Merge tag 'v5.10.64' into 5.10

This is the 5.10.64 stable release

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 10
-SUBLEVEL = 63
+SUBLEVEL = 64
 EXTRAVERSION =
 NAME = Dare mighty things
 

arch/x86/events/amd/iommu.c

@@ -18,8 +18,6 @@
 #include "../perf_event.h"
 #include "iommu.h"
 
-#define COUNTER_SHIFT		16
-
 /* iommu pmu conf masks */
 #define GET_CSOURCE(x)     ((x)->conf & 0xFFULL)
 #define GET_DEVID(x)       (((x)->conf >> 8)  & 0xFFFFULL)
@@ -285,22 +283,31 @@ static void perf_iommu_start(struct perf_event *event, int flags)
 	WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
 	hwc->state = 0;
 
+	/*
+	 * To account for power-gating, which prevents write to
+	 * the counter, we need to enable the counter
+	 * before setting up counter register.
+	 */
+	perf_iommu_enable_event(event);
+
 	if (flags & PERF_EF_RELOAD) {
-		u64 prev_raw_count = local64_read(&hwc->prev_count);
+		u64 count = 0;
 		struct amd_iommu *iommu = perf_event_2_iommu(event);
 
+		/*
+		 * Since the IOMMU PMU only support counting mode,
+		 * the counter always start with value zero.
+		 */
 		amd_iommu_pc_set_reg(iommu, hwc->iommu_bank, hwc->iommu_cntr,
-				     IOMMU_PC_COUNTER_REG, &prev_raw_count);
+				     IOMMU_PC_COUNTER_REG, &count);
 	}
 
-	perf_iommu_enable_event(event);
 	perf_event_update_userpage(event);
-
 }
 
 static void perf_iommu_read(struct perf_event *event)
 {
-	u64 count, prev, delta;
+	u64 count;
 	struct hw_perf_event *hwc = &event->hw;
 	struct amd_iommu *iommu = perf_event_2_iommu(event);
 
@@ -311,14 +318,11 @@ static void perf_iommu_read(struct perf_event *event)
 	/* IOMMU pc counter register is only 48 bits */
 	count &= GENMASK_ULL(47, 0);
 
-	prev = local64_read(&hwc->prev_count);
-	if (local64_cmpxchg(&hwc->prev_count, prev, count) != prev)
-		return;
-
-	/* Handle 48-bit counter overflow */
-	delta = (count << COUNTER_SHIFT) - (prev << COUNTER_SHIFT);
-	delta >>= COUNTER_SHIFT;
-	local64_add(delta, &event->count);
+	/*
+	 * Since the counter always start with value zero,
+	 * simply just accumulate the count for the event.
+	 */
+	local64_add(count, &event->count);
 }
 
 static void perf_iommu_stop(struct perf_event *event, int flags)
@@ -328,15 +332,16 @@ static void perf_iommu_stop(struct perf_event *event, int flags)
 	if (hwc->state & PERF_HES_UPTODATE)
 		return;
 
+	/*
+	 * To account for power-gating, in which reading the counter would
+	 * return zero, we need to read the register before disabling.
+	 */
+	perf_iommu_read(event);
+	hwc->state |= PERF_HES_UPTODATE;
+
 	perf_iommu_disable_event(event);
 	WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
 	hwc->state |= PERF_HES_STOPPED;
-
-	if (hwc->state & PERF_HES_UPTODATE)
-		return;
-
-	perf_iommu_read(event);
-	hwc->state |= PERF_HES_UPTODATE;
 }
 
 static int perf_iommu_add(struct perf_event *event, int flags)

arch/x86/kernel/reboot.c

@@ -388,10 +388,11 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = {
 	},
 	{	/* Handle problems with rebooting on the OptiPlex 990. */
 		.callback = set_pci_reboot,
-		.ident = "Dell OptiPlex 990",
+		.ident = "Dell OptiPlex 990 BIOS A0x",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 990"),
+			DMI_MATCH(DMI_BIOS_VERSION, "A0"),
 		},
 	},
 	{	/* Handle problems with rebooting on Dell 300's */

block/blk-core.c

@@ -121,7 +121,6 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	rq->internal_tag = BLK_MQ_NO_TAG;
 	rq->start_time_ns = ktime_get_ns();
 	rq->part = NULL;
-	refcount_set(&rq->ref, 1);
 	blk_crypto_rq_set_defaults(rq);
 }
 EXPORT_SYMBOL(blk_rq_init);

block/blk-flush.c

@@ -263,6 +263,11 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error)
 	spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
 }
 
