Skip to contentSkip to conversation

6.1.81-rc1 review

PATCH In review Greg Kroah-Hartman 13 participants 230 messages Mar 4, 2024 – Mar 6, 2024 Page 1 of 2

Subsystems (6)
lore
Share & tools
lore
author maintainer
#1 lore raw

PATCH 1/215 netfilter: nf_tables: disallow timeout for anonymous sets

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pablo Neira Ayuso <[email protected]>

commit e26d3009efda338f19016df4175f354a9bd0a4ab upstream.

Never used from userspace, disallow these parameters.

---
 net/netfilter/nf_tables_api.c |    7 +++++++
 1 file changed, 7 insertions(+)
net/netfilter/nf_tables_api.c +7 -0
@@ -4752,6 +4752,9 @@ static int nf_tables_newset(struct sk_bu
 		if (!(flags & NFT_SET_TIMEOUT))
 			return -EINVAL;
 
+		if (flags & NFT_SET_ANONYMOUS)
+			return -EOPNOTSUPP;
+
 		err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &desc.timeout);
 		if (err)
 			return err;
@@ -4760,6 +4763,10 @@ static int nf_tables_newset(struct sk_bu
 	if (nla[NFTA_SET_GC_INTERVAL] != NULL) {
 		if (!(flags & NFT_SET_TIMEOUT))
 			return -EINVAL;
+
+		if (flags & NFT_SET_ANONYMOUS)
+			return -EOPNOTSUPP;
+
 		desc.gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL]));
 	}
 
author maintainer
#10 lore raw

PATCH 10/215 mlxsw: spectrum_acl_tcam: Add missing mutex_destroy()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ido Schimmel <[email protected]>

[ Upstream commit 65823e07b1e4055b6278725fd92f4d7e6f8d53fd ]

Pair mutex_init() with a mutex_destroy() in the error path. Found during code review. No functional changes.

---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)
drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +6 -2
index 2107de4e9d99b..41eac7dfb67e7 100644
@@ -52,8 +52,10 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp,
 		max_regions = max_tcam_regions;
 
 	tcam->used_regions = bitmap_zalloc(max_regions, GFP_KERNEL);
-	if (!tcam->used_regions)
-		return -ENOMEM;
+	if (!tcam->used_regions) {
+		err = -ENOMEM;
+		goto err_alloc_used_regions;
+	}
 	tcam->max_regions = max_regions;
 
 	max_groups = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_GROUPS);
@@ -78,6 +80,8 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp,
 	bitmap_free(tcam->used_groups);
 err_alloc_used_groups:
 	bitmap_free(tcam->used_regions);
+err_alloc_used_regions:
+	mutex_destroy(&tcam->lock);
 	return err;
 }
 
Signature · 1 line
2.43.0
author maintainer
#11 lore raw

PATCH 11/215 PCI: layerscape: Add the endpoint linkup notifier support

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Frank Li <[email protected]>

[ Upstream commit 061cbfab09fb35898f2907d42f936cf9ae271d93 ]

Layerscape has PME interrupt, which can be used as linkup notifier. Set CFG_READY bit of PEX_PF0_CONFIG to enable accesses from root complex when linkup detected.

---
 .../pci/controller/dwc/pci-layerscape-ep.c    | 100 +++++++++++++++++-
 1 file changed, 99 insertions(+), 1 deletion(-)
drivers/pci/controller/dwc/pci-layerscape-ep.c +99 -1
index ad99707b3b994..5b27554e071a1 100644
@@ -18,6 +18,20 @@
 
 #include "pcie-designware.h"
 
+#define PEX_PF0_CONFIG			0xC0014
+#define PEX_PF0_CFG_READY		BIT(0)
+
+/* PEX PFa PCIE PME and message interrupt registers*/
+#define PEX_PF0_PME_MES_DR		0xC0020
+#define PEX_PF0_PME_MES_DR_LUD		BIT(7)
+#define PEX_PF0_PME_MES_DR_LDD		BIT(9)
+#define PEX_PF0_PME_MES_DR_HRD		BIT(10)
+
+#define PEX_PF0_PME_MES_IER		0xC0028
+#define PEX_PF0_PME_MES_IER_LUDIE	BIT(7)
+#define PEX_PF0_PME_MES_IER_LDDIE	BIT(9)
+#define PEX_PF0_PME_MES_IER_HRDIE	BIT(10)
+
 #define to_ls_pcie_ep(x)	dev_get_drvdata((x)->dev)
 
 struct ls_pcie_ep_drvdata {
@@ -30,8 +44,84 @@ struct ls_pcie_ep {
 	struct dw_pcie			*pci;
 	struct pci_epc_features		*ls_epc;
 	const struct ls_pcie_ep_drvdata *drvdata;
+	int				irq;
+	bool				big_endian;
 };
 
+static u32 ls_lut_readl(struct ls_pcie_ep *pcie, u32 offset)
+{
+	struct dw_pcie *pci = pcie->pci;
+
+	if (pcie->big_endian)
+		return ioread32be(pci->dbi_base + offset);
+	else
+		return ioread32(pci->dbi_base + offset);
+}
+
+static void ls_lut_writel(struct ls_pcie_ep *pcie, u32 offset, u32 value)
+{
+	struct dw_pcie *pci = pcie->pci;
+
+	if (pcie->big_endian)
+		iowrite32be(value, pci->dbi_base + offset);
+	else
+		iowrite32(value, pci->dbi_base + offset);
+}
+
+static irqreturn_t ls_pcie_ep_event_handler(int irq, void *dev_id)
+{
+	struct ls_pcie_ep *pcie = dev_id;
+	struct dw_pcie *pci = pcie->pci;
+	u32 val, cfg;
+
+	val = ls_lut_readl(pcie, PEX_PF0_PME_MES_DR);
+	ls_lut_writel(pcie, PEX_PF0_PME_MES_DR, val);
+
+	if (!val)
+		return IRQ_NONE;
+
+	if (val & PEX_PF0_PME_MES_DR_LUD) {
+		cfg = ls_lut_readl(pcie, PEX_PF0_CONFIG);
+		cfg |= PEX_PF0_CFG_READY;
+		ls_lut_writel(pcie, PEX_PF0_CONFIG, cfg);
+		dw_pcie_ep_linkup(&pci->ep);
+
+		dev_dbg(pci->dev, "Link up\n");
+	} else if (val & PEX_PF0_PME_MES_DR_LDD) {
+		dev_dbg(pci->dev, "Link down\n");
+	} else if (val & PEX_PF0_PME_MES_DR_HRD) {
+		dev_dbg(pci->dev, "Hot reset\n");
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int ls_pcie_ep_interrupt_init(struct ls_pcie_ep *pcie,
+				     struct platform_device *pdev)
+{
+	u32 val;
+	int ret;
+
+	pcie->irq = platform_get_irq_byname(pdev, "pme");
+	if (pcie->irq < 0)
+		return pcie->irq;
+
+	ret = devm_request_irq(&pdev->dev, pcie->irq, ls_pcie_ep_event_handler,
+			       IRQF_SHARED, pdev->name, pcie);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't register PCIe IRQ\n");
+		return ret;
+	}
+
+	/* Enable interrupts */
+	val = ls_lut_readl(pcie, PEX_PF0_PME_MES_IER);
+	val |=  PEX_PF0_PME_MES_IER_LDDIE | PEX_PF0_PME_MES_IER_HRDIE |
+		PEX_PF0_PME_MES_IER_LUDIE;
+	ls_lut_writel(pcie, PEX_PF0_PME_MES_IER, val);
+
+	return 0;
+}
+
 static const struct pci_epc_features*
 ls_pcie_ep_get_features(struct dw_pcie_ep *ep)
 {
@@ -124,6 +214,7 @@ static int __init ls_pcie_ep_probe(struct platform_device *pdev)
 	struct ls_pcie_ep *pcie;
 	struct pci_epc_features *ls_epc;
 	struct resource *dbi_base;
+	int ret;
 
 	pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL);
 	if (!pcie)
@@ -143,6 +234,7 @@ static int __init ls_pcie_ep_probe(struct platform_device *pdev)
 	pci->ops = pcie->drvdata->dw_pcie_ops;
 
 	ls_epc->bar_fixed_64bit = (1 << BAR_2) | (1 << BAR_4);
+	ls_epc->linkup_notifier = true;
 
 	pcie->pci = pci;
 	pcie->ls_epc = ls_epc;
@@ -154,9 +246,15 @@ static int __init ls_pcie_ep_probe(struct platform_device *pdev)
 
 	pci->ep.ops = &ls_pcie_ep_ops;
 
+	pcie->big_endian = of_property_read_bool(dev->of_node, "big-endian");
+
 	platform_set_drvdata(pdev, pcie);
 
-	return dw_pcie_ep_init(&pci->ep);
+	ret = dw_pcie_ep_init(&pci->ep);
+	if (ret)
+		return ret;
+
+	return ls_pcie_ep_interrupt_init(pcie, pdev);
 }
 
 static struct platform_driver ls_pcie_ep_driver = {
Signature · 1 line
2.43.0
author maintainer
#12 lore raw

PATCH 12/215 PCI: layerscape: Add workaround for lost link capabilities during reset

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Xiaowei Bao <[email protected]>

[ Upstream commit 17cf8661ee0f065c08152e611a568dd1fb0285f1 ]

The endpoint controller loses the Maximum Link Width and Supported Link Speed value from the Link Capabilities Register - initially configured by the Reset Configuration Word (RCW) - during a link-down or hot reset event.

Address this issue in the endpoint event handler.

---
 .../pci/controller/dwc/pci-layerscape-ep.c    | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)
drivers/pci/controller/dwc/pci-layerscape-ep.c +19 -0
index 5b27554e071a1..dd7d74fecc48e 100644
@@ -45,6 +45,7 @@ struct ls_pcie_ep {
 	struct pci_epc_features		*ls_epc;
 	const struct ls_pcie_ep_drvdata *drvdata;
 	int				irq;
+	u32				lnkcap;
 	bool				big_endian;
 };
 
@@ -73,6 +74,7 @@ static irqreturn_t ls_pcie_ep_event_handler(int irq, void *dev_id)
 	struct ls_pcie_ep *pcie = dev_id;
 	struct dw_pcie *pci = pcie->pci;
 	u32 val, cfg;
+	u8 offset;
 
 	val = ls_lut_readl(pcie, PEX_PF0_PME_MES_DR);
 	ls_lut_writel(pcie, PEX_PF0_PME_MES_DR, val);
@@ -81,6 +83,19 @@ static irqreturn_t ls_pcie_ep_event_handler(int irq, void *dev_id)
 		return IRQ_NONE;
 
 	if (val & PEX_PF0_PME_MES_DR_LUD) {
+
+		offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
+
+		/*
+		 * The values of the Maximum Link Width and Supported Link
+		 * Speed from the Link Capabilities Register will be lost
+		 * during link down or hot reset. Restore initial value
+		 * that configured by the Reset Configuration Word (RCW).
+		 */
+		dw_pcie_dbi_ro_wr_en(pci);
+		dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCAP, pcie->lnkcap);
+		dw_pcie_dbi_ro_wr_dis(pci);
+
 		cfg = ls_lut_readl(pcie, PEX_PF0_CONFIG);
 		cfg |= PEX_PF0_CFG_READY;
 		ls_lut_writel(pcie, PEX_PF0_CONFIG, cfg);
@@ -214,6 +229,7 @@ static int __init ls_pcie_ep_probe(struct platform_device *pdev)
 	struct ls_pcie_ep *pcie;
 	struct pci_epc_features *ls_epc;
 	struct resource *dbi_base;
+	u8 offset;
 	int ret;
 
 	pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL);
@@ -250,6 +266,9 @@ static int __init ls_pcie_ep_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, pcie);
 
+	offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
+	pcie->lnkcap = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP);
+
 	ret = dw_pcie_ep_init(&pci->ep);
 	if (ret)
 		return ret;
Signature · 1 line
2.43.0
author maintainer
#2 lore raw

PATCH 2/215 drm/meson: fix unbind path if HDMI fails to bind

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Neil Armstrong <[email protected]>

[ Upstream commit 6a044642988b5f8285f3173b8e88784bef2bc306 ]

If the case the HDMI controller fails to bind, we try to unbind all components before calling drm_dev_put() which makes drm_bridge_detach() crash because unbinding the HDMI controller frees the bridge memory.

The solution is the unbind all components at the end like in the remove path.

Stable-dep-of: bd915ae73a2d ("drm/meson: Don't remove bridges which are created by other drivers")

---
 drivers/gpu/drm/meson/meson_drv.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)
drivers/gpu/drm/meson/meson_drv.c +14 -9
index 119544d88b586..fbac39aa38cc4 100644
@@ -316,32 +316,34 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
 		goto exit_afbcd;
 
 	if (has_components) {
-		ret = component_bind_all(drm->dev, drm);
+		ret = component_bind_all(dev, drm);
 		if (ret) {
 			dev_err(drm->dev, "Couldn't bind all components\n");
+			/* Do not try to unbind */
+			has_components = false;
 			goto exit_afbcd;
 		}
 	}
 
 	ret = meson_encoder_hdmi_init(priv);
 	if (ret)
-		goto unbind_all;
+		goto exit_afbcd;
 
 	ret = meson_plane_create(priv);
 	if (ret)
-		goto unbind_all;
+		goto exit_afbcd;
 
 	ret = meson_overlay_create(priv);
 	if (ret)
-		goto unbind_all;
+		goto exit_afbcd;
 
 	ret = meson_crtc_create(priv);
 	if (ret)
-		goto unbind_all;
+		goto exit_afbcd;
 
 	ret = request_irq(priv->vsync_irq, meson_irq, 0, drm->driver->name, drm);
 	if (ret)
-		goto unbind_all;
+		goto exit_afbcd;
 
 	drm_mode_config_reset(drm);
 
@@ -359,15 +361,18 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
 
 uninstall_irq:
 	free_irq(priv->vsync_irq, drm);
-unbind_all:
-	if (has_components)
-		component_unbind_all(drm->dev, drm);
 exit_afbcd:
 	if (priv->afbcd.ops)
 		priv->afbcd.ops->exit(priv);
 free_drm:
 	drm_dev_put(drm);
 
+	meson_encoder_hdmi_remove(priv);
+	meson_encoder_cvbs_remove(priv);
+
+	if (has_components)
+		component_unbind_all(dev, drm);
+
 	return ret;
 }
 
Signature · 1 line
2.43.0
author maintainer
#3 lore raw

PATCH 3/215 drm/meson: Dont remove bridges which are created by other drivers

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Martin Blumenstingl <[email protected]>

[ Upstream commit bd915ae73a2d78559b376ad2caf5e4ef51de2455 ]

Stop calling drm_bridge_remove() for bridges allocated/managed by other drivers in the remove paths of meson_encoder_{cvbs,dsi,hdmi}. drm_bridge_remove() unregisters the bridge so it cannot be used anymore. Doing so for bridges we don't own can lead to the video pipeline not being able to come up after -EPROBE_DEFER of the VPU because we're unregistering a bridge that's managed by another driver. The other driver doesn't know that we have unregistered it's bridge and on subsequent .probe() we're not able to find those bridges anymore (since nobody re-creates them).

This fixes probe errors on Meson8b boards with the CVBS outputs enabled.

---
 drivers/gpu/drm/meson/meson_encoder_cvbs.c | 1 -
 drivers/gpu/drm/meson/meson_encoder_hdmi.c | 1 -
 2 files changed, 2 deletions(-)
drivers/gpu/drm/meson/meson_encoder_cvbs.c +0 -1
index 3f73b211fa8e3..3407450435e20 100644
@@ -294,6 +294,5 @@ void meson_encoder_cvbs_remove(struct meson_drm *priv)
 	if (priv->encoders[MESON_ENC_CVBS]) {
 		meson_encoder_cvbs = priv->encoders[MESON_ENC_CVBS];
 		drm_bridge_remove(&meson_encoder_cvbs->bridge);
-		drm_bridge_remove(meson_encoder_cvbs->next_bridge);
 	}
 }
drivers/gpu/drm/meson/meson_encoder_hdmi.c +0 -1
index b14e6e507c61b..03062e7a02b64 100644
@@ -472,6 +472,5 @@ void meson_encoder_hdmi_remove(struct meson_drm *priv)
 	if (priv->encoders[MESON_ENC_HDMI]) {
 		meson_encoder_hdmi = priv->encoders[MESON_ENC_HDMI];
 		drm_bridge_remove(&meson_encoder_hdmi->bridge);
-		drm_bridge_remove(meson_encoder_hdmi->next_bridge);
 	}
 }
Signature · 1 line
2.43.0
author maintainer
#4 lore raw

PATCH 4/215 scsi: core: Add struct for args to execution functions

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mike Christie <[email protected]>

[ Upstream commit d0949565811f0896c1c7e781ab2ad99d34273fdf ]

Move the SCSI execution functions to use a struct for passing in optional args. This commit adds the new struct, temporarily converts scsi_execute() and scsi_execute_req() ands a new helper, scsi_execute_cmd(), which takes the scsi_exec_args struct.

There should be no change in behavior. We no longer allow users to pass in any request->rq_flags value, but they were only passing in RQF_PM which we do support by allowing users to pass in the BLK_MQ_REQ flags used by blk_mq_alloc_request().

Subsequent commits will convert scsi_execute() and scsi_execute_req() users to the new helpers then remove scsi_execute() and scsi_execute_req().

Stable-dep-of: 321da3dc1f3c ("scsi: sd: usb_storage: uas: Access media prior to querying device properties")

---
 drivers/scsi/scsi_lib.c    | 52 ++++++++++++++++++--------------------
 include/scsi/scsi_device.h | 51 +++++++++++++++++++++++++++----------
 2 files changed, 62 insertions(+), 41 deletions(-)
drivers/scsi/scsi_lib.c +25 -27
index 5c5954b78585e..edd296f950a33 100644
@@ -185,39 +185,37 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
 	__scsi_queue_insert(cmd, reason, true);
 }
 
-
 /**
- * __scsi_execute - insert request and wait for the result
- * @sdev:	scsi device
+ * scsi_execute_cmd - insert request and wait for the result
+ * @sdev:	scsi_device
  * @cmd:	scsi command
- * @data_direction: data direction
+ * @opf:	block layer request cmd_flags
  * @buffer:	data buffer
  * @bufflen:	len of buffer
- * @sense:	optional sense buffer
- * @sshdr:	optional decoded sense header
  * @timeout:	request timeout in HZ
  * @retries:	number of times to retry request
- * @flags:	flags for ->cmd_flags
- * @rq_flags:	flags for ->rq_flags
- * @resid:	optional residual length
+ * @args:	Optional args. See struct definition for field descriptions
  *
  * Returns the scsi_cmnd result field if a command was executed, or a negative
  * Linux error code if we didn't get that far.
  */
-int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
-		 int data_direction, void *buffer, unsigned bufflen,
-		 unsigned char *sense, struct scsi_sense_hdr *sshdr,
-		 int timeout, int retries, blk_opf_t flags,
-		 req_flags_t rq_flags, int *resid)
+int scsi_execute_cmd(struct scsi_device *sdev, const unsigned char *cmd,
+		     blk_opf_t opf, void *buffer, unsigned int bufflen,
+		     int timeout, int retries,
+		     const struct scsi_exec_args *args)
 {
+	static const struct scsi_exec_args default_args;
 	struct request *req;
 	struct scsi_cmnd *scmd;
 	int ret;
 
-	req = scsi_alloc_request(sdev->request_queue,
-			data_direction == DMA_TO_DEVICE ?
-			REQ_OP_DRV_OUT : REQ_OP_DRV_IN,
-			rq_flags & RQF_PM ? BLK_MQ_REQ_PM : 0);
+	if (!args)
+		args = &default_args;
+	else if (WARN_ON_ONCE(args->sense &&
+			      args->sense_len != SCSI_SENSE_BUFFERSIZE))
+		return -EINVAL;
+
+	req = scsi_alloc_request(sdev->request_queue, opf, args->req_flags);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
@@ -232,8 +230,7 @@ int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 	memcpy(scmd->cmnd, cmd, scmd->cmd_len);
 	scmd->allowed = retries;
 	req->timeout = timeout;
-	req->cmd_flags |= flags;
-	req->rq_flags |= rq_flags | RQF_QUIET;
+	req->rq_flags |= RQF_QUIET;
 
 	/*
 	 * head injection *required* here otherwise quiesce won't work
@@ -249,20 +246,21 @@ int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 	if (unlikely(scmd->resid_len > 0 && scmd->resid_len <= bufflen))
 		memset(buffer + bufflen - scmd->resid_len, 0, scmd->resid_len);
 
-	if (resid)
-		*resid = scmd->resid_len;
-	if (sense && scmd->sense_len)
-		memcpy(sense, scmd->sense_buffer, SCSI_SENSE_BUFFERSIZE);
-	if (sshdr)
+	if (args->resid)
+		*args->resid = scmd->resid_len;
+	if (args->sense)
+		memcpy(args->sense, scmd->sense_buffer, SCSI_SENSE_BUFFERSIZE);
+	if (args->sshdr)
 		scsi_normalize_sense(scmd->sense_buffer, scmd->sense_len,
-				     sshdr);
+				     args->sshdr);
+
 	ret = scmd->result;
  out:
 	blk_mq_free_request(req);
 
 	return ret;
 }
-EXPORT_SYMBOL(__scsi_execute);
+EXPORT_SYMBOL(scsi_execute_cmd);
 
 /*
  * Wake up the error handler if necessary. Avoid as follows that the error
include/scsi/scsi_device.h +37 -14

65 lines not on this page · raw message

Signature · 1 line
2.43.0
author maintainer
#5 lore raw

PATCH 5/215 scsi: sd: usb_storage: uas: Access media prior to querying device properties

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Martin K. Petersen <[email protected]>

[ Upstream commit 321da3dc1f3c92a12e3c5da934090d2992a8814c ]

It has been observed that some USB/UAS devices return generic properties hardcoded in firmware for mode pages for a period of time after a device has been discovered. The reported properties are either garbage or they do not accurately reflect the characteristics of the physical storage device attached in the case of a bridge.

Prior to commit 1e029397d12f ("scsi: sd: Reorganize DIF/DIX code to avoid calling revalidate twice") we would call revalidate several times during device discovery. As a result, incorrect values would eventually get replaced with ones accurately describing the attached storage. When we did away with the redundant revalidate pass, several cases were reported where devices reported nonsensical values or would end up in write-protected state.

An initial attempt at addressing this issue involved introducing a delayed second revalidate invocation. However, this approach still left some devices reporting incorrect characteristics.

Tasos Sahanidis debugged the problem further and identified that introducing a READ operation prior to MODE SENSE fixed the problem and that it wasn't a timing issue. Issuing a READ appears to cause the devices to update their state to reflect the actual properties of the storage media. Device properties like vendor, model, and storage capacity appear to be correctly reported from the get-go. It is unclear why these devices defer populating the remaining characteristics.

Match the behavior of a well known commercial operating system and trigger a READ operation prior to querying device characteristics to force the device to populate the mode pages.

The additional READ is triggered by a flag set in the USB storage and UAS drivers. We avoid issuing the READ for other transport classes since some storage devices identify Linux through our particular discovery command sequence.

---
 drivers/scsi/sd.c              | 26 +++++++++++++++++++++++++-
 drivers/usb/storage/scsiglue.c |  7 +++++++
 drivers/usb/storage/uas.c      |  7 +++++++
 include/scsi/scsi_device.h     |  1 +
 4 files changed, 40 insertions(+), 1 deletion(-)
drivers/scsi/sd.c +25 -1
index 31b5273f43a71..4433b02c8935f 100644
@@ -3284,6 +3284,24 @@ static bool sd_validate_opt_xfer_size(struct scsi_disk *sdkp,
 	return true;
 }
 
+static void sd_read_block_zero(struct scsi_disk *sdkp)
+{
+	unsigned int buf_len = sdkp->device->sector_size;
+	char *buffer, cmd[10] = { };
+
+	buffer = kmalloc(buf_len, GFP_KERNEL);
+	if (!buffer)
+		return;
+
+	cmd[0] = READ_10;
+	put_unaligned_be32(0, &cmd[2]); /* Logical block address 0 */
+	put_unaligned_be16(1, &cmd[7]);	/* Transfer 1 logical block */
+
+	scsi_execute_cmd(sdkp->device, cmd, REQ_OP_DRV_IN, buffer, buf_len,
+			 SD_TIMEOUT, sdkp->max_retries, NULL);
+	kfree(buffer);
+}
+
 /**
  *	sd_revalidate_disk - called the first time a new disk is seen,
  *	performs disk spin up, read_capacity, etc.
@@ -3323,7 +3341,13 @@ static int sd_revalidate_disk(struct gendisk *disk)
 	 */
 	if (sdkp->media_present) {
 		sd_read_capacity(sdkp, buffer);
-
+		/*
+		 * Some USB/UAS devices return generic values for mode pages
+		 * until the media has been accessed. Trigger a READ operation
+		 * to force the device to populate mode pages.
+		 */
+		if (sdp->read_before_ms)
+			sd_read_block_zero(sdkp);
 		/*
 		 * set the default to rotational.  All non-rotational devices
 		 * support the block characteristics VPD page, which will
drivers/usb/storage/scsiglue.c +7 -0
index c54e9805da536..12cf9940e5b67 100644
@@ -179,6 +179,13 @@ static int slave_configure(struct scsi_device *sdev)
 		 */
 		sdev->use_192_bytes_for_3f = 1;
 
+		/*
+		 * Some devices report generic values until the media has been
+		 * accessed. Force a READ(10) prior to querying device
+		 * characteristics.
+		 */
+		sdev->read_before_ms = 1;
+
 		/*
 		 * Some devices don't like MODE SENSE with page=0x3f,
 		 * which is the command used for checking if a device
drivers/usb/storage/uas.c +7 -0
index de3836412bf32..ed22053b3252f 100644
@@ -878,6 +878,13 @@ static int uas_slave_configure(struct scsi_device *sdev)
 	if (devinfo->flags & US_FL_CAPACITY_HEURISTICS)
 		sdev->guess_capacity = 1;
 
+	/*
+	 * Some devices report generic values until the media has been
+	 * accessed. Force a READ(10) prior to querying device
+	 * characteristics.
+	 */
+	sdev->read_before_ms = 1;
+
 	/*
 	 * Some devices don't like MODE SENSE with page=0x3f,
 	 * which is the command used for checking if a device
include/scsi/scsi_device.h +1 -0
index b407807cc6695..a64713fe52640 100644
@@ -204,6 +204,7 @@ struct scsi_device {
 	unsigned use_10_for_rw:1; /* first try 10-byte read / write */
 	unsigned use_10_for_ms:1; /* first try 10-byte mode sense/select */
 	unsigned set_dbd_for_ms:1; /* Set "DBD" field in mode sense */
+	unsigned read_before_ms:1;	/* perform a READ before MODE SENSE */
 	unsigned no_report_opcodes:1;	/* no REPORT SUPPORTED OPERATION CODES */
 	unsigned no_write_same:1;	/* no WRITE SAME command */
 	unsigned use_16_for_rw:1; /* Use read/write(16) over read/write(10) */
Signature · 1 line
2.43.0
author maintainer
#6 lore raw

PATCH 6/215 af_unix: Fix task hung while purging oob_skb in GC.

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kuniyuki Iwashima <[email protected]>

[ Upstream commit 25236c91b5ab4a26a56ba2e79b8060cf4e047839 ]

syzbot reported a task hung; at the same time, GC was looping infinitely in list_for_each_entry_safe() for OOB skb. [0]

syzbot demonstrated that the list_for_each_entry_safe() was not actually safe in this case.

A single skb could have references for multiple sockets. If we free such a skb in the list_for_each_entry_safe(), the current and next sockets could be unlinked in a single iteration.

unix_notinflight() uses list_del_init() to unlink the socket, so the prefetched next socket forms a loop itself and list_for_each_entry_safe() never stops.

Here, we must use while() and make sure we always fetch the first socket.

[0]:
Sending NMI from CPU 0 to CPUs 1:
NMI backtrace for cpu 1

CPU: 1 PID: 5065 Comm: syz-executor236 Not tainted 6.8.0-rc3-syzkaller-00136-g1f719a2f3fa6 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024
RIP: 0010:preempt_count arch/x86/include/asm/preempt.h:26 [inline]
RIP: 0010:check_kcov_mode kernel/kcov.c:173 [inline]
RIP: 0010:__sanitizer_cov_trace_pc+0xd/0x60 kernel/kcov.c:207
Code: cc cc cc cc 66 0f 1f 84 00 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 65 48 8b 14 25 40 c2 03 00 <65> 8b 05 b4 7c 78 7e a9 00 01 ff 00 48 8b 34 24 74 0f f6 c4 01 74
RSP: 0018:ffffc900033efa58 EFLAGS: 00000283
RAX: ffff88807b077800 RBX: ffff88807b077800 RCX: 1ffffffff27b1189
RDX: ffff88802a5a3b80 RSI: ffffffff8968488d RDI: ffff88807b077f70
RBP: ffffc900033efbb0 R08: 0000000000000001 R09: fffffbfff27a900c
R10: ffffffff93d48067 R11: ffffffff8ae000eb R12: ffff88807b077800
R13: dffffc0000000000 R14: ffff88807b077e40 R15: 0000000000000001
FS:  0000000000000000(0000) GS:ffff8880b9500000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000564f4fc1e3a8 CR3: 000000000d57a000 CR4: 00000000003506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <NMI>
 </NMI>
 <TASK>
 unix_gc+0x563/0x13b0 net/unix/garbage.c:319
 unix_release_sock+0xa93/0xf80 net/unix/af_unix.c:683
 unix_release+0x91/0xf0 net/unix/af_unix.c:1064
 __sock_release+0xb0/0x270 net/socket.c:659
 sock_close+0x1c/0x30 net/socket.c:1421
 __fput+0x270/0xb80 fs/file_table.c:376
 task_work_run+0x14f/0x250 kernel/task_work.c:180
 exit_task_work include/linux/task_work.h:38 [inline]
 do_exit+0xa8a/0x2ad0 kernel/exit.c:871
 do_group_exit+0xd4/0x2a0 kernel/exit.c:1020
 __do_sys_exit_group kernel/exit.c:1031 [inline]
 __se_sys_exit_group kernel/exit.c:1029 [inline]
 __x64_sys_exit_group+0x3e/0x50 kernel/exit.c:1029
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xd5/0x270 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x6f/0x77
RIP: 0033:0x7f9d6cbdac09
Code: Unable to access opcode bytes at 0x7f9d6cbdabdf.
RSP: 002b:00007fff5952feb8 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9d6cbdac09
RDX: 000000000000003c RSI: 00000000000000e7 RDI: 0000000000000000
RBP: 00007f9d6cc552b0 R08: ffffffffffffffb8 R09: 0000000000000006
R10: 0000000000000006 R11: 0000000000000246 R12: 00007f9d6cc552b0
R13: 0000000000000000 R14: 00007f9d6cc55d00 R15: 00007f9d6cbabe70
 </TASK>
---
 net/unix/garbage.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)
net/unix/garbage.c +4 -3
index 767b338a7a2d4..9e1bab97c05ba 100644
@@ -315,10 +315,11 @@ void unix_gc(void)
 	__skb_queue_purge(&hitlist);
 
 #if IS_ENABLED(CONFIG_AF_UNIX_OOB)
-	list_for_each_entry_safe(u, next, &gc_candidates, link) {
-		struct sk_buff *skb = u->oob_skb;
+	while (!list_empty(&gc_candidates)) {
+		u = list_entry(gc_candidates.next, struct unix_sock, link);
+		if (u->oob_skb) {
+			struct sk_buff *skb = u->oob_skb;
 
-		if (skb) {
 			u->oob_skb = NULL;
 			kfree_skb(skb);
 		}
Signature · 1 line
2.43.0
author maintainer
#7 lore raw

PATCH 7/215 of: overlay: Reorder struct fragment fields kerneldoc

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Geert Uytterhoeven <[email protected]>

[ Upstream commit 5d007ffdf6025fe83e497c44ed7c8aa8f150c4d1 ]

The fields of the fragment structure were reordered, but the kerneldoc was not updated.

---
 drivers/of/overlay.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/of/overlay.c +1 -1
index 4402871b5c0c0..e663d5585a057 100644
@@ -45,8 +45,8 @@ struct target {
 
 /**
  * struct fragment - info about fragment nodes in overlay expanded device tree
- * @target:	target of the overlay operation
  * @overlay:	pointer to the __overlay__ node
+ * @target:	target of the overlay operation
  */
 struct fragment {
 	struct device_node *overlay;
Signature · 1 line
2.43.0
author maintainer
#8 lore raw

PATCH 8/215 net: restore alpha order to Ethernet devices in config

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Bjorn Helgaas <[email protected]>

[ Upstream commit a1331535aeb41b08fe0c2c78af51885edc93615b ]

The filename "wangxun" sorts between "intel" and "xscale", but xscale/Kconfig contains "Intel XScale" prompts, so Wangxun ends up in the wrong place in the config front-ends.

Move wangxun/Kconfig so the Wangxun devices appear in order in the user interface.

Fixes 3ce7547e5b71 ("net: txgbe: Add build support for txgbe")
---
 drivers/net/ethernet/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/Kconfig +1 -1
index 1917da7841919..5a274b99f2992 100644
@@ -84,7 +84,6 @@ source "drivers/net/ethernet/huawei/Kconfig"
 source "drivers/net/ethernet/i825xx/Kconfig"
 source "drivers/net/ethernet/ibm/Kconfig"
 source "drivers/net/ethernet/intel/Kconfig"
-source "drivers/net/ethernet/wangxun/Kconfig"
 source "drivers/net/ethernet/xscale/Kconfig"
 
 config JME
@@ -189,6 +188,7 @@ source "drivers/net/ethernet/toshiba/Kconfig"
 source "drivers/net/ethernet/tundra/Kconfig"
 source "drivers/net/ethernet/vertexcom/Kconfig"
 source "drivers/net/ethernet/via/Kconfig"
+source "drivers/net/ethernet/wangxun/Kconfig"
 source "drivers/net/ethernet/wiznet/Kconfig"
 source "drivers/net/ethernet/xilinx/Kconfig"
 source "drivers/net/ethernet/xircom/Kconfig"
Signature · 1 line
2.43.0
author maintainer
#9 lore raw

PATCH 9/215 mlxsw: spectrum_acl_tcam: Make fini symmetric to init

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ido Schimmel <[email protected]>

[ Upstream commit 61fe3b9102ac84ba479ab84d8f5454af2e21e468 ]

Move mutex_destroy() to the end to make the function symmetric with mlxsw_sp_acl_tcam_init(). No functional changes.

---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +1 -1
index dc2e204bcd727..2107de4e9d99b 100644
@@ -86,10 +86,10 @@ void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp,
 {
 	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 
-	mutex_destroy(&tcam->lock);
 	ops->fini(mlxsw_sp, tcam->priv);
 	bitmap_free(tcam->used_groups);
 	bitmap_free(tcam->used_regions);
+	mutex_destroy(&tcam->lock);
 }
 
 int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp,
Signature · 1 line
2.43.0

Greg Kroah-Hartman

author maintainer
#0 lore raw

cover 6.1.81-rc1 review

This is the start of the stable review cycle for the 6.1.81 release. There are 215 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Wed, 06 Mar 2024 21:15:26 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

	https://www.kernel.org/pub/linux/kernel/v6.x/stable-review/patch-6.1.81-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-6.1.y
and the diffstat can be found below.

thanks,

greg k-h

-------------
Pseudo-Shortlog of commits:

Greg Kroah-Hartman <[email protected]>

    Linux 6.1.81-rc1

Maximilian Heyne <[email protected]>
xen/events: close evtchn after mapping cleanup

Ard Biesheuvel <[email protected]>
x86/efistub: Give up if memory attribute protocol returns an error

Martynas Pumputis <[email protected]>
bpf: Derive source IP addr via bpf_*_fib_lookup()

Louis DeLosSantos <[email protected]>
bpf: Add table ID to bpf_fib_lookup BPF helper

Pawan Gupta <[email protected]>
KVM/VMX: Move VERW closer to VMentry for MDS mitigation

Pawan Gupta <[email protected]>
KVM/VMX: Use BT+JNC, i.e. EFLAGS.CF to select VMRESUME vs. VMLAUNCH

Pawan Gupta <[email protected]>
x86/bugs: Use ALTERNATIVE() instead of mds_user_clear static key

Pawan Gupta <[email protected]>
x86/entry_32: Add VERW just before userspace transition

Pawan Gupta <[email protected]>
x86/entry_64: Add VERW just before userspace transition

Pawan Gupta <[email protected]>
x86/bugs: Add asm helpers for executing VERW

Greg Kroah-Hartman <[email protected]>
Revert "interconnect: Teach lockdep about icc_bw_lock order"

Greg Kroah-Hartman <[email protected]>
Revert "interconnect: Fix locking for runpm vs reclaim"

Ming Lei <[email protected]>
block: define bvec_iter as __packed __aligned(4)

Bartosz Golaszewski <[email protected]>
gpio: fix resource unwinding order in error path

Andy Shevchenko <[email protected]>
gpiolib: Fix the error path order in gpiochip_add_data_with_key()

Arturas Moskvinas <[email protected]>
gpio: 74x164: Enable output pins after registers are reset

Gaurav Batra <[email protected]>
powerpc/pseries/iommu: IOMMU table is not initialized for kdump over SR-IOV

Alexander Stein <[email protected]>
phy: freescale: phy-fsl-imx8-mipi-dphy: Fix alias name to use dashes

Kuniyuki Iwashima <[email protected]>
af_unix: Drop oob_skb ref before purging queue in GC.

Ard Biesheuvel <[email protected]>

    efi/x86: Fix the missing KASLR_FLAG bit in boot_params->hdr.loadflags

Ard Biesheuvel <[email protected]>
x86/boot: efistub: Assign global boot_params variable

Ard Biesheuvel <[email protected]>
x86/boot: Rename conflicting 'boot_params' pointer to 'boot_params_ptr'

Ard Biesheuvel <[email protected]>
x86/efistub: Avoid placing the kernel below LOAD_PHYSICAL_ADDR

Ard Biesheuvel <[email protected]>
efi/x86: Avoid physical KASLR on older Dell systems

Ard Biesheuvel <[email protected]>
x86/efistub: Avoid legacy decompressor when doing EFI boot

Ard Biesheuvel <[email protected]>
x86/efistub: Perform SNP feature test while running in the firmware

Ard Biesheuvel <[email protected]>
x86/efistub: Prefer EFI memory attributes protocol over DXE services

Ard Biesheuvel <[email protected]>
x86/decompressor: Factor out kernel decompression and relocation

Ard Biesheuvel <[email protected]>
x86/efistub: Perform 4/5 level paging switch from the stub

Ard Biesheuvel <[email protected]>
efi/libstub: Add limit argument to efi_random_alloc()

Ard Biesheuvel <[email protected]>
efi/libstub: Add memory attribute protocol definitions

Ard Biesheuvel <[email protected]>
x86/efistub: Clear BSS in EFI handover protocol entrypoint

Ard Biesheuvel <[email protected]>
x86/decompressor: Avoid magic offsets for EFI handover entrypoint

Ard Biesheuvel <[email protected]>
x86/efistub: Simplify and clean up handover entry code

Ard Biesheuvel <[email protected]>
efi: efivars: prevent double registration

Ard Biesheuvel <[email protected]>
arm64: efi: Limit allocations to 48-bit addressable physical region

Jeff Layton <[email protected]>
nfsd: don't destroy global nfs4_file table in per-net shutdown

Dai Ngo <[email protected]>
NFSD: replace delayed_work with work_struct for nfsd_client_shrinker

Dai Ngo <[email protected]>
NFSD: register/unregister of nfsd-client shrinker at nfsd startup/shutdown time

Chuck Lever <[email protected]>
NFSD: Use set_bit(RQ_DROPME)

Kees Cook <[email protected]>
NFSD: Avoid clashing function prototypes

Chuck Lever <[email protected]>
NFSD: Use only RQ_DROPME to signal the need to drop a reply

Dai Ngo <[email protected]>
NFSD: add CB_RECALL_ANY tracepoints

Dai Ngo <[email protected]>
NFSD: add delegation reaper to react to low memory condition

Dai Ngo <[email protected]>
NFSD: add support for sending CB_RECALL_ANY

Dai Ngo <[email protected]>
NFSD: refactoring courtesy_client_reaper to a generic low memory shrinker

Chuck Lever <[email protected]>
trace: Relocate event helper files

Jeff Layton <[email protected]>
lockd: fix file selection in nlmsvc_cancel_blocked

Jeff Layton <[email protected]>
lockd: ensure we use the correct file descriptor when unlocking

Jeff Layton <[email protected]>
lockd: set missing fl_flags field when retrieving args

Xiu Jianfeng <[email protected]>
NFSD: Use struct_size() helper in alloc_session()

Jeff Layton <[email protected]>
nfsd: fix up the filecache laundrette scheduling

Jeff Layton <[email protected]>
nfsd: use locks_inode_context helper

Jeff Layton <[email protected]>
lockd: use locks_inode_context helper

Jeff Layton <[email protected]>
filelock: add a new locks_inode_context accessor function

Chuck Lever <[email protected]>
NFSD: Fix licensing header in filecache.c

Chuck Lever <[email protected]>
NFSD: Use rhashtable for managing nfs4_file objects

Chuck Lever <[email protected]>
NFSD: Refactor find_file()

Chuck Lever <[email protected]>
NFSD: Clean up find_or_add_file()

Chuck Lever <[email protected]>
NFSD: Add a nfsd4_file_hash_remove() helper

Chuck Lever <[email protected]>
NFSD: Clean up nfsd4_init_file()

Chuck Lever <[email protected]>
NFSD: Update file_hashtbl() helpers

Chuck Lever <[email protected]>
NFSD: Use const pointers as parameters to fh_ helpers

Chuck Lever <[email protected]>
NFSD: Trace delegation revocations

Chuck Lever <[email protected]>
NFSD: Trace stateids returned via DELEGRETURN

Chuck Lever <[email protected]>
NFSD: Clean up nfs4_preprocess_stateid_op() call sites

Chuck Lever <[email protected]>
NFSD: Flesh out a documenting comment for filecache.c

David Disseldorp <[email protected]>
exportfs: use pr_debug for unreachable debug statements

Jeff Layton <[email protected]>
nfsd: allow disabling NFSv2 at compile time

Jeff Layton <[email protected]>
nfsd: move nfserrno() to vfs.c

Jeff Layton <[email protected]>
nfsd: ignore requests to disable unsupported versions

Colin Ian King <[email protected]>
NFSD: Remove redundant assignment to variable host_err

Anna Schumaker <[email protected]>
NFSD: Simplify READ_PLUS

NeilBrown <[email protected]>
NFS: Fix data corruption caused by congestion.

Alex Deucher <[email protected]>
drm/amd/display: Increase frame warning limit with KASAN or KCSAN in dml

Ard Biesheuvel <[email protected]>
decompress: Use 8 byte alignment

Ard Biesheuvel <[email protected]>
x86/decompressor: Move global symbol references to C code

Ard Biesheuvel <[email protected]>
x86/decompressor: Merge trampoline cleanup with switching code

Ard Biesheuvel <[email protected]>
x86/decompressor: Pass pgtable address to trampoline directly

Ard Biesheuvel <[email protected]>
x86/decompressor: Only call the trampoline when changing paging levels

Ard Biesheuvel <[email protected]>
x86/decompressor: Call trampoline directly from C code

Ard Biesheuvel <[email protected]>
x86/decompressor: Avoid the need for a stack in the 32-bit trampoline

Ard Biesheuvel <[email protected]>
x86/decompressor: Use standard calling convention for trampoline

Ard Biesheuvel <[email protected]>
x86/decompressor: Call trampoline as a normal function

Ard Biesheuvel <[email protected]>
x86/decompressor: Assign paging related global variables earlier

Ard Biesheuvel <[email protected]>
x86/decompressor: Store boot_params pointer in callee save register

Ard Biesheuvel <[email protected]>
x86/efistub: Branch straight to kernel entry point from C code

Alexander Lobakin <[email protected]>
x86/boot: Robustify calling startup_{32,64}() from the decompressor code

Ard Biesheuvel <[email protected]>
x86/efi: Make the deprecated EFI handover protocol optional

Johan Hovold <[email protected]>
efi: verify that variable services are supported

Ard Biesheuvel <[email protected]>
x86/boot/compressed: Only build mem_encrypt.S if AMD_MEM_ENCRYPT=y

Ard Biesheuvel <[email protected]>
x86/boot/compressed: Adhere to calling convention in get_sev_encryption_bit()

Ard Biesheuvel <[email protected]>
x86/boot/compressed: Move startup32_check_sev_cbit() out of head_64.S

Ard Biesheuvel <[email protected]>
x86/boot/compressed: Move startup32_check_sev_cbit() into .text

Ard Biesheuvel <[email protected]>
x86/boot/compressed: Move startup32_load_idt() out of head_64.S

Ard Biesheuvel <[email protected]>
x86/boot/compressed: Move startup32_load_idt() into .text section

Ard Biesheuvel <[email protected]>
x86/boot/compressed: Pull global variable reference into startup32_load_idt()

Ard Biesheuvel <[email protected]>
x86/boot/compressed: Avoid touching ECX in startup32_set_idt_entry()

Ard Biesheuvel <[email protected]>
x86/boot/compressed: Simplify IDT/GDT preserve/restore in the EFI thunk

Ard Biesheuvel <[email protected]>
x86/boot/compressed, efi: Merge multiple definitions of image_offset into one

Ard Biesheuvel <[email protected]>

    x86/boot/compressed: Move efi32_pe_entry() out of head_64.S

Ard Biesheuvel <[email protected]>
x86/boot/compressed: Move efi32_entry out of head_64.S

Ard Biesheuvel <[email protected]>
x86/boot/compressed: Move efi32_pe_entry into .text section

Ard Biesheuvel <[email protected]>
x86/boot/compressed: Move bootargs parsing out of 32-bit startup code

Ard Biesheuvel <[email protected]>
x86/boot/compressed: Move 32-bit entrypoint code into .text section

Ard Biesheuvel <[email protected]>
x86/boot/compressed: Rename efi_thunk_64.S to efi-mixed.S

Ard Biesheuvel <[email protected]>
efi: libstub: use EFI_LOADER_CODE region when moving the kernel in memory

Shiraz Saleem <[email protected]>
RDMA/core: Update CMA destination address on rdma_resolve_addr

Patrisious Haddad <[email protected]>
RDMA/core: Refactor rdma_bind_addr

Paolo Abeni <[email protected]>
mptcp: fix possible deadlock in subflow diag

Davide Caratti <[email protected]>
mptcp: fix double-free on socket dismantle

Paolo Abeni <[email protected]>
mptcp: fix snd_wnd initialization for passive socket

Geliang Tang <[email protected]>
selftests: mptcp: join: add ss mptcp support check

Paolo Abeni <[email protected]>
mptcp: push at DSS boundaries

Geliang Tang <[email protected]>
mptcp: map v4 address to v6 when destroying subflow

Matthieu Baerts (NGI0) <[email protected]>
mptcp: continue marking the first subflow as UNCONNECTED

Paolo Abeni <[email protected]>
mptcp: fix duplicate subflow creation

Paolo Abeni <[email protected]>
mptcp: fix data races on remote_id

Paolo Abeni <[email protected]>
mptcp: fix data races on local_id

Paolo Bonzini <[email protected]>
x86/cpu/intel: Detect TME keyid bits before setting MTRR mask registers

Jiri Bohac <[email protected]>

    x86/e820: Don't reserve SETUP_RNG_SEED in e820

Bjorn Andersson <[email protected]>
pmdomain: qcom: rpmhpd: Fix enabled_corner aggregation

Tim Schumacher <[email protected]>
efivarfs: Request at most 512 bytes for variable names

Zong Li <[email protected]>
riscv: add CALLER_ADDRx support

Elad Nachman <[email protected]>
mmc: sdhci-xenon: fix PHY init clock stability

Elad Nachman <[email protected]>
mmc: sdhci-xenon: add timeout for PHY init complete

Ivan Semenov <[email protected]>
mmc: core: Fix eMMC initialization with 1-bit bus connection

Christophe Kerello <[email protected]>
mmc: mmci: stm32: fix DMA API overlapping mappings warning

Curtis Klein <[email protected]>
dmaengine: fsl-qdma: init irq after reg initialization

Tadeusz Struk <[email protected]>
dmaengine: ptdma: use consistent DMA masks

Ard Biesheuvel <[email protected]>
crypto: arm64/neonbs - fix out-of-bounds access on short input

Peng Ma <[email protected]>
dmaengine: fsl-qdma: fix SoC may hang on 16 byte unaligned read

Matthew Auld <[email protected]>
drm/buddy: fix range bias

Alex Deucher <[email protected]>
Revert "drm/amd/pm: resolve reboot exception for si oland"

Filipe Manana <[email protected]>
btrfs: send: don't issue unnecessary zero writes for trailing hole

David Sterba <[email protected]>
btrfs: dev-replace: properly validate device names

Filipe Manana <[email protected]>
btrfs: fix double free of anonymous device after snapshot creation failure

Johannes Berg <[email protected]>
wifi: nl80211: reject iftype change with mesh ID change

Alexander Ofitserov <[email protected]>
gtp: fix use-after-free and null-ptr-deref in gtp_newlink()

Mickaël Salaün <[email protected]>
landlock: Fix asymmetric private inodes referring

Eniac Zhang <[email protected]>
ALSA: hda/realtek: fix mute/micmute LED For HP mt440

Hans Peter <[email protected]>
ALSA: hda/realtek: Enable Mute LED on HP 840 G8 (MB 8AB8)

Takashi Sakamoto <[email protected]>
ALSA: firewire-lib: fix to check cycle continuity

Tetsuo Handa <[email protected]>
tomoyo: fix UAF write bug in tomoyo_write_control()

Saravana Kannan <[email protected]>
of: property: fw_devlink: Fix stupid bug in remote-endpoint parsing

Dimitris Vlachos <[email protected]>
riscv: Sparse-Memory/vmemmap out-of-bounds fix

David Howells <[email protected]>
afs: Fix endless loop in directory parsing

Jiri Slaby (SUSE) <[email protected]>
fbcon: always restore the old font data in fbcon_do_set_font()

Thierry Reding <[email protected]>
drm/tegra: Remove existing framebuffer only if we support display

Takashi Iwai <[email protected]>
ALSA: Drop leftover snd-rtctimer stuff from Makefile

Hans de Goede <[email protected]>
power: supply: bq27xxx-i2c: Do not free non existing IRQ

Arnd Bergmann <[email protected]>
efi/capsule-loader: fix incorrect allocation size

Sabrina Dubroca <[email protected]>
tls: fix peeking with sync+async decryption

Sabrina Dubroca <[email protected]>
tls: decrement decrypt_pending if no async completion will be called

Lukasz Majewski <[email protected]>
net: hsr: Use correct offset for HSR TLV values in supervisory HSR frames

Oleksij Rempel <[email protected]>
igb: extend PTP timestamp adjustments to i211

Lin Ma <[email protected]>
rtnetlink: fix error logic of IFLA_BRIDGE_FLAGS writing back

Florian Westphal <[email protected]>
netfilter: bridge: confirm multicast packets before passing them up the stack

Florian Westphal <[email protected]>
netfilter: let reset rules clean out conntrack entries

Ignat Korchagin <[email protected]>
netfilter: nf_tables: allow NFPROTO_INET in nft_(match/target)_validate()

Janaki Ramaiah Thota <[email protected]>
Bluetooth: hci_qca: Set BDA quirk bit if fwnode exists in DT

Neil Armstrong <[email protected]>
Bluetooth: qca: add support for WCN7850

Neil Armstrong <[email protected]>
Bluetooth: qca: use switch case for soc type behavior

Luca Weiss <[email protected]>
Bluetooth: btqca: Add WCN3988 support

Min-Hua Chen <[email protected]>
Bluetooth: btqca: use le32_to_cpu for ver.soc_id

Steev Klimaszewski <[email protected]>
Bluetooth: hci_qca: Add support for QTI Bluetooth chip wcn6855

Krzysztof Kozlowski <[email protected]>
Bluetooth: hci_qca: mark OF related data as maybe unused

Zijun Hu <[email protected]>
Bluetooth: qca: Fix wrong event type for patch config command

Kai-Heng Feng <[email protected]>
Bluetooth: Enforce validation on max value of connection interval

Luiz Augusto von Dentz <[email protected]>
Bluetooth: hci_event: Fix handling of HCI_EV_IO_CAPA_REQUEST

Zijun Hu <[email protected]>
Bluetooth: hci_event: Fix wrongly recorded wakeup BD_ADDR

Luiz Augusto von Dentz <[email protected]>
Bluetooth: hci_sync: Fix accept_list when attempting to suspend

Ying Hsu <[email protected]>
Bluetooth: Avoid potential use-after-free in hci_error_reset

Jonas Dreßler <[email protected]>
Bluetooth: hci_sync: Check the correct flag before starting a scan

Jakub Raczynski <[email protected]>
stmmac: Clear variable when destroying workqueue

Justin Iurman <[email protected]>
uapi: in6: replace temporary label with rfc9486

Oleksij Rempel <[email protected]>
net: lan78xx: fix "softirq work is pending" error

Javier Carrasco <[email protected]>
net: usb: dm9601: fix wrong return value in dm9601_mdio_read

Jakub Kicinski <[email protected]>
veth: try harder when allocating queue memory

Oleksij Rempel <[email protected]>
lan78xx: enable auto speed configuration for LAN7850 if no EEPROM is detected

Eric Dumazet <[email protected]>
ipv6: fix potential "struct net" leak in inet6_rtm_getaddr()

Jakub Kicinski <[email protected]>
net: veth: clear GRO when clearing XDP even when down

Doug Smythies <[email protected]>
cpufreq: intel_pstate: fix pstate limits enforcement for adjust_perf call back

Yunjian Wang <[email protected]>
tun: Fix xdp_rxq_info's queue_index when detaching

Jeremy Kerr <[email protected]>
net: mctp: take ownership of skb in mctp_local_output

Florian Westphal <[email protected]>
net: ip_tunnel: prevent perpetual headroom growth

Florian Westphal <[email protected]>
netlink: add nla be16/32 types to minlen array

Ryosuke Yasuoka <[email protected]>
netlink: Fix kernel-infoleak-after-free in __skb_datagram_iter

Han Xu <[email protected]>
mtd: spinand: gigadevice: Fix the get ecc status issue

Yang Shi <[email protected]>
mm: huge_memory: don't force huge page alignment on 32 bit

Gustavo A. R. Silva <[email protected]>
RDMA/core: Fix multiple -Warray-bounds warnings

Manivannan Sadhasivam <[email protected]>
iommu/arm-smmu-qcom: Limit the SMR groups to 128

Ye Bin <[email protected]>
fs/ntfs3: Fix NULL pointer dereference in 'ni_write_inode'

Abdun Nihaal <[email protected]>
fs/ntfs3: Fix NULL dereference in ni_write_inode

Edward Lo <[email protected]>
fs/ntfs3: Add length check in indx_get_root

Arnd Bergmann <[email protected]>
clk: tegra20: fix gcc-7 constant overflow warning

Jia-Ju Bai <[email protected]>
fs/ntfs3: Fix a possible null-pointer dereference in ni_clear()

Tomas Krcka <[email protected]>
iommu/arm-smmu-v3: Acknowledge pri/event queue overflow if any

Chunyan Zhang <[email protected]>
iommu/sprd: Release dma buffer to avoid memory leak

Vicki Pfau <[email protected]>
Input: xpad - add constants for GIP interface numbers

Elson Roy Serrao <[email protected]>
usb: gadget: Properly configure the device for remote wakeup

Marek Vasut <[email protected]>
ARM: dts: imx7s: Drop dma-apb interrupt-names

Stefan Wahren <[email protected]>
ARM: dts: imx: Adjust dma-apbh node name

Xiaowei Bao <[email protected]>
PCI: layerscape: Add workaround for lost link capabilities during reset

Frank Li <[email protected]>
PCI: layerscape: Add the endpoint linkup notifier support

Ido Schimmel <[email protected]>
mlxsw: spectrum_acl_tcam: Add missing mutex_destroy()

Ido Schimmel <[email protected]>
mlxsw: spectrum_acl_tcam: Make fini symmetric to init

Bjorn Helgaas <[email protected]>
net: restore alpha order to Ethernet devices in config

Geert Uytterhoeven <[email protected]>
of: overlay: Reorder struct fragment fields kerneldoc

Kuniyuki Iwashima <[email protected]>
af_unix: Fix task hung while purging oob_skb in GC.

