From d68f4e43a46ff1f772ff73085f96d44eb4163e9d Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 16 Dec 2019 14:18:42 +0100
Subject: mt76: fix LED link time failure

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

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

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

Fixes: 36f7e2b2bb1d ("mt76: do not use devm API for led classdev")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mac80211.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index b9f2a401041a..96018fd65779 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -378,7 +378,8 @@ void mt76_unregister_device(struct mt76_dev *dev)
 {
 	struct ieee80211_hw *hw = dev->hw;
 
-	mt76_led_cleanup(dev);
+	if (IS_ENABLED(CONFIG_MT76_LEDS))
+		mt76_led_cleanup(dev);
 	mt76_tx_status_check(dev, NULL, true);
 	ieee80211_unregister_hw(hw);
 }
-- 
cgit 


From b43e36d75e8727f78892652a25967a1ffa03d1d1 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 26 Nov 2019 07:49:56 +0300
Subject: mt76: Off by one in mt76_calc_rx_airtime()

The sband->bitrates[] array has "sband->n_bitrates" elements so this
check needs to be >= instead of > or we could read beyond the end of the
array.

These values come from when we call mt76_register_device():

	ret = mt76_register_device(&dev->mt76, true, mt7603_rates,
				   ARRAY_SIZE(mt7603_rates));

Here sband->bitrates[] is mt7603_rates[] and ->n_bitrates is the
ARRAY_SIZE()

Fixes: 5ce09c1a7907 ("mt76: track rx airtime for airtime fairness and survey")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/airtime.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/airtime.c b/drivers/net/wireless/mediatek/mt76/airtime.c
index 55116f395f9a..a4a785467748 100644
--- a/drivers/net/wireless/mediatek/mt76/airtime.c
+++ b/drivers/net/wireless/mediatek/mt76/airtime.c
@@ -242,7 +242,7 @@ u32 mt76_calc_rx_airtime(struct mt76_dev *dev, struct mt76_rx_status *status,
 			return 0;
 
 		sband = dev->hw->wiphy->bands[status->band];
-		if (!sband || status->rate_idx > sband->n_bitrates)
+		if (!sband || status->rate_idx >= sband->n_bitrates)
 			return 0;
 
 		rate = &sband->bitrates[status->rate_idx];
-- 
cgit 


From e5e884b42639c74b5b57dc277909915c0aefc8bb Mon Sep 17 00:00:00 2001
From: Wen Huang <huangwenabc@gmail.com>
Date: Thu, 28 Nov 2019 18:51:04 +0800
Subject: libertas: Fix two buffer overflows at parsing bss descriptor

add_ie_rates() copys rates without checking the length
in bss descriptor from remote AP.when victim connects to
remote attacker, this may trigger buffer overflow.
lbs_ibss_join_existing() copys rates without checking the length
in bss descriptor from remote IBSS node.when victim connects to
remote attacker, this may trigger buffer overflow.
Fix them by putting the length check before performing copy.

This fix addresses CVE-2019-14896 and CVE-2019-14897.
This also fix build warning of mixed declarations and code.

Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Wen Huang <huangwenabc@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/marvell/libertas/cfg.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/marvell/libertas/cfg.c b/drivers/net/wireless/marvell/libertas/cfg.c
index 57edfada0665..c9401c121a14 100644
--- a/drivers/net/wireless/marvell/libertas/cfg.c
+++ b/drivers/net/wireless/marvell/libertas/cfg.c
@@ -273,6 +273,10 @@ add_ie_rates(u8 *tlv, const u8 *ie, int *nrates)
 	int hw, ap, ap_max = ie[1];
 	u8 hw_rate;
 
+	if (ap_max > MAX_RATES) {
+		lbs_deb_assoc("invalid rates\n");
+		return tlv;
+	}
 	/* Advance past IE header */
 	ie += 2;
 
@@ -1717,6 +1721,9 @@ static int lbs_ibss_join_existing(struct lbs_private *priv,
 	struct cmd_ds_802_11_ad_hoc_join cmd;
 	u8 preamble = RADIO_PREAMBLE_SHORT;
 	int ret = 0;
+	int hw, i;
+	u8 rates_max;
+	u8 *rates;
 
 	/* TODO: set preamble based on scan result */
 	ret = lbs_set_radio(priv, preamble, 1);
@@ -1775,9 +1782,12 @@ static int lbs_ibss_join_existing(struct lbs_private *priv,
 	if (!rates_eid) {
 		lbs_add_rates(cmd.bss.rates);
 	} else {
-		int hw, i;
-		u8 rates_max = rates_eid[1];
-		u8 *rates = cmd.bss.rates;
+		rates_max = rates_eid[1];
+		if (rates_max > MAX_RATES) {
+			lbs_deb_join("invalid rates");
+			goto out;
+		}
+		rates = cmd.bss.rates;
 		for (hw = 0; hw < ARRAY_SIZE(lbs_rates); hw++) {
 			u8 hw_rate = lbs_rates[hw].bitrate / 5;
 			for (i = 0; i < rates_max; i++) {
-- 
cgit 


From 33328bfab892d676920abb440d41fbf4b16c2717 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <stf_xl@wp.pl>
Date: Thu, 19 Dec 2019 10:35:59 +0100
Subject: MAINTAINERS: change Gruszka's email address

My RedHat email address does not work any longer. Change to my private one.

Signed-off-by: Stanislaw Gruszka <stf_xl@wp.pl>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 MAINTAINERS | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index e34488f7baae..096a982c860c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8563,7 +8563,7 @@ S:	Maintained
 F:	drivers/platform/x86/intel-vbtn.c
 
 INTEL WIRELESS 3945ABG/BG, 4965AGN (iwlegacy)
-M:	Stanislaw Gruszka <sgruszka@redhat.com>
+M:	Stanislaw Gruszka <stf_xl@wp.pl>
 L:	linux-wireless@vger.kernel.org
 S:	Supported
 F:	drivers/net/wireless/intel/iwlegacy/
@@ -13817,7 +13817,7 @@ S:	Maintained
 F:	arch/mips/ralink
 
 RALINK RT2X00 WIRELESS LAN DRIVER
-M:	Stanislaw Gruszka <sgruszka@redhat.com>
+M:	Stanislaw Gruszka <stf_xl@wp.pl>
 M:	Helmut Schaa <helmut.schaa@googlemail.com>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
-- 
cgit 


From 160bab43419ebca9ee57219b2ccf02f0fa2c59e8 Mon Sep 17 00:00:00 2001
From: Gil Adam <gil.adam@intel.com>
Date: Thu, 7 Nov 2019 21:23:21 +0200
Subject: iwlwifi: don't send PPAG command if disabled

we should not send the PPAG (Per-Platform Antenna Gain)
command to FW unless the platform has this ACPI table and it was
read and validated during the init flow. also no need to send the
command if the feature is disabled, so check if enabled before
sending, as if there is no valid table the feature is disabled.

Signed-off-by: Gil Adam <gil.adam@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index dd685f7eb410..c09624d8d7ee 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -841,9 +841,13 @@ int iwl_mvm_ppag_send_cmd(struct iwl_mvm *mvm)
 		return 0;
 	}
 
+	if (!mvm->fwrt.ppag_table.enabled) {
+		IWL_DEBUG_RADIO(mvm,
+				"PPAG not enabled, command not sent.\n");
+		return 0;
+	}
+
 	IWL_DEBUG_RADIO(mvm, "Sending PER_PLATFORM_ANT_GAIN_CMD\n");
-	IWL_DEBUG_RADIO(mvm, "PPAG is %s\n",
-			mvm->fwrt.ppag_table.enabled ? "enabled" : "disabled");
 
 	for (i = 0; i < ACPI_PPAG_NUM_CHAINS; i++) {
 		for (j = 0; j < ACPI_PPAG_NUM_SUB_BANDS; j++) {
-- 
cgit 


From 7b02bf6194887eab2f8912f7284a9e407329a255 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 12 Nov 2019 15:18:16 +0100
Subject: iwlwifi: pcie: move page tracking into get_page_hdr()

Move the tracking that records the page in the SKB for later
free (refcount decrement) into the get_page_hdr() function
for better code reuse.

While at it, also add an assertion that this doesn't overwrite
any existing page pointer in the skb.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/internal.h |  3 ++-
 drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c  |  7 +------
 drivers/net/wireless/intel/iwlwifi/pcie/tx.c       | 20 +++++++++++++-------
 3 files changed, 16 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index a091690f6c79..3688911ce3df 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -1082,7 +1082,8 @@ void iwl_pcie_apply_destination(struct iwl_trans *trans);
 void iwl_pcie_free_tso_page(struct iwl_trans_pcie *trans_pcie,
 			    struct sk_buff *skb);
 #ifdef CONFIG_INET
-struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len);
+struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len,
+				      struct sk_buff *skb);
 #endif
 
 /* common functions that are used by gen3 transport */
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index 8ca0250de99e..494a8864368d 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -246,7 +246,6 @@ static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans,
 				     u8 hdr_len, struct iwl_device_cmd *dev_cmd)
 {
 #ifdef CONFIG_INET
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_tx_cmd_gen2 *tx_cmd = (void *)dev_cmd->payload;
 	struct ieee80211_hdr *hdr = (void *)skb->data;
 	unsigned int snap_ip_tcp_hdrlen, ip_hdrlen, total_len, hdr_room;
@@ -254,7 +253,6 @@ static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans,
 	u16 length, amsdu_pad;
 	u8 *start_hdr;
 	struct iwl_tso_hdr_page *hdr_page;
-	struct page **page_ptr;
 	struct tso_t tso;
 
 	trace_iwlwifi_dev_tx(trans->dev, skb, tfd, sizeof(*tfd),
@@ -270,14 +268,11 @@ static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans,
 		(3 + snap_ip_tcp_hdrlen + sizeof(struct ethhdr));
 
 	/* Our device supports 9 segments at most, it will fit in 1 page */
-	hdr_page = get_page_hdr(trans, hdr_room);
+	hdr_page = get_page_hdr(trans, hdr_room, skb);
 	if (!hdr_page)
 		return -ENOMEM;
 
-	get_page(hdr_page->page);
 	start_hdr = hdr_page->pos;
-	page_ptr = (void *)((u8 *)skb->cb + trans_pcie->page_offs);
-	*page_ptr = hdr_page->page;
 
 	/*
 	 * Pull the ieee80211 header to be able to use TSO core,
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index f21f16ab2a97..2d1758031a0a 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -2052,17 +2052,24 @@ static int iwl_fill_data_tbs(struct iwl_trans *trans, struct sk_buff *skb,
 }
 
 #ifdef CONFIG_INET
-struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len)
+struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len,
+				      struct sk_buff *skb)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_tso_hdr_page *p = this_cpu_ptr(trans_pcie->tso_hdr_page);
+	struct page **page_ptr;
+
+	page_ptr = (void *)((u8 *)skb->cb + trans_pcie->page_offs);
+
+	if (WARN_ON(*page_ptr))
+		return NULL;
 
 	if (!p->page)
 		goto alloc;
 
 	/* enough room on this page */
 	if (p->pos + len < (u8 *)page_address(p->page) + PAGE_SIZE)
-		return p;
+		goto out;
 
 	/* We don't have enough room on this page, get a new one. */
 	__free_page(p->page);
@@ -2072,6 +2079,9 @@ alloc:
 	if (!p->page)
 		return NULL;
 	p->pos = page_address(p->page);
+out:
+	*page_ptr = p->page;
+	get_page(p->page);
 	return p;
 }
 
@@ -2107,7 +2117,6 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb,
 	u16 length, iv_len, amsdu_pad;
 	u8 *start_hdr;
 	struct iwl_tso_hdr_page *hdr_page;
-	struct page **page_ptr;
 	struct tso_t tso;
 
 	/* if the packet is protected, then it must be CCMP or GCMP */
@@ -2130,14 +2139,11 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb,
 		(3 + snap_ip_tcp_hdrlen + sizeof(struct ethhdr)) + iv_len;
 
 	/* Our device supports 9 segments at most, it will fit in 1 page */
-	hdr_page = get_page_hdr(trans, hdr_room);
+	hdr_page = get_page_hdr(trans, hdr_room, skb);
 	if (!hdr_page)
 		return -ENOMEM;
 
-	get_page(hdr_page->page);
 	start_hdr = hdr_page->pos;
-	page_ptr = (void *)((u8 *)skb->cb + trans_pcie->page_offs);
-	*page_ptr = hdr_page->page;
 	memcpy(hdr_page->pos, skb->data + hdr_len, iv_len);
 	hdr_page->pos += iv_len;
 
-- 
cgit 


From c4a786b32621850775dedd1a329de0c060f9c904 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 12 Nov 2019 10:32:42 +0100
Subject: iwlwifi: pcie: work around DMA hardware bug

There's a hardware bug in the flow handler (DMA engine), if the
address + len of some TB wraps around a 2^32 boundary, the carry
bit is then carried over into the next TB.

Work around this by copying the data to a new page when we find
this situation, and then copy it in a way that we cannot hit the
very end of the page.

To be able to free the new page again later we need to chain it
to the TSO page, use the last pointer there to make sure we can
never use the page fully for DMA, and thus cannot cause the same
overflow situation on this page.

This leaves a few potential places (where we didn't observe the
problem) unaddressed:
 * The second TB could reach or cross the end of a page (and thus
   2^32) due to the way we allocate the dev_cmd for the header
 * For host commands, a similar thing could happen since they're
   just kmalloc().
We'll address these in further commits.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c | 179 ++++++++++++++++++----
 drivers/net/wireless/intel/iwlwifi/pcie/tx.c      |  28 +++-
 2 files changed, 176 insertions(+), 31 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index 494a8864368d..8abadfbc793a 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -213,6 +213,16 @@ static void iwl_pcie_gen2_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq)
 	}
 }
 
+/*
+ * We need this inline in case dma_addr_t is only 32-bits - since the
+ * hardware is always 64-bit, the issue can still occur in that case,
+ * so use u64 for 'phys' here to force the addition in 64-bit.
+ */
+static inline bool crosses_4g_boundary(u64 phys, u16 len)
+{
+	return upper_32_bits(phys) != upper_32_bits(phys + len);
+}
+
 static int iwl_pcie_gen2_set_tb(struct iwl_trans *trans,
 				struct iwl_tfh_tfd *tfd, dma_addr_t addr,
 				u16 len)
@@ -240,6 +250,107 @@ static int iwl_pcie_gen2_set_tb(struct iwl_trans *trans,
 	return idx;
 }
 
