[PATCH AUTOSEL 4.19 044/219] mwifiex: fix potential NULL dereference and use after free

[PATCH AUTOSEL 4.19 044/219] mwifiex: fix potential NULL dereference and use after free

[Sasha Levin]

From: Pan Bian <bianpan2016@163.com>

[ Upstream commit 1dcd9429212b98bea87fc6ec92fb50bf5953eb47 ]

There are two defects: (1) passing a NULL bss to
mwifiex_save_hidden_ssid_channels will result in NULL dereference,
(2) using bss after dropping the reference to it via cfg80211_put_bss.
To fix them, the patch moves the buggy code to the branch that bss is
not NULL and puts it before cfg80211_put_bss.

Signed-off-by: Pan Bian <bianpan2016@163.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/marvell/mwifiex/scan.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c
index ed27147efcb37..dd02bbd9544e7 100644
--- a/drivers/net/wireless/marvell/mwifiex/scan.c
+++ b/drivers/net/wireless/marvell/mwifiex/scan.c
@@ -1906,15 +1906,17 @@ mwifiex_parse_single_response_buf(struct mwifiex_private *priv, u8 **bss_info,
 					    ETH_ALEN))
 					mwifiex_update_curr_bss_params(priv,
 								       bss);
-				cfg80211_put_bss(priv->wdev.wiphy, bss);
-			}
 
-			if ((chan->flags & IEEE80211_CHAN_RADAR) ||
-			    (chan->flags & IEEE80211_CHAN_NO_IR)) {
-				mwifiex_dbg(adapter, INFO,
-					    "radar or passive channel %d\n",
-					    channel);
-				mwifiex_save_hidden_ssid_channels(priv, bss);
+				if ((chan->flags & IEEE80211_CHAN_RADAR) ||
+				    (chan->flags & IEEE80211_CHAN_NO_IR)) {
+					mwifiex_dbg(adapter, INFO,
+						    "radar or passive channel %d\n",
+						    channel);
+					mwifiex_save_hidden_ssid_channels(priv,
+									  bss);
+				}
+
+				cfg80211_put_bss(priv->wdev.wiphy, bss);
 			}
 		}
 	} else {
-- 
2.20.1

[PATCH AUTOSEL 4.19 045/219] mwifiex: debugfs: correct histogram spacing, formatting

[Sasha Levin]

From: Brian Norris <briannorris@chromium.org>

[ Upstream commit 4cb777c64e030778c569f605398d7604d8aabc0f ]

Currently, snippets of this file look like:

rx rates (in Mbps): 0=1M   1=2M2=5.5M  3=11M   4=6M   5=9M  6=12M
7=18M  8=24M  9=36M  10=48M  11=54M12-27=MCS0-15(BW20) 28-43=MCS0-15(BW40)
44-53=MCS0-9(VHT:BW20)54-63=MCS0-9(VHT:BW40)64-73=MCS0-9(VHT:BW80)
...
noise_flr[--96dBm] = 22
noise_flr[--95dBm] = 149
noise_flr[--94dBm] = 9
noise_flr[--93dBm] = 2

We're missing some spaces, and we're adding a minus sign ('-') on values
that are already negative signed integers.

Signed-off-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/marvell/mwifiex/debugfs.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/debugfs.c b/drivers/net/wireless/marvell/mwifiex/debugfs.c
index cce70252fd96b..cbe4493b32664 100644
--- a/drivers/net/wireless/marvell/mwifiex/debugfs.c
+++ b/drivers/net/wireless/marvell/mwifiex/debugfs.c
@@ -273,15 +273,13 @@ mwifiex_histogram_read(struct file *file, char __user *ubuf,
 		     "total samples = %d\n",
 		     atomic_read(&phist_data->num_samples));
 
-	p += sprintf(p, "rx rates (in Mbps): 0=1M   1=2M");
-	p += sprintf(p, "2=5.5M  3=11M   4=6M   5=9M  6=12M\n");
-	p += sprintf(p, "7=18M  8=24M  9=36M  10=48M  11=54M");
-	p += sprintf(p, "12-27=MCS0-15(BW20) 28-43=MCS0-15(BW40)\n");
+	p += sprintf(p,
+		     "rx rates (in Mbps): 0=1M   1=2M 2=5.5M  3=11M   4=6M   5=9M  6=12M\n"
+		     "7=18M  8=24M  9=36M  10=48M  11=54M 12-27=MCS0-15(BW20) 28-43=MCS0-15(BW40)\n");
 
 	if (ISSUPP_11ACENABLED(priv->adapter->fw_cap_info)) {
-		p += sprintf(p, "44-53=MCS0-9(VHT:BW20)");
-		p += sprintf(p, "54-63=MCS0-9(VHT:BW40)");
-		p += sprintf(p, "64-73=MCS0-9(VHT:BW80)\n\n");
+		p += sprintf(p,
+			     "44-53=MCS0-9(VHT:BW20) 54-63=MCS0-9(VHT:BW40) 64-73=MCS0-9(VHT:BW80)\n\n");
 	} else {
 		p += sprintf(p, "\n");
 	}
@@ -310,7 +308,7 @@ mwifiex_histogram_read(struct file *file, char __user *ubuf,
 	for (i = 0; i < MWIFIEX_MAX_NOISE_FLR; i++) {
 		value = atomic_read(&phist_data->noise_flr[i]);
 		if (value)
-			p += sprintf(p, "noise_flr[-%02ddBm] = %d\n",
+			p += sprintf(p, "noise_flr[%02ddBm] = %d\n",
 				(int)(i-128), value);
 	}
 	for (i = 0; i < MWIFIEX_MAX_SIG_STRENGTH; i++) {
-- 
2.20.1

[PATCH AUTOSEL 4.19 046/219] brcmfmac: set F2 watermark to 256 for 4373

[Sasha Levin]

From: Wright Feng <wright.feng@cypress.com>

[ Upstream commit e1a08730eeb0bad4d82c3bc40e74854872de618d ]

We got SDIO_CRC_ERROR with 4373 on SDR104 when doing bi-directional
throughput test. Enable watermark to 256 to guarantee the operation
stability.

Reviewed-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Wright Feng <wright.feng@cypress.com>
Signed-off-by: Chi-Hsien Lin <chi-hsien.lin@cypress.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../broadcom/brcm80211/brcmfmac/sdio.c        | 26 +++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index 53e4962ceb8ae..e487dd78cc024 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -49,6 +49,10 @@
 #define DCMD_RESP_TIMEOUT	msecs_to_jiffies(2500)
 #define CTL_DONE_TIMEOUT	msecs_to_jiffies(2500)
 
+/* watermark expressed in number of words */
+#define DEFAULT_F2_WATERMARK    0x8
+#define CY_4373_F2_WATERMARK    0x40
+
 #ifdef DEBUG
 
 #define BRCMF_TRAP_INFO_SIZE	80
@@ -138,6 +142,8 @@ struct rte_console {
 /* 1: isolate internal sdio signals, put external pads in tri-state; requires
  * sdio bus power cycle to clear (rev 9) */
 #define SBSDIO_DEVCTL_PADS_ISO		0x08
+/* 1: enable F2 Watermark */
+#define SBSDIO_DEVCTL_F2WM_ENAB		0x10
 /* Force SD->SB reset mapping (rev 11) */
 #define SBSDIO_DEVCTL_SB_RST_CTL	0x30
 /*   Determined by CoreControl bit */
@@ -4060,6 +4066,7 @@ static void brcmf_sdio_firmware_callback(struct device *dev, int err,
 	void *nvram;
 	u32 nvram_len;
 	u8 saveclk;
+	u8 devctl;
 
 	brcmf_dbg(TRACE, "Enter: dev=%s, err=%d\n", dev_name(dev), err);
 
@@ -4115,8 +4122,23 @@ static void brcmf_sdio_firmware_callback(struct device *dev, int err,
 		brcmf_sdiod_writel(sdiod, core->base + SD_REG(hostintmask),
 				   bus->hostintmask, NULL);
 
-
-		brcmf_sdiod_writeb(sdiod, SBSDIO_WATERMARK, 8, &err);
+		switch (sdiod->func1->device) {
+		case SDIO_DEVICE_ID_CYPRESS_4373:
+			brcmf_dbg(INFO, "set F2 watermark to 0x%x*4 bytes\n",
+				  CY_4373_F2_WATERMARK);
+			brcmf_sdiod_writeb(sdiod, SBSDIO_WATERMARK,
+					   CY_4373_F2_WATERMARK, &err);
+			devctl = brcmf_sdiod_readb(sdiod, SBSDIO_DEVICE_CTL,
+						   &err);
+			devctl |= SBSDIO_DEVCTL_F2WM_ENAB;
+			brcmf_sdiod_writeb(sdiod, SBSDIO_DEVICE_CTL, devctl,
+					   &err);
+			break;
+		default:
+			brcmf_sdiod_writeb(sdiod, SBSDIO_WATERMARK,
+					   DEFAULT_F2_WATERMARK, &err);
+			break;
+		}
 	} else {
 		/* Disable F2 again */
 		sdio_disable_func(sdiod->func2);
-- 
2.20.1

[PATCH AUTOSEL 4.19 047/219] brcmfmac: set SDIO F1 MesBusyCtrl for CYW4373

[Sasha Levin]

From: Madhan Mohan R <MadhanMohan.R@cypress.com>

[ Upstream commit 58e4bbea0c1d9b5ace11df968c5dc096ce052a73 ]

Along with F2 watermark (existing) configuration, F1 MesBusyCtrl
should be enabled & sdio device RX FIFO watermark should be
configured to avoid overflow errors.

Reviewed-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Madhan Mohan R <madhanmohan.r@cypress.com>
Signed-off-by: Chi-Hsien Lin <chi-hsien.lin@cypress.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c | 3 +++
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h | 9 ++++++++-
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index e487dd78cc024..abaed2fa2defd 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -4133,6 +4133,9 @@ static void brcmf_sdio_firmware_callback(struct device *dev, int err,
 			devctl |= SBSDIO_DEVCTL_F2WM_ENAB;
 			brcmf_sdiod_writeb(sdiod, SBSDIO_DEVICE_CTL, devctl,
 					   &err);
+			brcmf_sdiod_writeb(sdiod, SBSDIO_FUNC1_MESBUSYCTRL,
+					   CY_4373_F2_WATERMARK |
+					   SBSDIO_MESBUSYCTRL_ENAB, &err);
 			break;
 		default:
 			brcmf_sdiod_writeb(sdiod, SBSDIO_WATERMARK,
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
index 7faed831f07d5..34b031154da93 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
@@ -77,7 +77,7 @@
 #define SBSDIO_GPIO_OUT			0x10006
 /* gpio enable */
 #define SBSDIO_GPIO_EN			0x10007
-/* rev < 7, watermark for sdio device */
+/* rev < 7, watermark for sdio device TX path */
 #define SBSDIO_WATERMARK		0x10008
 /* control busy signal generation */
 #define SBSDIO_DEVICE_CTL		0x10009
@@ -104,6 +104,13 @@
 #define SBSDIO_FUNC1_RFRAMEBCHI		0x1001C
 /* MesBusyCtl (rev 11) */
 #define SBSDIO_FUNC1_MESBUSYCTRL	0x1001D
+/* Watermark for sdio device RX path */
+#define SBSDIO_MESBUSY_RXFIFO_WM_MASK	0x7F
+#define SBSDIO_MESBUSY_RXFIFO_WM_SHIFT	0
+/* Enable busy capability for MES access */
+#define SBSDIO_MESBUSYCTRL_ENAB		0x80
+#define SBSDIO_MESBUSYCTRL_ENAB_SHIFT	7
+
 /* Sdio Core Rev 12 */
 #define SBSDIO_FUNC1_WAKEUPCTRL		0x1001E
 #define SBSDIO_FUNC1_WCTRL_ALPWAIT_MASK		0x1
-- 
2.20.1

[PATCH AUTOSEL 4.19 048/219] rtl818x: fix potential use after free

[Sasha Levin]

From: Pan Bian <bianpan2016@163.com>

[ Upstream commit afbb1947db94eacc5a13302eee88a9772fb78935 ]

entry is released via usb_put_urb just after calling usb_submit_urb.
However, entry is used if the submission fails, resulting in a use after
free bug. The patch fixes this.

Signed-off-by: Pan Bian <bianpan2016@163.com>
ACKed-by: Larry Finger <Larry.Finger@lwfinger.net>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c b/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c
index 9a1d15b3ce453..518caaaf8a987 100644
--- a/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c
+++ b/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c
@@ -444,12 +444,13 @@ static int rtl8187_init_urbs(struct ieee80211_hw *dev)
 		skb_queue_tail(&priv->rx_queue, skb);
 		usb_anchor_urb(entry, &priv->anchored);
 		ret = usb_submit_urb(entry, GFP_KERNEL);
-		usb_put_urb(entry);
 		if (ret) {
 			skb_unlink(skb, &priv->rx_queue);
 			usb_unanchor_urb(entry);
+			usb_put_urb(entry);
 			goto err;
 		}
+		usb_put_urb(entry);
 	}
 	return ret;
 
-- 
2.20.1

[PATCH AUTOSEL 4.19 059/219] iwlwifi: move iwl_nvm_check_version() into dvm

[Sasha Levin]

From: Luca Coelho <luciano.coelho@intel.com>

[ Upstream commit 64866e5da1eabd0c52ff45029b245f5465920031 ]

This function is only half-used by mvm (i.e. only the nvm_version part
matters, since the calibration version is irrelevant), so it's
pointless to export it from iwlwifi.  If mvm uses this function, it
has the additional complexity of setting the calib version to a bogus
value on all cfg structs.

