume(struct device *dev)
 static int hda_codec_force_resume(struct device *dev)
 {
 	struct hda_codec *codec = dev_to_hda_codec(dev);
-	bool forced_resume = hda_codec_need_resume(codec);
 	int ret;
 
-	/* The get/put pair below enforces the runtime resume even if the
-	 * device hasn't been used at suspend time.  This trick is needed to
-	 * update the jack state change during the sleep.
-	 */
-	if (forced_resume)
-		pm_runtime_get_noresume(dev);
 	ret = pm_runtime_force_resume(dev);
-	if (forced_resume)
-		pm_runtime_put(dev);
+	/* schedule jackpoll work for jack detection update */
+	if (codec->jackpoll_interval ||
+	    (pm_runtime_suspended(dev) && hda_codec_need_resume(codec)))
+		schedule_delayed_work(&codec->jackpoll_work,
+				      codec->jackpoll_interval);
 	return ret;
 }
 

index a6e8aaa091c7d..754e4d1a86b57 100644
@@ -1002,7 +1002,8 @@ static void __azx_runtime_resume(struct azx *chip, bool from_rt)
 
 	if (status && from_rt) {
 		list_for_each_codec(codec, &chip->bus)
-			if (status & (1 << codec->addr))
+			if (!codec->relaxed_resume &&
+			    (status & (1 << codec->addr)))
 				schedule_delayed_work(&codec->jackpoll_work,
 						      codec->jackpoll_interval);
 	}

@@ -1041,9 +1042,7 @@ static int azx_suspend(struct device *dev)
 static int azx_resume(struct device *dev)
 {
 	struct snd_card *card = dev_get_drvdata(dev);
-	struct hda_codec *codec;
 	struct azx *chip;
-	bool forced_resume = false;
 
 	if (!azx_is_pm_ready(card))
 		return 0;

@@ -1055,19 +1054,7 @@ static int azx_resume(struct device *dev)
 	if (azx_acquire_irq(chip, 1) < 0)
 		return -EIO;
 
-	/* check for the forced resume */
-	list_for_each_codec(codec, &chip->bus) {
-		if (hda_codec_need_resume(codec)) {
-			forced_resume = true;
-			break;
-		}
-	}
-
-	if (forced_resume)
-		pm_runtime_get_noresume(dev);
 	pm_runtime_force_resume(dev);
-	if (forced_resume)
-		pm_runtime_put(dev);
 	snd_power_change_state(card, SNDRV_CTL_POWER_D0);
 
 	trace_azx_resume(chip);

2.25.1

From: Takashi Iwai <[email protected]>

[ Upstream commit a6630529aecb5a3e84370c376ed658e892e6261e ]

We've received a regression report on Intel HD-audio controller that wakes up immediately after S3 suspend. The bisection leads to the commit c4c8dd6ef807 ("ALSA: hda: Skip controller resume if not needed"). This commit replaces the system-suspend to use pm_runtime_force_suspend() instead of the direct call of __azx_runtime_suspend(). However, by some really mysterious reason, pm_runtime_force_suspend() causes a spurious wakeup (although it calls the same __azx_runtime_suspend() internally).

As an ugly workaround for now, revert the behavior to call __azx_runtime_suspend() and __azx_runtime_resume() for those old Intel platforms that may exhibit such a problem, while keeping the new standard pm_runtime_force_suspend() and pm_runtime_force_resume() pair for the remaining chips.

---
 sound/pci/hda/hda_controller.h |  2 +-
 sound/pci/hda/hda_intel.c      | 17 ++++++++++++++---
 2 files changed, 15 insertions(+), 4 deletions(-)

index 82e26442724ba..a356fb0e57738 100644
@@ -41,7 +41,7 @@
 /* 24 unused */
 #define AZX_DCAPS_COUNT_LPIB_DELAY  (1 << 25)	/* Take LPIB as delay */
 #define AZX_DCAPS_PM_RUNTIME	(1 << 26)	/* runtime PM support */
-/* 27 unused */
+#define AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP (1 << 27) /* Workaround for spurious wakeups after suspend */
 #define AZX_DCAPS_CORBRP_SELF_CLEAR (1 << 28)	/* CORBRP clears itself after reset */
 #define AZX_DCAPS_NO_MSI64      (1 << 29)	/* Stick to 32-bit MSIs */
 #define AZX_DCAPS_SEPARATE_STREAM_TAG	(1 << 30) /* capture and playback use separate stream tag */

index 754e4d1a86b57..590ea262f2e20 100644
@@ -295,7 +295,8 @@ enum {
 /* PCH for HSW/BDW; with runtime PM */
 /* no i915 binding for this as HSW/BDW has another controller for HDMI */
 #define AZX_DCAPS_INTEL_PCH \
-	(AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME)
+	(AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME |\
+	 AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP)
 
 /* HSW HDMI */
 #define AZX_DCAPS_INTEL_HASWELL \

@@ -1026,7 +1027,14 @@ static int azx_suspend(struct device *dev)
 	chip = card->private_data;
 	bus = azx_bus(chip);
 	snd_power_change_state(card, SNDRV_CTL_POWER_D3hot);
-	pm_runtime_force_suspend(dev);
+	/* An ugly workaround: direct call of __azx_runtime_suspend() and
+	 * __azx_runtime_resume() for old Intel platforms that suffer from
+	 * spurious wakeups after S3 suspend
+	 */
+	if (chip->driver_caps & AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP)
+		__azx_runtime_suspend(chip);
+	else
+		pm_runtime_force_suspend(dev);
 	if (bus->irq >= 0) {
 		free_irq(bus->irq, chip);
 		bus->irq = -1;