Martin K. Petersen <[email protected]>
scsi: sd: usb_storage: uas: Access media prior to querying device properties

Mike Christie <[email protected]>
scsi: core: Add struct for args to execution functions

Martin Blumenstingl <[email protected]>
drm/meson: Don't remove bridges which are created by other drivers

Neil Armstrong <[email protected]>
drm/meson: fix unbind path if HDMI fails to bind

Pablo Neira Ayuso <[email protected]>
netfilter: nf_tables: disallow timeout for anonymous sets

-------------

Diffstat:

 Documentation/x86/boot.rst                         |   2 +-
 Documentation/x86/mds.rst                          |  34 +-
 MAINTAINERS                                        |   7 +
 Makefile                                           |   4 +-
 arch/arm/boot/dts/imx23.dtsi                       |   2 +-
 arch/arm/boot/dts/imx28.dtsi                       |   2 +-
 arch/arm/boot/dts/imx6qdl.dtsi                     |   2 +-
 arch/arm/boot/dts/imx6sx.dtsi                      |   2 +-
 arch/arm/boot/dts/imx6ul.dtsi                      |   2 +-
 arch/arm/boot/dts/imx7s.dtsi                       |   3 +-
 arch/arm64/crypto/aes-neonbs-glue.c                |  11 +
 arch/arm64/include/asm/efi.h                       |   1 +
 arch/powerpc/platforms/pseries/iommu.c             | 156 +++--
 arch/riscv/include/asm/ftrace.h                    |   5 +
 arch/riscv/include/asm/pgtable.h                   |   2 +-
 arch/riscv/kernel/Makefile                         |   2 +
 arch/riscv/kernel/return_address.c                 |  48 ++
 arch/x86/Kconfig                                   |  17 +
 arch/x86/boot/compressed/Makefile                  |  13 +-
 arch/x86/boot/compressed/acpi.c                    |  14 +-
 arch/x86/boot/compressed/cmdline.c                 |   4 +-
 arch/x86/boot/compressed/efi_mixed.S               | 328 +++++++++
 arch/x86/boot/compressed/efi_thunk_64.S            | 195 ------
 arch/x86/boot/compressed/head_32.S                 |  38 +-
 arch/x86/boot/compressed/head_64.S                 | 593 +++-------------
 arch/x86/boot/compressed/ident_map_64.c            |   7 +-
 arch/x86/boot/compressed/kaslr.c                   |  26 +-
 arch/x86/boot/compressed/mem_encrypt.S             | 152 +++-
 arch/x86/boot/compressed/misc.c                    |  85 ++-
 arch/x86/boot/compressed/misc.h                    |   3 -
 arch/x86/boot/compressed/pgtable.h                 |  10 +-
 arch/x86/boot/compressed/pgtable_64.c              |  94 ++-
 arch/x86/boot/compressed/sev.c                     | 114 +--
 arch/x86/boot/header.S                             |   2 +-
 arch/x86/boot/tools/build.c                        |   2 +
 arch/x86/entry/entry.S                             |  23 +
 arch/x86/entry/entry_32.S                          |   3 +
 arch/x86/entry/entry_64.S                          |  11 +
 arch/x86/entry/entry_64_compat.S                   |   1 +
 arch/x86/include/asm/boot.h                        |  10 +
 arch/x86/include/asm/cpufeatures.h                 |   2 +-
 arch/x86/include/asm/efi.h                         |  14 +-
 arch/x86/include/asm/entry-common.h                |   1 -
 arch/x86/include/asm/nospec-branch.h               |  27 +-
 arch/x86/include/asm/sev.h                         |   7 +
 arch/x86/kernel/cpu/bugs.c                         |  15 +-
 arch/x86/kernel/cpu/intel.c                        | 178 ++---
 arch/x86/kernel/e820.c                             |   8 +-
 arch/x86/kernel/nmi.c                              |   3 -
 arch/x86/kvm/vmx/run_flags.h                       |   7 +-
 arch/x86/kvm/vmx/vmenter.S                         |   9 +-
 arch/x86/kvm/vmx/vmx.c                             |  12 +-
 drivers/bluetooth/btqca.c                          | 104 ++-
 drivers/bluetooth/btqca.h                          |  23 +-
 drivers/bluetooth/hci_qca.c                        | 310 +++++++--
 drivers/clk/tegra/clk-tegra20.c                    |  26 +-
 drivers/cpufreq/intel_pstate.c                     |   3 +
 drivers/dma/fsl-qdma.c                             |  25 +-
 drivers/dma/ptdma/ptdma-dmaengine.c                |   2 -
 drivers/firmware/efi/capsule-loader.c              |   2 +-
 drivers/firmware/efi/efi.c                         |  22 +
 drivers/firmware/efi/libstub/Makefile              |   1 +
 drivers/firmware/efi/libstub/alignedmem.c          |   7 +-
 drivers/firmware/efi/libstub/arm64-stub.c          |  11 +-
 drivers/firmware/efi/libstub/efi-stub-helper.c     |   2 +
 drivers/firmware/efi/libstub/efistub.h             |  32 +-
 drivers/firmware/efi/libstub/mem.c                 |   5 +-
 drivers/firmware/efi/libstub/randomalloc.c         |  17 +-
 drivers/firmware/efi/libstub/x86-5lvl.c            |  95 +++
 drivers/firmware/efi/libstub/x86-stub.c            | 319 +++++----
 drivers/firmware/efi/libstub/x86-stub.h            |  17 +
 drivers/firmware/efi/vars.c                        |  13 +-
 drivers/gpio/gpio-74x164.c                         |   4 +-
 drivers/gpio/gpiolib.c                             |  12 +-
 drivers/gpu/drm/amd/display/dc/dml/Makefile        |   4 +
 drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c         |  29 +
 drivers/gpu/drm/drm_buddy.c                        |  10 +
 drivers/gpu/drm/meson/meson_drv.c                  |  23 +-
 drivers/gpu/drm/meson/meson_encoder_cvbs.c         |   1 -
 drivers/gpu/drm/meson/meson_encoder_hdmi.c         |   1 -
 drivers/gpu/drm/tegra/drm.c                        |  23 +-
 drivers/infiniband/core/cm_trace.h                 |   2 +-
 drivers/infiniband/core/cma.c                      | 255 +++----
 drivers/infiniband/core/cma_trace.h                |   2 +-
 drivers/infiniband/core/user_mad.c                 |  23 +-
 drivers/input/joystick/xpad.c                      |   5 +-
 drivers/interconnect/core.c                        |  18 +-
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c        |  19 +-
 drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c         |  16 +-
 drivers/iommu/sprd-iommu.c                         |  29 +-
 drivers/mmc/core/mmc.c                             |   2 +
 drivers/mmc/host/mmci_stm32_sdmmc.c                |  24 +
 drivers/mmc/host/sdhci-xenon-phy.c                 |  48 +-
 drivers/mtd/nand/spi/gigadevice.c                  |   6 +-
 drivers/net/ethernet/Kconfig                       |   2 +-
 drivers/net/ethernet/intel/igb/igb_ptp.c           |   5 +-
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.c    |  10 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c  |   4 +-
 drivers/net/gtp.c                                  |  12 +-
 drivers/net/tun.c                                  |   1 +
 drivers/net/usb/dm9601.c                           |   2 +-
 drivers/net/usb/lan78xx.c                          |   5 +-
 drivers/net/veth.c                                 |  40 +-
 drivers/of/overlay.c                               |   2 +-
 drivers/of/property.c                              |   2 +-
 drivers/pci/controller/dwc/pci-layerscape-ep.c     | 119 +++-
 drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c     |   2 +-
 drivers/power/supply/bq27xxx_battery_i2c.c         |   4 +-
 drivers/scsi/scsi_lib.c                            |  52 +-
 drivers/scsi/sd.c                                  |  26 +-
 drivers/soc/qcom/rpmhpd.c                          |   7 +-
 drivers/usb/gadget/composite.c                     |  18 +
 drivers/usb/gadget/configfs.c                      |   3 +
 drivers/usb/gadget/udc/core.c                      |  27 +
 drivers/usb/gadget/udc/trace.h                     |   5 +
 drivers/usb/storage/scsiglue.c                     |   7 +
 drivers/usb/storage/uas.c                          |   7 +
 drivers/video/fbdev/core/fbcon.c                   |   8 +-
 drivers/xen/events/events_base.c                   |   5 +-
 fs/afs/dir.c                                       |   4 +-
 fs/btrfs/dev-replace.c                             |  24 +-
 fs/btrfs/disk-io.c                                 |  22 +-
 fs/btrfs/disk-io.h                                 |   2 +-
 fs/btrfs/ioctl.c                                   |   2 +-
 fs/btrfs/send.c                                    |  17 +-
 fs/btrfs/transaction.c                             |   2 +-
 fs/efivarfs/vars.c                                 |  17 +-
 fs/exportfs/expfs.c                                |   8 +-
 fs/lockd/svc4proc.c                                |   1 +
 fs/lockd/svclock.c                                 |  17 +-
 fs/lockd/svcproc.c                                 |   1 +
 fs/lockd/svcsubs.c                                 |   4 +-
 fs/locks.c                                         |  24 +-
 fs/nfs/nfs4trace.h                                 |   6 +-
 fs/nfs/nfstrace.h                                  |   6 +-
 fs/nfs/write.c                                     |   4 +-
 fs/nfsd/Kconfig                                    |  19 +-
 fs/nfsd/Makefile                                   |   5 +-
 fs/nfsd/blocklayout.c                              |   1 +
 fs/nfsd/blocklayoutxdr.c                           |   1 +
 fs/nfsd/export.h                                   |   1 -
 fs/nfsd/filecache.c                                |  39 +-
 fs/nfsd/flexfilelayout.c                           |   1 +
 fs/nfsd/netns.h                                    |   2 +-
 fs/nfsd/nfs4callback.c                             |  72 ++
 fs/nfsd/nfs4idmap.c                                |   1 +
 fs/nfsd/nfs4proc.c                                 |  31 +-
 fs/nfsd/nfs4state.c                                | 316 ++++++---
 fs/nfsd/nfs4xdr.c                                  | 771 +++++++++++----------
 fs/nfsd/nfsctl.c                                   |  13 +-
 fs/nfsd/nfsd.h                                     |   9 +-
 fs/nfsd/nfsfh.h                                    |  10 +-
 fs/nfsd/nfsproc.c                                  |  66 +-
 fs/nfsd/nfssvc.c                                   |   8 +-
 fs/nfsd/state.h                                    |  11 +-
 fs/nfsd/trace.h                                    | 106 +++
 fs/nfsd/vfs.c                                      |  64 +-
 fs/nfsd/vfs.h                                      |   1 +
 fs/nfsd/xdr4.h                                     |   5 +
 fs/nfsd/xdr4cb.h                                   |   6 +
 fs/ntfs3/frecord.c                                 |   5 +-
 fs/ntfs3/fsntfs.c                                  |   1 +
 fs/ntfs3/index.c                                   |  11 +-
 include/linux/bvec.h                               |   2 +-
 include/linux/decompress/mm.h                      |   2 +-
 include/linux/efi.h                                |   1 +
 include/linux/fs.h                                 |  14 +
 include/linux/netfilter.h                          |   4 +
 include/linux/nfs4.h                               |  13 +
 include/linux/usb/composite.h                      |   2 +
 include/linux/usb/gadget.h                         |   8 +
 include/net/ipv6_stubs.h                           |   5 +
 include/net/mctp.h                                 |   1 +
 include/net/netfilter/nf_conntrack.h               |   8 +
 include/scsi/scsi_device.h                         |  52 +-
 include/trace/events/rpcgss.h                      |   2 +-
 include/trace/events/rpcrdma.h                     |   4 +-
 include/trace/events/sunrpc.h                      |   2 +-
 include/trace/{events => misc}/fs.h                |   0
 include/trace/{events => misc}/nfs.h               |  12 +
 include/trace/{events => misc}/rdma.h              |   0
 .../trace/{events/sunrpc_base.h => misc/sunrpc.h}  |   0
 include/uapi/linux/bpf.h                           |  31 +-
 include/uapi/linux/in6.h                           |   2 +-
 lib/nlattr.c                                       |   4 +
 mm/huge_memory.c                                   |   4 +
 net/bluetooth/hci_core.c                           |   7 +-
 net/bluetooth/hci_event.c                          |  13 +-
 net/bluetooth/hci_sync.c                           |   7 +-
 net/bluetooth/l2cap_core.c                         |   8 +-
 net/bridge/br_netfilter_hooks.c                    |  96 +++
 net/bridge/netfilter/nf_conntrack_bridge.c         |  30 +
 net/core/filter.c                                  |  30 +-
 net/core/rtnetlink.c                               |  11 +-
 net/hsr/hsr_forward.c                              |   2 +-
 net/ipv4/ip_tunnel.c                               |  28 +-
 net/ipv4/netfilter/nf_reject_ipv4.c                |   1 +
 net/ipv6/addrconf.c                                |   7 +-
 net/ipv6/af_inet6.c                                |   1 +
 net/ipv6/netfilter/nf_reject_ipv6.c                |   1 +
 net/mctp/route.c                                   |  10 +-
 net/mptcp/diag.c                                   |   5 +-
 net/mptcp/pm_netlink.c                             |  48 +-
 net/mptcp/pm_userspace.c                           |  12 +-
 net/mptcp/protocol.c                               |  56 +-
 net/mptcp/protocol.h                               |  13 +-
 net/mptcp/subflow.c                                |  15 +-
 net/netfilter/core.c                               |  16 +
 net/netfilter/nf_conntrack_core.c                  |  13 +
 net/netfilter/nf_conntrack_proto_tcp.c             |  35 +
 net/netfilter/nf_tables_api.c                      |   7 +
 net/netfilter/nft_compat.c                         |  20 +
 net/netlink/af_netlink.c                           |   2 +-
 net/tls/tls_sw.c                                   |  11 +-
 net/unix/garbage.c                                 |  21 +-
 net/wireless/nl80211.c                             |   2 +
 security/landlock/fs.c                             |   4 +-
 security/tomoyo/common.c                           |   3 +-
 sound/core/Makefile                                |   1 -
 sound/firewire/amdtp-stream.c                      |   2 +-
 sound/pci/hda/patch_realtek.c                      |   3 +
 tools/include/uapi/linux/bpf.h                     |  31 +-
 tools/testing/selftests/net/mptcp/mptcp_join.sh    |   5 +
 223 files changed, 4349 insertions(+), 2418 deletions(-)
author maintainer
#14 lore raw

PATCH 14/215 ARM: dts: imx7s: Drop dma-apb interrupt-names

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marek Vasut <[email protected]>

[ Upstream commit 9928f0a9e7c0cee3360ca1442b4001d34ad67556 ]

Drop "interrupt-names" property, since it is broken. The drivers/dma/mxs-dma.c in Linux kernel does not use it, the property contains duplicate array entries in existing DTs, and even malformed entries (gmpi, should have been gpmi). Get rid of that optional property altogether.

---
 arch/arm/boot/dts/imx7s.dtsi | 1 -
 1 file changed, 1 deletion(-)
arch/arm/boot/dts/imx7s.dtsi +0 -1
index 2940dacaa56fc..69aebc691526f 100644
@@ -1274,7 +1274,6 @@ dma_apbh: dma-controller@33000000 {
 				     <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>;
-			interrupt-names = "gpmi0", "gpmi1", "gpmi2", "gpmi3";
 			#dma-cells = <1>;
 			dma-channels = <4>;
 			clocks = <&clks IMX7D_NAND_USDHC_BUS_RAWNAND_CLK>;
Signature · 1 line
2.43.0
author maintainer
#23 lore raw

PATCH 23/215 fs/ntfs3: Fix NULL pointer dereference in ni_write_inode

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ye Bin <[email protected]>

[ Upstream commit db2a3cc6a3481076da6344cc62a80a4e2525f36f ]

Syzbot found the following issue:

Unable to handle kernel NULL pointer dereference at virtual address 0000000000000016

Mem abort info:
ESR = 0x0000000096000006
EC = 0x25: DABT (current EL), IL = 32 bits
SET = 0, FnV = 0
EA = 0, S1PTW = 0
FSC = 0x06: level 2 translation fault
Data abort info:
ISV = 0, ISS = 0x00000006
CM = 0, WnR = 0
user pgtable: 4k pages, 48-bit VAs, pgdp=000000010af56000
[0000000000000016] pgd=08000001090da003, p4d=08000001090da003, pud=08000001090ce003, pmd=0000000000000000

Internal error: Oops: 0000000096000006 [#1] PREEMPT SMP
Modules linked in:
CPU: 1 PID: 3036 Comm: syz-executor206 Not tainted 6.0.0-rc6-syzkaller-17739-g16c9f284e746 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/26/2022
pstate: 80400005 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : is_rec_inuse fs/ntfs3/ntfs.h:313 [inline]
pc : ni_write_inode+0xac/0x798 fs/ntfs3/frecord.c:3232
lr : ni_write_inode+0xa0/0x798 fs/ntfs3/frecord.c:3226

sp : ffff8000126c3800
x29: ffff8000126c3860 x28: 0000000000000000 x27: ffff0000c8b02000
x26: ffff0000c7502320 x25: ffff0000c7502288 x24: 0000000000000000
x23: ffff80000cbec91c x22: ffff0000c8b03000 x21: ffff0000c8b02000
x20: 0000000000000001 x19: ffff0000c75024d8 x18: 00000000000000c0
x17: ffff80000dd1b198 x16: ffff80000db59158 x15: ffff0000c4b6b500
x14: 00000000000000b8 x13: 0000000000000000 x12: ffff0000c4b6b500
x11: ff80800008be1b60 x10: 0000000000000000 x9 : ffff0000c4b6b500 x8 : 0000000000000000 x7 : ffff800008be1b50 x6 : 0000000000000000 x5 : 0000000000000000 x4 : 0000000000000001 x3 : 0000000000000000 x2 : 0000000000000008 x1 : 0000000000000001 x0 : 0000000000000000

Call trace:
 is_rec_inuse fs/ntfs3/ntfs.h:313 [inline]
 ni_write_inode+0xac/0x798 fs/ntfs3/frecord.c:3232
 ntfs_evict_inode+0x54/0x84 fs/ntfs3/inode.c:1744
 evict+0xec/0x334 fs/inode.c:665
 iput_final fs/inode.c:1748 [inline]
 iput+0x2c4/0x324 fs/inode.c:1774
 ntfs_new_inode+0x7c/0xe0 fs/ntfs3/fsntfs.c:1660
 ntfs_create_inode+0x20c/0xe78 fs/ntfs3/inode.c:1278
 ntfs_create+0x54/0x74 fs/ntfs3/namei.c:100
 lookup_open fs/namei.c:3413 [inline]
 open_last_lookups fs/namei.c:3481 [inline]
 path_openat+0x804/0x11c4 fs/namei.c:3688
 do_filp_open+0xdc/0x1b8 fs/namei.c:3718
 do_sys_openat2+0xb8/0x22c fs/open.c:1311
 do_sys_open fs/open.c:1327 [inline]
 __do_sys_openat fs/open.c:1343 [inline]
 __se_sys_openat fs/open.c:1338 [inline]
 __arm64_sys_openat+0xb0/0xe0 fs/open.c:1338
 __invoke_syscall arch/arm64/kernel/syscall.c:38 [inline]
 invoke_syscall arch/arm64/kernel/syscall.c:52 [inline]
 el0_svc_common+0x138/0x220 arch/arm64/kernel/syscall.c:142
 do_el0_svc+0x48/0x164 arch/arm64/kernel/syscall.c:206
 el0_svc+0x58/0x150 arch/arm64/kernel/entry-common.c:636
 el0t_64_sync_handler+0x84/0xf0 arch/arm64/kernel/entry-common.c:654
 el0t_64_sync+0x18c/0x190
Code: 97dafee4 340001b4 f9401328 2a1f03e0 (79402d14)
---[ end trace 0000000000000000 ]---

Above issue may happens as follows:
ntfs_new_inode
mi_init

    mi->mrec = kmalloc(sbi->record_size, GFP_NOFS); -->failed to allocate memory
      if (!mi->mrec)
        return -ENOMEM;
iput
  iput_final
    evict
      ntfs_evict_inode
        ni_write_inode
	  is_rec_inuse(ni->mi.mrec)-> As 'ni->mi.mrec' is NULL trigger NULL-ptr-deref

To solve above issue if new inode failed make inode bad before call 'iput()' in 'ntfs_new_inode()'.

---
 fs/ntfs3/fsntfs.c | 1 +
 1 file changed, 1 insertion(+)
fs/ntfs3/fsntfs.c +1 -0
index 1eac80d55b554..4c2d079b3d49b 100644
@@ -1674,6 +1674,7 @@ struct ntfs_inode *ntfs_new_inode(struct ntfs_sb_info *sbi, CLST rno, bool dir)
 
 out:
 	if (err) {
+		make_bad_inode(inode);
 		iput(inode);
 		ni = ERR_PTR(err);
 	}
Signature · 1 line
2.43.0
author maintainer
#24 lore raw

PATCH 24/215 iommu/arm-smmu-qcom: Limit the SMR groups to 128

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Manivannan Sadhasivam <[email protected]>

[ Upstream commit 12261134732689b7e30c59db9978f81230965181 ]

Some platforms support more than 128 stream matching groups than what is defined by the ARM SMMU architecture specification. But due to some unknown reasons, those additional groups don't exhibit the same behavior as the architecture supported ones.

For instance, the additional groups will not detect the quirky behavior of some firmware versions intercepting writes to S2CR register, thus skipping the quirk implemented in the driver and causing boot crash.

So let's limit the groups to 128 for now until the issue with those groups are fixed and issue a notice to users in that case.

---
 drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)
drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c +15 -1
index d80065c8105af..f15dcb9e4175c 100644
@@ -267,12 +267,26 @@ static int qcom_smmu_init_context(struct arm_smmu_domain *smmu_domain,
 
 static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu)
 {
-	unsigned int last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1);
 	struct qcom_smmu *qsmmu = to_qcom_smmu(smmu);
+	unsigned int last_s2cr;
 	u32 reg;
 	u32 smr;
 	int i;
 
+	/*
+	 * Some platforms support more than the Arm SMMU architected maximum of
+	 * 128 stream matching groups. For unknown reasons, the additional
+	 * groups don't exhibit the same behavior as the architected registers,
+	 * so limit the groups to 128 until the behavior is fixed for the other
+	 * groups.
+	 */
+	if (smmu->num_mapping_groups > 128) {
+		dev_notice(smmu->dev, "\tLimiting the stream matching groups to 128\n");
+		smmu->num_mapping_groups = 128;
+	}
+
+	last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1);
+
 	/*
 	 * With some firmware versions writes to S2CR of type FAULT are
 	 * ignored, and writing BYPASS will end up written as FAULT in the
Signature · 1 line
2.43.0
author maintainer
#25 lore raw

PATCH 25/215 RDMA/core: Fix multiple -Warray-bounds warnings

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Gustavo A. R. Silva <[email protected]>

[ Upstream commit aa4d540b4150052ae3b36d286b9c833a961ce291 ]

GCC-13 (and Clang)[1] does not like to access a partially allocated object, since it cannot reason about it for bounds checking.

In this case 140 bytes are allocated for an object of type struct ib_umad_packet:

        packet = kzalloc(sizeof(*packet) + IB_MGMT_RMPP_HDR, GFP_KERNEL);

However, notice that sizeof(*packet) is only 104 bytes:

struct ib_umad_packet {
        struct ib_mad_send_buf *   msg;                  /*     0     8 */
        struct ib_mad_recv_wc *    recv_wc;              /*     8     8 */
        struct list_head           list;                 /*    16    16 */
        int                        length;               /*    32     4 */

        /* XXX 4 bytes hole, try to pack */

        struct ib_user_mad         mad __attribute__((__aligned__(8))); /*    40    64 */

        /* size: 104, cachelines: 2, members: 5 */
        /* sum members: 100, holes: 1, sum holes: 4 */
        /* forced alignments: 1, forced holes: 1, sum forced holes: 4 */
        /* last cacheline: 40 bytes */
} __attribute__((__aligned__(8)));

and 36 bytes extra bytes are allocated for a flexible-array member in struct ib_user_mad:

include/rdma/ib_mad.h:
120 enum {
...
123 IB_MGMT_RMPP_HDR = 36,
... }

struct ib_user_mad {
        struct ib_user_mad_hdr     hdr;                  /*     0    64 */
        /* --- cacheline 1 boundary (64 bytes) --- */
        __u64                      data[] __attribute__((__aligned__(8))); /*    64     0 */

        /* size: 64, cachelines: 1, members: 2 */
        /* forced alignments: 1 */
} __attribute__((__aligned__(8)));

So we have sizeof(*packet) + IB_MGMT_RMPP_HDR == 140 bytes

Then the address of the flex-array member (for which only 36 bytes were allocated) is casted and copied into a pointer to struct ib_rmpp_mad, which, in turn, is of size 256 bytes:

        rmpp_mad = (struct ib_rmpp_mad *) packet->mad.data;

struct ib_rmpp_mad {

        struct ib_mad_hdr          mad_hdr;              /*     0    24 */
        struct ib_rmpp_hdr         rmpp_hdr;             /*    24    12 */
        u8                         data[220];            /*    36   220 */
        /* size: 256, cachelines: 4, members: 3 */
};

The thing is that those 36 bytes allocated for flex-array member data in struct ib_user_mad onlly account for the size of both struct ib_mad_hdr and struct ib_rmpp_hdr, but nothing is left for array u8 data[220]. So, the compiler is legitimately complaining about accessing an object for which not enough memory was allocated.

Apparently, the only members of struct ib_rmpp_mad that are relevant (that are actually being used) in function ib_umad_write() are mad_hdr and rmpp_hdr. So, instead of casting packet->mad.data to (struct ib_rmpp_mad *) create a new structure

struct ib_rmpp_mad_hdr {
        struct ib_mad_hdr       mad_hdr;
        struct ib_rmpp_hdr      rmpp_hdr;
} __packed;

and cast packet->mad.data to (struct ib_rmpp_mad_hdr *).

Notice that

        IB_MGMT_RMPP_HDR == sizeof(struct ib_rmpp_mad_hdr) == 36 bytes

Refactor the rest of the code, accordingly.

Fix the following warnings seen under GCC-13 and -Warray-bounds:
drivers/infiniband/core/user_mad.c:564:50: warning: array subscript ‘struct ib_rmpp_mad[0]’ is partly outside array bounds of ‘unsigned char[140]’ [-Warray-bounds=] drivers/infiniband/core/user_mad.c:566:42: warning: array subscript ‘struct ib_rmpp_mad[0]’ is partly outside array bounds of ‘unsigned char[140]’ [-Warray-bounds=] drivers/infiniband/core/user_mad.c:618:25: warning: array subscript ‘struct ib_rmpp_mad[0]’ is partly outside array bounds of ‘unsigned char[140]’ [-Warray-bounds=] drivers/infiniband/core/user_mad.c:622:44: warning: array subscript ‘struct ib_rmpp_mad[0]’ is partly outside array bounds of ‘unsigned char[140]’ [-Warray-bounds=]

---
 drivers/infiniband/core/user_mad.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)
drivers/infiniband/core/user_mad.c +14 -9
index d96c78e436f98..5c284dfbe6923 100644
@@ -131,6 +131,11 @@ struct ib_umad_packet {
 	struct ib_user_mad mad;
 };
 
+struct ib_rmpp_mad_hdr {
+	struct ib_mad_hdr	mad_hdr;
+	struct ib_rmpp_hdr      rmpp_hdr;
+} __packed;
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/ib_umad.h>
 
@@ -494,11 +499,11 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf,
 			     size_t count, loff_t *pos)
 {
 	struct ib_umad_file *file = filp->private_data;
+	struct ib_rmpp_mad_hdr *rmpp_mad_hdr;
 	struct ib_umad_packet *packet;
 	struct ib_mad_agent *agent;
 	struct rdma_ah_attr ah_attr;
 	struct ib_ah *ah;
-	struct ib_rmpp_mad *rmpp_mad;
 	__be64 *tid;
 	int ret, data_len, hdr_len, copy_offset, rmpp_active;
 	u8 base_version;
@@ -506,7 +511,7 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf,
 	if (count < hdr_size(file) + IB_MGMT_RMPP_HDR)
 		return -EINVAL;
 
-	packet = kzalloc(sizeof *packet + IB_MGMT_RMPP_HDR, GFP_KERNEL);
+	packet = kzalloc(sizeof(*packet) + IB_MGMT_RMPP_HDR, GFP_KERNEL);
 	if (!packet)
 		return -ENOMEM;
 
@@ -560,13 +565,13 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf,
 		goto err_up;
 	}
 
-	rmpp_mad = (struct ib_rmpp_mad *) packet->mad.data;
-	hdr_len = ib_get_mad_data_offset(rmpp_mad->mad_hdr.mgmt_class);
+	rmpp_mad_hdr = (struct ib_rmpp_mad_hdr *)packet->mad.data;
+	hdr_len = ib_get_mad_data_offset(rmpp_mad_hdr->mad_hdr.mgmt_class);
 
-	if (ib_is_mad_class_rmpp(rmpp_mad->mad_hdr.mgmt_class)
+	if (ib_is_mad_class_rmpp(rmpp_mad_hdr->mad_hdr.mgmt_class)
 	    && ib_mad_kernel_rmpp_agent(agent)) {
 		copy_offset = IB_MGMT_RMPP_HDR;
-		rmpp_active = ib_get_rmpp_flags(&rmpp_mad->rmpp_hdr) &
+		rmpp_active = ib_get_rmpp_flags(&rmpp_mad_hdr->rmpp_hdr) &
 						IB_MGMT_RMPP_FLAG_ACTIVE;
 	} else {
 		copy_offset = IB_MGMT_MAD_HDR;
@@ -615,12 +620,12 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf,
 		tid = &((struct ib_mad_hdr *) packet->msg->mad)->tid;
 		*tid = cpu_to_be64(((u64) agent->hi_tid) << 32 |
 				   (be64_to_cpup(tid) & 0xffffffff));
-		rmpp_mad->mad_hdr.tid = *tid;
+		rmpp_mad_hdr->mad_hdr.tid = *tid;
 	}
 
 	if (!ib_mad_kernel_rmpp_agent(agent)
-	   && ib_is_mad_class_rmpp(rmpp_mad->mad_hdr.mgmt_class)
-	   && (ib_get_rmpp_flags(&rmpp_mad->rmpp_hdr) & IB_MGMT_RMPP_FLAG_ACTIVE)) {
+	    && ib_is_mad_class_rmpp(rmpp_mad_hdr->mad_hdr.mgmt_class)
+	    && (ib_get_rmpp_flags(&rmpp_mad_hdr->rmpp_hdr) & IB_MGMT_RMPP_FLAG_ACTIVE)) {
 		spin_lock_irq(&file->send_lock);
 		list_add_tail(&packet->list, &file->send_list);
 		spin_unlock_irq(&file->send_lock);
Signature · 1 line
2.43.0
author maintainer
#26 lore raw

PATCH 26/215 mm: huge_memory: dont force huge page alignment on 32 bit

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yang Shi <[email protected]>

commit 4ef9ad19e17676b9ef071309bc62020e2373705d upstream.

commit efa7df3e3bb5 ("mm: align larger anonymous mappings on THP boundaries") caused two issues [1] [2] reported on 32 bit system or compat userspace.

It doesn't make too much sense to force huge page alignment on 32 bit system due to the constrained virtual address space.

[1] https://lore.kernel.org/linux-mm/[email protected]/
[2] https://lore.kernel.org/linux-mm/CAJuCfpHXLdQy1a2B6xN2d7quTYwg2OoZseYPZTRpU0eHHKD-sQ@mail.gmail.com/

---
 mm/huge_memory.c |    4 ++++
 1 file changed, 4 insertions(+)
mm/huge_memory.c +4 -0
@@ -37,6 +37,7 @@
 #include <linux/page_owner.h>
 #include <linux/sched/sysctl.h>
 #include <linux/memory-tiers.h>
+#include <linux/compat.h>
 
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
@@ -607,6 +608,9 @@ static unsigned long __thp_get_unmapped_
 	loff_t off_align = round_up(off, size);
 	unsigned long len_pad, ret;
 
+	if (IS_ENABLED(CONFIG_32BIT) || in_compat_syscall())
+		return 0;
+
 	if (off_end <= off_align || (off_end - off_align) < size)
 		return 0;
 
author maintainer
#27 lore raw

PATCH 27/215 mtd: spinand: gigadevice: Fix the get ecc status issue

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Han Xu <[email protected]>

[ Upstream commit 59950610c0c00c7a06d8a75d2ee5d73dba4274cf ]

Some GigaDevice ecc_get_status functions use on-stack buffer for spi_mem_op causes spi_mem_check_op failing, fix the issue by using spinand scratchbuf.

Fixes c40c7a990a46 ("mtd: spinand: Add support for GigaDevice GD5F1GQ4UExxG")
---
 drivers/mtd/nand/spi/gigadevice.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)
drivers/mtd/nand/spi/gigadevice.c +4 -2
index 6b043e24855fb..9116ee7f023ed 100644
@@ -186,7 +186,7 @@ static int gd5fxgq4uexxg_ecc_get_status(struct spinand_device *spinand,
 {
 	u8 status2;
 	struct spi_mem_op op = SPINAND_GET_FEATURE_OP(GD5FXGQXXEXXG_REG_STATUS2,
-						      &status2);
+						      spinand->scratchbuf);
 	int ret;
 
 	switch (status & STATUS_ECC_MASK) {
@@ -207,6 +207,7 @@ static int gd5fxgq4uexxg_ecc_get_status(struct spinand_device *spinand,
 		 * report the maximum of 4 in this case
 		 */
 		/* bits sorted this way (3...0): ECCS1,ECCS0,ECCSE1,ECCSE0 */
+		status2 = *(spinand->scratchbuf);
 		return ((status & STATUS_ECC_MASK) >> 2) |
 			((status2 & STATUS_ECC_MASK) >> 4);
 
@@ -228,7 +229,7 @@ static int gd5fxgq5xexxg_ecc_get_status(struct spinand_device *spinand,
 {
 	u8 status2;
 	struct spi_mem_op op = SPINAND_GET_FEATURE_OP(GD5FXGQXXEXXG_REG_STATUS2,
-						      &status2);
+						      spinand->scratchbuf);
 	int ret;
 
 	switch (status & STATUS_ECC_MASK) {
@@ -248,6 +249,7 @@ static int gd5fxgq5xexxg_ecc_get_status(struct spinand_device *spinand,
 		 * 1 ... 4 bits are flipped (and corrected)
 		 */
 		/* bits sorted this way (1...0): ECCSE1, ECCSE0 */
+		status2 = *(spinand->scratchbuf);
 		return ((status2 & STATUS_ECC_MASK) >> 4) + 1;
 
 	case STATUS_ECC_UNCOR_ERROR:
Signature · 1 line
2.43.0
author maintainer
#28 lore raw

PATCH 28/215 netlink: Fix kernel-infoleak-after-free in __skb_datagram_iter

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ryosuke Yasuoka <[email protected]>

[ Upstream commit 661779e1fcafe1b74b3f3fe8e980c1e207fea1fd ]

syzbot reported the following uninit-value access issue [1]:

netlink_to_full_skb() creates a new skb and puts the skb->data passed as a 1st arg of netlink_to_full_skb() onto new skb. The data size is specified as len and passed to skb_put_data(). This len is based on skb->end that is not data offset but buffer offset. The skb->end contains data and tailroom. Since the tailroom is not initialized when the new skb created, KMSAN detects uninitialized memory area when copying the data.

This patch resolved this issue by correct the len from skb->end to skb->len, which is the actual data offset.

BUG: KMSAN: kernel-infoleak-after-free in instrument_copy_to_user include/linux/instrumented.h:114 [inline]
BUG: KMSAN: kernel-infoleak-after-free in copy_to_user_iter lib/iov_iter.c:24 [inline]
BUG: KMSAN: kernel-infoleak-after-free in iterate_ubuf include/linux/iov_iter.h:29 [inline]
BUG: KMSAN: kernel-infoleak-after-free in iterate_and_advance2 include/linux/iov_iter.h:245 [inline]
BUG: KMSAN: kernel-infoleak-after-free in iterate_and_advance include/linux/iov_iter.h:271 [inline]
BUG: KMSAN: kernel-infoleak-after-free in _copy_to_iter+0x364/0x2520 lib/iov_iter.c:186
 instrument_copy_to_user include/linux/instrumented.h:114 [inline]
 copy_to_user_iter lib/iov_iter.c:24 [inline]
 iterate_ubuf include/linux/iov_iter.h:29 [inline]
 iterate_and_advance2 include/linux/iov_iter.h:245 [inline]
 iterate_and_advance include/linux/iov_iter.h:271 [inline]
 _copy_to_iter+0x364/0x2520 lib/iov_iter.c:186
 copy_to_iter include/linux/uio.h:197 [inline]
 simple_copy_to_iter+0x68/0xa0 net/core/datagram.c:532
 __skb_datagram_iter+0x123/0xdc0 net/core/datagram.c:420
 skb_copy_datagram_iter+0x5c/0x200 net/core/datagram.c:546
 skb_copy_datagram_msg include/linux/skbuff.h:3960 [inline]
 packet_recvmsg+0xd9c/0x2000 net/packet/af_packet.c:3482
 sock_recvmsg_nosec net/socket.c:1044 [inline]
 sock_recvmsg net/socket.c:1066 [inline]
 sock_read_iter+0x467/0x580 net/socket.c:1136
 call_read_iter include/linux/fs.h:2014 [inline]
 new_sync_read fs/read_write.c:389 [inline]
 vfs_read+0x8f6/0xe00 fs/read_write.c:470
 ksys_read+0x20f/0x4c0 fs/read_write.c:613
 __do_sys_read fs/read_write.c:623 [inline]
 __se_sys_read fs/read_write.c:621 [inline]
 __x64_sys_read+0x93/0xd0 fs/read_write.c:621
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0x44/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

Uninit was stored to memory at:

 skb_put_data include/linux/skbuff.h:2622 [inline]
 netlink_to_full_skb net/netlink/af_netlink.c:181 [inline]
 __netlink_deliver_tap_skb net/netlink/af_netlink.c:298 [inline]
 __netlink_deliver_tap+0x5be/0xc90 net/netlink/af_netlink.c:325
 netlink_deliver_tap net/netlink/af_netlink.c:338 [inline]
 netlink_deliver_tap_kernel net/netlink/af_netlink.c:347 [inline]
 netlink_unicast_kernel net/netlink/af_netlink.c:1341 [inline]
 netlink_unicast+0x10f1/0x1250 net/netlink/af_netlink.c:1368
 netlink_sendmsg+0x1238/0x13d0 net/netlink/af_netlink.c:1910
 sock_sendmsg_nosec net/socket.c:730 [inline]
 __sock_sendmsg net/socket.c:745 [inline]
 ____sys_sendmsg+0x9c2/0xd60 net/socket.c:2584
 ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2638
 __sys_sendmsg net/socket.c:2667 [inline]
 __do_sys_sendmsg net/socket.c:2676 [inline]
 __se_sys_sendmsg net/socket.c:2674 [inline]
 __x64_sys_sendmsg+0x307/0x490 net/socket.c:2674
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0x44/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

Uninit was created at:

 free_pages_prepare mm/page_alloc.c:1087 [inline]
 free_unref_page_prepare+0xb0/0xa40 mm/page_alloc.c:2347
 free_unref_page_list+0xeb/0x1100 mm/page_alloc.c:2533
 release_pages+0x23d3/0x2410 mm/swap.c:1042
 free_pages_and_swap_cache+0xd9/0xf0 mm/swap_state.c:316
 tlb_batch_pages_flush mm/mmu_gather.c:98 [inline]
 tlb_flush_mmu_free mm/mmu_gather.c:293 [inline]
 tlb_flush_mmu+0x6f5/0x980 mm/mmu_gather.c:300
 tlb_finish_mmu+0x101/0x260 mm/mmu_gather.c:392
 exit_mmap+0x49e/0xd30 mm/mmap.c:3321
 __mmput+0x13f/0x530 kernel/fork.c:1349
 mmput+0x8a/0xa0 kernel/fork.c:1371
 exit_mm+0x1b8/0x360 kernel/exit.c:567
 do_exit+0xd57/0x4080 kernel/exit.c:858
 do_group_exit+0x2fd/0x390 kernel/exit.c:1021
 __do_sys_exit_group kernel/exit.c:1032 [inline]
 __se_sys_exit_group kernel/exit.c:1030 [inline]
 __x64_sys_exit_group+0x3c/0x50 kernel/exit.c:1030
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0x44/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

Bytes 3852-3903 of 3904 are uninitialized Memory access of size 3904 starts at ffff88812ea1e000 Data copied to user address 0000000020003280

CPU: 1 PID: 5043 Comm: syz-executor297 Not tainted 6.7.0-rc5-syzkaller-00047-g5bd7ef53ffe5 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/10/2023
---
 net/netlink/af_netlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
net/netlink/af_netlink.c +1 -1
index 6857a4965fe87..e9b81cba1e2b4 100644
@@ -167,7 +167,7 @@ static inline u32 netlink_group_mask(u32 group)
 static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb,
 					   gfp_t gfp_mask)
 {
-	unsigned int len = skb_end_offset(skb);
+	unsigned int len = skb->len;
 	struct sk_buff *new;
 
 	new = alloc_skb(len, gfp_mask);
Signature · 1 line
2.43.0
author maintainer
#29 lore raw

PATCH 29/215 netlink: add nla be16/32 types to minlen array

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Florian Westphal <[email protected]>

[ Upstream commit 9a0d18853c280f6a0ee99f91619f2442a17a323a ]

BUG: KMSAN: uninit-value in nla_validate_range_unsigned lib/nlattr.c:222 [inline]
BUG: KMSAN: uninit-value in nla_validate_int_range lib/nlattr.c:336 [inline]
BUG: KMSAN: uninit-value in validate_nla lib/nlattr.c:575 [inline]
BUG: KMSAN: uninit-value in __nla_validate_parse+0x2e20/0x45c0 lib/nlattr.c:631
 nla_validate_range_unsigned lib/nlattr.c:222 [inline]
 nla_validate_int_range lib/nlattr.c:336 [inline]
 validate_nla lib/nlattr.c:575 [inline]

...

The message in question matches this policy:

[NFTA_TARGET_REV] = NLA_POLICY_MAX(NLA_BE32, 255),

but because NLA_BE32 size in minlen array is 0, the validation code will read past the malformed (too small) attribute.

Note: Other attributes, e.g. BITFIELD32, SINT, UINT.. are also missing:
those likely should be added too.

---
 lib/nlattr.c | 4 ++++
 1 file changed, 4 insertions(+)
lib/nlattr.c +4 -0
index dffd60e4065fd..86344df0ccf7b 100644
@@ -30,6 +30,8 @@ static const u8 nla_attr_len[NLA_TYPE_MAX+1] = {
 	[NLA_S16]	= sizeof(s16),
 	[NLA_S32]	= sizeof(s32),
 	[NLA_S64]	= sizeof(s64),
+	[NLA_BE16]	= sizeof(__be16),
+	[NLA_BE32]	= sizeof(__be32),
 };
 
 static const u8 nla_attr_minlen[NLA_TYPE_MAX+1] = {
@@ -43,6 +45,8 @@ static const u8 nla_attr_minlen[NLA_TYPE_MAX+1] = {
 	[NLA_S16]	= sizeof(s16),
 	[NLA_S32]	= sizeof(s32),
 	[NLA_S64]	= sizeof(s64),
+	[NLA_BE16]	= sizeof(__be16),
+	[NLA_BE32]	= sizeof(__be32),
 };
 
 /*
Signature · 1 line
2.43.0
author maintainer
#30 lore raw

PATCH 30/215 net: ip_tunnel: prevent perpetual headroom growth

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Florian Westphal <[email protected]>

[ Upstream commit 5ae1e9922bbdbaeb9cfbe91085ab75927488ac0f ]

syzkaller triggered following kasan splat:

BUG: KASAN: use-after-free in __skb_flow_dissect+0x19d1/0x7a50 net/core/flow_dissector.c:1170
Read of size 1 at addr ffff88812fb4000e by task syz-executor183/5191
[..]
 kasan_report+0xda/0x110 mm/kasan/report.c:588
 __skb_flow_dissect+0x19d1/0x7a50 net/core/flow_dissector.c:1170
 skb_flow_dissect_flow_keys include/linux/skbuff.h:1514 [inline]
 ___skb_get_hash net/core/flow_dissector.c:1791 [inline]
 __skb_get_hash+0xc7/0x540 net/core/flow_dissector.c:1856
 skb_get_hash include/linux/skbuff.h:1556 [inline]
 ip_tunnel_xmit+0x1855/0x33c0 net/ipv4/ip_tunnel.c:748
 ipip_tunnel_xmit+0x3cc/0x4e0 net/ipv4/ipip.c:308
 __netdev_start_xmit include/linux/netdevice.h:4940 [inline]
 netdev_start_xmit include/linux/netdevice.h:4954 [inline]
 xmit_one net/core/dev.c:3548 [inline]
 dev_hard_start_xmit+0x13d/0x6d0 net/core/dev.c:3564
 __dev_queue_xmit+0x7c1/0x3d60 net/core/dev.c:4349
 dev_queue_xmit include/linux/netdevice.h:3134 [inline]
 neigh_connected_output+0x42c/0x5d0 net/core/neighbour.c:1592
 ...
 ip_finish_output2+0x833/0x2550 net/ipv4/ip_output.c:235
 ip_finish_output+0x31/0x310 net/ipv4/ip_output.c:323
 ..
 iptunnel_xmit+0x5b4/0x9b0 net/ipv4/ip_tunnel_core.c:82
 ip_tunnel_xmit+0x1dbc/0x33c0 net/ipv4/ip_tunnel.c:831
 ipgre_xmit+0x4a1/0x980 net/ipv4/ip_gre.c:665
 __netdev_start_xmit include/linux/netdevice.h:4940 [inline]
 netdev_start_xmit include/linux/netdevice.h:4954 [inline]
 xmit_one net/core/dev.c:3548 [inline]
 dev_hard_start_xmit+0x13d/0x6d0 net/core/dev.c:3564
 ...

The splat occurs because skb->data points past skb->head allocated area. This is because neigh layer does:
__skb_pull(skb, skb_network_offset(skb));

... but skb_network_offset() returns a negative offset and __skb_pull() arg is unsigned. IOW, we skb->data gets "adjusted" by a huge value.

The negative value is returned because skb->head and skb->data distance is more than 64k and skb->network_header (u16) has wrapped around.

The bug is in the ip_tunnel infrastructure, which can cause dev->needed_headroom to increment ad infinitum.

The syzkaller reproducer consists of packets getting routed via a gre tunnel, and route of gre encapsulated packets pointing at another (ipip) tunnel. The ipip encapsulation finds gre0 as next output device.

This results in the following pattern:

1). First packet is to be sent out via gre0.
Route lookup found an output device, ipip0.

2).
ip_tunnel_xmit for gre0 bumps gre0->needed_headroom based on the future output device, rt.dev->needed_headroom (ipip0).

3).
ip output / start_xmit moves skb on to ipip0. which runs the same code path again (xmit recursion).

4).
Routing step for the post-gre0-encap packet finds gre0 as output device to use for ipip0 encapsulated packet.

tunl0->needed_headroom is then incremented based on the (already bumped) gre0 device headroom.

This repeats for every future packet:

gre0->needed_headroom gets inflated because previous packets' ipip0 step incremented rt->dev (gre0) headroom, and ipip0 incremented because gre0 needed_headroom was increased.

For each subsequent packet, gre/ipip0->needed_headroom grows until post-expand-head reallocations result in a skb->head/data distance of more than 64k.

Once that happens, skb->network_header (u16) wraps around when pskb_expand_head tries to make sure that skb_network_offset() is unchanged after the headroom expansion/reallocation.

After this skb_network_offset(skb) returns a different (and negative) result post headroom expansion.

The next trip to neigh layer (or anything else that would __skb_pull the network header) makes skb->data point to a memory location outside skb->head area.

v2: Cap the needed_headroom update to an arbitarily chosen upperlimit to prevent perpetual increase instead of dropping the headroom increment completely.

---
 net/ipv4/ip_tunnel.c | 28 +++++++++++++++++++++-------
 1 file changed, 21 insertions(+), 7 deletions(-)
net/ipv4/ip_tunnel.c +21 -7
index 24961b304dad0..328f9068c6a43 100644
@@ -540,6 +540,20 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 	return 0;
 }
 
+static void ip_tunnel_adj_headroom(struct net_device *dev, unsigned int headroom)
+{
+	/* we must cap headroom to some upperlimit, else pskb_expand_head
+	 * will overflow header offsets in skb_headers_offset_update().
+	 */
+	static const unsigned int max_allowed = 512;
+
+	if (headroom > max_allowed)
+		headroom = max_allowed;
+
+	if (headroom > READ_ONCE(dev->needed_headroom))
+		WRITE_ONCE(dev->needed_headroom, headroom);
+}
+
 void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		       u8 proto, int tunnel_hlen)
 {
@@ -614,13 +628,13 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len;
-	if (headroom > READ_ONCE(dev->needed_headroom))
-		WRITE_ONCE(dev->needed_headroom, headroom);
-
-	if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) {
+	if (skb_cow_head(skb, headroom)) {
 		ip_rt_put(rt);
 		goto tx_dropped;
 	}
+
+	ip_tunnel_adj_headroom(dev, headroom);
+
 	iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, tos, ttl,
 		      df, !net_eq(tunnel->net, dev_net(dev)));
 	return;
@@ -800,16 +814,16 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
 			+ rt->dst.header_len + ip_encap_hlen(&tunnel->encap);
-	if (max_headroom > READ_ONCE(dev->needed_headroom))
-		WRITE_ONCE(dev->needed_headroom, max_headroom);
 
-	if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) {
+	if (skb_cow_head(skb, max_headroom)) {
 		ip_rt_put(rt);
 		dev->stats.tx_dropped++;
 		kfree_skb(skb);
 		return;
 	}
 
+	ip_tunnel_adj_headroom(dev, max_headroom);
+
 	iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl,
 		      df, !net_eq(tunnel->net, dev_net(dev)));
 	return;
Signature · 1 line
2.43.0
author maintainer
#31 lore raw

PATCH 31/215 net: mctp: take ownership of skb in mctp_local_output

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jeremy Kerr <[email protected]>

[ Upstream commit 3773d65ae5154ed7df404b050fd7387a36ab5ef3 ]

Currently, mctp_local_output only takes ownership of skb on success, and we may leak an skb if mctp_local_output fails in specific states; the skb ownership isn't transferred until the actual output routing occurs.

Instead, make mctp_local_output free the skb on all error paths up to the route action, so it always consumes the passed skb.

---
 include/net/mctp.h |  1 +
 net/mctp/route.c   | 10 ++++++++--
 2 files changed, 9 insertions(+), 2 deletions(-)
include/net/mctp.h +1 -0
index 82800d521c3de..7ed84054f4623 100644
@@ -249,6 +249,7 @@ struct mctp_route {
 struct mctp_route *mctp_route_lookup(struct net *net, unsigned int dnet,
 				     mctp_eid_t daddr);
 
+/* always takes ownership of skb */
 int mctp_local_output(struct sock *sk, struct mctp_route *rt,
 		      struct sk_buff *skb, mctp_eid_t daddr, u8 req_tag);
 
net/mctp/route.c +8 -2
index 256bf0b89e6ca..0144d8ebdaefb 100644
@@ -888,7 +888,7 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt,
 		dev = dev_get_by_index_rcu(sock_net(sk), cb->ifindex);
 		if (!dev) {
 			rcu_read_unlock();
-			return rc;
+			goto out_free;
 		}
 		rt->dev = __mctp_dev_get(dev);
 		rcu_read_unlock();
@@ -903,7 +903,8 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt,
 		rt->mtu = 0;
 
 	} else {
-		return -EINVAL;
+		rc = -EINVAL;
+		goto out_free;
 	}
 
 	spin_lock_irqsave(&rt->dev->addrs_lock, flags);
@@ -966,12 +967,17 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt,
 		rc = mctp_do_fragment_route(rt, skb, mtu, tag);
 	}
 
+	/* route output functions consume the skb, even on error */
+	skb = NULL;
+
 out_release:
 	if (!ext_rt)
 		mctp_route_release(rt);
 
 	mctp_dev_put(tmp_rt.dev);
 
+out_free:
+	kfree_skb(skb);
 	return rc;
 }
 
Signature · 1 line
2.43.0
author maintainer
#32 lore raw

PATCH 32/215 tun: Fix xdp_rxq_infos queue_index when detaching

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yunjian Wang <[email protected]>

[ Upstream commit 2a770cdc4382b457ca3d43d03f0f0064f905a0d0 ]

When a queue(tfile) is detached, we only update tfile's queue_index, but do not update xdp_rxq_info's queue_index. This patch fixes it.

---
 drivers/net/tun.c | 1 +
 1 file changed, 1 insertion(+)
drivers/net/tun.c +1 -0
index 367255bb44cdc..922d6f16d99d1 100644
@@ -653,6 +653,7 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 				   tun->tfiles[tun->numqueues - 1]);
 		ntfile = rtnl_dereference(tun->tfiles[index]);
 		ntfile->queue_index = index;
+		ntfile->xdp_rxq.queue_index = index;
 		rcu_assign_pointer(tun->tfiles[tun->numqueues - 1],
 				   NULL);
 
Signature · 1 line
2.43.0
author maintainer
#15 lore raw

PATCH 15/215 usb: gadget: Properly configure the device for remote wakeup

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Elson Roy Serrao <[email protected]>

[ Upstream commit b93c2a68f3d9dc98ec30dcb342ae47c1c8d09d18 ]

The wakeup bit in the bmAttributes field indicates whether the device is configured for remote wakeup. But this field should be allowed to set only if the UDC supports such wakeup mechanism. So configure this field based on UDC capability. Also inform the UDC whether the device is configured for remote wakeup by implementing a gadget op.