+static struct page *get_workaround_page(struct iwl_trans *trans,
+					struct sk_buff *skb)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct page **page_ptr;
+	struct page *ret;
+
+	page_ptr = (void *)((u8 *)skb->cb + trans_pcie->page_offs);
+
+	ret = alloc_page(GFP_ATOMIC);
+	if (!ret)
+		return NULL;
+
+	/* set the chaining pointer to the previous page if there */
+	*(void **)(page_address(ret) + PAGE_SIZE - sizeof(void *)) = *page_ptr;
+	*page_ptr = ret;
+
+	return ret;
+}
+
+/*
+ * Add a TB and if needed apply the FH HW bug workaround;
+ * meta != NULL indicates that it's a page mapping and we
+ * need to dma_unmap_page() and set the meta->tbs bit in
+ * this case.
+ */
+static int iwl_pcie_gen2_set_tb_with_wa(struct iwl_trans *trans,
+					struct sk_buff *skb,
+					struct iwl_tfh_tfd *tfd,
+					dma_addr_t phys, void *virt,
+					u16 len, struct iwl_cmd_meta *meta)
+{
+	dma_addr_t oldphys = phys;
+	struct page *page;
+	int ret;
+
+	if (unlikely(dma_mapping_error(trans->dev, phys)))
+		return -ENOMEM;
+
+	if (likely(!crosses_4g_boundary(phys, len))) {
+		ret = iwl_pcie_gen2_set_tb(trans, tfd, phys, len);
+
+		if (ret < 0)
+			goto unmap;
+
+		if (meta)
+			meta->tbs |= BIT(ret);
+
+		ret = 0;
+		goto trace;
+	}
+
+	/*
+	 * Work around a hardware bug. If (as expressed in the
+	 * condition above) the TB ends on a 32-bit boundary,
+	 * then the next TB may be accessed with the wrong
+	 * address.
+	 * To work around it, copy the data elsewhere and make
+	 * a new mapping for it so the device will not fail.
+	 */
+
+	if (WARN_ON(len > PAGE_SIZE - sizeof(void *))) {
+		ret = -ENOBUFS;
+		goto unmap;
+	}
+
+	page = get_workaround_page(trans, skb);
+	if (!page) {
+		ret = -ENOMEM;
+		goto unmap;
+	}
+
+	memcpy(page_address(page), virt, len);
+
+	phys = dma_map_single(trans->dev, page_address(page), len,
+			      DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(trans->dev, phys)))
+		return -ENOMEM;
+	ret = iwl_pcie_gen2_set_tb(trans, tfd, phys, len);
+	if (ret < 0) {
+		/* unmap the new allocation as single */
+		oldphys = phys;
+		meta = NULL;
+		goto unmap;
+	}
+	IWL_WARN(trans,
+		 "TB bug workaround: copied %d bytes from 0x%llx to 0x%llx\n",
+		 len, (unsigned long long)oldphys, (unsigned long long)phys);
+
+	ret = 0;
+unmap:
+	if (meta)
+		dma_unmap_page(trans->dev, oldphys, len, DMA_TO_DEVICE);
+	else
+		dma_unmap_single(trans->dev, oldphys, len, DMA_TO_DEVICE);
+trace:
+	trace_iwlwifi_dev_tx_tb(trans->dev, skb, virt, phys, len);
+
+	return ret;
+}
+
 static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans,
 				     struct sk_buff *skb,
 				     struct iwl_tfh_tfd *tfd, int start_len,
@@ -327,6 +438,11 @@ static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans,
 			dev_kfree_skb(csum_skb);
 			goto out_err;
 		}
+		/*
+		 * No need for _with_wa, this is from the TSO page and
+		 * we leave some space at the end of it so can't hit
+		 * the buggy scenario.
+		 */
 		iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, tb_len);
 		trace_iwlwifi_dev_tx_tb(trans->dev, skb, start_hdr,
 					tb_phys, tb_len);
@@ -338,16 +454,18 @@ static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans,
 
 		/* put the payload */
 		while (data_left) {
+			int ret;
+
 			tb_len = min_t(unsigned int, tso.size, data_left);
 			tb_phys = dma_map_single(trans->dev, tso.data,
 						 tb_len, DMA_TO_DEVICE);
-			if (unlikely(dma_mapping_error(trans->dev, tb_phys))) {
+			ret = iwl_pcie_gen2_set_tb_with_wa(trans, skb, tfd,
+							   tb_phys, tso.data,
+							   tb_len, NULL);
+			if (ret) {
 				dev_kfree_skb(csum_skb);
 				goto out_err;
 			}
-			iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, tb_len);
-			trace_iwlwifi_dev_tx_tb(trans->dev, skb, tso.data,
-						tb_phys, tb_len);
 
 			data_left -= tb_len;
 			tso_build_data(skb, &tso, tb_len);
@@ -381,6 +499,11 @@ iwl_tfh_tfd *iwl_pcie_gen2_build_tx_amsdu(struct iwl_trans *trans,
 
 	tb_phys = iwl_pcie_get_first_tb_dma(txq, idx);
 
+	/*
+	 * No need for _with_wa, the first TB allocation is aligned up
+	 * to a 64-byte boundary and thus can't be at the end or cross
+	 * a page boundary (much less a 2^32 boundary).
+	 */
 	iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, IWL_FIRST_TB_SIZE);
 
 	/*
@@ -425,24 +548,19 @@ static int iwl_pcie_gen2_tx_add_frags(struct iwl_trans *trans,
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 		dma_addr_t tb_phys;
-		int tb_idx;
+		unsigned int fragsz = skb_frag_size(frag);
+		int ret;
 
-		if (!skb_frag_size(frag))
+		if (!fragsz)
 			continue;
 
 		tb_phys = skb_frag_dma_map(trans->dev, frag, 0,
-					   skb_frag_size(frag), DMA_TO_DEVICE);
-
-		if (unlikely(dma_mapping_error(trans->dev, tb_phys)))
-			return -ENOMEM;
-		tb_idx = iwl_pcie_gen2_set_tb(trans, tfd, tb_phys,
-					      skb_frag_size(frag));
-		trace_iwlwifi_dev_tx_tb(trans->dev, skb, skb_frag_address(frag),
-					tb_phys, skb_frag_size(frag));
-		if (tb_idx < 0)
-			return tb_idx;
-
-		out_meta->tbs |= BIT(tb_idx);
+					   fragsz, DMA_TO_DEVICE);
+		ret = iwl_pcie_gen2_set_tb_with_wa(trans, skb, tfd, tb_phys,
+						   skb_frag_address(frag),
+						   fragsz, out_meta);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
@@ -470,6 +588,11 @@ iwl_tfh_tfd *iwl_pcie_gen2_build_tx(struct iwl_trans *trans,
 	/* The first TB points to bi-directional DMA data */
 	memcpy(&txq->first_tb_bufs[idx], dev_cmd, IWL_FIRST_TB_SIZE);
 
+	/*
+	 * No need for _with_wa, the first TB allocation is aligned up
+	 * to a 64-byte boundary and thus can't be at the end or cross
+	 * a page boundary (much less a 2^32 boundary).
+	 */
 	iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, IWL_FIRST_TB_SIZE);
 
 	/*
@@ -499,26 +622,30 @@ iwl_tfh_tfd *iwl_pcie_gen2_build_tx(struct iwl_trans *trans,
 	tb2_len = skb_headlen(skb) - hdr_len;
 
 	if (tb2_len > 0) {
+		int ret;
+
 		tb_phys = dma_map_single(trans->dev, skb->data + hdr_len,
 					 tb2_len, DMA_TO_DEVICE);
-		if (unlikely(dma_mapping_error(trans->dev, tb_phys)))
+		ret = iwl_pcie_gen2_set_tb_with_wa(trans, skb, tfd, tb_phys,
+						   skb->data + hdr_len, tb2_len,
+						   NULL);
+		if (ret)
 			goto out_err;
-		iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, tb2_len);
-		trace_iwlwifi_dev_tx_tb(trans->dev, skb, skb->data + hdr_len,
-					tb_phys, tb2_len);
 	}
 
 	if (iwl_pcie_gen2_tx_add_frags(trans, skb, tfd, out_meta))
 		goto out_err;
 
 	skb_walk_frags(skb, frag) {
+		int ret;
+
 		tb_phys = dma_map_single(trans->dev, frag->data,
 					 skb_headlen(frag), DMA_TO_DEVICE);
-		if (unlikely(dma_mapping_error(trans->dev, tb_phys)))
+		ret = iwl_pcie_gen2_set_tb_with_wa(trans, skb, tfd, tb_phys,
+						   frag->data,
+						   skb_headlen(frag), NULL);
+		if (ret)
 			goto out_err;
-		iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, skb_headlen(frag));
-		trace_iwlwifi_dev_tx_tb(trans->dev, skb, frag->data,
-					tb_phys, skb_headlen(frag));
 		if (iwl_pcie_gen2_tx_add_frags(trans, frag, tfd, out_meta))
 			goto out_err;
 	}
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index 2d1758031a0a..ba37b780dec4 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -624,12 +624,18 @@ void iwl_pcie_free_tso_page(struct iwl_trans_pcie *trans_pcie,
 			    struct sk_buff *skb)
 {
 	struct page **page_ptr;
+	struct page *next;
 
 	page_ptr = (void *)((u8 *)skb->cb + trans_pcie->page_offs);
+	next = *page_ptr;
+	*page_ptr = NULL;
 
-	if (*page_ptr) {
-		__free_page(*page_ptr);
-		*page_ptr = NULL;
+	while (next) {
+		struct page *tmp = next;
+
+		next = *(void **)(page_address(next) + PAGE_SIZE -
+				  sizeof(void *));
+		__free_page(tmp);
 	}
 }
 
@@ -2067,8 +2073,18 @@ struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len,
 	if (!p->page)
 		goto alloc;
 
-	/* enough room on this page */
-	if (p->pos + len < (u8 *)page_address(p->page) + PAGE_SIZE)
+	/*
+	 * Check if there's enough room on this page
+	 *
+	 * Note that we put a page chaining pointer *last* in the
+	 * page - we need it somewhere, and if it's there then we
+	 * avoid DMA mapping the last bits of the page which may
+	 * trigger the 32-bit boundary hardware bug.
+	 *
+	 * (see also get_workaround_page() in tx-gen2.c)
+	 */
+	if (p->pos + len < (u8 *)page_address(p->page) + PAGE_SIZE -
+			   sizeof(void *))
 		goto out;
 
 	/* We don't have enough room on this page, get a new one. */
@@ -2079,6 +2095,8 @@ alloc:
 	if (!p->page)
 		return NULL;
 	p->pos = page_address(p->page);
+	/* set the chaining pointer to NULL */
+	*(void **)(page_address(p->page) + PAGE_SIZE - sizeof(void *)) = NULL;
 out:
 	*page_ptr = p->page;
 	get_page(p->page);
-- 
cgit 


From c5a4e8eb683c6a80c6907c12acf7b66665ef4b0b Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 14 Nov 2019 09:26:20 +0100
Subject: iwlwifi: pcie: detect the DMA bug and warn if it happens

Warn if the DMA bug is going to happen. We don't have a good
way of actually aborting in this case and we have workarounds
in place for the cases where it happens, but in order to not
be surprised add a safety-check and warn.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index 8abadfbc793a..a2dc380ac17c 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -231,6 +231,17 @@ static int iwl_pcie_gen2_set_tb(struct iwl_trans *trans,
 	int idx = iwl_pcie_gen2_get_num_tbs(trans, tfd);
 	struct iwl_tfh_tb *tb;
 
+	/*
+	 * Only WARN here so we know about the issue, but we mess up our
+	 * unmap path because not every place currently checks for errors
+	 * returned from this function - it can only return an error if
+	 * there's no more space, and so when we know there is enough we
+	 * don't always check ...
+	 */
+	WARN(crosses_4g_boundary(addr, len),
+	     "possible DMA problem with iova:0x%llx, len:%d\n",
+	     (unsigned long long)addr, len);
+
 	if (WARN_ON(idx >= IWL_TFH_NUM_TBS))
 		return -EINVAL;
 	tb = &tfd->tbs[idx];
-- 
cgit 


From a89c72ffd07369f5ccc74f0332d2785a7077241d Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 14 Nov 2019 09:09:34 +0100
Subject: iwlwifi: pcie: allocate smaller dev_cmd for TX headers

As noted in the previous commit, due to the way we allocate the
dev_cmd headers with 324 byte size, and 4/8 byte alignment, the
part we use of them (bytes 20..40-68) could still cross a page
and thus 2^32 boundary.

Address this by using alignment to ensure that the allocation
cannot cross a page boundary, on hardware that's affected. To
make that not cause more memory consumption, reduce the size of
the allocations to the necessary size - we go from 324 bytes in
each allocation to 60/68 on gen2 depending on family, and ~120
or so on gen1 (so on gen1 it's a pure reduction in size, since
we don't need alignment there).

To avoid size and clearing issues, add a new structure that's
just the header, and use kmem_cache_zalloc().

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/dvm/tx.c        |  3 +-
 drivers/net/wireless/intel/iwlwifi/iwl-trans.c     | 10 +++----
 drivers/net/wireless/intel/iwlwifi/iwl-trans.h     | 26 ++++++++++++++----
 drivers/net/wireless/intel/iwlwifi/mvm/tx.c        | 15 ++++------
 drivers/net/wireless/intel/iwlwifi/pcie/internal.h |  6 ++--
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c    | 32 ++++++++++++++++------
 drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c  | 21 ++++++++++----
 drivers/net/wireless/intel/iwlwifi/pcie/tx.c       | 20 ++++++++------
 8 files changed, 84 insertions(+), 49 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/tx.c b/drivers/net/wireless/intel/iwlwifi/dvm/tx.c
index cd73fc5cfcbb..fd454836adbe 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/tx.c
@@ -267,7 +267,7 @@ int iwlagn_tx_skb(struct iwl_priv *priv,
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct iwl_station_priv *sta_priv = NULL;
 	struct iwl_rxon_context *ctx = &priv->contexts[IWL_RXON_CTX_BSS];
-	struct iwl_device_cmd *dev_cmd;
+	struct iwl_device_tx_cmd *dev_cmd;
 	struct iwl_tx_cmd *tx_cmd;
 	__le16 fc;
 	u8 hdr_len;
@@ -348,7 +348,6 @@ int iwlagn_tx_skb(struct iwl_priv *priv,
 	if (unlikely(!dev_cmd))
 		goto drop_unlock_priv;
 
-	memset(dev_cmd, 0, sizeof(*dev_cmd));
 	dev_cmd->hdr.cmd = REPLY_TX;
 	tx_cmd = (struct iwl_tx_cmd *) dev_cmd->payload;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
index 28bdc9a9617e..f91197e4ae40 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
@@ -66,7 +66,9 @@
 
 struct iwl_trans *iwl_trans_alloc(unsigned int priv_size,
 				  struct device *dev,
-				  const struct iwl_trans_ops *ops)
+				  const struct iwl_trans_ops *ops,
+				  unsigned int cmd_pool_size,
+				  unsigned int cmd_pool_align)
 {
 	struct iwl_trans *trans;
 #ifdef CONFIG_LOCKDEP
@@ -90,10 +92,8 @@ struct iwl_trans *iwl_trans_alloc(unsigned int priv_size,
 		 "iwl_cmd_pool:%s", dev_name(trans->dev));
 	trans->dev_cmd_pool =
 		kmem_cache_create(trans->dev_cmd_pool_name,
-				  sizeof(struct iwl_device_cmd),
-				  sizeof(void *),
-				  SLAB_HWCACHE_ALIGN,
-				  NULL);
+				  cmd_pool_size, cmd_pool_align,
+				  SLAB_HWCACHE_ALIGN, NULL);
 	if (!trans->dev_cmd_pool)
 		return NULL;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 8cadad7364ac..e33df5ad00e0 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -193,6 +193,18 @@ struct iwl_device_cmd {
 	};
 } __packed;
 
+/**
+ * struct iwl_device_tx_cmd - buffer for TX command
+ * @hdr: the header
+ * @payload: the payload placeholder
+ *
+ * The actual structure is sized dynamically according to need.
+ */
+struct iwl_device_tx_cmd {
+	struct iwl_cmd_header hdr;
+	u8 payload[];
+} __packed;
+
 #define TFD_MAX_PAYLOAD_SIZE (sizeof(struct iwl_device_cmd))
 
 /*
@@ -544,7 +556,7 @@ struct iwl_trans_ops {
 	int (*send_cmd)(struct iwl_trans *trans, struct iwl_host_cmd *cmd);
 
 	int (*tx)(struct iwl_trans *trans, struct sk_buff *skb,
-		  struct iwl_device_cmd *dev_cmd, int queue);
+		  struct iwl_device_tx_cmd *dev_cmd, int queue);
 	void (*reclaim)(struct iwl_trans *trans, int queue, int ssn,
 			struct sk_buff_head *skbs);
 
@@ -948,22 +960,22 @@ iwl_trans_dump_data(struct iwl_trans *trans, u32 dump_mask)
 	return trans->ops->dump_data(trans, dump_mask);
 }
 