To avoid this, move the function to dvm and make a simple comparison
of the nvm_version in mvm instead.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/intel/iwlwifi/dvm/main.c | 17 +++++++++++++++++
 .../wireless/intel/iwlwifi/iwl-eeprom-parse.c | 19 -------------------
 .../wireless/intel/iwlwifi/iwl-eeprom-parse.h |  5 ++---
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c   |  4 +++-
 4 files changed, 22 insertions(+), 23 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/main.c b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
index 030482b357a3c..06dd4e81b7374 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/main.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
@@ -1227,6 +1227,23 @@ static int iwl_eeprom_init_hw_params(struct iwl_priv *priv)
 	return 0;
 }
 
+static int iwl_nvm_check_version(struct iwl_nvm_data *data,
+				 struct iwl_trans *trans)
+{
+	if (data->nvm_version >= trans->cfg->nvm_ver ||
+	    data->calib_version >= trans->cfg->nvm_calib_ver) {
+		IWL_DEBUG_INFO(trans, "device EEPROM VER=0x%x, CALIB=0x%x\n",
+			       data->nvm_version, data->calib_version);
+		return 0;
+	}
+
+	IWL_ERR(trans,
+		"Unsupported (too old) EEPROM VER=0x%x < 0x%x CALIB=0x%x < 0x%x\n",
+		data->nvm_version, trans->cfg->nvm_ver,
+		data->calib_version,  trans->cfg->nvm_calib_ver);
+	return -EINVAL;
+}
+
 static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans,
 						 const struct iwl_cfg *cfg,
 						 const struct iwl_fw *fw,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c
index a4c96215933ba..a59bab8345f4e 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c
@@ -928,22 +928,3 @@ iwl_parse_eeprom_data(struct device *dev, const struct iwl_cfg *cfg,
 	return NULL;
 }
 IWL_EXPORT_SYMBOL(iwl_parse_eeprom_data);
-
-/* helper functions */
-int iwl_nvm_check_version(struct iwl_nvm_data *data,
-			     struct iwl_trans *trans)
-{
-	if (data->nvm_version >= trans->cfg->nvm_ver ||
-	    data->calib_version >= trans->cfg->nvm_calib_ver) {
-		IWL_DEBUG_INFO(trans, "device EEPROM VER=0x%x, CALIB=0x%x\n",
-			       data->nvm_version, data->calib_version);
-		return 0;
-	}
-
-	IWL_ERR(trans,
-		"Unsupported (too old) EEPROM VER=0x%x < 0x%x CALIB=0x%x < 0x%x\n",
-		data->nvm_version, trans->cfg->nvm_ver,
-		data->calib_version,  trans->cfg->nvm_calib_ver);
-	return -EINVAL;
-}
-IWL_EXPORT_SYMBOL(iwl_nvm_check_version);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.h b/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.h
index 8be50ed12300f..c59dd47cf15d3 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.h
@@ -7,6 +7,7 @@
  *
  * Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2015 Intel Mobile Communications GmbH
+ * Copyright (C) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -33,6 +34,7 @@
  *
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2015 Intel Mobile Communications GmbH
+ * Copyright (C) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -122,9 +124,6 @@ struct iwl_nvm_data *
 iwl_parse_eeprom_data(struct device *dev, const struct iwl_cfg *cfg,
 		      const u8 *eeprom, size_t eeprom_size);
 
-int iwl_nvm_check_version(struct iwl_nvm_data *data,
-			  struct iwl_trans *trans);
-
 int iwl_init_sband_channels(struct iwl_nvm_data *data,
 			    struct ieee80211_supported_band *sband,
 			    int n_channels, enum nl80211_band band);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 2eba6d6f367f8..9808d954dca29 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -547,7 +547,9 @@ int iwl_run_init_mvm_ucode(struct iwl_mvm *mvm, bool read_nvm)
 	if (mvm->nvm_file_name)
 		iwl_mvm_load_nvm_to_nic(mvm);
 
-	WARN_ON(iwl_nvm_check_version(mvm->nvm_data, mvm->trans));
+	WARN_ONCE(mvm->nvm_data->nvm_version < mvm->trans->cfg->nvm_ver,
+		  "Too old NVM version (0x%0x, required = 0x%0x)",
+		  mvm->nvm_data->nvm_version, mvm->trans->cfg->nvm_ver);
 
 	/*
 	 * abort after reading the nvm in case RF Kill is on, we will complete
-- 
2.20.1

[PATCH AUTOSEL 4.19 060/219] iwlwifi: mvm: force TCM re-evaluation on TCM resume

[Sasha Levin]

From: Avraham Stern <avraham.stern@intel.com>

[ Upstream commit 7bc2468277033e05401d5f8fd48a772f407338c2 ]

When traffic load is not low or low latency is active, TCM schedules
re-evaluation work so in case traffic stops TCM will detect that
traffic load has become low or that low latency is no longer active.
However, if TCM is paused when the re-evaluation work runs, it does
not re-evaluate and the re-evaluation work is no longer scheduled.
As a result, TCM will not indicate that low latency is no longer
active or that traffic load is low when traffic stops.

Fix this by forcing TCM re-evaluation when TCM is resumed in case
low latency is active or traffic load is not low.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/intel/iwlwifi/mvm/utils.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
index 6a5349401aa99..00712205c05f2 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
@@ -1804,6 +1804,7 @@ void iwl_mvm_pause_tcm(struct iwl_mvm *mvm, bool with_cancel)
 void iwl_mvm_resume_tcm(struct iwl_mvm *mvm)
 {
 	int mac;
+	bool low_latency = false;
 
 	spin_lock_bh(&mvm->tcm.lock);
 	mvm->tcm.ts = jiffies;
@@ -1815,10 +1816,23 @@ void iwl_mvm_resume_tcm(struct iwl_mvm *mvm)
 		memset(&mdata->tx.pkts, 0, sizeof(mdata->tx.pkts));
 		memset(&mdata->rx.airtime, 0, sizeof(mdata->rx.airtime));
 		memset(&mdata->tx.airtime, 0, sizeof(mdata->tx.airtime));
+
+		if (mvm->tcm.result.low_latency[mac])
+			low_latency = true;
 	}
 	/* The TCM data needs to be reset before "paused" flag changes */
 	smp_mb();
 	mvm->tcm.paused = false;
+
+	/*
+	 * if the current load is not low or low latency is active, force
+	 * re-evaluation to cover the case of no traffic.
+	 */
+	if (mvm->tcm.result.global_load > IWL_MVM_TRAFFIC_LOW)
+		schedule_delayed_work(&mvm->tcm.work, MVM_TCM_PERIOD);
+	else if (low_latency)
+		schedule_delayed_work(&mvm->tcm.work, MVM_LL_PERIOD);
+
 	spin_unlock_bh(&mvm->tcm.lock);
 }
 
-- 
2.20.1

[PATCH AUTOSEL 4.19 061/219] iwlwifi: pcie: fix erroneous print

[Sasha Levin]

From: Sara Sharon <sara.sharon@intel.com>

[ Upstream commit 0916224eaa77bff0fbbc747961d550ff8db45457 ]

When removing the driver, the following flow can happen:
1. host command is in progress, for example at index 68.
2. RX interrupt is received with the response.
3. Before it is processed, the remove flow kicks in, and
   calls iwl_pcie_txq_unmap. The function cleans all DMA,
   and promotes the read pointer to 69.
4. RX thread proceeds with the processing, and is calling
   iwl_pcie_cmdq_reclaim, which will print this error:
   iwl_pcie_cmdq_reclaim: Read index for DMA queue txq id (0),
   index 4 is out of range [0-256] 69 69.

Detect this situation, and avoid the print. Change it to
warning while at it, to make such issues more noticeable
in the future.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/intel/iwlwifi/pcie/tx.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index 42fdb7970cfdc..7cba4c37c66fd 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -1247,11 +1247,11 @@ static void iwl_pcie_cmdq_reclaim(struct iwl_trans *trans, int txq_id, int idx)
 
 	if (idx >= trans->cfg->base_params->max_tfd_queue_size ||
 	    (!iwl_queue_used(txq, idx))) {
-		IWL_ERR(trans,
-			"%s: Read index for DMA queue txq id (%d), index %d is out of range [0-%d] %d %d.\n",
-			__func__, txq_id, idx,
-			trans->cfg->base_params->max_tfd_queue_size,
-			txq->write_ptr, txq->read_ptr);
+		WARN_ONCE(test_bit(txq_id, trans_pcie->queue_used),
+			  "%s: Read index for DMA queue txq id (%d), index %d is out of range [0-%d] %d %d.\n",
+			  __func__, txq_id, idx,
+			  trans->cfg->base_params->max_tfd_queue_size,
+			  txq->write_ptr, txq->read_ptr);
 		return;
 	}
 
-- 
2.20.1

[PATCH AUTOSEL 4.19 062/219] iwlwifi: pcie: set cmd_len in the correct place

[Sasha Levin]

From: Sara Sharon <sara.sharon@intel.com>

[ Upstream commit 956343a61226e1af3d146386f70a059feb567d0c ]

command len is set too early in the code, since when building
AMSDU, the size changes. This causes the byte count table to
have the wrong size.

Fixes: a0ec0169b7a9 ("iwlwifi: support new tx api")
Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../net/wireless/intel/iwlwifi/pcie/tx-gen2.c | 24 +++++++++----------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index b99f33ff91230..a9e42f0437ccb 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -555,18 +555,6 @@ int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
 
 	spin_lock(&txq->lock);
 
-	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) {
-		struct iwl_tx_cmd_gen3 *tx_cmd_gen3 =
-			(void *)dev_cmd->payload;
-
-		cmd_len = le16_to_cpu(tx_cmd_gen3->len);
-	} else {
-		struct iwl_tx_cmd_gen2 *tx_cmd_gen2 =
-			(void *)dev_cmd->payload;
-
-		cmd_len = le16_to_cpu(tx_cmd_gen2->len);
-	}
-
 	if (iwl_queue_space(trans, txq) < txq->high_mark) {
 		iwl_stop_queue(trans, txq);
 
@@ -604,6 +592,18 @@ int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
 		return -1;
 	}
 
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) {
+		struct iwl_tx_cmd_gen3 *tx_cmd_gen3 =
+			(void *)dev_cmd->payload;
+
+		cmd_len = le16_to_cpu(tx_cmd_gen3->len);
+	} else {
+		struct iwl_tx_cmd_gen2 *tx_cmd_gen2 =
+			(void *)dev_cmd->payload;
+
+		cmd_len = le16_to_cpu(tx_cmd_gen2->len);
+	}
+
 	/* Set up entry for this TFD in Tx byte-count array */
 	iwl_pcie_gen2_update_byte_tbl(trans_pcie, txq, cmd_len,
 				      iwl_pcie_gen2_get_num_tbs(trans, tfd));
-- 
2.20.1

[PATCH AUTOSEL 4.19 067/219] VSOCK: bind to random port for VMADDR_PORT_ANY

[Sasha Levin]

From: Lepton Wu <ytht.net@gmail.com>

[ Upstream commit 8236b08cf50f85bbfaf48910a0b3ee68318b7c4b ]

The old code always starts from fixed port for VMADDR_PORT_ANY. Sometimes
when VMM crashed, there is still orphaned vsock which is waiting for
close timer, then it could cause connection time out for new started VM
if they are trying to connect to same port with same guest cid since the
new packets could hit that orphaned vsock. We could also fix this by doing
more in vhost_vsock_reset_orphans, but any way, it should be better to start
from a random local port instead of a fixed one.

Signed-off-by: Lepton Wu <ytht.net@gmail.com>
Reviewed-by: Jorgen Hansen <jhansen@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/vmw_vsock/af_vsock.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index b2724fb06bbbb..62ec9182f234d 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -107,6 +107,7 @@
 #include <linux/mutex.h>
 #include <linux/net.h>
 #include <linux/poll.h>
+#include <linux/random.h>
 #include <linux/skbuff.h>
 #include <linux/smp.h>
 #include <linux/socket.h>
@@ -480,9 +481,13 @@ static void vsock_pending_work(struct work_struct *work)
 static int __vsock_bind_stream(struct vsock_sock *vsk,
 			       struct sockaddr_vm *addr)
 {
-	static u32 port = LAST_RESERVED_PORT + 1;
+	static u32 port = 0;
 	struct sockaddr_vm new_addr;
 
+	if (!port)
+		port = LAST_RESERVED_PORT + 1 +
+			prandom_u32_max(U32_MAX - LAST_RESERVED_PORT);
+
 	vsock_addr_init(&new_addr, addr->svm_cid, addr->svm_port);
 
 	if (addr->svm_port == VMADDR_PORT_ANY) {
-- 
2.20.1

[PATCH AUTOSEL 4.19 087/219] net/mlx5: Continue driver initialization despite debugfs failure

[Sasha Levin]

From: Leon Romanovsky <leonro@mellanox.com>

[ Upstream commit 199fa087dc6b503baad06712716fac645a983e8a ]

The failure to create debugfs entry is unpleasant event, but not enough
to abort drier initialization. Align the mlx5_core code to debugfs design
and continue execution whenever debugfs_create_dir() successes or not.

Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 231ed508c240a..5fac00ea62457 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -859,11 +859,9 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 
 	priv->numa_node = dev_to_node(&dev->pdev->dev);
 
-	priv->dbg_root = debugfs_create_dir(dev_name(&pdev->dev), mlx5_debugfs_root);
-	if (!priv->dbg_root) {
-		dev_err(&pdev->dev, "Cannot create debugfs dir, aborting\n");
-		return -ENOMEM;
-	}
+	if (mlx5_debugfs_root)
+		priv->dbg_root =
+			debugfs_create_dir(pci_name(pdev), mlx5_debugfs_root);
 
 	err = mlx5_pci_enable_device(dev);
 	if (err) {
-- 
2.20.1

[PATCH AUTOSEL 4.19 088/219] netfilter: nf_nat_sip: fix RTP/RTCP source port translations

[Sasha Levin]

From: Alin Nastac <alin.nastac@gmail.com>

[ Upstream commit 8294059931448aa1ca112615bdffa3eab552c382 ]

Each media stream negotiation between 2 SIP peers will trigger creation
of 4 different expectations (2 RTP and 2 RTCP):
 - INVITE will create expectations for the media packets sent by the
   called peer
 - reply to the INVITE will create expectations for media packets sent
   by the caller

The dport used by these expectations usually match the ones selected
by the SIP peers, but they might get translated due to conflicts with
another expectation. When such event occur, it is important to do
this translation in both directions, dport translation on the receiving
path and sport translation on the sending path.

This commit fixes the sport translation when the peer requiring it is
also the one that starts the media stream. In this scenario, first media
stream packet is forwarded from LAN to WAN and will rely on
nf_nat_sip_expected() to do the necessary sport translation. However, the
expectation matched by this packet does not contain the necessary information
for doing SNAT, this data being stored in the paired expectation created by
the sender's SIP message (INVITE or reply to it).

Signed-off-by: Alin Nastac <alin.nastac@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/nf_nat_sip.c | 39 ++++++++++++++++++++++++++++++++++----
 1 file changed, 35 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c
index 1f30860749817..aa1be643d7a09 100644
--- a/net/netfilter/nf_nat_sip.c
+++ b/net/netfilter/nf_nat_sip.c
@@ -18,6 +18,7 @@
 
 #include <net/netfilter/nf_nat.h>
 #include <net/netfilter/nf_nat_helper.h>
+#include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_expect.h>
 #include <net/netfilter/nf_conntrack_seqadj.h>
@@ -316,6 +317,9 @@ static void nf_nat_sip_seq_adjust(struct sk_buff *skb, unsigned int protoff,
 static void nf_nat_sip_expected(struct nf_conn *ct,
 				struct nf_conntrack_expect *exp)
 {
+	struct nf_conn_help *help = nfct_help(ct->master);
+	struct nf_conntrack_expect *pair_exp;
+	int range_set_for_snat = 0;
 	struct nf_nat_range2 range;
 
 	/* This must be a fresh one. */
@@ -327,15 +331,42 @@ static void nf_nat_sip_expected(struct nf_conn *ct,
 	range.min_addr = range.max_addr = exp->saved_addr;
 	nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST);
 
-	/* Change src to where master sends to, but only if the connection
-	 * actually came from the same source. */
-	if (nf_inet_addr_cmp(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3,
+	/* Do media streams SRC manip according with the parameters
+	 * found in the paired expectation.
+	 */
+	if (exp->class != SIP_EXPECT_SIGNALLING) {
+		spin_lock_bh(&nf_conntrack_expect_lock);
+		hlist_for_each_entry(pair_exp, &help->expectations, lnode) {
+			if (pair_exp->tuple.src.l3num == nf_ct_l3num(ct) &&
+			    pair_exp->tuple.dst.protonum == ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum &&
+			    nf_inet_addr_cmp(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3, &pair_exp->saved_addr) &&
+			    ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.all == pair_exp->saved_proto.all) {
+				range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED);
+				range.min_proto.all = range.max_proto.all = pair_exp->tuple.dst.u.all;
+				range.min_addr = range.max_addr = pair_exp->tuple.dst.u3;
+				range_set_for_snat = 1;
+				break;
+			}
+		}
+		spin_unlock_bh(&nf_conntrack_expect_lock);
+	}
+
+	/* When no paired expectation has been found, change src to
+	 * where master sends to, but only if the connection actually came
+	 * from the same source.
+	 */
+	if (!range_set_for_snat &&
+	    nf_inet_addr_cmp(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3,
 			     &ct->master->tuplehash[exp->dir].tuple.src.u3)) {
 		range.flags = NF_NAT_RANGE_MAP_IPS;
 		range.min_addr = range.max_addr
 			= ct->master->tuplehash[!exp->dir].tuple.dst.u3;
-		nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC);
+		range_set_for_snat = 1;
 	}
+
+	/* Perform SRC manip. */
+	if (range_set_for_snat)
+		nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC);
 }
 
 static unsigned int nf_nat_sip_expect(struct sk_buff *skb, unsigned int protoff,
-- 
2.20.1

[PATCH AUTOSEL 4.19 090/219] bnxt_en: Return linux standard errors in bnxt_ethtool.c

[Sasha Levin]

From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>

[ Upstream commit 7c675421afef18253a86ffc383f57bc15ef32ea8 ]

Currently firmware specific errors are returned directly in flash_device
and reset ethtool hooks. Modify it to return linux standard errors
to userspace when flashing operations fail.

Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 56 +++++++++++++------
 1 file changed, 39 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index da9b876899963..eaa285bf908b9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1444,14 +1444,22 @@ static int bnxt_flash_nvram(struct net_device *dev,
 	rc = hwrm_send_message(bp, &req, sizeof(req), FLASH_NVRAM_TIMEOUT);
 	dma_free_coherent(&bp->pdev->dev, data_len, kmem, dma_handle);
 
+	if (rc == HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED) {
+		netdev_info(dev,
+			    "PF does not have admin privileges to flash the device\n");
+		rc = -EACCES;
+	} else if (rc) {
+		rc = -EIO;
+	}
 	return rc;
 }
 
 static int bnxt_firmware_reset(struct net_device *dev,
 			       u16 dir_type)
 {
-	struct bnxt *bp = netdev_priv(dev);
 	struct hwrm_fw_reset_input req = {0};
+	struct bnxt *bp = netdev_priv(dev);
+	int rc;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FW_RESET, -1, -1);
 
@@ -1491,7 +1499,15 @@ static int bnxt_firmware_reset(struct net_device *dev,
 		return -EINVAL;
 	}
 
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc == HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED) {
+		netdev_info(dev,
+			    "PF does not have admin privileges to reset the device\n");
+		rc = -EACCES;
+	} else if (rc) {
+		rc = -EIO;
+	}
+	return rc;
 }
 
 static int bnxt_flash_firmware(struct net_device *dev,
@@ -1698,9 +1714,9 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 	struct hwrm_nvm_install_update_output *resp = bp->hwrm_cmd_resp_addr;
 	struct hwrm_nvm_install_update_input install = {0};
 	const struct firmware *fw;
+	int rc, hwrm_err = 0;
 	u32 item_len;
 	u16 index;
-	int rc;
 
 	bnxt_hwrm_fw_set_time(bp);
 
@@ -1743,15 +1759,16 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 			memcpy(kmem, fw->data, fw->size);
 			modify.host_src_addr = cpu_to_le64(dma_handle);
 
-			rc = hwrm_send_message(bp, &modify, sizeof(modify),
-					       FLASH_PACKAGE_TIMEOUT);
+			hwrm_err = hwrm_send_message(bp, &modify,
+						     sizeof(modify),
+						     FLASH_PACKAGE_TIMEOUT);
 			dma_free_coherent(&bp->pdev->dev, fw->size, kmem,
 					  dma_handle);
 		}
 	}
 	release_firmware(fw);
-	if (rc)
-		return rc;
+	if (rc || hwrm_err)
+		goto err_exit;
 
 	if ((install_type & 0xffff) == 0)
 		install_type >>= 16;
@@ -1759,12 +1776,10 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 	install.install_type = cpu_to_le32(install_type);
 
 	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &install, sizeof(install),
-				INSTALL_PACKAGE_TIMEOUT);
-	if (rc) {
-		rc = -EOPNOTSUPP;
+	hwrm_err = _hwrm_send_message(bp, &install, sizeof(install),
+				      INSTALL_PACKAGE_TIMEOUT);
+	if (hwrm_err)
 		goto flash_pkg_exit;
-	}
 
 	if (resp->error_code) {
 		u8 error_code = ((struct hwrm_err_output *)resp)->cmd_err;
@@ -1772,12 +1787,11 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 		if (error_code == NVM_INSTALL_UPDATE_CMD_ERR_CODE_FRAG_ERR) {
 			install.flags |= cpu_to_le16(
 			       NVM_INSTALL_UPDATE_REQ_FLAGS_ALLOWED_TO_DEFRAG);
-			rc = _hwrm_send_message(bp, &install, sizeof(install),
-						INSTALL_PACKAGE_TIMEOUT);
-			if (rc) {
-				rc = -EOPNOTSUPP;
+			hwrm_err = _hwrm_send_message(bp, &install,
+						      sizeof(install),
+						      INSTALL_PACKAGE_TIMEOUT);
+			if (hwrm_err)
 				goto flash_pkg_exit;
-			}
 		}
 	}
 
@@ -1788,6 +1802,14 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 	}
 flash_pkg_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
+err_exit:
+	if (hwrm_err == HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED) {
+		netdev_info(dev,
+			    "PF does not have admin privileges to flash the device\n");
+		rc = -EACCES;
+	} else if (hwrm_err) {
+		rc = -EOPNOTSUPP;
+	}
 	return rc;
 }
 
-- 
2.20.1

[PATCH AUTOSEL 4.19 091/219] bnxt_en: Save ring statistics before reset.

[Sasha Levin]

From: Michael Chan <michael.chan@broadcom.com>

[ Upstream commit b8875ca356f1c0b17ec68be6666269373a62288e ]

With the current driver, the statistics reported by .ndo_get_stats64()
are reset when the device goes down.  Store a snapshot of the
rtnl_link_stats64 before shutdown.  This snapshot is added to the
current counters in .ndo_get_stats64() so that the counters will not
get reset when the device is down.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 57 +++++++++++++++++------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  1 +
 2 files changed, 44 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index c54a74de7b088..2f61175f5655a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7148,6 +7148,9 @@ static bool bnxt_drv_busy(struct bnxt *bp)
 		test_bit(BNXT_STATE_READ_STATS, &bp->state));
 }
 
+static void bnxt_get_ring_stats(struct bnxt *bp,
+				struct rtnl_link_stats64 *stats);
+
 static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,
 			     bool link_re_init)
 {
@@ -7173,6 +7176,9 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,
 	del_timer_sync(&bp->timer);
 	bnxt_free_skbs(bp);
 
+	/* Save ring stats before shutdown */
+	if (bp->bnapi)
+		bnxt_get_ring_stats(bp, &bp->net_stats_prev);
 	if (irq_re_init) {
 		bnxt_free_irq(bp);
 		bnxt_del_napi(bp);
@@ -7234,23 +7240,12 @@ static int bnxt_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	return -EOPNOTSUPP;
 }
 
-static void
-bnxt_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
+static void bnxt_get_ring_stats(struct bnxt *bp,
+				struct rtnl_link_stats64 *stats)
 {
-	u32 i;
-	struct bnxt *bp = netdev_priv(dev);
+	int i;
 
-	set_bit(BNXT_STATE_READ_STATS, &bp->state);
-	/* Make sure bnxt_close_nic() sees that we are reading stats before
-	 * we check the BNXT_STATE_OPEN flag.
-	 */
-	smp_mb__after_atomic();
-	if (!test_bit(BNXT_STATE_OPEN, &bp->state)) {
-		clear_bit(BNXT_STATE_READ_STATS, &bp->state);
-		return;
-	}
 
-	/* TODO check if we need to synchronize with bnxt_close path */
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 		struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
@@ -7279,6 +7274,40 @@ bnxt_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 
 		stats->tx_dropped += le64_to_cpu(hw_stats->tx_drop_pkts);
 	}
+}
+
+static void bnxt_add_prev_stats(struct bnxt *bp,
+				struct rtnl_link_stats64 *stats)
+{
+	struct rtnl_link_stats64 *prev_stats = &bp->net_stats_prev;
+
+	stats->rx_packets += prev_stats->rx_packets;
+	stats->tx_packets += prev_stats->tx_packets;
+	stats->rx_bytes += prev_stats->rx_bytes;
+	stats->tx_bytes += prev_stats->tx_bytes;
+	stats->rx_missed_errors += prev_stats->rx_missed_errors;
+	stats->multicast += prev_stats->multicast;
+	stats->tx_dropped += prev_stats->tx_dropped;
+}
+
+static void
+bnxt_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
+{
+	struct bnxt *bp = netdev_priv(dev);
+
+	set_bit(BNXT_STATE_READ_STATS, &bp->state);
+	/* Make sure bnxt_close_nic() sees that we are reading stats before
+	 * we check the BNXT_STATE_OPEN flag.
+	 */
+	smp_mb__after_atomic();
+	if (!test_bit(BNXT_STATE_OPEN, &bp->state)) {
+		clear_bit(BNXT_STATE_READ_STATS, &bp->state);
+		*stats = bp->net_stats_prev;
+		return;
+	}
+
+	bnxt_get_ring_stats(bp, stats);
+	bnxt_add_prev_stats(bp, stats);
 
 	if (bp->flags & BNXT_FLAG_PORT_STATS) {
 		struct rx_port_stats *rx = bp->hw_rx_port_stats;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index cf2d4a6583d55..f9e253b705ece 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1302,6 +1302,7 @@ struct bnxt {
 	void			*hwrm_cmd_resp_addr;
 	dma_addr_t		hwrm_cmd_resp_dma_addr;
 
+	struct rtnl_link_stats64	net_stats_prev;
 	struct rx_port_stats	*hw_rx_port_stats;
 	struct tx_port_stats	*hw_tx_port_stats;
 	struct rx_port_stats_ext	*hw_rx_port_stats_ext;
-- 
2.20.1

[PATCH AUTOSEL 4.19 092/219] bnxt_en: query force speeds before disabling autoneg mode.

[Sasha Levin]

From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>

[ Upstream commit 56d374624778652d2a999e18c87a25338b127b41 ]

With autoneg enabled, PHY loopback test fails. To disable autoneg,
driver needs to send a valid forced speed to FW. FW is not sending
async event for invalid speeds. To fix this, query forced speeds
and send the correct speed when disabling autoneg mode.

Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 22 ++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index eaa285bf908b9..2240c23b0a4c9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -2390,17 +2390,37 @@ static int bnxt_hwrm_mac_loopback(struct bnxt *bp, bool enable)
 	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 }
 
+static int bnxt_query_force_speeds(struct bnxt *bp, u16 *force_speeds)
+{
+	struct hwrm_port_phy_qcaps_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_port_phy_qcaps_input req = {0};
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_QCAPS, -1, -1);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc)
+		*force_speeds = le16_to_cpu(resp->supported_speeds_force_mode);
+
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
+}
+
 static int bnxt_disable_an_for_lpbk(struct bnxt *bp,
 				    struct hwrm_port_phy_cfg_input *req)
 {
 	struct bnxt_link_info *link_info = &bp->link_info;
-	u16 fw_advertising = link_info->advertising;
+	u16 fw_advertising;
 	u16 fw_speed;
 	int rc;
 
 	if (!link_info->autoneg)
 		return 0;
 
+	rc = bnxt_query_force_speeds(bp, &fw_advertising);
+	if (rc)
+		return rc;
+
 	fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_1GB;
 	if (netif_carrier_ok(bp->dev))
 		fw_speed = bp->link_info.link_speed;
-- 
2.20.1

[PATCH AUTOSEL 4.19 105/219] vxlan: Fix error path in __vxlan_dev_create()

[Sasha Levin]

From: Petr Machata <petrm@mellanox.com>

[ Upstream commit 6db9246871394b3a136cd52001a0763676563840 ]

When a failure occurs in rtnl_configure_link(), the current code
calls unregister_netdevice() to roll back the earlier call to
register_netdevice(), and jumps to errout, which calls
vxlan_fdb_destroy().

However unregister_netdevice() calls transitively ndo_uninit, which is
vxlan_uninit(), and that already takes care of deleting the default FDB
entry by calling vxlan_fdb_delete_default(). Since the entry added
earlier in __vxlan_dev_create() is exactly the default entry, the
cleanup code in the errout block always leads to double free and thus a
panic.

Besides, since vxlan_fdb_delete_default() always destroys the FDB entry
with notification enabled, the deletion of the default entry is notified
even before the addition was notified.

Instead, move the unregister_netdevice() call after the manual destroy,
which solves both problems.

Fixes: 0241b836732f ("vxlan: fix default fdb entry netlink notify ordering during netdev create")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/vxlan.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 2a536f84d5f69..d8a56df3933f0 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -3213,6 +3213,7 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_fdb *f = NULL;
+	bool unregister = false;
 	int err;
 
 	err = vxlan_dev_configure(net, dev, conf, false, extack);
@@ -3238,12 +3239,11 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 	err = register_netdevice(dev);
 	if (err)
 		goto errout;
+	unregister = true;
 
 	err = rtnl_configure_link(dev, NULL);
-	if (err) {
-		unregister_netdevice(dev);
+	if (err)
 		goto errout;
-	}
 
 	/* notify default fdb entry */
 	if (f)
@@ -3251,9 +3251,16 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 
 	list_add(&vxlan->next, &vn->vxlan_list);
 	return 0;
+
 errout:
+	/* unregister_netdevice() destroys the default FDB entry with deletion
+	 * notification. But the addition notification was not sent yet, so
+	 * destroy the entry by hand here.
+	 */
 	if (f)
 		vxlan_fdb_destroy(vxlan, f, false);
+	if (unregister)
+		unregister_netdevice(dev);
 	return err;
 }
 
-- 
2.20.1

[PATCH AUTOSEL 4.19 115/219] brcmfmac: Fix access point mode

[Sasha Levin]

From: Stefan Wahren <stefan.wahren@i2se.com>

[ Upstream commit 861cb5eb467f5e38dce1aabe4e8db379255bd89b ]

Since commit 1204aa17f3b4 ("brcmfmac: set WIPHY_FLAG_HAVE_AP_SME flag")
the Raspberry Pi 3 A+ (BCM43455) isn't able to operate in AP mode with
hostapd (device_ap_sme=1 use_monitor=0):

brcmfmac: brcmf_cfg80211_stop_ap: setting AP mode failed -52

So add the missing mgmt_stypes for AP mode to fix this.