+bool is_flush_rq(struct request *rq)
+{
+	return rq->end_io == flush_end_io;
+}
+
 /**
  * blk_kick_flush - consider issuing flush request
  * @q: request_queue being kicked
@@ -330,6 +335,14 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq,
 	flush_rq->rq_flags |= RQF_FLUSH_SEQ;
 	flush_rq->rq_disk = first_rq->rq_disk;
 	flush_rq->end_io = flush_end_io;
+	/*
+	 * Order WRITE ->end_io and WRITE rq->ref, and its pair is the one
+	 * implied in refcount_inc_not_zero() called from
+	 * blk_mq_find_and_get_req(), which orders WRITE/READ flush_rq->ref
+	 * and READ flush_rq->end_io
+	 */
+	smp_wmb();
+	refcount_set(&flush_rq->ref, 1);
 
 	blk_flush_queue_rq(flush_rq, false);
 }

block/blk-mq.c

@@ -929,7 +929,7 @@ static bool blk_mq_req_expired(struct request *rq, unsigned long *next)
 
 void blk_mq_put_rq_ref(struct request *rq)
 {
-	if (is_flush_rq(rq, rq->mq_hctx))
+	if (is_flush_rq(rq))
 		rq->end_io(rq, 0);
 	else if (refcount_dec_and_test(&rq->ref))
 		__blk_mq_free_request(rq);
@@ -2589,16 +2589,49 @@ static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx)
 					    &hctx->cpuhp_dead);
 }
 
+/*
+ * Before freeing hw queue, clearing the flush request reference in
+ * tags->rqs[] for avoiding potential UAF.
+ */
+static void blk_mq_clear_flush_rq_mapping(struct blk_mq_tags *tags,
+		unsigned int queue_depth, struct request *flush_rq)
+{
+	int i;
+	unsigned long flags;
+
+	/* The hw queue may not be mapped yet */
+	if (!tags)
+		return;
+
+	WARN_ON_ONCE(refcount_read(&flush_rq->ref) != 0);
+
+	for (i = 0; i < queue_depth; i++)
+		cmpxchg(&tags->rqs[i], flush_rq, NULL);
+
+	/*
+	 * Wait until all pending iteration is done.
+	 *
+	 * Request reference is cleared and it is guaranteed to be observed
+	 * after the ->lock is released.
+	 */
+	spin_lock_irqsave(&tags->lock, flags);
+	spin_unlock_irqrestore(&tags->lock, flags);
+}
+
 /* hctx->ctxs will be freed in queue's release handler */
 static void blk_mq_exit_hctx(struct request_queue *q,
 		struct blk_mq_tag_set *set,
 		struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
 {
+	struct request *flush_rq = hctx->fq->flush_rq;
+
 	if (blk_mq_hw_queue_mapped(hctx))
 		blk_mq_tag_idle(hctx);
 
+	blk_mq_clear_flush_rq_mapping(set->tags[hctx_idx],
+			set->queue_depth, flush_rq);
 	if (set->ops->exit_request)
-		set->ops->exit_request(set, hctx->fq->flush_rq, hctx_idx);
+		set->ops->exit_request(set, flush_rq, hctx_idx);
 
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);

block/blk.h

@@ -44,11 +44,7 @@ static inline void __blk_get_queue(struct request_queue *q)
 	kobject_get(&q->kobj);
 }
 
-static inline bool
-is_flush_rq(struct request *req, struct blk_mq_hw_ctx *hctx)
-{
-	return hctx->fq->flush_rq == req;
-}
+bool is_flush_rq(struct request *req);
 
 struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size,
 					      gfp_t flags);

drivers/net/ethernet/realtek/r8169_main.c

@@ -3547,6 +3547,7 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp)
 	rtl_eri_write(tp, 0x1b0, ERIAR_MASK_0011, 0x0000);
 
 	rtl_pcie_state_l2l3_disable(tp);
+	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 DECLARE_RTL_COND(rtl_mac_ocp_e00e_cond)

drivers/net/ethernet/xilinx/ll_temac_main.c

@@ -942,10 +942,8 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	wmb();
 	lp->dma_out(lp, TX_TAILDESC_PTR, tail_p); /* DMA start */
 