-static inline struct iwl_device_cmd *
+static inline struct iwl_device_tx_cmd *
 iwl_trans_alloc_tx_cmd(struct iwl_trans *trans)
 {
-	return kmem_cache_alloc(trans->dev_cmd_pool, GFP_ATOMIC);
+	return kmem_cache_zalloc(trans->dev_cmd_pool, GFP_ATOMIC);
 }
 
 int iwl_trans_send_cmd(struct iwl_trans *trans, struct iwl_host_cmd *cmd);
 
 static inline void iwl_trans_free_tx_cmd(struct iwl_trans *trans,
-					 struct iwl_device_cmd *dev_cmd)
+					 struct iwl_device_tx_cmd *dev_cmd)
 {
 	kmem_cache_free(trans->dev_cmd_pool, dev_cmd);
 }
 
 static inline int iwl_trans_tx(struct iwl_trans *trans, struct sk_buff *skb,
-			       struct iwl_device_cmd *dev_cmd, int queue)
+			       struct iwl_device_tx_cmd *dev_cmd, int queue)
 {
 	if (unlikely(test_bit(STATUS_FW_ERROR, &trans->status)))
 		return -EIO;
@@ -1271,7 +1283,9 @@ static inline bool iwl_trans_dbg_ini_valid(struct iwl_trans *trans)
  *****************************************************/
 struct iwl_trans *iwl_trans_alloc(unsigned int priv_size,
 				  struct device *dev,
-				  const struct iwl_trans_ops *ops);
+				  const struct iwl_trans_ops *ops,
+				  unsigned int cmd_pool_size,
+				  unsigned int cmd_pool_align);
 void iwl_trans_free(struct iwl_trans *trans);
 
 /*****************************************************
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index dc5c02fbc65a..80052ad1fa6d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -490,13 +490,13 @@ static void iwl_mvm_set_tx_cmd_crypto(struct iwl_mvm *mvm,
 /*
  * Allocates and sets the Tx cmd the driver data pointers in the skb
  */
-static struct iwl_device_cmd *
+static struct iwl_device_tx_cmd *
 iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 		      struct ieee80211_tx_info *info, int hdrlen,
 		      struct ieee80211_sta *sta, u8 sta_id)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
-	struct iwl_device_cmd *dev_cmd;
+	struct iwl_device_tx_cmd *dev_cmd;
 	struct iwl_tx_cmd *tx_cmd;
 
 	dev_cmd = iwl_trans_alloc_tx_cmd(mvm->trans);
@@ -504,11 +504,6 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 	if (unlikely(!dev_cmd))
 		return NULL;
 
-	/* Make sure we zero enough of dev_cmd */
-	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_gen2) > sizeof(*tx_cmd));
-	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_gen3) > sizeof(*tx_cmd));
-
-	memset(dev_cmd, 0, sizeof(dev_cmd->hdr) + sizeof(*tx_cmd));
 	dev_cmd->hdr.cmd = TX_CMD;
 
 	if (iwl_mvm_has_new_tx_api(mvm)) {
@@ -597,7 +592,7 @@ out:
 }
 
 static void iwl_mvm_skb_prepare_status(struct sk_buff *skb,
-				       struct iwl_device_cmd *cmd)
+				       struct iwl_device_tx_cmd *cmd)
 {
 	struct ieee80211_tx_info *skb_info = IEEE80211_SKB_CB(skb);
 
@@ -716,7 +711,7 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	struct ieee80211_tx_info info;
-	struct iwl_device_cmd *dev_cmd;
+	struct iwl_device_tx_cmd *dev_cmd;
 	u8 sta_id;
 	int hdrlen = ieee80211_hdrlen(hdr->frame_control);
 	__le16 fc = hdr->frame_control;
@@ -1078,7 +1073,7 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	struct iwl_mvm_sta *mvmsta;
-	struct iwl_device_cmd *dev_cmd;
+	struct iwl_device_tx_cmd *dev_cmd;
 	__le16 fc;
 	u16 seq_number = 0;
 	u8 tid = IWL_MAX_TID_COUNT;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index 3688911ce3df..04361ecf31bd 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -305,7 +305,7 @@ struct iwl_cmd_meta {
 #define IWL_FIRST_TB_SIZE_ALIGN ALIGN(IWL_FIRST_TB_SIZE, 64)
 
 struct iwl_pcie_txq_entry {
-	struct iwl_device_cmd *cmd;
+	void *cmd;
 	struct sk_buff *skb;
 	/* buffer to free after command completes */
 	const void *free_buf;
@@ -688,7 +688,7 @@ void iwl_trans_pcie_txq_set_shared_mode(struct iwl_trans *trans, u32 txq_id,
 void iwl_trans_pcie_log_scd_error(struct iwl_trans *trans,
 				  struct iwl_txq *txq);
 int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
-		      struct iwl_device_cmd *dev_cmd, int txq_id);
+		      struct iwl_device_tx_cmd *dev_cmd, int txq_id);
 void iwl_pcie_txq_check_wrptrs(struct iwl_trans *trans);
 int iwl_trans_pcie_send_hcmd(struct iwl_trans *trans, struct iwl_host_cmd *cmd);
 void iwl_pcie_cmdq_reclaim(struct iwl_trans *trans, int txq_id, int idx);
@@ -1107,7 +1107,7 @@ int iwl_trans_pcie_dyn_txq_alloc(struct iwl_trans *trans,
 				 unsigned int timeout);
 void iwl_trans_pcie_dyn_txq_free(struct iwl_trans *trans, int queue);
 int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
-			   struct iwl_device_cmd *dev_cmd, int txq_id);
+			   struct iwl_device_tx_cmd *dev_cmd, int txq_id);
 int iwl_trans_pcie_gen2_send_hcmd(struct iwl_trans *trans,
 				  struct iwl_host_cmd *cmd);
 void iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index a0677131634d..91fa439d1255 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -79,6 +79,7 @@
 #include "iwl-agn-hw.h"
 #include "fw/error-dump.h"
 #include "fw/dbg.h"
+#include "fw/api/tx.h"
 #include "internal.h"
 #include "iwl-fh.h"
 
@@ -3460,19 +3461,34 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 {
 	struct iwl_trans_pcie *trans_pcie;
 	struct iwl_trans *trans;
-	int ret, addr_size;
+	int ret, addr_size, txcmd_size, txcmd_align;
+	const struct iwl_trans_ops *ops = &trans_ops_pcie_gen2;
+
+	if (!cfg_trans->gen2) {
+		ops = &trans_ops_pcie;
+		txcmd_size = sizeof(struct iwl_tx_cmd);
+		txcmd_align = sizeof(void *);
+	} else if (cfg_trans->device_family < IWL_DEVICE_FAMILY_AX210) {
+		txcmd_size = sizeof(struct iwl_tx_cmd_gen2);
+		txcmd_align = 64;
+	} else {
+		txcmd_size = sizeof(struct iwl_tx_cmd_gen3);
+		txcmd_align = 128;
+	}
+
+	txcmd_size += sizeof(struct iwl_cmd_header);
+	txcmd_size += 36; /* biggest possible 802.11 header */
+
+	/* Ensure device TX cmd cannot reach/cross a page boundary in gen2 */
+	if (WARN_ON(cfg_trans->gen2 && txcmd_size >= txcmd_align))
+		return ERR_PTR(-EINVAL);
 
 	ret = pcim_enable_device(pdev);
 	if (ret)
 		return ERR_PTR(ret);
 
-	if (cfg_trans->gen2)
-		trans = iwl_trans_alloc(sizeof(struct iwl_trans_pcie),
-					&pdev->dev, &trans_ops_pcie_gen2);
-	else
-		trans = iwl_trans_alloc(sizeof(struct iwl_trans_pcie),
-					&pdev->dev, &trans_ops_pcie);
-
+	trans = iwl_trans_alloc(sizeof(struct iwl_trans_pcie), &pdev->dev, ops,
+				txcmd_size, txcmd_align);
 	if (!trans)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index a2dc380ac17c..56d752beb940 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -365,7 +365,8 @@ trace:
 static int iwl_pcie_gen2_build_amsdu(struct iwl_trans *trans,
 				     struct sk_buff *skb,
 				     struct iwl_tfh_tfd *tfd, int start_len,
-				     u8 hdr_len, struct iwl_device_cmd *dev_cmd)
+				     u8 hdr_len,
+				     struct iwl_device_tx_cmd *dev_cmd)
 {
 #ifdef CONFIG_INET
 	struct iwl_tx_cmd_gen2 *tx_cmd = (void *)dev_cmd->payload;
@@ -496,7 +497,7 @@ out_err:
 static struct
 iwl_tfh_tfd *iwl_pcie_gen2_build_tx_amsdu(struct iwl_trans *trans,
 					  struct iwl_txq *txq,
-					  struct iwl_device_cmd *dev_cmd,
+					  struct iwl_device_tx_cmd *dev_cmd,
 					  struct sk_buff *skb,
 					  struct iwl_cmd_meta *out_meta,
 					  int hdr_len,
@@ -533,6 +534,10 @@ iwl_tfh_tfd *iwl_pcie_gen2_build_tx_amsdu(struct iwl_trans *trans,
 	tb_phys = dma_map_single(trans->dev, tb1_addr, len, DMA_TO_DEVICE);
 	if (unlikely(dma_mapping_error(trans->dev, tb_phys)))
 		goto out_err;
+	/*
+	 * No need for _with_wa(), we ensure (via alignment) that the data
+	 * here can never cross or end at a page boundary.
+	 */
 	iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, len);
 
 	if (iwl_pcie_gen2_build_amsdu(trans, skb, tfd,
@@ -580,7 +585,7 @@ static int iwl_pcie_gen2_tx_add_frags(struct iwl_trans *trans,
 static struct
 iwl_tfh_tfd *iwl_pcie_gen2_build_tx(struct iwl_trans *trans,
 				    struct iwl_txq *txq,
-				    struct iwl_device_cmd *dev_cmd,
+				    struct iwl_device_tx_cmd *dev_cmd,
 				    struct sk_buff *skb,
 				    struct iwl_cmd_meta *out_meta,
 				    int hdr_len,
@@ -625,6 +630,10 @@ iwl_tfh_tfd *iwl_pcie_gen2_build_tx(struct iwl_trans *trans,
 	tb_phys = dma_map_single(trans->dev, tb1_addr, tb1_len, DMA_TO_DEVICE);
 	if (unlikely(dma_mapping_error(trans->dev, tb_phys)))
 		goto out_err;
+	/*
+	 * No need for _with_wa(), we ensure (via alignment) that the data
+	 * here can never cross or end at a page boundary.
+	 */
 	iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, tb1_len);
 	trace_iwlwifi_dev_tx(trans->dev, skb, tfd, sizeof(*tfd), &dev_cmd->hdr,
 			     IWL_FIRST_TB_SIZE + tb1_len, hdr_len);
@@ -671,7 +680,7 @@ out_err:
 static
 struct iwl_tfh_tfd *iwl_pcie_gen2_build_tfd(struct iwl_trans *trans,
 					    struct iwl_txq *txq,
-					    struct iwl_device_cmd *dev_cmd,
+					    struct iwl_device_tx_cmd *dev_cmd,
 					    struct sk_buff *skb,
 					    struct iwl_cmd_meta *out_meta)
 {
@@ -711,7 +720,7 @@ struct iwl_tfh_tfd *iwl_pcie_gen2_build_tfd(struct iwl_trans *trans,
 }
 
 int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
-			   struct iwl_device_cmd *dev_cmd, int txq_id)
+			   struct iwl_device_tx_cmd *dev_cmd, int txq_id)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_cmd_meta *out_meta;
@@ -736,7 +745,7 @@ int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
 
 		/* don't put the packet on the ring, if there is no room */
 		if (unlikely(iwl_queue_space(trans, txq) < 3)) {
-			struct iwl_device_cmd **dev_cmd_ptr;
+			struct iwl_device_tx_cmd **dev_cmd_ptr;
 
 			dev_cmd_ptr = (void *)((u8 *)skb->cb +
 					       trans_pcie->dev_cmd_offs);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index ba37b780dec4..b0eb52b4951b 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -213,8 +213,8 @@ static void iwl_pcie_txq_update_byte_cnt_tbl(struct iwl_trans *trans,
 	u8 sec_ctl = 0;
 	u16 len = byte_cnt + IWL_TX_CRC_SIZE + IWL_TX_DELIMITER_SIZE;
 	__le16 bc_ent;
-	struct iwl_tx_cmd *tx_cmd =
-		(void *)txq->entries[txq->write_ptr].cmd->payload;
+	struct iwl_device_tx_cmd *dev_cmd = txq->entries[txq->write_ptr].cmd;
+	struct iwl_tx_cmd *tx_cmd = (void *)dev_cmd->payload;
 	u8 sta_id = tx_cmd->sta_id;
 
 	scd_bc_tbl = trans_pcie->scd_bc_tbls.addr;
@@ -257,8 +257,8 @@ static void iwl_pcie_txq_inval_byte_cnt_tbl(struct iwl_trans *trans,
 	int read_ptr = txq->read_ptr;
 	u8 sta_id = 0;
 	__le16 bc_ent;
-	struct iwl_tx_cmd *tx_cmd =
-		(void *)txq->entries[read_ptr].cmd->payload;
+	struct iwl_device_tx_cmd *dev_cmd = txq->entries[read_ptr].cmd;
+	struct iwl_tx_cmd *tx_cmd = (void *)dev_cmd->payload;
 
 	WARN_ON(read_ptr >= TFD_QUEUE_SIZE_MAX);
 
@@ -1202,7 +1202,7 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 
 		while (!skb_queue_empty(&overflow_skbs)) {
 			struct sk_buff *skb = __skb_dequeue(&overflow_skbs);
-			struct iwl_device_cmd *dev_cmd_ptr;
+			struct iwl_device_tx_cmd *dev_cmd_ptr;
 
 			dev_cmd_ptr = *(void **)((u8 *)skb->cb +
 						 trans_pcie->dev_cmd_offs);
@@ -2125,7 +2125,8 @@ static void iwl_compute_pseudo_hdr_csum(void *iph, struct tcphdr *tcph,
 static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb,
 				   struct iwl_txq *txq, u8 hdr_len,
 				   struct iwl_cmd_meta *out_meta,
-				   struct iwl_device_cmd *dev_cmd, u16 tb1_len)
+				   struct iwl_device_tx_cmd *dev_cmd,
+				   u16 tb1_len)
 {
 	struct iwl_tx_cmd *tx_cmd = (void *)dev_cmd->payload;
 	struct iwl_trans_pcie *trans_pcie = txq->trans_pcie;
@@ -2303,7 +2304,8 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb,
 static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb,
 				   struct iwl_txq *txq, u8 hdr_len,
 				   struct iwl_cmd_meta *out_meta,
-				   struct iwl_device_cmd *dev_cmd, u16 tb1_len)
+				   struct iwl_device_tx_cmd *dev_cmd,
+				   u16 tb1_len)
 {
 	/* No A-MSDU without CONFIG_INET */
 	WARN_ON(1);
@@ -2313,7 +2315,7 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb,
 #endif /* CONFIG_INET */
 
 int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
-		      struct iwl_device_cmd *dev_cmd, int txq_id)
+		      struct iwl_device_tx_cmd *dev_cmd, int txq_id)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct ieee80211_hdr *hdr;
@@ -2370,7 +2372,7 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 
 		/* don't put the packet on the ring, if there is no room */
 		if (unlikely(iwl_queue_space(trans, txq) < 3)) {
-			struct iwl_device_cmd **dev_cmd_ptr;
+			struct iwl_device_tx_cmd **dev_cmd_ptr;
 
 			dev_cmd_ptr = (void *)((u8 *)skb->cb +
 					       trans_pcie->dev_cmd_offs);
-- 
cgit 


From 4f565ee2999960d541854389e20b78e7105e3afc Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Mon, 25 Nov 2019 11:50:58 +0200
Subject: iwlwifi: fix TLV fragment allocation loop

In the allocation loop, "pages" will never become zero (because of the
DIV_ROUND_UP), so if we can't allocate any size and pages becomes 1,
we will keep trying to allocate 1 page until it succeeds.  And in that
case, as coverity reported, block will never be NULL.