Fixes: 1204aa17f3b4 ("brcmfmac: set WIPHY_FLAG_HAVE_AP_SME flag")
Suggested-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../wireless/broadcom/brcm80211/brcmfmac/cfg80211.c    | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index c7c520f327f2b..bbdc6000afb9b 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -6314,6 +6314,16 @@ brcmf_txrx_stypes[NUM_NL80211_IFTYPES] = {
 		.tx = 0xffff,
 		.rx = BIT(IEEE80211_STYPE_ACTION >> 4) |
 		      BIT(IEEE80211_STYPE_PROBE_REQ >> 4)
+	},
+	[NL80211_IFTYPE_AP] = {
+		.tx = 0xffff,
+		.rx = BIT(IEEE80211_STYPE_ASSOC_REQ >> 4) |
+		      BIT(IEEE80211_STYPE_REASSOC_REQ >> 4) |
+		      BIT(IEEE80211_STYPE_PROBE_REQ >> 4) |
+		      BIT(IEEE80211_STYPE_DISASSOC >> 4) |
+		      BIT(IEEE80211_STYPE_AUTH >> 4) |
+		      BIT(IEEE80211_STYPE_DEAUTH >> 4) |
+		      BIT(IEEE80211_STYPE_ACTION >> 4)
 	}
 };
 
-- 
2.20.1

[PATCH AUTOSEL 4.19 116/219] ath6kl: Only use match sets when firmware supports it

[Sasha Levin]

From: Kyle Roeschley <kyle.roeschley@ni.com>

[ Upstream commit fb376a495fbdb886f38cfaf5a3805401b9e46f13 ]

Commit dd45b7598f1c ("ath6kl: Include match ssid list in scheduled scan")
merged the probed and matched SSID lists before sending them to the
firmware. In the process, it assumed match set support is always available
in ath6kl_set_probed_ssids, which breaks scans for hidden SSIDs. Now, check
that the firmware supports matching SSIDs in scheduled scans before setting
MATCH_SSID_FLAG.

Fixes: dd45b7598f1c ("ath6kl: Include match ssid list in scheduled scan")
Signed-off-by: Kyle Roeschley <kyle.roeschley@ni.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/ath/ath6kl/cfg80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index e121187f371ff..6c98d7903ffb6 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -939,7 +939,7 @@ static int ath6kl_set_probed_ssids(struct ath6kl *ar,
 		else
 			ssid_list[i].flag = ANY_SSID_FLAG;
 
-		if (n_match_ssid == 0)
+		if (ar->wiphy->max_match_sets != 0 && n_match_ssid == 0)
 			ssid_list[i].flag |= MATCH_SSID_FLAG;
 	}
 
-- 
2.20.1

[PATCH AUTOSEL 4.19 117/219] ath6kl: Fix off by one error in scan completion

[Sasha Levin]

From: Kyle Roeschley <kyle.roeschley@ni.com>

[ Upstream commit 5803c12816c43bd09e5f4247dd9313c2d9a2c41b ]

When ath6kl was reworked to share code between regular and scheduled scans
in commit 3b8ffc6a22ba ("ath6kl: Configure probed SSID list consistently"),
probed SSID entry changed from 1-index to 0-indexed. However,
ath6kl_cfg80211_scan_complete_event() was missed in that change. Fix its
indexing so that we correctly clear out the probed SSID list.

Signed-off-by: Kyle Roeschley <kyle.roeschley@ni.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wireless/ath/ath6kl/cfg80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index 6c98d7903ffb6..d7c626d9594e1 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -1093,7 +1093,7 @@ void ath6kl_cfg80211_scan_complete_event(struct ath6kl_vif *vif, bool aborted)
 	if (vif->scan_req->n_ssids && vif->scan_req->ssids[0].ssid_len) {
 		for (i = 0; i < vif->scan_req->n_ssids; i++) {
 			ath6kl_wmi_probedssid_cmd(ar->wmi, vif->fw_vif_idx,
-						  i + 1, DISABLE_SSID_FLAG,
+						  i, DISABLE_SSID_FLAG,
 						  0, NULL);
 		}
 	}
-- 
2.20.1

[PATCH AUTOSEL 4.19 130/219] bpf/cpumap: make sure frame_size for build_skb is aligned if headroom isn't

[Sasha Levin]

From: Jesper Dangaard Brouer <brouer@redhat.com>

[ Upstream commit 77ea5f4cbe2084db9ab021ba73fb7eadf1610884 ]

The frame_size passed to build_skb must be aligned, else it is
possible that the embedded struct skb_shared_info gets unaligned.

For correctness make sure that xdpf->headroom in included in the
alignment. No upstream drivers can hit this, as all XDP drivers provide
an aligned headroom.  This was discovered when playing with implementing
XDP support for mvneta, which have a 2 bytes DSA header, and this
Marvell ARM64 platform didn't like doing atomic operations on an
unaligned skb_shinfo(skb)->dataref addresses.

Fixes: 1c601d829ab0 ("bpf: cpumap xdp_buff to skb conversion and allocation")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/bpf/cpumap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 24aac0d0f4127..8974b3755670e 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -183,7 +183,7 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
 	 * is not at a fixed memory location, with mixed length
 	 * packets, which is bad for cache-line hotness.
 	 */
-	frame_size = SKB_DATA_ALIGN(xdpf->len) + xdpf->headroom +
+	frame_size = SKB_DATA_ALIGN(xdpf->len + xdpf->headroom) +
 		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
 	pkt_data_start = xdpf->data - xdpf->headroom;
-- 
2.20.1

[PATCH AUTOSEL 4.19 138/219] net/netlink_compat: Fix a missing check of nla_parse_nested

[Sasha Levin]

From: Aditya Pakki <pakki001@umn.edu>

[ Upstream commit 89dfd0083751d00d5d7ead36f6d8b045bf89c5e1 ]

In tipc_nl_compat_sk_dump(), if nla_parse_nested() fails, it could return
an error. To be consistent with other invocations of the function call,
on error, the fix passes the return value upstream.

Signed-off-by: Aditya Pakki <pakki001@umn.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/tipc/netlink_compat.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 318c541970ecd..6494d6b5e1b24 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -1030,8 +1030,11 @@ static int tipc_nl_compat_sk_dump(struct tipc_nl_compat_msg *msg,
 		u32 node;
 		struct nlattr *con[TIPC_NLA_CON_MAX + 1];
 
-		nla_parse_nested(con, TIPC_NLA_CON_MAX,
-				 sock[TIPC_NLA_SOCK_CON], NULL, NULL);
+		err = nla_parse_nested(con, TIPC_NLA_CON_MAX,
+				       sock[TIPC_NLA_SOCK_CON], NULL, NULL);
+
+		if (err)
+			return err;
 
 		node = nla_get_u32(con[TIPC_NLA_CON_NODE]);
 		tipc_tlv_sprintf(msg->rep, "  connected to <%u.%u.%u:%u>",
-- 
2.20.1

[PATCH AUTOSEL 4.19 139/219] net/net_namespace: Check the return value of register_pernet_subsys()

[Sasha Levin]

From: Aditya Pakki <pakki001@umn.edu>

[ Upstream commit 0eb987c874dc93f9c9d85a6465dbde20fdd3884c ]

In net_ns_init(), register_pernet_subsys() could fail while registering
network namespace subsystems. The fix checks the return value and
sends a panic() on failure.

Signed-off-by: Aditya Pakki <pakki001@umn.edu>
Reviewed-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/core/net_namespace.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 6dab186d4b8f6..c60123dff8039 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -913,7 +913,8 @@ static int __init net_ns_init(void)
 	init_net_initialized = true;
 	up_write(&pernet_ops_rwsem);
 
-	register_pernet_subsys(&net_ns_ops);
+	if (register_pernet_subsys(&net_ns_ops))
+		panic("Could not register network namespace subsystems");
 
 	rtnl_register(PF_UNSPEC, RTM_NEWNSID, rtnl_net_newid, NULL,
 		      RTNL_FLAG_DOIT_UNLOCKED);
-- 
2.20.1

[PATCH AUTOSEL 4.19 140/219] libceph: drop last_piece logic from write_partial_message_data()

[Sasha Levin]

From: Ilya Dryomov <idryomov@gmail.com>

[ Upstream commit 1f6b821aef78e3d79e8d598ae59fc7e23fb6c563 ]

last_piece is for the last piece in the current data item, not in the
entire data payload of the message.  This is harmful for messages with
multiple data items.  On top of that, we don't need to signal the end
of a data payload either because it is always followed by a footer.

We used to signal "more" unconditionally, until commit fe38a2b67bc6
("libceph: start defining message data cursor").  Part of a large
series, it introduced cursor->last_piece and also mistakenly inverted
the hint by passing last_piece for "more".  This was corrected with
commit c2cfa1940097 ("libceph: Fix ceph_tcp_sendpage()'s more boolean
usage").

As it is, last_piece is not helping at all: because Nagle algorithm is
disabled, for a simple message with two 512-byte data items we end up
emitting three packets: front + first data item, second data item and
footer.  Go back to the original pre-fe38a2b67bc6 behavior -- a single
packet in most cases.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/ceph/messenger.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index f7d7f32ac673c..6514816947fbe 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -1612,7 +1612,6 @@ static int write_partial_message_data(struct ceph_connection *con)
 		struct page *page;
 		size_t page_offset;
 		size_t length;
-		bool last_piece;
 		int ret;
 
 		if (!cursor->resid) {
@@ -1620,10 +1619,9 @@ static int write_partial_message_data(struct ceph_connection *con)
 			continue;
 		}
 
-		page = ceph_msg_data_next(cursor, &page_offset, &length,
-					  &last_piece);
-		ret = ceph_tcp_sendpage(con->sock, page, page_offset,
-					length, !last_piece);
+		page = ceph_msg_data_next(cursor, &page_offset, &length, NULL);
+		ret = ceph_tcp_sendpage(con->sock, page, page_offset, length,
+					true);
 		if (ret <= 0) {
 			if (do_datacrc)
 				msg->footer.data_crc = cpu_to_le32(crc);
-- 
2.20.1

Re: [PATCH AUTOSEL 4.19 140/219] libceph: drop last_piece logic from write_partial_message_data()

[Ilya Dryomov]

On Fri, Nov 22, 2019 at 6:51 AM Sasha Levin <sashal@kernel.org> wrote:
>
> From: Ilya Dryomov <idryomov@gmail.com>
>
> [ Upstream commit 1f6b821aef78e3d79e8d598ae59fc7e23fb6c563 ]
>
> last_piece is for the last piece in the current data item, not in the
> entire data payload of the message.  This is harmful for messages with
> multiple data items.  On top of that, we don't need to signal the end
> of a data payload either because it is always followed by a footer.
>
> We used to signal "more" unconditionally, until commit fe38a2b67bc6
> ("libceph: start defining message data cursor").  Part of a large
> series, it introduced cursor->last_piece and also mistakenly inverted
> the hint by passing last_piece for "more".  This was corrected with
> commit c2cfa1940097 ("libceph: Fix ceph_tcp_sendpage()'s more boolean
> usage").
>
> As it is, last_piece is not helping at all: because Nagle algorithm is
> disabled, for a simple message with two 512-byte data items we end up
> emitting three packets: front + first data item, second data item and
> footer.  Go back to the original pre-fe38a2b67bc6 behavior -- a single
> packet in most cases.
>
> Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
> Signed-off-by: Sasha Levin <sashal@kernel.org>
> ---
>  net/ceph/messenger.c | 8 +++-----
>  1 file changed, 3 insertions(+), 5 deletions(-)
>
> diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
> index f7d7f32ac673c..6514816947fbe 100644
> --- a/net/ceph/messenger.c
> +++ b/net/ceph/messenger.c
> @@ -1612,7 +1612,6 @@ static int write_partial_message_data(struct ceph_connection *con)
>                 struct page *page;
>                 size_t page_offset;
>                 size_t length;
> -               bool last_piece;
>                 int ret;
>
>                 if (!cursor->resid) {
> @@ -1620,10 +1619,9 @@ static int write_partial_message_data(struct ceph_connection *con)
>                         continue;
>                 }
>
> -               page = ceph_msg_data_next(cursor, &page_offset, &length,
> -                                         &last_piece);
> -               ret = ceph_tcp_sendpage(con->sock, page, page_offset,
> -                                       length, !last_piece);
> +               page = ceph_msg_data_next(cursor, &page_offset, &length, NULL);
> +               ret = ceph_tcp_sendpage(con->sock, page, page_offset, length,
> +                                       true);
>                 if (ret <= 0) {
>                         if (do_datacrc)
>                                 msg->footer.data_crc = cpu_to_le32(crc);

Hi Sasha,

This commit was part of a larger series and shouldn't be backported on
its own.  Please drop it.

Thanks,

                Ilya

Re: [PATCH AUTOSEL 4.19 140/219] libceph: drop last_piece logic from write_partial_message_data()

[Sasha Levin]

On Fri, Nov 22, 2019 at 03:00:43PM +0100, Ilya Dryomov wrote:
>On Fri, Nov 22, 2019 at 6:51 AM Sasha Levin <sashal@kernel.org> wrote:
>>
>> From: Ilya Dryomov <idryomov@gmail.com>
>>
>> [ Upstream commit 1f6b821aef78e3d79e8d598ae59fc7e23fb6c563 ]
>>
>> last_piece is for the last piece in the current data item, not in the
>> entire data payload of the message.  This is harmful for messages with
>> multiple data items.  On top of that, we don't need to signal the end
>> of a data payload either because it is always followed by a footer.
>>
>> We used to signal "more" unconditionally, until commit fe38a2b67bc6
>> ("libceph: start defining message data cursor").  Part of a large
>> series, it introduced cursor->last_piece and also mistakenly inverted
>> the hint by passing last_piece for "more".  This was corrected with
>> commit c2cfa1940097 ("libceph: Fix ceph_tcp_sendpage()'s more boolean
>> usage").
>>
>> As it is, last_piece is not helping at all: because Nagle algorithm is
>> disabled, for a simple message with two 512-byte data items we end up
>> emitting three packets: front + first data item, second data item and
>> footer.  Go back to the original pre-fe38a2b67bc6 behavior -- a single
>> packet in most cases.
>>
>> Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
>> Signed-off-by: Sasha Levin <sashal@kernel.org>
>> ---
>>  net/ceph/messenger.c | 8 +++-----
>>  1 file changed, 3 insertions(+), 5 deletions(-)
>>
>> diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
>> index f7d7f32ac673c..6514816947fbe 100644
>> --- a/net/ceph/messenger.c
>> +++ b/net/ceph/messenger.c
>> @@ -1612,7 +1612,6 @@ static int write_partial_message_data(struct ceph_connection *con)
>>                 struct page *page;
>>                 size_t page_offset;
>>                 size_t length;
>> -               bool last_piece;
>>                 int ret;
>>
>>                 if (!cursor->resid) {
>> @@ -1620,10 +1619,9 @@ static int write_partial_message_data(struct ceph_connection *con)
>>                         continue;
>>                 }
>>
>> -               page = ceph_msg_data_next(cursor, &page_offset, &length,
>> -                                         &last_piece);
>> -               ret = ceph_tcp_sendpage(con->sock, page, page_offset,
>> -                                       length, !last_piece);
>> +               page = ceph_msg_data_next(cursor, &page_offset, &length, NULL);
>> +               ret = ceph_tcp_sendpage(con->sock, page, page_offset, length,
>> +                                       true);
>>                 if (ret <= 0) {
>>                         if (do_datacrc)
>>                                 msg->footer.data_crc = cpu_to_le32(crc);
>
>Hi Sasha,
>
>This commit was part of a larger series and shouldn't be backported on
>its own.  Please drop it.