@@ -1054,7 +1062,10 @@ static int azx_resume(struct device *dev)
 	if (azx_acquire_irq(chip, 1) < 0)
 		return -EIO;
 
-	pm_runtime_force_resume(dev);
+	if (chip->driver_caps & AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP)
+		__azx_runtime_resume(chip, false);
+	else
+		pm_runtime_force_resume(dev);
 	snd_power_change_state(card, SNDRV_CTL_POWER_D0);
 
 	trace_azx_resume(chip);

2.25.1

From: Tonghao Zhang <[email protected]>

[ Upstream commit 659d4587fe7233bfdff303744b20d6f41ad04362 ]

Compile the kernel for arm 32 platform, the build warning found. To fix that, should use div_u64() for divisions.
| net/openvswitch/meter.c:396: undefined reference to `__udivdi3'

[add more commit msg, change reported tag, and use div_u64 instead of do_div by Tonghao]

---
 net/openvswitch/meter.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index b10734f18bbd6..541eea74ef7a6 100644
@@ -252,7 +252,7 @@ static struct dp_meter *dp_meter_create(struct nlattr **a)
 		 * Start with a full bucket.
 		 */
 		band->bucket = (band->burst_size + band->rate) * 1000ULL;
-		band_max_delta_t = band->bucket / band->rate;
+		band_max_delta_t = div_u64(band->bucket, band->rate);
 		if (band_max_delta_t > meter->max_delta_t)
 			meter->max_delta_t = band_max_delta_t;
 		band++;

2.25.1

From: Anthony Iliopoulos <[email protected]>

[ Upstream commit 05b29021fba5e725dd385151ef00b6340229b500 ]

Commit 3b4b19721ec652 ("nvme: fix possible deadlock when I/O is blocked") reverted multipath head disk revalidation due to deadlocks caused by holding the bd_mutex during revalidate.

Updating the multipath disk blockdev size is still required though for userspace to be able to observe any resizing while the device is mounted. Directly update the bdev inode size to avoid unnecessarily holding the bdev->bd_mutex.

blocked")

---
 drivers/nvme/host/core.c |  1 +
 drivers/nvme/host/nvme.h | 13 +++++++++++++
 2 files changed, 14 insertions(+)

index 5702bc59c569c..2cd32901d95c7 100644
@@ -1864,6 +1864,7 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 	if (ns->head->disk) {
 		nvme_update_disk_info(ns->head->disk, ns, id);
 		blk_queue_stack_limits(ns->head->disk->queue, ns->queue);
+		nvme_mpath_update_disk_size(ns->head->disk);
 	}
 #endif
 }

index 5eb9500c89392..b7117fb09dd0f 100644
@@ -561,6 +561,16 @@ static inline void nvme_trace_bio_complete(struct request *req,
 					 req->bio, status);
 }
 
+static inline void nvme_mpath_update_disk_size(struct gendisk *disk)
+{
+	struct block_device *bdev = bdget_disk(disk, 0);
+
+	if (bdev) {
+		bd_set_size(bdev, get_capacity(disk) << SECTOR_SHIFT);
+		bdput(bdev);
+	}
+}
+
 extern struct device_attribute dev_attr_ana_grpid;
 extern struct device_attribute dev_attr_ana_state;
 extern struct device_attribute subsys_attr_iopolicy;

@@ -636,6 +646,9 @@ static inline void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys)
 static inline void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
 {
 }
+static inline void nvme_mpath_update_disk_size(struct gendisk *disk)
+{
+}
 #endif /* CONFIG_NVME_MULTIPATH */
 
 #ifdef CONFIG_NVM

2.25.1

From: Amol Grover <[email protected]>

[ Upstream commit bc62d68e2a0a69fcdcf28aca8edb01abf306b698 ]

exceptions may be traversed using list_for_each_entry_rcu() outside of an RCU read side critical section BUT under the protection of decgroup_mutex. Hence add the corresponding lockdep expression to fix the following false-positive warning:

[    2.304417] =============================
[    2.304418] WARNING: suspicious RCU usage
[    2.304420] 5.5.4-stable #17 Tainted: G            E
[    2.304422] -----------------------------
[    2.304424] security/device_cgroup.c:355 RCU-list traversed in non-reader section!!

---
 security/device_cgroup.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

index 725674f3276d3..5d7bb91c64876 100644
@@ -352,7 +352,8 @@ static bool match_exception_partial(struct list_head *exceptions, short type,
 {
 	struct dev_exception_item *ex;
 
-	list_for_each_entry_rcu(ex, exceptions, list) {
+	list_for_each_entry_rcu(ex, exceptions, list,
+				lockdep_is_held(&devcgroup_mutex)) {
 		if ((type & DEVCG_DEV_BLOCK) && !(ex->type & DEVCG_DEV_BLOCK))
 			continue;
 		if ((type & DEVCG_DEV_CHAR) && !(ex->type & DEVCG_DEV_CHAR))