---
 drivers/usb/gadget/composite.c | 18 ++++++++++++++++++
 drivers/usb/gadget/configfs.c  |  3 +++
 drivers/usb/gadget/udc/core.c  | 27 +++++++++++++++++++++++++++
 drivers/usb/gadget/udc/trace.h |  5 +++++
 include/linux/usb/composite.h  |  2 ++
 include/linux/usb/gadget.h     |  8 ++++++++
 6 files changed, 63 insertions(+)
drivers/usb/gadget/composite.c +18 -0
index cb0a4e2cdbb73..247cca46cdfae 100644
@@ -511,6 +511,19 @@ static u8 encode_bMaxPower(enum usb_device_speed speed,
 		return min(val, 900U) / 8;
 }
 
+void check_remote_wakeup_config(struct usb_gadget *g,
+				struct usb_configuration *c)
+{
+	if (USB_CONFIG_ATT_WAKEUP & c->bmAttributes) {
+		/* Reset the rw bit if gadget is not capable of it */
+		if (!g->wakeup_capable && g->ops->set_remote_wakeup) {
+			WARN(c->cdev, "Clearing wakeup bit for config c.%d\n",
+			     c->bConfigurationValue);
+			c->bmAttributes &= ~USB_CONFIG_ATT_WAKEUP;
+		}
+	}
+}
+
 static int config_buf(struct usb_configuration *config,
 		enum usb_device_speed speed, void *buf, u8 type)
 {
@@ -959,6 +972,11 @@ static int set_config(struct usb_composite_dev *cdev,
 		power = min(power, 500U);
 	else
 		power = min(power, 900U);
+
+	if (USB_CONFIG_ATT_WAKEUP & c->bmAttributes)
+		usb_gadget_set_remote_wakeup(gadget, 1);
+	else
+		usb_gadget_set_remote_wakeup(gadget, 0);
 done:
 	if (power <= USB_SELF_POWER_VBUS_MAX_DRAW)
 		usb_gadget_set_selfpowered(gadget);
drivers/usb/gadget/configfs.c +3 -0
index 4dcf29577f8f1..b94aec6227c51 100644
@@ -1376,6 +1376,9 @@ static int configfs_composite_bind(struct usb_gadget *gadget,
 		if (gadget_is_otg(gadget))
 			c->descriptors = otg_desc;
 
+		/* Properly configure the bmAttributes wakeup bit */
+		check_remote_wakeup_config(gadget, c);
+
 		cfg = container_of(c, struct config_usb_cfg, c);
 		if (!list_empty(&cfg->string_list)) {
 			i = 0;
drivers/usb/gadget/udc/core.c +27 -0
index c40f2ecbe1b8c..0edd9e53fc5a1 100644
@@ -525,6 +525,33 @@ int usb_gadget_wakeup(struct usb_gadget *gadget)
 }
 EXPORT_SYMBOL_GPL(usb_gadget_wakeup);
 
+/**
+ * usb_gadget_set_remote_wakeup - configures the device remote wakeup feature.
+ * @gadget:the device being configured for remote wakeup
+ * @set:value to be configured.
+ *
+ * set to one to enable remote wakeup feature and zero to disable it.
+ *
+ * returns zero on success, else negative errno.
+ */
+int usb_gadget_set_remote_wakeup(struct usb_gadget *gadget, int set)
+{
+	int ret = 0;
+
+	if (!gadget->ops->set_remote_wakeup) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
+	ret = gadget->ops->set_remote_wakeup(gadget, set);
+
+out:
+	trace_usb_gadget_set_remote_wakeup(gadget, ret);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(usb_gadget_set_remote_wakeup);
+
 /**
  * usb_gadget_set_selfpowered - sets the device selfpowered feature.
  * @gadget:the device being declared as self-powered
drivers/usb/gadget/udc/trace.h +5 -0
index abdbcb1bacb0b..a5ed26fbc2dad 100644
@@ -91,6 +91,11 @@ DEFINE_EVENT(udc_log_gadget, usb_gadget_wakeup,
 	TP_ARGS(g, ret)
 );
 
+DEFINE_EVENT(udc_log_gadget, usb_gadget_set_remote_wakeup,
+	TP_PROTO(struct usb_gadget *g, int ret),
+	TP_ARGS(g, ret)
+);
+
 DEFINE_EVENT(udc_log_gadget, usb_gadget_set_selfpowered,
 	TP_PROTO(struct usb_gadget *g, int ret),
 	TP_ARGS(g, ret)
include/linux/usb/composite.h +2 -0
index 43ac3fa760dbe..9783b9107d76b 100644
@@ -412,6 +412,8 @@ extern int composite_dev_prepare(struct usb_composite_driver *composite,
 extern int composite_os_desc_req_prepare(struct usb_composite_dev *cdev,
 					 struct usb_ep *ep0);
 void composite_dev_cleanup(struct usb_composite_dev *cdev);
+void check_remote_wakeup_config(struct usb_gadget *g,
+				struct usb_configuration *c);
 
 static inline struct usb_composite_driver *to_cdriver(
 		struct usb_gadget_driver *gdrv)
include/linux/usb/gadget.h +8 -0
index dc3092cea99e9..5bec668b41dcd 100644
@@ -309,6 +309,7 @@ struct usb_udc;
 struct usb_gadget_ops {
 	int	(*get_frame)(struct usb_gadget *);
 	int	(*wakeup)(struct usb_gadget *);
+	int	(*set_remote_wakeup)(struct usb_gadget *, int set);
 	int	(*set_selfpowered) (struct usb_gadget *, int is_selfpowered);
 	int	(*vbus_session) (struct usb_gadget *, int is_active);
 	int	(*vbus_draw) (struct usb_gadget *, unsigned mA);
@@ -383,6 +384,8 @@ struct usb_gadget_ops {
  * @connected: True if gadget is connected.
  * @lpm_capable: If the gadget max_speed is FULL or HIGH, this flag
  *	indicates that it supports LPM as per the LPM ECN & errata.
+ * @wakeup_capable: True if gadget is capable of sending remote wakeup.
+ * @wakeup_armed: True if gadget is armed by the host for remote wakeup.
  * @irq: the interrupt number for device controller.
  * @id_number: a unique ID number for ensuring that gadget names are distinct
  *
@@ -444,6 +447,8 @@ struct usb_gadget {
 	unsigned			deactivated:1;
 	unsigned			connected:1;
 	unsigned			lpm_capable:1;
+	unsigned			wakeup_capable:1;
+	unsigned			wakeup_armed:1;
 	int				irq;
 	int				id_number;
 };
@@ -600,6 +605,7 @@ static inline int gadget_is_otg(struct usb_gadget *g)
 #if IS_ENABLED(CONFIG_USB_GADGET)
 int usb_gadget_frame_number(struct usb_gadget *gadget);
 int usb_gadget_wakeup(struct usb_gadget *gadget);
+int usb_gadget_set_remote_wakeup(struct usb_gadget *gadget, int set);
 int usb_gadget_set_selfpowered(struct usb_gadget *gadget);
 int usb_gadget_clear_selfpowered(struct usb_gadget *gadget);
 int usb_gadget_vbus_connect(struct usb_gadget *gadget);
@@ -615,6 +621,8 @@ static inline int usb_gadget_frame_number(struct usb_gadget *gadget)
 { return 0; }
 static inline int usb_gadget_wakeup(struct usb_gadget *gadget)
 { return 0; }
+static inline int usb_gadget_set_remote_wakeup(struct usb_gadget *gadget, int set)
+{ return 0; }
 static inline int usb_gadget_set_selfpowered(struct usb_gadget *gadget)
 { return 0; }
 static inline int usb_gadget_clear_selfpowered(struct usb_gadget *gadget)
Signature · 1 line
2.43.0
author maintainer
#33 lore raw

PATCH 33/215 cpufreq: intel_pstate: fix pstate limits enforcement for adjust_perf call back

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Doug Smythies <[email protected]>

[ Upstream commit f0a0fc10abb062d122db5ac4ed42f6d1ca342649 ]

There is a loophole in pstate limit clamping for the intel_cpufreq CPU frequency scaling driver (intel_pstate in passive mode), schedutil CPU frequency scaling governor, HWP (HardWare Pstate) control enabled, when the adjust_perf call back path is used.

Fix it.

Fixes a365ab6b9dfb cpufreq: intel_pstate: Implement the ->adjust_perf() callback
---
 drivers/cpufreq/intel_pstate.c | 3 +++
 1 file changed, 3 insertions(+)
drivers/cpufreq/intel_pstate.c +3 -0
index abdd26f7d04c9..5771f3fc6115d 100644
@@ -2952,6 +2952,9 @@ static void intel_cpufreq_adjust_perf(unsigned int cpunum,
 	if (min_pstate < cpu->min_perf_ratio)
 		min_pstate = cpu->min_perf_ratio;
 
+	if (min_pstate > cpu->max_perf_ratio)
+		min_pstate = cpu->max_perf_ratio;
+
 	max_pstate = min(cap_pstate, cpu->max_perf_ratio);
 	if (max_pstate < min_pstate)
 		max_pstate = min_pstate;
Signature · 1 line
2.43.0
author maintainer
#34 lore raw

PATCH 34/215 net: veth: clear GRO when clearing XDP even when down

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jakub Kicinski <[email protected]>

[ Upstream commit fe9f801355f0b47668419f30f1fac1cf4539e736 ]

veth sets NETIF_F_GRO automatically when XDP is enabled, because both features use the same NAPI machinery.

The logic to clear NETIF_F_GRO sits in veth_disable_xdp() which is called both on ndo_stop and when XDP is turned off. To avoid the flag from being cleared when the device is brought down, the clearing is skipped when IFF_UP is not set. Bringing the device down should indeed not modify its features.

Unfortunately, this means that clearing is also skipped when XDP is disabled _while_ the device is down. And there's nothing on the open path to bring the device features back into sync. IOW if user enables XDP, disables it and then brings the device up we'll end up with a stray GRO flag set but no NAPI instances.

We don't depend on the GRO flag on the datapath, so the datapath won't crash. We will crash (or hang), however, next time features are sync'ed (either by user via ethtool or peer changing its config). The GRO flag will go away, and veth will try to disable the NAPIs. But the open path never created them since XDP was off, the GRO flag was a stray. If NAPI was initialized before we'll hang in napi_disable(). If it never was we'll crash trying to stop uninitialized hrtimer.

Move the GRO flag updates to the XDP enable / disable paths, instead of mixing them with the ndo_open / ndo_close paths.

Fixes d3256efd8e8b ("veth: allow enabling NAPI even without XDP")
Reported-by [email protected]
---
 drivers/net/veth.c | 35 +++++++++++++++++------------------
 1 file changed, 17 insertions(+), 18 deletions(-)
drivers/net/veth.c +17 -18
index 36c5a41f84e44..dea9cc8c39f7a 100644
@@ -1135,14 +1135,6 @@ static int veth_enable_xdp(struct net_device *dev)
 				veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, true);
 				return err;
 			}
-
-			if (!veth_gro_requested(dev)) {
-				/* user-space did not require GRO, but adding XDP
-				 * is supposed to get GRO working
-				 */
-				dev->features |= NETIF_F_GRO;
-				netdev_features_change(dev);
-			}
 		}
 	}
 
@@ -1162,18 +1154,9 @@ static void veth_disable_xdp(struct net_device *dev)
 	for (i = 0; i < dev->real_num_rx_queues; i++)
 		rcu_assign_pointer(priv->rq[i].xdp_prog, NULL);
 
-	if (!netif_running(dev) || !veth_gro_requested(dev)) {
+	if (!netif_running(dev) || !veth_gro_requested(dev))
 		veth_napi_del(dev);
 
-		/* if user-space did not require GRO, since adding XDP
-		 * enabled it, clear it now
-		 */
-		if (!veth_gro_requested(dev) && netif_running(dev)) {
-			dev->features &= ~NETIF_F_GRO;
-			netdev_features_change(dev);
-		}
-	}
-
 	veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, false);
 }
 
@@ -1558,6 +1541,14 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		}
 
 		if (!old_prog) {
+			if (!veth_gro_requested(dev)) {
+				/* user-space did not require GRO, but adding
+				 * XDP is supposed to get GRO working
+				 */
+				dev->features |= NETIF_F_GRO;
+				netdev_features_change(dev);
+			}
+
 			peer->hw_features &= ~NETIF_F_GSO_SOFTWARE;
 			peer->max_mtu = max_mtu;
 		}
@@ -1568,6 +1559,14 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 			if (dev->flags & IFF_UP)
 				veth_disable_xdp(dev);
 
+			/* if user-space did not require GRO, since adding XDP
+			 * enabled it, clear it now
+			 */
+			if (!veth_gro_requested(dev)) {
+				dev->features &= ~NETIF_F_GRO;
+				netdev_features_change(dev);
+			}
+
 			if (peer) {
 				peer->hw_features |= NETIF_F_GSO_SOFTWARE;
 				peer->max_mtu = ETH_MAX_MTU;
Signature · 1 line
2.43.0
author maintainer
#35 lore raw

PATCH 35/215 ipv6: fix potential "struct net" leak in inet6_rtm_getaddr()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit 10bfd453da64a057bcfd1a49fb6b271c48653cdb ]

It seems that if userspace provides a correct IFA_TARGET_NETNSID value but no IFA_ADDRESS and IFA_LOCAL attributes, inet6_rtm_getaddr() returns -EINVAL with an elevated "struct net" refcount.

Fixes 6ecf4c37eb3e ("ipv6: enable IFA_TARGET_NETNSID for RTM_GETADDR")
Cc Christian Brauner <[email protected]>
Cc David Ahern <[email protected]>
---
 net/ipv6/addrconf.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)
net/ipv6/addrconf.c +4 -3
index 46527b5cc8f0c..1648373692a99 100644
@@ -5473,9 +5473,10 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	}
 
 	addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer);
-	if (!addr)
-		return -EINVAL;
-
+	if (!addr) {
+		err = -EINVAL;
+		goto errout;
+	}
 	ifm = nlmsg_data(nlh);
 	if (ifm->ifa_index)
 		dev = dev_get_by_index(tgt_net, ifm->ifa_index);
Signature · 1 line
2.43.0
author maintainer
#36 lore raw

PATCH 36/215 lan78xx: enable auto speed configuration for LAN7850 if no EEPROM is detected

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Oleksij Rempel <[email protected]>

[ Upstream commit 0e67899abfbfdea0c3c0ed3fd263ffc601c5c157 ]

Same as LAN7800, LAN7850 can be used without EEPROM. If EEPROM is not present or not flashed, LAN7850 will fail to sync the speed detected by the PHY with the MAC. In case link speed is 100Mbit, it will accidentally work, otherwise no data can be transferred.

Better way would be to implement link_up callback, or set auto speed configuration unconditionally. But this changes would be more intrusive. So, for now, set it only if no EEPROM is found.

Fixes e69647a19c87 ("lan78xx: Set ASD in MAC_CR when EEE is enabled.")
---
 drivers/net/usb/lan78xx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/net/usb/lan78xx.c +2 -1
index c458c030fadf6..7b9d480e44fe4 100644
@@ -3035,7 +3035,8 @@ static int lan78xx_reset(struct lan78xx_net *dev)
 	if (dev->chipid == ID_REV_CHIP_ID_7801_)
 		buf &= ~MAC_CR_GMII_EN_;
 
-	if (dev->chipid == ID_REV_CHIP_ID_7800_) {
+	if (dev->chipid == ID_REV_CHIP_ID_7800_ ||
+	    dev->chipid == ID_REV_CHIP_ID_7850_) {
 		ret = lan78xx_read_raw_eeprom(dev, 0, 1, &sig);
 		if (!ret && sig != EEPROM_INDICATOR) {
 			/* Implies there is no external eeprom. Set mac speed */
Signature · 1 line
2.43.0
author maintainer
#37 lore raw

PATCH 37/215 veth: try harder when allocating queue memory

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jakub Kicinski <[email protected]>

[ Upstream commit 1ce7d306ea63f3e379557c79abd88052e0483813 ]

struct veth_rq is pretty large, 832B total without debug options enabled. Since commit under Fixes we try to pre-allocate enough queues for every possible CPU. Miao Wang reports that this may lead to order-5 allocations which will fail in production.

Let the allocation fallback to vmalloc() and try harder. These are the same flags we pass to netdev queue allocation.

---
 drivers/net/veth.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
drivers/net/veth.c +3 -2
index dea9cc8c39f7a..dd9f5f1461921 100644
@@ -1359,7 +1359,8 @@ static int veth_alloc_queues(struct net_device *dev)
 	struct veth_priv *priv = netdev_priv(dev);
 	int i;
 
-	priv->rq = kcalloc(dev->num_rx_queues, sizeof(*priv->rq), GFP_KERNEL_ACCOUNT);
+	priv->rq = kvcalloc(dev->num_rx_queues, sizeof(*priv->rq),
+			    GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL);
 	if (!priv->rq)
 		return -ENOMEM;
 
@@ -1375,7 +1376,7 @@ static void veth_free_queues(struct net_device *dev)
 {
 	struct veth_priv *priv = netdev_priv(dev);
 
-	kfree(priv->rq);
+	kvfree(priv->rq);
 }
 
 static int veth_dev_init(struct net_device *dev)
Signature · 1 line
2.43.0
author maintainer
#38 lore raw

PATCH 38/215 net: usb: dm9601: fix wrong return value in dm9601_mdio_read

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Javier Carrasco <[email protected]>

[ Upstream commit c68b2c9eba38ec3f60f4894b189090febf4d8d22 ]

The MII code does not check the return value of mdio_read (among others), and therefore no error code should be sent. A previous fix to the use of an uninitialized variable propagates negative error codes, that might lead to wrong operations by the MII library.

An example of such issues is the use of mii_nway_restart by the dm9601 driver. The mii_nway_restart function does not check the value returned by mdio_read, which in this case might be a negative number which could contain the exact bit the function checks (BMCR_ANENABLE = 0x1000).

Return zero in case of error, as it is common practice in users of mdio_read to avoid wrong uses of the return value.

Fixes 8f8abb863fa5 ("net: usb: dm9601: fix uninitialized variable use in dm9601_mdio_read")
---
 drivers/net/usb/dm9601.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/usb/dm9601.c +1 -1
index 99ec1d4a972db..8b6d6a1b3c2ec 100644
@@ -232,7 +232,7 @@ static int dm9601_mdio_read(struct net_device *netdev, int phy_id, int loc)
 	err = dm_read_shared_word(dev, 1, loc, &res);
 	if (err < 0) {
 		netdev_err(dev->net, "MDIO read error: %d\n", err);
-		return err;
+		return 0;
 	}
 
 	netdev_dbg(dev->net,
Signature · 1 line
2.43.0
author maintainer
#16 lore raw

PATCH 16/215 Input: xpad - add constants for GIP interface numbers

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Vicki Pfau <[email protected]>

[ Upstream commit f9b2e603c6216824e34dc9a67205d98ccc9a41ca ]

Wired GIP devices present multiple interfaces with the same USB identification other than the interface number. This adds constants for differentiating two of them and uses them where appropriate

---
 drivers/input/joystick/xpad.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/input/joystick/xpad.c +4 -1
index 02f3bc4e4895e..13c36f51b9353 100644
@@ -564,6 +564,9 @@ struct xboxone_init_packet {
 #define GIP_MOTOR_LT BIT(3)
 #define GIP_MOTOR_ALL (GIP_MOTOR_R | GIP_MOTOR_L | GIP_MOTOR_RT | GIP_MOTOR_LT)
 
+#define GIP_WIRED_INTF_DATA 0
+#define GIP_WIRED_INTF_AUDIO 1
+
 /*
  * This packet is required for all Xbox One pads with 2015
  * or later firmware installed (or present from the factory).
@@ -2008,7 +2011,7 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id
 	}
 
 	if (xpad->xtype == XTYPE_XBOXONE &&
-	    intf->cur_altsetting->desc.bInterfaceNumber != 0) {
+	    intf->cur_altsetting->desc.bInterfaceNumber != GIP_WIRED_INTF_DATA) {
 		/*
 		 * The Xbox One controller lists three interfaces all with the
 		 * same interface class, subclass and protocol. Differentiate by
Signature · 1 line
2.43.0
author maintainer
#17 lore raw

PATCH 17/215 iommu/sprd: Release dma buffer to avoid memory leak

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chunyan Zhang <[email protected]>

[ Upstream commit 9afea57384d4ae7b2034593eac7fa76c7122762a ]

When attaching to a domain, the driver would alloc a DMA buffer which is used to store address mapping table, and it need to be released when the IOMMU domain is freed.

---
 drivers/iommu/sprd-iommu.c | 29 ++++++++++++++++++++++-------
 1 file changed, 22 insertions(+), 7 deletions(-)
drivers/iommu/sprd-iommu.c +22 -7
index 8261066de07d7..e4358393fe378 100644
@@ -152,13 +152,6 @@ static struct iommu_domain *sprd_iommu_domain_alloc(unsigned int domain_type)
 	return &dom->domain;
 }
 
-static void sprd_iommu_domain_free(struct iommu_domain *domain)
-{
-	struct sprd_iommu_domain *dom = to_sprd_domain(domain);
-
-	kfree(dom);
-}
-
 static void sprd_iommu_first_vpn(struct sprd_iommu_domain *dom)
 {
 	struct sprd_iommu_device *sdev = dom->sdev;
@@ -231,6 +224,28 @@ static void sprd_iommu_hw_en(struct sprd_iommu_device *sdev, bool en)
 	sprd_iommu_update_bits(sdev, reg_cfg, mask, 0, val);
 }
 
+static void sprd_iommu_cleanup(struct sprd_iommu_domain *dom)
+{
+	size_t pgt_size;
+
+	/* Nothing need to do if the domain hasn't been attached */
+	if (!dom->sdev)
+		return;
+
+	pgt_size = sprd_iommu_pgt_size(&dom->domain);
+	dma_free_coherent(dom->sdev->dev, pgt_size, dom->pgt_va, dom->pgt_pa);
+	dom->sdev = NULL;
+	sprd_iommu_hw_en(dom->sdev, false);
+}
+
+static void sprd_iommu_domain_free(struct iommu_domain *domain)
+{
+	struct sprd_iommu_domain *dom = to_sprd_domain(domain);
+
+	sprd_iommu_cleanup(dom);
+	kfree(dom);
+}
+
 static int sprd_iommu_attach_device(struct iommu_domain *domain,
 				    struct device *dev)
 {
Signature · 1 line
2.43.0
author maintainer
#18 lore raw

PATCH 18/215 iommu/arm-smmu-v3: Acknowledge pri/event queue overflow if any

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tomas Krcka <[email protected]>

[ Upstream commit 67ea0b7ce41844eae7c10bb04dfe66a23318c224 ]

When an overflow occurs in the PRI queue, the SMMU toggles the overflow flag in the PROD register. To exit the overflow condition, the PRI thread is supposed to acknowledge it by toggling this flag in the CONS register. Unacknowledged overflow causes the queue to stop adding anything new.

Currently, the priq thread always writes the CONS register back to the SMMU after clearing the queue.

The writeback is not necessary if the OVFLG in the PROD register has not been changed, no overflow has occured.

This commit checks the difference of the overflow flag between CONS and PROD register. If it's different, toggles the OVACKFLG flag in the CONS register and write it to the SMMU.

The situation is similar for the event queue.
The acknowledge register is also toggled after clearing the event queue but never propagated to the hardware. This would only be done the next time when executing evtq thread.

Unacknowledged event queue overflow doesn't affect the event queue, because the SMMU still adds elements to that queue when the overflow condition is active.
But it feel nicer to keep SMMU in sync when possible, so use the same way here as well.

---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +14 -5
index 8966f7d5aab61..82f100e591b5a 100644
@@ -152,6 +152,18 @@ static void queue_inc_cons(struct arm_smmu_ll_queue *q)
 	q->cons = Q_OVF(q->cons) | Q_WRP(q, cons) | Q_IDX(q, cons);
 }
 
+static void queue_sync_cons_ovf(struct arm_smmu_queue *q)
+{
+	struct arm_smmu_ll_queue *llq = &q->llq;
+
+	if (likely(Q_OVF(llq->prod) == Q_OVF(llq->cons)))
+		return;
+
+	llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) |
+		      Q_IDX(llq, llq->cons);
+	queue_sync_cons_out(q);
+}
+
 static int queue_sync_prod_in(struct arm_smmu_queue *q)
 {
 	u32 prod;
@@ -1583,8 +1595,7 @@ static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
 	} while (!queue_empty(llq));
 
 	/* Sync our overflow flag, as we believe we're up to speed */
-	llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) |
-		    Q_IDX(llq, llq->cons);
+	queue_sync_cons_ovf(q);
 	return IRQ_HANDLED;
 }
 
@@ -1642,9 +1653,7 @@ static irqreturn_t arm_smmu_priq_thread(int irq, void *dev)
 	} while (!queue_empty(llq));
 
 	/* Sync our overflow flag, as we believe we're up to speed */
-	llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) |
-		      Q_IDX(llq, llq->cons);
-	queue_sync_cons_out(q);
+	queue_sync_cons_ovf(q);
 	return IRQ_HANDLED;
 }
 
Signature · 1 line
2.43.0
author maintainer
#19 lore raw

PATCH 19/215 fs/ntfs3: Fix a possible null-pointer dereference in ni_clear()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jia-Ju Bai <[email protected]>

[ Upstream commit ec275bf9693d19cc0fdce8436f4c425ced86f6e7 ]

In a previous commit c1006bd13146, ni->mi.mrec in ni_write_inode() could be NULL, and thus a NULL check is added for this variable.

However, in the same call stack, ni->mi.mrec can be also dereferenced in ni_clear():

ntfs_evict_inode(inode)
ni_write_inode(inode, ...)

    ni = ntfs_i(inode);
    is_rec_inuse(ni->mi.mrec) -> Add a NULL check by previous commit
  ni_clear(ntfs_i(inode))
    is_rec_inuse(ni->mi.mrec) -> No check

Thus, a possible null-pointer dereference may exist in ni_clear(). To fix it, a NULL check is added in this function.

---
 fs/ntfs3/frecord.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
fs/ntfs3/frecord.c +1 -1
index bb7e33c240737..1f0e230ec9e2c 100644
@@ -102,7 +102,7 @@ void ni_clear(struct ntfs_inode *ni)
 {
 	struct rb_node *node;
 
-	if (!ni->vfs_inode.i_nlink && is_rec_inuse(ni->mi.mrec))
+	if (!ni->vfs_inode.i_nlink && ni->mi.mrec && is_rec_inuse(ni->mi.mrec))
 		ni_delete_all(ni);
 
 	al_destroy(ni);
Signature · 1 line
2.43.0
author maintainer
#20 lore raw

PATCH 20/215 clk: tegra20: fix gcc-7 constant overflow warning

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Arnd Bergmann <[email protected]>

[ Upstream commit b4a2adbf3586efa12fe78b9dec047423e01f3010 ]

Older gcc versions get confused by comparing a u32 value to a negative constant in a switch()/case block:

drivers/clk/tegra/clk-tegra20.c: In function 'tegra20_clk_measure_input_freq':
drivers/clk/tegra/clk-tegra20.c:581:2: error: case label does not reduce to an integer constant
case OSC_CTRL_OSC_FREQ_12MHZ:
^~~~
drivers/clk/tegra/clk-tegra20.c:593:2: error: case label does not reduce to an integer constant
case OSC_CTRL_OSC_FREQ_26MHZ:

Make the constants unsigned instead.

---
 drivers/clk/tegra/clk-tegra20.c | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)
drivers/clk/tegra/clk-tegra20.c +14 -14
index 422d782475532..dcacc5064d339 100644
@@ -21,24 +21,24 @@
 #define MISC_CLK_ENB 0x48
 
 #define OSC_CTRL 0x50
-#define OSC_CTRL_OSC_FREQ_MASK (3<<30)
-#define OSC_CTRL_OSC_FREQ_13MHZ (0<<30)
-#define OSC_CTRL_OSC_FREQ_19_2MHZ (1<<30)
-#define OSC_CTRL_OSC_FREQ_12MHZ (2<<30)
-#define OSC_CTRL_OSC_FREQ_26MHZ (3<<30)
-#define OSC_CTRL_MASK (0x3f2 | OSC_CTRL_OSC_FREQ_MASK)
-
-#define OSC_CTRL_PLL_REF_DIV_MASK (3<<28)
-#define OSC_CTRL_PLL_REF_DIV_1		(0<<28)
-#define OSC_CTRL_PLL_REF_DIV_2		(1<<28)
-#define OSC_CTRL_PLL_REF_DIV_4		(2<<28)
+#define OSC_CTRL_OSC_FREQ_MASK (3u<<30)
+#define OSC_CTRL_OSC_FREQ_13MHZ (0u<<30)
+#define OSC_CTRL_OSC_FREQ_19_2MHZ (1u<<30)
+#define OSC_CTRL_OSC_FREQ_12MHZ (2u<<30)
+#define OSC_CTRL_OSC_FREQ_26MHZ (3u<<30)
+#define OSC_CTRL_MASK (0x3f2u | OSC_CTRL_OSC_FREQ_MASK)
+
+#define OSC_CTRL_PLL_REF_DIV_MASK	(3u<<28)
+#define OSC_CTRL_PLL_REF_DIV_1		(0u<<28)
+#define OSC_CTRL_PLL_REF_DIV_2		(1u<<28)
+#define OSC_CTRL_PLL_REF_DIV_4		(2u<<28)
 
 #define OSC_FREQ_DET 0x58
-#define OSC_FREQ_DET_TRIG (1<<31)
+#define OSC_FREQ_DET_TRIG (1u<<31)
 
 #define OSC_FREQ_DET_STATUS 0x5c
-#define OSC_FREQ_DET_BUSY (1<<31)
-#define OSC_FREQ_DET_CNT_MASK 0xFFFF
+#define OSC_FREQ_DET_BUSYu (1<<31)
+#define OSC_FREQ_DET_CNT_MASK 0xFFFFu
 
 #define TEGRA20_CLK_PERIPH_BANKS	3
 
Signature · 1 line
2.43.0
author maintainer
#21 lore raw

PATCH 21/215 fs/ntfs3: Add length check in indx_get_root

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Edward Lo <[email protected]>

[ Upstream commit 08e8cf5f2d9ec383a2e339a2711b62a54ff3fba0 ]

This adds a length check to guarantee the retrieved index root is legit.

[  162.459513] BUG: KASAN: use-after-free in hdr_find_e.isra.0+0x10c/0x320
[  162.460176] Read of size 2 at addr ffff8880037bca99 by task mount/243
[  162.460851]
[  162.461252] CPU: 0 PID: 243 Comm: mount Not tainted 6.0.0-rc7 #42
[  162.461744] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014
[  162.462609] Call Trace:
[  162.462954]  <TASK>
[  162.463276]  dump_stack_lvl+0x49/0x63
[  162.463822]  print_report.cold+0xf5/0x689
[  162.464608]  ? unwind_get_return_address+0x3a/0x60
[  162.465766]  ? hdr_find_e.isra.0+0x10c/0x320
[  162.466975]  kasan_report+0xa7/0x130
[  162.467506]  ? _raw_spin_lock_irq+0xc0/0xf0
[  162.467998]  ? hdr_find_e.isra.0+0x10c/0x320
[  162.468536]  __asan_load2+0x68/0x90
[  162.468923]  hdr_find_e.isra.0+0x10c/0x320
[  162.469282]  ? cmp_uints+0xe0/0xe0
[  162.469557]  ? cmp_sdh+0x90/0x90
[  162.469864]  ? ni_find_attr+0x214/0x300
[  162.470217]  ? ni_load_mi+0x80/0x80
[  162.470479]  ? entry_SYSCALL_64_after_hwframe+0x63/0xcd
[  162.470931]  ? ntfs_bread_run+0x190/0x190
[  162.471307]  ? indx_get_root+0xe4/0x190
[  162.471556]  ? indx_get_root+0x140/0x190
[  162.471833]  ? indx_init+0x1e0/0x1e0
[  162.472069]  ? fnd_clear+0x115/0x140
[  162.472363]  ? _raw_spin_lock_irqsave+0x100/0x100
[  162.472731]  indx_find+0x184/0x470
[  162.473461]  ? sysvec_apic_timer_interrupt+0x57/0xc0
[  162.474429]  ? indx_find_buffer+0x2d0/0x2d0
[  162.474704]  ? do_syscall_64+0x3b/0x90
[  162.474962]  dir_search_u+0x196/0x2f0
[  162.475381]  ? ntfs_nls_to_utf16+0x450/0x450
[  162.475661]  ? ntfs_security_init+0x3d6/0x440
[  162.475906]  ? is_sd_valid+0x180/0x180
[  162.476191]  ntfs_extend_init+0x13f/0x2c0
[  162.476496]  ? ntfs_fix_post_read+0x130/0x130
[  162.476861]  ? iput.part.0+0x286/0x320
[  162.477325]  ntfs_fill_super+0x11e0/0x1b50
[  162.477709]  ? put_ntfs+0x1d0/0x1d0
[  162.477970]  ? vsprintf+0x20/0x20
[  162.478258]  ? set_blocksize+0x95/0x150
[  162.478538]  get_tree_bdev+0x232/0x370
[  162.478789]  ? put_ntfs+0x1d0/0x1d0
[  162.479038]  ntfs_fs_get_tree+0x15/0x20
[  162.479374]  vfs_get_tree+0x4c/0x130
[  162.479729]  path_mount+0x654/0xfe0
[  162.480124]  ? putname+0x80/0xa0
[  162.480484]  ? finish_automount+0x2e0/0x2e0
[  162.480894]  ? putname+0x80/0xa0
[  162.481467]  ? kmem_cache_free+0x1c4/0x440
[  162.482280]  ? putname+0x80/0xa0
[  162.482714]  do_mount+0xd6/0xf0
[  162.483264]  ? path_mount+0xfe0/0xfe0
[  162.484782]  ? __kasan_check_write+0x14/0x20
[  162.485593]  __x64_sys_mount+0xca/0x110
[  162.486024]  do_syscall_64+0x3b/0x90
[  162.486543]  entry_SYSCALL_64_after_hwframe+0x63/0xcd
[  162.487141] RIP: 0033:0x7f9d374e948a
[  162.488324] Code: 48 8b 0d 11 fa 2a 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 008
[  162.489728] RSP: 002b:00007ffe30e73d18 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5
[  162.490971] RAX: ffffffffffffffda RBX: 0000561cdb43a060 RCX: 00007f9d374e948a
[  162.491669] RDX: 0000561cdb43a260 RSI: 0000561cdb43a2e0 RDI: 0000561cdb442af0
[  162.492050] RBP: 0000000000000000 R08: 0000561cdb43a280 R09: 0000000000000020
[  162.492459] R10: 00000000c0ed0000 R11: 0000000000000206 R12: 0000561cdb442af0
[  162.493183] R13: 0000561cdb43a260 R14: 0000000000000000 R15: 00000000ffffffff
[  162.493644]  </TASK>
[  162.493908]
[  162.494214] The buggy address belongs to the physical page:
[  162.494761] page:000000003e38a3d5 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x37bc
[  162.496064] flags: 0xfffffc0000000(node=0|zone=1|lastcpupid=0x1fffff)
[  162.497278] raw: 000fffffc0000000 ffffea00000df1c8 ffffea00000df008 0000000000000000
[  162.498928] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000
[  162.500542] page dumped because: kasan: bad access detected
[  162.501057]
[  162.501242] Memory state around the buggy address:
[  162.502230]  ffff8880037bc980: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
[  162.502977]  ffff8880037bca00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
[  162.503522] >ffff8880037bca80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
[  162.503963]                             ^
[  162.504370]  ffff8880037bcb00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
[  162.504766]  ffff8880037bcb80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
---
 fs/ntfs3/index.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)
fs/ntfs3/index.c +10 -1
index 7371f7855e4c4..eee01db6e0cc5 100644
@@ -998,6 +998,7 @@ struct INDEX_ROOT *indx_get_root(struct ntfs_index *indx, struct ntfs_inode *ni,
 	struct ATTR_LIST_ENTRY *le = NULL;
 	struct ATTRIB *a;
 	const struct INDEX_NAMES *in = &s_index_names[indx->type];
+	struct INDEX_ROOT *root = NULL;
 
 	a = ni_find_attr(ni, NULL, &le, ATTR_ROOT, in->name, in->name_len, NULL,
 			 mi);
@@ -1007,7 +1008,15 @@ struct INDEX_ROOT *indx_get_root(struct ntfs_index *indx, struct ntfs_inode *ni,
 	if (attr)
 		*attr = a;
 
-	return resident_data_ex(a, sizeof(struct INDEX_ROOT));
+	root = resident_data_ex(a, sizeof(struct INDEX_ROOT));
+
+	/* length check */
+	if (root && offsetof(struct INDEX_ROOT, ihdr) + le32_to_cpu(root->ihdr.used) >
+			le32_to_cpu(a->res.data_size)) {
+		return NULL;
+	}
+
+	return root;
 }
 
 static int indx_write(struct ntfs_index *indx, struct ntfs_inode *ni,
Signature · 1 line
2.43.0
author maintainer
#22 lore raw

PATCH 22/215 fs/ntfs3: Fix NULL dereference in ni_write_inode

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Abdun Nihaal <[email protected]>

[ Upstream commit 8dae4f6341e335a09575be60b4fdf697c732a470 ]

Syzbot reports a NULL dereference in ni_write_inode. When creating a new inode, if allocation fails in mi_init function (called in mi_format_new function), mi->mrec is set to NULL. In the error path of this inode creation, mi->mrec is later dereferenced in ni_write_inode.

Add a NULL check to prevent NULL dereference.

---
 fs/ntfs3/frecord.c | 3 +++
 1 file changed, 3 insertions(+)
fs/ntfs3/frecord.c +3 -0
index 1f0e230ec9e2c..d260260900241 100644
@@ -3255,6 +3255,9 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint)
 		return 0;
 	}
 
+	if (!ni->mi.mrec)
+		goto out;
+
 	if (is_rec_inuse(ni->mi.mrec) &&
 	    !(sbi->flags & NTFS_FLAGS_LOG_REPLAYING) && inode->i_nlink) {
 		bool modified = false;
Signature · 1 line
2.43.0
author maintainer
#13 lore raw

PATCH 13/215 ARM: dts: imx: Adjust dma-apbh node name

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Stefan Wahren <[email protected]>

[ Upstream commit e9f5cd85f1f931bb7b64031492f7051187ccaac7 ]

Currently the dtbs_check generates warnings like this:

$nodename:0: 'dma-apbh@110000' does not match '^dma-controller(@.*)?$'

So fix all affected dma-apbh node names.

---
 arch/arm/boot/dts/imx23.dtsi   | 2 +-
 arch/arm/boot/dts/imx28.dtsi   | 2 +-
 arch/arm/boot/dts/imx6qdl.dtsi | 2 +-
 arch/arm/boot/dts/imx6sx.dtsi  | 2 +-
 arch/arm/boot/dts/imx6ul.dtsi  | 2 +-
 arch/arm/boot/dts/imx7s.dtsi   | 2 +-
 6 files changed, 6 insertions(+), 6 deletions(-)
arch/arm/boot/dts/imx23.dtsi +1 -1
index ec476b1596496..b236d23f80715 100644
@@ -59,7 +59,7 @@ icoll: interrupt-controller@80000000 {
 				reg = <0x80000000 0x2000>;
 			};
 
-			dma_apbh: dma-apbh@80004000 {
+			dma_apbh: dma-controller@80004000 {
 				compatible = "fsl,imx23-dma-apbh";
 				reg = <0x80004000 0x2000>;
 				interrupts = <0 14 20 0
arch/arm/boot/dts/imx28.dtsi +1 -1
index b15df16ecb01a..b81592a613112 100644
@@ -78,7 +78,7 @@ hsadc: hsadc@80002000 {
 				status = "disabled";
 			};
 
-			dma_apbh: dma-apbh@80004000 {
+			dma_apbh: dma-controller@80004000 {
 				compatible = "fsl,imx28-dma-apbh";
 				reg = <0x80004000 0x2000>;
 				interrupts = <82 83 84 85
arch/arm/boot/dts/imx6qdl.dtsi +1 -1
index ff1e0173b39be..2c6eada01d792 100644
@@ -150,7 +150,7 @@ soc: soc {
 		interrupt-parent = <&gpc>;
 		ranges;
 
-		dma_apbh: dma-apbh@110000 {
+		dma_apbh: dma-controller@110000 {
 			compatible = "fsl,imx6q-dma-apbh", "fsl,imx28-dma-apbh";
 			reg = <0x00110000 0x2000>;
 			interrupts = <0 13 IRQ_TYPE_LEVEL_HIGH>,
arch/arm/boot/dts/imx6sx.dtsi +1 -1
index 1f1053a898fbf..67d344ae76b51 100644
@@ -209,7 +209,7 @@ gpu: gpu@1800000 {
 			power-domains = <&pd_pu>;
 		};
 
-		dma_apbh: dma-apbh@1804000 {
+		dma_apbh: dma-controller@1804000 {
 			compatible = "fsl,imx6sx-dma-apbh", "fsl,imx28-dma-apbh";
 			reg = <0x01804000 0x2000>;
 			interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>,
arch/arm/boot/dts/imx6ul.dtsi +1 -1
index 2b5996395701a..aac081b6daaac 100644
@@ -164,7 +164,7 @@ intc: interrupt-controller@a01000 {
 			      <0x00a06000 0x2000>;
 		};
 
-		dma_apbh: dma-apbh@1804000 {
+		dma_apbh: dma-controller@1804000 {
 			compatible = "fsl,imx6q-dma-apbh", "fsl,imx28-dma-apbh";
 			reg = <0x01804000 0x2000>;
 			interrupts = <0 13 IRQ_TYPE_LEVEL_HIGH>,
arch/arm/boot/dts/imx7s.dtsi +1 -1
index 4b23630fc738d..2940dacaa56fc 100644
@@ -1267,7 +1267,7 @@ fec1: ethernet@30be0000 {
 			};
 		};
 
-		dma_apbh: dma-apbh@33000000 {
+		dma_apbh: dma-controller@33000000 {
 			compatible = "fsl,imx7d-dma-apbh", "fsl,imx28-dma-apbh";
 			reg = <0x33000000 0x2000>;
 			interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>,
Signature · 1 line
2.43.0
author maintainer
#40 lore raw

PATCH 40/215 uapi: in6: replace temporary label with rfc9486

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Justin Iurman <[email protected]>

[ Upstream commit 6a2008641920a9c6fe1abbeb9acbec463215d505 ]

Not really a fix per se, but IPV6_TLV_IOAM is still tagged as "TEMPORARY IANA allocation for IOAM", while RFC 9486 is available for some time now. Just update the reference.

Fixes 9ee11f0fff20 ("ipv6: ioam: Data plane support for Pre-allocated Trace")
---
 include/uapi/linux/in6.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
include/uapi/linux/in6.h +1 -1
index c4c53a9ab9595..ff8d21f9e95b7 100644
@@ -145,7 +145,7 @@ struct in6_flowlabel_req {
 #define IPV6_TLV_PADN		1
 #define IPV6_TLV_ROUTERALERT	5
 #define IPV6_TLV_CALIPSO	7	/* RFC 5570 */
-#define IPV6_TLV_IOAM		49	/* TEMPORARY IANA allocation for IOAM */
+#define IPV6_TLV_IOAM		49	/* RFC 9486 */
 #define IPV6_TLV_JUMBO		194
 #define IPV6_TLV_HAO		201	/* home address option */
 
Signature · 1 line
2.43.0
author maintainer
#49 lore raw

PATCH 49/215 Bluetooth: hci_qca: mark OF related data as maybe unused

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Krzysztof Kozlowski <[email protected]>

[ Upstream commit 44fac8a2fd2f72ee98ee41e6bc9ecc7765b5d3cc ]

The driver can be compile tested with !CONFIG_OF making certain data unused:

drivers/bluetooth/hci_qca.c:1869:37: error: ‘qca_soc_data_wcn6750’ defined but not used [-Werror=unused-const-variable=] drivers/bluetooth/hci_qca.c:1853:37: error: ‘qca_soc_data_wcn3998’ defined but not used [-Werror=unused-const-variable=] drivers/bluetooth/hci_qca.c:1841:37: error: ‘qca_soc_data_wcn3991’ defined but not used [-Werror=unused-const-variable=] drivers/bluetooth/hci_qca.c:1830:37: error: ‘qca_soc_data_wcn3990’ defined but not used [-Werror=unused-const-variable=]

Stable-dep-of: 7dcd3e014aa7 ("Bluetooth: hci_qca: Set BDA quirk bit if fwnode exists in DT")

---
 drivers/bluetooth/hci_qca.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)
drivers/bluetooth/hci_qca.c +5 -5
index 76ceb8a0183d1..0e908a337e534 100644
@@ -1824,7 +1824,7 @@ static const struct hci_uart_proto qca_proto = {
 	.dequeue	= qca_dequeue,
 };
 
-static const struct qca_device_data qca_soc_data_wcn3990 = {
+static const struct qca_device_data qca_soc_data_wcn3990 __maybe_unused = {
 	.soc_type = QCA_WCN3990,
 	.vregs = (struct qca_vreg []) {
 		{ "vddio", 15000  },
@@ -1835,7 +1835,7 @@ static const struct qca_device_data qca_soc_data_wcn3990 = {
 	.num_vregs = 4,
 };
 
-static const struct qca_device_data qca_soc_data_wcn3991 = {
+static const struct qca_device_data qca_soc_data_wcn3991 __maybe_unused = {
 	.soc_type = QCA_WCN3991,
 	.vregs = (struct qca_vreg []) {
 		{ "vddio", 15000  },
@@ -1847,7 +1847,7 @@ static const struct qca_device_data qca_soc_data_wcn3991 = {
 	.capabilities = QCA_CAP_WIDEBAND_SPEECH | QCA_CAP_VALID_LE_STATES,
 };
 
-static const struct qca_device_data qca_soc_data_wcn3998 = {
+static const struct qca_device_data qca_soc_data_wcn3998 __maybe_unused = {
 	.soc_type = QCA_WCN3998,
 	.vregs = (struct qca_vreg []) {
 		{ "vddio", 10000  },
@@ -1858,13 +1858,13 @@ static const struct qca_device_data qca_soc_data_wcn3998 = {
 	.num_vregs = 4,
 };
 
-static const struct qca_device_data qca_soc_data_qca6390 = {
+static const struct qca_device_data qca_soc_data_qca6390 __maybe_unused = {
 	.soc_type = QCA_QCA6390,
 	.num_vregs = 0,
 	.capabilities = QCA_CAP_WIDEBAND_SPEECH | QCA_CAP_VALID_LE_STATES,
 };
 
-static const struct qca_device_data qca_soc_data_wcn6750 = {
+static const struct qca_device_data qca_soc_data_wcn6750 __maybe_unused = {
 	.soc_type = QCA_WCN6750,
 	.vregs = (struct qca_vreg []) {
 		{ "vddio", 5000 },
Signature · 1 line
2.43.0
author maintainer
#50 lore raw

PATCH 50/215 Bluetooth: hci_qca: Add support for QTI Bluetooth chip wcn6855

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Steev Klimaszewski <[email protected]>

[ Upstream commit 095327fede005f4b14d40b2183b2f7965c739dbd ]

Add regulators, GPIOs and changes required to power on/off wcn6855. Add support for firmware download for wcn6855 which is in the linux-firmware repository as hpbtfw21.tlv and hpnv21.bin.

Based on the assumption that this is similar to the wcn6750

Tested-on: BTFW.HSP.2.1.0-00538-VER_PATCHZ-1

Stable-dep-of: 7dcd3e014aa7 ("Bluetooth: hci_qca: Set BDA quirk bit if fwnode exists in DT")

---
 drivers/bluetooth/btqca.c   | 14 ++++++++-
 drivers/bluetooth/btqca.h   | 10 +++++++
 drivers/bluetooth/hci_qca.c | 57 ++++++++++++++++++++++++++++---------
 3 files changed, 66 insertions(+), 15 deletions(-)
drivers/bluetooth/btqca.c +13 -1
index d7d0c9de3dc31..4cb541096b934 100644
@@ -614,6 +614,9 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 		config.type = ELF_TYPE_PATCH;
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/msbtfw%02x.mbn", rom_ver);
+	} else if (soc_type == QCA_WCN6855) {
+		snprintf(config.fwname, sizeof(config.fwname),
+			 "qca/hpbtfw%02x.tlv", rom_ver);
 	} else {
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/rampatch_%08x.bin", soc_ver);
@@ -648,6 +651,9 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 	else if (soc_type == QCA_WCN6750)
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/msnv%02x.bin", rom_ver);
+	else if (soc_type == QCA_WCN6855)
+		snprintf(config.fwname, sizeof(config.fwname),
+			 "qca/hpnv%02x.bin", rom_ver);
 	else
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/nvm_%08x.bin", soc_ver);
@@ -685,11 +691,17 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 		return err;
 	}
 
-	if (soc_type == QCA_WCN3991 || soc_type == QCA_WCN6750) {
+	switch (soc_type) {
+	case QCA_WCN3991:
+	case QCA_WCN6750:
+	case QCA_WCN6855:
 		/* get fw build info */
 		err = qca_read_fw_build_info(hdev);
 		if (err < 0)
 			return err;
+		break;
+	default:
+		break;
 	}
 
 	bt_dev_info(hdev, "QCA setup on UART is completed");
drivers/bluetooth/btqca.h +10 -0
index 61e9a50e66ae1..b884095bcd9d0 100644
@@ -147,6 +147,7 @@ enum qca_btsoc_type {
 	QCA_WCN3991,
 	QCA_QCA6390,
 	QCA_WCN6750,
+	QCA_WCN6855,
 };
 
 #if IS_ENABLED(CONFIG_BT_QCA)
@@ -168,6 +169,10 @@ static inline bool qca_is_wcn6750(enum qca_btsoc_type soc_type)
 {
 	return soc_type == QCA_WCN6750;
 }
+static inline bool qca_is_wcn6855(enum qca_btsoc_type soc_type)
+{
+	return soc_type == QCA_WCN6855;
+}
 
 #else
 
@@ -206,6 +211,11 @@ static inline bool qca_is_wcn6750(enum qca_btsoc_type soc_type)
 	return false;
 }
 
+static inline bool qca_is_wcn6855(enum qca_btsoc_type soc_type)
+{
+	return false;
+}
+
 static inline int qca_send_pre_shutdown_cmd(struct hci_dev *hdev)
 {
 	return -EOPNOTSUPP;
drivers/bluetooth/hci_qca.c +43 -14

147 lines not on this page · raw message

Signature · 1 line
2.43.0
author maintainer
#51 lore raw

PATCH 51/215 Bluetooth: btqca: use le32_to_cpu for ver.soc_id

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Min-Hua Chen <[email protected]>

[ Upstream commit 8153b738bc547878a017889d2b1cf8dd2de0e0c6 ]

Use le32_to_cpu for ver.soc_id to fix the following sparse warning.

drivers/bluetooth/btqca.c:640:24: sparse: warning: restricted __le32 degrades to integer

Stable-dep-of: 7dcd3e014aa7 ("Bluetooth: hci_qca: Set BDA quirk bit if fwnode exists in DT")

---
 drivers/bluetooth/btqca.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/bluetooth/btqca.c +1 -1
index 4cb541096b934..d40a6041c48cd 100644
@@ -637,7 +637,7 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/%s", firmware_name);
 	else if (qca_is_wcn399x(soc_type)) {
-		if (ver.soc_id == QCA_WCN3991_SOC_ID) {
+		if (le32_to_cpu(ver.soc_id) == QCA_WCN3991_SOC_ID) {
 			snprintf(config.fwname, sizeof(config.fwname),
 				 "qca/crnv%02xu.bin", rom_ver);
 		} else {
Signature · 1 line
2.43.0
author maintainer
#52 lore raw

PATCH 52/215 Bluetooth: btqca: Add WCN3988 support

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Luca Weiss <[email protected]>

[ Upstream commit f904feefe60c28b6852d5625adc4a2c39426a2d9 ]

Add support for the Bluetooth chip codenamed APACHE which is part of WCN3988.

The firmware for this chip has a slightly different naming scheme compared to most others. For ROM Version 0x0200 we need to use apbtfw10.tlv + apnv10.bin and for ROM version 0x201 apbtfw11.tlv + apnv11.bin

Stable-dep-of: 7dcd3e014aa7 ("Bluetooth: hci_qca: Set BDA quirk bit if fwnode exists in DT")

---
 drivers/bluetooth/btqca.c   | 13 +++++++++++--
 drivers/bluetooth/btqca.h   | 12 ++++++++++--
 drivers/bluetooth/hci_qca.c | 12 ++++++++++++
 3 files changed, 33 insertions(+), 4 deletions(-)
drivers/bluetooth/btqca.c +11 -2
index d40a6041c48cd..d775402b33df3 100644
@@ -594,14 +594,20 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 	/* Firmware files to download are based on ROM version.
 	 * ROM version is derived from last two bytes of soc_ver.
 	 */
-	rom_ver = ((soc_ver & 0x00000f00) >> 0x04) | (soc_ver & 0x0000000f);
+	if (soc_type == QCA_WCN3988)
+		rom_ver = ((soc_ver & 0x00000f00) >> 0x05) | (soc_ver & 0x0000000f);
+	else
+		rom_ver = ((soc_ver & 0x00000f00) >> 0x04) | (soc_ver & 0x0000000f);
 
 	if (soc_type == QCA_WCN6750)
 		qca_send_patch_config_cmd(hdev);
 
 	/* Download rampatch file */
 	config.type = TLV_TYPE_PATCH;
-	if (qca_is_wcn399x(soc_type)) {
+	if (soc_type == QCA_WCN3988) {
+		snprintf(config.fwname, sizeof(config.fwname),
+			 "qca/apbtfw%02x.tlv", rom_ver);
+	} else if (qca_is_wcn399x(soc_type)) {
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/crbtfw%02x.tlv", rom_ver);
 	} else if (soc_type == QCA_QCA6390) {
@@ -636,6 +642,9 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 	if (firmware_name)
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/%s", firmware_name);
+	else if (soc_type == QCA_WCN3988)
+		snprintf(config.fwname, sizeof(config.fwname),
+			 "qca/apnv%02x.bin", rom_ver);
 	else if (qca_is_wcn399x(soc_type)) {
 		if (le32_to_cpu(ver.soc_id) == QCA_WCN3991_SOC_ID) {
 			snprintf(config.fwname, sizeof(config.fwname),
drivers/bluetooth/btqca.h +10 -2
index b884095bcd9d0..fc6cf314eb0ef 100644
@@ -142,6 +142,7 @@ enum qca_btsoc_type {
 	QCA_INVALID = -1,
 	QCA_AR3002,
 	QCA_ROME,
+	QCA_WCN3988,
 	QCA_WCN3990,
 	QCA_WCN3998,
 	QCA_WCN3991,
@@ -162,8 +163,15 @@ int qca_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr);
 int qca_send_pre_shutdown_cmd(struct hci_dev *hdev);
 static inline bool qca_is_wcn399x(enum qca_btsoc_type soc_type)
 {
-	return soc_type == QCA_WCN3990 || soc_type == QCA_WCN3991 ||
-	       soc_type == QCA_WCN3998;
+	switch (soc_type) {
+	case QCA_WCN3988:
+	case QCA_WCN3990:
+	case QCA_WCN3991:
+	case QCA_WCN3998:
+		return true;
+	default:
+		return false;
+	}
 }
 static inline bool qca_is_wcn6750(enum qca_btsoc_type soc_type)
 {
drivers/bluetooth/hci_qca.c +12 -0
index f217c2821b9fb..746eb096c037c 100644
@@ -1832,6 +1832,17 @@ static const struct hci_uart_proto qca_proto = {
 	.dequeue	= qca_dequeue,
 };
 
+static const struct qca_device_data qca_soc_data_wcn3988 __maybe_unused = {
+	.soc_type = QCA_WCN3988,
+	.vregs = (struct qca_vreg []) {
+		{ "vddio", 15000  },
+		{ "vddxo", 80000  },
+		{ "vddrf", 300000 },
+		{ "vddch0", 450000 },
+	},
+	.num_vregs = 4,
+};
+
 static const struct qca_device_data qca_soc_data_wcn3990 __maybe_unused = {
 	.soc_type = QCA_WCN3990,
 	.vregs = (struct qca_vreg []) {
@@ -2357,6 +2368,7 @@ static const struct of_device_id qca_bluetooth_of_match[] = {
 	{ .compatible = "qcom,qca6174-bt" },
 	{ .compatible = "qcom,qca6390-bt", .data = &qca_soc_data_qca6390},
 	{ .compatible = "qcom,qca9377-bt" },
+	{ .compatible = "qcom,wcn3988-bt", .data = &qca_soc_data_wcn3988},
 	{ .compatible = "qcom,wcn3990-bt", .data = &qca_soc_data_wcn3990},
 	{ .compatible = "qcom,wcn3991-bt", .data = &qca_soc_data_wcn3991},
 	{ .compatible = "qcom,wcn3998-bt", .data = &qca_soc_data_wcn3998},
Signature · 1 line
2.43.0
author maintainer
#53 lore raw

PATCH 53/215 Bluetooth: qca: use switch case for soc type behavior

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Neil Armstrong <[email protected]>

[ Upstream commit 691d54d0f7cb14baac1ff4af210d13c0e4897e27 ]

Use switch/case to handle soc type specific behaviour, the permit dropping the qca_is_xxx() inline functions and make the code clearer and easier to update for new SoCs.