Now dropped, thanks!

-- 
Thanks,
Sasha

[PATCH AUTOSEL 4.19 145/219] net: (cpts) fix a missing check of clk_prepare

[Sasha Levin]

From: Kangjie Lu <kjlu@umn.edu>

[ Upstream commit 2d822f2dbab7f4c820f72eb8570aacf3f35855bd ]

clk_prepare() could fail, so let's check its status, and if it fails,
return its error code upstream.

Signed-off-by: Kangjie Lu <kjlu@umn.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/ti/cpts.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index b96b93c686bf1..4f644ac314fe8 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -572,7 +572,9 @@ struct cpts *cpts_create(struct device *dev, void __iomem *regs,
 		return ERR_CAST(cpts->refclk);
 	}
 
-	clk_prepare(cpts->refclk);
+	ret = clk_prepare(cpts->refclk);
+	if (ret)
+		return ERR_PTR(ret);
 
 	cpts->cc.read = cpts_systim_read;
 	cpts->cc.mask = CLOCKSOURCE_MASK(32);
-- 
2.20.1

[PATCH AUTOSEL 4.19 146/219] net: stmicro: fix a missing check of clk_prepare

[Sasha Levin]

From: Kangjie Lu <kjlu@umn.edu>

[ Upstream commit f86a3b83833e7cfe558ca4d70b64ebc48903efec ]

clk_prepare() could fail, so let's check its status, and if it fails,
return its error code upstream.

Signed-off-by: Kangjie Lu <kjlu@umn.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
index d07520fb969e6..62ccbd47c1db2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
@@ -59,7 +59,9 @@ static int sun7i_gmac_init(struct platform_device *pdev, void *priv)
 		gmac->clk_enabled = 1;
 	} else {
 		clk_set_rate(gmac->tx_clk, SUN7I_GMAC_MII_RATE);
-		clk_prepare(gmac->tx_clk);
+		ret = clk_prepare(gmac->tx_clk);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
-- 
2.20.1

[PATCH AUTOSEL 4.19 147/219] net: dsa: bcm_sf2: Propagate error value from mdio_write

[Sasha Levin]

From: Kangjie Lu <kjlu@umn.edu>

[ Upstream commit e49505f7255be8ced695919c08a29bf2c3d79616 ]

Both bcm_sf2_sw_indir_rw and mdiobus_write_nested could fail, so let's
return their error codes upstream.

Signed-off-by: Kangjie Lu <kjlu@umn.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/dsa/bcm_sf2.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index ca3655d28e00f..1ffdad278899f 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -309,11 +309,10 @@ static int bcm_sf2_sw_mdio_write(struct mii_bus *bus, int addr, int regnum,
 	 * send them to our master MDIO bus controller
 	 */
 	if (addr == BRCM_PSEUDO_PHY_ADDR && priv->indir_phy_mask & BIT(addr))
-		bcm_sf2_sw_indir_rw(priv, 0, addr, regnum, val);
+		return bcm_sf2_sw_indir_rw(priv, 0, addr, regnum, val);
 	else
-		mdiobus_write_nested(priv->master_mii_bus, addr, regnum, val);
-
-	return 0;
+		return mdiobus_write_nested(priv->master_mii_bus, addr,
+				regnum, val);
 }
 
 static irqreturn_t bcm_sf2_switch_0_isr(int irq, void *dev_id)
-- 
2.20.1

[PATCH AUTOSEL 4.19 148/219] atl1e: checking the status of atl1e_write_phy_reg

[Sasha Levin]

From: Kangjie Lu <kjlu@umn.edu>

[ Upstream commit ff07d48d7bc0974d4f96a85a4df14564fb09f1ef ]

atl1e_write_phy_reg() could fail. The fix issues an error message when
it fails.

Signed-off-by: Kangjie Lu <kjlu@umn.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/atheros/atl1e/atl1e_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
index 9dc6da039a6d9..3164aad29bcf8 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -473,7 +473,9 @@ static void atl1e_mdio_write(struct net_device *netdev, int phy_id,
 {
 	struct atl1e_adapter *adapter = netdev_priv(netdev);
 
-	atl1e_write_phy_reg(&adapter->hw, reg_num & MDIO_REG_ADDR_MASK, val);
+	if (atl1e_write_phy_reg(&adapter->hw,
+				reg_num & MDIO_REG_ADDR_MASK, val))
+		netdev_err(netdev, "write phy register failed\n");
 }
 
 static int atl1e_mii_ioctl(struct net_device *netdev,
-- 
2.20.1

[PATCH AUTOSEL 4.19 149/219] tipc: fix a missing check of genlmsg_put

[Sasha Levin]

From: Kangjie Lu <kjlu@umn.edu>

[ Upstream commit 46273cf7e009231d2b6bc10a926e82b8928a9fb2 ]

genlmsg_put could fail. The fix inserts a check of its return value, and
if it fails, returns -EMSGSIZE.

Signed-off-by: Kangjie Lu <kjlu@umn.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/tipc/netlink_compat.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 6494d6b5e1b24..fab0384d2b4b3 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -983,6 +983,8 @@ static int tipc_nl_compat_publ_dump(struct tipc_nl_compat_msg *msg, u32 sock)
 
 	hdr = genlmsg_put(args, 0, 0, &tipc_genl_family, NLM_F_MULTI,
 			  TIPC_NL_PUBL_GET);
+	if (!hdr)
+		return -EMSGSIZE;
 
 	nest = nla_nest_start(args, TIPC_NLA_SOCK);
 	if (!nest) {
-- 
2.20.1

[PATCH AUTOSEL 4.19 150/219] net: marvell: fix a missing check of acpi_match_device

[Sasha Levin]

From: Kangjie Lu <kjlu@umn.edu>

[ Upstream commit 92ee77d148bf06d8c52664be4d1b862583fd5c0e ]

When acpi_match_device fails, its return value is NULL. Directly using
the return value without a check may result in a NULL-pointer
dereference. The fix checks if acpi_match_device fails, and if so,
returns -EINVAL.

Signed-off-by: Kangjie Lu <kjlu@umn.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 9b608d23ff7ee..9d95add05e3e6 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -5131,6 +5131,8 @@ static int mvpp2_probe(struct platform_device *pdev)
 	if (has_acpi_companion(&pdev->dev)) {
 		acpi_id = acpi_match_device(pdev->dev.driver->acpi_match_table,
 					    &pdev->dev);
+		if (!acpi_id)
+			return -EINVAL;
 		priv->hw_version = (unsigned long)acpi_id->driver_data;
 	} else {
 		priv->hw_version =
-- 
2.20.1

[PATCH AUTOSEL 4.19 151/219] net/wan/fsl_ucc_hdlc: Avoid double free in ucc_hdlc_probe()

[Sasha Levin]

From: Wen Yang <wen.yang99@zte.com.cn>

[ Upstream commit 40752b3eae29f8ca2378e978a02bd6dbeeb06d16 ]

This patch fixes potential double frees if register_hdlc_device() fails.

Signed-off-by: Wen Yang <wen.yang99@zte.com.cn>
Reviewed-by: Peng Hao <peng.hao2@zte.com.cn>
CC: Zhao Qiang <qiang.zhao@nxp.com>
CC: "David S. Miller" <davem@davemloft.net>
CC: netdev@vger.kernel.org
CC: linuxppc-dev@lists.ozlabs.org
CC: linux-kernel@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wan/fsl_ucc_hdlc.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
index 5f0366a125e26..0212f576a838c 100644
--- a/drivers/net/wan/fsl_ucc_hdlc.c
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -1113,7 +1113,6 @@ static int ucc_hdlc_probe(struct platform_device *pdev)
 	if (register_hdlc_device(dev)) {
 		ret = -ENOBUFS;
 		pr_err("ucc_hdlc: unable to register hdlc device\n");
-		free_netdev(dev);
 		goto free_dev;
 	}
 
-- 
2.20.1

[PATCH AUTOSEL 4.19 158/219] netfilter: nf_tables: fix a missing check of nla_put_failure

[Sasha Levin]

From: Kangjie Lu <kjlu@umn.edu>

[ Upstream commit eb8950861c1bfd3eecc8f6faad213e3bca0dc395 ]

If nla_nest_start() may fail. The fix checks its return value and goes
to nla_put_failure if it fails.

Signed-off-by: Kangjie Lu <kjlu@umn.edu>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/nf_tables_api.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 24fddf0322790..4c1a88b7ba285 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5735,6 +5735,8 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net,
 		goto nla_put_failure;
 
 	nest = nla_nest_start(skb, NFTA_FLOWTABLE_HOOK);
+	if (!nest)
+		goto nla_put_failure;
 	if (nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_NUM, htonl(flowtable->hooknum)) ||
 	    nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_PRIORITY, htonl(flowtable->priority)))
 		goto nla_put_failure;
-- 
2.20.1

[PATCH AUTOSEL 4.19 159/219] xprtrdma: Prevent leak of rpcrdma_rep objects

[Sasha Levin]

From: Chuck Lever <chuck.lever@oracle.com>

[ Upstream commit 07e10308ee5da8e6132e0b737ece1c99dd651fb6 ]

If a reply has been processed but the RPC is later retransmitted
anyway, the req->rl_reply field still contains the only pointer to
the old rpcrdma rep. When the next reply comes in, the reply handler
will stomp on the rl_reply field, leaking the old rep.

A trace event is added to capture such leaks.

This problem seems to be worsened by the restructuring of the RPC
Call path in v4.20. Fully addressing this issue will require at
least a re-architecture of the disconnect logic, which is not
appropriate during -rc.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/trace/events/rpcrdma.h | 28 ++++++++++++++++++++++++++++
 net/sunrpc/xprtrdma/rpc_rdma.c |  4 ++++
 2 files changed, 32 insertions(+)

diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index 53df203b8057a..4c91cadd1871d 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -917,6 +917,34 @@ TRACE_EVENT(xprtrdma_cb_setup,
 DEFINE_CB_EVENT(xprtrdma_cb_call);
 DEFINE_CB_EVENT(xprtrdma_cb_reply);
 
+TRACE_EVENT(xprtrdma_leaked_rep,
+	TP_PROTO(
+		const struct rpc_rqst *rqst,
+		const struct rpcrdma_rep *rep
+	),
+
+	TP_ARGS(rqst, rep),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, task_id)
+		__field(unsigned int, client_id)
+		__field(u32, xid)
+		__field(const void *, rep)
+	),
+
+	TP_fast_assign(
+		__entry->task_id = rqst->rq_task->tk_pid;
+		__entry->client_id = rqst->rq_task->tk_client->cl_clid;
+		__entry->xid = be32_to_cpu(rqst->rq_xid);
+		__entry->rep = rep;
+	),
+
+	TP_printk("task:%u@%u xid=0x%08x rep=%p",
+		__entry->task_id, __entry->client_id, __entry->xid,
+		__entry->rep
+	)
+);
+
 /**
  ** Server-side RPC/RDMA events
  **/
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index c8ae983c6cc01..f2eaf264726be 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -1360,6 +1360,10 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 	spin_unlock(&xprt->recv_lock);
 
 	req = rpcr_to_rdmar(rqst);
+	if (req->rl_reply) {
+		trace_xprtrdma_leaked_rep(rqst, req->rl_reply);
+		rpcrdma_recv_buffer_put(req->rl_reply);
+	}
 	req->rl_reply = rep;
 	rep->rr_rqst = rqst;
 	clear_bit(RPCRDMA_REQ_F_PENDING, &req->rl_flags);
-- 
2.20.1

[PATCH AUTOSEL 4.19 170/219] tipc: fix memory leak in tipc_nl_compat_publ_dump

[Sasha Levin]

From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>

[ Upstream commit f87d8ad9233f115db92c6c087d58403b0009ed36 ]

There is a memory leak in case genlmsg_put fails.

Fix this by freeing *args* before return.

Addresses-Coverity-ID: 1476406 ("Resource leak")
Fixes: 46273cf7e009 ("tipc: fix a missing check of genlmsg_put")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/tipc/netlink_compat.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index fab0384d2b4b3..b4860084a8f56 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -983,8 +983,10 @@ static int tipc_nl_compat_publ_dump(struct tipc_nl_compat_msg *msg, u32 sock)
 
 	hdr = genlmsg_put(args, 0, 0, &tipc_genl_family, NLM_F_MULTI,
 			  TIPC_NL_PUBL_GET);
-	if (!hdr)
+	if (!hdr) {
+		kfree_skb(args);
 		return -EMSGSIZE;
+	}
 
 	nest = nla_nest_start(args, TIPC_NLA_SOCK);
 	if (!nest) {
-- 
2.20.1

[PATCH AUTOSEL 4.19 171/219] net/core/neighbour: tell kmemleak about hash tables

[Sasha Levin]

From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>

[ Upstream commit 85704cb8dcfd88d351bfc87faaeba1c8214f3177 ]

This fixes false-positive kmemleak reports about leaked neighbour entries:

unreferenced object 0xffff8885c6e4d0a8 (size 1024):
  comm "softirq", pid 0, jiffies 4294922664 (age 167640.804s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 20 2c f3 83 ff ff ff ff  ........ ,......
    08 c0 ef 5f 84 88 ff ff 01 8c 7d 02 01 00 00 00  ..._......}.....
  backtrace:
    [<00000000748509fe>] ip6_finish_output2+0x887/0x1e40
    [<0000000036d7a0d8>] ip6_output+0x1ba/0x600
    [<0000000027ea7dba>] ip6_send_skb+0x92/0x2f0
    [<00000000d6e2111d>] udp_v6_send_skb.isra.24+0x680/0x15e0
    [<000000000668a8be>] udpv6_sendmsg+0x18c9/0x27a0
    [<000000004bd5fa90>] sock_sendmsg+0xb3/0xf0
    [<000000008227b29f>] ___sys_sendmsg+0x745/0x8f0
    [<000000008698009d>] __sys_sendmsg+0xde/0x170
    [<00000000889dacf1>] do_syscall_64+0x9b/0x400
    [<0000000081cdb353>] entry_SYSCALL_64_after_hwframe+0x49/0xbe
    [<000000005767ed39>] 0xffffffffffffffff

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/core/neighbour.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index c52d6e6b341cf..4721793babed5 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -18,6 +18,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/slab.h>
+#include <linux/kmemleak.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -363,12 +364,14 @@ static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift)
 	ret = kmalloc(sizeof(*ret), GFP_ATOMIC);
 	if (!ret)
 		return NULL;
-	if (size <= PAGE_SIZE)
+	if (size <= PAGE_SIZE) {
 		buckets = kzalloc(size, GFP_ATOMIC);
-	else
+	} else {
 		buckets = (struct neighbour __rcu **)
 			  __get_free_pages(GFP_ATOMIC | __GFP_ZERO,
 					   get_order(size));
+		kmemleak_alloc(buckets, size, 0, GFP_ATOMIC);
+	}
 	if (!buckets) {
 		kfree(ret);
 		return NULL;
@@ -388,10 +391,12 @@ static void neigh_hash_free_rcu(struct rcu_head *head)
 	size_t size = (1 << nht->hash_shift) * sizeof(struct neighbour *);
 	struct neighbour __rcu **buckets = nht->hash_buckets;
 