Reported-by: coverity-bot <keescook+coverity-bot@chromium.org>
Addresses-Coverity-ID: 1487402 ("Control flow issues")
Fixes: 14124b25780d ("iwlwifi: dbg_ini: implement monitor allocation flow")
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Fixes: 14124b25780d ("iwlwifi: dbg_ini: implement monitor allocation flow")
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
index f266647dc08c..ce8f248c33ea 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
@@ -480,7 +480,14 @@ static int iwl_dbg_tlv_alloc_fragment(struct iwl_fw_runtime *fwrt,
 	if (!frag || frag->size || !pages)
 		return -EIO;
 
-	while (pages) {
+	/*
+	 * We try to allocate as many pages as we can, starting with
+	 * the requested amount and going down until we can allocate
+	 * something.  Because of DIV_ROUND_UP(), pages will never go
+	 * down to 0 and stop the loop, so stop when pages reaches 1,
+	 * which is too small anyway.
+	 */
+	while (pages > 1) {
 		block = dma_alloc_coherent(fwrt->dev, pages * PAGE_SIZE,
 					   &physical,
 					   GFP_KERNEL | __GFP_NOWARN);
-- 
cgit 


From b3f20e098293892388d6a0491d6bbb2efb46fbff Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Mon, 25 Nov 2019 13:21:58 +0200
Subject: iwlwifi: mvm: fix NVM check for 3168 devices

We had a check on !NVM_EXT and then a check for NVM_SDP in the else
block of this if.  The else block, obviously, could only be reached if
using NVM_EXT, so it would never be NVM_SDP.

Fix that by checking whether the nvm_type is IWL_NVM instead of
checking for !IWL_NVM_EXT to solve this issue.

Reported-by: Stefan Sperling <stsp@stsp.name>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/nvm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
index 945c1ea5cda8..493bcc54a848 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
@@ -281,7 +281,7 @@ iwl_parse_nvm_sections(struct iwl_mvm *mvm)
 	int regulatory_type;
 
 	/* Checking for required sections */
-	if (mvm->trans->cfg->nvm_type != IWL_NVM_EXT) {
+	if (mvm->trans->cfg->nvm_type == IWL_NVM) {
 		if (!mvm->nvm_sections[NVM_SECTION_TYPE_SW].data ||
 		    !mvm->nvm_sections[mvm->cfg->nvm_hw_section_num].data) {
 			IWL_ERR(mvm, "Can't parse empty OTP/NVM sections\n");
-- 
cgit 


From ed780545c13a21dc0276807897e2d4fc142e11ac Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 21 Nov 2019 11:02:31 +0100
Subject: iwlwifi: mvm: report TX rate to mac80211 directly for RS offload

If we have offloaded rate scaling, which is always true for those
devices supporting HE, then report the TX rate directly from the
data the firmware gives us, instead of only passing it to mac80211
on frame status only and for it to track it.

First of all, this makes us always report the last good rate that
the rate scaling algorithm picked, which is better than reporting
the last rate for any frame since management frames etc. are sent
with very low rates and could interfere.

Additionally, this allows us to properly report HE rates, though
in case there's a lot of trigger-based traffic, we don't get any
choice in the rates and don't report that properly right now.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 126 ++++++++++++++++++++++
 1 file changed, 126 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 32dc9d6f0fb6..481f1c9d814f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -4771,6 +4771,125 @@ static int iwl_mvm_mac_get_survey(struct ieee80211_hw *hw, int idx,
 	return ret;
 }
 
+static void iwl_mvm_set_sta_rate(u32 rate_n_flags, struct rate_info *rinfo)
+{
+	switch (rate_n_flags & RATE_MCS_CHAN_WIDTH_MSK) {
+	case RATE_MCS_CHAN_WIDTH_20:
+		rinfo->bw = RATE_INFO_BW_20;
+		break;
+	case RATE_MCS_CHAN_WIDTH_40:
+		rinfo->bw = RATE_INFO_BW_40;
+		break;
+	case RATE_MCS_CHAN_WIDTH_80:
+		rinfo->bw = RATE_INFO_BW_80;
+		break;
+	case RATE_MCS_CHAN_WIDTH_160:
+		rinfo->bw = RATE_INFO_BW_160;
+		break;
+	}
+
+	if (rate_n_flags & RATE_MCS_HT_MSK) {
+		rinfo->flags |= RATE_INFO_FLAGS_MCS;
+		rinfo->mcs = u32_get_bits(rate_n_flags, RATE_HT_MCS_INDEX_MSK);
+		rinfo->nss = u32_get_bits(rate_n_flags,
+					  RATE_HT_MCS_NSS_MSK) + 1;
+		if (rate_n_flags & RATE_MCS_SGI_MSK)
+			rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI;
+	} else if (rate_n_flags & RATE_MCS_VHT_MSK) {
+		rinfo->flags |= RATE_INFO_FLAGS_VHT_MCS;
+		rinfo->mcs = u32_get_bits(rate_n_flags,
+					  RATE_VHT_MCS_RATE_CODE_MSK);
+		rinfo->nss = u32_get_bits(rate_n_flags,
+					  RATE_VHT_MCS_NSS_MSK) + 1;
+		if (rate_n_flags & RATE_MCS_SGI_MSK)
+			rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI;
+	} else if (rate_n_flags & RATE_MCS_HE_MSK) {
+		u32 gi_ltf = u32_get_bits(rate_n_flags,
+					  RATE_MCS_HE_GI_LTF_MSK);
+
+		rinfo->flags |= RATE_INFO_FLAGS_HE_MCS;
+		rinfo->mcs = u32_get_bits(rate_n_flags,
+					  RATE_VHT_MCS_RATE_CODE_MSK);
+		rinfo->nss = u32_get_bits(rate_n_flags,
+					  RATE_VHT_MCS_NSS_MSK) + 1;
+
+		if (rate_n_flags & RATE_MCS_HE_106T_MSK) {
+			rinfo->bw = RATE_INFO_BW_HE_RU;
+			rinfo->he_ru_alloc = NL80211_RATE_INFO_HE_RU_ALLOC_106;
+		}
+
+		switch (rate_n_flags & RATE_MCS_HE_TYPE_MSK) {
+		case RATE_MCS_HE_TYPE_SU:
+		case RATE_MCS_HE_TYPE_EXT_SU:
+			if (gi_ltf == 0 || gi_ltf == 1)
+				rinfo->he_gi = NL80211_RATE_INFO_HE_GI_0_8;
+			else if (gi_ltf == 2)
+				rinfo->he_gi = NL80211_RATE_INFO_HE_GI_1_6;
+			else if (rate_n_flags & RATE_MCS_SGI_MSK)
+				rinfo->he_gi = NL80211_RATE_INFO_HE_GI_0_8;
+			else
+				rinfo->he_gi = NL80211_RATE_INFO_HE_GI_3_2;
+			break;
+		case RATE_MCS_HE_TYPE_MU:
+			if (gi_ltf == 0 || gi_ltf == 1)
+				rinfo->he_gi = NL80211_RATE_INFO_HE_GI_0_8;
+			else if (gi_ltf == 2)
+				rinfo->he_gi = NL80211_RATE_INFO_HE_GI_1_6;
+			else
+				rinfo->he_gi = NL80211_RATE_INFO_HE_GI_3_2;
+			break;
+		case RATE_MCS_HE_TYPE_TRIG:
+			if (gi_ltf == 0 || gi_ltf == 1)
+				rinfo->he_gi = NL80211_RATE_INFO_HE_GI_1_6;
+			else
+				rinfo->he_gi = NL80211_RATE_INFO_HE_GI_3_2;
+			break;
+		}
+
+		if (rate_n_flags & RATE_HE_DUAL_CARRIER_MODE_MSK)
+			rinfo->he_dcm = 1;
+	} else {
+		switch (u32_get_bits(rate_n_flags, RATE_LEGACY_RATE_MSK)) {
+		case IWL_RATE_1M_PLCP:
+			rinfo->legacy = 10;
+			break;
+		case IWL_RATE_2M_PLCP:
+			rinfo->legacy = 20;
+			break;
+		case IWL_RATE_5M_PLCP:
+			rinfo->legacy = 55;
+			break;
+		case IWL_RATE_11M_PLCP:
+			rinfo->legacy = 110;
+			break;
+		case IWL_RATE_6M_PLCP:
+			rinfo->legacy = 60;
+			break;
+		case IWL_RATE_9M_PLCP:
+			rinfo->legacy = 90;
+			break;
+		case IWL_RATE_12M_PLCP:
+			rinfo->legacy = 120;
+			break;
+		case IWL_RATE_18M_PLCP:
+			rinfo->legacy = 180;
+			break;
+		case IWL_RATE_24M_PLCP:
+			rinfo->legacy = 240;
+			break;
+		case IWL_RATE_36M_PLCP:
+			rinfo->legacy = 360;
+			break;
+		case IWL_RATE_48M_PLCP:
+			rinfo->legacy = 480;
+			break;
+		case IWL_RATE_54M_PLCP:
+			rinfo->legacy = 540;
+			break;
+		}
+	}
+}
+
 static void iwl_mvm_mac_sta_statistics(struct ieee80211_hw *hw,
 				       struct ieee80211_vif *vif,
 				       struct ieee80211_sta *sta,
@@ -4785,6 +4904,13 @@ static void iwl_mvm_mac_sta_statistics(struct ieee80211_hw *hw,
 		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG);
 	}
 
+	if (iwl_mvm_has_tlc_offload(mvm)) {
+		struct iwl_lq_sta_rs_fw *lq_sta = &mvmsta->lq_sta.rs_fw;
+
+		iwl_mvm_set_sta_rate(lq_sta->last_rate_n_flags, &sinfo->txrate);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
+	}
+
 	/* if beacon filtering isn't on mac80211 does it anyway */
 	if (!(vif->driver_flags & IEEE80211_VIF_BEACON_FILTER))
 		return;
-- 
cgit 


From 2763bba6328c53c455d8f7f5302b80030551c31b Mon Sep 17 00:00:00 2001
From: Haim Dreyfuss <haim.dreyfuss@intel.com>
Date: Wed, 27 Nov 2019 14:55:58 -0500
Subject: iwlwifi: Don't ignore the cap field upon mcc update

When receiving a new MCC driver get all the data about the new country
code and its regulatory information.
Mistakenly, we ignored the cap field, which includes global regulatory
information which should be applies to every channel.
Fix it.

Signed-off-by: Haim Dreyfuss <haim.dreyfuss@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c | 48 +++++++++++++++++++++-
 drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h |  6 +--
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c  |  3 +-
 3 files changed, 51 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 1e240a2a8329..068e4924c04e 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -224,6 +224,34 @@ enum iwl_nvm_channel_flags {
 	NVM_CHANNEL_DC_HIGH		= BIT(12),
 };
 
+/**
+ * enum iwl_reg_capa_flags - global flags applied for the whole regulatory
+ * domain.
+ * @REG_CAPA_BF_CCD_LOW_BAND: Beam-forming or Cyclic Delay Diversity in the
+ *	2.4Ghz band is allowed.
+ * @REG_CAPA_BF_CCD_HIGH_BAND: Beam-forming or Cyclic Delay Diversity in the
+ *	5Ghz band is allowed.
+ * @REG_CAPA_160MHZ_ALLOWED: 11ac channel with a width of 160Mhz is allowed
+ *	for this regulatory domain (valid only in 5Ghz).
+ * @REG_CAPA_80MHZ_ALLOWED: 11ac channel with a width of 80Mhz is allowed
+ *	for this regulatory domain (valid only in 5Ghz).
+ * @REG_CAPA_MCS_8_ALLOWED: 11ac with MCS 8 is allowed.
+ * @REG_CAPA_MCS_9_ALLOWED: 11ac with MCS 9 is allowed.
+ * @REG_CAPA_40MHZ_FORBIDDEN: 11n channel with a width of 40Mhz is forbidden
+ *	for this regulatory domain (valid only in 5Ghz).
+ * @REG_CAPA_DC_HIGH_ENABLED: DC HIGH allowed.
+ */
+enum iwl_reg_capa_flags {
+	REG_CAPA_BF_CCD_LOW_BAND	= BIT(0),
+	REG_CAPA_BF_CCD_HIGH_BAND	= BIT(1),
+	REG_CAPA_160MHZ_ALLOWED		= BIT(2),
+	REG_CAPA_80MHZ_ALLOWED		= BIT(3),
+	REG_CAPA_MCS_8_ALLOWED		= BIT(4),
+	REG_CAPA_MCS_9_ALLOWED		= BIT(5),
+	REG_CAPA_40MHZ_FORBIDDEN	= BIT(7),
+	REG_CAPA_DC_HIGH_ENABLED	= BIT(9),
+};
+
 static inline void iwl_nvm_print_channel_flags(struct device *dev, u32 level,
 					       int chan, u32 flags)
 {
@@ -1038,6 +1066,7 @@ IWL_EXPORT_SYMBOL(iwl_parse_nvm_data);
 
 static u32 iwl_nvm_get_regdom_bw_flags(const u16 *nvm_chan,
 				       int ch_idx, u16 nvm_flags,
+				       u16 cap_flags,
 				       const struct iwl_cfg *cfg)
 {
 	u32 flags = NL80211_RRF_NO_HT40;
@@ -1076,13 +1105,27 @@ static u32 iwl_nvm_get_regdom_bw_flags(const u16 *nvm_chan,
 	    (flags & NL80211_RRF_NO_IR))
 		flags |= NL80211_RRF_GO_CONCURRENT;
 
+	/*
+	 * cap_flags is per regulatory domain so apply it for every channel
+	 */
+	if (ch_idx >= NUM_2GHZ_CHANNELS) {
+		if (cap_flags & REG_CAPA_40MHZ_FORBIDDEN)
+			flags |= NL80211_RRF_NO_HT40;
+
+		if (!(cap_flags & REG_CAPA_80MHZ_ALLOWED))
+			flags |= NL80211_RRF_NO_80MHZ;
+
+		if (!(cap_flags & REG_CAPA_160MHZ_ALLOWED))
+			flags |= NL80211_RRF_NO_160MHZ;
+	}
+
 	return flags;
 }
 
 struct ieee80211_regdomain *
 iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
 		       int num_of_ch, __le32 *channels, u16 fw_mcc,
-		       u16 geo_info)
+		       u16 geo_info, u16 cap)
 {
 	int ch_idx;
 	u16 ch_flags;
@@ -1140,7 +1183,8 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
 		}
 
 		reg_rule_flags = iwl_nvm_get_regdom_bw_flags(nvm_chan, ch_idx,
-							     ch_flags, cfg);
+							     ch_flags, cap,
+							     cfg);
 
 		/* we can't continue the same rule */
 		if (ch_idx == 0 || prev_reg_rule_flags != reg_rule_flags ||
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
index b7e1ddf8f177..4eeedb41e9ac 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
@@ -7,7 +7,7 @@
  *
  * Copyright(c) 2008 - 2015 Intel Corporation. All rights reserved.
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018        Intel Corporation
+ * Copyright(c) 2018 - 2019 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
@@ -29,7 +29,7 @@
  *
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018        Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -103,7 +103,7 @@ iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 struct ieee80211_regdomain *
 iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg,
 		       int num_of_ch, __le32 *channels, u16 fw_mcc,
-		       u16 geo_info);
+		       u16 geo_info, u16 cap);
 
 /**
  * struct iwl_nvm_section - describes an NVM section in memory.
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 481f1c9d814f..a46204b905d2 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -256,7 +256,8 @@ struct ieee80211_regdomain *iwl_mvm_get_regdomain(struct wiphy *wiphy,
 				      __le32_to_cpu(resp->n_channels),
 				      resp->channels,
 				      __le16_to_cpu(resp->mcc),
-				      __le16_to_cpu(resp->geo_info));
+				      __le16_to_cpu(resp->geo_info),
+				      __le16_to_cpu(resp->cap));
 	/* Store the return source id */
 	src_id = resp->source_id;
 	kfree(resp);
-- 
cgit 


From d84a7a654a66eead599cfd4f436d1f921e01074f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 5 Dec 2019 09:31:07 +0100
Subject: iwlwifi: pcie: extend hardware workaround to context-info

After more investigation on the hardware side, it appears that the
hardware bug regarding 2^32 boundary reaching/crossing also affects
other uses of the DMA engine, in particular the ones triggered by
the context-info (image loader) mechanism.