Stable-dep-of: 7dcd3e014aa7 ("Bluetooth: hci_qca: Set BDA quirk bit if fwnode exists in DT")

---
 drivers/bluetooth/btqca.c   |  87 +++++++++-----
 drivers/bluetooth/btqca.h   |  36 ------
 drivers/bluetooth/hci_qca.c | 233 +++++++++++++++++++++++++++---------
 3 files changed, 236 insertions(+), 120 deletions(-)
drivers/bluetooth/btqca.c +57 -30
index d775402b33df3..8331090af86ea 100644
@@ -604,26 +604,34 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 
 	/* Download rampatch file */
 	config.type = TLV_TYPE_PATCH;
-	if (soc_type == QCA_WCN3988) {
-		snprintf(config.fwname, sizeof(config.fwname),
-			 "qca/apbtfw%02x.tlv", rom_ver);
-	} else if (qca_is_wcn399x(soc_type)) {
+	switch (soc_type) {
+	case QCA_WCN3990:
+	case QCA_WCN3991:
+	case QCA_WCN3998:
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/crbtfw%02x.tlv", rom_ver);
-	} else if (soc_type == QCA_QCA6390) {
+		break;
+	case QCA_WCN3988:
+		snprintf(config.fwname, sizeof(config.fwname),
+			 "qca/apbtfw%02x.tlv", rom_ver);
+		break;
+	case QCA_QCA6390:
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/htbtfw%02x.tlv", rom_ver);
-	} else if (soc_type == QCA_WCN6750) {
+		break;
+	case QCA_WCN6750:
 		/* Choose mbn file by default.If mbn file is not found
 		 * then choose tlv file
 		 */
 		config.type = ELF_TYPE_PATCH;
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/msbtfw%02x.mbn", rom_ver);
-	} else if (soc_type == QCA_WCN6855) {
+		break;
+	case QCA_WCN6855:
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/hpbtfw%02x.tlv", rom_ver);
-	} else {
+		break;
+	default:
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/rampatch_%08x.bin", soc_ver);
 	}
@@ -639,33 +647,44 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 
 	/* Download NVM configuration */
 	config.type = TLV_TYPE_NVM;
-	if (firmware_name)
+	if (firmware_name) {
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/%s", firmware_name);
-	else if (soc_type == QCA_WCN3988)
-		snprintf(config.fwname, sizeof(config.fwname),
-			 "qca/apnv%02x.bin", rom_ver);
-	else if (qca_is_wcn399x(soc_type)) {
-		if (le32_to_cpu(ver.soc_id) == QCA_WCN3991_SOC_ID) {
+	} else {
+		switch (soc_type) {
+		case QCA_WCN3990:
+		case QCA_WCN3991:
+		case QCA_WCN3998:
+			if (le32_to_cpu(ver.soc_id) == QCA_WCN3991_SOC_ID) {
+				snprintf(config.fwname, sizeof(config.fwname),
+					 "qca/crnv%02xu.bin", rom_ver);
+			} else {
+				snprintf(config.fwname, sizeof(config.fwname),
+					 "qca/crnv%02x.bin", rom_ver);
+			}
+			break;
+		case QCA_WCN3988:
 			snprintf(config.fwname, sizeof(config.fwname),
-				 "qca/crnv%02xu.bin", rom_ver);
-		} else {
+				 "qca/apnv%02x.bin", rom_ver);
+			break;
+		case QCA_QCA6390:
+			snprintf(config.fwname, sizeof(config.fwname),
+				 "qca/htnv%02x.bin", rom_ver);
+			break;
+		case QCA_WCN6750:
+			snprintf(config.fwname, sizeof(config.fwname),
+				 "qca/msnv%02x.bin", rom_ver);
+			break;
+		case QCA_WCN6855:
+			snprintf(config.fwname, sizeof(config.fwname),
+				 "qca/hpnv%02x.bin", rom_ver);
+			break;
+
+		default:
 			snprintf(config.fwname, sizeof(config.fwname),
-				 "qca/crnv%02x.bin", rom_ver);
+				 "qca/nvm_%08x.bin", soc_ver);
 		}
 	}
-	else if (soc_type == QCA_QCA6390)
-		snprintf(config.fwname, sizeof(config.fwname),
-			 "qca/htnv%02x.bin", rom_ver);
-	else if (soc_type == QCA_WCN6750)
-		snprintf(config.fwname, sizeof(config.fwname),
-			 "qca/msnv%02x.bin", rom_ver);
-	else if (soc_type == QCA_WCN6855)
-		snprintf(config.fwname, sizeof(config.fwname),
-			 "qca/hpnv%02x.bin", rom_ver);
-	else
-		snprintf(config.fwname, sizeof(config.fwname),
-			 "qca/nvm_%08x.bin", soc_ver);
 
 	err = qca_download_firmware(hdev, &config, soc_type, rom_ver);
 	if (err < 0) {
@@ -673,16 +692,24 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 		return err;
 	}
 
-	if (soc_type >= QCA_WCN3991) {
+	switch (soc_type) {
+	case QCA_WCN3991:
+	case QCA_QCA6390:
+	case QCA_WCN6750:
+	case QCA_WCN6855:
 		err = qca_disable_soc_logging(hdev);
 		if (err < 0)
 			return err;
+		break;
+	default:
+		break;
 	}
 
 	/* WCN399x and WCN6750 supports the Microsoft vendor extension with 0xFD70 as the
 	 * VsMsftOpCode.
 	 */
 	switch (soc_type) {
+	case QCA_WCN3988:
 	case QCA_WCN3990:
 	case QCA_WCN3991:
 	case QCA_WCN3998:
drivers/bluetooth/btqca.h +0 -36
index fc6cf314eb0ef..fe51c632d7720 100644
@@ -161,27 +161,6 @@ int qca_read_soc_version(struct hci_dev *hdev, struct qca_btsoc_version *ver,
 			 enum qca_btsoc_type);
 int qca_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr);
 int qca_send_pre_shutdown_cmd(struct hci_dev *hdev);
-static inline bool qca_is_wcn399x(enum qca_btsoc_type soc_type)
-{
-	switch (soc_type) {
-	case QCA_WCN3988:
-	case QCA_WCN3990:
-	case QCA_WCN3991:
-	case QCA_WCN3998:
-		return true;
-	default:
-		return false;
-	}
-}
-static inline bool qca_is_wcn6750(enum qca_btsoc_type soc_type)
-{
-	return soc_type == QCA_WCN6750;
-}
-static inline bool qca_is_wcn6855(enum qca_btsoc_type soc_type)
-{
-	return soc_type == QCA_WCN6855;
-}
-
 #else
 
 static inline int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr)
@@ -209,21 +188,6 @@ static inline int qca_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr)
 	return -EOPNOTSUPP;
 }
 
-static inline bool qca_is_wcn399x(enum qca_btsoc_type soc_type)
-{
-	return false;
-}
-
-static inline bool qca_is_wcn6750(enum qca_btsoc_type soc_type)
-{
-	return false;
-}
-
-static inline bool qca_is_wcn6855(enum qca_btsoc_type soc_type)
-{
-	return false;
-}
-
 static inline int qca_send_pre_shutdown_cmd(struct hci_dev *hdev)
 {
 	return -EOPNOTSUPP;
drivers/bluetooth/hci_qca.c +179 -54

373 lines not on this page · raw message

Signature · 1 line
2.43.0
author maintainer
#54 lore raw

PATCH 54/215 Bluetooth: qca: add support for WCN7850

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Neil Armstrong <[email protected]>

[ Upstream commit e0c1278ac89b0390fe9a74f673b6f25172292db2 ]

Add support for the WCN7850 Bluetooth chipset.

Tested on the SM8550 QRD platform.

Stable-dep-of: 7dcd3e014aa7 ("Bluetooth: hci_qca: Set BDA quirk bit if fwnode exists in DT")

---
 drivers/bluetooth/btqca.c   | 10 ++++++++++
 drivers/bluetooth/btqca.h   |  1 +
 drivers/bluetooth/hci_qca.c | 31 ++++++++++++++++++++++++++++++-
 3 files changed, 41 insertions(+), 1 deletion(-)
drivers/bluetooth/btqca.c +10 -0
index 8331090af86ea..0211f704a358b 100644
@@ -631,6 +631,10 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/hpbtfw%02x.tlv", rom_ver);
 		break;
+	case QCA_WCN7850:
+		snprintf(config.fwname, sizeof(config.fwname),
+			 "qca/hmtbtfw%02x.tlv", rom_ver);
+		break;
 	default:
 		snprintf(config.fwname, sizeof(config.fwname),
 			 "qca/rampatch_%08x.bin", soc_ver);
@@ -679,6 +683,10 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 			snprintf(config.fwname, sizeof(config.fwname),
 				 "qca/hpnv%02x.bin", rom_ver);
 			break;
+		case QCA_WCN7850:
+			snprintf(config.fwname, sizeof(config.fwname),
+				 "qca/hmtnv%02x.bin", rom_ver);
+			break;
 
 		default:
 			snprintf(config.fwname, sizeof(config.fwname),
@@ -697,6 +705,7 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 	case QCA_QCA6390:
 	case QCA_WCN6750:
 	case QCA_WCN6855:
+	case QCA_WCN7850:
 		err = qca_disable_soc_logging(hdev);
 		if (err < 0)
 			return err;
@@ -731,6 +740,7 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 	case QCA_WCN3991:
 	case QCA_WCN6750:
 	case QCA_WCN6855:
+	case QCA_WCN7850:
 		/* get fw build info */
 		err = qca_read_fw_build_info(hdev);
 		if (err < 0)
drivers/bluetooth/btqca.h +1 -0
index fe51c632d7720..03bff5c0059de 100644
@@ -149,6 +149,7 @@ enum qca_btsoc_type {
 	QCA_QCA6390,
 	QCA_WCN6750,
 	QCA_WCN6855,
+	QCA_WCN7850,
 };
 
 #if IS_ENABLED(CONFIG_BT_QCA)
drivers/bluetooth/hci_qca.c +30 -1
index e6ead996948a8..43abdaf92a0ed 100644
@@ -1330,6 +1330,7 @@ static int qca_set_baudrate(struct hci_dev *hdev, uint8_t baudrate)
 	case QCA_WCN3998:
 	case QCA_WCN6750:
 	case QCA_WCN6855:
+	case QCA_WCN7850:
 		usleep_range(1000, 10000);
 		break;
 
@@ -1415,6 +1416,7 @@ static int qca_check_speeds(struct hci_uart *hu)
 	case QCA_WCN3998:
 	case QCA_WCN6750:
 	case QCA_WCN6855:
+	case QCA_WCN7850:
 		if (!qca_get_speed(hu, QCA_INIT_SPEED) &&
 		    !qca_get_speed(hu, QCA_OPER_SPEED))
 			return -EINVAL;
@@ -1456,6 +1458,7 @@ static int qca_set_speed(struct hci_uart *hu, enum qca_speed_type speed_type)
 		case QCA_WCN3998:
 		case QCA_WCN6750:
 		case QCA_WCN6855:
+		case QCA_WCN7850:
 			hci_uart_set_flow_control(hu, true);
 			break;
 
@@ -1489,6 +1492,7 @@ static int qca_set_speed(struct hci_uart *hu, enum qca_speed_type speed_type)
 		case QCA_WCN3998:
 		case QCA_WCN6750:
 		case QCA_WCN6855:
+		case QCA_WCN7850:
 			hci_uart_set_flow_control(hu, false);
 			break;
 
@@ -1756,6 +1760,7 @@ static int qca_power_on(struct hci_dev *hdev)
 	case QCA_WCN3998:
 	case QCA_WCN6750:
 	case QCA_WCN6855:
+	case QCA_WCN7850:
 		ret = qca_regulator_init(hu);
 		break;
 
@@ -1813,6 +1818,10 @@ static int qca_setup(struct hci_uart *hu)
 		soc_name = "wcn6855";
 		break;
 
+	case QCA_WCN7850:
+		soc_name = "wcn7850";
+		break;
+
 	default:
 		soc_name = "ROME/QCA6390";
 	}
@@ -1834,6 +1843,7 @@ static int qca_setup(struct hci_uart *hu)
 	case QCA_WCN3998:
 	case QCA_WCN6750:
 	case QCA_WCN6855:
+	case QCA_WCN7850:
 		set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks);
 		hci_set_aosp_capable(hdev);
 
@@ -1863,6 +1873,7 @@ static int qca_setup(struct hci_uart *hu)
 	case QCA_WCN3998:
 	case QCA_WCN6750:
 	case QCA_WCN6855:
+	case QCA_WCN7850:
 		break;
 
 	default:
@@ -2016,6 +2027,20 @@ static const struct qca_device_data qca_soc_data_wcn6855 = {
 	.capabilities = QCA_CAP_WIDEBAND_SPEECH | QCA_CAP_VALID_LE_STATES,
 };
 
+static const struct qca_device_data qca_soc_data_wcn7850 __maybe_unused = {
+	.soc_type = QCA_WCN7850,
+	.vregs = (struct qca_vreg []) {
+		{ "vddio", 5000 },
+		{ "vddaon", 26000 },
+		{ "vdddig", 126000 },
+		{ "vddrfa0p8", 102000 },
+		{ "vddrfa1p2", 257000 },
+		{ "vddrfa1p9", 302000 },
+	},
+	.num_vregs = 6,
+	.capabilities = QCA_CAP_WIDEBAND_SPEECH | QCA_CAP_VALID_LE_STATES,
+};
+
 static void qca_power_shutdown(struct hci_uart *hu)
 {
 	struct qca_serdev *qcadev;
@@ -2199,6 +2224,7 @@ static int qca_serdev_probe(struct serdev_device *serdev)
 	case QCA_WCN3998:
 	case QCA_WCN6750:
 	case QCA_WCN6855:
+	case QCA_WCN7850:
 		qcadev->bt_power = devm_kzalloc(&serdev->dev,
 						sizeof(struct qca_power),
 						GFP_KERNEL);
@@ -2228,7 +2254,8 @@ static int qca_serdev_probe(struct serdev_device *serdev)
 					       GPIOD_IN);
 		if (IS_ERR_OR_NULL(qcadev->sw_ctrl) &&
 		    (data->soc_type == QCA_WCN6750 ||
-		     data->soc_type == QCA_WCN6855))
+		     data->soc_type == QCA_WCN6855 ||
+		     data->soc_type == QCA_WCN7850))
 			dev_warn(&serdev->dev, "failed to acquire SW_CTRL gpio\n");
 
 		qcadev->susclk = devm_clk_get_optional(&serdev->dev, NULL);
@@ -2307,6 +2334,7 @@ static void qca_serdev_remove(struct serdev_device *serdev)
 	case QCA_WCN3998:
 	case QCA_WCN6750:
 	case QCA_WCN6855:
+	case QCA_WCN7850:
 		if (power->vregs_on) {
 			qca_power_shutdown(&qcadev->serdev_hu);
 			break;
@@ -2499,6 +2527,7 @@ static const struct of_device_id qca_bluetooth_of_match[] = {
 	{ .compatible = "qcom,wcn3998-bt", .data = &qca_soc_data_wcn3998},
 	{ .compatible = "qcom,wcn6750-bt", .data = &qca_soc_data_wcn6750},
 	{ .compatible = "qcom,wcn6855-bt", .data = &qca_soc_data_wcn6855},
+	{ .compatible = "qcom,wcn7850-bt", .data = &qca_soc_data_wcn7850},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, qca_bluetooth_of_match);
Signature · 1 line
2.43.0
author maintainer
#55 lore raw

PATCH 55/215 Bluetooth: hci_qca: Set BDA quirk bit if fwnode exists in DT

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Janaki Ramaiah Thota <[email protected]>

[ Upstream commit 7dcd3e014aa7faeeaf4047190b22d8a19a0db696 ]

BT adapter going into UNCONFIGURED state during BT turn ON when devicetree has no local-bd-address node.

Bluetooth will not work out of the box on such devices, to avoid this problem, added check to set HCI_QUIRK_USE_BDADDR_PROPERTY based on local-bd-address node entry.

When this quirk is not set, the public Bluetooth address read by host from controller though HCI Read BD Address command is considered as valid.

Fixes e668eb1e1578 ("Bluetooth: hci_core: Don't stop BT if the BD address missing in dts")
---
 drivers/bluetooth/hci_qca.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)
drivers/bluetooth/hci_qca.c +12 -1
index 43abdaf92a0ed..8bfef7f81b417 100644
@@ -7,6 +7,7 @@
  *
  *  Copyright (C) 2007 Texas Instruments, Inc.
  *  Copyright (c) 2010, 2012, 2018 The Linux Foundation. All rights reserved.
+ *  Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
  *
  *  Acknowledgements:
  *  This file is based on hci_ll.c, which was...
@@ -1844,7 +1845,17 @@ static int qca_setup(struct hci_uart *hu)
 	case QCA_WCN6750:
 	case QCA_WCN6855:
 	case QCA_WCN7850:
-		set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks);
+
+		/* Set BDA quirk bit for reading BDA value from fwnode property
+		 * only if that property exist in DT.
+		 */
+		if (fwnode_property_present(dev_fwnode(hdev->dev.parent), "local-bd-address")) {
+			set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks);
+			bt_dev_info(hdev, "setting quirk bit to read BDA from fwnode later");
+		} else {
+			bt_dev_dbg(hdev, "local-bd-address` is not present in the devicetree so not setting quirk bit for BDA");
+		}
+
 		hci_set_aosp_capable(hdev);
 
 		ret = qca_read_soc_version(hdev, &ver, soc_type);
Signature · 1 line
2.43.0
author maintainer
#56 lore raw

PATCH 56/215 netfilter: nf_tables: allow NFPROTO_INET in nft_(match/target)_validate()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ignat Korchagin <[email protected]>

[ Upstream commit 7e0f122c65912740327e4c54472acaa5f85868cb ]

Commit d0009effa886 ("netfilter: nf_tables: validate NFPROTO_* family") added some validation of NFPROTO_* families in the nft_compat module, but it broke the ability to use legacy iptables modules in dual-stack nftables.

While with legacy iptables one had to independently manage IPv4 and IPv6 tables, with nftables it is possible to have dual-stack tables sharing the rules. Moreover, it was possible to use rules based on legacy iptables match/target modules in dual-stack nftables.

As an example, the program from [2] creates an INET dual-stack family table using an xt_bpf based rule, which looks like the following (the actual output was generated with a patched nft tool as the current nft tool does not parse dual stack tables with legacy match rules, so consider it for illustrative purposes only):

table inet testfw {
chain input {
type filter hook prerouting priority filter; policy accept; bytecode counter packets 0 bytes 0 accept
}
}

After d0009effa886 ("netfilter: nf_tables: validate NFPROTO_* family") we get EOPNOTSUPP for the above program.

Fix this by allowing NFPROTO_INET for nft_(match/target)_validate(), but also restrict the functions to classic iptables hooks.

Changes in v3:
* clarify that upstream nft will not display such configuration properly and that the output was generated with a patched nft tool
* remove example program from commit description and link to it instead
* no code changes otherwise

Changes in v2:
* restrict nft_(match/target)_validate() to classic iptables hooks
* rewrite example program to use unmodified libnftnl

---
 net/netfilter/nft_compat.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)
net/netfilter/nft_compat.c +20 -0
index e1623fbf36548..e4b8c02c5e6ae 100644
@@ -358,10 +358,20 @@ static int nft_target_validate(const struct nft_ctx *ctx,
 
 	if (ctx->family != NFPROTO_IPV4 &&
 	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET &&
 	    ctx->family != NFPROTO_BRIDGE &&
 	    ctx->family != NFPROTO_ARP)
 		return -EOPNOTSUPP;
 
+	ret = nft_chain_validate_hooks(ctx->chain,
+				       (1 << NF_INET_PRE_ROUTING) |
+				       (1 << NF_INET_LOCAL_IN) |
+				       (1 << NF_INET_FORWARD) |
+				       (1 << NF_INET_LOCAL_OUT) |
+				       (1 << NF_INET_POST_ROUTING));
+	if (ret)
+		return ret;
+
 	if (nft_is_base_chain(ctx->chain)) {
 		const struct nft_base_chain *basechain =
 						nft_base_chain(ctx->chain);
@@ -607,10 +617,20 @@ static int nft_match_validate(const struct nft_ctx *ctx,
 
 	if (ctx->family != NFPROTO_IPV4 &&
 	    ctx->family != NFPROTO_IPV6 &&
+	    ctx->family != NFPROTO_INET &&
 	    ctx->family != NFPROTO_BRIDGE &&
 	    ctx->family != NFPROTO_ARP)
 		return -EOPNOTSUPP;
 
+	ret = nft_chain_validate_hooks(ctx->chain,
+				       (1 << NF_INET_PRE_ROUTING) |
+				       (1 << NF_INET_LOCAL_IN) |
+				       (1 << NF_INET_FORWARD) |
+				       (1 << NF_INET_LOCAL_OUT) |
+				       (1 << NF_INET_POST_ROUTING));
+	if (ret)
+		return ret;
+
 	if (nft_is_base_chain(ctx->chain)) {
 		const struct nft_base_chain *basechain =
 						nft_base_chain(ctx->chain);
Signature · 1 line
2.43.0
author maintainer
#57 lore raw

PATCH 57/215 netfilter: let reset rules clean out conntrack entries

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Florian Westphal <[email protected]>

[ Upstream commit 2954fe60e33da0f4de4d81a4c95c7dddb517d00c ]

iptables/nftables support responding to tcp packets with tcp resets.

The generated tcp reset packet passes through both output and postrouting netfilter hooks, but conntrack will never see them because the generated skb has its ->nfct pointer copied over from the packet that triggered the reset rule.

If the reset rule is used for established connections, this may result in the conntrack entry to be around for a very long time (default timeout is 5 days).

One way to avoid this would be to not copy the nf_conn pointer so that the rest packet passes through conntrack too.

Problem is that output rules might not have the same conntrack zone setup as the prerouting ones, so its possible that the reset skb won't find the correct entry. Generating a template entry for the skb seems error prone as well.

Add an explicit "closing" function that switches a confirmed conntrack entry to closed state and wire this up for tcp.

If the entry isn't confirmed, no action is needed because the conntrack entry will never be committed to the table.

Stable-dep-of: 62e7151ae3eb ("netfilter: bridge: confirm multicast packets before passing them up the stack")

---
 include/linux/netfilter.h              |  3 +++
 include/net/netfilter/nf_conntrack.h   |  8 ++++++
 net/ipv4/netfilter/nf_reject_ipv4.c    |  1 +
 net/ipv6/netfilter/nf_reject_ipv6.c    |  1 +
 net/netfilter/core.c                   | 16 ++++++++++++
 net/netfilter/nf_conntrack_core.c      | 12 +++++++++
 net/netfilter/nf_conntrack_proto_tcp.c | 35 ++++++++++++++++++++++++++
 7 files changed, 76 insertions(+)
include/linux/netfilter.h +3 -0
index bef8db9d6c085..c8e03bcaecaaa 100644
@@ -437,11 +437,13 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family)
 #include <linux/netfilter/nf_conntrack_zones_common.h>
 
 void nf_ct_attach(struct sk_buff *, const struct sk_buff *);
+void nf_ct_set_closing(struct nf_conntrack *nfct);
 struct nf_conntrack_tuple;
 bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple,
 			 const struct sk_buff *skb);
 #else
 static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {}
+static inline void nf_ct_set_closing(struct nf_conntrack *nfct) {}
 struct nf_conntrack_tuple;
 static inline bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple,
 				       const struct sk_buff *skb)
@@ -459,6 +461,7 @@ struct nf_ct_hook {
 	bool (*get_tuple_skb)(struct nf_conntrack_tuple *,
 			      const struct sk_buff *);
 	void (*attach)(struct sk_buff *nskb, const struct sk_buff *skb);
+	void (*set_closing)(struct nf_conntrack *nfct);
 };
 extern const struct nf_ct_hook __rcu *nf_ct_hook;
 
include/net/netfilter/nf_conntrack.h +8 -0
index 6a2019aaa4644..3dbf947285be2 100644
@@ -125,6 +125,12 @@ struct nf_conn {
 	union nf_conntrack_proto proto;
 };
 
+static inline struct nf_conn *
+nf_ct_to_nf_conn(const struct nf_conntrack *nfct)
+{
+	return container_of(nfct, struct nf_conn, ct_general);
+}
+
 static inline struct nf_conn *
 nf_ct_tuplehash_to_ctrack(const struct nf_conntrack_tuple_hash *hash)
 {
@@ -175,6 +181,8 @@ nf_ct_get(const struct sk_buff *skb, enum ip_conntrack_info *ctinfo)
 
 void nf_ct_destroy(struct nf_conntrack *nfct);
 
+void nf_conntrack_tcp_set_closing(struct nf_conn *ct);
+
 /* decrement reference count on a conntrack */
 static inline void nf_ct_put(struct nf_conn *ct)
 {
net/ipv4/netfilter/nf_reject_ipv4.c +1 -0
index 4073762996e22..fc761915c5f6f 100644
@@ -279,6 +279,7 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 		goto free_nskb;
 
 	nf_ct_attach(nskb, oldskb);
+	nf_ct_set_closing(skb_nfct(oldskb));
 
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	/* If we use ip_local_out for bridged traffic, the MAC source on
net/ipv6/netfilter/nf_reject_ipv6.c +1 -0
index 433d98bbe33f7..71d692728230e 100644
@@ -344,6 +344,7 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 	nf_reject_ip6_tcphdr_put(nskb, oldskb, otcph, otcplen);
 
 	nf_ct_attach(nskb, oldskb);
+	nf_ct_set_closing(skb_nfct(oldskb));
 
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	/* If we use ip6_local_out for bridged traffic, the MAC source on
net/netfilter/core.c +16 -0
index 55a7f72d547cd..edf92074221e2 100644
@@ -707,6 +707,22 @@ void nf_conntrack_destroy(struct nf_conntrack *nfct)
 }
 EXPORT_SYMBOL(nf_conntrack_destroy);
 
+void nf_ct_set_closing(struct nf_conntrack *nfct)
+{
+	const struct nf_ct_hook *ct_hook;
+
+	if (!nfct)
+		return;
+
+	rcu_read_lock();
+	ct_hook = rcu_dereference(nf_ct_hook);
+	if (ct_hook)
+		ct_hook->set_closing(nfct);
+
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(nf_ct_set_closing);
+
 bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple,
 			 const struct sk_buff *skb)
 {
net/netfilter/nf_conntrack_core.c +12 -0
index 7960262966094..6d30c64a5fe86 100644
@@ -2772,11 +2772,23 @@ int nf_conntrack_init_start(void)
 	return ret;
 }
 
+static void nf_conntrack_set_closing(struct nf_conntrack *nfct)
+{
+	struct nf_conn *ct = nf_ct_to_nf_conn(nfct);
+
+	switch (nf_ct_protonum(ct)) {
+	case IPPROTO_TCP:
+		nf_conntrack_tcp_set_closing(ct);
+		break;
+	}
+}
+
 static const struct nf_ct_hook nf_conntrack_hook = {
 	.update		= nf_conntrack_update,
 	.destroy	= nf_ct_destroy,
 	.get_tuple_skb  = nf_conntrack_get_tuple_skb,
 	.attach		= nf_conntrack_attach,
+	.set_closing	= nf_conntrack_set_closing,
 };
 
 void nf_conntrack_init_end(void)
net/netfilter/nf_conntrack_proto_tcp.c +35 -0
index e0092bf273fd0..9480e638e5d15 100644
@@ -913,6 +913,41 @@ static bool tcp_can_early_drop(const struct nf_conn *ct)
 	return false;
 }
 
+void nf_conntrack_tcp_set_closing(struct nf_conn *ct)
+{
+	enum tcp_conntrack old_state;
+	const unsigned int *timeouts;
+	u32 timeout;
+
+	if (!nf_ct_is_confirmed(ct))
+		return;
+
+	spin_lock_bh(&ct->lock);
+	old_state = ct->proto.tcp.state;
+	ct->proto.tcp.state = TCP_CONNTRACK_CLOSE;
+
+	if (old_state == TCP_CONNTRACK_CLOSE ||
+	    test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status)) {
+		spin_unlock_bh(&ct->lock);
+		return;
+	}
+
+	timeouts = nf_ct_timeout_lookup(ct);
+	if (!timeouts) {
+		const struct nf_tcp_net *tn;
+
+		tn = nf_tcp_pernet(nf_ct_net(ct));
+		timeouts = tn->timeouts;
+	}
+
+	timeout = timeouts[TCP_CONNTRACK_CLOSE];
+	WRITE_ONCE(ct->timeout, timeout + nfct_time_stamp);
+
+	spin_unlock_bh(&ct->lock);
+
+	nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
+}
+
 static void nf_ct_tcp_state_reset(struct ip_ct_tcp_state *state)
 {
 	state->td_end		= 0;
Signature · 1 line
2.43.0
author maintainer
#58 lore raw

PATCH 58/215 netfilter: bridge: confirm multicast packets before passing them up the stack

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Florian Westphal <[email protected]>

[ Upstream commit 62e7151ae3eb465e0ab52a20c941ff33bb6332e9 ]

conntrack nf_confirm logic cannot handle cloned skbs referencing the same nf_conn entry, which will happen for multicast (broadcast) frames on bridges.

Example:

    macvlan0
       |
      br0
     /  \

ethX ethY

ethX (or Y) receives a L2 multicast or broadcast packet containing an IP packet, flow is not yet in conntrack table.

1. skb passes through bridge and fake-ip (br_netfilter)Prerouting.

    -> skb->_nfct now references a unconfirmed entry

2. skb is broad/mcast packet. bridge now passes clones out on each bridge interface.
3. skb gets passed up the stack.
4. In macvlan case, macvlan driver retains clone(s) of the mcast skb and schedules a work queue to send them out on the lower devices.

The clone skb->_nfct is not a copy, it is the same entry as the original skb. The macvlan rx handler then returns RX_HANDLER_PASS.
5. Normal conntrack hooks (in NF_INET_LOCAL_IN) confirm the orig skb.

The Macvlan broadcast worker and normal confirm path will race.

This race will not happen if step 2 already confirmed a clone. In that case later steps perform skb_clone() with skb->_nfct already confirmed (in hash table). This works fine.

But such confirmation won't happen when eb/ip/nftables rules dropped the packets before they reached the nf_confirm step in postrouting.

Pablo points out that nf_conntrack_bridge doesn't allow use of stateful nat, so we can safely discard the nf_conn entry and let inet call conntrack again.

This doesn't work for bridge netfilter: skb could have a nat transformation. Also bridge nf prevents re-invocation of inet prerouting via 'sabotage_in' hook.

Work around this problem by explicit confirmation of the entry at LOCAL_IN time, before upper layer has a chance to clone the unconfirmed entry.

The downside is that this disables NAT and conntrack helpers.

Alternative fix would be to add locking to all code parts that deal with unconfirmed packets, but even if that could be done in a sane way this opens up other problems, for example:

-m physdev --physdev-out eth0 -j SNAT --snat-to 1.2.3.4 -m physdev --physdev-out eth1 -j SNAT --snat-to 1.2.3.5

For multicast case, only one of such conflicting mappings will be created, conntrack only handles 1:1 NAT mappings.

Users should set create a setup that explicitly marks such traffic NOTRACK (conntrack bypass) to avoid this, but we cannot auto-bypass them, ruleset might have accept rules for untracked traffic already, so user-visible behaviour would change.

---
 include/linux/netfilter.h                  |  1 +
 net/bridge/br_netfilter_hooks.c            | 96 ++++++++++++++++++++++
 net/bridge/netfilter/nf_conntrack_bridge.c | 30 +++++++
 net/netfilter/nf_conntrack_core.c          |  1 +
 4 files changed, 128 insertions(+)
include/linux/netfilter.h +1 -0
index c8e03bcaecaaa..e5f4b6f8d1c09 100644
@@ -462,6 +462,7 @@ struct nf_ct_hook {
 			      const struct sk_buff *);
 	void (*attach)(struct sk_buff *nskb, const struct sk_buff *skb);
 	void (*set_closing)(struct nf_conntrack *nfct);
+	int (*confirm)(struct sk_buff *skb);
 };
 extern const struct nf_ct_hook __rcu *nf_ct_hook;
 
net/bridge/br_netfilter_hooks.c +96 -0

114 lines not on this page · raw message

net/bridge/netfilter/nf_conntrack_bridge.c +30 -0
index 06d94b2c6b5de..c7c27ada67044 100644
@@ -291,6 +291,30 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb,
 	return nf_conntrack_in(skb, &bridge_state);
 }
 
+static unsigned int nf_ct_bridge_in(void *priv, struct sk_buff *skb,
+				    const struct nf_hook_state *state)
+{
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct;
+
+	if (skb->pkt_type == PACKET_HOST)
+		return NF_ACCEPT;
+
+	/* nf_conntrack_confirm() cannot handle concurrent clones,
+	 * this happens for broad/multicast frames with e.g. macvlan on top
+	 * of the bridge device.
+	 */
+	ct = nf_ct_get(skb, &ctinfo);
+	if (!ct || nf_ct_is_confirmed(ct) || nf_ct_is_template(ct))
+		return NF_ACCEPT;
+
+	/* let inet prerouting call conntrack again */
+	skb->_nfct = 0;
+	nf_ct_put(ct);
+
+	return NF_ACCEPT;
+}
+
 static void nf_ct_bridge_frag_save(struct sk_buff *skb,
 				   struct nf_bridge_frag_data *data)
 {
@@ -415,6 +439,12 @@ static struct nf_hook_ops nf_ct_bridge_hook_ops[] __read_mostly = {
 		.hooknum	= NF_BR_PRE_ROUTING,
 		.priority	= NF_IP_PRI_CONNTRACK,
 	},
+	{
+		.hook		= nf_ct_bridge_in,
+		.pf		= NFPROTO_BRIDGE,
+		.hooknum	= NF_BR_LOCAL_IN,
+		.priority	= NF_IP_PRI_CONNTRACK_CONFIRM,
+	},
 	{
 		.hook		= nf_ct_bridge_post,
 		.pf		= NFPROTO_BRIDGE,
net/netfilter/nf_conntrack_core.c +1 -0
index 6d30c64a5fe86..024f93fc8c0bb 100644
@@ -2789,6 +2789,7 @@ static const struct nf_ct_hook nf_conntrack_hook = {
 	.get_tuple_skb  = nf_conntrack_get_tuple_skb,
 	.attach		= nf_conntrack_attach,
 	.set_closing	= nf_conntrack_set_closing,
+	.confirm	= __nf_conntrack_confirm,
 };
 
 void nf_conntrack_init_end(void)
Signature · 1 line
2.43.0
author maintainer
#41 lore raw

PATCH 41/215 stmmac: Clear variable when destroying workqueue

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jakub Raczynski <[email protected]>

[ Upstream commit 8af411bbba1f457c33734795f024d0ef26d0963f ]

Currently when suspending driver and stopping workqueue it is checked whether workqueue is not NULL and if so, it is destroyed.
Function destroy_workqueue() does drain queue and does clear variable, but it does not set workqueue variable to NULL. This can cause kernel/module panic if code attempts to clear workqueue that was not initialized.

This scenario is possible when resuming suspended driver in stmmac_resume(), because there is no handling for failed stmmac_hw_setup(),
which can fail and return if DMA engine has failed to initialize, and workqueue is initialized after DMA engine.
Should DMA engine fail to initialize, resume will proceed normally, but interface won't work and TX queue will eventually timeout, causing 'Reset adapter' error.
This then does destroy workqueue during reset process.
And since workqueue is initialized after DMA engine and can be skipped, it will cause kernel/module panic.

To secure against this possible crash, set workqueue variable to NULL when destroying workqueue.

Log/backtrace from crash goes as follows:

[88.031977]------------[ cut here ]------------
[88.031985]NETDEV WATCHDOG: eth0 (sxgmac): transmit queue 1 timed out
[88.032017]WARNING: CPU: 0 PID: 0 at net/sched/sch_generic.c:477 dev_watchdog+0x390/0x398
           <Skipping backtrace for watchdog timeout>
[88.032251]---[ end trace e70de432e4d5c2c0 ]---
[88.032282]sxgmac 16d88000.ethernet eth0: Reset adapter.
[88.036359]------------[ cut here ]------------
[88.036519]Call trace:
[88.036523] flush_workqueue+0x3e4/0x430
[88.036528] drain_workqueue+0xc4/0x160
[88.036533] destroy_workqueue+0x40/0x270
[88.036537] stmmac_fpe_stop_wq+0x4c/0x70
[88.036541] stmmac_release+0x278/0x280
[88.036546] __dev_close_many+0xcc/0x158
[88.036551] dev_close_many+0xbc/0x190
[88.036555] dev_close.part.0+0x70/0xc0
[88.036560] dev_close+0x24/0x30
[88.036564] stmmac_service_task+0x110/0x140
[88.036569] process_one_work+0x1d8/0x4a0
[88.036573] worker_thread+0x54/0x408
[88.036578] kthread+0x164/0x170
[88.036583] ret_from_fork+0x10/0x20
[88.036588]---[ end trace e70de432e4d5c2c1 ]---
[88.036597]Unable to handle kernel NULL pointer dereference at virtual address 0000000000000004
Fixes 5a5586112b929 ("net: stmmac: support FPE link partner hand-shaking procedure")
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +3 -1
index 91b2aa81914ba..e2d51014ab4bc 100644
@@ -3900,8 +3900,10 @@ static void stmmac_fpe_stop_wq(struct stmmac_priv *priv)
 {
 	set_bit(__FPE_REMOVING, &priv->fpe_task_state);
 
-	if (priv->fpe_wq)
+	if (priv->fpe_wq) {
 		destroy_workqueue(priv->fpe_wq);
+		priv->fpe_wq = NULL;
+	}
 
 	netdev_info(priv->dev, "FPE workqueue stop");
 }
Signature · 1 line
2.43.0
author maintainer
#59 lore raw

PATCH 59/215 rtnetlink: fix error logic of IFLA_BRIDGE_FLAGS writing back

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Lin Ma <[email protected]>

[ Upstream commit 743ad091fb46e622f1b690385bb15e3cd3daf874 ]

In the commit d73ef2d69c0d ("rtnetlink: let rtnl_bridge_setlink checks IFLA_BRIDGE_MODE length"), an adjustment was made to the old loop logic in the function rtnl_bridge_setlink to enable the loop to also check the length of the IFLA_BRIDGE_MODE attribute. However, this adjustment removed the break statement and led to an error logic of the flags writing back at the end of this function.

if (have_flags)

    memcpy(nla_data(attr), &flags, sizeof(flags));
    // attr should point to IFLA_BRIDGE_FLAGS NLA !!!

Before the mentioned commit, the attr is granted to be IFLA_BRIDGE_FLAGS. However, this is not necessarily true fow now as the updated loop will let the attr point to the last NLA, even an invalid NLA which could cause overflow writes.

This patch introduces a new variable br_flag to save the NLA pointer that points to IFLA_BRIDGE_FLAGS and uses it to resolve the mentioned error logic.

Fixes d73ef2d69c0d ("rtnetlink: let rtnl_bridge_setlink checks IFLA_BRIDGE_MODE length")
---
 net/core/rtnetlink.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)
net/core/rtnetlink.c +5 -6
index 7cf1e42d7f93b..ac379e4590f8d 100644
@@ -5026,10 +5026,9 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net *net = sock_net(skb->sk);
 	struct ifinfomsg *ifm;
 	struct net_device *dev;
-	struct nlattr *br_spec, *attr = NULL;
+	struct nlattr *br_spec, *attr, *br_flags_attr = NULL;
 	int rem, err = -EOPNOTSUPP;
 	u16 flags = 0;
-	bool have_flags = false;
 
 	if (nlmsg_len(nlh) < sizeof(*ifm))
 		return -EINVAL;
@@ -5047,11 +5046,11 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 	br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
 	if (br_spec) {
 		nla_for_each_nested(attr, br_spec, rem) {
-			if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !have_flags) {
+			if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !br_flags_attr) {
 				if (nla_len(attr) < sizeof(flags))
 					return -EINVAL;
 
-				have_flags = true;
+				br_flags_attr = attr;
 				flags = nla_get_u16(attr);
 			}
 
@@ -5095,8 +5094,8 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 		}
 	}
 
-	if (have_flags)
-		memcpy(nla_data(attr), &flags, sizeof(flags));
+	if (br_flags_attr)
+		memcpy(nla_data(br_flags_attr), &flags, sizeof(flags));
 out:
 	return err;
 }
Signature · 1 line
2.43.0
author maintainer
#60 lore raw

PATCH 60/215 igb: extend PTP timestamp adjustments to i211

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Oleksij Rempel <[email protected]>

[ Upstream commit 0bb7b09392eb74b152719ae87b1ba5e4bf910ef0 ]

The i211 requires the same PTP timestamp adjustments as the i210, according to its datasheet. To ensure consistent timestamping across different platforms, this change extends the existing adjustments to include the i211.

The adjustment result are tested and comparable for i210 and i211 based systems.

---
 drivers/net/ethernet/intel/igb/igb_ptp.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
drivers/net/ethernet/intel/igb/igb_ptp.c +3 -2
index 07171e574e7d7..36e62197fba0b 100644
@@ -976,7 +976,7 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter)
 
 	igb_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval);
 	/* adjust timestamp for the TX latency based on link speed */
-	if (adapter->hw.mac.type == e1000_i210) {
+	if (hw->mac.type == e1000_i210 || hw->mac.type == e1000_i211) {
 		switch (adapter->link_speed) {
 		case SPEED_10:
 			adjust = IGB_I210_TX_LATENCY_10;
@@ -1022,6 +1022,7 @@ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
 			ktime_t *timestamp)
 {
 	struct igb_adapter *adapter = q_vector->adapter;
+	struct e1000_hw *hw = &adapter->hw;
 	struct skb_shared_hwtstamps ts;
 	__le64 *regval = (__le64 *)va;
 	int adjust = 0;
@@ -1041,7 +1042,7 @@ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
 	igb_ptp_systim_to_hwtstamp(adapter, &ts, le64_to_cpu(regval[1]));
 
 	/* adjust timestamp for the RX latency based on link speed */
-	if (adapter->hw.mac.type == e1000_i210) {
+	if (hw->mac.type == e1000_i210 || hw->mac.type == e1000_i211) {
 		switch (adapter->link_speed) {
 		case SPEED_10:
 			adjust = IGB_I210_RX_LATENCY_10;
Signature · 1 line
2.43.0
author maintainer
#61 lore raw

PATCH 61/215 net: hsr: Use correct offset for HSR TLV values in supervisory HSR frames

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Lukasz Majewski <[email protected]>

[ Upstream commit 51dd4ee0372228ffb0f7709fa7aa0678d4199d06 ]

Current HSR implementation uses following supervisory frame (even for HSRv1 the HSR tag is not is not present):

00000000: 01 15 4e 00 01 2d XX YY ZZ 94 77 10 88 fb 00 01 00000010: 7e 1c 17 06 XX YY ZZ 94 77 10 1e 06 XX YY ZZ 94 00000020: 77 10 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00000030: 00 00 00 00 00 00 00 00 00 00 00 00

The current code adds extra two bytes (i.e. sizeof(struct hsr_sup_tlv)) when offset for skb_pull() is calculated.
This is wrong, as both 'struct hsrv1_ethhdr_sp' and 'hsrv0_ethhdr_sp' already have 'struct hsr_sup_tag' defined in them, so there is no need for adding extra two bytes.

This code was working correctly as with no RedBox support, the check for HSR_TLV_EOT (0x00) was off by two bytes, which were corresponding to zeroed padded bytes for minimal packet size.

Fixes eafaa88b3eb7 ("net: hsr: Add support for redbox supervision frames")
---
 net/hsr/hsr_forward.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
net/hsr/hsr_forward.c +1 -1
index 80cdc6f6b34c9..0323ab5023c69 100644
@@ -83,7 +83,7 @@ static bool is_supervision_frame(struct hsr_priv *hsr, struct sk_buff *skb)
 		return false;
 
 	/* Get next tlv */
-	total_length += sizeof(struct hsr_sup_tlv) + hsr_sup_tag->tlv.HSR_TLV_length;
+	total_length += hsr_sup_tag->tlv.HSR_TLV_length;
 	if (!pskb_may_pull(skb, total_length))
 		return false;
 	skb_pull(skb, total_length);
Signature · 1 line
2.43.0
author maintainer
#62 lore raw

PATCH 62/215 tls: decrement decrypt_pending if no async completion will be called

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sabrina Dubroca <[email protected]>

[ Upstream commit f7fa16d49837f947ee59492958f9e6f0e51d9a78 ]

With mixed sync/async decryption, or failures of crypto_aead_decrypt, we increment decrypt_pending but we never do the corresponding decrement since tls_decrypt_done will not be called. In this case, we should decrement decrypt_pending immediately to avoid getting stuck.

For example, the prequeue prequeue test gets stuck with mixed modes (one async decrypt + one sync decrypt).

---
 net/tls/tls_sw.c | 2 ++
 1 file changed, 2 insertions(+)
net/tls/tls_sw.c +2 -0
index 93e1bfa72d791..c6ad435a44218 100644
@@ -273,6 +273,8 @@ static int tls_do_decryption(struct sock *sk,
 			return 0;
 
 		ret = crypto_wait_req(ret, &ctx->async_wait);
+	} else if (darg->async) {
+		atomic_dec(&ctx->decrypt_pending);
 	}
 	darg->async = false;
 
Signature · 1 line
2.43.0
author maintainer
#63 lore raw

PATCH 63/215 tls: fix peeking with sync+async decryption

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sabrina Dubroca <[email protected]>

[ Upstream commit 6caaf104423d809b49a67ee6500191d063b40dc6 ]

If we peek from 2 records with a currently empty rx_list, and the first record is decrypted synchronously but the second record is decrypted async, the following happens:
1. decrypt record 1 (sync)
2. copy from record 1 to the userspace's msg
3. queue the decrypted record to rx_list for future read(!PEEK)
4. decrypt record 2 (async)
5. queue record 2 to rx_list
6. call process_rx_list to copy data from the 2nd record

We currently pass copied=0 as skip offset to process_rx_list, so we end up copying once again from the first record. We should skip over the data we've already copied.

Seen with selftest tls.12_aes_gcm.recv_peek_large_buf_mult_recs

---
 net/tls/tls_sw.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)
net/tls/tls_sw.c +6 -3
index c6ad435a44218..2bd27b77769cb 100644
@@ -2023,6 +2023,7 @@ int tls_sw_recvmsg(struct sock *sk,
 	struct strp_msg *rxm;
 	struct tls_msg *tlm;
 	ssize_t copied = 0;
+	ssize_t peeked = 0;
 	bool async = false;
 	int target, err;
 	bool is_kvec = iov_iter_is_kvec(&msg->msg_iter);
@@ -2170,8 +2171,10 @@ int tls_sw_recvmsg(struct sock *sk,
 			if (err < 0)
 				goto put_on_rx_list_err;
 
-			if (is_peek)
+			if (is_peek) {
+				peeked += chunk;
 				goto put_on_rx_list;
+			}
 
 			if (partially_consumed) {
 				rxm->offset += chunk;
@@ -2210,8 +2213,8 @@ int tls_sw_recvmsg(struct sock *sk,
 
 		/* Drain records from the rx_list & copy if required */
 		if (is_peek || is_kvec)
-			err = process_rx_list(ctx, msg, &control, copied,
-					      decrypted, is_peek, NULL);
+			err = process_rx_list(ctx, msg, &control, copied + peeked,
+					      decrypted - peeked, is_peek, NULL);
 		else
 			err = process_rx_list(ctx, msg, &control, 0,
 					      async_copy_bytes, is_peek, NULL);
Signature · 1 line
2.43.0
author maintainer
#64 lore raw

PATCH 64/215 efi/capsule-loader: fix incorrect allocation size

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Arnd Bergmann <[email protected]>

[ Upstream commit fccfa646ef3628097d59f7d9c1a3e84d4b6bb45e ]

gcc-14 notices that the allocation with sizeof(void) on 32-bit architectures is not enough for a 64-bit phys_addr_t:

drivers/firmware/efi/capsule-loader.c: In function 'efi_capsule_open':
drivers/firmware/efi/capsule-loader.c:295:24: error: allocation of insufficient size '4' for type 'phys_addr_t' {aka 'long long unsigned int'} with size '8' [-Werror=alloc-size]
295 | cap_info->phys = kzalloc(sizeof(void *), GFP_KERNEL);
| ^

Use the correct type instead here.

Fixes f24c4d478013 ("efi/capsule-loader: Reinstate virtual capsule mapping")
---
 drivers/firmware/efi/capsule-loader.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/firmware/efi/capsule-loader.c +1 -1
index 3e8d4b51a8140..97bafb5f70389 100644
@@ -292,7 +292,7 @@ static int efi_capsule_open(struct inode *inode, struct file *file)
 		return -ENOMEM;
 	}
 
-	cap_info->phys = kzalloc(sizeof(void *), GFP_KERNEL);
+	cap_info->phys = kzalloc(sizeof(phys_addr_t), GFP_KERNEL);
 	if (!cap_info->phys) {
 		kfree(cap_info->pages);
 		kfree(cap_info);
Signature · 1 line
2.43.0
author maintainer
#65 lore raw

PATCH 65/215 power: supply: bq27xxx-i2c: Do not free non existing IRQ

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hans de Goede <[email protected]>

[ Upstream commit 2df70149e73e79783bcbc7db4fa51ecef0e2022c ]

The bq27xxx i2c-client may not have an IRQ, in which case client->irq will be 0. bq27xxx_battery_i2c_probe() already has an if (client->irq) check wrapping the request_threaded_irq().

But bq27xxx_battery_i2c_remove() unconditionally calls free_irq(client->irq) leading to:

[  190.310742] ------------[ cut here ]------------
[  190.310843] Trying to free already-free IRQ 0
[  190.310861] WARNING: CPU: 2 PID: 1304 at kernel/irq/manage.c:1893 free_irq+0x1b8/0x310

Followed by a backtrace when unbinding the driver. Add an if (client->irq) to bq27xxx_battery_i2c_remove() mirroring probe() to fix this.

Fixes 444ff00734f3 ("power: supply: bq27xxx: Fix I2C IRQ race on remove")
---
 drivers/power/supply/bq27xxx_battery_i2c.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/power/supply/bq27xxx_battery_i2c.c +3 -1
index 0713a52a25107..17b37354e32c0 100644
@@ -209,7 +209,9 @@ static void bq27xxx_battery_i2c_remove(struct i2c_client *client)
 {
 	struct bq27xxx_device_info *di = i2c_get_clientdata(client);
 
-	free_irq(client->irq, di);
+	if (client->irq)
+		free_irq(client->irq, di);
+
 	bq27xxx_battery_teardown(di);
 
 	mutex_lock(&battery_mutex);
Signature · 1 line
2.43.0
author maintainer
#42 lore raw

PATCH 42/215 Bluetooth: hci_sync: Check the correct flag before starting a scan

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jonas Dreßler <[email protected]>

[ Upstream commit 6b3899be24b16ff8ee0cb25f0bd59b01b15ba1d1 ]

There's a very confusing mistake in the code starting a HCI inquiry: We're calling hci_dev_test_flag() to test for HCI_INQUIRY, but hci_dev_test_flag() checks hdev->dev_flags instead of hdev->flags. HCI_INQUIRY is a bit that's set on hdev->flags, not on hdev->dev_flags though.

HCI_INQUIRY equals the integer 7, and in hdev->dev_flags, 7 means HCI_BONDABLE, so we were actually checking for HCI_BONDABLE here.

The mistake is only present in the synchronous code for starting an inquiry, not in the async one. Also devices are typically bondable while doing an inquiry, so that might be the reason why nobody noticed it so far.

Fixes abfeea476c68 ("Bluetooth: hci_sync: Convert MGMT_OP_START_DISCOVERY")
---
 net/bluetooth/hci_sync.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
net/bluetooth/hci_sync.c +1 -1
index 45d19294aa772..13ed6cbfade3e 100644
@@ -5482,7 +5482,7 @@ static int hci_inquiry_sync(struct hci_dev *hdev, u8 length)
 
 	bt_dev_dbg(hdev, "");
 
-	if (hci_dev_test_flag(hdev, HCI_INQUIRY))
+	if (test_bit(HCI_INQUIRY, &hdev->flags))
 		return 0;
 
 	hci_dev_lock(hdev);
Signature · 1 line
2.43.0
author maintainer
#43 lore raw

PATCH 43/215 Bluetooth: Avoid potential use-after-free in hci_error_reset

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ying Hsu <[email protected]>

[ Upstream commit 2449007d3f73b2842c9734f45f0aadb522daf592 ]

While handling the HCI_EV_HARDWARE_ERROR event, if the underlying BT controller is not responding, the GPIO reset mechanism would free the hci_dev and lead to a use-after-free in hci_error_reset.

Here's the call trace observed on a ChromeOS device with Intel AX201:

   queue_work_on+0x3e/0x6c
   __hci_cmd_sync_sk+0x2ee/0x4c0 [bluetooth <HASH:3b4a6>]
   ? init_wait_entry+0x31/0x31
   __hci_cmd_sync+0x16/0x20 [bluetooth <HASH:3b4a 6>]
   hci_error_reset+0x4f/0xa4 [bluetooth <HASH:3b4a 6>]
   process_one_work+0x1d8/0x33f
   worker_thread+0x21b/0x373
   kthread+0x13a/0x152
   ? pr_cont_work+0x54/0x54
   ? kthread_blkcg+0x31/0x31
    ret_from_fork+0x1f/0x30

This patch holds the reference count on the hci_dev while processing a HCI_EV_HARDWARE_ERROR event to avoid potential crash.

Fixes c7741d16a57c ("Bluetooth: Perform a power cycle when receiving hardware error event")
---
 net/bluetooth/hci_core.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)
net/bluetooth/hci_core.c +4 -3
index 6a1db678d032f..a8932d449eb63 100644
@@ -1049,6 +1049,7 @@ static void hci_error_reset(struct work_struct *work)
 {
 	struct hci_dev *hdev = container_of(work, struct hci_dev, error_reset);
 
+	hci_dev_hold(hdev);
 	BT_DBG("%s", hdev->name);
 
 	if (hdev->hw_error)
@@ -1056,10 +1057,10 @@ static void hci_error_reset(struct work_struct *work)
 	else
 		bt_dev_err(hdev, "hardware error 0x%2.2x", hdev->hw_error_code);
 
-	if (hci_dev_do_close(hdev))
-		return;
+	if (!hci_dev_do_close(hdev))
+		hci_dev_do_open(hdev);
 
-	hci_dev_do_open(hdev);
+	hci_dev_put(hdev);
 }
 
 void hci_uuids_clear(struct hci_dev *hdev)
Signature · 1 line
2.43.0
author maintainer
#44 lore raw

PATCH 44/215 Bluetooth: hci_sync: Fix accept_list when attempting to suspend

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Luiz Augusto von Dentz <[email protected]>

[ Upstream commit e5469adb2a7e930d96813316592302d9f8f1df4e ]

During suspend, only wakeable devices can be in acceptlist, so if the device was previously added it needs to be removed otherwise the device can end up waking up the system prematurely.

Fixes 3b42055388c3 ("Bluetooth: hci_sync: Fix attempting to suspend with unfiltered passive scan")
---
 net/bluetooth/hci_sync.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
net/bluetooth/hci_sync.c +4 -1
index 13ed6cbfade3e..a337340464567 100644
@@ -2251,8 +2251,11 @@ static int hci_le_add_accept_list_sync(struct hci_dev *hdev,
 
 	/* During suspend, only wakeable devices can be in acceptlist */
 	if (hdev->suspended &&
-	    !(params->flags & HCI_CONN_FLAG_REMOTE_WAKEUP))
+	    !(params->flags & HCI_CONN_FLAG_REMOTE_WAKEUP)) {
+		hci_le_del_accept_list_sync(hdev, &params->addr,
+					    params->addr_type);
 		return 0;
+	}
 
 	/* Select filter policy to accept all advertising */
 	if (*num_entries >= hdev->le_accept_list_size)
Signature · 1 line
2.43.0
author maintainer
#45 lore raw

PATCH 45/215 Bluetooth: hci_event: Fix wrongly recorded wakeup BD_ADDR

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Zijun Hu <[email protected]>

[ Upstream commit 61a5ab72edea7ebc3ad2c6beea29d966f528ebfb ]

hci_store_wake_reason() wrongly parses event HCI_Connection_Request as HCI_Connection_Complete and HCI_Connection_Complete as HCI_Connection_Request, so causes recording wakeup BD_ADDR error and potential stability issue, fix it by using the correct field.

Fixes 2f20216c1d6f ("Bluetooth: Emit controller suspend and resume events")
---
 net/bluetooth/hci_event.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
net/bluetooth/hci_event.c +2 -2
index 56ecc5f97b916..b18f5e5df8ad0 100644
@@ -7245,10 +7245,10 @@ static void hci_store_wake_reason(struct hci_dev *hdev, u8 event,
 	 * keep track of the bdaddr of the connection event that woke us up.
 	 */
 	if (event == HCI_EV_CONN_REQUEST) {
-		bacpy(&hdev->wake_addr, &conn_complete->bdaddr);
+		bacpy(&hdev->wake_addr, &conn_request->bdaddr);
 		hdev->wake_addr_type = BDADDR_BREDR;
 	} else if (event == HCI_EV_CONN_COMPLETE) {
-		bacpy(&hdev->wake_addr, &conn_request->bdaddr);
+		bacpy(&hdev->wake_addr, &conn_complete->bdaddr);
 		hdev->wake_addr_type = BDADDR_BREDR;
 	} else if (event == HCI_EV_LE_META) {
 		struct hci_ev_le_meta *le_ev = (void *)skb->data;
Signature · 1 line
2.43.0
author maintainer
#46 lore raw

PATCH 46/215 Bluetooth: hci_event: Fix handling of HCI_EV_IO_CAPA_REQUEST

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Luiz Augusto von Dentz <[email protected]>

[ Upstream commit 7e74aa53a68bf60f6019bd5d9a9a1406ec4d4865 ]

If we received HCI_EV_IO_CAPA_REQUEST while HCI_OP_READ_REMOTE_EXT_FEATURES is yet to be responded assume the remote does support SSP since otherwise this event shouldn't be generated.