-	if (temac_check_tx_bd_space(lp, MAX_SKB_FRAGS + 1)) {
-		netdev_info(ndev, "%s -> netif_stop_queue\n", __func__);
+	if (temac_check_tx_bd_space(lp, MAX_SKB_FRAGS + 1))
 		netif_stop_queue(ndev);
-	}
 
 	return NETDEV_TX_OK;
 }

drivers/pci/quirks.c

@@ -3246,12 +3246,12 @@ static void fixup_mpss_256(struct pci_dev *dev)
 {
 	dev->pcie_mpss = 1; /* 256 bytes */
 }
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SOLARFLARE,
-			 PCI_DEVICE_ID_SOLARFLARE_SFC4000A_0, fixup_mpss_256);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SOLARFLARE,
-			 PCI_DEVICE_ID_SOLARFLARE_SFC4000A_1, fixup_mpss_256);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SOLARFLARE,
-			 PCI_DEVICE_ID_SOLARFLARE_SFC4000B, fixup_mpss_256);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SOLARFLARE,
+			PCI_DEVICE_ID_SOLARFLARE_SFC4000A_0, fixup_mpss_256);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SOLARFLARE,
+			PCI_DEVICE_ID_SOLARFLARE_SFC4000A_1, fixup_mpss_256);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SOLARFLARE,
+			PCI_DEVICE_ID_SOLARFLARE_SFC4000B, fixup_mpss_256);
 
 /*
  * Intel 5000 and 5100 Memory controllers have an erratum with read completion

drivers/tty/serial/8250/8250_omap.c

@@ -538,6 +538,11 @@ static void omap_8250_pm(struct uart_port *port, unsigned int state,
 static void omap_serial_fill_features_erratas(struct uart_8250_port *up,
 					      struct omap8250_priv *priv)
 {
+	const struct soc_device_attribute k3_soc_devices[] = {
+		{ .family = "AM65X",  },
+		{ .family = "J721E", .revision = "SR1.0" },
+		{ /* sentinel */ }
+	};
 	u32 mvr, scheme;
 	u16 revision, major, minor;
 
@@ -585,6 +590,14 @@ static void omap_serial_fill_features_erratas(struct uart_8250_port *up,
 	default:
 		break;
 	}
+
+	/*
+	 * AM65x SR1.0, AM65x SR2.0 and J721e SR1.0 don't
+	 * don't have RHR_IT_DIS bit in IER2 register. So drop to flag
+	 * to enable errata workaround.
+	 */
+	if (soc_device_match(k3_soc_devices))
+		priv->habit &= ~UART_HAS_RHR_IT_DIS;
 }
 
 static void omap8250_uart_qos_work(struct work_struct *work)
@@ -1208,12 +1221,6 @@ static int omap8250_no_handle_irq(struct uart_port *port)
 	return 0;
 }
 
-static const struct soc_device_attribute k3_soc_devices[] = {
-	{ .family = "AM65X",  },
-	{ .family = "J721E", .revision = "SR1.0" },
-	{ /* sentinel */ }
-};
-
 static struct omap8250_dma_params am654_dma = {
 	.rx_size = SZ_2K,
 	.rx_trigger = 1,
@@ -1419,13 +1426,6 @@ static int omap8250_probe(struct platform_device *pdev)
 			up.dma->rxconf.src_maxburst = RX_TRIGGER;
 			up.dma->txconf.dst_maxburst = TX_TRIGGER;
 		}
-
-		/*
-		 * AM65x SR1.0, AM65x SR2.0 and J721e SR1.0 don't
-		 * don't have RHR_IT_DIS bit in IER2 register
-		 */
-		if (soc_device_match(k3_soc_devices))
-			priv->habit &= ~UART_HAS_RHR_IT_DIS;
 	}
 #endif
 	ret = serial8250_register_8250_port(&up);

drivers/usb/gadget/udc/tegra-xudc.c

@@ -1610,7 +1610,7 @@ static void tegra_xudc_ep_context_setup(struct tegra_xudc_ep *ep)
 	u16 maxpacket, maxburst = 0, esit = 0;
 	u32 val;
 