It also turns out that the bug only affects devices with gen2 TX
hardware engine, so we don't need to change context info for gen3.
The TX path workarounds are simpler to still keep for both though.

Add the workaround to that code as well; this is a lot simpler as
we have just a single way to allocate DMA memory there.

I made the algorithm recursive (with a small limit) since it's
actually (almost) impossible to hit this today - dma_alloc_coherent
is currently documented to always return 32-bit addressable memory
regardless of the DMA mask for it, and so we could only get REALLY
unlucky to get the very last page in that area.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 .../net/wireless/intel/iwlwifi/pcie/ctxt-info.c    | 45 ++++++++++++++++++++--
 drivers/net/wireless/intel/iwlwifi/pcie/internal.h | 10 +++++
 drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c  | 14 +------
 3 files changed, 54 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
index d38cefbb779e..e249e3fd14c6 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
@@ -57,6 +57,42 @@
 #include "internal.h"
 #include "iwl-prph.h"
 
+static void *_iwl_pcie_ctxt_info_dma_alloc_coherent(struct iwl_trans *trans,
+						    size_t size,
+						    dma_addr_t *phys,
+						    int depth)
+{
+	void *result;
+
+	if (WARN(depth > 2,
+		 "failed to allocate DMA memory not crossing 2^32 boundary"))
+		return NULL;
+
+	result = dma_alloc_coherent(trans->dev, size, phys, GFP_KERNEL);
+
+	if (!result)
+		return NULL;
+
+	if (unlikely(iwl_pcie_crosses_4g_boundary(*phys, size))) {
+		void *old = result;
+		dma_addr_t oldphys = *phys;
+
+		result = _iwl_pcie_ctxt_info_dma_alloc_coherent(trans, size,
+								phys,
+								depth + 1);
+		dma_free_coherent(trans->dev, size, old, oldphys);
+	}
+
+	return result;
+}
+
+static void *iwl_pcie_ctxt_info_dma_alloc_coherent(struct iwl_trans *trans,
+						   size_t size,
+						   dma_addr_t *phys)
+{
+	return _iwl_pcie_ctxt_info_dma_alloc_coherent(trans, size, phys, 0);
+}
+
 void iwl_pcie_ctxt_info_free_paging(struct iwl_trans *trans)
 {
 	struct iwl_self_init_dram *dram = &trans->init_dram;
@@ -161,14 +197,17 @@ int iwl_pcie_ctxt_info_init(struct iwl_trans *trans,
 	struct iwl_context_info *ctxt_info;
 	struct iwl_context_info_rbd_cfg *rx_cfg;
 	u32 control_flags = 0, rb_size;
+	dma_addr_t phys;
 	int ret;
 
-	ctxt_info = dma_alloc_coherent(trans->dev, sizeof(*ctxt_info),
-				       &trans_pcie->ctxt_info_dma_addr,
-				       GFP_KERNEL);
+	ctxt_info = iwl_pcie_ctxt_info_dma_alloc_coherent(trans,
+							  sizeof(*ctxt_info),
+							  &phys);
 	if (!ctxt_info)
 		return -ENOMEM;
 
+	trans_pcie->ctxt_info_dma_addr = phys;
+
 	ctxt_info->version.version = 0;
 	ctxt_info->version.mac_id =
 		cpu_to_le16((u16)iwl_read32(trans, CSR_HW_REV));
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index 04361ecf31bd..f14bcef3495e 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -672,6 +672,16 @@ void iwl_pcie_disable_ict(struct iwl_trans *trans);
 /*****************************************************
 * TX / HCMD
 ******************************************************/
+/*
+ * We need this inline in case dma_addr_t is only 32-bits - since the
+ * hardware is always 64-bit, the issue can still occur in that case,
+ * so use u64 for 'phys' here to force the addition in 64-bit.
+ */
+static inline bool iwl_pcie_crosses_4g_boundary(u64 phys, u16 len)
+{
+	return upper_32_bits(phys) != upper_32_bits(phys + len);
+}
+
 int iwl_pcie_tx_init(struct iwl_trans *trans);
 int iwl_pcie_gen2_tx_init(struct iwl_trans *trans, int txq_id,
 			  int queue_size);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index 56d752beb940..bfb984b2e00c 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -213,16 +213,6 @@ static void iwl_pcie_gen2_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq)
 	}
 }
 
-/*
- * We need this inline in case dma_addr_t is only 32-bits - since the
- * hardware is always 64-bit, the issue can still occur in that case,
- * so use u64 for 'phys' here to force the addition in 64-bit.
- */
-static inline bool crosses_4g_boundary(u64 phys, u16 len)
-{
-	return upper_32_bits(phys) != upper_32_bits(phys + len);
-}
-
 static int iwl_pcie_gen2_set_tb(struct iwl_trans *trans,
 				struct iwl_tfh_tfd *tfd, dma_addr_t addr,
 				u16 len)
@@ -238,7 +228,7 @@ static int iwl_pcie_gen2_set_tb(struct iwl_trans *trans,
 	 * there's no more space, and so when we know there is enough we
 	 * don't always check ...
 	 */
-	WARN(crosses_4g_boundary(addr, len),
+	WARN(iwl_pcie_crosses_4g_boundary(addr, len),
 	     "possible DMA problem with iova:0x%llx, len:%d\n",
 	     (unsigned long long)addr, len);
 
@@ -300,7 +290,7 @@ static int iwl_pcie_gen2_set_tb_with_wa(struct iwl_trans *trans,
 	if (unlikely(dma_mapping_error(trans->dev, phys)))
 		return -ENOMEM;
 
-	if (likely(!crosses_4g_boundary(phys, len))) {
+	if (likely(!iwl_pcie_crosses_4g_boundary(phys, len))) {
 		ret = iwl_pcie_gen2_set_tb(trans, tfd, phys, len);
 
 		if (ret < 0)
-- 
cgit 


From b9f726c94224e863d4d3458dfec2e7e1284a39ce Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 11 Dec 2019 10:09:56 +0100
Subject: iwlwifi: mvm: fix SKB leak on invalid queue

It used to be the case that if we got here, we wouldn't warn
but instead allocate the queue (DQA). With using the mac80211
TXQs model this changed, and we really have nothing to do with
the frame here anymore, hence the warning now.

However, clearly we missed in coding & review that this is now
a pure error path and leaks the SKB if we return 0 instead of
an indication that the SKB needs to be freed. Fix this.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Fixes: cfbc6c4c5b91 ("iwlwifi: mvm: support mac80211 TXQs model")
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index 80052ad1fa6d..eaeb8501c9b5 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -1149,7 +1149,7 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
 	if (WARN_ONCE(txq_id == IWL_MVM_INVALID_QUEUE, "Invalid TXQ id")) {
 		iwl_trans_free_tx_cmd(mvm->trans, dev_cmd);
 		spin_unlock(&mvmsta->lock);
-		return 0;
+		return -1;
 	}
 
 	if (!iwl_mvm_has_new_tx_api(mvm)) {
-- 
cgit 


From df2378ab0f2a9dd4cf4501268af1902cc4ebacd8 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 11 Dec 2019 10:15:52 +0100
Subject: iwlwifi: mvm: fix potential SKB leak on TXQ TX

When we transmit after TXQ dequeue, we aren't paying attention to
the return value of the transmit functions, leading to a potential
SKB leak.

Refactor the code a bit (and rename ..._tx to ..._tx_sta) to check
for this happening.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Fixes: cfbc6c4c5b91 ("iwlwifi: mvm: support mac80211 TXQs model")
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 28 +++++++++++++----------
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h      |  4 ++--
 drivers/net/wireless/intel/iwlwifi/mvm/tx.c       |  4 ++--
 3 files changed, 20 insertions(+), 16 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index a46204b905d2..6717f25c46b1 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -755,6 +755,20 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 	return ret;
 }
 
+static void iwl_mvm_tx_skb(struct iwl_mvm *mvm, struct sk_buff *skb,
+			   struct ieee80211_sta *sta)
+{
+	if (likely(sta)) {
+		if (likely(iwl_mvm_tx_skb_sta(mvm, skb, sta) == 0))
+			return;
+	} else {
+		if (likely(iwl_mvm_tx_skb_non_sta(mvm, skb) == 0))
+			return;
+	}
+
+	ieee80211_free_txskb(mvm->hw, skb);
+}
+
 static void iwl_mvm_mac_tx(struct ieee80211_hw *hw,
 			   struct ieee80211_tx_control *control,
 			   struct sk_buff *skb)
@@ -798,14 +812,7 @@ static void iwl_mvm_mac_tx(struct ieee80211_hw *hw,
 		}
 	}
 
-	if (sta) {
-		if (iwl_mvm_tx_skb(mvm, skb, sta))
-			goto drop;
-		return;
-	}
-
-	if (iwl_mvm_tx_skb_non_sta(mvm, skb))
-		goto drop;
+	iwl_mvm_tx_skb(mvm, skb, sta);
 	return;
  drop:
 	ieee80211_free_txskb(hw, skb);
@@ -855,10 +862,7 @@ void iwl_mvm_mac_itxq_xmit(struct ieee80211_hw *hw, struct ieee80211_txq *txq)
 				break;
 			}
 
-			if (!txq->sta)
-				iwl_mvm_tx_skb_non_sta(mvm, skb);
-			else
-				iwl_mvm_tx_skb(mvm, skb, txq->sta);
+			iwl_mvm_tx_skb(mvm, skb, txq->sta);
 		}
 	} while (atomic_dec_return(&mvmtxq->tx_request));
 	rcu_read_unlock();
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 3ec8de00f3aa..e5b21f8b02e7 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1508,8 +1508,8 @@ int __must_check iwl_mvm_send_cmd_status(struct iwl_mvm *mvm,
 int __must_check iwl_mvm_send_cmd_pdu_status(struct iwl_mvm *mvm, u32 id,
 					     u16 len, const void *data,
 					     u32 *status);
-int iwl_mvm_tx_skb(struct iwl_mvm *mvm, struct sk_buff *skb,
-		   struct ieee80211_sta *sta);
+int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb,
+		       struct ieee80211_sta *sta);
 int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb);
 void iwl_mvm_set_tx_cmd(struct iwl_mvm *mvm, struct sk_buff *skb,
 			struct iwl_tx_cmd *tx_cmd,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index eaeb8501c9b5..ddfc9a668036 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -1201,8 +1201,8 @@ drop:
 	return -1;
 }
 
-int iwl_mvm_tx_skb(struct iwl_mvm *mvm, struct sk_buff *skb,
-		   struct ieee80211_sta *sta)
+int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb,
+		       struct ieee80211_sta *sta)
 {
 	struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
 	struct ieee80211_tx_info info;
-- 
cgit 


From 3d1b28fd30ab8b87c0935584aff6f9b433939d2c Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Tue, 10 Dec 2019 15:11:36 +0200
Subject: iwlwifi: pcie: rename L0S_ENABLED bit to L0S_DISABLED

This bit has been misnamed since the initial implementation of the
driver.  The correct semantics is that setting this bit disables L0S
states, and we already clearly use it as such in the code.  Rename it
to avoid confusion.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-csr.h    | 2 +-
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
index 92d9898ab7c2..c2f7252ae4e7 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
@@ -379,7 +379,7 @@ enum {
 
 
 /* CSR GIO */
-#define CSR_GIO_REG_VAL_L0S_ENABLED	(0x00000002)
+#define CSR_GIO_REG_VAL_L0S_DISABLED	(0x00000002)
 
 /*
  * UCODE-DRIVER GP (general purpose) mailbox register 1
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 91fa439d1255..2e599ba2f2ad 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -311,9 +311,9 @@ void iwl_pcie_apm_config(struct iwl_trans *trans)
 	 */
 	pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_LNKCTL, &lctl);
 	if (lctl & PCI_EXP_LNKCTL_ASPM_L1)
-		iwl_set_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_ENABLED);
+		iwl_set_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_DISABLED);
 	else
-		iwl_clear_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_ENABLED);
+		iwl_clear_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_DISABLED);
 	trans->pm_support = !(lctl & PCI_EXP_LNKCTL_ASPM_L0S);
 
 	pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_DEVCTL2, &cap);
-- 
cgit 


From cc894b85abf70d40e9920976c7fadd6ded757c60 Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Tue, 10 Dec 2019 15:18:16 +0200
Subject: iwlwifi: pcie: always disable L0S states

L0S states have been found to be unstable with our devices and in
newer hardware they are not supported at all, so we must always set
the L0S_DISABLED bit.  Previously we were only disabling L0S states if
L1 was supported, because the assumption was that transitions from L0S
to L1 state was the problematic case.  But now we should never use
L0S, so do it regardless of whether L1 is supported or not.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 2e599ba2f2ad..f60d66f1e55b 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -302,18 +302,13 @@ void iwl_pcie_apm_config(struct iwl_trans *trans)
 	u16 cap;
 
 	/*
-	 * HW bug W/A for instability in PCIe bus L0S->L1 transition.
-	 * Check if BIOS (or OS) enabled L1-ASPM on this device.
-	 * If so (likely), disable L0S, so device moves directly L0->L1;
-	 *    costs negligible amount of power savings.
-	 * If not (unlikely), enable L0S, so there is at least some
-	 *    power savings, even without L1.
+	 * L0S states have been found to be unstable with our devices
+	 * and in newer hardware they are not officially supported at
+	 * all, so we must always set the L0S_DISABLED bit.
 	 */
+	iwl_set_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_DISABLED);
+
 	pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_LNKCTL, &lctl);
-	if (lctl & PCI_EXP_LNKCTL_ASPM_L1)
-		iwl_set_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_DISABLED);
-	else
-		iwl_clear_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_DISABLED);
 	trans->pm_support = !(lctl & PCI_EXP_LNKCTL_ASPM_L0S);
 
 	pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_DEVCTL2, &cap);
-- 
cgit 


From 990aba28f5001f6e90fdd84e13612b560a75deda Mon Sep 17 00:00:00 2001
From: Shahar S Matityahu <shahar.s.matityahu@intel.com>
Date: Sun, 15 Dec 2019 20:06:22 +0200
Subject: iwlwifi: dbg: force stop the debug monitor HW

The driver is required to stop the debug monitor HW recording regardless
of the debug configuration since the driver is responsible to halt the
FW DBGC.