---
 net/bluetooth/hci_event.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
net/bluetooth/hci_event.c +4 -1
index b18f5e5df8ad0..f79aaef5a276d 100644
@@ -5282,9 +5282,12 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, void *data,
 	hci_dev_lock(hdev);
 
 	conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr);
-	if (!conn || !hci_conn_ssp_enabled(conn))
+	if (!conn || !hci_dev_test_flag(hdev, HCI_SSP_ENABLED))
 		goto unlock;
 
+	/* Assume remote supports SSP since it has triggered this event */
+	set_bit(HCI_CONN_SSP_ENABLED, &conn->flags);
+
 	hci_conn_hold(conn);
 
 	if (!hci_dev_test_flag(hdev, HCI_MGMT))
Signature · 1 line
2.43.0
author maintainer
#47 lore raw

PATCH 47/215 Bluetooth: Enforce validation on max value of connection interval

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kai-Heng Feng <[email protected]>

[ Upstream commit e4b019515f950b4e6e5b74b2e1bb03a90cb33039 ]

Right now Linux BT stack cannot pass test case "GAP/CONN/CPUP/BV-05-C 'Connection Parameter Update Procedure Invalid Parameters Central Responder'" in Bluetooth Test Suite revision GAP.TS.p44. [0]

That was revoled by commit c49a8682fc5d ("Bluetooth: validate BLE connection interval updates"), but later got reverted due to devices like keyboards and mice may require low connection interval.

So only validate the max value connection interval to pass the Test Suite, and let devices to request low connection interval if needed.

[0] https://www.bluetooth.org/docman/handlers/DownloadDoc.ashx?doc_id=229869

Fixes 68d19d7d9957 ("Revert "Bluetooth: validate BLE connection interval updates"")
---
 net/bluetooth/hci_event.c  | 4 ++++
 net/bluetooth/l2cap_core.c | 8 +++++++-
 2 files changed, 11 insertions(+), 1 deletion(-)
net/bluetooth/hci_event.c +4 -0
index f79aaef5a276d..452d839c152fc 100644
@@ -6719,6 +6719,10 @@ static void hci_le_remote_conn_param_req_evt(struct hci_dev *hdev, void *data,
 		return send_conn_param_neg_reply(hdev, handle,
 						 HCI_ERROR_UNKNOWN_CONN_ID);
 
+	if (max > hcon->le_conn_max_interval)
+		return send_conn_param_neg_reply(hdev, handle,
+						 HCI_ERROR_INVALID_LL_PARAMS);
+
 	if (hci_check_conn_params(min, max, latency, timeout))
 		return send_conn_param_neg_reply(hdev, handle,
 						 HCI_ERROR_INVALID_LL_PARAMS);
net/bluetooth/l2cap_core.c +7 -1
index 81f5974e5eb5a..b4cba55be5ad9 100644
@@ -5614,7 +5614,13 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn,
 
 	memset(&rsp, 0, sizeof(rsp));
 
-	err = hci_check_conn_params(min, max, latency, to_multiplier);
+	if (max > hcon->le_conn_max_interval) {
+		BT_DBG("requested connection interval exceeds current bounds.");
+		err = -EINVAL;
+	} else {
+		err = hci_check_conn_params(min, max, latency, to_multiplier);
+	}
+
 	if (err)
 		rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_REJECTED);
 	else
Signature · 1 line
2.43.0
author maintainer
#48 lore raw

PATCH 48/215 Bluetooth: qca: Fix wrong event type for patch config command

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Zijun Hu <[email protected]>

[ Upstream commit c0dbc56077ae759f2dd602c7561480bc2b1b712c ]

Vendor-specific command patch config has HCI_Command_Complete event as response, but qca_send_patch_config_cmd() wrongly expects vendor-specific event for the command, fixed by using right event type.

Btmon log for the vendor-specific command are shown below:
< HCI Command: Vendor (0x3f|0x0000) plen 5

        28 01 00 00 00
Quoted 1 line

HCI Event: Command Complete (0x0e) plen 5

      Vendor (0x3f|0x0000) ncmd 1
        Status: Success (0x00)
        28
Fixes 4fac8a7ac80b ("Bluetooth: btqca: sequential validation")
---
 drivers/bluetooth/btqca.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/bluetooth/btqca.c +1 -1
index c9064d34d8308..d7d0c9de3dc31 100644
@@ -152,7 +152,7 @@ static int qca_send_patch_config_cmd(struct hci_dev *hdev)
 	bt_dev_dbg(hdev, "QCA Patch config");
 
 	skb = __hci_cmd_sync_ev(hdev, EDL_PATCH_CMD_OPCODE, sizeof(cmd),
-				cmd, HCI_EV_VENDOR, HCI_INIT_TIMEOUT);
+				cmd, 0, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		err = PTR_ERR(skb);
 		bt_dev_err(hdev, "Sending QCA Patch config failed (%d)", err);
Signature · 1 line
2.43.0
author maintainer
#39 lore raw

PATCH 39/215 net: lan78xx: fix "softirq work is pending" error

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Oleksij Rempel <[email protected]>

[ Upstream commit e3d5d70cb483df8296dd44e9ae3b6355ef86494c ]

Disable BH around the call to napi_schedule() to avoid following error:
NOHZ tick-stop error: local softirq work is pending, handler #08!!!

Fixes ec4c7e12396b ("lan78xx: Introduce NAPI polling support")
---
 drivers/net/usb/lan78xx.c | 2 ++
 1 file changed, 2 insertions(+)
drivers/net/usb/lan78xx.c +2 -0
index 7b9d480e44fe4..4fd4563811299 100644
@@ -1501,7 +1501,9 @@ static int lan78xx_link_reset(struct lan78xx_net *dev)
 
 		lan78xx_rx_urb_submit_all(dev);
 
+		local_bh_disable();
 		napi_schedule(&dev->napi);
+		local_bh_enable();
 	}
 
 	return 0;
Signature · 1 line
2.43.0
author maintainer
#67 lore raw

PATCH 67/215 drm/tegra: Remove existing framebuffer only if we support display

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thierry Reding <[email protected]>

[ Upstream commit 86bf8cfda6d2a6720fa2e6e676c98f0882c9d3d7 ]

Tegra DRM doesn't support display on Tegra234 and later, so make sure not to remove any existing framebuffers in that case.

v2: - add comments explaining how this situation can come about
- clear DRIVER_MODESET and DRIVER_ATOMIC feature bits

---
 drivers/gpu/drm/tegra/drm.c | 23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)
drivers/gpu/drm/tegra/drm.c +20 -3
index 5fc55b9777cbf..6806779f8ecce 100644
@@ -1252,9 +1252,26 @@ static int host1x_drm_probe(struct host1x_device *dev)
 
 	drm_mode_config_reset(drm);
 
-	err = drm_aperture_remove_framebuffers(&tegra_drm_driver);
-	if (err < 0)
-		goto hub;
+	/*
+	 * Only take over from a potential firmware framebuffer if any CRTCs
+	 * have been registered. This must not be a fatal error because there
+	 * are other accelerators that are exposed via this driver.
+	 *
+	 * Another case where this happens is on Tegra234 where the display
+	 * hardware is no longer part of the host1x complex, so this driver
+	 * will not expose any modesetting features.
+	 */
+	if (drm->mode_config.num_crtc > 0) {
+		err = drm_aperture_remove_framebuffers(&tegra_drm_driver);
+		if (err < 0)
+			goto hub;
+	} else {
+		/*
+		 * Indicate to userspace that this doesn't expose any display
+		 * capabilities.
+		 */
+		drm->driver_features &= ~(DRIVER_MODESET | DRIVER_ATOMIC);
+	}
 
 	err = tegra_drm_fb_init(drm);
 	if (err < 0)
Signature · 1 line
2.43.0
author maintainer
#76 lore raw

PATCH 76/215 landlock: Fix asymmetric private inodes referring

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mickaël Salaün <[email protected]>

commit d9818b3e906a0ee1ab02ea79e74a2f755fc5461a upstream.

When linking or renaming a file, if only one of the source or destination directory is backed by an S_PRIVATE inode, then the related set of layer masks would be used as uninitialized by is_access_to_paths_allowed(). This would result to indeterministic access for one side instead of always being allowed.

This bug could only be triggered with a mounted filesystem containing both S_PRIVATE and !S_PRIVATE inodes, which doesn't seem possible.

The collect_domain_accesses() calls return early if is_nouser_or_private() returns false, which means that the directory's superblock has SB_NOUSER or its inode has S_PRIVATE. Because rename or link actions are only allowed on the same mounted filesystem, the superblock is always the same for both source and destination directories. However, it might be possible in theory to have an S_PRIVATE parent source inode with an !S_PRIVATE parent destination inode, or vice versa.

To make sure this case is not an issue, explicitly initialized both set of layer masks to 0, which means to allow all actions on the related side. If at least on side has !S_PRIVATE, then collect_domain_accesses() and is_access_to_paths_allowed() check for the required access rights.

Cc Arnd Bergmann <[email protected]>
Cc Christian Brauner <[email protected]>
Cc Günther Noack <[email protected]>
Cc Jann Horn <[email protected]>
Cc Shervin Oloumi <[email protected]>
Fixes b91c3e4ea756 ("landlock: Add support for file reparenting with LANDLOCK_ACCESS_FS_REFER")
---
 security/landlock/fs.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
security/landlock/fs.c +2 -2
@@ -824,8 +824,8 @@ static int current_check_refer_path(stru
 	bool allow_parent1, allow_parent2;
 	access_mask_t access_request_parent1, access_request_parent2;
 	struct path mnt_dir;
-	layer_mask_t layer_masks_parent1[LANDLOCK_NUM_ACCESS_FS],
-		layer_masks_parent2[LANDLOCK_NUM_ACCESS_FS];
+	layer_mask_t layer_masks_parent1[LANDLOCK_NUM_ACCESS_FS] = {},
+		     layer_masks_parent2[LANDLOCK_NUM_ACCESS_FS] = {};
 
 	if (!dom)
 		return 0;
author maintainer
#77 lore raw

PATCH 77/215 gtp: fix use-after-free and null-ptr-deref in gtp_newlink()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alexander Ofitserov <[email protected]>

commit 616d82c3cfa2a2146dd7e3ae47bda7e877ee549e upstream.

The gtp_link_ops operations structure for the subsystem must be registered after registering the gtp_net_ops pernet operations structure.

Syzkaller hit 'general protection fault in gtp_genl_dump_pdp' bug:

[ 1010.702740] gtp: GTP module unloaded
[ 1010.715877] general protection fault, probably for non-canonical address 0xdffffc0000000001: 0000 [#1] SMP KASAN NOPTI
[ 1010.715888] KASAN: null-ptr-deref in range [0x0000000000000008-0x000000000000000f]
[ 1010.715895] CPU: 1 PID: 128616 Comm: a.out Not tainted 6.8.0-rc6-std-def-alt1 #1
[ 1010.715899] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.0-alt1 04/01/2014
[ 1010.715908] RIP: 0010:gtp_newlink+0x4d7/0x9c0 [gtp]
[ 1010.715915] Code: 80 3c 02 00 0f 85 41 04 00 00 48 8b bb d8 05 00 00 e8 ed f6 ff ff 48 89 c2 48 89 c5 48 b8 00 00 00 00 00 fc ff df 48 c1 ea 03 <80> 3c 02 00 0f 85 4f 04 00 00 4c 89 e2 4c 8b 6d 00 48 b8 00 00 00
[ 1010.715920] RSP: 0018:ffff888020fbf180 EFLAGS: 00010203
[ 1010.715929] RAX: dffffc0000000000 RBX: ffff88800399c000 RCX: 0000000000000000
[ 1010.715933] RDX: 0000000000000001 RSI: ffffffff84805280 RDI: 0000000000000282
[ 1010.715938] RBP: 000000000000000d R08: 0000000000000001 R09: 0000000000000000
[ 1010.715942] R10: 0000000000000001 R11: 0000000000000001 R12: ffff88800399cc80
[ 1010.715947] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000400
[ 1010.715953] FS:  00007fd1509ab5c0(0000) GS:ffff88805b300000(0000) knlGS:0000000000000000
[ 1010.715958] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1010.715962] CR2: 0000000000000000 CR3: 000000001c07a000 CR4: 0000000000750ee0
[ 1010.715968] PKRU: 55555554
[ 1010.715972] Call Trace:
[ 1010.715985]  ? __die_body.cold+0x1a/0x1f
[ 1010.715995]  ? die_addr+0x43/0x70
[ 1010.716002]  ? exc_general_protection+0x199/0x2f0
[ 1010.716016]  ? asm_exc_general_protection+0x1e/0x30
[ 1010.716026]  ? gtp_newlink+0x4d7/0x9c0 [gtp]
[ 1010.716034]  ? gtp_net_exit+0x150/0x150 [gtp]
[ 1010.716042]  __rtnl_newlink+0x1063/0x1700
[ 1010.716051]  ? rtnl_setlink+0x3c0/0x3c0
[ 1010.716063]  ? is_bpf_text_address+0xc0/0x1f0
[ 1010.716070]  ? kernel_text_address.part.0+0xbb/0xd0
[ 1010.716076]  ? __kernel_text_address+0x56/0xa0
[ 1010.716084]  ? unwind_get_return_address+0x5a/0xa0
[ 1010.716091]  ? create_prof_cpu_mask+0x30/0x30
[ 1010.716098]  ? arch_stack_walk+0x9e/0xf0
[ 1010.716106]  ? stack_trace_save+0x91/0xd0
[ 1010.716113]  ? stack_trace_consume_entry+0x170/0x170
[ 1010.716121]  ? __lock_acquire+0x15c5/0x5380
[ 1010.716139]  ? mark_held_locks+0x9e/0xe0
[ 1010.716148]  ? kmem_cache_alloc_trace+0x35f/0x3c0
[ 1010.716155]  ? __rtnl_newlink+0x1700/0x1700
[ 1010.716160]  rtnl_newlink+0x69/0xa0
[ 1010.716166]  rtnetlink_rcv_msg+0x43b/0xc50
[ 1010.716172]  ? rtnl_fdb_dump+0x9f0/0x9f0
[ 1010.716179]  ? lock_acquire+0x1fe/0x560
[ 1010.716188]  ? netlink_deliver_tap+0x12f/0xd50
[ 1010.716196]  netlink_rcv_skb+0x14d/0x440
[ 1010.716202]  ? rtnl_fdb_dump+0x9f0/0x9f0
[ 1010.716208]  ? netlink_ack+0xab0/0xab0
[ 1010.716213]  ? netlink_deliver_tap+0x202/0xd50
[ 1010.716220]  ? netlink_deliver_tap+0x218/0xd50
[ 1010.716226]  ? __virt_addr_valid+0x30b/0x590
[ 1010.716233]  netlink_unicast+0x54b/0x800
[ 1010.716240]  ? netlink_attachskb+0x870/0x870
[ 1010.716248]  ? __check_object_size+0x2de/0x3b0
[ 1010.716254]  netlink_sendmsg+0x938/0xe40
[ 1010.716261]  ? netlink_unicast+0x800/0x800
[ 1010.716269]  ? __import_iovec+0x292/0x510
[ 1010.716276]  ? netlink_unicast+0x800/0x800
[ 1010.716284]  __sock_sendmsg+0x159/0x190
[ 1010.716290]  ____sys_sendmsg+0x712/0x880
[ 1010.716297]  ? sock_write_iter+0x3d0/0x3d0
[ 1010.716304]  ? __ia32_sys_recvmmsg+0x270/0x270
[ 1010.716309]  ? lock_acquire+0x1fe/0x560
[ 1010.716315]  ? drain_array_locked+0x90/0x90
[ 1010.716324]  ___sys_sendmsg+0xf8/0x170
[ 1010.716331]  ? sendmsg_copy_msghdr+0x170/0x170
[ 1010.716337]  ? lockdep_init_map_type+0x2c7/0x860
[ 1010.716343]  ? lockdep_hardirqs_on_prepare+0x430/0x430
[ 1010.716350]  ? debug_mutex_init+0x33/0x70
[ 1010.716360]  ? percpu_counter_add_batch+0x8b/0x140
[ 1010.716367]  ? lock_acquire+0x1fe/0x560
[ 1010.716373]  ? find_held_lock+0x2c/0x110
[ 1010.716384]  ? __fd_install+0x1b6/0x6f0
[ 1010.716389]  ? lock_downgrade+0x810/0x810
[ 1010.716396]  ? __fget_light+0x222/0x290
[ 1010.716403]  __sys_sendmsg+0xea/0x1b0
[ 1010.716409]  ? __sys_sendmsg_sock+0x40/0x40
[ 1010.716419]  ? lockdep_hardirqs_on_prepare+0x2b3/0x430
[ 1010.716425]  ? syscall_enter_from_user_mode+0x1d/0x60
[ 1010.716432]  do_syscall_64+0x30/0x40
[ 1010.716438]  entry_SYSCALL_64_after_hwframe+0x62/0xc7
[ 1010.716444] RIP: 0033:0x7fd1508cbd49
[ 1010.716452] Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d ef 70 0d 00 f7 d8 64 89 01 48
[ 1010.716456] RSP: 002b:00007fff18872348 EFLAGS: 00000202 ORIG_RAX: 000000000000002e
[ 1010.716463] RAX: ffffffffffffffda RBX: 000055f72bf0eac0 RCX: 00007fd1508cbd49
[ 1010.716468] RDX: 0000000000000000 RSI: 0000000020000280 RDI: 0000000000000006
[ 1010.716473] RBP: 00007fff18872360 R08: 00007fff18872360 R09: 00007fff18872360
[ 1010.716478] R10: 00007fff18872360 R11: 0000000000000202 R12: 000055f72bf0e1b0
[ 1010.716482] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
[ 1010.716491] Modules linked in: gtp(+) udp_tunnel ib_core uinput af_packet rfkill qrtr joydev hid_generic usbhid hid kvm_intel iTCO_wdt intel_pmc_bxt iTCO_vendor_support kvm snd_hda_codec_generic ledtrig_audio irqbypass crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel snd_hda_intel nls_utf8 snd_intel_dspcfg nls_cp866 psmouse aesni_intel vfat crypto_simd fat cryptd glue_helper snd_hda_codec pcspkr snd_hda_core i2c_i801 snd_hwdep i2c_smbus xhci_pci snd_pcm lpc_ich xhci_pci_renesas xhci_hcd qemu_fw_cfg tiny_power_button button sch_fq_codel vboxvideo drm_vram_helper drm_ttm_helper ttm vboxsf vboxguest snd_seq_midi snd_seq_midi_event snd_seq snd_rawmidi snd_seq_device snd_timer snd soundcore msr fuse efi_pstore dm_mod ip_tables x_tables autofs4 virtio_gpu virtio_dma_buf drm_kms_helper cec rc_core drm virtio_rng virtio_scsi rng_core virtio_balloon virtio_blk virtio_net virtio_console net_failover failover ahci libahci libata evdev scsi_mod input_leds serio_raw virtio_pci intel_agp
[ 1010.716674]  virtio_ring intel_gtt virtio [last unloaded: gtp]
[ 1010.716693] ---[ end trace 04990a4ce61e174b ]---
Fixes 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)")
---
 drivers/net/gtp.c |   12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)
drivers/net/gtp.c +6 -6
@@ -1902,26 +1902,26 @@ static int __init gtp_init(void)
 
 	get_random_bytes(&gtp_h_initval, sizeof(gtp_h_initval));
 
-	err = rtnl_link_register(&gtp_link_ops);
+	err = register_pernet_subsys(&gtp_net_ops);
 	if (err < 0)
 		goto error_out;
 
-	err = register_pernet_subsys(&gtp_net_ops);
+	err = rtnl_link_register(&gtp_link_ops);
 	if (err < 0)
-		goto unreg_rtnl_link;
+		goto unreg_pernet_subsys;
 
 	err = genl_register_family(&gtp_genl_family);
 	if (err < 0)
-		goto unreg_pernet_subsys;
+		goto unreg_rtnl_link;
 
 	pr_info("GTP module loaded (pdp ctx size %zd bytes)\n",
 		sizeof(struct pdp_ctx));
 	return 0;
 
-unreg_pernet_subsys:
-	unregister_pernet_subsys(&gtp_net_ops);
 unreg_rtnl_link:
 	rtnl_link_unregister(&gtp_link_ops);
+unreg_pernet_subsys:
+	unregister_pernet_subsys(&gtp_net_ops);
 error_out:
 	pr_err("error loading GTP module loaded\n");
 	return err;
author maintainer
#78 lore raw

PATCH 78/215 wifi: nl80211: reject iftype change with mesh ID change

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Johannes Berg <[email protected]>

commit f78c1375339a291cba492a70eaf12ec501d28a8e upstream.

It's currently possible to change the mesh ID when the interface isn't yet in mesh mode, at the same time as changing it into mesh mode. This leads to an overwrite of data in the wdev->u union for the interface type it currently has, causing cfg80211_change_iface() to do wrong things when switching.

We could probably allow setting an interface to mesh while setting the mesh ID at the same time by doing a different order of operations here, but realistically there's no userspace that's going to do this, so just disallow changes in iftype when setting mesh ID.

Fixes 29cbe68c516a ("cfg80211/mac80211: add mesh join/leave commands")
Reported-by [email protected]
---
 net/wireless/nl80211.c |    2 ++
 1 file changed, 2 insertions(+)
net/wireless/nl80211.c +2 -0
@@ -4137,6 +4137,8 @@ static int nl80211_set_interface(struct
 
 		if (ntype != NL80211_IFTYPE_MESH_POINT)
 			return -EINVAL;
+		if (otype != NL80211_IFTYPE_MESH_POINT)
+			return -EINVAL;
 		if (netif_running(dev))
 			return -EBUSY;
 
author maintainer
#79 lore raw

PATCH 79/215 btrfs: fix double free of anonymous device after snapshot creation failure

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Filipe Manana <[email protected]>

commit e2b54eaf28df0c978626c9736b94f003b523b451 upstream.

When creating a snapshot we may do a double free of an anonymous device in case there's an error committing the transaction. The second free may result in freeing an anonymous device number that was allocated by some other subsystem in the kernel or another btrfs filesystem.

The steps that lead to this:

1) At ioctl.c:create_snapshot() we allocate an anonymous device number and assign it to pending_snapshot->anon_dev;

2) Then we call btrfs_commit_transaction() and end up at transaction.c:create_pending_snapshot();

3) There we call btrfs_get_new_fs_root() and pass it the anonymous device number stored in pending_snapshot->anon_dev;

4) btrfs_get_new_fs_root() frees that anonymous device number because btrfs_lookup_fs_root() returned a root - someone else did a lookup of the new root already, which could some task doing backref walking;

5) After that some error happens in the transaction commit path, and at ioctl.c:create_snapshot() we jump to the 'fail' label, and after that we free again the same anonymous device number, which in the meanwhile may have been reallocated somewhere else, because pending_snapshot->anon_dev still has the same value as in step 1.

Recently syzbot ran into this and reported the following trace:

  ------------[ cut here ]------------
  ida_free called for id=51 which is not allocated.
  WARNING: CPU: 1 PID: 31038 at lib/idr.c:525 ida_free+0x370/0x420 lib/idr.c:525
  Modules linked in:
  CPU: 1 PID: 31038 Comm: syz-executor.2 Not tainted 6.8.0-rc4-syzkaller-00410-gc02197fc9076 #0
  Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024
  RIP: 0010:ida_free+0x370/0x420 lib/idr.c:525
  Code: 10 42 80 3c 28 (...)
  RSP: 0018:ffffc90015a67300 EFLAGS: 00010246
  RAX: be5130472f5dd000 RBX: 0000000000000033 RCX: 0000000000040000
  RDX: ffffc90009a7a000 RSI: 000000000003ffff RDI: 0000000000040000
  RBP: ffffc90015a673f0 R08: ffffffff81577992 R09: 1ffff92002b4cdb4
  R10: dffffc0000000000 R11: fffff52002b4cdb5 R12: 0000000000000246
  R13: dffffc0000000000 R14: ffffffff8e256b80 R15: 0000000000000246
  FS:  00007fca3f4b46c0(0000) GS:ffff8880b9500000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00007f167a17b978 CR3: 000000001ed26000 CR4: 0000000000350ef0
  Call Trace:
   <TASK>
   btrfs_get_root_ref+0xa48/0xaf0 fs/btrfs/disk-io.c:1346
   create_pending_snapshot+0xff2/0x2bc0 fs/btrfs/transaction.c:1837
   create_pending_snapshots+0x195/0x1d0 fs/btrfs/transaction.c:1931
   btrfs_commit_transaction+0xf1c/0x3740 fs/btrfs/transaction.c:2404
   create_snapshot+0x507/0x880 fs/btrfs/ioctl.c:848
   btrfs_mksubvol+0x5d0/0x750 fs/btrfs/ioctl.c:998
   btrfs_mksnapshot+0xb5/0xf0 fs/btrfs/ioctl.c:1044
   __btrfs_ioctl_snap_create+0x387/0x4b0 fs/btrfs/ioctl.c:1306
   btrfs_ioctl_snap_create_v2+0x1ca/0x400 fs/btrfs/ioctl.c:1393
   btrfs_ioctl+0xa74/0xd40
   vfs_ioctl fs/ioctl.c:51 [inline]
   __do_sys_ioctl fs/ioctl.c:871 [inline]
   __se_sys_ioctl+0xfe/0x170 fs/ioctl.c:857
   do_syscall_64+0xfb/0x240
   entry_SYSCALL_64_after_hwframe+0x6f/0x77
  RIP: 0033:0x7fca3e67dda9
  Code: 28 00 00 00 (...)
  RSP: 002b:00007fca3f4b40c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
  RAX: ffffffffffffffda RBX: 00007fca3e7abf80 RCX: 00007fca3e67dda9
  RDX: 00000000200005c0 RSI: 0000000050009417 RDI: 0000000000000003
  RBP: 00007fca3e6ca47a R08: 0000000000000000 R09: 0000000000000000
  R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
  R13: 000000000000000b R14: 00007fca3e7abf80 R15: 00007fff6bf95658
   </TASK>

Where we get an explicit message where we attempt to free an anonymous device number that is not currently allocated. It happens in a different code path from the example below, at btrfs_get_root_ref(), so this change may not fix the case triggered by syzbot.

To fix at least the code path from the example above, change btrfs_get_root_ref() and its callers to receive a dev_t pointer argument for the anonymous device number, so that in case it frees the number, it also resets it to 0, so that up in the call chain we don't attempt to do the double free.

Fixes e03ee2fe873e ("btrfs: do not ASSERT() if the newly created subvolume already got read")
---
 fs/btrfs/disk-io.c     |   22 +++++++++++-----------
 fs/btrfs/disk-io.h     |    2 +-
 fs/btrfs/ioctl.c       |    2 +-
 fs/btrfs/transaction.c |    2 +-
 4 files changed, 14 insertions(+), 14 deletions(-)
fs/btrfs/disk-io.c +11 -11
@@ -1643,12 +1643,12 @@ void btrfs_free_fs_info(struct btrfs_fs_
  *
  * @objectid:	root id
  * @anon_dev:	preallocated anonymous block device number for new roots,
- * 		pass 0 for new allocation.
+ *		pass NULL for a new allocation.
  * @check_ref:	whether to check root item references, If true, return -ENOENT
  *		for orphan roots
  */
 static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info,
-					     u64 objectid, dev_t anon_dev,
+					     u64 objectid, dev_t *anon_dev,
 					     bool check_ref)
 {
 	struct btrfs_root *root;
@@ -1668,9 +1668,9 @@ again:
 		 * that common but still possible.  In that case, we just need
 		 * to free the anon_dev.
 		 */
-		if (unlikely(anon_dev)) {
-			free_anon_bdev(anon_dev);
-			anon_dev = 0;
+		if (unlikely(anon_dev && *anon_dev)) {
+			free_anon_bdev(*anon_dev);
+			*anon_dev = 0;
 		}
 
 		if (check_ref && btrfs_root_refs(&root->root_item) == 0) {
@@ -1692,7 +1692,7 @@ again:
 		goto fail;
 	}
 
-	ret = btrfs_init_fs_root(root, anon_dev);
+	ret = btrfs_init_fs_root(root, anon_dev ? *anon_dev : 0);
 	if (ret)
 		goto fail;
 
@@ -1728,7 +1728,7 @@ fail:
 	 * root's anon_dev to 0 to avoid a double free, once by btrfs_put_root()
 	 * and once again by our caller.
 	 */
-	if (anon_dev)
+	if (anon_dev && *anon_dev)
 		root->anon_dev = 0;
 	btrfs_put_root(root);
 	return ERR_PTR(ret);
@@ -1744,7 +1744,7 @@ fail:
 struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
 				     u64 objectid, bool check_ref)
 {
-	return btrfs_get_root_ref(fs_info, objectid, 0, check_ref);
+	return btrfs_get_root_ref(fs_info, objectid, NULL, check_ref);
 }
 
 /*
@@ -1752,11 +1752,11 @@ struct btrfs_root *btrfs_get_fs_root(str
  * the anonymous block device id
  *
  * @objectid:	tree objectid
- * @anon_dev:	if zero, allocate a new anonymous block device or use the
- *		parameter value
+ * @anon_dev:	if NULL, allocate a new anonymous block device or use the
+ *		parameter value if not NULL
  */
 struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
-					 u64 objectid, dev_t anon_dev)
+					 u64 objectid, dev_t *anon_dev)
 {
 	return btrfs_get_root_ref(fs_info, objectid, anon_dev, true);
 }
fs/btrfs/disk-io.h +1 -1
@@ -65,7 +65,7 @@ void btrfs_free_fs_roots(struct btrfs_fs
 struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
 				     u64 objectid, bool check_ref);
 struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
-					 u64 objectid, dev_t anon_dev);
+					 u64 objectid, dev_t *anon_dev);
 struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info,
 						 struct btrfs_path *path,
 						 u64 objectid);
fs/btrfs/ioctl.c +1 -1
@@ -708,7 +708,7 @@ static noinline int create_subvol(struct
 	free_extent_buffer(leaf);
 	leaf = NULL;
 
-	new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev);
+	new_root = btrfs_get_new_fs_root(fs_info, objectid, &anon_dev);
 	if (IS_ERR(new_root)) {
 		ret = PTR_ERR(new_root);
 		btrfs_abort_transaction(trans, ret);
fs/btrfs/transaction.c +1 -1
@@ -1809,7 +1809,7 @@ static noinline int create_pending_snaps
 	}
 
 	key.offset = (u64)-1;
-	pending->snap = btrfs_get_new_fs_root(fs_info, objectid, pending->anon_dev);
+	pending->snap = btrfs_get_new_fs_root(fs_info, objectid, &pending->anon_dev);
 	if (IS_ERR(pending->snap)) {
 		ret = PTR_ERR(pending->snap);
 		pending->snap = NULL;
author maintainer
#80 lore raw

PATCH 80/215 btrfs: dev-replace: properly validate device names

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Sterba <[email protected]>

commit 9845664b9ee47ce7ee7ea93caf47d39a9d4552c4 upstream.

There's a syzbot report that device name buffers passed to device replace are not properly checked for string termination which could lead to a read out of bounds in getname_kernel().

Add a helper that validates both source and target device name buffers. For devid as the source initialize the buffer to empty string in case something tries to read it later.

This was originally analyzed and fixed in a different way by Edward Adam Davis (see links).

---
 fs/btrfs/dev-replace.c |   24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)
fs/btrfs/dev-replace.c +20 -4
@@ -740,6 +740,23 @@ leave:
 	return ret;
 }
 
+static int btrfs_check_replace_dev_names(struct btrfs_ioctl_dev_replace_args *args)
+{
+	if (args->start.srcdevid == 0) {
+		if (memchr(args->start.srcdev_name, 0,
+			   sizeof(args->start.srcdev_name)) == NULL)
+			return -ENAMETOOLONG;
+	} else {
+		args->start.srcdev_name[0] = 0;
+	}
+
+	if (memchr(args->start.tgtdev_name, 0,
+		   sizeof(args->start.tgtdev_name)) == NULL)
+	    return -ENAMETOOLONG;
+
+	return 0;
+}
+
 int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info,
 			    struct btrfs_ioctl_dev_replace_args *args)
 {
@@ -752,10 +769,9 @@ int btrfs_dev_replace_by_ioctl(struct bt
 	default:
 		return -EINVAL;
 	}
-
-	if ((args->start.srcdevid == 0 && args->start.srcdev_name[0] == '\0') ||
-	    args->start.tgtdev_name[0] == '\0')
-		return -EINVAL;
+	ret = btrfs_check_replace_dev_names(args);
+	if (ret < 0)
+		return ret;
 
 	ret = btrfs_dev_replace_start(fs_info, args->start.tgtdev_name,
 					args->start.srcdevid,
author maintainer
#81 lore raw

PATCH 81/215 btrfs: send: dont issue unnecessary zero writes for trailing hole

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Filipe Manana <[email protected]>

commit 5897710b28cabab04ea6c7547f27b7989de646ae upstream.

If we have a sparse file with a trailing hole (from the last extent's end to i_size) and then create an extent in the file that ends before the file's i_size, then when doing an incremental send we will issue a write full of zeroes for the range that starts immediately after the new extent ends up to i_size. While this isn't incorrect because the file ends up with exactly the same data, it unnecessarily results in using extra space at the destination with one or more extents full of zeroes instead of having a hole. In same cases this results in using megabytes or even gigabytes of unnecessary space.

Example, reproducer:

   $ cat test.sh
   #!/bin/bash

DEV=/dev/sdh
MNT=/mnt/sdh

mkfs.btrfs -f $DEV
mount $DEV $MNT

# Create 1G sparse file.
xfs_io -f -c "truncate 1G" $MNT/foobar

# Create base snapshot.
btrfs subvolume snapshot -r $MNT $MNT/mysnap1

# Create send stream (full send) for the base snapshot. btrfs send -f /tmp/1.snap $MNT/mysnap1

   # Now write one extent at the beginning of the file and one somewhere
   # in the middle, leaving a gap between the end of this second extent
   # and the file's size.
   xfs_io -c "pwrite -S 0xab 0 128K" \
          -c "pwrite -S 0xcd 512M 128K" \
          $MNT/foobar

# Now create a second snapshot which is going to be used for an

   # incremental send operation.
   btrfs subvolume snapshot -r $MNT $MNT/mysnap2

# Create send stream (incremental send) for the second snapshot. btrfs send -p $MNT/mysnap1 -f /tmp/2.snap $MNT/mysnap2

# Now recreate the filesystem by receiving both send streams and

   # verify we get the same content that the original filesystem had
   # and file foobar has only two extents with a size of 128K each.
   umount $MNT
   mkfs.btrfs -f $DEV
   mount $DEV $MNT

btrfs receive -f /tmp/1.snap $MNT
btrfs receive -f /tmp/2.snap $MNT

echo -e "\nFile fiemap in the second snapshot:" # Should have:
#
# 128K extent at file range [0, 128K[

   # hole at file range [128K, 512M[
   # 128K extent file range [512M, 512M + 128K[
   # hole at file range [512M + 128K, 1G[
   xfs_io -r -c "fiemap -v" $MNT/mysnap2/foobar
   # File should be using 256K of data (two 128K extents).
   echo -e "\nSpace used by the file: $(du -h $MNT/mysnap2/foobar | cut -f 1)"

umount $MNT

Running the test, we can see with fiemap that we get an extent for the range [512M, 1G[, while in the source filesystem we have an extent for the range [512M, 512M + 128K[ and a hole for the rest of the file (the range [512M + 128K, 1G[):

   $ ./test.sh
   (...)
   File fiemap in the second snapshot:
   /mnt/sdh/mysnap2/foobar:
    EXT: FILE-OFFSET        BLOCK-RANGE        TOTAL FLAGS
      0: [0..255]:          26624..26879         256   0x0
      1: [256..1048575]:    hole             1048320
      2: [1048576..2097151]: 2156544..3205119 1048576   0x1

Space used by the file: 513M

This happens because once we finish processing an inode, at finish_inode_if_needed(), we always issue a hole (write operations full of zeros) if there's a gap between the end of the last processed extent and the file's size, even if that range is already a hole in the parent snapshot. Fix this by issuing the hole only if the range is not already a hole.

After this change, running the test above, we get the expected layout:

   $ ./test.sh
   (...)
   File fiemap in the second snapshot:
   /mnt/sdh/mysnap2/foobar:
    EXT: FILE-OFFSET        BLOCK-RANGE      TOTAL FLAGS
      0: [0..255]:          26624..26879       256   0x0
      1: [256..1048575]:    hole             1048320
      2: [1048576..1048831]: 26880..27135       256   0x1
      3: [1048832..2097151]: hole             1048320

Space used by the file: 256K

A test case for fstests will follow soon.

---
 fs/btrfs/send.c |   17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)
fs/btrfs/send.c +13 -4
@@ -6462,11 +6462,20 @@ static int finish_inode_if_needed(struct
 				if (ret)
 					goto out;
 			}
-			if (sctx->cur_inode_last_extent <
-			    sctx->cur_inode_size) {
-				ret = send_hole(sctx, sctx->cur_inode_size);
-				if (ret)
+			if (sctx->cur_inode_last_extent < sctx->cur_inode_size) {
+				ret = range_is_hole_in_parent(sctx,
+						      sctx->cur_inode_last_extent,
+						      sctx->cur_inode_size);
+				if (ret < 0) {
 					goto out;
+				} else if (ret == 0) {
+					ret = send_hole(sctx, sctx->cur_inode_size);
+					if (ret < 0)
+						goto out;
+				} else {
+					/* Range is already a hole, skip. */
+					ret = 0;
+				}
 			}
 		}
 		if (need_truncate) {
author maintainer
#82 lore raw

PATCH 82/215 Revert "drm/amd/pm: resolve reboot exception for si oland"

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alex Deucher <[email protected]>

commit 955558030954b9637b41c97b730f9b38c92ac488 upstream.

This reverts commit e490d60a2f76bff636c68ce4fe34c1b6c34bbd86.

This causes hangs on SI when DC is enabled and errors on driver reboot and power off cycles.

---
 drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c |   29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)
drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +29 -0
@@ -6925,6 +6925,23 @@ static int si_dpm_enable(struct amdgpu_d
 	return 0;
 }
 
+static int si_set_temperature_range(struct amdgpu_device *adev)
+{
+	int ret;
+
+	ret = si_thermal_enable_alert(adev, false);
+	if (ret)
+		return ret;
+	ret = si_thermal_set_temperature_range(adev, R600_TEMP_RANGE_MIN, R600_TEMP_RANGE_MAX);
+	if (ret)
+		return ret;
+	ret = si_thermal_enable_alert(adev, true);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+
 static void si_dpm_disable(struct amdgpu_device *adev)
 {
 	struct rv7xx_power_info *pi = rv770_get_pi(adev);
@@ -7608,6 +7625,18 @@ static int si_dpm_process_interrupt(stru
 
 static int si_dpm_late_init(void *handle)
 {
+	int ret;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	if (!adev->pm.dpm_enabled)
+		return 0;
+
+	ret = si_set_temperature_range(adev);
+	if (ret)
+		return ret;
+#if 0 //TODO ?
+	si_dpm_powergate_uvd(adev, true);
+#endif
 	return 0;
 }
 
author maintainer
#83 lore raw

PATCH 83/215 drm/buddy: fix range bias

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Matthew Auld <[email protected]>

commit f41900e4a6ef019d64a70394b0e0c3bd048d4ec8 upstream.

There is a corner case here where start/end is after/before the block range we are currently checking. If so we need to be sure that splitting the block will eventually give use the block size we need. To do that we should adjust the block range to account for the start/end, and only continue with the split if the size/alignment will fit the requested size. Not doing so can result in leaving split blocks unmerged when it eventually fails.

Fixes afea229fe102 ("drm: improve drm_buddy_alloc function")
Cc Arunpravin Paneer Selvam <[email protected]>
Cc Christian König <[email protected]>
Cc <[email protected]> # v5.18+
---
 drivers/gpu/drm/drm_buddy.c |   10 ++++++++++
 1 file changed, 10 insertions(+)
drivers/gpu/drm/drm_buddy.c +10 -0
@@ -332,6 +332,7 @@ alloc_range_bias(struct drm_buddy *mm,
 		 u64 start, u64 end,
 		 unsigned int order)
 {
+	u64 req_size = mm->chunk_size << order;
 	struct drm_buddy_block *block;
 	struct drm_buddy_block *buddy;
 	LIST_HEAD(dfs);
@@ -367,6 +368,15 @@ alloc_range_bias(struct drm_buddy *mm,
 		if (drm_buddy_block_is_allocated(block))
 			continue;
 
+		if (block_start < start || block_end > end) {
+			u64 adjusted_start = max(block_start, start);
+			u64 adjusted_end = min(block_end, end);
+
+			if (round_down(adjusted_end + 1, req_size) <=
+			    round_up(adjusted_start, req_size))
+				continue;
+		}
+
 		if (contains(start, end, block_start, block_end) &&
 		    order == drm_buddy_block_order(block)) {
 			/*
author maintainer
#84 lore raw

PATCH 84/215 dmaengine: fsl-qdma: fix SoC may hang on 16 byte unaligned read

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Peng Ma <[email protected]>

commit 9d739bccf261dd93ec1babf82f5c5d71dd4caa3e upstream.

There is chip (ls1028a) errata:

The SoC may hang on 16 byte unaligned read transactions by QDMA.

Unaligned read transactions initiated by QDMA may stall in the NOC (Network On-Chip), causing a deadlock condition. Stalled transactions will trigger completion timeouts in PCIe controller.

Workaround:
Enable prefetch by setting the source descriptor prefetchable bit ( SD[PF] = 1 ).

Implement this workaround.

Fixes b092529e0aa0 ("dmaengine: fsl-qdma: Add qDMA controller driver for Layerscape SoCs")
---
 drivers/dma/fsl-qdma.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/dma/fsl-qdma.c +3 -1
@@ -109,6 +109,7 @@
 #define FSL_QDMA_CMD_WTHROTL_OFFSET	20
 #define FSL_QDMA_CMD_DSEN_OFFSET	19
 #define FSL_QDMA_CMD_LWC_OFFSET		16
+#define FSL_QDMA_CMD_PF			BIT(17)
 
 /* Field definition for Descriptor status */
 #define QDMA_CCDF_STATUS_RTE		BIT(5)
@@ -384,7 +385,8 @@ static void fsl_qdma_comp_fill_memcpy(st
 	qdma_csgf_set_f(csgf_dest, len);
 	/* Descriptor Buffer */
 	cmd = cpu_to_le32(FSL_QDMA_CMD_RWTTYPE <<
-			  FSL_QDMA_CMD_RWTTYPE_OFFSET);
+			  FSL_QDMA_CMD_RWTTYPE_OFFSET) |
+			  FSL_QDMA_CMD_PF;
 	sdf->data = QDMA_SDDF_CMD(cmd);
 
 	cmd = cpu_to_le32(FSL_QDMA_CMD_RWTTYPE <<
author maintainer
#85 lore raw

PATCH 85/215 crypto: arm64/neonbs - fix out-of-bounds access on short input

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit 1c0cf6d19690141002889d72622b90fc01562ce4 upstream.

The bit-sliced implementation of AES-CTR operates on blocks of 128 bytes, and will fall back to the plain NEON version for tail blocks or inputs that are shorter than 128 bytes to begin with.

It will call straight into the plain NEON asm helper, which performs all memory accesses in granules of 16 bytes (the size of a NEON register). For this reason, the associated plain NEON glue code will copy inputs shorter than 16 bytes into a temporary buffer, given that this is a rare occurrence and it is not worth the effort to work around this in the asm code.

The fallback from the bit-sliced NEON version fails to take this into account, potentially resulting in out-of-bounds accesses. So clone the same workaround, and use a temp buffer for short in/outputs.

Fixes fc074e130051 ("crypto: arm64/aes-neonbs-ctr - fallback to plain NEON for final chunk")
Reported-by [email protected]
---
 arch/arm64/crypto/aes-neonbs-glue.c |   11 +++++++++++
 1 file changed, 11 insertions(+)
arch/arm64/crypto/aes-neonbs-glue.c +11 -0
@@ -227,8 +227,19 @@ static int ctr_encrypt(struct skcipher_r
 			src += blocks * AES_BLOCK_SIZE;
 		}
 		if (nbytes && walk.nbytes == walk.total) {
+			u8 buf[AES_BLOCK_SIZE];
+			u8 *d = dst;
+
+			if (unlikely(nbytes < AES_BLOCK_SIZE))
+				src = dst = memcpy(buf + sizeof(buf) - nbytes,
+						   src, nbytes);
+
 			neon_aes_ctr_encrypt(dst, src, ctx->enc, ctx->key.rounds,
 					     nbytes, walk.iv);
+
+			if (unlikely(nbytes < AES_BLOCK_SIZE))
+				memcpy(d, dst, nbytes);
+
 			nbytes = 0;
 		}
 		kernel_neon_end();
author maintainer
#68 lore raw

PATCH 68/215 fbcon: always restore the old font data in fbcon_do_set_font()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jiri Slaby (SUSE) <[email protected]>

[ Upstream commit 00d6a284fcf3fad1b7e1b5bc3cd87cbfb60ce03f ]

Commit a5a923038d70 (fbdev: fbcon: Properly revert changes when vc_resize() failed) started restoring old font data upon failure (of vc_resize()). But it performs so only for user fonts. It means that the "system"/internal fonts are not restored at all. So in result, the very first call to fbcon_do_set_font() performs no restore at all upon failing vc_resize().

This can be reproduced by Syzkaller to crash the system on the next invocation of font_get(). It's rather hard to hit the allocation failure in vc_resize() on the first font_set(), but not impossible. Esp. if fault injection is used to aid the execution/failure. It was demonstrated by Sirius:

  BUG: unable to handle page fault for address: fffffffffffffff8
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  PGD cb7b067 P4D cb7b067 PUD cb7d067 PMD 0
  Oops: 0000 [#1] PREEMPT SMP KASAN
  CPU: 1 PID: 8007 Comm: poc Not tainted 6.7.0-g9d1694dc91ce #20
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
  RIP: 0010:fbcon_get_font+0x229/0x800 drivers/video/fbdev/core/fbcon.c:2286
  Call Trace:
   <TASK>
   con_font_get drivers/tty/vt/vt.c:4558 [inline]
   con_font_op+0x1fc/0xf20 drivers/tty/vt/vt.c:4673
   vt_k_ioctl drivers/tty/vt/vt_ioctl.c:474 [inline]
   vt_ioctl+0x632/0x2ec0 drivers/tty/vt/vt_ioctl.c:752
   tty_ioctl+0x6f8/0x1570 drivers/tty/tty_io.c:2803
   vfs_ioctl fs/ioctl.c:51 [inline]
  ...

So restore the font data in any case, not only for user fonts. Note the later 'if' is now protected by 'old_userfont' and not 'old_data' as the latter is always set now. (And it is supposed to be non-NULL. Otherwise we would see the bug above again.)

Fixes a5a923038d70 ("fbdev: fbcon: Properly revert changes when vc_resize() failed")
Cc Ubisectech Sirius <[email protected]>
Cc Daniel Vetter <[email protected]>
Cc Helge Deller <[email protected]>
---
 drivers/video/fbdev/core/fbcon.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)
drivers/video/fbdev/core/fbcon.c +3 -5
index fa205be94a4b8..14498a0d13e0b 100644
@@ -2397,11 +2397,9 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount,
 	struct fbcon_ops *ops = info->fbcon_par;
 	struct fbcon_display *p = &fb_display[vc->vc_num];
 	int resize, ret, old_userfont, old_width, old_height, old_charcount;
-	char *old_data = NULL;
+	u8 *old_data = vc->vc_font.data;
 
 	resize = (w != vc->vc_font.width) || (h != vc->vc_font.height);
-	if (p->userfont)
-		old_data = vc->vc_font.data;
 	vc->vc_font.data = (void *)(p->fontdata = data);
 	old_userfont = p->userfont;
 	if ((p->userfont = userfont))
@@ -2435,13 +2433,13 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount,
 		update_screen(vc);
 	}
 
-	if (old_data && (--REFCOUNT(old_data) == 0))
+	if (old_userfont && (--REFCOUNT(old_data) == 0))
 		kfree(old_data - FONT_EXTRA_WORDS * sizeof(int));
 	return 0;
 
 err_out:
 	p->fontdata = old_data;
-	vc->vc_font.data = (void *)old_data;
+	vc->vc_font.data = old_data;
 
 	if (userfont) {
 		p->userfont = old_userfont;
Signature · 1 line
2.43.0
author maintainer
#86 lore raw

PATCH 86/215 dmaengine: ptdma: use consistent DMA masks

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tadeusz Struk <[email protected]>

commit df2515a17914ecfc2a0594509deaf7fcb8d191ac upstream.

The PTDMA driver sets DMA masks in two different places for the same device inconsistently. First call is in pt_pci_probe(), where it uses 48bit mask. The second call is in pt_dmaengine_register(), where it uses a 64bit mask. Using 64bit dma mask causes IO_PAGE_FAULT errors on DMA transfers between main memory and other devices. Without the extra call it works fine. Additionally the second call doesn't check the return value so it can silently fail. Remove the superfluous dma_set_mask() call and only use 48bit mask.

Fixes b0b4a6b10577 ("dmaengine: ptdma: register PTDMA controller as a DMA resource")
---
 drivers/dma/ptdma/ptdma-dmaengine.c |    2 --
 1 file changed, 2 deletions(-)
drivers/dma/ptdma/ptdma-dmaengine.c +0 -2
@@ -385,8 +385,6 @@ int pt_dmaengine_register(struct pt_devi
 	chan->vc.desc_free = pt_do_cleanup;
 	vchan_init(&chan->vc, dma_dev);
 
-	dma_set_mask_and_coherent(pt->dev, DMA_BIT_MASK(64));
-
 	ret = dma_async_device_register(dma_dev);
 	if (ret)
 		goto err_reg;
author maintainer
#87 lore raw

PATCH 87/215 dmaengine: fsl-qdma: init irq after reg initialization

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Curtis Klein <[email protected]>

commit 87a39071e0b639f45e05d296cc0538eef44ec0bd upstream.

Initialize the qDMA irqs after the registers are configured so that interrupts that may have been pending from a primary kernel don't get processed by the irq handler before it is ready to and cause panic with the following trace:

  Call trace:
   fsl_qdma_queue_handler+0xf8/0x3e8
   __handle_irq_event_percpu+0x78/0x2b0
   handle_irq_event_percpu+0x1c/0x68
   handle_irq_event+0x44/0x78
   handle_fasteoi_irq+0xc8/0x178
   generic_handle_irq+0x24/0x38
   __handle_domain_irq+0x90/0x100
   gic_handle_irq+0x5c/0xb8
   el1_irq+0xb8/0x180
   _raw_spin_unlock_irqrestore+0x14/0x40
   __setup_irq+0x4bc/0x798
   request_threaded_irq+0xd8/0x190
   devm_request_threaded_irq+0x74/0xe8
   fsl_qdma_probe+0x4d4/0xca8
   platform_drv_probe+0x50/0xa0
   really_probe+0xe0/0x3f8
   driver_probe_device+0x64/0x130
   device_driver_attach+0x6c/0x78
   __driver_attach+0xbc/0x158
   bus_for_each_dev+0x5c/0x98
   driver_attach+0x20/0x28
   bus_add_driver+0x158/0x220
   driver_register+0x60/0x110
   __platform_driver_register+0x44/0x50
   fsl_qdma_driver_init+0x18/0x20
   do_one_initcall+0x48/0x258
   kernel_init_freeable+0x1a4/0x23c
   kernel_init+0x10/0xf8
   ret_from_fork+0x10/0x18
Fixes b092529e0aa0 ("dmaengine: fsl-qdma: Add qDMA controller driver for Layerscape SoCs")
---
 drivers/dma/fsl-qdma.c |   17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)
drivers/dma/fsl-qdma.c +8 -9
@@ -1203,10 +1203,6 @@ static int fsl_qdma_probe(struct platfor
 	if (!fsl_qdma->queue)
 		return -ENOMEM;
 
-	ret = fsl_qdma_irq_init(pdev, fsl_qdma);
-	if (ret)
-		return ret;
-
 	fsl_qdma->irq_base = platform_get_irq_byname(pdev, "qdma-queue0");
 	if (fsl_qdma->irq_base < 0)
 		return fsl_qdma->irq_base;
@@ -1245,16 +1241,19 @@ static int fsl_qdma_probe(struct platfor
 
 	platform_set_drvdata(pdev, fsl_qdma);
 
-	ret = dma_async_device_register(&fsl_qdma->dma_dev);
+	ret = fsl_qdma_reg_init(fsl_qdma);
 	if (ret) {
-		dev_err(&pdev->dev,
-			"Can't register NXP Layerscape qDMA engine.\n");
+		dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n");
 		return ret;
 	}
 
-	ret = fsl_qdma_reg_init(fsl_qdma);
+	ret = fsl_qdma_irq_init(pdev, fsl_qdma);
+	if (ret)
+		return ret;
+
+	ret = dma_async_device_register(&fsl_qdma->dma_dev);
 	if (ret) {
-		dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n");
+		dev_err(&pdev->dev, "Can't register NXP Layerscape qDMA engine.\n");
 		return ret;
 	}
 
author maintainer
#88 lore raw

PATCH 88/215 mmc: mmci: stm32: fix DMA API overlapping mappings warning

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christophe Kerello <[email protected]>

commit 6b1ba3f9040be5efc4396d86c9752cdc564730be upstream.

Turning on CONFIG_DMA_API_DEBUG_SG results in the following warning:

DMA-API: mmci-pl18x 48220000.mmc: cacheline tracking EEXIST, overlapping mappings aren't supported

WARNING: CPU: 1 PID: 51 at kernel/dma/debug.c:568
add_dma_entry+0x234/0x2f4
Modules linked in:
CPU: 1 PID: 51 Comm: kworker/1:2 Not tainted 6.1.28 #1
Hardware name: STMicroelectronics STM32MP257F-EV1 Evaluation Board (DT)
Workqueue: events_freezable mmc_rescan
Call trace:
add_dma_entry+0x234/0x2f4
debug_dma_map_sg+0x198/0x350
__dma_map_sg_attrs+0xa0/0x110
dma_map_sg_attrs+0x10/0x2c
sdmmc_idma_prep_data+0x80/0xc0
mmci_prep_data+0x38/0x84
mmci_start_data+0x108/0x2dc
mmci_request+0xe4/0x190
__mmc_start_request+0x68/0x140
mmc_start_request+0x94/0xc0
mmc_wait_for_req+0x70/0x100
mmc_send_tuning+0x108/0x1ac
sdmmc_execute_tuning+0x14c/0x210
mmc_execute_tuning+0x48/0xec
mmc_sd_init_uhs_card.part.0+0x208/0x464
mmc_sd_init_card+0x318/0x89c
mmc_attach_sd+0xe4/0x180
mmc_rescan+0x244/0x320

DMA API debug brings to light leaking dma-mappings as dma_map_sg and dma_unmap_sg are not correctly balanced.

If an error occurs in mmci_cmd_irq function, only mmci_dma_error function is called and as this API is not managed on stm32 variant, dma_unmap_sg is never called in this error path.

---
 drivers/mmc/host/mmci_stm32_sdmmc.c |   24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)
drivers/mmc/host/mmci_stm32_sdmmc.c +24 -0
@@ -200,6 +200,8 @@ static int sdmmc_idma_start(struct mmci_
 	struct scatterlist *sg;
 	int i;
 
+	host->dma_in_progress = true;
+
 	if (!host->variant->dma_lli || data->sg_len == 1 ||
 	    idma->use_bounce_buffer) {
 		u32 dma_addr;
@@ -238,9 +240,30 @@ static int sdmmc_idma_start(struct mmci_
 	return 0;
 }
 
+static void sdmmc_idma_error(struct mmci_host *host)
+{
+	struct mmc_data *data = host->data;
+	struct sdmmc_idma *idma = host->dma_priv;
+
+	if (!dma_inprogress(host))
+		return;
+
+	writel_relaxed(0, host->base + MMCI_STM32_IDMACTRLR);
+	host->dma_in_progress = false;
+	data->host_cookie = 0;
+
+	if (!idma->use_bounce_buffer)
+		dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
+			     mmc_get_dma_dir(data));
+}
+
 static void sdmmc_idma_finalize(struct mmci_host *host, struct mmc_data *data)
 {
+	if (!dma_inprogress(host))
+		return;
+
 	writel_relaxed(0, host->base + MMCI_STM32_IDMACTRLR);
+	host->dma_in_progress = false;
 
 	if (!data->host_cookie)
 		sdmmc_idma_unprep_data(host, data, 0);
@@ -567,6 +590,7 @@ static struct mmci_host_ops sdmmc_varian
 	.dma_setup = sdmmc_idma_setup,
 	.dma_start = sdmmc_idma_start,
 	.dma_finalize = sdmmc_idma_finalize,
+	.dma_error = sdmmc_idma_error,
 	.set_clkreg = mmci_sdmmc_set_clkreg,
 	.set_pwrreg = mmci_sdmmc_set_pwrreg,
 	.busy_complete = sdmmc_busy_complete,
author maintainer
#89 lore raw

PATCH 89/215 mmc: core: Fix eMMC initialization with 1-bit bus connection

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ivan Semenov <[email protected]>

commit ff3206d2186d84e4f77e1378ba1d225633f17b9b upstream.