-	maxpacket = usb_endpoint_maxp(desc) & 0x7ff;
+	maxpacket = usb_endpoint_maxp(desc);
 	if (xudc->gadget.speed == USB_SPEED_SUPER) {
 		if (!usb_endpoint_xfer_control(desc))
 			maxburst = comp_desc->bMaxBurst;
@@ -1621,7 +1621,7 @@ static void tegra_xudc_ep_context_setup(struct tegra_xudc_ep *ep)
 		   (usb_endpoint_xfer_int(desc) ||
 		    usb_endpoint_xfer_isoc(desc))) {
 		if (xudc->gadget.speed == USB_SPEED_HIGH) {
-			maxburst = (usb_endpoint_maxp(desc) >> 11) & 0x3;
+			maxburst = usb_endpoint_maxp_mult(desc) - 1;
 			if (maxburst == 0x3) {
 				dev_warn(xudc->dev,
 					 "invalid endpoint maxburst\n");

drivers/usb/host/xhci-debugfs.c

@@ -198,12 +198,13 @@ static void xhci_ring_dump_segment(struct seq_file *s,
 	int			i;
 	dma_addr_t		dma;
 	union xhci_trb		*trb;
+	char			str[XHCI_MSG_MAX];
 
 	for (i = 0; i < TRBS_PER_SEGMENT; i++) {
 		trb = &seg->trbs[i];
 		dma = seg->dma + i * sizeof(*trb);
 		seq_printf(s, "%pad: %s\n", &dma,
-			   xhci_decode_trb(le32_to_cpu(trb->generic.field[0]),
+			   xhci_decode_trb(str, XHCI_MSG_MAX, le32_to_cpu(trb->generic.field[0]),
 					   le32_to_cpu(trb->generic.field[1]),
 					   le32_to_cpu(trb->generic.field[2]),
 					   le32_to_cpu(trb->generic.field[3])));
@@ -260,11 +261,13 @@ static int xhci_slot_context_show(struct seq_file *s, void *unused)
 	struct xhci_slot_ctx	*slot_ctx;
 	struct xhci_slot_priv	*priv = s->private;
 	struct xhci_virt_device	*dev = priv->dev;
+	char			str[XHCI_MSG_MAX];
 
 	xhci = hcd_to_xhci(bus_to_hcd(dev->udev->bus));
 	slot_ctx = xhci_get_slot_ctx(xhci, dev->out_ctx);
 	seq_printf(s, "%pad: %s\n", &dev->out_ctx->dma,
-		   xhci_decode_slot_context(le32_to_cpu(slot_ctx->dev_info),
+		   xhci_decode_slot_context(str,
+					    le32_to_cpu(slot_ctx->dev_info),
 					    le32_to_cpu(slot_ctx->dev_info2),
 					    le32_to_cpu(slot_ctx->tt_info),
 					    le32_to_cpu(slot_ctx->dev_state)));
@@ -280,14 +283,16 @@ static int xhci_endpoint_context_show(struct seq_file *s, void *unused)
 	struct xhci_ep_ctx	*ep_ctx;
 	struct xhci_slot_priv	*priv = s->private;
 	struct xhci_virt_device	*dev = priv->dev;
+	char			str[XHCI_MSG_MAX];
 
 	xhci = hcd_to_xhci(bus_to_hcd(dev->udev->bus));
 
 	for (ep_index = 0; ep_index < 31; ep_index++) {
 		ep_ctx = xhci_get_ep_ctx(xhci, dev->out_ctx, ep_index);
 		dma = dev->out_ctx->dma + (ep_index + 1) * CTX_SIZE(xhci->hcc_params);
 		seq_printf(s, "%pad: %s\n", &dma,
-			   xhci_decode_ep_context(le32_to_cpu(ep_ctx->ep_info),
+			   xhci_decode_ep_context(str,
+						  le32_to_cpu(ep_ctx->ep_info),
 						  le32_to_cpu(ep_ctx->ep_info2),
 						  le64_to_cpu(ep_ctx->deq),
 						  le32_to_cpu(ep_ctx->tx_info)));
@@ -341,9 +346,10 @@ static int xhci_portsc_show(struct seq_file *s, void *unused)
 {
 	struct xhci_port	*port = s->private;
 	u32			portsc;
+	char			str[XHCI_MSG_MAX];
 
 	portsc = readl(port->addr);
-	seq_printf(s, "%s\n", xhci_decode_portsc(portsc));
+	seq_printf(s, "%s\n", xhci_decode_portsc(str, portsc));
 
 	return 0;
 }