Signed-off-by: Shahar S Matityahu <shahar.s.matityahu@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index ed90dd104366..4c60f9959f7b 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -2669,12 +2669,7 @@ int iwl_fw_dbg_stop_restart_recording(struct iwl_fw_runtime *fwrt,
 {
 	int ret = 0;
 
-	/* if the FW crashed or not debug monitor cfg was given, there is
-	 * no point in changing the recording state
-	 */
-	if (test_bit(STATUS_FW_ERROR, &fwrt->trans->status) ||
-	    (!fwrt->trans->dbg.dest_tlv &&
-	     fwrt->trans->dbg.ini_dest == IWL_FW_INI_LOCATION_INVALID))
+	if (test_bit(STATUS_FW_ERROR, &fwrt->trans->status))
 		return 0;
 
 	if (fw_has_capa(&fwrt->fw->ucode_capa,
-- 
cgit 


From f06021a18fcf8d8a1e79c5e0a8ec4eb2b038e153 Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Mon, 16 Dec 2019 22:23:15 +0200
Subject: iwlwifi: remove lar_disable module parameter

This is an old parameter that was used supposed to be used only when
LAR was still under development.  It should not be used anymore, but,
since it's available, end-users have been mangling with it
unnecessarily.  In some cases it can cause problems because when LAR
is supported the driver and the firmware do not expect it to be
disabled.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-drv.c       |  3 ---
 drivers/net/wireless/intel/iwlwifi/iwl-modparams.h |  2 --
 drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c | 13 +++++++------
 drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h |  3 ++-
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h       |  3 ---
 drivers/net/wireless/intel/iwlwifi/mvm/nvm.c       | 10 ++--------
 6 files changed, 11 insertions(+), 23 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index 4096ccf58b07..bc8c959588ca 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -1817,9 +1817,6 @@ MODULE_PARM_DESC(antenna_coupling,
 module_param_named(nvm_file, iwlwifi_mod_params.nvm_file, charp, 0444);
 MODULE_PARM_DESC(nvm_file, "NVM file name");
 
-module_param_named(lar_disable, iwlwifi_mod_params.lar_disable, bool, 0444);
-MODULE_PARM_DESC(lar_disable, "disable LAR functionality (default: N)");
-
 module_param_named(uapsd_disable, iwlwifi_mod_params.uapsd_disable, uint, 0644);
 MODULE_PARM_DESC(uapsd_disable,
 		 "disable U-APSD functionality bitmap 1: BSS 2: P2P Client (default: 3)");
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h b/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h
index ebea3f308b5d..82e5cac23d8d 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h
@@ -115,7 +115,6 @@ enum iwl_uapsd_disable {
  * @nvm_file: specifies a external NVM file
  * @uapsd_disable: disable U-APSD, see &enum iwl_uapsd_disable, default =
  *	IWL_DISABLE_UAPSD_BSS | IWL_DISABLE_UAPSD_P2P_CLIENT
- * @lar_disable: disable LAR (regulatory), default = 0
  * @fw_monitor: allow to use firmware monitor
  * @disable_11ac: disable VHT capabilities, default = false.
  * @remove_when_gone: remove an inaccessible device from the PCIe bus.
@@ -136,7 +135,6 @@ struct iwl_mod_params {
 	int antenna_coupling;
 	char *nvm_file;
 	u32 uapsd_disable;
-	bool lar_disable;
 	bool fw_monitor;
 	bool disable_11ac;
 	/**
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 068e4924c04e..d4f834b52f50 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -967,10 +967,11 @@ iwl_nvm_no_wide_in_5ghz(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 
 struct iwl_nvm_data *
 iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
+		   const struct iwl_fw *fw,
 		   const __be16 *nvm_hw, const __le16 *nvm_sw,
 		   const __le16 *nvm_calib, const __le16 *regulatory,
 		   const __le16 *mac_override, const __le16 *phy_sku,
-		   u8 tx_chains, u8 rx_chains, bool lar_fw_supported)
+		   u8 tx_chains, u8 rx_chains)
 {
 	struct iwl_nvm_data *data;
 	bool lar_enabled;
@@ -1050,7 +1051,8 @@ iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 		return NULL;
 	}
 
-	if (lar_fw_supported && lar_enabled)
+	if (lar_enabled &&
+	    fw_has_capa(&fw->ucode_capa, IWL_UCODE_TLV_CAPA_LAR_SUPPORT))
 		sbands_flags |= IWL_NVM_SBANDS_FLAGS_LAR;
 
 	if (iwl_nvm_no_wide_in_5ghz(trans, cfg, nvm_hw))
@@ -1449,9 +1451,6 @@ struct iwl_nvm_data *iwl_get_nvm(struct iwl_trans *trans,
 		.id = WIDE_ID(REGULATORY_AND_NVM_GROUP, NVM_GET_INFO)
 	};
 	int  ret;
-	bool lar_fw_supported = !iwlwifi_mod_params.lar_disable &&
-				fw_has_capa(&fw->ucode_capa,
-					    IWL_UCODE_TLV_CAPA_LAR_SUPPORT);
 	bool empty_otp;
 	u32 mac_flags;
 	u32 sbands_flags = 0;
@@ -1529,7 +1528,9 @@ struct iwl_nvm_data *iwl_get_nvm(struct iwl_trans *trans,
 	nvm->valid_tx_ant = (u8)le32_to_cpu(rsp->phy_sku.tx_chains);
 	nvm->valid_rx_ant = (u8)le32_to_cpu(rsp->phy_sku.rx_chains);
 
-	if (le32_to_cpu(rsp->regulatory.lar_enabled) && lar_fw_supported) {
+	if (le32_to_cpu(rsp->regulatory.lar_enabled) &&
+	    fw_has_capa(&fw->ucode_capa,
+			IWL_UCODE_TLV_CAPA_LAR_SUPPORT)) {
 		nvm->lar_enabled = true;
 		sbands_flags |= IWL_NVM_SBANDS_FLAGS_LAR;
 	}
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
index 4eeedb41e9ac..fb0b385d10fd 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h
@@ -85,10 +85,11 @@ enum iwl_nvm_sbands_flags {
  */
 struct iwl_nvm_data *
 iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg,
+		   const struct iwl_fw *fw,
 		   const __be16 *nvm_hw, const __le16 *nvm_sw,
 		   const __le16 *nvm_calib, const __le16 *regulatory,
 		   const __le16 *mac_override, const __le16 *phy_sku,
-		   u8 tx_chains, u8 rx_chains, bool lar_fw_supported);
+		   u8 tx_chains, u8 rx_chains);
 
 /**
  * iwl_parse_mcc_info - parse MCC (mobile country code) info coming from FW
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index e5b21f8b02e7..67ab7e7e9c9d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1298,9 +1298,6 @@ static inline bool iwl_mvm_is_lar_supported(struct iwl_mvm *mvm)
 	bool tlv_lar = fw_has_capa(&mvm->fw->ucode_capa,
 				   IWL_UCODE_TLV_CAPA_LAR_SUPPORT);
 
-	if (iwlwifi_mod_params.lar_disable)
-		return false;
-
 	/*
 	 * Enable LAR only if it is supported by the FW (TLV) &&
 	 * enabled in the NVM
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
index 493bcc54a848..46128a2a9c6e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
@@ -277,7 +277,6 @@ iwl_parse_nvm_sections(struct iwl_mvm *mvm)
 	struct iwl_nvm_section *sections = mvm->nvm_sections;
 	const __be16 *hw;
 	const __le16 *sw, *calib, *regulatory, *mac_override, *phy_sku;
-	bool lar_enabled;
 	int regulatory_type;
 
 	/* Checking for required sections */
@@ -327,14 +326,9 @@ iwl_parse_nvm_sections(struct iwl_mvm *mvm)
 		(const __le16 *)sections[NVM_SECTION_TYPE_REGULATORY_SDP].data :
 		(const __le16 *)sections[NVM_SECTION_TYPE_REGULATORY].data;
 
-	lar_enabled = !iwlwifi_mod_params.lar_disable &&
-		      fw_has_capa(&mvm->fw->ucode_capa,
-				  IWL_UCODE_TLV_CAPA_LAR_SUPPORT);
-
-	return iwl_parse_nvm_data(mvm->trans, mvm->cfg, hw, sw, calib,
+	return iwl_parse_nvm_data(mvm->trans, mvm->cfg, mvm->fw, hw, sw, calib,
 				  regulatory, mac_override, phy_sku,
-				  mvm->fw->valid_tx_ant, mvm->fw->valid_rx_ant,
-				  lar_enabled);
+				  mvm->fw->valid_tx_ant, mvm->fw->valid_rx_ant);
 }
 
 /* Loads the NVM data stored in mvm->nvm_sections into the NIC */
-- 
cgit 


From fb3c06cfda0db68f6082f05c43d63c1fb1761af0 Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Mon, 23 Dec 2019 13:00:59 +0200
Subject: iwlwifi: fw: make pos static in iwl_sar_get_ewrd_table() loop

In the for loop where we are supposed to go through the entire table,
we are using a non-static local to keep the pos index.  This makes
each iteration start with 3, so we always access the first item on the
table.  Fix this by moving the variable outside of the loo so it
doesn't lose its value at every iteration.

Reported-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Fixes: ba3224db7803 ("iwlwifi: mvm: fix an out-of-bound access")
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/acpi.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
index 40fe2d667622..48d375a86d86 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
@@ -357,8 +357,8 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt)
 {
 	union acpi_object *wifi_pkg, *data;
 	bool enabled;
-	int i, n_profiles, tbl_rev;
-	int  ret = 0;
+	int i, n_profiles, tbl_rev, pos;
+	int ret = 0;
 
 	data = iwl_acpi_get_object(fwrt->dev, ACPI_EWRD_METHOD);
 	if (IS_ERR(data))
@@ -390,10 +390,10 @@ int iwl_sar_get_ewrd_table(struct iwl_fw_runtime *fwrt)
 		goto out_free;
 	}
 
-	for (i = 0; i < n_profiles; i++) {
-		/* the tables start at element 3 */
-		int pos = 3;
+	/* the tables start at element 3 */
+	pos = 3;
 
+	for (i = 0; i < n_profiles; i++) {
 		/* The EWRD profiles officially go from 2 to 4, but we
 		 * save them in sar_profiles[1-3] (because we don't
 		 * have profile 0).  So in the array we start from 1.
-- 
cgit 


From 205608749e1ef394f513888091e613c5bfccbcca Mon Sep 17 00:00:00 2001
From: Mehmet Akif Tasova <makiftasova@gmail.com>
Date: Fri, 13 Dec 2019 23:35:10 +0300
Subject: Revert "iwlwifi: mvm: fix scan config command size"

Since v5.4-rc1 was released, iwlwifi started throwing errors when scan
commands were sent to the firmware with certain devices (depending on
the OTP burned in the device, which contains the list of available
channels).  For instance:

iwlwifi 0000:00:14.3: FW error in SYNC CMD SCAN_CFG_CMD

This bug was reported in the ArchLinux bug tracker:
https://bugs.archlinux.org/task/64703

And also in a specific case in bugzilla, when the lar_disabled option
was set: https://bugzilla.kernel.org/show_bug.cgi?id=205193

Revert the commit that introduced this error, by using the number of
channels from the OTP instead of the number of channels that is
specified in the FW TLV that tells us how many channels it supports.

This reverts commit 06eb547c4ae4382e70d556ba213d13c95ca1801b.

Cc: stable@vger.kernel.org # v5.4+
Signed-off-by: Mehmet Akif Tasova <makiftasova@gmail.com>
[ Luca: reworded the commit message a bit. ]
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/scan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index a046ac9fa852..a5af8f4128b1 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -1213,7 +1213,7 @@ static int iwl_mvm_legacy_config_scan(struct iwl_mvm *mvm)
 		cmd_size = sizeof(struct iwl_scan_config_v2);
 	else
 		cmd_size = sizeof(struct iwl_scan_config_v1);
-	cmd_size += num_channels;
+	cmd_size += mvm->fw->ucode_capa.n_scan_channels;
 
 	cfg = kzalloc(cmd_size, GFP_KERNEL);
 	if (!cfg)
-- 
cgit 


From 95224166a9032ff5d08fca633d37113078ce7d01 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Mon, 13 Jan 2020 09:32:46 +0100
Subject: vti[6]: fix packet tx through bpf_redirect()

With an ebpf program that redirects packets through a vti[6] interface,
the packets are dropped because no dst is attached.

This could also be reproduced with an AF_PACKET socket, with the following
python script (vti1 is an ip_vti interface):

 import socket
 send_s = socket.socket(socket.AF_PACKET, socket.SOCK_RAW, 0)
 # scapy
 # p = IP(src='10.100.0.2', dst='10.200.0.1')/ICMP(type='echo-request')
 # raw(p)
 req = b'E\x00\x00\x1c\x00\x01\x00\x00@\x01e\xb2\nd\x00\x02\n\xc8\x00\x01\x08\x00\xf7\xff\x00\x00\x00\x00'
 send_s.sendto(req, ('vti1', 0x800, 0, 0))

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/ipv4/ip_vti.c  | 13 +++++++++++--
 net/ipv6/ip6_vti.c | 13 +++++++++++--
 2 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index e90b600c7a25..37cddd18f282 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -187,8 +187,17 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 	int mtu;
 
 	if (!dst) {
-		dev->stats.tx_carrier_errors++;
-		goto tx_error_icmp;
+		struct rtable *rt;
+
+		fl->u.ip4.flowi4_oif = dev->ifindex;
+		fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC;
+		rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4);
+		if (IS_ERR(rt)) {
+			dev->stats.tx_carrier_errors++;
+			goto tx_error_icmp;
+		}
+		dst = &rt->dst;
+		skb_dst_set(skb, dst);
 	}
 
 	dst_hold(dst);
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 6f08b760c2a7..524006aa0d78 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -449,8 +449,17 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 	int err = -1;
 	int mtu;
 
-	if (!dst)
-		goto tx_err_link_failure;
+	if (!dst) {
+		fl->u.ip6.flowi6_oif = dev->ifindex;
+		fl->u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC;
+		dst = ip6_route_output(dev_net(dev), NULL, &fl->u.ip6);
+		if (dst->error) {
+			dst_release(dst);
+			dst = NULL;
+			goto tx_err_link_failure;
+		}
+		skb_dst_set(skb, dst);
+	}
 
 	dst_hold(dst);
 	dst = xfrm_lookup(t->net, dst, fl, NULL, 0);
-- 
cgit 


From f042365dbffea98fb8148c98c700402e8d099f02 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Mon, 13 Jan 2020 09:32:47 +0100
Subject: xfrm interface: fix packet tx through bpf_redirect()

With an ebpf program that redirects packets through a xfrm interface,
packets are dropped because no dst is attached to skb.

This could also be reproduced with an AF_PACKET socket, with the following
python script (xfrm1 is a xfrm interface):

 import socket
 send_s = socket.socket(socket.AF_PACKET, socket.SOCK_RAW, 0)
 # scapy
 # p = IP(src='10.100.0.2', dst='10.200.0.1')/ICMP(type='echo-request')
 # raw(p)
 req = b'E\x00\x00\x1c\x00\x01\x00\x00@\x01e\xb2\nd\x00\x02\n\xc8\x00\x01\x08\x00\xf7\xff\x00\x00\x00\x00'
 send_s.sendto(req, ('xfrm1', 0x800, 0, 0))

It was also not possible to send an ip packet through an AF_PACKET socket
because a LL header was expected. Let's remove those LL header constraints.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_interface.c | 32 +++++++++++++++++++++++++-------
 1 file changed, 25 insertions(+), 7 deletions(-)

diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 7ac1542feaf8..00393179f185 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -268,9 +268,6 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 	int err = -1;
 	int mtu;
 
-	if (!dst)
-		goto tx_err_link_failure;
-
 	dst_hold(dst);
 	dst = xfrm_lookup_with_ifid(xi->net, dst, fl, NULL, 0, xi->p.if_id);
 	if (IS_ERR(dst)) {
@@ -343,6 +340,7 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct xfrm_if *xi = netdev_priv(dev);
 	struct net_device_stats *stats = &xi->dev->stats;
+	struct dst_entry *dst = skb_dst(skb);
 	struct flowi fl;
 	int ret;
 
@@ -352,10 +350,33 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
 	case htons(ETH_P_IPV6):
 		xfrm_decode_session(skb, &fl, AF_INET6);
 		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+		if (!dst) {
+			fl.u.ip6.flowi6_oif = dev->ifindex;
+			fl.u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC;
+			dst = ip6_route_output(dev_net(dev), NULL, &fl.u.ip6);
+			if (dst->error) {
+				dst_release(dst);
+				stats->tx_carrier_errors++;
+				goto tx_err;
+			}
+			skb_dst_set(skb, dst);
+		}
 		break;
 	case htons(ETH_P_IP):
 		xfrm_decode_session(skb, &fl, AF_INET);
 		memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+		if (!dst) {
+			struct rtable *rt;
+
+			fl.u.ip4.flowi4_oif = dev->ifindex;
+			fl.u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC;
+			rt = __ip_route_output_key(dev_net(dev), &fl.u.ip4);
+			if (IS_ERR(rt)) {
+				stats->tx_carrier_errors++;
+				goto tx_err;
+			}
+			skb_dst_set(skb, &rt->dst);
+		}
 		break;
 	default:
 		goto tx_err;
@@ -563,12 +584,9 @@ static void xfrmi_dev_setup(struct net_device *dev)
 {
 	dev->netdev_ops 	= &xfrmi_netdev_ops;
 	dev->type		= ARPHRD_NONE;
-	dev->hard_header_len 	= ETH_HLEN;
-	dev->min_header_len	= ETH_HLEN;
 	dev->mtu		= ETH_DATA_LEN;
 	dev->min_mtu		= ETH_MIN_MTU;
-	dev->max_mtu		= ETH_DATA_LEN;
-	dev->addr_len		= ETH_ALEN;
+	dev->max_mtu		= IP_MAX_MTU;
 	dev->flags 		= IFF_NOARP;
 	dev->needs_free_netdev	= true;
 	dev->priv_destructor	= xfrmi_dev_free;
-- 
cgit 


From 8aaea2b0428b6aad7c7e22d3fddc31a78bb1d724 Mon Sep 17 00:00:00 2001
From: Xu Wang <vulab@iscas.ac.cn>
Date: Mon, 13 Jan 2020 09:00:36 +0000
Subject: xfrm: interface: do not confirm neighbor when do pmtu update

When do IPv6 tunnel PMTU update and calls __ip6_rt_update_pmtu() in the end,
we should not call dst_confirm_neigh() as there is no two-way communication.