Initializing an eMMC that's connected via a 1-bit bus is current failing, if the HW (DT) informs that 4-bit bus is supported. In fact this is a regression, as we were earlier capable of falling back to 1-bit mode, when switching to 4/8-bit bus failed. Therefore, let's restore the behaviour.

Log for Samsung eMMC 5.1 chip connected via 1bit bus (only D0 pin) Before patch:

[134509.044225] mmc0: switch to bus width 4 failed
[134509.044509] mmc0: new high speed MMC card at address 0001
[134509.054594] mmcblk0: mmc0:0001 BGUF4R 29.1 GiB
[134509.281602] mmc0: switch to bus width 4 failed
[134509.282638] I/O error, dev mmcblk0, sector 0 op 0x0:(READ) flags 0x0 phys_seg 1 prio class 2
[134509.282657] Buffer I/O error on dev mmcblk0, logical block 0, async page read
[134509.284598] I/O error, dev mmcblk0, sector 0 op 0x0:(READ) flags 0x0 phys_seg 1 prio class 2
[134509.284602] Buffer I/O error on dev mmcblk0, logical block 0, async page read
[134509.284609] ldm_validate_partition_table(): Disk read failed.
[134509.286495] I/O error, dev mmcblk0, sector 0 op 0x0:(READ) flags 0x0 phys_seg 1 prio class 2
[134509.286500] Buffer I/O error on dev mmcblk0, logical block 0, async page read
[134509.288303] I/O error, dev mmcblk0, sector 0 op 0x0:(READ) flags 0x0 phys_seg 1 prio class 2
[134509.288308] Buffer I/O error on dev mmcblk0, logical block 0, async page read
[134509.289540] I/O error, dev mmcblk0, sector 0 op 0x0:(READ) flags 0x0 phys_seg 1 prio class 2
[134509.289544] Buffer I/O error on dev mmcblk0, logical block 0, async page read
[134509.289553]  mmcblk0: unable to read partition table
[134509.289728] mmcblk0boot0: mmc0:0001 BGUF4R 31.9 MiB
[134509.290283] mmcblk0boot1: mmc0:0001 BGUF4R 31.9 MiB
[134509.294577] I/O error, dev mmcblk0, sector 0 op 0x0:(READ) flags 0x80700 phys_seg 1 prio class 2
[134509.295835] I/O error, dev mmcblk0, sector 0 op 0x0:(READ) flags 0x0 phys_seg 1 prio class 2
[134509.295841] Buffer I/O error on dev mmcblk0, logical block 0, async page read

After patch:

[134551.089613] mmc0: switch to bus width 4 failed
[134551.090377] mmc0: new high speed MMC card at address 0001
[134551.102271] mmcblk0: mmc0:0001 BGUF4R 29.1 GiB
[134551.113365]  mmcblk0: p1 p2 p3 p4 p5 p6 p7 p8 p9 p10 p11 p12 p13 p14 p15 p16 p17 p18 p19 p20 p21
[134551.114262] mmcblk0boot0: mmc0:0001 BGUF4R 31.9 MiB
[134551.114925] mmcblk0boot1: mmc0:0001 BGUF4R 31.9 MiB
---
 drivers/mmc/core/mmc.c |    2 ++
 1 file changed, 2 insertions(+)
drivers/mmc/core/mmc.c +2 -0
@@ -1007,10 +1007,12 @@ static int mmc_select_bus_width(struct m
 	static unsigned ext_csd_bits[] = {
 		EXT_CSD_BUS_WIDTH_8,
 		EXT_CSD_BUS_WIDTH_4,
+		EXT_CSD_BUS_WIDTH_1,
 	};
 	static unsigned bus_widths[] = {
 		MMC_BUS_WIDTH_8,
 		MMC_BUS_WIDTH_4,
+		MMC_BUS_WIDTH_1,
 	};
 	struct mmc_host *host = card->host;
 	unsigned idx, bus_width = 0;
author maintainer
#90 lore raw

PATCH 90/215 mmc: sdhci-xenon: add timeout for PHY init complete

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Elad Nachman <[email protected]>

commit 09e23823ae9a3e2d5d20f2e1efe0d6e48cef9129 upstream.

AC5X spec says PHY init complete bit must be polled until zero. We see cases in which timeout can take longer than the standard calculation on AC5X, which is expected following the spec comment above. According to the spec, we must wait as long as it takes for that bit to toggle on AC5X.
Cap that with 100 delay loops so we won't get stuck forever.

Fixes 06c8b667ff5b ("mmc: sdhci-xenon: Add support to PHYs of Marvell Xenon SDHC")
---
 drivers/mmc/host/sdhci-xenon-phy.c |   29 ++++++++++++++++++++---------
 1 file changed, 20 insertions(+), 9 deletions(-)
drivers/mmc/host/sdhci-xenon-phy.c +20 -9
@@ -109,6 +109,8 @@
 #define XENON_EMMC_PHY_LOGIC_TIMING_ADJUST	(XENON_EMMC_PHY_REG_BASE + 0x18)
 #define XENON_LOGIC_TIMING_VALUE		0x00AA8977
 
+#define XENON_MAX_PHY_TIMEOUT_LOOPS		100
+
 /*
  * List offset of PHY registers and some special register values
  * in eMMC PHY 5.0 or eMMC PHY 5.1
@@ -259,18 +261,27 @@ static int xenon_emmc_phy_init(struct sd
 	/* get the wait time */
 	wait /= clock;
 	wait++;
-	/* wait for host eMMC PHY init completes */
-	udelay(wait);
 
-	reg = sdhci_readl(host, phy_regs->timing_adj);
-	reg &= XENON_PHY_INITIALIZAION;
-	if (reg) {
+	/*
+	 * AC5X spec says bit must be polled until zero.
+	 * We see cases in which timeout can take longer
+	 * than the standard calculation on AC5X, which is
+	 * expected following the spec comment above.
+	 * According to the spec, we must wait as long as
+	 * it takes for that bit to toggle on AC5X.
+	 * Cap that with 100 delay loops so we won't get
+	 * stuck here forever:
+	 */
+
+	ret = read_poll_timeout(sdhci_readl, reg,
+				!(reg & XENON_PHY_INITIALIZAION),
+				wait, XENON_MAX_PHY_TIMEOUT_LOOPS * wait,
+				false, host, phy_regs->timing_adj);
+	if (ret)
 		dev_err(mmc_dev(host->mmc), "eMMC PHY init cannot complete after %d us\n",
-			wait);
-		return -ETIMEDOUT;
-	}
+			wait * XENON_MAX_PHY_TIMEOUT_LOOPS);
 
-	return 0;
+	return ret;
 }
 
 #define ARMADA_3700_SOC_PAD_1_8V	0x1
author maintainer
#91 lore raw

PATCH 91/215 mmc: sdhci-xenon: fix PHY init clock stability

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Elad Nachman <[email protected]>

commit 8e9f25a290ae0016353c9ea13314c95fb3207812 upstream.

Each time SD/mmc phy is initialized, at times, in some of the attempts, phy fails to completes its initialization which results into timeout error. Per the HW spec, it is a pre-requisite to ensure a stable SD clock before a phy initialization is attempted.

Fixes 06c8b667ff5b ("mmc: sdhci-xenon: Add support to PHYs of Marvell Xenon SDHC")
---
 drivers/mmc/host/sdhci-xenon-phy.c |   19 +++++++++++++++++++
 1 file changed, 19 insertions(+)
drivers/mmc/host/sdhci-xenon-phy.c +19 -0
@@ -11,6 +11,7 @@
 #include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/ktime.h>
+#include <linux/iopoll.h>
 #include <linux/of_address.h>
 
 #include "sdhci-pltfm.h"
@@ -218,6 +219,19 @@ static int xenon_alloc_emmc_phy(struct s
 	return 0;
 }
 
+static int xenon_check_stability_internal_clk(struct sdhci_host *host)
+{
+	u32 reg;
+	int err;
+
+	err = read_poll_timeout(sdhci_readw, reg, reg & SDHCI_CLOCK_INT_STABLE,
+				1100, 20000, false, host, SDHCI_CLOCK_CONTROL);
+	if (err)
+		dev_err(mmc_dev(host->mmc), "phy_init: Internal clock never stabilized.\n");
+
+	return err;
+}
+
 /*
  * eMMC 5.0/5.1 PHY init/re-init.
  * eMMC PHY init should be executed after:
@@ -234,6 +248,11 @@ static int xenon_emmc_phy_init(struct sd
 	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
 	struct xenon_emmc_phy_regs *phy_regs = priv->emmc_phy_regs;
 
+	int ret = xenon_check_stability_internal_clk(host);
+
+	if (ret)
+		return ret;
+
 	reg = sdhci_readl(host, phy_regs->timing_adj);
 	reg |= XENON_PHY_INITIALIZAION;
 	sdhci_writel(host, reg, phy_regs->timing_adj);
author maintainer
#92 lore raw

PATCH 92/215 riscv: add CALLER_ADDRx support

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Zong Li <[email protected]>

commit 680341382da56bd192ebfa4e58eaf4fec2e5bca7 upstream.

CALLER_ADDRx returns caller's address at specified level, they are used for several tracers. These macros eventually use __builtin_return_address(n) to get the caller's address if arch doesn't define their own implementation.

In RISC-V, __builtin_return_address(n) only works when n == 0, we need to walk the stack frame to get the caller's address at specified level.

data.level started from 'level + 3' due to the call flow of getting caller's address in RISC-V implementation. If we don't have additional three iteration, the level is corresponding to follows:

callsite -> return_address -> arch_stack_walk -> walk_stackframe

|           |                 |                  |
level 3     level 2           level 1            level 0
---
 arch/riscv/include/asm/ftrace.h    |    5 +++
 arch/riscv/kernel/Makefile         |    2 +
 arch/riscv/kernel/return_address.c |   48 +++++++++++++++++++++++++++++++++++++
 3 files changed, 55 insertions(+)
 create mode 100644 arch/riscv/kernel/return_address.c
arch/riscv/include/asm/ftrace.h +5 -0
@@ -25,6 +25,11 @@
 
 #define ARCH_SUPPORTS_FTRACE_OPS 1
 #ifndef __ASSEMBLY__
+
+extern void *return_address(unsigned int level);
+
+#define ftrace_return_address(n) return_address(n)
+
 void MCOUNT_NAME(void);
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
arch/riscv/kernel/Makefile +2 -0
@@ -7,6 +7,7 @@ ifdef CONFIG_FTRACE
 CFLAGS_REMOVE_ftrace.o	= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_patch.o	= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_sbi.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_return_address.o	= $(CC_FLAGS_FTRACE)
 endif
 CFLAGS_syscall_table.o	+= $(call cc-option,-Wno-override-init,)
 CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,)
@@ -41,6 +42,7 @@ obj-y	+= irq.o
 obj-y	+= process.o
 obj-y	+= ptrace.o
 obj-y	+= reset.o
+obj-y	+= return_address.o
 obj-y	+= setup.o
 obj-y	+= signal.o
 obj-y	+= syscall_table.o
arch/riscv/kernel/return_address.c new file +48 -0

48 lines not on this page · raw message

author maintainer
#69 lore raw

PATCH 69/215 afs: Fix endless loop in directory parsing

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Howells <[email protected]>

[ Upstream commit 5f7a07646655fb4108da527565dcdc80124b14c4 ]

If a directory has a block with only ".__afsXXXX" files in it (from uncompleted silly-rename), these .__afsXXXX files are skipped but without advancing the file position in the dir_context. This leads to afs_dir_iterate() repeating the block again and again.

Fix this by making the code that skips the .__afsXXXX file also manually advance the file position.

The symptoms are a soft lookup:

        watchdog: BUG: soft lockup - CPU#3 stuck for 52s! [check:5737]
        ...
        RIP: 0010:afs_dir_iterate_block+0x39/0x1fd
        ...
         ? watchdog_timer_fn+0x1a6/0x213
        ...
         ? asm_sysvec_apic_timer_interrupt+0x16/0x20
         ? afs_dir_iterate_block+0x39/0x1fd
         afs_dir_iterate+0x10a/0x148
         afs_readdir+0x30/0x4a
         iterate_dir+0x93/0xd3
         __do_sys_getdents64+0x6b/0xd4

This is almost certainly the actual fix for:

        https://bugzilla.kernel.org/show_bug.cgi?id=218496
Fixes 57e9d49c5452 ("afs: Hide silly-rename files from userspace")
cc Marc Dionne <[email protected]>
cc Markus Suvanto <[email protected]>
---
 fs/afs/dir.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
fs/afs/dir.c +3 -1
index cf811b77ee671..6e2c967fae6fc 100644
@@ -478,8 +478,10 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode,
 		    dire->u.name[0] == '.' &&
 		    ctx->actor != afs_lookup_filldir &&
 		    ctx->actor != afs_lookup_one_filldir &&
-		    memcmp(dire->u.name, ".__afs", 6) == 0)
+		    memcmp(dire->u.name, ".__afs", 6) == 0) {
+			ctx->pos = blkoff + next * sizeof(union afs_xdr_dirent);
 			continue;
+		}
 
 		/* found the next entry */
 		if (!dir_emit(ctx, dire->u.name, nlen,
Signature · 1 line
2.43.0
author maintainer
#70 lore raw

PATCH 70/215 riscv: Sparse-Memory/vmemmap out-of-bounds fix

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dimitris Vlachos <[email protected]>

[ Upstream commit a11dd49dcb9376776193e15641f84fcc1e5980c9 ]

Offset vmemmap so that the first page of vmemmap will be mapped to the first page of physical memory in order to ensure that vmemmap’s bounds will be respected during pfn_to_page()/page_to_pfn() operations.
The conversion macros will produce correct SV39/48/57 addresses for every possible/valid DRAM_BASE inside the physical memory limits.

v2:Address Alex's comments

---
 arch/riscv/include/asm/pgtable.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/riscv/include/asm/pgtable.h +1 -1
index 59bb53da473dd..63055c6ad2c25 100644
@@ -79,7 +79,7 @@
  * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel
  * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled.
  */
-#define vmemmap		((struct page *)VMEMMAP_START)
+#define vmemmap		((struct page *)VMEMMAP_START - (phys_ram_base >> PAGE_SHIFT))
 
 #define PCI_IO_SIZE      SZ_16M
 #define PCI_IO_END       VMEMMAP_START
Signature · 1 line
2.43.0
author maintainer
#71 lore raw

PATCH 71/215 of: property: fw_devlink: Fix stupid bug in remote-endpoint parsing

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Saravana Kannan <[email protected]>

[ Upstream commit 7cb50f6c9fbaa1c0b80100b8971bf13db5d75d06 ]

Introduced a stupid bug in commit 782bfd03c3ae ("of: property: Improve finding the supplier of a remote-endpoint property") due to a last minute incorrect edit of "index !=0" into "!index". This patch fixes it to be "index > 0" to match the comment right next to it.

---
 drivers/of/property.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/of/property.c +1 -1
index 33d5f16c81204..da5d712197704 100644
@@ -1332,7 +1332,7 @@ static struct device_node *parse_remote_endpoint(struct device_node *np,
 						 int index)
 {
 	/* Return NULL for index > 0 to signify end of remote-endpoints. */
-	if (!index || strcmp(prop_name, "remote-endpoint"))
+	if (index > 0 || strcmp(prop_name, "remote-endpoint"))
 		return NULL;
 
 	return of_graph_get_remote_port_parent(np);
Signature · 1 line
2.43.0
author maintainer
#72 lore raw

PATCH 72/215 tomoyo: fix UAF write bug in tomoyo_write_control()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tetsuo Handa <[email protected]>

commit 2f03fc340cac9ea1dc63cbf8c93dd2eb0f227815 upstream.

Since tomoyo_write_control() updates head->write_buf when write() of long lines is requested, we need to fetch head->write_buf after head->io_sem is held. Otherwise, concurrent write() requests can cause use-after-free-write and double-free problems.

---
 security/tomoyo/common.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
security/tomoyo/common.c +2 -1
@@ -2648,13 +2648,14 @@ ssize_t tomoyo_write_control(struct tomo
 {
 	int error = buffer_len;
 	size_t avail_len = buffer_len;
-	char *cp0 = head->write_buf;
+	char *cp0;
 	int idx;
 
 	if (!head->write)
 		return -EINVAL;
 	if (mutex_lock_interruptible(&head->io_sem))
 		return -EINTR;
+	cp0 = head->write_buf;
 	head->read_user_buf_avail = 0;
 	idx = tomoyo_read_lock();
 	/* Read a line and dispatch it to the policy handler. */
author maintainer
#73 lore raw

PATCH 73/215 ALSA: firewire-lib: fix to check cycle continuity

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Takashi Sakamoto <[email protected]>

commit 77ce96543b03f437c6b45f286d8110db2b6622a3 upstream.

The local helper function to compare the given pair of cycle count evaluates them. If the left value is less than the right value, the function returns negative value.

If the safe cycle is less than the current cycle, it is the case of cycle lost. However, it is not currently handled properly.

This commit fixes the bug.

---
 sound/firewire/amdtp-stream.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
sound/firewire/amdtp-stream.c +1 -1
@@ -934,7 +934,7 @@ static int generate_device_pkt_descs(str
 				// to the reason.
 				unsigned int safe_cycle = increment_ohci_cycle_count(next_cycle,
 								IR_JUMBO_PAYLOAD_MAX_SKIP_CYCLES);
-				lost = (compare_ohci_cycle_count(safe_cycle, cycle) > 0);
+				lost = (compare_ohci_cycle_count(safe_cycle, cycle) < 0);
 			}
 			if (lost) {
 				dev_err(&s->unit->device, "Detect discontinuity of cycle: %d %d\n",
author maintainer
#74 lore raw

PATCH 74/215 ALSA: hda/realtek: Enable Mute LED on HP 840 G8 (MB 8AB8)

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hans Peter <[email protected]>

commit 1fdf4e8be7059e7784fec11d30cd32784f0bdc83 upstream.

On my EliteBook 840 G8 Notebook PC (ProdId 5S7R6EC#ABD; built 2022 for german market) the Mute LED is always on. The mute button itself works as expected. alsa-info.sh shows a different subsystem-id 0x8ab9 for Realtek ALC285 Codec, thus the existing quirks for HP 840 G8 don't work. Therefore, add a new quirk for this type of EliteBook.

---
 sound/pci/hda/patch_realtek.c |    1 +
 1 file changed, 1 insertion(+)
sound/pci/hda/patch_realtek.c +1 -0
@@ -9687,6 +9687,7 @@ static const struct snd_pci_quirk alc269
 	SND_PCI_QUIRK(0x103c, 0x8aa3, "HP ProBook 450 G9 (MB 8AA1)", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8aa8, "HP EliteBook 640 G9 (MB 8AA6)", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8aab, "HP EliteBook 650 G9 (MB 8AA9)", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8ab9, "HP EliteBook 840 G8 (MB 8AB8)", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
author maintainer
#75 lore raw

PATCH 75/215 ALSA: hda/realtek: fix mute/micmute LED For HP mt440

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eniac Zhang <[email protected]>

commit 67c3d7717efbd46092f217b1f811df1b205cce06 upstream.

The HP mt440 Thin Client uses an ALC236 codec and needs the ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF quirk to make the mute and micmute LEDs work.

There are two variants of the USB-C PD chip on this device. Each uses a different BIOS and board ID, hence the two entries.

---
 sound/pci/hda/patch_realtek.c |    2 ++
 1 file changed, 2 insertions(+)
sound/pci/hda/patch_realtek.c +2 -0
@@ -9662,6 +9662,7 @@ static const struct snd_pci_quirk alc269
 	SND_PCI_QUIRK(0x103c, 0x8973, "HP EliteBook 860 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8974, "HP EliteBook 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8975, "HP EliteBook x360 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x897d, "HP mt440 Mobile Thin Client U74", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8981, "HP Elite Dragonfly G3", ALC245_FIXUP_CS35L41_SPI_4),
 	SND_PCI_QUIRK(0x103c, 0x898e, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x898f, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2),
@@ -9693,6 +9694,7 @@ static const struct snd_pci_quirk alc269
 	SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8b0f, "HP Elite mt645 G7 Mobile Thin Client U81", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8b2f, "HP 255 15.6 inch G10 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
+	SND_PCI_QUIRK(0x103c, 0x8b3f, "HP mt440 Mobile Thin Client U91", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8b42, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8b43, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8b44, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
author maintainer
#66 lore raw

PATCH 66/215 ALSA: Drop leftover snd-rtctimer stuff from Makefile

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Takashi Iwai <[email protected]>

[ Upstream commit 4df49712eb54141be00a9312547436d55677f092 ]

We forgot to remove the line for snd-rtctimer from Makefile while dropping the functionality. Get rid of the stale line.

Fixes 34ce71a96dcb ("ALSA: timer: remove legacy rtctimer")
---
 sound/core/Makefile | 1 -
 1 file changed, 1 deletion(-)
sound/core/Makefile +0 -1
index 2762f03d9b7bc..a7a1590b29526 100644
@@ -30,7 +30,6 @@ snd-ctl-led-objs  := control_led.o
 snd-rawmidi-objs  := rawmidi.o
 snd-timer-objs    := timer.o
 snd-hrtimer-objs  := hrtimer.o
-snd-rtctimer-objs := rtctimer.o
 snd-hwdep-objs    := hwdep.o
 snd-seq-device-objs := seq_device.o
 
Signature · 1 line
2.43.0
author maintainer
#94 lore raw

PATCH 94/215 pmdomain: qcom: rpmhpd: Fix enabled_corner aggregation

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Bjorn Andersson <[email protected]>

commit 2a93c6cbd5a703d44c414a3c3945a87ce11430ba upstream.

Commit 'e3e56c050ab6 ("soc: qcom: rpmhpd: Make power_on actually enable the domain")' aimed to make sure that a power-domain that is being enabled without any particular performance-state requested will at least turn the rail on, to avoid filling DeviceTree with otherwise unnecessary required-opps properties.

But in the event that aggregation happens on a disabled power-domain, with an enabled peer without performance-state, both the local and peer corner are 0. The peer's enabled_corner is not considered, with the result that the underlying (shared) resource is disabled.

One case where this can be observed is when the display stack keeps mmcx enabled (but without a particular performance-state vote) in order to access registers and sync_state happens in the rpmhpd driver. As mmcx_ao is flushed the state of the peer (mmcx) is not considered and mmcx_ao ends up turning off "mmcx.lvl" underneath mmcx. This has been observed several times, but has been painted over in DeviceTree by adding an explicit vote for the lowest non-disabled performance-state.

---
 drivers/soc/qcom/rpmhpd.c |    7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)
drivers/soc/qcom/rpmhpd.c +5 -2
@@ -492,12 +492,15 @@ static int rpmhpd_aggregate_corner(struc
 	unsigned int active_corner, sleep_corner;
 	unsigned int this_active_corner = 0, this_sleep_corner = 0;
 	unsigned int peer_active_corner = 0, peer_sleep_corner = 0;
+	unsigned int peer_enabled_corner;
 
 	to_active_sleep(pd, corner, &this_active_corner, &this_sleep_corner);
 
-	if (peer && peer->enabled)
-		to_active_sleep(peer, peer->corner, &peer_active_corner,
+	if (peer && peer->enabled) {
+		peer_enabled_corner = max(peer->corner, peer->enable_corner);
+		to_active_sleep(peer, peer_enabled_corner, &peer_active_corner,
 				&peer_sleep_corner);
+	}
 
 	active_corner = max(this_active_corner, peer_active_corner);
 
author maintainer
#103 lore raw

PATCH 103/215 selftests: mptcp: join: add ss mptcp support check

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Geliang Tang <[email protected]>

commit 9480f388a2ef54fba911d9325372abd69a328601 upstream.

Commands 'ss -M' are used in script mptcp_join.sh to display only MPTCP sockets. So it must be checked if ss tool supports MPTCP in this script.

---
 tools/testing/selftests/net/mptcp/mptcp_join.sh |    5 +++++
 1 file changed, 5 insertions(+)
tools/testing/selftests/net/mptcp/mptcp_join.sh +5 -0
@@ -144,6 +144,11 @@ check_tools()
 		exit $ksft_skip
 	fi
 
+	if ! ss -h | grep -q MPTCP; then
+		echo "SKIP: ss tool does not support MPTCP"
+		exit $ksft_skip
+	fi
+
 	# Use the legacy version if available to support old kernel versions
 	if iptables-legacy -V &> /dev/null; then
 		iptables="iptables-legacy"
author maintainer
#104 lore raw

PATCH 104/215 mptcp: fix snd_wnd initialization for passive socket

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Paolo Abeni <[email protected]>

commit adf1bb78dab55e36d4d557aa2fb446ebcfe9e5ce upstream.

Such value should be inherited from the first subflow, but passive sockets always used 'rsk_rcv_wnd'.

---
 net/mptcp/protocol.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
net/mptcp/protocol.c +1 -1
@@ -3203,7 +3203,7 @@ struct sock *mptcp_sk_clone_init(const s
 	msk->write_seq = subflow_req->idsn + 1;
 	msk->snd_nxt = msk->write_seq;
 	msk->snd_una = msk->write_seq;
-	msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd;
+	msk->wnd_end = msk->snd_nxt + tcp_sk(ssk)->snd_wnd;
 	msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq;
 
 	if (mp_opt->suboptions & OPTIONS_MPTCP_MPC) {
author maintainer
#105 lore raw

PATCH 105/215 mptcp: fix double-free on socket dismantle

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Davide Caratti <[email protected]>

commit 10048689def7e40a4405acda16fdc6477d4ecc5c upstream.

when MPTCP server accepts an incoming connection, it clones its listener socket. However, the pointer to 'inet_opt' for the new socket has the same value as the original one: as a consequence, on program exit it's possible to observe the following splat:

  BUG: KASAN: double-free in inet_sock_destruct+0x54f/0x8b0
  Free of addr ffff888485950880 by task swapper/25/0

  CPU: 25 PID: 0 Comm: swapper/25 Kdump: loaded Not tainted 6.8.0-rc1+ #609
  Hardware name: Supermicro SYS-6027R-72RF/X9DRH-7TF/7F/iTF/iF, BIOS 3.0  07/26/2013
  Call Trace:
   <IRQ>
   dump_stack_lvl+0x32/0x50
   print_report+0xca/0x620
   kasan_report_invalid_free+0x64/0x90
   __kasan_slab_free+0x1aa/0x1f0
   kfree+0xed/0x2e0
   inet_sock_destruct+0x54f/0x8b0
   __sk_destruct+0x48/0x5b0
   rcu_do_batch+0x34e/0xd90
   rcu_core+0x559/0xac0
   __do_softirq+0x183/0x5a4
   irq_exit_rcu+0x12d/0x170
   sysvec_apic_timer_interrupt+0x6b/0x80
   </IRQ>
   <TASK>
   asm_sysvec_apic_timer_interrupt+0x16/0x20
  RIP: 0010:cpuidle_enter_state+0x175/0x300
  Code: 30 00 0f 84 1f 01 00 00 83 e8 01 83 f8 ff 75 e5 48 83 c4 18 44 89 e8 5b 5d 41 5c 41 5d 41 5e 41 5f c3 cc cc cc cc fb 45 85 ed <0f> 89 60 ff ff ff 48 c1 e5 06 48 c7 43 18 00 00 00 00 48 83 44 2b
  RSP: 0018:ffff888481cf7d90 EFLAGS: 00000202
  RAX: 0000000000000000 RBX: ffff88887facddc8 RCX: 0000000000000000
  RDX: 1ffff1110ff588b1 RSI: 0000000000000019 RDI: ffff88887fac4588
  RBP: 0000000000000004 R08: 0000000000000002 R09: 0000000000043080
  R10: 0009b02ea273363f R11: ffff88887fabf42b R12: ffffffff932592e0
  R13: 0000000000000004 R14: 0000000000000000 R15: 00000022c880ec80
   cpuidle_enter+0x4a/0xa0
   do_idle+0x310/0x410
   cpu_startup_entry+0x51/0x60
   start_secondary+0x211/0x270
   secondary_startup_64_no_verify+0x184/0x18b
   </TASK>

  Allocated by task 6853:
   kasan_save_stack+0x1c/0x40
   kasan_save_track+0x10/0x30
   __kasan_kmalloc+0xa6/0xb0
   __kmalloc+0x1eb/0x450
   cipso_v4_sock_setattr+0x96/0x360
   netlbl_sock_setattr+0x132/0x1f0
   selinux_netlbl_socket_post_create+0x6c/0x110
   selinux_socket_post_create+0x37b/0x7f0
   security_socket_post_create+0x63/0xb0
   __sock_create+0x305/0x450
   __sys_socket_create.part.23+0xbd/0x130
   __sys_socket+0x37/0xb0
   __x64_sys_socket+0x6f/0xb0
   do_syscall_64+0x83/0x160
   entry_SYSCALL_64_after_hwframe+0x6e/0x76

  Freed by task 6858:
   kasan_save_stack+0x1c/0x40
   kasan_save_track+0x10/0x30
   kasan_save_free_info+0x3b/0x60
   __kasan_slab_free+0x12c/0x1f0
   kfree+0xed/0x2e0
   inet_sock_destruct+0x54f/0x8b0
   __sk_destruct+0x48/0x5b0
   subflow_ulp_release+0x1f0/0x250
   tcp_cleanup_ulp+0x6e/0x110
   tcp_v4_destroy_sock+0x5a/0x3a0
   inet_csk_destroy_sock+0x135/0x390
   tcp_fin+0x416/0x5c0
   tcp_data_queue+0x1bc8/0x4310
   tcp_rcv_state_process+0x15a3/0x47b0
   tcp_v4_do_rcv+0x2c1/0x990
   tcp_v4_rcv+0x41fb/0x5ed0
   ip_protocol_deliver_rcu+0x6d/0x9f0
   ip_local_deliver_finish+0x278/0x360
   ip_local_deliver+0x182/0x2c0
   ip_rcv+0xb5/0x1c0
   __netif_receive_skb_one_core+0x16e/0x1b0
   process_backlog+0x1e3/0x650
   __napi_poll+0xa6/0x500
   net_rx_action+0x740/0xbb0
   __do_softirq+0x183/0x5a4

  The buggy address belongs to the object at ffff888485950880
   which belongs to the cache kmalloc-64 of size 64
  The buggy address is located 0 bytes inside of
   64-byte region [ffff888485950880, ffff8884859508c0)

  The buggy address belongs to the physical page:
  page:0000000056d1e95e refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff888485950700 pfn:0x485950
  flags: 0x57ffffc0000800(slab|node=1|zone=2|lastcpupid=0x1fffff)
  page_type: 0xffffffff()
  raw: 0057ffffc0000800 ffff88810004c640 ffffea00121b8ac0 dead000000000006
  raw: ffff888485950700 0000000000200019 00000001ffffffff 0000000000000000
  page dumped because: kasan: bad access detected

  Memory state around the buggy address:
   ffff888485950780: fa fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
   ffff888485950800: fa fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
  >ffff888485950880: fa fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
                     ^
   ffff888485950900: fa fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
   ffff888485950980: 00 00 00 00 00 01 fc fc fc fc fc fc fc fc fc fc

Something similar (a refcount underflow) happens with CALIPSO/IPv6. Fix this by duplicating IP / IPv6 options after clone, so that ip{,6}_sock_destruct() doesn't end up freeing the same memory area twice.

---
 net/mptcp/protocol.c |   49 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 49 insertions(+)
net/mptcp/protocol.c +49 -0
@@ -3169,8 +3169,50 @@ static struct ipv6_pinfo *mptcp_inet6_sk
 
 	return (struct ipv6_pinfo *)(((u8 *)sk) + offset);
 }
+
+static void mptcp_copy_ip6_options(struct sock *newsk, const struct sock *sk)
+{
+	const struct ipv6_pinfo *np = inet6_sk(sk);
+	struct ipv6_txoptions *opt;
+	struct ipv6_pinfo *newnp;
+
+	newnp = inet6_sk(newsk);
+
+	rcu_read_lock();
+	opt = rcu_dereference(np->opt);
+	if (opt) {
+		opt = ipv6_dup_options(newsk, opt);
+		if (!opt)
+			net_warn_ratelimited("%s: Failed to copy ip6 options\n", __func__);
+	}
+	RCU_INIT_POINTER(newnp->opt, opt);
+	rcu_read_unlock();
+}
 #endif
 
+static void mptcp_copy_ip_options(struct sock *newsk, const struct sock *sk)
+{
+	struct ip_options_rcu *inet_opt, *newopt = NULL;
+	const struct inet_sock *inet = inet_sk(sk);
+	struct inet_sock *newinet;
+
+	newinet = inet_sk(newsk);
+
+	rcu_read_lock();
+	inet_opt = rcu_dereference(inet->inet_opt);
+	if (inet_opt) {
+		newopt = sock_kmalloc(newsk, sizeof(*inet_opt) +
+				      inet_opt->opt.optlen, GFP_ATOMIC);
+		if (newopt)
+			memcpy(newopt, inet_opt, sizeof(*inet_opt) +
+			       inet_opt->opt.optlen);
+		else
+			net_warn_ratelimited("%s: Failed to copy ip options\n", __func__);
+	}
+	RCU_INIT_POINTER(newinet->inet_opt, newopt);
+	rcu_read_unlock();
+}
+
 struct sock *mptcp_sk_clone_init(const struct sock *sk,
 				 const struct mptcp_options_received *mp_opt,
 				 struct sock *ssk,
@@ -3191,6 +3233,13 @@ struct sock *mptcp_sk_clone_init(const s
 
 	__mptcp_init_sock(nsk);
 
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	if (nsk->sk_family == AF_INET6)
+		mptcp_copy_ip6_options(nsk, sk);
+	else
+#endif
+		mptcp_copy_ip_options(nsk, sk);
+
 	msk = mptcp_sk(nsk);
 	msk->local_key = subflow_req->local_key;
 	msk->token = subflow_req->token;
author maintainer
#106 lore raw

PATCH 106/215 mptcp: fix possible deadlock in subflow diag

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Paolo Abeni <[email protected]>

commit d6a9608af9a75d13243d217f6ce1e30e57d56ffe upstream.

Syzbot and Eric reported a lockdep splat in the subflow diag:

WARNING: possible circular locking dependency detected 6.8.0-rc4-syzkaller-00212-g40b9385dd8e6 #0 Not tainted

syz-executor.2/24141 is trying to acquire lock:
ffff888045870130 (k-sk_lock-AF_INET6){+.+.}-{0:0}, at:

   tcp_diag_put_ulp net/ipv4/tcp_diag.c:100 [inline]
   ffff888045870130 (k-sk_lock-AF_INET6){+.+.}-{0:0}, at:
   tcp_diag_get_aux+0x738/0x830 net/ipv4/tcp_diag.c:137

but task is already holding lock:
ffffc9000135e488 (&h->lhash2[i].lock){+.+.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline] ffffc9000135e488 (&h->lhash2[i].lock){+.+.}-{2:2}, at:
inet_diag_dump_icsk+0x39f/0x1f80 net/ipv4/inet_diag.c:1038

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #1 (&h->lhash2[i].lock){+.+.}-{2:2}:

   lock_acquire+0x1e3/0x530 kernel/locking/lockdep.c:5754
   __raw_spin_lock include/linux/spinlock_api_smp.h:133 [inline]
   _raw_spin_lock+0x2e/0x40 kernel/locking/spinlock.c:154
   spin_lock include/linux/spinlock.h:351 [inline]
   __inet_hash+0x335/0xbe0 net/ipv4/inet_hashtables.c:743
   inet_csk_listen_start+0x23a/0x320 net/ipv4/inet_connection_sock.c:1261
   __inet_listen_sk+0x2a2/0x770 net/ipv4/af_inet.c:217
   inet_listen+0xa3/0x110 net/ipv4/af_inet.c:239
   rds_tcp_listen_init+0x3fd/0x5a0 net/rds/tcp_listen.c:316
   rds_tcp_init_net+0x141/0x320 net/rds/tcp.c:577
   ops_init+0x352/0x610 net/core/net_namespace.c:136
   __register_pernet_operations net/core/net_namespace.c:1214 [inline]
   register_pernet_operations+0x2cb/0x660 net/core/net_namespace.c:1283
   register_pernet_device+0x33/0x80 net/core/net_namespace.c:1370
   rds_tcp_init+0x62/0xd0 net/rds/tcp.c:735
   do_one_initcall+0x238/0x830 init/main.c:1236
   do_initcall_level+0x157/0x210 init/main.c:1298
   do_initcalls+0x3f/0x80 init/main.c:1314
   kernel_init_freeable+0x42f/0x5d0 init/main.c:1551
   kernel_init+0x1d/0x2a0 init/main.c:1441
   ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147
   ret_from_fork_asm+0x1b/0x30 arch/x86/entry/entry_64.S:242

-> #0 (k-sk_lock-AF_INET6){+.+.}-{0:0}:

   check_prev_add kernel/locking/lockdep.c:3134 [inline]
   check_prevs_add kernel/locking/lockdep.c:3253 [inline]
   validate_chain+0x18ca/0x58e0 kernel/locking/lockdep.c:3869
   __lock_acquire+0x1345/0x1fd0 kernel/locking/lockdep.c:5137
   lock_acquire+0x1e3/0x530 kernel/locking/lockdep.c:5754
   lock_sock_fast include/net/sock.h:1723 [inline]
   subflow_get_info+0x166/0xd20 net/mptcp/diag.c:28
   tcp_diag_put_ulp net/ipv4/tcp_diag.c:100 [inline]
   tcp_diag_get_aux+0x738/0x830 net/ipv4/tcp_diag.c:137
   inet_sk_diag_fill+0x10ed/0x1e00 net/ipv4/inet_diag.c:345
   inet_diag_dump_icsk+0x55b/0x1f80 net/ipv4/inet_diag.c:1061
   __inet_diag_dump+0x211/0x3a0 net/ipv4/inet_diag.c:1263
   inet_diag_dump_compat+0x1c1/0x2d0 net/ipv4/inet_diag.c:1371
   netlink_dump+0x59b/0xc80 net/netlink/af_netlink.c:2264
   __netlink_dump_start+0x5df/0x790 net/netlink/af_netlink.c:2370
   netlink_dump_start include/linux/netlink.h:338 [inline]
   inet_diag_rcv_msg_compat+0x209/0x4c0 net/ipv4/inet_diag.c:1405
   sock_diag_rcv_msg+0xe7/0x410
   netlink_rcv_skb+0x1e3/0x430 net/netlink/af_netlink.c:2543
   sock_diag_rcv+0x2a/0x40 net/core/sock_diag.c:280
   netlink_unicast_kernel net/netlink/af_netlink.c:1341 [inline]
   netlink_unicast+0x7ea/0x980 net/netlink/af_netlink.c:1367
   netlink_sendmsg+0xa3b/0xd70 net/netlink/af_netlink.c:1908
   sock_sendmsg_nosec net/socket.c:730 [inline]
   __sock_sendmsg+0x221/0x270 net/socket.c:745
   ____sys_sendmsg+0x525/0x7d0 net/socket.c:2584
   ___sys_sendmsg net/socket.c:2638 [inline]
   __sys_sendmsg+0x2b0/0x3a0 net/socket.c:2667
   do_syscall_64+0xf9/0x240
   entry_SYSCALL_64_after_hwframe+0x6f/0x77

As noted by Eric we can break the lock dependency chain avoid dumping any extended info for the mptcp subflow listener:
nothing actually useful is presented there.

---
 net/mptcp/diag.c |    3 +++
 1 file changed, 3 insertions(+)
net/mptcp/diag.c +3 -0
@@ -21,6 +21,9 @@ static int subflow_get_info(struct sock
 	bool slow;
 	int err;
 
+	if (inet_sk_state_load(sk) == TCP_LISTEN)
+		return 0;
+
 	start = nla_nest_start_noflag(skb, INET_ULP_INFO_MPTCP);
 	if (!start)
 		return -EMSGSIZE;
author maintainer
#107 lore raw

PATCH 107/215 RDMA/core: Refactor rdma_bind_addr

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Patrisious Haddad <[email protected]>

commit 8d037973d48c026224ab285e6a06985ccac6f7bf upstream.

Refactor rdma_bind_addr function so that it doesn't require that the cma destination address be changed before calling it.

So now it will update the destination address internally only when it is really needed and after passing all the required checks.

Which in turn results in a cleaner and more sensible call and error handling flows for the functions that call it directly or indirectly.

---
 drivers/infiniband/core/cma.c |  253 +++++++++++++++++++++---------------------
 1 file changed, 130 insertions(+), 123 deletions(-)
drivers/infiniband/core/cma.c +130 -123
@@ -3547,121 +3547,6 @@ err:
 	return ret;
 }
 
-static int cma_bind_addr(struct rdma_cm_id *id, struct sockaddr *src_addr,
-			 const struct sockaddr *dst_addr)
-{
-	struct sockaddr_storage zero_sock = {};
-
-	if (src_addr && src_addr->sa_family)
-		return rdma_bind_addr(id, src_addr);
-
-	/*
-	 * When the src_addr is not specified, automatically supply an any addr
-	 */
-	zero_sock.ss_family = dst_addr->sa_family;
-	if (IS_ENABLED(CONFIG_IPV6) && dst_addr->sa_family == AF_INET6) {
-		struct sockaddr_in6 *src_addr6 =
-			(struct sockaddr_in6 *)&zero_sock;
-		struct sockaddr_in6 *dst_addr6 =
-			(struct sockaddr_in6 *)dst_addr;
-
-		src_addr6->sin6_scope_id = dst_addr6->sin6_scope_id;
-		if (ipv6_addr_type(&dst_addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL)
-			id->route.addr.dev_addr.bound_dev_if =
-				dst_addr6->sin6_scope_id;
-	} else if (dst_addr->sa_family == AF_IB) {
-		((struct sockaddr_ib *)&zero_sock)->sib_pkey =
-			((struct sockaddr_ib *)dst_addr)->sib_pkey;
-	}
-	return rdma_bind_addr(id, (struct sockaddr *)&zero_sock);
-}
-
-/*
- * If required, resolve the source address for bind and leave the id_priv in
- * state RDMA_CM_ADDR_BOUND. This oddly uses the state to determine the prior
- * calls made by ULP, a previously bound ID will not be re-bound and src_addr is
- * ignored.
- */
-static int resolve_prepare_src(struct rdma_id_private *id_priv,
-			       struct sockaddr *src_addr,
-			       const struct sockaddr *dst_addr)
-{
-	int ret;
-
-	memcpy(cma_dst_addr(id_priv), dst_addr, rdma_addr_size(dst_addr));
-	if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY)) {
-		/* For a well behaved ULP state will be RDMA_CM_IDLE */
-		ret = cma_bind_addr(&id_priv->id, src_addr, dst_addr);
-		if (ret)
-			goto err_dst;
-		if (WARN_ON(!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND,
-					   RDMA_CM_ADDR_QUERY))) {
-			ret = -EINVAL;
-			goto err_dst;
-		}
-	}
-
-	if (cma_family(id_priv) != dst_addr->sa_family) {
-		ret = -EINVAL;
-		goto err_state;
-	}
-	return 0;
-
-err_state:
-	cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND);
-err_dst:
-	memset(cma_dst_addr(id_priv), 0, rdma_addr_size(dst_addr));
-	return ret;
-}
-
-int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr,
-		      const struct sockaddr *dst_addr, unsigned long timeout_ms)
-{
-	struct rdma_id_private *id_priv =
-		container_of(id, struct rdma_id_private, id);
-	int ret;
-
-	ret = resolve_prepare_src(id_priv, src_addr, dst_addr);
-	if (ret)
-		return ret;
-
-	if (cma_any_addr(dst_addr)) {
-		ret = cma_resolve_loopback(id_priv);
-	} else {
-		if (dst_addr->sa_family == AF_IB) {
-			ret = cma_resolve_ib_addr(id_priv);
-		} else {
-			/*
-			 * The FSM can return back to RDMA_CM_ADDR_BOUND after
-			 * rdma_resolve_ip() is called, eg through the error
-			 * path in addr_handler(). If this happens the existing
-			 * request must be canceled before issuing a new one.
-			 * Since canceling a request is a bit slow and this
-			 * oddball path is rare, keep track once a request has
-			 * been issued. The track turns out to be a permanent
-			 * state since this is the only cancel as it is
-			 * immediately before rdma_resolve_ip().
-			 */
-			if (id_priv->used_resolve_ip)
-				rdma_addr_cancel(&id->route.addr.dev_addr);
-			else
-				id_priv->used_resolve_ip = 1;
-			ret = rdma_resolve_ip(cma_src_addr(id_priv), dst_addr,
-					      &id->route.addr.dev_addr,
-					      timeout_ms, addr_handler,
-					      false, id_priv);
-		}
-	}
-	if (ret)
-		goto err;
-
-	return 0;
-err:
-	cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND);
-	return ret;
-}
-EXPORT_SYMBOL(rdma_resolve_addr);
-
 int rdma_set_reuseaddr(struct rdma_cm_id *id, int reuse)
 {
 	struct rdma_id_private *id_priv;
@@ -4064,27 +3949,26 @@ err:
 }
 EXPORT_SYMBOL(rdma_listen);
 
-int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr)
+static int rdma_bind_addr_dst(struct rdma_id_private *id_priv,
+			      struct sockaddr *addr, const struct sockaddr *daddr)
 {
-	struct rdma_id_private *id_priv;
+	struct sockaddr *id_daddr;
 	int ret;
-	struct sockaddr  *daddr;
 
 	if (addr->sa_family != AF_INET && addr->sa_family != AF_INET6 &&
 	    addr->sa_family != AF_IB)
 		return -EAFNOSUPPORT;
 
-	id_priv = container_of(id, struct rdma_id_private, id);
 	if (!cma_comp_exch(id_priv, RDMA_CM_IDLE, RDMA_CM_ADDR_BOUND))
 		return -EINVAL;
 
-	ret = cma_check_linklocal(&id->route.addr.dev_addr, addr);
+	ret = cma_check_linklocal(&id_priv->id.route.addr.dev_addr, addr);
 	if (ret)
 		goto err1;
 
 	memcpy(cma_src_addr(id_priv), addr, rdma_addr_size(addr));
 	if (!cma_any_addr(addr)) {
-		ret = cma_translate_addr(addr, &id->route.addr.dev_addr);
+		ret = cma_translate_addr(addr, &id_priv->id.route.addr.dev_addr);
 		if (ret)
 			goto err1;
 
@@ -4104,8 +3988,10 @@ int rdma_bind_addr(struct rdma_cm_id *id
 		}
 #endif
 	}
-	daddr = cma_dst_addr(id_priv);
-	daddr->sa_family = addr->sa_family;
+	id_daddr = cma_dst_addr(id_priv);
+	if (daddr != id_daddr)
+		memcpy(id_daddr, daddr, rdma_addr_size(addr));
+	id_daddr->sa_family = addr->sa_family;
 
 	ret = cma_get_port(id_priv);
 	if (ret)
@@ -4121,6 +4007,127 @@ err1:
 	cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_IDLE);
 	return ret;
 }
+
+static int cma_bind_addr(struct rdma_cm_id *id, struct sockaddr *src_addr,
+			 const struct sockaddr *dst_addr)
+{
+	struct rdma_id_private *id_priv =
+		container_of(id, struct rdma_id_private, id);
+	struct sockaddr_storage zero_sock = {};
+
+	if (src_addr && src_addr->sa_family)
+		return rdma_bind_addr_dst(id_priv, src_addr, dst_addr);
+
+	/*
+	 * When the src_addr is not specified, automatically supply an any addr
+	 */
+	zero_sock.ss_family = dst_addr->sa_family;
+	if (IS_ENABLED(CONFIG_IPV6) && dst_addr->sa_family == AF_INET6) {
+		struct sockaddr_in6 *src_addr6 =
+			(struct sockaddr_in6 *)&zero_sock;
+		struct sockaddr_in6 *dst_addr6 =
+			(struct sockaddr_in6 *)dst_addr;
+
+		src_addr6->sin6_scope_id = dst_addr6->sin6_scope_id;
+		if (ipv6_addr_type(&dst_addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL)
+			id->route.addr.dev_addr.bound_dev_if =
+				dst_addr6->sin6_scope_id;
+	} else if (dst_addr->sa_family == AF_IB) {
+		((struct sockaddr_ib *)&zero_sock)->sib_pkey =
+			((struct sockaddr_ib *)dst_addr)->sib_pkey;
+	}
+	return rdma_bind_addr_dst(id_priv, (struct sockaddr *)&zero_sock, dst_addr);
+}
+
+/*
+ * If required, resolve the source address for bind and leave the id_priv in
+ * state RDMA_CM_ADDR_BOUND. This oddly uses the state to determine the prior
+ * calls made by ULP, a previously bound ID will not be re-bound and src_addr is
+ * ignored.
+ */
+static int resolve_prepare_src(struct rdma_id_private *id_priv,
+			       struct sockaddr *src_addr,
+			       const struct sockaddr *dst_addr)
+{
+	int ret;
+
+	if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY)) {
+		/* For a well behaved ULP state will be RDMA_CM_IDLE */
+		ret = cma_bind_addr(&id_priv->id, src_addr, dst_addr);
+		if (ret)
+			return ret;
+		if (WARN_ON(!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND,
+					   RDMA_CM_ADDR_QUERY)))
+			return -EINVAL;
+
+	}
+
+	if (cma_family(id_priv) != dst_addr->sa_family) {
+		ret = -EINVAL;
+		goto err_state;
+	}
+	return 0;
+
+err_state:
+	cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND);
+	return ret;
+}
+
+int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr,
+		      const struct sockaddr *dst_addr, unsigned long timeout_ms)
+{
+	struct rdma_id_private *id_priv =
+		container_of(id, struct rdma_id_private, id);
+	int ret;
+
+	ret = resolve_prepare_src(id_priv, src_addr, dst_addr);
+	if (ret)
+		return ret;
+
+	if (cma_any_addr(dst_addr)) {
+		ret = cma_resolve_loopback(id_priv);
+	} else {
+		if (dst_addr->sa_family == AF_IB) {
+			ret = cma_resolve_ib_addr(id_priv);
+		} else {
+			/*
+			 * The FSM can return back to RDMA_CM_ADDR_BOUND after
+			 * rdma_resolve_ip() is called, eg through the error
+			 * path in addr_handler(). If this happens the existing
+			 * request must be canceled before issuing a new one.
+			 * Since canceling a request is a bit slow and this
+			 * oddball path is rare, keep track once a request has
+			 * been issued. The track turns out to be a permanent
+			 * state since this is the only cancel as it is
+			 * immediately before rdma_resolve_ip().
+			 */
+			if (id_priv->used_resolve_ip)
+				rdma_addr_cancel(&id->route.addr.dev_addr);
+			else
+				id_priv->used_resolve_ip = 1;
+			ret = rdma_resolve_ip(cma_src_addr(id_priv), dst_addr,
+					      &id->route.addr.dev_addr,
+					      timeout_ms, addr_handler,
+					      false, id_priv);
+		}
+	}
+	if (ret)
+		goto err;
+
+	return 0;
+err:
+	cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND);
+	return ret;
+}
+EXPORT_SYMBOL(rdma_resolve_addr);
+
+int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr)
+{
+	struct rdma_id_private *id_priv =
+		container_of(id, struct rdma_id_private, id);
+
+	return rdma_bind_addr_dst(id_priv, addr, cma_dst_addr(id_priv));
+}
 EXPORT_SYMBOL(rdma_bind_addr);
 
 static int cma_format_hdr(void *hdr, struct rdma_id_private *id_priv)
author maintainer
#108 lore raw

PATCH 108/215 RDMA/core: Update CMA destination address on rdma_resolve_addr

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Shiraz Saleem <[email protected]>

commit 0e15863015d97c1ee2cc29d599abcc7fa2dc3e95 upstream.

8d037973d48c ("RDMA/core: Refactor rdma_bind_addr") intoduces as regression on irdma devices on certain tests which uses rdma CM, such as cmtime.

No connections can be established with the MAD QP experiences a fatal error on the active side.

The cma destination address is not updated with the dst_addr when ULP on active side calls rdma_bind_addr followed by rdma_resolve_addr. The id_priv state is 'bound' in resolve_prepare_src and update is skipped.

This leaves the dgid passed into irdma driver to create an Address Handle (AH) for the MAD QP at 0. The create AH descriptor as well as the ARP cache entry is invalid and HW throws an asynchronous events as result.

[ 1207.656888] resolve_prepare_src caller: ucma_resolve_addr+0xff/0x170 [rdma_ucm] daddr=200.0.4.28 id_priv->state=7
[....]
[ 1207.680362] ice 0000:07:00.1 rocep7s0f1: caller: irdma_create_ah+0x3e/0x70 [irdma] ah_id=0 arp_idx=0 dest_ip=0.0.0.0
destMAC=00:00:64:ca:b7:52 ipvalid=1 raw=0000:0000:0000:0000:0000:ffff:0000:0000
[ 1207.682077] ice 0000:07:00.1 rocep7s0f1: abnormal ae_id = 0x401 bool qp=1 qp_id = 1, ae_src=5
[ 1207.691657] infiniband rocep7s0f1: Fatal error (1) on MAD QP (1)

Fix this by updating the CMA destination address when the ULP calls a resolve address with the CM state already bound.

---
 drivers/infiniband/core/cma.c |    2 ++
 1 file changed, 2 insertions(+)
drivers/infiniband/core/cma.c +2 -0
@@ -4060,6 +4060,8 @@ static int resolve_prepare_src(struct rd
 					   RDMA_CM_ADDR_QUERY)))
 			return -EINVAL;
 
+	} else {
+		memcpy(cma_dst_addr(id_priv), dst_addr, rdma_addr_size(dst_addr));
 	}
 
 	if (cma_family(id_priv) != dst_addr->sa_family) {
author maintainer
#109 lore raw

PATCH 109/215 efi: libstub: use EFI_LOADER_CODE region when moving the kernel in memory

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit 9cf42bca30e98a1c6c9e8abf876940a551eaa3d1 upstream.

The EFI spec is not very clear about which permissions are being given when allocating pages of a certain type. However, it is quite obvious that EFI_LOADER_CODE is more likely to permit execution than EFI_LOADER_DATA, which becomes relevant once we permit booting the kernel proper with the firmware's 1:1 mapping still active.

Ostensibly, recent systems such as the Surface Pro X grant executable permissions to EFI_LOADER_CODE regions but not EFI_LOADER_DATA regions.