-	if (size <= PAGE_SIZE)
+	if (size <= PAGE_SIZE) {
 		kfree(buckets);
-	else
+	} else {
+		kmemleak_free(buckets);
 		free_pages((unsigned long)buckets, get_order(size));
+	}
 	kfree(nht);
 }
 
-- 
2.20.1

[PATCH AUTOSEL 4.19 174/219] net/core/neighbour: fix kmemleak minimal reference count for hash tables

[Sasha Levin]

From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>

[ Upstream commit 01b833ab44c9e484060aad72267fc7e71beb559b ]

This should be 1 for normal allocations, 0 disables leak reporting.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Reported-by: Cong Wang <xiyou.wangcong@gmail.com>
Fixes: 85704cb8dcfd ("net/core/neighbour: tell kmemleak about hash tables")
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/core/neighbour.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 4721793babed5..7597afee70680 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -370,7 +370,7 @@ static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift)
 		buckets = (struct neighbour __rcu **)
 			  __get_free_pages(GFP_ATOMIC | __GFP_ZERO,
 					   get_order(size));
-		kmemleak_alloc(buckets, size, 0, GFP_ATOMIC);
+		kmemleak_alloc(buckets, size, 1, GFP_ATOMIC);
 	}
 	if (!buckets) {
 		kfree(ret);
-- 
2.20.1

[PATCH AUTOSEL 4.19 177/219] sfc: suppress duplicate nvmem partition types in efx_ef10_mtd_probe

[Sasha Levin]

From: Edward Cree <ecree@solarflare.com>

[ Upstream commit 3366463513f544c12c6b88c13da4462ee9e7a1a1 ]

Use a bitmap to keep track of which partition types we've already seen;
 for duplicates, return -EEXIST from efx_ef10_mtd_probe_partition() and
 thus skip adding that partition.
Duplicate partitions occur because of the A/B backup scheme used by newer
 sfc NICs.  Prior to this patch they cause sysfs_warn_dup errors because
 they have the same name, causing us not to expose any MTDs at all.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/sfc/ef10.c | 29 +++++++++++++++++++++--------
 1 file changed, 21 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 7eeac3d6cfe89..a497aace7e4f4 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -6042,22 +6042,25 @@ static const struct efx_ef10_nvram_type_info efx_ef10_nvram_types[] = {
 	{ NVRAM_PARTITION_TYPE_LICENSE,		   0,    0, "sfc_license" },
 	{ NVRAM_PARTITION_TYPE_PHY_MIN,		   0xff, 0, "sfc_phy_fw" },
 };
+#define EF10_NVRAM_PARTITION_COUNT	ARRAY_SIZE(efx_ef10_nvram_types)
 
 static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,
 					struct efx_mcdi_mtd_partition *part,
-					unsigned int type)
+					unsigned int type,
+					unsigned long *found)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_METADATA_IN_LEN);
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_METADATA_OUT_LENMAX);
 	const struct efx_ef10_nvram_type_info *info;
 	size_t size, erase_size, outlen;
+	int type_idx = 0;
 	bool protected;
 	int rc;
 
-	for (info = efx_ef10_nvram_types; ; info++) {
-		if (info ==
-		    efx_ef10_nvram_types + ARRAY_SIZE(efx_ef10_nvram_types))
+	for (type_idx = 0; ; type_idx++) {
+		if (type_idx == EF10_NVRAM_PARTITION_COUNT)
 			return -ENODEV;
+		info = efx_ef10_nvram_types + type_idx;
 		if ((type & ~info->type_mask) == info->type)
 			break;
 	}
@@ -6070,6 +6073,13 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,
 	if (protected)
 		return -ENODEV; /* hide it */
 
+	/* If we've already exposed a partition of this type, hide this
+	 * duplicate.  All operations on MTDs are keyed by the type anyway,
+	 * so we can't act on the duplicate.
+	 */
+	if (__test_and_set_bit(type_idx, found))
+		return -EEXIST;
+
 	part->nvram_type = type;
 
 	MCDI_SET_DWORD(inbuf, NVRAM_METADATA_IN_TYPE, type);
@@ -6098,6 +6108,7 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,
 static int efx_ef10_mtd_probe(struct efx_nic *efx)
 {
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_PARTITIONS_OUT_LENMAX);
+	DECLARE_BITMAP(found, EF10_NVRAM_PARTITION_COUNT);
 	struct efx_mcdi_mtd_partition *parts;
 	size_t outlen, n_parts_total, i, n_parts;
 	unsigned int type;
@@ -6126,11 +6137,13 @@ static int efx_ef10_mtd_probe(struct efx_nic *efx)
 	for (i = 0; i < n_parts_total; i++) {
 		type = MCDI_ARRAY_DWORD(outbuf, NVRAM_PARTITIONS_OUT_TYPE_ID,
 					i);
-		rc = efx_ef10_mtd_probe_partition(efx, &parts[n_parts], type);
-		if (rc == 0)
-			n_parts++;
-		else if (rc != -ENODEV)
+		rc = efx_ef10_mtd_probe_partition(efx, &parts[n_parts], type,
+						  found);
+		if (rc == -EEXIST || rc == -ENODEV)
+			continue;
+		if (rc)
 			goto fail;
+		n_parts++;
 	}
 
 	rc = efx_mtd_add(efx, &parts[0].common, n_parts, sizeof(*parts));
-- 
2.20.1

[PATCH AUTOSEL 4.19 178/219] ip_tunnel: Make none-tunnel-dst tunnel port work with lwtunnel

[Sasha Levin]

From: wenxu <wenxu@ucloud.cn>

[ Upstream commit d71b57532d70c03f4671dd04e84157ac6bf021b0 ]

ip l add dev tun type gretap key 1000
ip a a dev tun 10.0.0.1/24

Packets with tun-id 1000 can be recived by tun dev. But packet can't
be sent through dev tun for non-tunnel-dst

With this patch: tunnel-dst can be get through lwtunnel like beflow:
ip r a 10.0.0.7 encap ip dst 172.168.0.11 dev tun

Signed-off-by: wenxu <wenxu@ucloud.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/ipv4/ip_tunnel.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index c4f5602308edc..054d01c16dc6a 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -644,13 +644,19 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	dst = tnl_params->daddr;
 	if (dst == 0) {
 		/* NBMA tunnel */
+		struct ip_tunnel_info *tun_info;
 
 		if (!skb_dst(skb)) {
 			dev->stats.tx_fifo_errors++;
 			goto tx_error;
 		}
 
-		if (skb->protocol == htons(ETH_P_IP)) {
+		tun_info = skb_tunnel_info(skb);
+		if (tun_info && (tun_info->mode & IP_TUNNEL_INFO_TX) &&
+		    ip_tunnel_info_af(tun_info) == AF_INET &&
+		    tun_info->key.u.ipv4.dst)
+			dst = tun_info->key.u.ipv4.dst;
+		else if (skb->protocol == htons(ETH_P_IP)) {
 			rt = skb_rtable(skb);
 			dst = rt_nexthop(rt, inner_iph->daddr);
 		}
-- 
2.20.1

[PATCH AUTOSEL 4.19 179/219] decnet: fix DN_IFREQ_SIZE

[Sasha Levin]

From: Johannes Berg <johannes.berg@intel.com>

[ Upstream commit 50c2936634bcb1db78a8ca63249236810c11a80f ]

Digging through the ioctls with Al because of the previous
patches, we found that on 64-bit decnet's dn_dev_ioctl()
is wrong, because struct ifreq::ifr_ifru is actually 24
bytes (not 16 as expected from struct sockaddr) due to the
ifru_map and ifru_settings members.

Clearly, decnet expects the ioctl to be called with a struct
like
  struct ifreq_dn {
    char ifr_name[IFNAMSIZ];
    struct sockaddr_dn ifr_addr;
  };

since it does
  struct ifreq *ifr = ...;
  struct sockaddr_dn *sdn = (struct sockaddr_dn *)&ifr->ifr_addr;

This means that DN_IFREQ_SIZE is too big for what it wants on
64-bit, as it is
  sizeof(struct ifreq) - sizeof(struct sockaddr) +
  sizeof(struct sockaddr_dn)

This assumes that sizeof(struct sockaddr) is the size of ifr_ifru
but that isn't true.

Fix this to use offsetof(struct ifreq, ifr_ifru).

This indeed doesn't really matter much - the result is that we
copy in/out 8 bytes more than we should on 64-bit platforms. In
case the "struct ifreq_dn" lands just on the end of a page though
it might lead to faults.

As far as I can tell, it has been like this forever, so it seems
very likely that nobody cares.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/decnet/dn_dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index bfd43e8f2c06e..3235540f6adff 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -56,7 +56,7 @@
 #include <net/dn_neigh.h>
 #include <net/dn_fib.h>
 
-#define DN_IFREQ_SIZE (sizeof(struct ifreq) - sizeof(struct sockaddr) + sizeof(struct sockaddr_dn))
+#define DN_IFREQ_SIZE (offsetof(struct ifreq, ifr_ifru) + sizeof(struct sockaddr_dn))
 
 static char dn_rt_all_end_mcast[ETH_ALEN] = {0xAB,0x00,0x00,0x04,0x00,0x00};
 static char dn_rt_all_rt_mcast[ETH_ALEN]  = {0xAB,0x00,0x00,0x03,0x00,0x00};
-- 
2.20.1

[PATCH AUTOSEL 4.19 180/219] net/smc: prevent races between smc_lgr_terminate() and smc_conn_free()

[Sasha Levin]

From: Karsten Graul <kgraul@linux.ibm.com>

[ Upstream commit 77f838ace755d2f466536c44dac6c856f62cd901 ]

To prevent races between smc_lgr_terminate() and smc_conn_free() add an
extra check of the lgr field before accessing it, and cancel a delayed
free_work when a new smc connection is created.
This fixes the problem that free_work cleared the lgr variable but
smc_lgr_terminate() or smc_conn_free() still access it in parallel.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/smc/smc_core.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 18daebcef1813..2c9baf8bf1189 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -128,6 +128,8 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn)
 {
 	struct smc_link_group *lgr = conn->lgr;
 
+	if (!lgr)
+		return;
 	write_lock_bh(&lgr->conns_lock);
 	if (conn->alert_token_local) {
 		__smc_lgr_unregister_conn(conn);
@@ -612,6 +614,8 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
 			local_contact = SMC_REUSE_CONTACT;
 			conn->lgr = lgr;
 			smc_lgr_register_conn(conn); /* add smc conn to lgr */
+			if (delayed_work_pending(&lgr->free_work))
+				cancel_delayed_work(&lgr->free_work);
 			write_unlock_bh(&lgr->conns_lock);
 			break;
 		}
-- 
2.20.1

[PATCH AUTOSEL 4.19 181/219] net/smc: don't wait for send buffer space when data was already sent

[Sasha Levin]

From: Karsten Graul <kgraul@linux.ibm.com>

[ Upstream commit 6889b36da78a21a312d8b462c1fa25a03c2ff192 ]

When there is no more send buffer space and at least 1 byte was already
sent then return to user space. The wait is only done when no data was
sent by the sendmsg() call.
This fixes smc_tx_sendmsg() which tried to always send all user data and
started to wait for free send buffer space when needed. During this wait
the user space program was blocked in the sendmsg() call and hence not
able to receive incoming data. When both sides were in such a situation
then the connection stalled forever.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/smc/smc_tx.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index 28361aef99825..f1f621675db01 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -163,12 +163,11 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
 			conn->local_tx_ctrl.prod_flags.urg_data_pending = 1;
 
 		if (!atomic_read(&conn->sndbuf_space) || conn->urg_tx_pend) {
+			if (send_done)
+				return send_done;
 			rc = smc_tx_wait(smc, msg->msg_flags);
-			if (rc) {
-				if (send_done)
-					return send_done;
+			if (rc)
 				goto out_err;
-			}
 			continue;
 		}
 
-- 
2.20.1

[PATCH AUTOSEL 4.19 184/219] net/smc: fix sender_free computation

[Sasha Levin]

From: Ursula Braun <ubraun@linux.ibm.com>

[ Upstream commit b8649efad879c69c7ab1f19ce8814fcabef1f72b ]

In some scenarios a separate consumer cursor update is necessary.
The decision is made in smc_tx_consumer_cursor_update(). The
sender_free computation could be wrong:

The rx confirmed cursor is always smaller than or equal to the
rx producer cursor. The parameters in the smc_curs_diff() call
have to be exchanged, otherwise sender_free might even be negative.

And if more data arrives local_rx_ctrl.prod might be updated, enabling
a cursor difference between local_rx_ctrl.prod and rx confirmed cursor
larger than the RMB size. This case is not covered by smc_curs_diff().
Thus function smc_curs_diff_large() is introduced here.

If a recvmsg() is processed in parallel, local_tx_ctrl.cons might
change during smc_cdc_msg_send. Make sure rx_curs_confirmed is updated
with the actually sent local_tx_ctrl.cons value.

Fixes: e82f2e31f559 ("net/smc: optimize consumer cursor updates")
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/smc/smc_cdc.c |  5 +++--
 net/smc/smc_cdc.h | 26 +++++++++++++++++++++++++-
 net/smc/smc_tx.c  |  3 ++-
 3 files changed, 30 insertions(+), 4 deletions(-)

diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index ed5dcf03fe0b6..8f691b5a44ddf 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -96,6 +96,7 @@ int smc_cdc_msg_send(struct smc_connection *conn,
 		     struct smc_wr_buf *wr_buf,
 		     struct smc_cdc_tx_pend *pend)
 {
+	union smc_host_cursor cfed;
 	struct smc_link *link;
 	int rc;
 
@@ -107,10 +108,10 @@ int smc_cdc_msg_send(struct smc_connection *conn,
 	conn->local_tx_ctrl.seqno = conn->tx_cdc_seq;
 	smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf,
 			    &conn->local_tx_ctrl, conn);
+	smc_curs_copy(&cfed, &((struct smc_host_cdc_msg *)wr_buf)->cons, conn);
 	rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend);
 	if (!rc)
-		smc_curs_copy(&conn->rx_curs_confirmed,
-			      &conn->local_tx_ctrl.cons, conn);
+		smc_curs_copy(&conn->rx_curs_confirmed, &cfed, conn);
 
 	return rc;
 }
diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h
index 934df4473a7ce..2377a51772d51 100644
--- a/net/smc/smc_cdc.h
+++ b/net/smc/smc_cdc.h
@@ -135,7 +135,9 @@ static inline void smc_curs_copy_net(union smc_cdc_cursor *tgt,
 #endif
 }
 
-/* calculate cursor difference between old and new, where old <= new */
+/* calculate cursor difference between old and new, where old <= new and
+ * difference cannot exceed size
+ */
 static inline int smc_curs_diff(unsigned int size,
 				union smc_host_cursor *old,
 				union smc_host_cursor *new)
@@ -160,6 +162,28 @@ static inline int smc_curs_comp(unsigned int size,
 	return smc_curs_diff(size, old, new);
 }
 
+/* calculate cursor difference between old and new, where old <= new and
+ * difference may exceed size
+ */
+static inline int smc_curs_diff_large(unsigned int size,
+				      union smc_host_cursor *old,
+				      union smc_host_cursor *new)
+{
+	if (old->wrap < new->wrap)
+		return min_t(int,
+			     (size - old->count) + new->count +
+			     (new->wrap - old->wrap - 1) * size,
+			     size);
+
+	if (old->wrap > new->wrap) /* wrap has switched from 0xffff to 0x0000 */
+		return min_t(int,
+			     (size - old->count) + new->count +
+			     (new->wrap + 0xffff - old->wrap) * size,
+			     size);
+
+	return max_t(int, 0, (new->count - old->count));
+}
+
 static inline void smc_host_cursor_to_cdc(union smc_cdc_cursor *peer,
 					  union smc_host_cursor *local,
 					  struct smc_connection *conn)
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index f1f621675db01..0ecbbdc337b82 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -595,7 +595,8 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force)
 	if (to_confirm > conn->rmbe_update_limit) {
 		smc_curs_copy(&prod, &conn->local_rx_ctrl.prod, conn);
 		sender_free = conn->rmb_desc->len -
-			      smc_curs_diff(conn->rmb_desc->len, &prod, &cfed);
+			      smc_curs_diff_large(conn->rmb_desc->len,
+						  &cfed, &prod);
 	}
 
 	if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req ||
-- 
2.20.1

[PATCH AUTOSEL 4.19 186/219] net/smc: fix byte_order for rx_curs_confirmed

[Sasha Levin]

From: Ursula Braun <ubraun@linux.ibm.com>

[ Upstream commit ccc8ca9b90acb45a3309f922b2591b07b4e070ec ]

The recent change in the rx_curs_confirmed assignment disregards
byte order, which causes problems on little endian architectures.
This patch fixes it.