Signed-off-by: Xu Wang <vulab@iscas.ac.cn>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_interface.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 00393179f185..dc651a628dcf 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -294,7 +294,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 
 	mtu = dst_mtu(dst);
 	if (!skb->ignore_df && skb->len > mtu) {
-		skb_dst_update_pmtu(skb, mtu);
+		skb_dst_update_pmtu_no_confirm(skb, mtu);
 
 		if (skb->protocol == htons(ETH_P_IPV6)) {
 			if (mtu < IPV6_MIN_MTU)
-- 
cgit 


From 4e4362d2bf2a49ff44dbbc9585207977ca3d71d0 Mon Sep 17 00:00:00 2001
From: Ulrich Weber <ulrich.weber@gmail.com>
Date: Wed, 15 Jan 2020 12:11:29 +0100
Subject: xfrm: support output_mark for offload ESP packets

Commit 9b42c1f179a6 ("xfrm: Extend the output_mark") added output_mark
support but missed ESP offload support.

xfrm_smark_get() is not called within xfrm_input() for packets coming
from esp4_gro_receive() or esp6_gro_receive(). Therefore call
xfrm_smark_get() directly within these functions.

Fixes: 9b42c1f179a6 ("xfrm: Extend the output_mark to support input direction and masking.")
Signed-off-by: Ulrich Weber <ulrich.weber@gmail.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/ipv4/esp4_offload.c | 2 ++
 net/ipv6/esp6_offload.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 0e4a7cf6bc87..e2e219c7854a 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -57,6 +57,8 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head,
 		if (!x)
 			goto out_reset;
 
+		skb->mark = xfrm_smark_get(skb->mark, x);
+
 		sp->xvec[sp->len++] = x;
 		sp->olen++;
 
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index e31626ffccd1..fd535053245b 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -79,6 +79,8 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
 		if (!x)
 			goto out_reset;
 
+		skb->mark = xfrm_smark_get(skb->mark, x);
+
 		sp->xvec[sp->len++] = x;
 		sp->olen++;
 
-- 
cgit 


From 7eaecf7963c1c8f62d62c6a8e7c439b0e7f2d365 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Sat, 18 Jan 2020 11:27:25 +0100
Subject: netfilter: nft_osf: add missing check for DREG attribute

syzbot reports just another NULL deref crash because of missing test
for presence of the attribute.

Reported-by: syzbot+cf23983d697c26c34f60@syzkaller.appspotmail.com
Fixes:  b96af92d6eaf9fadd ("netfilter: nf_tables: implement Passive OS fingerprint module in nft_osf")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_osf.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c
index f54d6ae15bb1..b42247aa48a9 100644
--- a/net/netfilter/nft_osf.c
+++ b/net/netfilter/nft_osf.c
@@ -61,6 +61,9 @@ static int nft_osf_init(const struct nft_ctx *ctx,
 	int err;
 	u8 ttl;
 
+	if (!tb[NFTA_OSF_DREG])
+		return -EINVAL;
+
 	if (tb[NFTA_OSF_TTL]) {
 		ttl = nla_get_u8(tb[NFTA_OSF_TTL]);
 		if (ttl > 2)
-- 
cgit 


From 690afc165bb314354667f67157c1a1aea7dc797a Mon Sep 17 00:00:00 2001
From: Niko Kortstrom <niko.kortstrom@nokia.com>
Date: Thu, 16 Jan 2020 11:43:27 +0200
Subject: net: ip6_gre: fix moving ip6gre between namespaces

Support for moving IPv4 GRE tunnels between namespaces was added in
commit b57708add314 ("gre: add x-netns support"). The respective change
for IPv6 tunnels, commit 22f08069e8b4 ("ip6gre: add x-netns support")
did not drop NETIF_F_NETNS_LOCAL flag so moving them from one netns to
another is still denied in IPv6 case. Drop NETIF_F_NETNS_LOCAL flag from
ip6gre tunnels to allow moving ip6gre tunnel endpoints between network
namespaces.

Signed-off-by: Niko Kortstrom <niko.kortstrom@nokia.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: William Tu <u9012063@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index ee968d980746..55bfc5149d0c 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1466,7 +1466,6 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
 		dev->mtu -= 8;
 
 	if (tunnel->parms.collect_md) {
-		dev->features |= NETIF_F_NETNS_LOCAL;
 		netif_keep_dst(dev);
 	}
 	ip6gre_tnl_init_features(dev);
@@ -1894,7 +1893,6 @@ static void ip6gre_tap_setup(struct net_device *dev)
 	dev->needs_free_netdev = true;
 	dev->priv_destructor = ip6gre_dev_free;
 
-	dev->features |= NETIF_F_NETNS_LOCAL;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	netif_keep_dst(dev);
@@ -2197,7 +2195,6 @@ static void ip6erspan_tap_setup(struct net_device *dev)
 	dev->needs_free_netdev = true;
 	dev->priv_destructor = ip6gre_dev_free;
 
-	dev->features |= NETIF_F_NETNS_LOCAL;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	netif_keep_dst(dev);
-- 
cgit 


From 80892772c4edac88c538165d26a0105f19b61c1c Mon Sep 17 00:00:00 2001
From: "xiaofeng.yan" <yanxiaofeng7@jd.com>
Date: Mon, 20 Jan 2020 14:26:39 +0800
Subject: hsr: Fix a compilation error

A compliation error happen when building branch 5.5-rc7

In file included from net/hsr/hsr_main.c:12:0:
net/hsr/hsr_main.h:194:20: error: two or more data types in declaration specifiers
 static inline void void hsr_debugfs_rename(struct net_device *dev)

So Removed one void.

Fixes: 4c2d5e33dcd3 ("hsr: rename debugfs file when interface name is changed")
Signed-off-by: xiaofeng.yan <yanxiaofeng7@jd.com>
Acked-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/hsr/hsr_main.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h
index d40de84a637f..754d84b217f0 100644
--- a/net/hsr/hsr_main.h
+++ b/net/hsr/hsr_main.h
@@ -191,7 +191,7 @@ void hsr_debugfs_term(struct hsr_priv *priv);
 void hsr_debugfs_create_root(void);
 void hsr_debugfs_remove_root(void);
 #else
-static inline void void hsr_debugfs_rename(struct net_device *dev)
+static inline void hsr_debugfs_rename(struct net_device *dev)
 {
 }
 static inline void hsr_debugfs_init(struct hsr_priv *priv,
-- 
cgit 


From 32c72165dbd0e246e69d16a3ad348a4851afd415 Mon Sep 17 00:00:00 2001
From: Kadlecsik József <kadlec@blackhole.kfki.hu>
Date: Sun, 19 Jan 2020 22:06:49 +0100
Subject: netfilter: ipset: use bitmap infrastructure completely

The bitmap allocation did not use full unsigned long sizes
when calculating the required size and that was triggered by KASAN
as slab-out-of-bounds read in several places. The patch fixes all
of them.

Reported-by: syzbot+fabca5cbf5e54f3fe2de@syzkaller.appspotmail.com
Reported-by: syzbot+827ced406c9a1d9570ed@syzkaller.appspotmail.com
Reported-by: syzbot+190d63957b22ef673ea5@syzkaller.appspotmail.com
Reported-by: syzbot+dfccdb2bdb4a12ad425e@syzkaller.appspotmail.com
Reported-by: syzbot+df0d0f5895ef1f41a65b@syzkaller.appspotmail.com
Reported-by: syzbot+b08bd19bb37513357fd4@syzkaller.appspotmail.com
Reported-by: syzbot+53cdd0ec0bbabd53370a@syzkaller.appspotmail.com
Signed-off-by: Jozsef Kadlecsik <kadlec@netfilter.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/ipset/ip_set.h    | 7 -------
 net/netfilter/ipset/ip_set_bitmap_gen.h   | 2 +-
 net/netfilter/ipset/ip_set_bitmap_ip.c    | 6 +++---
 net/netfilter/ipset/ip_set_bitmap_ipmac.c | 6 +++---
 net/netfilter/ipset/ip_set_bitmap_port.c  | 6 +++---
 5 files changed, 10 insertions(+), 17 deletions(-)

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index 4d8b1eaf7708..908d38dbcb91 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -426,13 +426,6 @@ ip6addrptr(const struct sk_buff *skb, bool src, struct in6_addr *addr)
 	       sizeof(*addr));
 }
 
-/* Calculate the bytes required to store the inclusive range of a-b */
-static inline int
-bitmap_bytes(u32 a, u32 b)
-{
-	return 4 * ((((b - a + 8) / 8) + 3) / 4);
-}
-
 /* How often should the gc be run by default */
 #define IPSET_GC_TIME			(3 * 60)
 
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index 077a2cb65fcb..26ab0e9612d8 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -75,7 +75,7 @@ mtype_flush(struct ip_set *set)
 
 	if (set->extensions & IPSET_EXT_DESTROY)
 		mtype_ext_cleanup(set);
-	memset(map->members, 0, map->memsize);
+	bitmap_zero(map->members, map->elements);
 	set->elements = 0;
 	set->ext_size = 0;
 }
diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c
index abe8f77d7d23..0a2196f59106 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ip.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ip.c
@@ -37,7 +37,7 @@ MODULE_ALIAS("ip_set_bitmap:ip");
 
 /* Type structure */
 struct bitmap_ip {
-	void *members;		/* the set members */
+	unsigned long *members;	/* the set members */
 	u32 first_ip;		/* host byte order, included in range */
 	u32 last_ip;		/* host byte order, included in range */
 	u32 elements;		/* number of max elements in the set */
@@ -220,7 +220,7 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map,
 	    u32 first_ip, u32 last_ip,
 	    u32 elements, u32 hosts, u8 netmask)
 {
-	map->members = ip_set_alloc(map->memsize);
+	map->members = bitmap_zalloc(elements, GFP_KERNEL | __GFP_NOWARN);
 	if (!map->members)
 		return false;
 	map->first_ip = first_ip;
@@ -322,7 +322,7 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
 	if (!map)
 		return -ENOMEM;
 
-	map->memsize = bitmap_bytes(0, elements - 1);
+	map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long);
 	set->variant = &bitmap_ip;
 	if (!init_map_ip(set, map, first_ip, last_ip,
 			 elements, hosts, netmask)) {
diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index b618713297da..739e343efaf6 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -42,7 +42,7 @@ enum {
 
 /* Type structure */
 struct bitmap_ipmac {
-	void *members;		/* the set members */
+	unsigned long *members;	/* the set members */
 	u32 first_ip;		/* host byte order, included in range */
 	u32 last_ip;		/* host byte order, included in range */
 	u32 elements;		/* number of max elements in the set */
@@ -299,7 +299,7 @@ static bool
 init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map,
 	       u32 first_ip, u32 last_ip, u32 elements)
 {
-	map->members = ip_set_alloc(map->memsize);
+	map->members = bitmap_zalloc(elements, GFP_KERNEL | __GFP_NOWARN);
 	if (!map->members)
 		return false;
 	map->first_ip = first_ip;
@@ -360,7 +360,7 @@ bitmap_ipmac_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
 	if (!map)
 		return -ENOMEM;
 
-	map->memsize = bitmap_bytes(0, elements - 1);
+	map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long);
 	set->variant = &bitmap_ipmac;
 	if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) {
 		kfree(map);
diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c
index 23d6095cb196..b49978dd810d 100644
--- a/net/netfilter/ipset/ip_set_bitmap_port.c
+++ b/net/netfilter/ipset/ip_set_bitmap_port.c
@@ -30,7 +30,7 @@ MODULE_ALIAS("ip_set_bitmap:port");
 
 /* Type structure */
 struct bitmap_port {
-	void *members;		/* the set members */
+	unsigned long *members;	/* the set members */
 	u16 first_port;		/* host byte order, included in range */
 	u16 last_port;		/* host byte order, included in range */
 	u32 elements;		/* number of max elements in the set */
@@ -231,7 +231,7 @@ static bool
 init_map_port(struct ip_set *set, struct bitmap_port *map,
 	      u16 first_port, u16 last_port)
 {
-	map->members = ip_set_alloc(map->memsize);
+	map->members = bitmap_zalloc(map->elements, GFP_KERNEL | __GFP_NOWARN);
 	if (!map->members)
 		return false;
 	map->first_port = first_port;
@@ -271,7 +271,7 @@ bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
 		return -ENOMEM;
 
 	map->elements = elements;
-	map->memsize = bitmap_bytes(0, map->elements);
+	map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long);
 	set->variant = &bitmap_port;
 	if (!init_map_port(set, map, first_port, last_port)) {
 		kfree(map);
-- 
cgit 


From 62ebaeaedee7591c257543d040677a60e35c7aec Mon Sep 17 00:00:00 2001
From: Yuki Taguchi <tagyounit@gmail.com>
Date: Mon, 20 Jan 2020 13:48:37 +0900
Subject: ipv6: sr: remove SKB_GSO_IPXIP6 on End.D* actions

After LRO/GRO is applied, SRv6 encapsulated packets have
SKB_GSO_IPXIP6 feature flag, and this flag must be removed right after
decapulation procedure.

Currently, SKB_GSO_IPXIP6 flag is not removed on End.D* actions, which
creates inconsistent packet state, that is, a normal TCP/IP packets
have the SKB_GSO_IPXIP6 flag. This behavior can cause unexpected
fallback to GSO on routing to netdevices that do not support
SKB_GSO_IPXIP6. For example, on inter-VRF forwarding, decapsulated
packets separated into small packets by GSO because VRF devices do not
support TSO for packets with SKB_GSO_IPXIP6 flag, and this degrades
forwarding performance.

This patch removes encapsulation related GSO flags from the skb right
after the End.D* action is applied.

Fixes: d7a669dd2f8b ("ipv6: sr: add helper functions for seg6local")
Signed-off-by: Yuki Taguchi <tagyounit@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6_local.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index 85a5447a3e8d..7cbc19731997 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -23,6 +23,7 @@
 #include <net/addrconf.h>
 #include <net/ip6_route.h>
 #include <net/dst_cache.h>
+#include <net/ip_tunnels.h>
 #ifdef CONFIG_IPV6_SEG6_HMAC
 #include <net/seg6_hmac.h>
 #endif
@@ -135,7 +136,8 @@ static bool decap_and_validate(struct sk_buff *skb, int proto)
 
 	skb_reset_network_header(skb);
 	skb_reset_transport_header(skb);
-	skb->encapsulation = 0;
+	if (iptunnel_pull_offloads(skb))
+		return false;
 
 	return true;
 }
-- 
cgit 


From cb626bf566eb4433318d35681286c494f04fedcc Mon Sep 17 00:00:00 2001
From: Jouni Hogander <jouni.hogander@unikie.com>
Date: Mon, 20 Jan 2020 09:51:03 +0200
Subject: net-sysfs: Fix reference count leak

Netdev_register_kobject is calling device_initialize. In case of error
reference taken by device_initialize is not given up.