---
 drivers/firmware/efi/libstub/alignedmem.c  |    5 +++--
 drivers/firmware/efi/libstub/arm64-stub.c  |    6 ++++--
 drivers/firmware/efi/libstub/efistub.h     |    6 ++++--
 drivers/firmware/efi/libstub/mem.c         |    3 ++-
 drivers/firmware/efi/libstub/randomalloc.c |    5 +++--
 5 files changed, 16 insertions(+), 9 deletions(-)
drivers/firmware/efi/libstub/alignedmem.c +3 -2
@@ -22,7 +22,8 @@
  * Return:	status code
  */
 efi_status_t efi_allocate_pages_aligned(unsigned long size, unsigned long *addr,
-					unsigned long max, unsigned long align)
+					unsigned long max, unsigned long align,
+					int memory_type)
 {
 	efi_physical_addr_t alloc_addr;
 	efi_status_t status;
@@ -36,7 +37,7 @@ efi_status_t efi_allocate_pages_aligned(
 	slack = align / EFI_PAGE_SIZE - 1;
 
 	status = efi_bs_call(allocate_pages, EFI_ALLOCATE_MAX_ADDRESS,
-			     EFI_LOADER_DATA, size / EFI_PAGE_SIZE + slack,
+			     memory_type, size / EFI_PAGE_SIZE + slack,
 			     &alloc_addr);
 	if (status != EFI_SUCCESS)
 		return status;
drivers/firmware/efi/libstub/arm64-stub.c +4 -2
@@ -180,7 +180,8 @@ efi_status_t handle_kernel_image(unsigne
 		 * locate the kernel at a randomized offset in physical memory.
 		 */
 		status = efi_random_alloc(*reserve_size, min_kimg_align,
-					  reserve_addr, phys_seed);
+					  reserve_addr, phys_seed,
+					  EFI_LOADER_CODE);
 		if (status != EFI_SUCCESS)
 			efi_warn("efi_random_alloc() failed: 0x%lx\n", status);
 	} else {
@@ -201,7 +202,8 @@ efi_status_t handle_kernel_image(unsigne
 		}
 
 		status = efi_allocate_pages_aligned(*reserve_size, reserve_addr,
-						    ULONG_MAX, min_kimg_align);
+						    ULONG_MAX, min_kimg_align,
+						    EFI_LOADER_CODE);
 
 		if (status != EFI_SUCCESS) {
 			efi_err("Failed to relocate kernel\n");
drivers/firmware/efi/libstub/efistub.h +4 -2
@@ -880,7 +880,8 @@ void efi_get_virtmap(efi_memory_desc_t *
 efi_status_t efi_get_random_bytes(unsigned long size, u8 *out);
 
 efi_status_t efi_random_alloc(unsigned long size, unsigned long align,
-			      unsigned long *addr, unsigned long random_seed);
+			      unsigned long *addr, unsigned long random_seed,
+			      int memory_type);
 
 efi_status_t efi_random_get_seed(void);
 
@@ -907,7 +908,8 @@ efi_status_t efi_allocate_pages(unsigned
 				unsigned long max);
 
 efi_status_t efi_allocate_pages_aligned(unsigned long size, unsigned long *addr,
-					unsigned long max, unsigned long align);
+					unsigned long max, unsigned long align,
+					int memory_type);
 
 efi_status_t efi_low_alloc_above(unsigned long size, unsigned long align,
 				 unsigned long *addr, unsigned long min);
drivers/firmware/efi/libstub/mem.c +2 -1
@@ -91,7 +91,8 @@ efi_status_t efi_allocate_pages(unsigned
 
 	if (EFI_ALLOC_ALIGN > EFI_PAGE_SIZE)
 		return efi_allocate_pages_aligned(size, addr, max,
-						  EFI_ALLOC_ALIGN);
+						  EFI_ALLOC_ALIGN,
+						  EFI_LOADER_DATA);
 
 	alloc_addr = ALIGN_DOWN(max + 1, EFI_ALLOC_ALIGN) - 1;
 	status = efi_bs_call(allocate_pages, EFI_ALLOCATE_MAX_ADDRESS,
drivers/firmware/efi/libstub/randomalloc.c +3 -2
@@ -53,7 +53,8 @@ static unsigned long get_entry_num_slots
 efi_status_t efi_random_alloc(unsigned long size,
 			      unsigned long align,
 			      unsigned long *addr,
-			      unsigned long random_seed)
+			      unsigned long random_seed,
+			      int memory_type)
 {
 	unsigned long total_slots = 0, target_slot;
 	unsigned long total_mirrored_slots = 0;
@@ -118,7 +119,7 @@ efi_status_t efi_random_alloc(unsigned l
 		pages = size / EFI_PAGE_SIZE;
 
 		status = efi_bs_call(allocate_pages, EFI_ALLOCATE_ADDRESS,
-				     EFI_LOADER_DATA, pages, &target);
+				     memory_type, pages, &target);
 		if (status == EFI_SUCCESS)
 			*addr = target;
 		break;
author maintainer
#110 lore raw

PATCH 110/215 x86/boot/compressed: Rename efi_thunk_64.S to efi-mixed.S

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit cb8bda8ad4438b4bcfcf89697fc84803fb210017 upstream.

In preparation for moving the mixed mode specific code out of head_64.S, rename the existing file to clarify that it contains more than just the mixed mode thunk.

While at it, clean up the Makefile rules that add it to the build.

---
 arch/x86/boot/compressed/Makefile                        | 6 +++---
 arch/x86/boot/compressed/{efi_thunk_64.S => efi_mixed.S} | 0
 arch/x86/boot/compressed/Makefile       |    6 
 arch/x86/boot/compressed/efi_mixed.S    |  195 ++++++++++++++++++++++++++++++++
 arch/x86/boot/compressed/efi_thunk_64.S |  195 --------------------------------
 3 files changed, 198 insertions(+), 198 deletions(-)
 rename arch/x86/boot/compressed/{efi_thunk_64.S => efi_mixed.S} (100%)
arch/x86/boot/compressed/Makefile +3 -3
@@ -108,11 +108,11 @@ endif
 vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o
 vmlinux-objs-$(CONFIG_INTEL_TDX_GUEST) += $(obj)/tdx.o $(obj)/tdcall.o
 
-vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o
 vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o
-efi-obj-$(CONFIG_EFI_STUB) = $(objtree)/drivers/firmware/efi/libstub/lib.a
+vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_mixed.o
+vmlinux-objs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
 
-$(obj)/vmlinux: $(vmlinux-objs-y) $(efi-obj-y) FORCE
+$(obj)/vmlinux: $(vmlinux-objs-y) FORCE
 	$(call if_changed,ld)
 
 OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S
arch/x86/boot/compressed/efi_mixed.S new file +195 -0

195 lines not on this page · raw message

arch/x86/boot/compressed/efi_thunk_64.S deleted +0 -195

195 lines not on this page · raw message

author maintainer
#111 lore raw

PATCH 111/215 x86/boot/compressed: Move 32-bit entrypoint code into .text section

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit e2ab9eab324cdf240de89741e4a1aa79919f0196 upstream.

Move the code that stores the arguments passed to the EFI entrypoint into the .text section, so that it can be moved into a separate compilation unit in a subsequent patch.

---
 arch/x86/boot/compressed/head_64.S |   48 ++++++++++++++++++++++++++-----------
 1 file changed, 34 insertions(+), 14 deletions(-)
arch/x86/boot/compressed/head_64.S +34 -14
@@ -303,24 +303,41 @@ SYM_FUNC_START(efi32_stub_entry)
 	popl	%ecx
 	popl	%edx
 	popl	%esi
+	jmp	efi32_entry
+SYM_FUNC_END(efi32_stub_entry)
 
+	.text
+/*
+ * This is the common EFI stub entry point for mixed mode.
+ *
+ * Arguments:	%ecx	image handle
+ * 		%edx	EFI system table pointer
+ *		%esi	struct bootparams pointer (or NULL when not using
+ *			the EFI handover protocol)
+ *
+ * Since this is the point of no return for ordinary execution, no registers
+ * are considered live except for the function parameters. [Note that the EFI
+ * stub may still exit and return to the firmware using the Exit() EFI boot
+ * service.]
+ */
+SYM_FUNC_START_LOCAL(efi32_entry)
 	call	1f
-1:	pop	%ebp
-	subl	$ rva(1b), %ebp
-
-	movl	%esi, rva(efi32_boot_args+8)(%ebp)
-SYM_INNER_LABEL(efi32_pe_stub_entry, SYM_L_LOCAL)
-	movl	%ecx, rva(efi32_boot_args)(%ebp)
-	movl	%edx, rva(efi32_boot_args+4)(%ebp)
-	movb	$0, rva(efi_is64)(%ebp)
+1:	pop	%ebx
 
 	/* Save firmware GDTR and code/data selectors */
-	sgdtl	rva(efi32_boot_gdt)(%ebp)
-	movw	%cs, rva(efi32_boot_cs)(%ebp)
-	movw	%ds, rva(efi32_boot_ds)(%ebp)
+	sgdtl	(efi32_boot_gdt - 1b)(%ebx)
+	movw	%cs, (efi32_boot_cs - 1b)(%ebx)
+	movw	%ds, (efi32_boot_ds - 1b)(%ebx)
 
 	/* Store firmware IDT descriptor */
-	sidtl	rva(efi32_boot_idt)(%ebp)
+	sidtl	(efi32_boot_idt - 1b)(%ebx)
+
+	/* Store boot arguments */
+	leal	(efi32_boot_args - 1b)(%ebx), %ebx
+	movl	%ecx, 0(%ebx)
+	movl	%edx, 4(%ebx)
+	movl	%esi, 8(%ebx)
+	movb	$0x0, 12(%ebx)          // efi_is64
 
 	/* Disable paging */
 	movl	%cr0, %eax
@@ -328,7 +345,8 @@ SYM_INNER_LABEL(efi32_pe_stub_entry, SYM
 	movl	%eax, %cr0
 
 	jmp	startup_32
-SYM_FUNC_END(efi32_stub_entry)
+SYM_FUNC_END(efi32_entry)
+	__HEAD
 #endif
 
 	.code64
@@ -847,7 +865,9 @@ SYM_FUNC_START(efi32_pe_entry)
 	 */
 	subl	%esi, %ebx
 	movl	%ebx, rva(image_offset)(%ebp)	// save image_offset
-	jmp	efi32_pe_stub_entry
+	xorl	%esi, %esi
+	jmp	efi32_entry			// pass %ecx, %edx, %esi
+						// no other registers remain live
 
 2:	popl	%edi				// restore callee-save registers
 	popl	%ebx
author maintainer
#112 lore raw

PATCH 112/215 x86/boot/compressed: Move bootargs parsing out of 32-bit startup code

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit 5c3a85f35b583259cf5ca0344cd79c8899ba1bb7 upstream.

Move the logic that chooses between the different EFI entrypoints out of the 32-bit boot path, and into a 64-bit helper that can perform the same task much more cleanly. While at it, document the mixed mode boot flow in a code comment.

---
 arch/x86/boot/compressed/efi_mixed.S |   43 +++++++++++++++++++++++++++++++++++
 arch/x86/boot/compressed/head_64.S   |   24 +++----------------
 2 files changed, 47 insertions(+), 20 deletions(-)
arch/x86/boot/compressed/efi_mixed.S +43 -0
@@ -22,6 +22,49 @@
 
 	.code64
 	.text
+/*
+ * When booting in 64-bit mode on 32-bit EFI firmware, startup_64_mixed_mode()
+ * is the first thing that runs after switching to long mode. Depending on
+ * whether the EFI handover protocol or the compat entry point was used to
+ * enter the kernel, it will either branch to the 64-bit EFI handover
+ * entrypoint at offset 0x390 in the image, or to the 64-bit EFI PE/COFF
+ * entrypoint efi_pe_entry(). In the former case, the bootloader must provide a
+ * struct bootparams pointer as the third argument, so the presence of such a
+ * pointer is used to disambiguate.
+ *
+ *                                                             +--------------+
+ *  +------------------+     +------------+            +------>| efi_pe_entry |
+ *  | efi32_pe_entry   |---->|            |            |       +-----------+--+
+ *  +------------------+     |            |     +------+----------------+  |
+ *                           | startup_32 |---->| startup_64_mixed_mode |  |
+ *  +------------------+     |            |     +------+----------------+  V
+ *  | efi32_stub_entry |---->|            |            |     +------------------+
+ *  +------------------+     +------------+            +---->| efi64_stub_entry |
+ *                                                           +-------------+----+
+ *                           +------------+     +----------+               |
+ *                           | startup_64 |<----| efi_main |<--------------+
+ *                           +------------+     +----------+
+ */
+SYM_FUNC_START(startup_64_mixed_mode)
+	lea	efi32_boot_args(%rip), %rdx
+	mov	0(%rdx), %edi
+	mov	4(%rdx), %esi
+	mov	8(%rdx), %edx		// saved bootparams pointer
+	test	%edx, %edx
+	jnz	efi64_stub_entry
+	/*
+	 * efi_pe_entry uses MS calling convention, which requires 32 bytes of
+	 * shadow space on the stack even if all arguments are passed in
+	 * registers. We also need an additional 8 bytes for the space that
+	 * would be occupied by the return address, and this also results in
+	 * the correct stack alignment for entry.
+	 */
+	sub	$40, %rsp
+	mov	%rdi, %rcx		// MS calling convention
+	mov	%rsi, %rdx
+	jmp	efi_pe_entry
+SYM_FUNC_END(startup_64_mixed_mode)
+
 SYM_FUNC_START(__efi64_thunk)
 	push	%rbp
 	push	%rbx
arch/x86/boot/compressed/head_64.S +4 -20
@@ -261,25 +261,9 @@ SYM_FUNC_START(startup_32)
 	 */
 	leal	rva(startup_64)(%ebp), %eax
 #ifdef CONFIG_EFI_MIXED
-	movl	rva(efi32_boot_args)(%ebp), %edi
-	testl	%edi, %edi
-	jz	1f
-	leal	rva(efi64_stub_entry)(%ebp), %eax
-	movl	rva(efi32_boot_args+4)(%ebp), %esi
-	movl	rva(efi32_boot_args+8)(%ebp), %edx	// saved bootparams pointer
-	testl	%edx, %edx
-	jnz	1f
-	/*
-	 * efi_pe_entry uses MS calling convention, which requires 32 bytes of
-	 * shadow space on the stack even if all arguments are passed in
-	 * registers. We also need an additional 8 bytes for the space that
-	 * would be occupied by the return address, and this also results in
-	 * the correct stack alignment for entry.
-	 */
-	subl	$40, %esp
-	leal	rva(efi_pe_entry)(%ebp), %eax
-	movl	%edi, %ecx			// MS calling convention
-	movl	%esi, %edx
+	cmpb	$1, rva(efi_is64)(%ebp)
+	je	1f
+	leal	rva(startup_64_mixed_mode)(%ebp), %eax
 1:
 #endif
 	/* Check if the C-bit position is correct when SEV is active */
@@ -795,7 +779,7 @@ SYM_DATA_END_LABEL(boot32_idt, SYM_L_GLO
 SYM_DATA(image_offset, .long 0)
 #endif
 #ifdef CONFIG_EFI_MIXED
-SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0, 0)
+SYM_DATA(efi32_boot_args, .long 0, 0, 0)
 SYM_DATA(efi_is64, .byte 1)
 
 #define ST32_boottime		60 // offsetof(efi_system_table_32_t, boottime)
author maintainer
#95 lore raw

PATCH 95/215 x86/e820: Dont reserve SETUP_RNG_SEED in e820

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jiri Bohac <[email protected]>

commit 7fd817c906503b6813ea3b41f5fdf4192449a707 upstream.

SETUP_RNG_SEED in setup_data is supplied by kexec and should not be reserved in the e820 map.

Doing so reserves 16 bytes of RAM when booting with kexec. (16 bytes because data->len is zeroed by parse_setup_data so only sizeof(setup_data) is reserved.)

When kexec is used repeatedly, each boot adds two entries in the kexec-provided e820 map as the 16-byte range splits a larger range of usable memory. Eventually all of the 128 available entries get used up. The next split will result in losing usable memory as the new entries cannot be added to the e820 map.

---
 arch/x86/kernel/e820.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)
arch/x86/kernel/e820.c +5 -3
index fb8cf953380d..b66f540de054 100644
@@ -1017,10 +1017,12 @@ void __init e820__reserve_setup_data(void)
 		e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
 
 		/*
-		 * SETUP_EFI and SETUP_IMA are supplied by kexec and do not need
-		 * to be reserved.
+		 * SETUP_EFI, SETUP_IMA and SETUP_RNG_SEED are supplied by
+		 * kexec and do not need to be reserved.
 		 */
-		if (data->type != SETUP_EFI && data->type != SETUP_IMA)
+		if (data->type != SETUP_EFI &&
+		    data->type != SETUP_IMA &&
+		    data->type != SETUP_RNG_SEED)
 			e820__range_update_kexec(pa_data,
 						 sizeof(*data) + data->len,
 						 E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
Signature · 1 line
2.44.0
author maintainer
#113 lore raw

PATCH 113/215 x86/boot/compressed: Move efi32_pe_entry into .text section

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit 91592b5c0c2f076ff9d8cc0c14aa563448ac9fc4 upstream.

Move efi32_pe_entry() into the .text section, so that it can be moved out of head_64.S and into a separate compilation unit in a subsequent patch.

---
 arch/x86/boot/compressed/head_64.S |   11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)
arch/x86/boot/compressed/head_64.S +5 -6
@@ -786,7 +786,7 @@ SYM_DATA(efi_is64, .byte 1)
 #define BS32_handle_protocol	88 // offsetof(efi_boot_services_32_t, handle_protocol)
 #define LI32_image_base		32 // offsetof(efi_loaded_image_32_t, image_base)
 
-	__HEAD
+	.text
 	.code32
 SYM_FUNC_START(efi32_pe_entry)
 /*
@@ -808,12 +808,11 @@ SYM_FUNC_START(efi32_pe_entry)
 
 	call	1f
 1:	pop	%ebx
-	subl	$ rva(1b), %ebx
 
 	/* Get the loaded image protocol pointer from the image handle */
 	leal	-4(%ebp), %eax
 	pushl	%eax				// &loaded_image
-	leal	rva(loaded_image_proto)(%ebx), %eax
+	leal	(loaded_image_proto - 1b)(%ebx), %eax
 	pushl	%eax				// pass the GUID address
 	pushl	8(%ebp)				// pass the image handle
 
@@ -842,13 +841,13 @@ SYM_FUNC_START(efi32_pe_entry)
 	movl	12(%ebp), %edx			// sys_table
 	movl	-4(%ebp), %esi			// loaded_image
 	movl	LI32_image_base(%esi), %esi	// loaded_image->image_base
-	movl	%ebx, %ebp			// startup_32 for efi32_pe_stub_entry
+	leal	(startup_32 - 1b)(%ebx), %ebp	// runtime address of startup_32
 	/*
 	 * We need to set the image_offset variable here since startup_32() will
 	 * use it before we get to the 64-bit efi_pe_entry() in C code.
 	 */
-	subl	%esi, %ebx
-	movl	%ebx, rva(image_offset)(%ebp)	// save image_offset
+	subl	%esi, %ebp			// calculate image_offset
+	movl	%ebp, (image_offset - 1b)(%ebx)	// save image_offset
 	xorl	%esi, %esi
 	jmp	efi32_entry			// pass %ecx, %edx, %esi
 						// no other registers remain live
author maintainer
#114 lore raw

PATCH 114/215 x86/boot/compressed: Move efi32_entry out of head_64.S

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit 73a6dec80e2acedaef3ca603d4b5799049f6e9f8 upstream.

Move the efi32_entry() routine out of head_64.S and into efi-mixed.S, which reduces clutter in the complicated startup routines. It also permits linkage of some symbols used by code to be made local.

---
 arch/x86/boot/compressed/efi_mixed.S |   57 ++++++++++++++++++++++++++++-------
 arch/x86/boot/compressed/head_64.S   |   45 ---------------------------
 2 files changed, 47 insertions(+), 55 deletions(-)
arch/x86/boot/compressed/efi_mixed.S +47 -10
@@ -105,7 +105,7 @@ SYM_FUNC_START(__efi64_thunk)
 	/*
 	 * Switch to IDT and GDT with 32-bit segments. This is the firmware GDT
 	 * and IDT that was installed when the kernel started executing. The
-	 * pointers were saved at the EFI stub entry point in head_64.S.
+	 * pointers were saved by the efi32_entry() routine below.
 	 *
 	 * Pass the saved DS selector to the 32-bit code, and use far return to
 	 * restore the saved CS selector.
@@ -217,22 +217,59 @@ SYM_FUNC_START_LOCAL(efi_enter32)
 	lret
 SYM_FUNC_END(efi_enter32)
 
+/*
+ * This is the common EFI stub entry point for mixed mode.
+ *
+ * Arguments:	%ecx	image handle
+ * 		%edx	EFI system table pointer
+ *		%esi	struct bootparams pointer (or NULL when not using
+ *			the EFI handover protocol)
+ *
+ * Since this is the point of no return for ordinary execution, no registers
+ * are considered live except for the function parameters. [Note that the EFI
+ * stub may still exit and return to the firmware using the Exit() EFI boot
+ * service.]
+ */
+SYM_FUNC_START(efi32_entry)
+	call	1f
+1:	pop	%ebx
+
+	/* Save firmware GDTR and code/data selectors */
+	sgdtl	(efi32_boot_gdt - 1b)(%ebx)
+	movw	%cs, (efi32_boot_cs - 1b)(%ebx)
+	movw	%ds, (efi32_boot_ds - 1b)(%ebx)
+
+	/* Store firmware IDT descriptor */
+	sidtl	(efi32_boot_idt - 1b)(%ebx)
+
+	/* Store boot arguments */
+	leal	(efi32_boot_args - 1b)(%ebx), %ebx
+	movl	%ecx, 0(%ebx)
+	movl	%edx, 4(%ebx)
+	movl	%esi, 8(%ebx)
+	movb	$0x0, 12(%ebx)          // efi_is64
+
+	/* Disable paging */
+	movl	%cr0, %eax
+	btrl	$X86_CR0_PG_BIT, %eax
+	movl	%eax, %cr0
+
+	jmp	startup_32
+SYM_FUNC_END(efi32_entry)
+
 	.data
 	.balign	8
-SYM_DATA_START(efi32_boot_gdt)
+SYM_DATA_START_LOCAL(efi32_boot_gdt)
 	.word	0
 	.quad	0
 SYM_DATA_END(efi32_boot_gdt)
 
-SYM_DATA_START(efi32_boot_idt)
+SYM_DATA_START_LOCAL(efi32_boot_idt)
 	.word	0
 	.quad	0
 SYM_DATA_END(efi32_boot_idt)
 
-SYM_DATA_START(efi32_boot_cs)
-	.word	0
-SYM_DATA_END(efi32_boot_cs)
-
-SYM_DATA_START(efi32_boot_ds)
-	.word	0
-SYM_DATA_END(efi32_boot_ds)
+SYM_DATA_LOCAL(efi32_boot_cs, .word 0)
+SYM_DATA_LOCAL(efi32_boot_ds, .word 0)
+SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0, 0)
+SYM_DATA(efi_is64, .byte 1)
arch/x86/boot/compressed/head_64.S +0 -45

57 lines not on this page · raw message

author maintainer
#115 lore raw

PATCH 115/215 x86/boot/compressed: Move efi32_pe_entry() out of head_64.S

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit 7f22ca396778fea9332d83ec2359dbe8396e9a06 upstream.

Move the implementation of efi32_pe_entry() into efi-mixed.S, which is a more suitable location that only gets built if EFI mixed mode is actually enabled.

---
 arch/x86/boot/compressed/efi_mixed.S |   82 ++++++++++++++++++++++++++++++++
 arch/x86/boot/compressed/head_64.S   |   87 -----------------------------------
 2 files changed, 83 insertions(+), 86 deletions(-)
arch/x86/boot/compressed/efi_mixed.S +82 -0
@@ -257,6 +257,88 @@ SYM_FUNC_START(efi32_entry)
 	jmp	startup_32
 SYM_FUNC_END(efi32_entry)
 
+#define ST32_boottime		60 // offsetof(efi_system_table_32_t, boottime)
+#define BS32_handle_protocol	88 // offsetof(efi_boot_services_32_t, handle_protocol)
+#define LI32_image_base		32 // offsetof(efi_loaded_image_32_t, image_base)
+
+/*
+ * efi_status_t efi32_pe_entry(efi_handle_t image_handle,
+ *			       efi_system_table_32_t *sys_table)
+ */
+SYM_FUNC_START(efi32_pe_entry)
+	pushl	%ebp
+	movl	%esp, %ebp
+	pushl	%eax				// dummy push to allocate loaded_image
+
+	pushl	%ebx				// save callee-save registers
+	pushl	%edi
+
+	call	verify_cpu			// check for long mode support
+	testl	%eax, %eax
+	movl	$0x80000003, %eax		// EFI_UNSUPPORTED
+	jnz	2f
+
+	call	1f
+1:	pop	%ebx
+
+	/* Get the loaded image protocol pointer from the image handle */
+	leal	-4(%ebp), %eax
+	pushl	%eax				// &loaded_image
+	leal	(loaded_image_proto - 1b)(%ebx), %eax
+	pushl	%eax				// pass the GUID address
+	pushl	8(%ebp)				// pass the image handle
+
+	/*
+	 * Note the alignment of the stack frame.
+	 *   sys_table
+	 *   handle             <-- 16-byte aligned on entry by ABI
+	 *   return address
+	 *   frame pointer
+	 *   loaded_image       <-- local variable
+	 *   saved %ebx		<-- 16-byte aligned here
+	 *   saved %edi
+	 *   &loaded_image
+	 *   &loaded_image_proto
+	 *   handle             <-- 16-byte aligned for call to handle_protocol
+	 */
+
+	movl	12(%ebp), %eax			// sys_table
+	movl	ST32_boottime(%eax), %eax	// sys_table->boottime
+	call	*BS32_handle_protocol(%eax)	// sys_table->boottime->handle_protocol
+	addl	$12, %esp			// restore argument space
+	testl	%eax, %eax
+	jnz	2f
+
+	movl	8(%ebp), %ecx			// image_handle
+	movl	12(%ebp), %edx			// sys_table
+	movl	-4(%ebp), %esi			// loaded_image
+	movl	LI32_image_base(%esi), %esi	// loaded_image->image_base
+	leal	(startup_32 - 1b)(%ebx), %ebp	// runtime address of startup_32
+	/*
+	 * We need to set the image_offset variable here since startup_32() will
+	 * use it before we get to the 64-bit efi_pe_entry() in C code.
+	 */
+	subl	%esi, %ebp			// calculate image_offset
+	movl	%ebp, (image_offset - 1b)(%ebx)	// save image_offset
+	xorl	%esi, %esi
+	jmp	efi32_entry			// pass %ecx, %edx, %esi
+						// no other registers remain live
+
+2:	popl	%edi				// restore callee-save registers
+	popl	%ebx
+	leave
+	RET
+SYM_FUNC_END(efi32_pe_entry)
+
+	.section ".rodata"
+	/* EFI loaded image protocol GUID */
+	.balign 4
+SYM_DATA_START_LOCAL(loaded_image_proto)
+	.long	0x5b1b31a1
+	.word	0x9562, 0x11d2
+	.byte	0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b
+SYM_DATA_END(loaded_image_proto)
+
 	.data
 	.balign	8
 SYM_DATA_START_LOCAL(efi32_boot_gdt)
arch/x86/boot/compressed/head_64.S +1 -86

99 lines not on this page · raw message

author maintainer
#116 lore raw

PATCH 116/215 x86/boot/compressed, efi: Merge multiple definitions of image_offset into one

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit 4b52016247aeaa55ca3e3bc2e03cd91114c145c2 upstream.

There is no need for head_32.S and head_64.S both declaring a copy of the global 'image_offset' variable, so drop those and make the extern C declaration the definition.

When image_offset is moved to the .c file, it needs to be placed particularly in the .data section because it lands by default in the .bss section which is cleared too late, in .Lrelocated, before the first access to it and thus garbage gets read, leading to SEV guests exploding in early boot.

This happens only when the SEV guest kernel is loaded through grub. If supplied with qemu's -kernel command line option, that memory is always cleared upfront by qemu and all is fine there.

[ bp: Expand commit message with SEV aspect. ]

---
 arch/x86/boot/compressed/head_32.S      |    4 ----
 arch/x86/boot/compressed/head_64.S      |    4 ----
 drivers/firmware/efi/libstub/x86-stub.c |    2 +-
 3 files changed, 1 insertion(+), 9 deletions(-)
arch/x86/boot/compressed/head_32.S +0 -4
@@ -208,10 +208,6 @@ SYM_DATA_START_LOCAL(gdt)
 	.quad	0x00cf92000000ffff	/* __KERNEL_DS */
 SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end)
 
-#ifdef CONFIG_EFI_STUB
-SYM_DATA(image_offset, .long 0)
-#endif
-
 /*
  * Stack and heap for uncompression
  */
arch/x86/boot/compressed/head_64.S +0 -4
@@ -734,10 +734,6 @@ SYM_DATA_START(boot32_idt)
 SYM_DATA_END_LABEL(boot32_idt, SYM_L_GLOBAL, boot32_idt_end)
 #endif
 
-#ifdef CONFIG_EFI_STUB
-SYM_DATA(image_offset, .long 0)
-#endif
-
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 	__HEAD
 	.code32
drivers/firmware/efi/libstub/x86-stub.c +1 -1
@@ -23,7 +23,7 @@
 
 const efi_system_table_t *efi_system_table;
 const efi_dxe_services_table_t *efi_dxe_table;
-extern u32 image_offset;
+u32 image_offset __section(".data");
 static efi_loaded_image_t *image = NULL;
 
 static efi_status_t
author maintainer
#117 lore raw

PATCH 117/215 x86/boot/compressed: Simplify IDT/GDT preserve/restore in the EFI thunk

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit 630f337f0c4fd80390e8600adcab31550aea33df upstream.

Tweak the asm and remove some redundant instructions. While at it, fix the associated comment for style and correctness.

---
 arch/x86/boot/compressed/efi_mixed.S |   20 +++++++-------------
 1 file changed, 7 insertions(+), 13 deletions(-)
arch/x86/boot/compressed/efi_mixed.S +7 -13
@@ -96,24 +96,20 @@ SYM_FUNC_START(__efi64_thunk)
 
 	leaq	0x20(%rsp), %rbx
 	sgdt	(%rbx)
-
-	addq	$16, %rbx
-	sidt	(%rbx)
+	sidt	16(%rbx)
 
 	leaq	1f(%rip), %rbp
 
 	/*
-	 * Switch to IDT and GDT with 32-bit segments. This is the firmware GDT
-	 * and IDT that was installed when the kernel started executing. The
-	 * pointers were saved by the efi32_entry() routine below.
+	 * Switch to IDT and GDT with 32-bit segments. These are the firmware
+	 * GDT and IDT that were installed when the kernel started executing.
+	 * The pointers were saved by the efi32_entry() routine below.
 	 *
 	 * Pass the saved DS selector to the 32-bit code, and use far return to
 	 * restore the saved CS selector.
 	 */
-	leaq	efi32_boot_idt(%rip), %rax
-	lidt	(%rax)
-	leaq	efi32_boot_gdt(%rip), %rax
-	lgdt	(%rax)
+	lidt	efi32_boot_idt(%rip)
+	lgdt	efi32_boot_gdt(%rip)
 
 	movzwl	efi32_boot_ds(%rip), %edx
 	movzwq	efi32_boot_cs(%rip), %rax
@@ -187,9 +183,7 @@ SYM_FUNC_START_LOCAL(efi_enter32)
 	 */
 	cli
 
-	lidtl	(%ebx)
-	subl	$16, %ebx
-
+	lidtl	16(%ebx)
 	lgdtl	(%ebx)
 
 	movl	%cr4, %eax
author maintainer
#118 lore raw

PATCH 118/215 x86/boot/compressed: Avoid touching ECX in startup32_set_idt_entry()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit 6aac80a8da46d70f2ae7ff97c9f45a15c7c9b3ef upstream.

Avoid touching register %ecx in startup32_set_idt_entry(), by folding the MOV, SHL and ORL instructions into a single ORL which no longer requires a temp register.

This permits ECX to be used as a function argument in a subsequent patch.

---
 arch/x86/boot/compressed/head_64.S |    8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)
arch/x86/boot/compressed/head_64.S +2 -6
@@ -749,7 +749,6 @@ SYM_DATA_END_LABEL(boot32_idt, SYM_L_GLO
  */
 SYM_FUNC_START(startup32_set_idt_entry)
 	push    %ebx
-	push    %ecx
 
 	/* IDT entry address to %ebx */
 	leal    rva(boot32_idt)(%ebp), %ebx
@@ -758,10 +757,8 @@ SYM_FUNC_START(startup32_set_idt_entry)
 
 	/* Build IDT entry, lower 4 bytes */
 	movl    %eax, %edx
-	andl    $0x0000ffff, %edx	# Target code segment offset [15:0]
-	movl    $__KERNEL32_CS, %ecx	# Target code segment selector
-	shl     $16, %ecx
-	orl     %ecx, %edx
+	andl    $0x0000ffff, %edx		# Target code segment offset [15:0]
+	orl	$(__KERNEL32_CS << 16), %edx	# Target code segment selector
 
 	/* Store lower 4 bytes to IDT */
 	movl    %edx, (%ebx)
@@ -774,7 +771,6 @@ SYM_FUNC_START(startup32_set_idt_entry)
 	/* Store upper 4 bytes to IDT */
 	movl    %edx, 4(%ebx)
 
-	pop     %ecx
 	pop     %ebx
 	RET
 SYM_FUNC_END(startup32_set_idt_entry)
author maintainer
#96 lore raw

PATCH 96/215 x86/cpu/intel: Detect TME keyid bits before setting MTRR mask registers

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Paolo Bonzini <[email protected]>

commit 6890cb1ace350b4386c8aee1343dc3b3ddd214da upstream.

MKTME repurposes the high bit of physical address to key id for encryption key and, even though MAXPHYADDR in CPUID[0x80000008] remains the same, the valid bits in the MTRR mask register are based on the reduced number of physical address bits.

detect_tme() in arch/x86/kernel/cpu/intel.c detects TME and subtracts it from the total usable physical bits, but it is called too late. Move the call to early_init_intel() so that it is called in setup_arch(), before MTRRs are setup.

This fixes boot on TDX-enabled systems, which until now only worked with "disable_mtrr_cleanup". Without the patch, the values written to the MTRRs mask registers were 52-bit wide (e.g. 0x000fffff_80000800) and the writes failed; with the patch, the values are 46-bit wide, which matches the reduced MAXPHYADDR that is shown in /proc/cpuinfo.

---
 arch/x86/kernel/cpu/intel.c |  178 ++++++++++++++++++++++----------------------
 1 file changed, 91 insertions(+), 87 deletions(-)
arch/x86/kernel/cpu/intel.c +91 -87
@@ -216,6 +216,90 @@ int intel_cpu_collect_info(struct ucode_
 }
 EXPORT_SYMBOL_GPL(intel_cpu_collect_info);
 
+#define MSR_IA32_TME_ACTIVATE		0x982
+
+/* Helpers to access TME_ACTIVATE MSR */
+#define TME_ACTIVATE_LOCKED(x)		(x & 0x1)
+#define TME_ACTIVATE_ENABLED(x)		(x & 0x2)
+
+#define TME_ACTIVATE_POLICY(x)		((x >> 4) & 0xf)	/* Bits 7:4 */
+#define TME_ACTIVATE_POLICY_AES_XTS_128	0
+
+#define TME_ACTIVATE_KEYID_BITS(x)	((x >> 32) & 0xf)	/* Bits 35:32 */
+
+#define TME_ACTIVATE_CRYPTO_ALGS(x)	((x >> 48) & 0xffff)	/* Bits 63:48 */
+#define TME_ACTIVATE_CRYPTO_AES_XTS_128	1
+
+/* Values for mktme_status (SW only construct) */
+#define MKTME_ENABLED			0
+#define MKTME_DISABLED			1
+#define MKTME_UNINITIALIZED		2
+static int mktme_status = MKTME_UNINITIALIZED;
+
+static void detect_tme_early(struct cpuinfo_x86 *c)
+{
+	u64 tme_activate, tme_policy, tme_crypto_algs;
+	int keyid_bits = 0, nr_keyids = 0;
+	static u64 tme_activate_cpu0 = 0;
+
+	rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate);
+
+	if (mktme_status != MKTME_UNINITIALIZED) {
+		if (tme_activate != tme_activate_cpu0) {
+			/* Broken BIOS? */
+			pr_err_once("x86/tme: configuration is inconsistent between CPUs\n");
+			pr_err_once("x86/tme: MKTME is not usable\n");
+			mktme_status = MKTME_DISABLED;
+
+			/* Proceed. We may need to exclude bits from x86_phys_bits. */
+		}
+	} else {
+		tme_activate_cpu0 = tme_activate;
+	}
+
+	if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) {
+		pr_info_once("x86/tme: not enabled by BIOS\n");
+		mktme_status = MKTME_DISABLED;
+		return;
+	}
+
+	if (mktme_status != MKTME_UNINITIALIZED)
+		goto detect_keyid_bits;
+
+	pr_info("x86/tme: enabled by BIOS\n");
+
+	tme_policy = TME_ACTIVATE_POLICY(tme_activate);
+	if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128)
+		pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy);
+
+	tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate);
+	if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) {
+		pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n",
+				tme_crypto_algs);
+		mktme_status = MKTME_DISABLED;
+	}
+detect_keyid_bits:
+	keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate);
+	nr_keyids = (1UL << keyid_bits) - 1;
+	if (nr_keyids) {
+		pr_info_once("x86/mktme: enabled by BIOS\n");
+		pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids);
+	} else {
+		pr_info_once("x86/mktme: disabled by BIOS\n");
+	}
+
+	if (mktme_status == MKTME_UNINITIALIZED) {
+		/* MKTME is usable */
+		mktme_status = MKTME_ENABLED;
+	}
+
+	/*
+	 * KeyID bits effectively lower the number of physical address
+	 * bits.  Update cpuinfo_x86::x86_phys_bits accordingly.
+	 */
+	c->x86_phys_bits -= keyid_bits;
+}
+
 static void early_init_intel(struct cpuinfo_x86 *c)
 {
 	u64 misc_enable;
@@ -367,6 +451,13 @@ static void early_init_intel(struct cpui
 	 */
 	if (detect_extended_topology_early(c) < 0)
 		detect_ht_early(c);
+
+	/*
+	 * Adjust the number of physical bits early because it affects the
+	 * valid bits of the MTRR mask registers.
+	 */
+	if (cpu_has(c, X86_FEATURE_TME))
+		detect_tme_early(c);
 }
 
 static void bsp_init_intel(struct cpuinfo_x86 *c)
@@ -527,90 +618,6 @@ static void srat_detect_node(struct cpui
 #endif
 }
 
-#define MSR_IA32_TME_ACTIVATE		0x982
-
-/* Helpers to access TME_ACTIVATE MSR */
-#define TME_ACTIVATE_LOCKED(x)		(x & 0x1)
-#define TME_ACTIVATE_ENABLED(x)		(x & 0x2)
-
-#define TME_ACTIVATE_POLICY(x)		((x >> 4) & 0xf)	/* Bits 7:4 */
-#define TME_ACTIVATE_POLICY_AES_XTS_128	0
-
-#define TME_ACTIVATE_KEYID_BITS(x)	((x >> 32) & 0xf)	/* Bits 35:32 */
-
-#define TME_ACTIVATE_CRYPTO_ALGS(x)	((x >> 48) & 0xffff)	/* Bits 63:48 */
-#define TME_ACTIVATE_CRYPTO_AES_XTS_128	1
-
-/* Values for mktme_status (SW only construct) */
-#define MKTME_ENABLED			0
-#define MKTME_DISABLED			1
-#define MKTME_UNINITIALIZED		2
-static int mktme_status = MKTME_UNINITIALIZED;
-
-static void detect_tme(struct cpuinfo_x86 *c)
-{
-	u64 tme_activate, tme_policy, tme_crypto_algs;
-	int keyid_bits = 0, nr_keyids = 0;
-	static u64 tme_activate_cpu0 = 0;
-
-	rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate);
-
-	if (mktme_status != MKTME_UNINITIALIZED) {
-		if (tme_activate != tme_activate_cpu0) {
-			/* Broken BIOS? */
-			pr_err_once("x86/tme: configuration is inconsistent between CPUs\n");
-			pr_err_once("x86/tme: MKTME is not usable\n");
-			mktme_status = MKTME_DISABLED;
-
-			/* Proceed. We may need to exclude bits from x86_phys_bits. */
-		}
-	} else {
-		tme_activate_cpu0 = tme_activate;
-	}
-
-	if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) {
-		pr_info_once("x86/tme: not enabled by BIOS\n");
-		mktme_status = MKTME_DISABLED;
-		return;
-	}
-
-	if (mktme_status != MKTME_UNINITIALIZED)
-		goto detect_keyid_bits;
-
-	pr_info("x86/tme: enabled by BIOS\n");
-
-	tme_policy = TME_ACTIVATE_POLICY(tme_activate);
-	if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128)
-		pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy);
-
-	tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate);
-	if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) {
-		pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n",
-				tme_crypto_algs);
-		mktme_status = MKTME_DISABLED;
-	}
-detect_keyid_bits:
-	keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate);
-	nr_keyids = (1UL << keyid_bits) - 1;
-	if (nr_keyids) {
-		pr_info_once("x86/mktme: enabled by BIOS\n");
-		pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids);
-	} else {
-		pr_info_once("x86/mktme: disabled by BIOS\n");
-	}
-
-	if (mktme_status == MKTME_UNINITIALIZED) {
-		/* MKTME is usable */
-		mktme_status = MKTME_ENABLED;
-	}
-
-	/*
-	 * KeyID bits effectively lower the number of physical address
-	 * bits.  Update cpuinfo_x86::x86_phys_bits accordingly.
-	 */
-	c->x86_phys_bits -= keyid_bits;
-}
-
 static void init_cpuid_fault(struct cpuinfo_x86 *c)
 {
 	u64 msr;
@@ -747,9 +754,6 @@ static void init_intel(struct cpuinfo_x8
 
 	init_ia32_feat_ctl(c);
 
-	if (cpu_has(c, X86_FEATURE_TME))
-		detect_tme(c);
-
 	init_intel_misc_features(c);
 
 	split_lock_init();
author maintainer
#97 lore raw

PATCH 97/215 mptcp: fix data races on local_id

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Paolo Abeni <[email protected]>

commit a7cfe776637004a4c938fde78be4bd608c32c3ef upstream.

The local address id is accessed lockless by the NL PM, add all the required ONCE annotation. There is a caveat: the local id can be initialized late in the subflow life-cycle, and its validity is controlled by the local_id_valid flag.

Remove such flag and encode the validity in the local_id field itself with negative value before initialization. That allows accessing the field consistently with a single read operation.

---

---
 net/mptcp/diag.c         |    2 +-
 net/mptcp/pm_netlink.c   |    6 +++---
 net/mptcp/pm_userspace.c |    2 +-
 net/mptcp/protocol.c     |    2 +-
 net/mptcp/protocol.h     |   13 +++++++++++--
 net/mptcp/subflow.c      |    9 +++++----
 6 files changed, 22 insertions(+), 12 deletions(-)
net/mptcp/diag.c +1 -1
@@ -65,7 +65,7 @@ static int subflow_get_info(struct sock
 			sf->map_data_len) ||
 	    nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_FLAGS, flags) ||
 	    nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_REM, sf->remote_id) ||
-	    nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, sf->local_id)) {
+	    nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, subflow_get_local_id(sf))) {
 		err = -EMSGSIZE;
 		goto nla_failure;
 	}
net/mptcp/pm_netlink.c +3 -3
@@ -799,7 +799,7 @@ static void mptcp_pm_nl_rm_addr_or_subfl
 		mptcp_for_each_subflow_safe(msk, subflow, tmp) {
 			struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 			int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
-			u8 id = subflow->local_id;
+			u8 id = subflow_get_local_id(subflow);
 
 			if (rm_type == MPTCP_MIB_RMADDR && subflow->remote_id != rm_id)
 				continue;
@@ -808,7 +808,7 @@ static void mptcp_pm_nl_rm_addr_or_subfl
 
 			pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u",
 				 rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow",
-				 i, rm_id, subflow->local_id, subflow->remote_id,
+				 i, rm_id, id, subflow->remote_id,
 				 msk->mpc_endpoint_id);
 			spin_unlock_bh(&msk->pm.lock);
 			mptcp_subflow_shutdown(sk, ssk, how);
@@ -2028,7 +2028,7 @@ static int mptcp_event_add_subflow(struc
 	if (WARN_ON_ONCE(!sf))
 		return -EINVAL;
 
-	if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, sf->local_id))
+	if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, subflow_get_local_id(sf)))
 		return -EMSGSIZE;
 
 	if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, sf->remote_id))
net/mptcp/pm_userspace.c +1 -1
@@ -233,7 +233,7 @@ static int mptcp_userspace_pm_remove_id_
 
 	lock_sock(sk);
 	mptcp_for_each_subflow(msk, subflow) {
-		if (subflow->local_id == 0) {
+		if (READ_ONCE(subflow->local_id) == 0) {
 			has_id_0 = true;
 			break;
 		}
net/mptcp/protocol.c +1 -1
@@ -119,7 +119,7 @@ static int __mptcp_socket_create(struct
 	subflow->request_mptcp = 1;
 
 	/* This is the first subflow, always with id 0 */
-	subflow->local_id_valid = 1;
+	WRITE_ONCE(subflow->local_id, 0);
 	mptcp_sock_graft(msk->first, sk->sk_socket);
 
 	return 0;
net/mptcp/protocol.h +11 -2
@@ -475,7 +475,6 @@ struct mptcp_subflow_context {
 		can_ack : 1,        /* only after processing the remote a key */
 		disposable : 1,	    /* ctx can be free at ulp release time */
 		stale : 1,	    /* unable to snd/rcv data, do not use for xmit */
-		local_id_valid : 1, /* local_id is correctly initialized */
 		valid_csum_seen : 1;        /* at least one csum validated */
 	enum mptcp_data_avail data_avail;
 	u32	remote_nonce;
@@ -483,7 +482,7 @@ struct mptcp_subflow_context {
 	u32	local_nonce;
 	u32	remote_token;
 	u8	hmac[MPTCPOPT_HMAC_LEN];
-	u8	local_id;
+	s16	local_id;	    /* if negative not initialized yet */
 	u8	remote_id;
 	u8	reset_seen:1;
 	u8	reset_transient:1;
@@ -529,6 +528,7 @@ mptcp_subflow_ctx_reset(struct mptcp_sub
 {
 	memset(&subflow->reset, 0, sizeof(subflow->reset));
 	subflow->request_mptcp = 1;
+	WRITE_ONCE(subflow->local_id, -1);
 }
 
 static inline u64
@@ -909,6 +909,15 @@ bool mptcp_pm_rm_addr_signal(struct mptc
 int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
 int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
 
+static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflow)
+{
+	int local_id = READ_ONCE(subflow->local_id);
+
+	if (local_id < 0)
+		return 0;
+	return local_id;
+}
+
 void __init mptcp_pm_nl_init(void);
 void mptcp_pm_nl_work(struct mptcp_sock *msk);
 void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
net/mptcp/subflow.c +5 -4
@@ -489,8 +489,8 @@ do_reset:
 
 static void subflow_set_local_id(struct mptcp_subflow_context *subflow, int local_id)
 {
-	subflow->local_id = local_id;
-	subflow->local_id_valid = 1;
+	WARN_ON_ONCE(local_id < 0 || local_id > 255);
+	WRITE_ONCE(subflow->local_id, local_id);
 }
 
 static int subflow_chk_local_id(struct sock *sk)
@@ -499,7 +499,7 @@ static int subflow_chk_local_id(struct s
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
 	int err;
 
-	if (likely(subflow->local_id_valid))
+	if (likely(subflow->local_id >= 0))
 		return 0;
 
 	err = mptcp_pm_get_local_id(msk, (struct sock_common *)sk);
@@ -1630,6 +1630,7 @@ static struct mptcp_subflow_context *sub
 	pr_debug("subflow=%p", ctx);
 
 	ctx->tcp_sock = sk;
+	WRITE_ONCE(ctx->local_id, -1);
 
 	return ctx;
 }
@@ -1867,7 +1868,7 @@ static void subflow_ulp_clone(const stru
 		new_ctx->idsn = subflow_req->idsn;
 
 		/* this is the first subflow, id is always 0 */
-		new_ctx->local_id_valid = 1;
+		subflow_set_local_id(new_ctx, 0);
 	} else if (subflow_req->mp_join) {
 		new_ctx->ssn_offset = subflow_req->ssn_offset;
 		new_ctx->mp_join = 1;
author maintainer
#98 lore raw

PATCH 98/215 mptcp: fix data races on remote_id

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Paolo Abeni <[email protected]>

commit 967d3c27127e71a10ff5c083583a038606431b61 upstream.

Similar to the previous patch, address the data race on remote_id, adding the suitable ONCE annotations.

---
 net/mptcp/pm_netlink.c |    8 ++++----
 net/mptcp/subflow.c    |    6 +++---
 2 files changed, 7 insertions(+), 7 deletions(-)
net/mptcp/pm_netlink.c +4 -4
@@ -449,7 +449,7 @@ static unsigned int fill_remote_addresse
 		mptcp_for_each_subflow(msk, subflow) {
 			ssk = mptcp_subflow_tcp_sock(subflow);
 			remote_address((struct sock_common *)ssk, &addrs[i]);
-			addrs[i].id = subflow->remote_id;
+			addrs[i].id = READ_ONCE(subflow->remote_id);
 			if (deny_id0 && !addrs[i].id)
 				continue;
 
@@ -798,18 +798,18 @@ static void mptcp_pm_nl_rm_addr_or_subfl
 
 		mptcp_for_each_subflow_safe(msk, subflow, tmp) {
 			struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+			u8 remote_id = READ_ONCE(subflow->remote_id);
 			int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
 			u8 id = subflow_get_local_id(subflow);
 
-			if (rm_type == MPTCP_MIB_RMADDR && subflow->remote_id != rm_id)
+			if (rm_type == MPTCP_MIB_RMADDR && remote_id != rm_id)
 				continue;
 			if (rm_type == MPTCP_MIB_RMSUBFLOW && !mptcp_local_id_match(msk, id, rm_id))
 				continue;
 
 			pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u",
 				 rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow",
-				 i, rm_id, id, subflow->remote_id,
-				 msk->mpc_endpoint_id);
+				 i, rm_id, id, remote_id, msk->mpc_endpoint_id);
 			spin_unlock_bh(&msk->pm.lock);
 			mptcp_subflow_shutdown(sk, ssk, how);
 
net/mptcp/subflow.c +3 -3
@@ -446,7 +446,7 @@ static void subflow_finish_connect(struc
 		subflow->backup = mp_opt.backup;
 		subflow->thmac = mp_opt.thmac;
 		subflow->remote_nonce = mp_opt.nonce;
-		subflow->remote_id = mp_opt.join_id;
+		WRITE_ONCE(subflow->remote_id, mp_opt.join_id);
 		pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d",
 			 subflow, subflow->thmac, subflow->remote_nonce,
 			 subflow->backup);
@@ -1477,7 +1477,7 @@ int __mptcp_subflow_connect(struct sock
 	pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk,
 		 remote_token, local_id, remote_id);
 	subflow->remote_token = remote_token;
-	subflow->remote_id = remote_id;
+	WRITE_ONCE(subflow->remote_id, remote_id);
 	subflow->request_join = 1;
 	subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP);
 	mptcp_info2sockaddr(remote, &addr, ssk->sk_family);
@@ -1874,7 +1874,7 @@ static void subflow_ulp_clone(const stru
 		new_ctx->mp_join = 1;
 		new_ctx->fully_established = 1;
 		new_ctx->backup = subflow_req->backup;
-		new_ctx->remote_id = subflow_req->remote_id;
+		WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id);
 		new_ctx->token = subflow_req->token;
 		new_ctx->thmac = subflow_req->thmac;
 
author maintainer
#99 lore raw

PATCH 99/215 mptcp: fix duplicate subflow creation

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Paolo Abeni <[email protected]>

commit 045e9d812868a2d80b7a57b224ce8009444b7bbc upstream.

Fullmesh endpoints could end-up unexpectedly generating duplicate subflows - same local and remote addresses - when multiple incoming ADD_ADDR are processed before the PM creates the subflow for the local endpoints.

Address the issue explicitly checking for duplicates at subflow creation time.

To avoid a quadratic computational complexity, track the unavailable remote address ids in a temporary bitmap and initialize such bitmap with the remote ids of all the existing subflows matching the local address currently processed.

The above allows additionally replacing the existing code checking for duplicate entry in the current set with a simple bit test operation.

---
 net/mptcp/pm_netlink.c |   36 +++++++++++++++++++-----------------
 1 file changed, 19 insertions(+), 17 deletions(-)
net/mptcp/pm_netlink.c +19 -17
@@ -407,23 +407,12 @@ void mptcp_pm_free_anno_list(struct mptc
 	}
 }
 
-static bool lookup_address_in_vec(const struct mptcp_addr_info *addrs, unsigned int nr,
-				  const struct mptcp_addr_info *addr)
-{
-	int i;
-
-	for (i = 0; i < nr; i++) {
-		if (addrs[i].id == addr->id)
-			return true;
-	}
-
-	return false;
-}
-
 /* Fill all the remote addresses into the array addrs[],
  * and return the array size.
  */
-static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullmesh,
+static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk,
+					      struct mptcp_addr_info *local,
+					      bool fullmesh,
 					      struct mptcp_addr_info *addrs)
 {
 	bool deny_id0 = READ_ONCE(msk->pm.remote_deny_join_id0);
@@ -446,6 +435,16 @@ static unsigned int fill_remote_addresse
 		msk->pm.subflows++;
 		addrs[i++] = remote;
 	} else {
+		DECLARE_BITMAP(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1);
+
+		/* Forbid creation of new subflows matching existing
+		 * ones, possibly already created by incoming ADD_ADDR
+		 */
+		bitmap_zero(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1);
+		mptcp_for_each_subflow(msk, subflow)
+			if (READ_ONCE(subflow->local_id) == local->id)
+				__set_bit(subflow->remote_id, unavail_id);
+
 		mptcp_for_each_subflow(msk, subflow) {
 			ssk = mptcp_subflow_tcp_sock(subflow);
 			remote_address((struct sock_common *)ssk, &addrs[i]);
@@ -453,8 +452,11 @@ static unsigned int fill_remote_addresse
 			if (deny_id0 && !addrs[i].id)
 				continue;
 
-			if (!lookup_address_in_vec(addrs, i, &addrs[i]) &&
-			    msk->pm.subflows < subflows_max) {
+			if (msk->pm.subflows < subflows_max) {
+				/* forbid creating multiple address towards
+				 * this id
+				 */
+				__set_bit(addrs[i].id, unavail_id);
 				msk->pm.subflows++;
 				i++;
 			}
@@ -603,7 +605,7 @@ static void mptcp_pm_create_subflow_or_s
 		fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
 
 		msk->pm.local_addr_used++;
-		nr = fill_remote_addresses_vec(msk, fullmesh, addrs);
+		nr = fill_remote_addresses_vec(msk, &local->addr, fullmesh, addrs);
 		if (nr)
 			__clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
 		spin_unlock_bh(&msk->pm.lock);
author maintainer
#100 lore raw

PATCH 100/215 mptcp: continue marking the first subflow as UNCONNECTED

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: "Matthieu Baerts (NGI0)" <[email protected]>

After the 'Fixes' commit mentioned below, which is a partial backport, the MPTCP worker was no longer marking the first subflow as "UNCONNECTED" when the socket was transitioning to TCP_CLOSE state.

As a result, in v6.1, it was no longer possible to reconnect to the just disconnected socket. Continue to do that like before, only for the first subflow.

A few refactoring have been done around the 'msk->subflow' in later versions, and it looks like this is not needed to do that there, but still needed in v6.1. Without that, the 'disconnect' tests from the mptcp_connect.sh selftest fail: they repeat the transfer 3 times by reconnecting to the server each time.

Fixes 7857e35ef10e ("mptcp: get rid of msk->subflow")
---
 net/mptcp/protocol.c |    2 ++
 1 file changed, 2 insertions(+)
net/mptcp/protocol.c +2 -0
@@ -2440,6 +2440,8 @@ static void __mptcp_close_ssk(struct soc
 	need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk);
 	if (!dispose_it) {
 		__mptcp_subflow_disconnect(ssk, subflow, flags);
+		if (msk->subflow && ssk == msk->subflow->sk)
+			msk->subflow->state = SS_UNCONNECTED;
 		release_sock(ssk);
 
 		goto out;
author maintainer
#101 lore raw

PATCH 101/215 mptcp: map v4 address to v6 when destroying subflow

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Geliang Tang <[email protected]>

commit 535d620ea5ff1a033dc64ee3d912acadc7470619 upstream.

Address family of server side mismatches with that of client side, like in "userspace pm add & remove address" test:

    userspace_pm_add_addr $ns1 10.0.2.1 10
    userspace_pm_rm_sf $ns1 "::ffff:10.0.2.1" $SUB_ESTABLISHED

That's because on the server side, the family is set to AF_INET6 and the v4 address is mapped in a v6 one.

This patch fixes this issue. In mptcp_pm_nl_subflow_destroy_doit(), before checking local address family with remote address family, map an IPv4 address to an IPv6 address if the pair is a v4-mapped address.

---
 net/mptcp/pm_userspace.c |   10 ++++++++++
 1 file changed, 10 insertions(+)
net/mptcp/pm_userspace.c +10 -0
@@ -489,6 +489,16 @@ int mptcp_nl_cmd_sf_destroy(struct sk_bu
 		goto destroy_err;
 	}
 
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	if (addr_l.family == AF_INET && ipv6_addr_v4mapped(&addr_r.addr6)) {
+		ipv6_addr_set_v4mapped(addr_l.addr.s_addr, &addr_l.addr6);
+		addr_l.family = AF_INET6;
+	}
+	if (addr_r.family == AF_INET && ipv6_addr_v4mapped(&addr_l.addr6)) {
+		ipv6_addr_set_v4mapped(addr_r.addr.s_addr, &addr_r.addr6);
+		addr_r.family = AF_INET6;
+	}
+#endif
 	if (addr_l.family != addr_r.family) {
 		GENL_SET_ERR_MSG(info, "address families do not match");
 		err = -EINVAL;
author maintainer
#102 lore raw

PATCH 102/215 mptcp: push at DSS boundaries

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Paolo Abeni <[email protected]>

commit b9cd26f640a308ea314ad23532de9a8592cd09d2 upstream.

when inserting not contiguous data in the subflow write queue, the protocol creates a new skb and prevent the TCP stack from merging it later with already queued skbs by setting the EOR marker.