Fixes: b8649efad879 ("net/smc: fix sender_free computation") (net-tree)
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/smc/smc_cdc.c |  4 +---
 net/smc/smc_cdc.h | 19 ++++++++++---------
 2 files changed, 11 insertions(+), 12 deletions(-)

diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index 8f691b5a44ddf..333e4353498f8 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -106,9 +106,7 @@ int smc_cdc_msg_send(struct smc_connection *conn,
 
 	conn->tx_cdc_seq++;
 	conn->local_tx_ctrl.seqno = conn->tx_cdc_seq;
-	smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf,
-			    &conn->local_tx_ctrl, conn);
-	smc_curs_copy(&cfed, &((struct smc_host_cdc_msg *)wr_buf)->cons, conn);
+	smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf, conn, &cfed);
 	rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend);
 	if (!rc)
 		smc_curs_copy(&conn->rx_curs_confirmed, &cfed, conn);
diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h
index 2377a51772d51..34d2e1450320a 100644
--- a/net/smc/smc_cdc.h
+++ b/net/smc/smc_cdc.h
@@ -186,26 +186,27 @@ static inline int smc_curs_diff_large(unsigned int size,
 
 static inline void smc_host_cursor_to_cdc(union smc_cdc_cursor *peer,
 					  union smc_host_cursor *local,
+					  union smc_host_cursor *save,
 					  struct smc_connection *conn)
 {
-	union smc_host_cursor temp;
-
-	smc_curs_copy(&temp, local, conn);
-	peer->count = htonl(temp.count);
-	peer->wrap = htons(temp.wrap);
+	smc_curs_copy(save, local, conn);
+	peer->count = htonl(save->count);
+	peer->wrap = htons(save->wrap);
 	/* peer->reserved = htons(0); must be ensured by caller */
 }
 
 static inline void smc_host_msg_to_cdc(struct smc_cdc_msg *peer,
-				       struct smc_host_cdc_msg *local,
-				       struct smc_connection *conn)
+				       struct smc_connection *conn,
+				       union smc_host_cursor *save)
 {
+	struct smc_host_cdc_msg *local = &conn->local_tx_ctrl;
+
 	peer->common.type = local->common.type;
 	peer->len = local->len;
 	peer->seqno = htons(local->seqno);
 	peer->token = htonl(local->token);
-	smc_host_cursor_to_cdc(&peer->prod, &local->prod, conn);
-	smc_host_cursor_to_cdc(&peer->cons, &local->cons, conn);
+	smc_host_cursor_to_cdc(&peer->prod, &local->prod, save, conn);
+	smc_host_cursor_to_cdc(&peer->cons, &local->cons, save, conn);
 	peer->prod_flags = local->prod_flags;
 	peer->conn_state_flags = local->conn_state_flags;
 }
-- 
2.20.1

[PATCH AUTOSEL 4.19 187/219] tipc: fix skb may be leaky in tipc_link_input

[Sasha Levin]

From: Hoang Le <hoang.h.le@dektech.com.au>

[ Upstream commit 7384b538d3aed2ed49d3575483d17aeee790fb06 ]

When we free skb at tipc_data_input, we return a 'false' boolean.
Then, skb passed to subcalling tipc_link_input in tipc_link_rcv,

<snip>
1303 int tipc_link_rcv:
...
1354    if (!tipc_data_input(l, skb, l->inputq))
1355        rc |= tipc_link_input(l, skb, l->inputq);
</snip>

Fix it by simple changing to a 'true' boolean when skb is being free-ed.
Then, tipc_link_rcv will bypassed to subcalling tipc_link_input as above
condition.

Acked-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <maloy@donjonn.com>
Signed-off-by: Hoang Le <hoang.h.le@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/tipc/link.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tipc/link.c b/net/tipc/link.c
index 6344aca4487b6..0fbf8ea18ce04 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1114,7 +1114,7 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb,
 	default:
 		pr_warn("Dropping received illegal msg type\n");
 		kfree_skb(skb);
-		return false;
+		return true;
 	};
 }
 
-- 
2.20.1

[PATCH AUTOSEL 4.19 189/219] sfc: initialise found bitmap in efx_ef10_mtd_probe

[Sasha Levin]

From: Bert Kenward <bkenward@solarflare.com>

[ Upstream commit c65285428b6e7797f1bb063f33b0ae7e93397b7b ]

The bitmap of found partitions in efx_ef10_mtd_probe was not
initialised, causing partitions to be suppressed based off whatever
value was in the bitmap at the start.

Fixes: 3366463513f5 ("sfc: suppress duplicate nvmem partition types in efx_ef10_mtd_probe")
Signed-off-by: Bert Kenward <bkenward@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/sfc/ef10.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index a497aace7e4f4..1f971d31ec302 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -6108,7 +6108,7 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,
 static int efx_ef10_mtd_probe(struct efx_nic *efx)
 {
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_PARTITIONS_OUT_LENMAX);
-	DECLARE_BITMAP(found, EF10_NVRAM_PARTITION_COUNT);
+	DECLARE_BITMAP(found, EF10_NVRAM_PARTITION_COUNT) = { 0 };
 	struct efx_mcdi_mtd_partition *parts;
 	size_t outlen, n_parts_total, i, n_parts;
 	unsigned int type;
-- 
2.20.1

[PATCH AUTOSEL 4.19 190/219] geneve: change NET_UDP_TUNNEL dependency to select

[Sasha Levin]

From: Matteo Croce <mcroce@redhat.com>

[ Upstream commit a7603ac1fc8ce1409f8ff70e6ce505f308b2c002 ]

Due to the depends on NET_UDP_TUNNEL, at the moment it is impossible to
compile GENEVE if no other protocol depending on NET_UDP_TUNNEL is
selected.

Fix this changing the depends to a select, and drop NET_IP_TUNNEL from the
select list, as it already depends on NET_UDP_TUNNEL.

Signed-off-by: Matteo Croce <mcroce@redhat.com>
Reviewed-and-tested-by: Andrea Claudi <aclaudi@redhat.com>
Tested-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/Kconfig | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 619bf1498a662..0652caad57ec1 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -197,9 +197,9 @@ config VXLAN
 
 config GENEVE
        tristate "Generic Network Virtualization Encapsulation"
-       depends on INET && NET_UDP_TUNNEL
+       depends on INET
        depends on IPV6 || !IPV6
-       select NET_IP_TUNNEL
+       select NET_UDP_TUNNEL
        select GRO_CELLS
        ---help---
 	  This allows one to create geneve virtual interfaces that provide
-- 
2.20.1

[PATCH AUTOSEL 4.19 191/219] net: fix possible overflow in __sk_mem_raise_allocated()

[Sasha Levin]

From: Eric Dumazet <edumazet@google.com>

[ Upstream commit 5bf325a53202b8728cf7013b72688c46071e212e ]

With many active TCP sockets, fat TCP sockets could fool
__sk_mem_raise_allocated() thanks to an overflow.

They would increase their share of the memory, instead
of decreasing it.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/net/sock.h | 2 +-
 net/core/sock.c    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 0252c0d003104..4545a9ecc2193 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1272,7 +1272,7 @@ static inline void sk_sockets_allocated_inc(struct sock *sk)
 	percpu_counter_inc(sk->sk_prot->sockets_allocated);
 }
 
-static inline int
+static inline u64
 sk_sockets_allocated_read_positive(struct sock *sk)
 {
 	return percpu_counter_read_positive(sk->sk_prot->sockets_allocated);
diff --git a/net/core/sock.c b/net/core/sock.c
index 6c11078217769..f49bcaf1deefa 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2435,7 +2435,7 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind)
 	}
 
 	if (sk_has_memory_pressure(sk)) {
-		int alloc;
+		u64 alloc;
 
 		if (!sk_under_memory_pressure(sk))
 			return 1;
-- 
2.20.1

[PATCH AUTOSEL 4.19 192/219] net: ip_gre: do not report erspan_ver for gre or gretap

[Sasha Levin]

From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>

[ Upstream commit 2bdf700e538828d6456150b9319e5f689b062d54 ]

Report erspan version field to userspace in ipgre_fill_info just for
erspan tunnels. The issue can be triggered with the following reproducer:

$ip link add name gre1 type gre local 192.168.0.1 remote 192.168.1.1
$ip link set dev gre1 up
$ip -d link sh gre1
13: gre1@NONE: <POINTOPOINT,NOARP,UP,LOWER_UP> mtu 1476 qdisc noqueue state UNKNOWN mode DEFAULT group default qlen 1000
    link/gre 192.168.0.1 peer 192.168.1.1 promiscuity 0 minmtu 0 maxmtu 0
    gre remote 192.168.1.1 local 192.168.0.1 ttl inherit erspan_ver 0 addrgenmode eui64 numtxqueues 1 numrxqueues 1

Fixes: f551c91de262 ("net: erspan: introduce erspan v2 for ip_gre")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/ipv4/ip_gre.c | 33 +++++++++++++++++----------------
 1 file changed, 17 insertions(+), 16 deletions(-)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 758a0f86d499f..1cb6142532536 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1469,9 +1469,23 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	struct ip_tunnel_parm *p = &t->parms;
 	__be16 o_flags = p->o_flags;
 
-	if ((t->erspan_ver == 1 || t->erspan_ver == 2) &&
-	    !t->collect_md)
-		o_flags |= TUNNEL_KEY;
+	if (t->erspan_ver == 1 || t->erspan_ver == 2) {
+		if (!t->collect_md)
+			o_flags |= TUNNEL_KEY;
+
+		if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver))
+			goto nla_put_failure;
+
+		if (t->erspan_ver == 1) {
+			if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index))
+				goto nla_put_failure;
+		} else {
+			if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir))
+				goto nla_put_failure;
+			if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid))
+				goto nla_put_failure;
+		}
+	}
 
 	if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) ||
 	    nla_put_be16(skb, IFLA_GRE_IFLAGS,
@@ -1507,19 +1521,6 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 			goto nla_put_failure;
 	}
 
-	if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver))
-		goto nla_put_failure;
-
-	if (t->erspan_ver == 1) {
-		if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index))
-			goto nla_put_failure;
-	} else if (t->erspan_ver == 2) {
-		if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir))
-			goto nla_put_failure;
-		if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid))
-			goto nla_put_failure;
-	}
-
 	return 0;
 
 nla_put_failure:
-- 
2.20.1

[PATCH AUTOSEL 4.19 193/219] net: ip6_gre: do not report erspan_ver for ip6gre or ip6gretap

[Sasha Levin]

From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>

[ Upstream commit 103d0244d29fcaf38f1339d4538919bbbc051490 ]

Report erspan version field to userspace in ip6gre_fill_info just for
erspan_v6 tunnels. Moreover report IFLA_GRE_ERSPAN_INDEX only for
erspan version 1.
The issue can be triggered with the following reproducer:

$ip link add name gre6 type ip6gre local 2001::1 remote 2002::2
$ip link set gre6 up
$ip -d link sh gre6
14: grep6@NONE: <POINTOPOINT,NOARP,UP,LOWER_UP> mtu 1448 qdisc noqueue state UNKNOWN mode DEFAULT group default qlen 1000
    link/gre6 2001::1 peer 2002::2 promiscuity 0 minmtu 0 maxmtu 0
    ip6gre remote 2002::2 local 2001::1 hoplimit 64 encaplimit 4 tclass 0x00 flowlabel 0x00000 erspan_index 0 erspan_ver 0 addrgenmode eui64

Fixes: 94d7d8f29287 ("ip6_gre: add erspan v2 support")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/ipv6/ip6_gre.c | 36 ++++++++++++++++++------------------
 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index dee4113f21a9a..8fd28edd6ac57 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -2135,9 +2135,23 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	struct __ip6_tnl_parm *p = &t->parms;
 	__be16 o_flags = p->o_flags;
 
-	if ((p->erspan_ver == 1 || p->erspan_ver == 2) &&
-	    !p->collect_md)
-		o_flags |= TUNNEL_KEY;
+	if (p->erspan_ver == 1 || p->erspan_ver == 2) {
+		if (!p->collect_md)
+			o_flags |= TUNNEL_KEY;
+
+		if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, p->erspan_ver))
+			goto nla_put_failure;
+
+		if (p->erspan_ver == 1) {
+			if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index))
+				goto nla_put_failure;
+		} else {
+			if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, p->dir))
+				goto nla_put_failure;
+			if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, p->hwid))
+				goto nla_put_failure;
+		}
+	}
 
 	if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) ||
 	    nla_put_be16(skb, IFLA_GRE_IFLAGS,
@@ -2152,8 +2166,7 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u8(skb, IFLA_GRE_ENCAP_LIMIT, p->encap_limit) ||
 	    nla_put_be32(skb, IFLA_GRE_FLOWINFO, p->flowinfo) ||
 	    nla_put_u32(skb, IFLA_GRE_FLAGS, p->flags) ||
-	    nla_put_u32(skb, IFLA_GRE_FWMARK, p->fwmark) ||
-	    nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index))
+	    nla_put_u32(skb, IFLA_GRE_FWMARK, p->fwmark))
 		goto nla_put_failure;
 
 	if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE,
@@ -2171,19 +2184,6 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 			goto nla_put_failure;
 	}
 
-	if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, p->erspan_ver))
-		goto nla_put_failure;
-
-	if (p->erspan_ver == 1) {
-		if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index))
-			goto nla_put_failure;
-	} else if (p->erspan_ver == 2) {
-		if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, p->dir))
-			goto nla_put_failure;
-		if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, p->hwid))
-			goto nla_put_failure;
-	}
-
 	return 0;
 
 nla_put_failure:
-- 
2.20.1

[PATCH AUTOSEL 4.19 194/219] sctp: don't compare hb_timer expire date before starting it

[Sasha Levin]

From: Maciej Kwiecien <maciej.kwiecien@nokia.com>

[ Upstream commit d1f20c03f48102e52eb98b8651d129b83134cae4 ]

hb_timer might not start at all for a particular transport because its
start is conditional. In a result a node is not sending heartbeats.