Still no push flag is explicitly set at the end of previous GSO packet, making the aggregation on the receiver side sub-optimal - and packetdrill self-tests less predictable.

Explicitly mark the end of not contiguous DSS with the push flag.

---
 net/mptcp/protocol.c |    1 +
 1 file changed, 1 insertion(+)
net/mptcp/protocol.c +1 -0
@@ -1319,6 +1319,7 @@ static int mptcp_sendmsg_frag(struct soc
 		mpext = skb_ext_find(skb, SKB_EXT_MPTCP);
 		if (!mptcp_skb_can_collapse_to(data_seq, skb, mpext)) {
 			TCP_SKB_CB(skb)->eor = 1;
+			tcp_mark_push(tcp_sk(ssk), skb);
 			goto alloc_skb;
 		}
 
author maintainer
#93 lore raw

PATCH 93/215 efivarfs: Request at most 512 bytes for variable names

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tim Schumacher <[email protected]>

commit f45812cc23fb74bef62d4eb8a69fe7218f4b9f2a upstream.

Work around a quirk in a few old (2011-ish) UEFI implementations, where a call to GetNextVariableName with a buffer size larger than 512 bytes will always return EFI_INVALID_PARAMETER.

There is some lore around EFI variable names being up to 1024 bytes in size, but this has no basis in the UEFI specification, and the upper bounds are typically platform specific, and apply to the entire variable (name plus payload).

Given that Linux does not permit creating files with names longer than NAME_MAX (255) bytes, 512 bytes (== 256 UTF-16 characters) is a reasonable limit.

---
 fs/efivarfs/vars.c |   17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)
fs/efivarfs/vars.c +11 -6
@@ -372,7 +372,7 @@ static void dup_variable_bug(efi_char16_
 int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *),
 		void *data, bool duplicates, struct list_head *head)
 {
-	unsigned long variable_name_size = 1024;
+	unsigned long variable_name_size = 512;
 	efi_char16_t *variable_name;
 	efi_status_t status;
 	efi_guid_t vendor_guid;
@@ -389,12 +389,13 @@ int efivar_init(int (*func)(efi_char16_t
 		goto free;
 
 	/*
-	 * Per EFI spec, the maximum storage allocated for both
-	 * the variable name and variable data is 1024 bytes.
+	 * A small set of old UEFI implementations reject sizes
+	 * above a certain threshold, the lowest seen in the wild
+	 * is 512.
 	 */
 
 	do {
-		variable_name_size = 1024;
+		variable_name_size = 512;
 
 		status = efivar_get_next_variable(&variable_name_size,
 						  variable_name,
@@ -431,9 +432,13 @@ int efivar_init(int (*func)(efi_char16_t
 			break;
 		case EFI_NOT_FOUND:
 			break;
+		case EFI_BUFFER_TOO_SMALL:
+			pr_warn("efivars: Variable name size exceeds maximum (%lu > 512)\n",
+				variable_name_size);
+			status = EFI_NOT_FOUND;
+			break;
 		default:
-			printk(KERN_WARNING "efivars: get_next_variable: status=%lx\n",
-				status);
+			pr_warn("efivars: get_next_variable: status=%lx\n", status);
 			status = EFI_NOT_FOUND;
 			break;
 		}
author maintainer
#120 lore raw

PATCH 120/215 x86/boot/compressed: Move startup32_load_idt() into .text section

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit c6355995ba471d7ad574174e593192ce805c7e1a upstream.

Convert startup32_load_idt() into an ordinary function and move it into the .text section. This involves turning the rva() immediates into ones derived from a local label, and preserving/restoring the %ebp and %ebx as per the calling convention.

Also move the #ifdef to the only existing call site. This makes it clear that the function call does nothing if support for memory encryption is not compiled in.

---
 arch/x86/boot/compressed/head_64.S |   31 ++++++++++++++++++++-----------
 1 file changed, 20 insertions(+), 11 deletions(-)
arch/x86/boot/compressed/head_64.S +20 -11
@@ -118,7 +118,9 @@ SYM_FUNC_START(startup_32)
 1:
 
 	/* Setup Exception handling for SEV-ES */
+#ifdef CONFIG_AMD_MEM_ENCRYPT
 	call	startup32_load_idt
+#endif
 
 	/* Make sure cpu supports long mode. */
 	call	verify_cpu
@@ -732,10 +734,8 @@ SYM_DATA_START(boot32_idt)
 	.quad 0
 	.endr
 SYM_DATA_END_LABEL(boot32_idt, SYM_L_GLOBAL, boot32_idt_end)
-#endif
 
-#ifdef CONFIG_AMD_MEM_ENCRYPT
-	__HEAD
+	.text
 	.code32
 /*
  * Write an IDT entry into boot32_idt
@@ -768,24 +768,32 @@ SYM_FUNC_START_LOCAL(startup32_set_idt_e
 
 	RET
 SYM_FUNC_END(startup32_set_idt_entry)
-#endif
 
 SYM_FUNC_START(startup32_load_idt)
-#ifdef CONFIG_AMD_MEM_ENCRYPT
-	leal    rva(boot32_idt)(%ebp), %ecx
+	push	%ebp
+	push	%ebx
+
+	call	1f
+1:	pop	%ebp
+
+	leal    (boot32_idt - 1b)(%ebp), %ebx
 
 	/* #VC handler */
-	leal    rva(startup32_vc_handler)(%ebp), %eax
+	leal    (startup32_vc_handler - 1b)(%ebp), %eax
 	movl    $X86_TRAP_VC, %edx
+	movl	%ebx, %ecx
 	call    startup32_set_idt_entry
 
 	/* Load IDT */
-	leal	rva(boot32_idt)(%ebp), %eax
-	movl	%eax, rva(boot32_idt_desc+2)(%ebp)
-	lidt    rva(boot32_idt_desc)(%ebp)
-#endif
+	leal	(boot32_idt_desc - 1b)(%ebp), %ecx
+	movl	%ebx, 2(%ecx)
+	lidt    (%ecx)
+
+	pop	%ebx
+	pop	%ebp
 	RET
 SYM_FUNC_END(startup32_load_idt)
+#endif
 
 /*
  * Check for the correct C-bit position when the startup_32 boot-path is used.
@@ -804,6 +812,7 @@ SYM_FUNC_END(startup32_load_idt)
  * succeed. An incorrect C-bit position will map all memory unencrypted, so that
  * the compare will use the encrypted random data and fail.
  */
+	__HEAD
 SYM_FUNC_START(startup32_check_sev_cbit)
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 	pushl	%eax
author maintainer
#133 lore raw

PATCH 129/215 x86/efistub: Branch straight to kernel entry point from C code

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit d2d7a54f69b67cd0a30e0ebb5307cb2de625baac upstream.

Instead of returning to the calling code in assembler that does nothing more than perform an indirect call with the boot_params pointer in register ESI/RSI, perform the jump directly from the EFI stub C code. This will allow the asm entrypoint code to be dropped entirely in subsequent patches.

---
 drivers/firmware/efi/libstub/x86-stub.c |   22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)
drivers/firmware/efi/libstub/x86-stub.c +17 -5
@@ -279,7 +279,7 @@ adjust_memory_range_protection(unsigned
 #define TRAMPOLINE_PLACEMENT_BASE ((128 - 8)*1024)
 #define TRAMPOLINE_PLACEMENT_SIZE (640*1024 - (128 - 8)*1024)
 
-void startup_32(struct boot_params *boot_params);
+extern const u8 startup_32[], startup_64[];
 
 static void
 setup_memory_protection(unsigned long image_base, unsigned long image_size)
@@ -760,10 +760,19 @@ static efi_status_t exit_boot(struct boo
 	return EFI_SUCCESS;
 }
 
+static void __noreturn enter_kernel(unsigned long kernel_addr,
+				    struct boot_params *boot_params)
+{
+	/* enter decompressed kernel with boot_params pointer in RSI/ESI */
+	asm("jmp *%0"::"r"(kernel_addr), "S"(boot_params));
+
+	unreachable();
+}
+
 /*
- * On success, we return the address of startup_32, which has potentially been
- * relocated by efi_relocate_kernel.
- * On failure, we exit to the firmware via efi_exit instead of returning.
+ * On success, this routine will jump to the relocated image directly and never
+ * return.  On failure, it will exit to the firmware via efi_exit() instead of
+ * returning.
  */
 asmlinkage unsigned long efi_main(efi_handle_t handle,
 				  efi_system_table_t *sys_table_arg,
@@ -905,7 +914,10 @@ asmlinkage unsigned long efi_main(efi_ha
 		goto fail;
 	}
 
-	return bzimage_addr;
+	if (IS_ENABLED(CONFIG_X86_64))
+		bzimage_addr += startup_64 - startup_32;
+
+	enter_kernel(bzimage_addr, boot_params);
 fail:
 	efi_err("efi_main() failed!\n");
 
author maintainer
#134 lore raw

PATCH 130/215 x86/decompressor: Store boot_params pointer in callee save register

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit 8b63cba746f86a754d66e302c43209cc9b9b6e39 upstream.

Instead of pushing and popping %RSI several times to preserve the struct boot_params pointer across the execution of the startup code, move it into a callee save register before the first call into C, and copy it back when needed.

---
 arch/x86/boot/compressed/head_64.S |   42 ++++++++++++++-----------------------
 1 file changed, 16 insertions(+), 26 deletions(-)
arch/x86/boot/compressed/head_64.S +16 -26
@@ -408,10 +408,14 @@ SYM_CODE_START(startup_64)
 	lretq
 
 .Lon_kernel_cs:
+	/*
+	 * RSI holds a pointer to a boot_params structure provided by the
+	 * loader, and this needs to be preserved across C function calls. So
+	 * move it into a callee saved register.
+	 */
+	movq	%rsi, %r15
 
-	pushq	%rsi
 	call	load_stage1_idt
-	popq	%rsi
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 	/*
@@ -422,12 +426,10 @@ SYM_CODE_START(startup_64)
 	 * CPUID instructions being issued, so go ahead and do that now via
 	 * sev_enable(), which will also handle the rest of the SEV-related
 	 * detection/setup to ensure that has been done in advance of any dependent
-	 * code.
+	 * code. Pass the boot_params pointer as the first argument.
 	 */
-	pushq	%rsi
-	movq	%rsi, %rdi		/* real mode address */
+	movq	%r15, %rdi
 	call	sev_enable
-	popq	%rsi
 #endif
 
 	/*
@@ -440,13 +442,10 @@ SYM_CODE_START(startup_64)
 	 *   - Non zero RDX means trampoline needs to enable 5-level
 	 *     paging.
 	 *
-	 * RSI holds real mode data and needs to be preserved across
-	 * this function call.
+	 * Pass the boot_params pointer as the first argument.
 	 */
-	pushq	%rsi
-	movq	%rsi, %rdi		/* real mode address */
+	movq	%r15, %rdi
 	call	paging_prepare
-	popq	%rsi
 
 	/* Save the trampoline address in RCX */
 	movq	%rax, %rcx
@@ -459,9 +458,9 @@ SYM_CODE_START(startup_64)
 	 * because the architecture does not guarantee that GPRs will retain
 	 * their full 64-bit values across a 32-bit mode switch.
 	 */
+	pushq	%r15
 	pushq	%rbp
 	pushq	%rbx
-	pushq	%rsi
 
 	/*
 	 * Push the 64-bit address of trampoline_return() onto the new stack.
@@ -478,9 +477,9 @@ SYM_CODE_START(startup_64)
 	lretq
 trampoline_return:
 	/* Restore live 64-bit registers */
-	popq	%rsi
 	popq	%rbx
 	popq	%rbp
+	popq	%r15
 
 	/* Restore the stack, the 32-bit trampoline uses its own stack */
 	leaq	rva(boot_stack_end)(%rbx), %rsp
@@ -490,14 +489,9 @@ trampoline_return:
 	 *
 	 * RDI is address of the page table to use instead of page table
 	 * in trampoline memory (if required).
-	 *
-	 * RSI holds real mode data and needs to be preserved across
-	 * this function call.
 	 */
-	pushq	%rsi
 	leaq	rva(top_pgtable)(%rbx), %rdi
 	call	cleanup_trampoline
-	popq	%rsi
 
 	/* Zero EFLAGS */
 	pushq	$0
@@ -507,7 +501,6 @@ trampoline_return:
  * Copy the compressed kernel to the end of our buffer
  * where decompression in place becomes safe.
  */
-	pushq	%rsi
 	leaq	(_bss-8)(%rip), %rsi
 	leaq	rva(_bss-8)(%rbx), %rdi
 	movl	$(_bss - startup_32), %ecx
@@ -515,7 +508,6 @@ trampoline_return:
 	std
 	rep	movsq
 	cld
-	popq	%rsi
 
 	/*
 	 * The GDT may get overwritten either during the copy we just did or
@@ -562,30 +554,28 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated
 	shrq	$3, %rcx
 	rep	stosq
 
-	pushq	%rsi
 	call	load_stage2_idt
 
 	/* Pass boot_params to initialize_identity_maps() */
-	movq	(%rsp), %rdi
+	movq	%r15, %rdi
 	call	initialize_identity_maps
-	popq	%rsi
 
 /*
  * Do the extraction, and jump to the new kernel..
  */
-	pushq	%rsi			/* Save the real mode argument */
-	movq	%rsi, %rdi		/* real mode address */
+	/* pass struct boot_params pointer */
+	movq	%r15, %rdi
 	leaq	boot_heap(%rip), %rsi	/* malloc area for uncompression */
 	leaq	input_data(%rip), %rdx  /* input_data */
 	movl	input_len(%rip), %ecx	/* input_len */
 	movq	%rbp, %r8		/* output target address */
 	movl	output_len(%rip), %r9d	/* decompressed length, end of relocs */
 	call	extract_kernel		/* returns kernel entry point in %rax */
-	popq	%rsi
 
 /*
  * Jump to the decompressed kernel.
  */
+	movq	%r15, %rsi
 	jmp	*%rax
 SYM_FUNC_END(.Lrelocated)
 
author maintainer
#135 lore raw

PATCH 131/215 x86/decompressor: Assign paging related global variables earlier

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit 00c6b0978ec182f1a672095930872168b9d5b1e2 upstream.

There is no need to defer the assignment of the paging related global variables 'pgdir_shift' and 'ptrs_per_p4d' until after the trampoline is cleaned up, so assign them as soon as it is clear that 5-level paging will be enabled.

---
 arch/x86/boot/compressed/misc.h       |    2 --
 arch/x86/boot/compressed/pgtable_64.c |   14 +++++---------
 2 files changed, 5 insertions(+), 11 deletions(-)
arch/x86/boot/compressed/misc.h +0 -2
@@ -170,9 +170,7 @@ static inline int count_immovable_mem_re
 #endif
 
 /* ident_map_64.c */
-#ifdef CONFIG_X86_5LEVEL
 extern unsigned int __pgtable_l5_enabled, pgdir_shift, ptrs_per_p4d;
-#endif
 extern void kernel_add_identity_map(unsigned long start, unsigned long end);
 
 /* Used by PAGE_KERN* macros: */
arch/x86/boot/compressed/pgtable_64.c +5 -9
@@ -130,6 +130,11 @@ struct paging_config paging_prepare(void
 			native_cpuid_eax(0) >= 7 &&
 			(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) {
 		paging_config.l5_required = 1;
+
+		/* Initialize variables for 5-level paging */
+		__pgtable_l5_enabled = 1;
+		pgdir_shift = 48;
+		ptrs_per_p4d = 512;
 	}
 
 	paging_config.trampoline_start = find_trampoline_placement();
@@ -206,13 +211,4 @@ void cleanup_trampoline(void *pgtable)
 
 	/* Restore trampoline memory */
 	memcpy(trampoline_32bit, trampoline_save, TRAMPOLINE_32BIT_SIZE);
-
-	/* Initialize variables for 5-level paging */
-#ifdef CONFIG_X86_5LEVEL
-	if (__read_cr4() & X86_CR4_LA57) {
-		__pgtable_l5_enabled = 1;
-		pgdir_shift = 48;
-		ptrs_per_p4d = 512;
-	}
-#endif
 }
author maintainer
#136 lore raw

PATCH 132/215 x86/decompressor: Call trampoline as a normal function

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit e8972a76aa90c05a0078043413f806c02fcb3487 upstream.

Move the long return to switch to 32-bit mode into the trampoline code so it can be called as an ordinary function. This will allow it to be called directly from C code in a subsequent patch.

While at it, reorganize the code somewhat to keep the prologue and epilogue of the function together, making the code a bit easier to follow. Also, given that the trampoline is now entered in 64-bit mode, a simple RIP-relative reference can be used to take the address of the exit point.

---
 arch/x86/boot/compressed/head_64.S |   79 ++++++++++++++++---------------------
 arch/x86/boot/compressed/pgtable.h |    2 
 2 files changed, 36 insertions(+), 45 deletions(-)
arch/x86/boot/compressed/head_64.S +35 -44
@@ -450,39 +450,8 @@ SYM_CODE_START(startup_64)
 	/* Save the trampoline address in RCX */
 	movq	%rax, %rcx
 
-	/* Set up 32-bit addressable stack */
-	leaq	TRAMPOLINE_32BIT_STACK_END(%rcx), %rsp
-
-	/*
-	 * Preserve live 64-bit registers on the stack: this is necessary
-	 * because the architecture does not guarantee that GPRs will retain
-	 * their full 64-bit values across a 32-bit mode switch.
-	 */
-	pushq	%r15
-	pushq	%rbp
-	pushq	%rbx
-
-	/*
-	 * Push the 64-bit address of trampoline_return() onto the new stack.
-	 * It will be used by the trampoline to return to the main code. Due to
-	 * the 32-bit mode switch, it cannot be kept it in a register either.
-	 */
-	leaq	trampoline_return(%rip), %rdi
-	pushq	%rdi
-
-	/* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */
-	pushq	$__KERNEL32_CS
 	leaq	TRAMPOLINE_32BIT_CODE_OFFSET(%rax), %rax
-	pushq	%rax
-	lretq
-trampoline_return:
-	/* Restore live 64-bit registers */
-	popq	%rbx
-	popq	%rbp
-	popq	%r15
-
-	/* Restore the stack, the 32-bit trampoline uses its own stack */
-	leaq	rva(boot_stack_end)(%rbx), %rsp
+	call	*%rax
 
 	/*
 	 * cleanup_trampoline() would restore trampoline memory.
@@ -579,7 +548,6 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated
 	jmp	*%rax
 SYM_FUNC_END(.Lrelocated)
 
-	.code32
 /*
  * This is the 32-bit trampoline that will be copied over to low memory.
  *
@@ -588,6 +556,39 @@ SYM_FUNC_END(.Lrelocated)
  * Non zero RDX means trampoline needs to enable 5-level paging.
  */
 SYM_CODE_START(trampoline_32bit_src)
+	/*
+	 * Preserve live 64-bit registers on the stack: this is necessary
+	 * because the architecture does not guarantee that GPRs will retain
+	 * their full 64-bit values across a 32-bit mode switch.
+	 */
+	pushq	%r15
+	pushq	%rbp
+	pushq	%rbx
+
+	/* Set up 32-bit addressable stack and push the old RSP value */
+	leaq	(TRAMPOLINE_32BIT_STACK_END - 8)(%rcx), %rbx
+	movq	%rsp, (%rbx)
+	movq	%rbx, %rsp
+
+	/* Take the address of the trampoline exit code */
+	leaq	.Lret(%rip), %rbx
+
+	/* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */
+	pushq	$__KERNEL32_CS
+	leaq	0f(%rip), %rax
+	pushq	%rax
+	lretq
+
+.Lret:
+	/* Restore the preserved 64-bit registers */
+	movq	(%rsp), %rsp
+	popq	%rbx
+	popq	%rbp
+	popq	%r15
+	retq
+
+	.code32
+0:
 	/* Set up data and stack segments */
 	movl	$__KERNEL_DS, %eax
 	movl	%eax, %ds
@@ -651,12 +652,9 @@ SYM_CODE_START(trampoline_32bit_src)
 1:
 	movl	%eax, %cr4
 
-	/* Calculate address of paging_enabled() once we are executing in the trampoline */
-	leal	.Lpaging_enabled - trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_OFFSET(%ecx), %eax
-
 	/* Prepare the stack for far return to Long Mode */
 	pushl	$__KERNEL_CS
-	pushl	%eax
+	pushl	%ebx
 
 	/* Enable paging again. */
 	movl	%cr0, %eax
@@ -666,12 +664,6 @@ SYM_CODE_START(trampoline_32bit_src)
 	lret
 SYM_CODE_END(trampoline_32bit_src)
 
-	.code64
-SYM_FUNC_START_LOCAL_NOALIGN(.Lpaging_enabled)
-	/* Return from the trampoline */
-	retq
-SYM_FUNC_END(.Lpaging_enabled)
-
 	/*
          * The trampoline code has a size limit.
          * Make sure we fail to compile if the trampoline code grows
@@ -679,7 +671,6 @@ SYM_FUNC_END(.Lpaging_enabled)
 	 */
 	.org	trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_SIZE
 
-	.code32
 SYM_FUNC_START_LOCAL_NOALIGN(.Lno_longmode)
 	/* This isn't an x86-64 CPU, so hang intentionally, we cannot continue */
 1:
arch/x86/boot/compressed/pgtable.h +1 -1
@@ -6,7 +6,7 @@
 #define TRAMPOLINE_32BIT_PGTABLE_OFFSET	0
 
 #define TRAMPOLINE_32BIT_CODE_OFFSET	PAGE_SIZE
-#define TRAMPOLINE_32BIT_CODE_SIZE	0x80
+#define TRAMPOLINE_32BIT_CODE_SIZE	0xA0
 
 #define TRAMPOLINE_32BIT_STACK_END	TRAMPOLINE_32BIT_SIZE
 
author maintainer
#137 lore raw

PATCH 133/215 x86/decompressor: Use standard calling convention for trampoline

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit 918a7a04e71745e99a0efc6753e587439b794b29 upstream.

Update the trampoline code so its arguments are passed via RDI and RSI, which matches the ordinary SysV calling convention for x86_64. This will allow this code to be called directly from C.

---
 arch/x86/boot/compressed/head_64.S |   27 +++++++++++++--------------
 arch/x86/boot/compressed/pgtable.h |    2 +-
 2 files changed, 14 insertions(+), 15 deletions(-)
arch/x86/boot/compressed/head_64.S +13 -14
@@ -447,9 +447,9 @@ SYM_CODE_START(startup_64)
 	movq	%r15, %rdi
 	call	paging_prepare
 
-	/* Save the trampoline address in RCX */
-	movq	%rax, %rcx
-
+	/* Pass the trampoline address and boolean flag as args #1 and #2 */
+	movq	%rax, %rdi
+	movq	%rdx, %rsi
 	leaq	TRAMPOLINE_32BIT_CODE_OFFSET(%rax), %rax
 	call	*%rax
 
@@ -549,11 +549,14 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated
 SYM_FUNC_END(.Lrelocated)
 
 /*
- * This is the 32-bit trampoline that will be copied over to low memory.
+ * This is the 32-bit trampoline that will be copied over to low memory. It
+ * will be called using the ordinary 64-bit calling convention from code
+ * running in 64-bit mode.
  *
  * Return address is at the top of the stack (might be above 4G).
- * ECX contains the base address of the trampoline memory.
- * Non zero RDX means trampoline needs to enable 5-level paging.
+ * The first argument (EDI) contains the 32-bit addressable base of the
+ * trampoline memory. A non-zero second argument (ESI) means that the
+ * trampoline needs to enable 5-level paging.
  */
 SYM_CODE_START(trampoline_32bit_src)
 	/*
@@ -600,7 +603,7 @@ SYM_CODE_START(trampoline_32bit_src)
 	movl	%eax, %cr0
 
 	/* Check what paging mode we want to be in after the trampoline */
-	testl	%edx, %edx
+	testl	%esi, %esi
 	jz	1f
 
 	/* We want 5-level paging: don't touch CR3 if it already points to 5-level page tables */
@@ -615,21 +618,17 @@ SYM_CODE_START(trampoline_32bit_src)
 	jz	3f
 2:
 	/* Point CR3 to the trampoline's new top level page table */
-	leal	TRAMPOLINE_32BIT_PGTABLE_OFFSET(%ecx), %eax
+	leal	TRAMPOLINE_32BIT_PGTABLE_OFFSET(%edi), %eax
 	movl	%eax, %cr3
 3:
 	/* Set EFER.LME=1 as a precaution in case hypervsior pulls the rug */
-	pushl	%ecx
-	pushl	%edx
 	movl	$MSR_EFER, %ecx
 	rdmsr
 	btsl	$_EFER_LME, %eax
 	/* Avoid writing EFER if no change was made (for TDX guest) */
 	jc	1f
 	wrmsr
-1:	popl	%edx
-	popl	%ecx
-
+1:
 #ifdef CONFIG_X86_MCE
 	/*
 	 * Preserve CR4.MCE if the kernel will enable #MC support.
@@ -646,7 +645,7 @@ SYM_CODE_START(trampoline_32bit_src)
 
 	/* Enable PAE and LA57 (if required) paging modes */
 	orl	$X86_CR4_PAE, %eax
-	testl	%edx, %edx
+	testl	%esi, %esi
 	jz	1f
 	orl	$X86_CR4_LA57, %eax
 1:
arch/x86/boot/compressed/pgtable.h +1 -1
@@ -14,7 +14,7 @@
 
 extern unsigned long *trampoline_32bit;
 
-extern void trampoline_32bit_src(void *return_ptr);
+extern void trampoline_32bit_src(void *trampoline, bool enable_5lvl);
 
 #endif /* __ASSEMBLER__ */
 #endif /* BOOT_COMPRESSED_PAGETABLE_H */
author maintainer
#138 lore raw

PATCH 134/215 x86/decompressor: Avoid the need for a stack in the 32-bit trampoline

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit bd328aa01ff77a45aeffea5fc4521854291db11f upstream.

The 32-bit trampoline no longer uses the stack for anything except performing a far return back to long mode, and preserving the caller's stack pointer value. Currently, the trampoline stack is placed in the same page that carries the trampoline code, which means this page must be mapped writable and executable, and the stack is therefore executable as well.

Replace the far return with a far jump, so that the return address can be pre-calculated and patched into the code before it is called. This removes the need for a 32-bit addressable stack entirely, and in a later patch, this will be taken advantage of by removing writable permissions from (and adding executable permissions to) the trampoline code page when booting via the EFI stub.

Note that the value of RSP still needs to be preserved explicitly across the switch into 32-bit mode, as the register may get truncated to 32 bits.

---
 arch/x86/boot/compressed/head_64.S    |   45 ++++++++++++++++++++--------------
 arch/x86/boot/compressed/pgtable.h    |    4 +--
 arch/x86/boot/compressed/pgtable_64.c |   12 ++++++++-
 3 files changed, 40 insertions(+), 21 deletions(-)
arch/x86/boot/compressed/head_64.S +27 -18
@@ -558,6 +558,7 @@ SYM_FUNC_END(.Lrelocated)
  * trampoline memory. A non-zero second argument (ESI) means that the
  * trampoline needs to enable 5-level paging.
  */
+	.section ".rodata", "a", @progbits
 SYM_CODE_START(trampoline_32bit_src)
 	/*
 	 * Preserve live 64-bit registers on the stack: this is necessary
@@ -568,13 +569,9 @@ SYM_CODE_START(trampoline_32bit_src)
 	pushq	%rbp
 	pushq	%rbx
 
-	/* Set up 32-bit addressable stack and push the old RSP value */
-	leaq	(TRAMPOLINE_32BIT_STACK_END - 8)(%rcx), %rbx
-	movq	%rsp, (%rbx)
-	movq	%rbx, %rsp
-
-	/* Take the address of the trampoline exit code */
-	leaq	.Lret(%rip), %rbx
+	/* Preserve top half of RSP in a legacy mode GPR to avoid truncation */
+	movq	%rsp, %rbx
+	shrq	$32, %rbx
 
 	/* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */
 	pushq	$__KERNEL32_CS
@@ -582,9 +579,17 @@ SYM_CODE_START(trampoline_32bit_src)
 	pushq	%rax
 	lretq
 
+	/*
+	 * The 32-bit code below will do a far jump back to long mode and end
+	 * up here after reconfiguring the number of paging levels. First, the
+	 * stack pointer needs to be restored to its full 64-bit value before
+	 * the callee save register contents can be popped from the stack.
+	 */
 .Lret:
+	shlq	$32, %rbx
+	orq	%rbx, %rsp
+
 	/* Restore the preserved 64-bit registers */
-	movq	(%rsp), %rsp
 	popq	%rbx
 	popq	%rbp
 	popq	%r15
@@ -592,11 +597,6 @@ SYM_CODE_START(trampoline_32bit_src)
 
 	.code32
 0:
-	/* Set up data and stack segments */
-	movl	$__KERNEL_DS, %eax
-	movl	%eax, %ds
-	movl	%eax, %ss
-
 	/* Disable paging */
 	movl	%cr0, %eax
 	btrl	$X86_CR0_PG_BIT, %eax
@@ -651,18 +651,26 @@ SYM_CODE_START(trampoline_32bit_src)
 1:
 	movl	%eax, %cr4
 
-	/* Prepare the stack for far return to Long Mode */
-	pushl	$__KERNEL_CS
-	pushl	%ebx
-
 	/* Enable paging again. */
 	movl	%cr0, %eax
 	btsl	$X86_CR0_PG_BIT, %eax
 	movl	%eax, %cr0
 
-	lret
+	/*
+	 * Return to the 64-bit calling code using LJMP rather than LRET, to
+	 * avoid the need for a 32-bit addressable stack. The destination
+	 * address will be adjusted after the template code is copied into a
+	 * 32-bit addressable buffer.
+	 */
+.Ljmp:	ljmpl	$__KERNEL_CS, $(.Lret - trampoline_32bit_src)
 SYM_CODE_END(trampoline_32bit_src)
 
+/*
+ * This symbol is placed right after trampoline_32bit_src() so its address can
+ * be used to infer the size of the trampoline code.
+ */
+SYM_DATA(trampoline_ljmp_imm_offset, .word  .Ljmp + 1 - trampoline_32bit_src)
+
 	/*
          * The trampoline code has a size limit.
          * Make sure we fail to compile if the trampoline code grows
@@ -670,6 +678,7 @@ SYM_CODE_END(trampoline_32bit_src)
 	 */
 	.org	trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_SIZE
 
+	.text
 SYM_FUNC_START_LOCAL_NOALIGN(.Lno_longmode)
 	/* This isn't an x86-64 CPU, so hang intentionally, we cannot continue */
 1:
arch/x86/boot/compressed/pgtable.h +2 -2
@@ -8,13 +8,13 @@
 #define TRAMPOLINE_32BIT_CODE_OFFSET	PAGE_SIZE
 #define TRAMPOLINE_32BIT_CODE_SIZE	0xA0
 
-#define TRAMPOLINE_32BIT_STACK_END	TRAMPOLINE_32BIT_SIZE
-
 #ifndef __ASSEMBLER__
 
 extern unsigned long *trampoline_32bit;
 
 extern void trampoline_32bit_src(void *trampoline, bool enable_5lvl);
 
+extern const u16 trampoline_ljmp_imm_offset;
+
 #endif /* __ASSEMBLER__ */
 #endif /* BOOT_COMPRESSED_PAGETABLE_H */
arch/x86/boot/compressed/pgtable_64.c +11 -1
@@ -109,6 +109,7 @@ static unsigned long find_trampoline_pla
 struct paging_config paging_prepare(void *rmode)
 {
 	struct paging_config paging_config = {};
+	void *tramp_code;
 
 	/* Initialize boot_params. Required for cmdline_find_option_bool(). */
 	boot_params = rmode;
@@ -148,10 +149,19 @@ struct paging_config paging_prepare(void
 	memset(trampoline_32bit, 0, TRAMPOLINE_32BIT_SIZE);
 
 	/* Copy trampoline code in place */
-	memcpy(trampoline_32bit + TRAMPOLINE_32BIT_CODE_OFFSET / sizeof(unsigned long),
+	tramp_code = memcpy(trampoline_32bit +
+			TRAMPOLINE_32BIT_CODE_OFFSET / sizeof(unsigned long),
 			&trampoline_32bit_src, TRAMPOLINE_32BIT_CODE_SIZE);
 
 	/*
+	 * Avoid the need for a stack in the 32-bit trampoline code, by using
+	 * LJMP rather than LRET to return back to long mode. LJMP takes an
+	 * immediate absolute address, which needs to be adjusted based on the
+	 * placement of the trampoline.
+	 */
+	*(u32 *)(tramp_code + trampoline_ljmp_imm_offset) += (unsigned long)tramp_code;
+
+	/*
 	 * The code below prepares page table in trampoline memory.
 	 *
 	 * The new page table will be used by trampoline code for switching
author maintainer
#139 lore raw

PATCH 135/215 x86/decompressor: Call trampoline directly from C code

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit 64ef578b6b6866bec012544416946533444036c8 upstream.

Instead of returning to the asm calling code to invoke the trampoline, call it straight from the C code that sets it up. That way, the struct return type is no longer needed for returning two values, and the call can be made conditional more cleanly in a subsequent patch.

This means that all callee save 64-bit registers need to be preserved and restored, as their contents may not survive the legacy mode switch.

---
 arch/x86/boot/compressed/head_64.S    |   31 +++++++++++++------------------
 arch/x86/boot/compressed/pgtable_64.c |   32 +++++++++++++-------------------
 2 files changed, 26 insertions(+), 37 deletions(-)
arch/x86/boot/compressed/head_64.S +13 -18
@@ -433,25 +433,14 @@ SYM_CODE_START(startup_64)
 #endif
 
 	/*
-	 * paging_prepare() sets up the trampoline and checks if we need to
-	 * enable 5-level paging.
-	 *
-	 * paging_prepare() returns a two-quadword structure which lands
-	 * into RDX:RAX:
-	 *   - Address of the trampoline is returned in RAX.
-	 *   - Non zero RDX means trampoline needs to enable 5-level
-	 *     paging.
+	 * configure_5level_paging() updates the number of paging levels using
+	 * a trampoline in 32-bit addressable memory if the current number does
+	 * not match the desired number.
 	 *
 	 * Pass the boot_params pointer as the first argument.
 	 */
 	movq	%r15, %rdi
-	call	paging_prepare
-
-	/* Pass the trampoline address and boolean flag as args #1 and #2 */
-	movq	%rax, %rdi
-	movq	%rdx, %rsi
-	leaq	TRAMPOLINE_32BIT_CODE_OFFSET(%rax), %rax
-	call	*%rax
+	call	configure_5level_paging
 
 	/*
 	 * cleanup_trampoline() would restore trampoline memory.
@@ -561,11 +550,14 @@ SYM_FUNC_END(.Lrelocated)
 	.section ".rodata", "a", @progbits
 SYM_CODE_START(trampoline_32bit_src)
 	/*
-	 * Preserve live 64-bit registers on the stack: this is necessary
-	 * because the architecture does not guarantee that GPRs will retain
-	 * their full 64-bit values across a 32-bit mode switch.
+	 * Preserve callee save 64-bit registers on the stack: this is
+	 * necessary because the architecture does not guarantee that GPRs will
+	 * retain their full 64-bit values across a 32-bit mode switch.
 	 */
 	pushq	%r15
+	pushq	%r14
+	pushq	%r13
+	pushq	%r12
 	pushq	%rbp
 	pushq	%rbx
 
@@ -592,6 +584,9 @@ SYM_CODE_START(trampoline_32bit_src)
 	/* Restore the preserved 64-bit registers */
 	popq	%rbx
 	popq	%rbp
+	popq	%r12
+	popq	%r13
+	popq	%r14
 	popq	%r15
 	retq
 
arch/x86/boot/compressed/pgtable_64.c +13 -19
@@ -16,11 +16,6 @@ unsigned int __section(".data") pgdir_sh
 unsigned int __section(".data") ptrs_per_p4d = 1;
 #endif
 
-struct paging_config {
-	unsigned long trampoline_start;
-	unsigned long l5_required;
-};
-
 /* Buffer to preserve trampoline memory */
 static char trampoline_save[TRAMPOLINE_32BIT_SIZE];
 
@@ -29,7 +24,7 @@ static char trampoline_save[TRAMPOLINE_3
  * purposes.
  *
  * Avoid putting the pointer into .bss as it will be cleared between
- * paging_prepare() and extract_kernel().
+ * configure_5level_paging() and extract_kernel().
  */
 unsigned long *trampoline_32bit __section(".data");
 
@@ -106,13 +101,13 @@ static unsigned long find_trampoline_pla
 	return bios_start - TRAMPOLINE_32BIT_SIZE;
 }
 
-struct paging_config paging_prepare(void *rmode)
+asmlinkage void configure_5level_paging(struct boot_params *bp)
 {
-	struct paging_config paging_config = {};
-	void *tramp_code;
+	void (*toggle_la57)(void *trampoline, bool enable_5lvl);
+	bool l5_required = false;
 
 	/* Initialize boot_params. Required for cmdline_find_option_bool(). */
-	boot_params = rmode;
+	boot_params = bp;
 
 	/*
 	 * Check if LA57 is desired and supported.
@@ -130,7 +125,7 @@ struct paging_config paging_prepare(void
 			!cmdline_find_option_bool("no5lvl") &&
 			native_cpuid_eax(0) >= 7 &&
 			(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) {
-		paging_config.l5_required = 1;
+		l5_required = true;
 
 		/* Initialize variables for 5-level paging */
 		__pgtable_l5_enabled = 1;
@@ -138,9 +133,7 @@ struct paging_config paging_prepare(void
 		ptrs_per_p4d = 512;
 	}
 
-	paging_config.trampoline_start = find_trampoline_placement();
-
-	trampoline_32bit = (unsigned long *)paging_config.trampoline_start;
+	trampoline_32bit = (unsigned long *)find_trampoline_placement();
 
 	/* Preserve trampoline memory */
 	memcpy(trampoline_save, trampoline_32bit, TRAMPOLINE_32BIT_SIZE);
@@ -149,7 +142,7 @@ struct paging_config paging_prepare(void
 	memset(trampoline_32bit, 0, TRAMPOLINE_32BIT_SIZE);
 
 	/* Copy trampoline code in place */
-	tramp_code = memcpy(trampoline_32bit +
+	toggle_la57 = memcpy(trampoline_32bit +
 			TRAMPOLINE_32BIT_CODE_OFFSET / sizeof(unsigned long),
 			&trampoline_32bit_src, TRAMPOLINE_32BIT_CODE_SIZE);
 
@@ -159,7 +152,8 @@ struct paging_config paging_prepare(void
 	 * immediate absolute address, which needs to be adjusted based on the
 	 * placement of the trampoline.
 	 */
-	*(u32 *)(tramp_code + trampoline_ljmp_imm_offset) += (unsigned long)tramp_code;
+	*(u32 *)((u8 *)toggle_la57 + trampoline_ljmp_imm_offset) +=
+						(unsigned long)toggle_la57;
 
 	/*
 	 * The code below prepares page table in trampoline memory.
@@ -175,10 +169,10 @@ struct paging_config paging_prepare(void
 	 * We are not going to use the page table in trampoline memory if we
 	 * are already in the desired paging mode.
 	 */
-	if (paging_config.l5_required == !!(native_read_cr4() & X86_CR4_LA57))
+	if (l5_required == !!(native_read_cr4() & X86_CR4_LA57))
 		goto out;
 
-	if (paging_config.l5_required) {
+	if (l5_required) {
 		/*
 		 * For 4- to 5-level paging transition, set up current CR3 as
 		 * the first and the only entry in a new top-level page table.
@@ -201,7 +195,7 @@ struct paging_config paging_prepare(void
 	}
 
 out:
-	return paging_config;
+	toggle_la57(trampoline_32bit, l5_required);
 }
 
 void cleanup_trampoline(void *pgtable)
author maintainer
#140 lore raw

PATCH 136/215 x86/decompressor: Only call the trampoline when changing paging levels

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit f97b67a773cd84bd8b55c0a0ec32448a87fc56bb upstream.

Since the current and desired number of paging levels are known when the trampoline is being prepared, avoid calling the trampoline at all if it is clear that calling it is not going to result in a change to the number of paging levels.

Given that the CPU is already running in long mode, the PAE and LA57 settings are necessarily consistent with the currently active page tables, and other fields in CR4 will be initialized by the startup code in the kernel proper. So limit the manipulation of CR4 to toggling the LA57 bit, which is the only thing that really needs doing at this point in the boot. This also means that there is no need to pass the value of l5_required to toggle_la57(), as it will not be called unless CR4.LA57 needs to toggle.

---
 arch/x86/boot/compressed/head_64.S    |   45 +++-------------------------------
 arch/x86/boot/compressed/pgtable_64.c |   22 ++++++----------
 2 files changed, 13 insertions(+), 54 deletions(-)
arch/x86/boot/compressed/head_64.S +4 -41
@@ -390,10 +390,6 @@ SYM_CODE_START(startup_64)
 	 * For the trampoline, we need the top page table to reside in lower
 	 * memory as we don't have a way to load 64-bit values into CR3 in
 	 * 32-bit mode.
-	 *
-	 * We go though the trampoline even if we don't have to: if we're
-	 * already in a desired paging mode. This way the trampoline code gets
-	 * tested on every boot.
 	 */
 
 	/* Make sure we have GDT with 32-bit code segment */
@@ -544,8 +540,7 @@ SYM_FUNC_END(.Lrelocated)
  *
  * Return address is at the top of the stack (might be above 4G).
  * The first argument (EDI) contains the 32-bit addressable base of the
- * trampoline memory. A non-zero second argument (ESI) means that the
- * trampoline needs to enable 5-level paging.
+ * trampoline memory.
  */
 	.section ".rodata", "a", @progbits
 SYM_CODE_START(trampoline_32bit_src)
@@ -597,25 +592,10 @@ SYM_CODE_START(trampoline_32bit_src)
 	btrl	$X86_CR0_PG_BIT, %eax
 	movl	%eax, %cr0
 
-	/* Check what paging mode we want to be in after the trampoline */
-	testl	%esi, %esi
-	jz	1f
-
-	/* We want 5-level paging: don't touch CR3 if it already points to 5-level page tables */
-	movl	%cr4, %eax
-	testl	$X86_CR4_LA57, %eax
-	jnz	3f
-	jmp	2f
-1:
-	/* We want 4-level paging: don't touch CR3 if it already points to 4-level page tables */
-	movl	%cr4, %eax
-	testl	$X86_CR4_LA57, %eax
-	jz	3f
-2:
 	/* Point CR3 to the trampoline's new top level page table */
 	leal	TRAMPOLINE_32BIT_PGTABLE_OFFSET(%edi), %eax
 	movl	%eax, %cr3
-3:
+
 	/* Set EFER.LME=1 as a precaution in case hypervsior pulls the rug */
 	movl	$MSR_EFER, %ecx
 	rdmsr
@@ -624,26 +604,9 @@ SYM_CODE_START(trampoline_32bit_src)
 	jc	1f
 	wrmsr
 1:
-#ifdef CONFIG_X86_MCE
-	/*
-	 * Preserve CR4.MCE if the kernel will enable #MC support.
-	 * Clearing MCE may fault in some environments (that also force #MC
-	 * support). Any machine check that occurs before #MC support is fully
-	 * configured will crash the system regardless of the CR4.MCE value set
-	 * here.
-	 */
+	/* Toggle CR4.LA57 */
 	movl	%cr4, %eax
-	andl	$X86_CR4_MCE, %eax
-#else
-	movl	$0, %eax
-#endif
-
-	/* Enable PAE and LA57 (if required) paging modes */
-	orl	$X86_CR4_PAE, %eax
-	testl	%esi, %esi
-	jz	1f
-	orl	$X86_CR4_LA57, %eax
-1:
+	btcl	$X86_CR4_LA57_BIT, %eax
 	movl	%eax, %cr4
 
 	/* Enable paging again. */
arch/x86/boot/compressed/pgtable_64.c +9 -13
@@ -103,7 +103,7 @@ static unsigned long find_trampoline_pla
 
 asmlinkage void configure_5level_paging(struct boot_params *bp)
 {
-	void (*toggle_la57)(void *trampoline, bool enable_5lvl);
+	void (*toggle_la57)(void *trampoline);
 	bool l5_required = false;
 
 	/* Initialize boot_params. Required for cmdline_find_option_bool(). */
@@ -133,6 +133,13 @@ asmlinkage void configure_5level_paging(
 		ptrs_per_p4d = 512;
 	}
 
+	/*
+	 * The trampoline will not be used if the paging mode is already set to
+	 * the desired one.
+	 */
+	if (l5_required == !!(native_read_cr4() & X86_CR4_LA57))
+		return;
+
 	trampoline_32bit = (unsigned long *)find_trampoline_placement();
 
 	/* Preserve trampoline memory */
@@ -160,18 +167,8 @@ asmlinkage void configure_5level_paging(
 	 *
 	 * The new page table will be used by trampoline code for switching
 	 * from 4- to 5-level paging or vice versa.
-	 *
-	 * If switching is not required, the page table is unused: trampoline
-	 * code wouldn't touch CR3.
 	 */
 
-	/*
-	 * We are not going to use the page table in trampoline memory if we
-	 * are already in the desired paging mode.
-	 */
-	if (l5_required == !!(native_read_cr4() & X86_CR4_LA57))
-		goto out;
-
 	if (l5_required) {
 		/*
 		 * For 4- to 5-level paging transition, set up current CR3 as
@@ -194,8 +191,7 @@ asmlinkage void configure_5level_paging(
 		       (void *)src, PAGE_SIZE);
 	}
 
-out:
-	toggle_la57(trampoline_32bit, l5_required);
+	toggle_la57(trampoline_32bit);
 }
 
 void cleanup_trampoline(void *pgtable)
author maintainer
#141 lore raw

PATCH 137/215 x86/decompressor: Pass pgtable address to trampoline directly

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit cb83cece57e1889109dd73ea08ee338668c9d1b8 upstream.

The only remaining use of the trampoline address by the trampoline itself is deriving the page table address from it, and this involves adding an offset of 0x0. So simplify this, and pass the new CR3 value directly.

This makes the fact that the page table happens to be at the start of the trampoline allocation an implementation detail of the caller.

---
 arch/x86/boot/compressed/head_64.S    |    8 ++++----
 arch/x86/boot/compressed/pgtable.h    |    2 --
 arch/x86/boot/compressed/pgtable_64.c |    9 ++++-----
 3 files changed, 8 insertions(+), 11 deletions(-)
arch/x86/boot/compressed/head_64.S +4 -4
@@ -539,8 +539,9 @@ SYM_FUNC_END(.Lrelocated)
  * running in 64-bit mode.
  *
  * Return address is at the top of the stack (might be above 4G).
- * The first argument (EDI) contains the 32-bit addressable base of the
- * trampoline memory.
+ * The first argument (EDI) contains the address of the temporary PGD level
+ * page table in 32-bit addressable memory which will be programmed into
+ * register CR3.
  */
 	.section ".rodata", "a", @progbits
 SYM_CODE_START(trampoline_32bit_src)
@@ -593,8 +594,7 @@ SYM_CODE_START(trampoline_32bit_src)
 	movl	%eax, %cr0
 
 	/* Point CR3 to the trampoline's new top level page table */
-	leal	TRAMPOLINE_32BIT_PGTABLE_OFFSET(%edi), %eax
-	movl	%eax, %cr3
+	movl	%edi, %cr3
 
 	/* Set EFER.LME=1 as a precaution in case hypervsior pulls the rug */
 	movl	$MSR_EFER, %ecx
arch/x86/boot/compressed/pgtable.h +0 -2
@@ -3,8 +3,6 @@
 
 #define TRAMPOLINE_32BIT_SIZE		(2 * PAGE_SIZE)
 
-#define TRAMPOLINE_32BIT_PGTABLE_OFFSET	0
-
 #define TRAMPOLINE_32BIT_CODE_OFFSET	PAGE_SIZE
 #define TRAMPOLINE_32BIT_CODE_SIZE	0xA0
 
arch/x86/boot/compressed/pgtable_64.c +4 -5
@@ -103,7 +103,7 @@ static unsigned long find_trampoline_pla
 
 asmlinkage void configure_5level_paging(struct boot_params *bp)
 {
-	void (*toggle_la57)(void *trampoline);
+	void (*toggle_la57)(void *cr3);
 	bool l5_required = false;
 
 	/* Initialize boot_params. Required for cmdline_find_option_bool(). */
@@ -174,7 +174,7 @@ asmlinkage void configure_5level_paging(
 		 * For 4- to 5-level paging transition, set up current CR3 as
 		 * the first and the only entry in a new top-level page table.
 		 */
-		trampoline_32bit[TRAMPOLINE_32BIT_PGTABLE_OFFSET] = __native_read_cr3() | _PAGE_TABLE_NOENC;
+		*trampoline_32bit = __native_read_cr3() | _PAGE_TABLE_NOENC;
 	} else {
 		unsigned long src;
 
@@ -187,8 +187,7 @@ asmlinkage void configure_5level_paging(
 		 * may be above 4G.
 		 */
 		src = *(unsigned long *)__native_read_cr3() & PAGE_MASK;
-		memcpy(trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET / sizeof(unsigned long),
-		       (void *)src, PAGE_SIZE);
+		memcpy(trampoline_32bit, (void *)src, PAGE_SIZE);
 	}
 
 	toggle_la57(trampoline_32bit);
@@ -198,7 +197,7 @@ void cleanup_trampoline(void *pgtable)
 {
 	void *trampoline_pgtable;
 
-	trampoline_pgtable = trampoline_32bit + TRAMPOLINE_32BIT_PGTABLE_OFFSET / sizeof(unsigned long);
+	trampoline_pgtable = trampoline_32bit;
 
 	/*
 	 * Move the top level page table out of trampoline memory,
author maintainer
#142 lore raw

PATCH 138/215 x86/decompressor: Merge trampoline cleanup with switching code

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit 03dda95137d3247564854ad9032c0354273a159d upstream.

Now that the trampoline setup code and the actual invocation of it are all done from the C routine, the trampoline cleanup can be merged into it as well, instead of returning to asm just to call another C function.

---
 arch/x86/boot/compressed/head_64.S    |   14 ++++----------
 arch/x86/boot/compressed/pgtable_64.c |   18 ++++--------------
 2 files changed, 8 insertions(+), 24 deletions(-)
arch/x86/boot/compressed/head_64.S +4 -10
@@ -433,20 +433,14 @@ SYM_CODE_START(startup_64)
 	 * a trampoline in 32-bit addressable memory if the current number does
 	 * not match the desired number.
 	 *
-	 * Pass the boot_params pointer as the first argument.
+	 * Pass the boot_params pointer as the first argument. The second
+	 * argument is the relocated address of the page table to use instead
+	 * of the page table in trampoline memory (if required).
 	 */
 	movq	%r15, %rdi
+	leaq	rva(top_pgtable)(%rbx), %rsi
 	call	configure_5level_paging
 
-	/*
-	 * cleanup_trampoline() would restore trampoline memory.
-	 *
-	 * RDI is address of the page table to use instead of page table
-	 * in trampoline memory (if required).
-	 */
-	leaq	rva(top_pgtable)(%rbx), %rdi
-	call	cleanup_trampoline
-
 	/* Zero EFLAGS */
 	pushq	$0
 	popfq
arch/x86/boot/compressed/pgtable_64.c +4 -14
@@ -101,7 +101,7 @@ static unsigned long find_trampoline_pla
 	return bios_start - TRAMPOLINE_32BIT_SIZE;
 }
 
-asmlinkage void configure_5level_paging(struct boot_params *bp)
+asmlinkage void configure_5level_paging(struct boot_params *bp, void *pgtable)
 {
 	void (*toggle_la57)(void *cr3);
 	bool l5_required = false;
@@ -191,22 +191,12 @@ asmlinkage void configure_5level_paging(
 	}
 
 	toggle_la57(trampoline_32bit);
-}
-
-void cleanup_trampoline(void *pgtable)
-{
-	void *trampoline_pgtable;
-
-	trampoline_pgtable = trampoline_32bit;
 
 	/*
-	 * Move the top level page table out of trampoline memory,
-	 * if it's there.
+	 * Move the top level page table out of trampoline memory.
 	 */
-	if ((void *)__native_read_cr3() == trampoline_pgtable) {
-		memcpy(pgtable, trampoline_pgtable, PAGE_SIZE);
-		native_write_cr3((unsigned long)pgtable);
-	}
+	memcpy(pgtable, trampoline_32bit, PAGE_SIZE);
+	native_write_cr3((unsigned long)pgtable);
 
 	/* Restore trampoline memory */
 	memcpy(trampoline_32bit, trampoline_save, TRAMPOLINE_32BIT_SIZE);
author maintainer
#121 lore raw

PATCH 121/215 x86/boot/compressed: Move startup32_load_idt() out of head_64.S

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ard Biesheuvel <[email protected]>

commit 9ea813be3d345dfb8ac5bf6fbb29e6a63647a39d upstream.

Now that startup32_load_idt() has been refactored into an ordinary callable function, move it into mem-encrypt.S where it belongs.

---
 arch/x86/boot/compressed/head_64.S     |   72 ---------------------------------
 arch/x86/boot/compressed/mem_encrypt.S |   72 ++++++++++++++++++++++++++++++++-
 2 files changed, 71 insertions(+), 73 deletions(-)
arch/x86/boot/compressed/head_64.S +0 -72
@@ -723,78 +723,6 @@ SYM_DATA_START(boot_idt)
 	.endr
 SYM_DATA_END_LABEL(boot_idt, SYM_L_GLOBAL, boot_idt_end)
 
-#ifdef CONFIG_AMD_MEM_ENCRYPT
-SYM_DATA_START(boot32_idt_desc)
-	.word   boot32_idt_end - boot32_idt - 1
-	.long   0
-SYM_DATA_END(boot32_idt_desc)
-	.balign 8
-SYM_DATA_START(boot32_idt)
-	.rept 32
-	.quad 0
-	.endr
-SYM_DATA_END_LABEL(boot32_idt, SYM_L_GLOBAL, boot32_idt_end)
-
-	.text
-	.code32
-/*
- * Write an IDT entry into boot32_idt
- *
- * Parameters:
- *
- * %eax:	Handler address
- * %edx:	Vector number
- * %ecx:	IDT address
- */
-SYM_FUNC_START_LOCAL(startup32_set_idt_entry)
-	/* IDT entry address to %ecx */
-	leal	(%ecx, %edx, 8), %ecx
-
-	/* Build IDT entry, lower 4 bytes */
-	movl    %eax, %edx
-	andl    $0x0000ffff, %edx		# Target code segment offset [15:0]
-	orl	$(__KERNEL32_CS << 16), %edx	# Target code segment selector
-
-	/* Store lower 4 bytes to IDT */
-	movl    %edx, (%ecx)
-
-	/* Build IDT entry, upper 4 bytes */
-	movl    %eax, %edx
-	andl    $0xffff0000, %edx	# Target code segment offset [31:16]
-	orl     $0x00008e00, %edx	# Present, Type 32-bit Interrupt Gate
-
-	/* Store upper 4 bytes to IDT */
-	movl    %edx, 4(%ecx)
-
-	RET
-SYM_FUNC_END(startup32_set_idt_entry)
-
-SYM_FUNC_START(startup32_load_idt)
-	push	%ebp
-	push	%ebx
-
-	call	1f
-1:	pop	%ebp
-
-	leal    (boot32_idt - 1b)(%ebp), %ebx
-
-	/* #VC handler */
-	leal    (startup32_vc_handler - 1b)(%ebp), %eax
-	movl    $X86_TRAP_VC, %edx
-	movl	%ebx, %ecx
-	call    startup32_set_idt_entry
-
-	/* Load IDT */
-	leal	(boot32_idt_desc - 1b)(%ebp), %ecx
-	movl	%ebx, 2(%ecx)
-	lidt    (%ecx)
-
-	pop	%ebx
-	pop	%ebp
-	RET
-SYM_FUNC_END(startup32_load_idt)
-#endif
-
 /*
  * Check for the correct C-bit position when the startup_32 boot-path is used.
  *
arch/x86/boot/compressed/mem_encrypt.S +71 -1

94 lines not on this page · raw message