Function sctp_transport_reset_hb_timer has two roles:
    - initial start of hb_timer for a given transport,
    - update expire date of hb_timer for a given transport.
The function is optimized to update timer's expire only if it is before
a new calculated one but this comparison is invalid for a timer which
has not yet started. Such a timer has expire == 0 and if a new expire
value is bigger than (MAX_JIFFIES / 2 + 2) then "time_before" macro will
fail and timer will not start resulting in no heartbeat packets send by
the node.

This was found when association was initialized within first 5 mins
after system boot due to jiffies init value which is near to MAX_JIFFIES.

Test kernel version: 4.9.154 (ARCH=arm)
hb_timer.expire = 0;                //initialized, not started timer
new_expire = MAX_JIFFIES / 2 + 2;   //or more
time_before(hb_timer.expire, new_expire) == false

Fixes: ba6f5e33bdbb ("sctp: avoid refreshing heartbeat timer too often")
Reported-by: Marcin Stojek <marcin.stojek@nokia.com>
Tested-by: Marcin Stojek <marcin.stojek@nokia.com>
Signed-off-by: Maciej Kwiecien <maciej.kwiecien@nokia.com>
Reviewed-by: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/sctp/transport.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 033696e6f74fb..ad158d311ffae 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -207,7 +207,8 @@ void sctp_transport_reset_hb_timer(struct sctp_transport *transport)
 
 	/* When a data chunk is sent, reset the heartbeat interval.  */
 	expires = jiffies + sctp_transport_timeout(transport);
-	if (time_before(transport->hb_timer.expires, expires) &&
+	if ((time_before(transport->hb_timer.expires, expires) ||
+	     !timer_pending(&transport->hb_timer)) &&
 	    !mod_timer(&transport->hb_timer,
 		       expires + prandom_u32_max(transport->rto)))
 		sctp_transport_hold(transport);
-- 
2.20.1

[PATCH AUTOSEL 4.19 195/219] bpf: decrease usercnt if bpf_map_new_fd() fails in bpf_map_get_fd_by_id()

[Sasha Levin]

From: Peng Sun <sironhide0null@gmail.com>

[ Upstream commit 781e62823cb81b972dc8652c1827205cda2ac9ac ]

In bpf/syscall.c, bpf_map_get_fd_by_id() use bpf_map_inc_not_zero()
to increase the refcount, both map->refcnt and map->usercnt. Then, if
bpf_map_new_fd() fails, should handle map->usercnt too.

Fixes: bd5f5f4ecb78 ("bpf: Add BPF_MAP_GET_FD_BY_ID")
Signed-off-by: Peng Sun <sironhide0null@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/bpf/syscall.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 6e544e364821e..90bb0c05c10e9 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1887,7 +1887,7 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr)
 
 	fd = bpf_map_new_fd(map, f_flags);
 	if (fd < 0)
-		bpf_map_put(map);
+		bpf_map_put_with_uref(map);
 
 	return fd;
 }
-- 
2.20.1

[PATCH AUTOSEL 4.19 197/219] net: dev: Use unsigned integer as an argument to left-shift

[Sasha Levin]

From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>

[ Upstream commit f4d7b3e23d259c44f1f1c39645450680fcd935d6 ]

1 << 31 is Undefined Behaviour according to the C standard.
Use U type modifier to avoid theoretical overflow.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/linux/netdevice.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 8c2fec0bcb265..5ada5fd9652dd 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3790,7 +3790,7 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits)
 	if (debug_value == 0)	/* no output */
 		return 0;
 	/* set low N bits */
-	return (1 << debug_value) - 1;
+	return (1U << debug_value) - 1;
 }
 
 static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu)
-- 
2.20.1

[PATCH AUTOSEL 4.19 199/219] bpf: drop refcount if bpf_map_new_fd() fails in map_create()

[Sasha Levin]

From: Peng Sun <sironhide0null@gmail.com>

[ Upstream commit 352d20d611414715353ee65fc206ee57ab1a6984 ]

In bpf/syscall.c, map_create() first set map->usercnt to 1, a file
descriptor is supposed to return to userspace. When bpf_map_new_fd()
fails, drop the refcount.

Fixes: bd5f5f4ecb78 ("bpf: Add BPF_MAP_GET_FD_BY_ID")
Signed-off-by: Peng Sun <sironhide0null@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/bpf/syscall.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 90bb0c05c10e9..596959288eb9e 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -559,12 +559,12 @@ static int map_create(union bpf_attr *attr)
 	err = bpf_map_new_fd(map, f_flags);
 	if (err < 0) {
 		/* failed to allocate fd.
-		 * bpf_map_put() is needed because the above
+		 * bpf_map_put_with_uref() is needed because the above
 		 * bpf_map_alloc_id() has published the map
 		 * to the userspace and the userspace may
 		 * have refcnt-ed it through BPF_MAP_GET_FD_BY_ID.
 		 */
-		bpf_map_put(map);
+		bpf_map_put_with_uref(map);
 		return err;
 	}
 
-- 
2.20.1

[PATCH AUTOSEL 4.19 200/219] net: hns3: Change fw error code NOT_EXEC to NOT_SUPPORTED

[Sasha Levin]

From: Yunsheng Lin <linyunsheng@huawei.com>

[ Upstream commit 4a402f47cfce904051cd8b31bef4fe2910d9dce9 ]

According to firmware error code definition, the error code of 2
means NOT_SUPPORTED, this patch changes it to NOT_SUPPORTED.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c | 2 ++
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index 68026a5ad7e77..8fe3a0d2e5f1c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -260,6 +260,8 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 
 			if (desc_ret == HCLGE_CMD_EXEC_SUCCESS)
 				retval = 0;
+			else if (desc_ret == HCLGE_CMD_NOT_SUPPORTED)
+				retval = -EOPNOTSUPP;
 			else
 				retval = -EIO;
 			hw->cmq.last_status = desc_ret;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 821d4c2f84bd3..d7520686509fd 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -39,7 +39,7 @@ struct hclge_cmq_ring {
 enum hclge_cmd_return_status {
 	HCLGE_CMD_EXEC_SUCCESS	= 0,
 	HCLGE_CMD_NO_AUTH	= 1,
-	HCLGE_CMD_NOT_EXEC	= 2,
+	HCLGE_CMD_NOT_SUPPORTED	= 2,
 	HCLGE_CMD_QUEUE_FULL	= 3,
 };
 
-- 
2.20.1

[PATCH AUTOSEL 4.19 201/219] net: hns3: fix PFC not setting problem for DCB module

[Sasha Levin]

From: Yunsheng Lin <linyunsheng@huawei.com>

[ Upstream commit d3ad430ac531e65f29c9737f86744c425c9173ef ]

The PFC enabling is based on user priority, currently it is
based on TC, which may cause PFC not setting correctly when pri
to TC mapping is not one to one relation.

This patch adds pfc_en in tm_info to fix it.

Fixes: cacde272dd00 ("net: hns3: Add hclge_dcb module for the support of DCB feature")
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c  | 7 ++++---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 1 +
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c   | 2 +-
 3 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
index 92f19384e2585..a75d7c826fc2b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
@@ -245,6 +245,9 @@ static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc)
 	    hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE)
 		return -EINVAL;
 
+	if (pfc->pfc_en == hdev->tm_info.pfc_en)
+		return 0;
+
 	prio_tc = hdev->tm_info.prio_tc;
 	pfc_map = 0;
 
@@ -257,10 +260,8 @@ static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc)
 		}
 	}
 
-	if (pfc_map == hdev->tm_info.hw_pfc_map)
-		return 0;
-
 	hdev->tm_info.hw_pfc_map = pfc_map;
+	hdev->tm_info.pfc_en = pfc->pfc_en;
 
 	return hclge_pause_setup_hw(hdev);
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 1528fb3fa6be6..260b1e7796908 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -249,6 +249,7 @@ struct hclge_tm_info {
 	struct hclge_tc_info tc_info[HNAE3_MAX_TC];
 	enum hclge_fc_mode fc_mode;
 	u8 hw_pfc_map; /* Allow for packet drop or not on this TC */
+	u8 pfc_en;	/* PFC enabled or not for user priority */
 };
 
 struct hclge_comm_stats_str {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 11e9259ca0407..daf364e421b73 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -1162,7 +1162,7 @@ static int hclge_pfc_setup_hw(struct hclge_dev *hdev)
 				HCLGE_RX_MAC_PAUSE_EN_MSK;
 
 	return hclge_pfc_pause_en_cfg(hdev, enable_bitmap,
-				      hdev->tm_info.hw_pfc_map);
+				      hdev->tm_info.pfc_en);
 }
 
 /* Each Tc has a 1024 queue sets to backpress, it divides to
-- 
2.20.1

[PATCH AUTOSEL 4.19 202/219] net: hns3: fix an issue for hclgevf_ae_get_hdev

[Sasha Levin]

From: Peng Li <lipeng321@huawei.com>

[ Upstream commit eed9535f9f716a532ec0c5d6cc7a48584acdf435 ]

HNS3 VF driver support NIC and Roce, hdev stores NIC
handle and Roce handle, should use correct parameter for
container_of.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 5570fb5dc2eb4..f6a579220ec18 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -26,7 +26,12 @@ MODULE_DEVICE_TABLE(pci, ae_algovf_pci_tbl);
 static inline struct hclgevf_dev *hclgevf_ae_get_hdev(
 	struct hnae3_handle *handle)
 {
-	return container_of(handle, struct hclgevf_dev, nic);
+	if (!handle->client)
+		return container_of(handle, struct hclgevf_dev, nic);
+	else if (handle->client->type == HNAE3_CLIENT_ROCE)
+		return container_of(handle, struct hclgevf_dev, roce);
+	else
+		return container_of(handle, struct hclgevf_dev, nic);
 }
 
 static int hclgevf_tqps_update_stats(struct hnae3_handle *handle)
-- 
2.20.1

[PATCH AUTOSEL 4.19 203/219] net: hns3: fix an issue for hns3_update_new_int_gl

[Sasha Levin]

From: Peng Li <lipeng321@huawei.com>

[ Upstream commit 6241e71e7207102ffc733991f7a00f74098d7da0 ]

HNS3 supports setting rx-usecs|tx-usecs as 0, but it will not
update dynamically when adaptive-tx or adaptive-rx is enable.
This patch removes the Redundant check.

Fixes: a95e1f8666e9 ("net: hns3: change the time interval of int_gl calculating")
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 0ccfa6a845353..0ea791e0ae0f5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2377,7 +2377,7 @@ static bool hns3_get_new_int_gl(struct hns3_enet_ring_group *ring_group)
 	u32 time_passed_ms;
 	u16 new_int_gl;
 
-	if (!ring_group->coal.int_gl || !tqp_vector->last_jiffies)
+	if (!tqp_vector->last_jiffies)
 		return false;
 
 	if (ring_group->total_packets == 0) {
-- 
2.20.1

[PATCH AUTOSEL 4.19 218/219] xdp: fix cpumap redirect SKB creation bug

[Sasha Levin]

From: Jesper Dangaard Brouer <brouer@redhat.com>

[ Upstream commit 676e4a6fe703f2dae699ee9d56f14516f9ada4ea ]

We want to avoid leaking pointer info from xdp_frame (that is placed in
top of frame) like commit 6dfb970d3dbd ("xdp: avoid leaking info stored in
frame data on page reuse"), and followup commit 97e19cce05e5 ("bpf:
reserve xdp_frame size in xdp headroom") that reserve this headroom.

These changes also affected how cpumap constructed SKBs, as xdpf->headroom
size changed, the skb data starting point were in-effect shifted with 32
bytes (sizeof xdp_frame). This was still okay, as the cpumap frame_size
calculation also included xdpf->headroom which were reduced by same amount.

A bug was introduced in commit 77ea5f4cbe20 ("bpf/cpumap: make sure
frame_size for build_skb is aligned if headroom isn't"), where the
xdpf->headroom became part of the SKB_DATA_ALIGN rounding up. This
round-up to find the frame_size is in principle still correct as it does
not exceed the 2048 bytes frame_size (which is max for ixgbe and i40e),
but the 32 bytes offset of pkt_data_start puts this over the 2048 bytes
limit. This cause skb_shared_info to spill into next frame. It is a little
hard to trigger, as the SKB need to use above 15 skb_shinfo->frags[] as
far as I calculate. This does happen in practise for TCP streams when
skb_try_coalesce() kicks in.

KASAN can be used to detect these wrong memory accesses, I've seen:
 BUG: KASAN: use-after-free in skb_try_coalesce+0x3cb/0x760
 BUG: KASAN: wild-memory-access in skb_release_data+0xe2/0x250

Driver veth also construct a SKB from xdp_frame in this way, but is not
affected, as it doesn't reserve/deduct the room (used by xdp_frame) from
the SKB headroom. Instead is clears the pointers via xdp_scrub_frame(),
and allows SKB to use this area.

The fix in this patch is to do like veth and instead allow SKB to (re)use
the area occupied by xdp_frame, by clearing via xdp_scrub_frame().  (This
does kill the idea of the SKB being able to access (mem) info from this
area, but I guess it was a bad idea anyhow, and it was already killed by
the veth changes.)

Fixes: 77ea5f4cbe20 ("bpf/cpumap: make sure frame_size for build_skb is aligned if headroom isn't")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/bpf/cpumap.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 8974b3755670e..3c18260403dde 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -162,10 +162,14 @@ static void cpu_map_kthread_stop(struct work_struct *work)
 static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
 					 struct xdp_frame *xdpf)
 {
+	unsigned int hard_start_headroom;
 	unsigned int frame_size;
 	void *pkt_data_start;
 	struct sk_buff *skb;
 
+	/* Part of headroom was reserved to xdpf */
+	hard_start_headroom = sizeof(struct xdp_frame) +  xdpf->headroom;
+
 	/* build_skb need to place skb_shared_info after SKB end, and
 	 * also want to know the memory "truesize".  Thus, need to
 	 * know the memory frame size backing xdp_buff.
@@ -183,15 +187,15 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
 	 * is not at a fixed memory location, with mixed length
 	 * packets, which is bad for cache-line hotness.
 	 */
-	frame_size = SKB_DATA_ALIGN(xdpf->len + xdpf->headroom) +
+	frame_size = SKB_DATA_ALIGN(xdpf->len + hard_start_headroom) +
 		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
-	pkt_data_start = xdpf->data - xdpf->headroom;
+	pkt_data_start = xdpf->data - hard_start_headroom;
 	skb = build_skb(pkt_data_start, frame_size);
 	if (!skb)
 		return NULL;
 
-	skb_reserve(skb, xdpf->headroom);
+	skb_reserve(skb, hard_start_headroom);
 	__skb_put(skb, xdpf->len);
 	if (xdpf->metasize)
 		skb_metadata_set(skb, xdpf->metasize);
@@ -205,6 +209,9 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
 	 * - RX ring dev queue index	(skb_record_rx_queue)
 	 */
 
+	/* Allow SKB to reuse area used by xdp_frame */
+	xdp_scrub_frame(xdpf);
+
 	return skb;
 }
 
-- 
2.20.1