Drivers are supposed to call free_netdev in case of error. In non-error
case the last reference is given up there and device release sequence
is triggered. In error case this reference is kept and the release
sequence is never started.

Fix this by setting reg_state as NETREG_UNREGISTERED if registering
fails.

This is the rootcause for couple of memory leaks reported by Syzkaller:

BUG: memory leak unreferenced object 0xffff8880675ca008 (size 256):
  comm "netdev_register", pid 281, jiffies 4294696663 (age 6.808s)
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
  backtrace:
    [<0000000058ca4711>] kmem_cache_alloc_trace+0x167/0x280
    [<000000002340019b>] device_add+0x882/0x1750
    [<000000001d588c3a>] netdev_register_kobject+0x128/0x380
    [<0000000011ef5535>] register_netdevice+0xa1b/0xf00
    [<000000007fcf1c99>] __tun_chr_ioctl+0x20d5/0x3dd0
    [<000000006a5b7b2b>] tun_chr_ioctl+0x2f/0x40
    [<00000000f30f834a>] do_vfs_ioctl+0x1c7/0x1510
    [<00000000fba062ea>] ksys_ioctl+0x99/0xb0
    [<00000000b1c1b8d2>] __x64_sys_ioctl+0x78/0xb0
    [<00000000984cabb9>] do_syscall_64+0x16f/0x580
    [<000000000bde033d>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
    [<00000000e6ca2d9f>] 0xffffffffffffffff

BUG: memory leak
unreferenced object 0xffff8880668ba588 (size 8):
  comm "kobject_set_nam", pid 286, jiffies 4294725297 (age 9.871s)
  hex dump (first 8 bytes):
    6e 72 30 00 cc be df 2b                          nr0....+
  backtrace:
    [<00000000a322332a>] __kmalloc_track_caller+0x16e/0x290
    [<00000000236fd26b>] kstrdup+0x3e/0x70
    [<00000000dd4a2815>] kstrdup_const+0x3e/0x50
    [<0000000049a377fc>] kvasprintf_const+0x10e/0x160
    [<00000000627fc711>] kobject_set_name_vargs+0x5b/0x140
    [<0000000019eeab06>] dev_set_name+0xc0/0xf0
    [<0000000069cb12bc>] netdev_register_kobject+0xc8/0x320
    [<00000000f2e83732>] register_netdevice+0xa1b/0xf00
    [<000000009e1f57cc>] __tun_chr_ioctl+0x20d5/0x3dd0
    [<000000009c560784>] tun_chr_ioctl+0x2f/0x40
    [<000000000d759e02>] do_vfs_ioctl+0x1c7/0x1510
    [<00000000351d7c31>] ksys_ioctl+0x99/0xb0
    [<000000008390040a>] __x64_sys_ioctl+0x78/0xb0
    [<0000000052d196b7>] do_syscall_64+0x16f/0x580
    [<0000000019af9236>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
    [<00000000bc384531>] 0xffffffffffffffff

v3 -> v4:
  Set reg_state to NETREG_UNREGISTERED if registering fails

v2 -> v3:
* Replaced BUG_ON with WARN_ON in free_netdev and netdev_release

v1 -> v2:
* Relying on driver calling free_netdev rather than calling
  put_device directly in error path

Reported-by: syzbot+ad8ca40ecd77896d51e2@syzkaller.appspotmail.com
Cc: David Miller <davem@davemloft.net>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Signed-off-by: Jouni Hogander <jouni.hogander@unikie.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 7e885d069707..e82e9b82dfd9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9302,8 +9302,10 @@ int register_netdevice(struct net_device *dev)
 		goto err_uninit;
 
 	ret = netdev_register_kobject(dev);
-	if (ret)
+	if (ret) {
+		dev->reg_state = NETREG_UNREGISTERED;
 		goto err_uninit;
+	}
 	dev->reg_state = NETREG_REGISTERED;
 
 	__netdev_update_features(dev);
-- 
cgit 


From 5b2f1f3070b6447b76174ea8bfb7390dc6253ebd Mon Sep 17 00:00:00 2001
From: Wen Yang <wenyang@linux.alibaba.com>
Date: Mon, 20 Jan 2020 18:04:56 +0800
Subject: tcp_bbr: improve arithmetic division in bbr_update_bw()

do_div() does a 64-by-32 division. Use div64_long() instead of it
if the divisor is long, to avoid truncation to 32-bit.
And as a nice side effect also cleans up the function a bit.

Signed-off-by: Wen Yang <wenyang@linux.alibaba.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_bbr.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index a6545ef0d27b..6c4d79baff26 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -779,8 +779,7 @@ static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs)
 	 * bandwidth sample. Delivered is in packets and interval_us in uS and
 	 * ratio will be <<1 for most connections. So delivered is first scaled.
 	 */
-	bw = (u64)rs->delivered * BW_UNIT;
-	do_div(bw, rs->interval_us);
+	bw = div64_long((u64)rs->delivered * BW_UNIT, rs->interval_us);
 
 	/* If this sample is application-limited, it is likely to have a very
 	 * low delivered count that represents application behavior rather than
-- 
cgit 


From ce896476c65d72b4b99fa09c2f33436b4198f034 Mon Sep 17 00:00:00 2001
From: James Hughes <james.hughes@raspberrypi.org>
Date: Mon, 20 Jan 2020 11:12:40 +0000
Subject: net: usb: lan78xx: Add .ndo_features_check

As reported by Eric Dumazet, there are still some outstanding
cases where the driver does not handle TSO correctly when skb's
are over a certain size. Most cases have been fixed, this patch
should ensure that forwarded SKB's that are greater than
MAX_SINGLE_PACKET_SIZE - TX_OVERHEAD are software segmented
and handled correctly.

Signed-off-by: James Hughes <james.hughes@raspberrypi.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 75bdfae5f3e2..c2a58f05b9a1 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -20,6 +20,7 @@
 #include <linux/mdio.h>
 #include <linux/phy.h>
 #include <net/ip6_checksum.h>
+#include <net/vxlan.h>
 #include <linux/interrupt.h>
 #include <linux/irqdomain.h>
 #include <linux/irq.h>
@@ -3668,6 +3669,19 @@ static void lan78xx_tx_timeout(struct net_device *net)
 	tasklet_schedule(&dev->bh);
 }
 
+static netdev_features_t lan78xx_features_check(struct sk_buff *skb,
+						struct net_device *netdev,
+						netdev_features_t features)
+{
+	if (skb->len + TX_OVERHEAD > MAX_SINGLE_PACKET_SIZE)
+		features &= ~NETIF_F_GSO_MASK;
+
+	features = vlan_features_check(skb, features);
+	features = vxlan_features_check(skb, features);
+
+	return features;
+}
+
 static const struct net_device_ops lan78xx_netdev_ops = {
 	.ndo_open		= lan78xx_open,
 	.ndo_stop		= lan78xx_stop,
@@ -3681,6 +3695,7 @@ static const struct net_device_ops lan78xx_netdev_ops = {
 	.ndo_set_features	= lan78xx_set_features,
 	.ndo_vlan_rx_add_vid	= lan78xx_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= lan78xx_vlan_rx_kill_vid,
+	.ndo_features_check	= lan78xx_features_check,
 };
 
 static void lan78xx_stat_monitor(struct timer_list *t)
-- 
cgit 


From bfe02b9f9476bc8784ebb0f78fa244ad15bb15ea Mon Sep 17 00:00:00 2001
From: Theodore Dubois <tblodt@icloud.com>
Date: Mon, 20 Jan 2020 14:10:53 -0800
Subject: tcp: remove redundant assigment to snd_cwnd

Not sure how this got in here. git blame says the second assignment was
added in 3a9a57f6, but that commit also removed the first assignment.

Signed-off-by: Theodore Dubois <tblodt@icloud.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d885ba868822..04273d6aa36b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2614,7 +2614,6 @@ int tcp_disconnect(struct sock *sk, int flags)
 	WRITE_ONCE(tp->write_seq, seq);
 
 	icsk->icsk_backoff = 0;
-	tp->snd_cwnd = 2;
 	icsk->icsk_probes_out = 0;
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
 	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
-- 
cgit 


From d0f418516022c32ecceaf4275423e5bd3f8743a9 Mon Sep 17 00:00:00 2001
From: William Dauchy <w.dauchy@criteo.com>
Date: Tue, 21 Jan 2020 15:26:24 +0100
Subject: net, ip_tunnel: fix namespaces move

in the same manner as commit 690afc165bb3 ("net: ip6_gre: fix moving
ip6gre between namespaces"), fix namespace moving as it was broken since
commit 2e15ea390e6f ("ip_gre: Add support to collect tunnel metadata.").
Indeed, the ip6_gre commit removed the local flag for collect_md
condition, so there is no reason to keep it for ip_gre/ip_tunnel.

this patch will fix both ip_tunnel and ip_gre modules.

Fixes: 2e15ea390e6f ("ip_gre: Add support to collect tunnel metadata.")
Signed-off-by: William Dauchy <w.dauchy@criteo.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 0fe2a5d3e258..74e1d964a615 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -1236,10 +1236,8 @@ int ip_tunnel_init(struct net_device *dev)
 	iph->version		= 4;
 	iph->ihl		= 5;
 
-	if (tunnel->collect_md) {
-		dev->features |= NETIF_F_NETNS_LOCAL;
+	if (tunnel->collect_md)
 		netif_keep_dst(dev);
-	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_init);
-- 
cgit 


From d829229e35f302fd49c052b5c5906c90ecf9911d Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Tue, 3 Dec 2019 10:08:49 +0200
Subject: iwlwifi: mvm: don't send the IWL_MVM_RXQ_NSSN_SYNC notif to Rx queues

The purpose of this was to keep all the queues updated with
the Rx sequence numbers because unlikely yet possible
situations where queues can't understand if a specific
packet needs to be dropped or not.

Unfortunately, it was reported that this caused issues in
our DMA engine. We don't fully understand how this is related,
but this is being currently debugged. For now, just don't send
this notification to the Rx queues. This de-facto reverts my
commit 3c514bf831ac12356b695ff054bef641b9e99593:

iwlwifi: mvm: add a loose synchronization of the NSSN across Rx queues

This issue was reported here:
https://bugzilla.kernel.org/show_bug.cgi?id=204873
https://bugzilla.kernel.org/show_bug.cgi?id=205001
and others maybe.

Fixes: 3c514bf831ac ("iwlwifi: mvm: add a loose synchronization of the NSSN across Rx queues")
CC: <stable@vger.kernel.org> # 5.3+
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlwifi/mvm/constants.h |  1 +
 drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c      | 19 +++++++++++--------
 2 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
index 60aff2ecec12..58df25e2fb32 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
@@ -154,5 +154,6 @@
 #define IWL_MVM_D3_DEBUG			false
 #define IWL_MVM_USE_TWT				false
 #define IWL_MVM_AMPDU_CONSEC_DROPS_DELBA	10
+#define IWL_MVM_USE_NSSN_SYNC			0
 
 #endif /* __MVM_CONSTANTS_H */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index ef99c49247b7..c15f7dbc9516 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -514,14 +514,17 @@ static bool iwl_mvm_is_sn_less(u16 sn1, u16 sn2, u16 buffer_size)
 
 static void iwl_mvm_sync_nssn(struct iwl_mvm *mvm, u8 baid, u16 nssn)
 {
-	struct iwl_mvm_rss_sync_notif notif = {
-		.metadata.type = IWL_MVM_RXQ_NSSN_SYNC,
-		.metadata.sync = 0,
-		.nssn_sync.baid = baid,
-		.nssn_sync.nssn = nssn,
-	};
-
-	iwl_mvm_sync_rx_queues_internal(mvm, (void *)&notif, sizeof(notif));
+	if (IWL_MVM_USE_NSSN_SYNC) {
+		struct iwl_mvm_rss_sync_notif notif = {
+			.metadata.type = IWL_MVM_RXQ_NSSN_SYNC,
+			.metadata.sync = 0,
+			.nssn_sync.baid = baid,
+			.nssn_sync.nssn = nssn,
+		};
+
+		iwl_mvm_sync_rx_queues_internal(mvm, (void *)&notif,
+						sizeof(notif));
+	}
 }
 
 #define RX_REORDER_BUF_TIMEOUT_MQ (HZ / 10)
-- 
cgit 


From 58c8db929db1c1d785a6f5d8f8692e5dbcc35e84 Mon Sep 17 00:00:00 2001
From: Jakub Sitnicki <jakub@cloudflare.com>
Date: Tue, 21 Jan 2020 13:31:47 +0100
Subject: net, sk_msg: Don't check if sock is locked when tearing down psock

As John Fastabend reports [0], psock state tear-down can happen on receive
path *after* unlocking the socket, if the only other psock user, that is
sockmap or sockhash, releases its psock reference before tcp_bpf_recvmsg
does so:

 tcp_bpf_recvmsg()
  psock = sk_psock_get(sk)                         <- refcnt 2
  lock_sock(sk);
  ...
                                  sock_map_free()  <- refcnt 1
  release_sock(sk)
  sk_psock_put()                                   <- refcnt 0

Remove the lockdep check for socket lock in psock tear-down that got
introduced in 7e81a3530206 ("bpf: Sockmap, ensure sock lock held during
tear down").

[0] https://lore.kernel.org/netdev/5e25dc995d7d_74082aaee6e465b441@john-XPS-13-9370.notmuch/

Fixes: 7e81a3530206 ("bpf: Sockmap, ensure sock lock held during tear down")
Reported-by: syzbot+d73682fcf7fee6982fe3@syzkaller.appspotmail.com
Suggested-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skmsg.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 3866d7e20c07..ded2d5227678 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -594,8 +594,6 @@ EXPORT_SYMBOL_GPL(sk_psock_destroy);
 
 void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
 {
-	sock_owned_by_me(sk);
-
 	sk_psock_cork_free(psock);
 	sk_psock_zap_ingress(psock);
 
-- 
cgit 


From 0ace17d56824165c7f4c68785d6b58971db954dd Mon Sep 17 00:00:00 2001
From: Richard Palethorpe <rpalethorpe@suse.com>
Date: Tue, 21 Jan 2020 14:42:58 +0100
Subject: can, slip: Protect tty->disc_data in write_wakeup and close with RCU

write_wakeup can happen in parallel with close/hangup where tty->disc_data
is set to NULL and the netdevice is freed thus also freeing
disc_data. write_wakeup accesses disc_data so we must prevent close from
freeing the netdev while write_wakeup has a non-NULL view of
tty->disc_data.

We also need to make sure that accesses to disc_data are atomic. Which can
all be done with RCU.

This problem was found by Syzkaller on SLCAN, but the same issue is
reproducible with the SLIP line discipline using an LTP test based on the
Syzkaller reproducer.

A fix which didn't use RCU was posted by Hillf Danton.

Fixes: 661f7fda21b1 ("slip: Fix deadlock in write_wakeup")
Fixes: a8e83b17536a ("slcan: Port write_wakeup deadlock fix from slip")
Reported-by: syzbot+017e491ae13c0068598a@syzkaller.appspotmail.com
Signed-off-by: Richard Palethorpe <rpalethorpe@suse.com>
Cc: Wolfgang Grandegger <wg@grandegger.com>
Cc: Marc Kleine-Budde <mkl@pengutronix.de>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Tyler Hall <tylerwhall@gmail.com>
Cc: linux-can@vger.kernel.org
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: syzkaller@googlegroups.com
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/can/slcan.c | 12 ++++++++++--
 drivers/net/slip/slip.c | 12 ++++++++++--
 2 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index 2e57122f02fb..2f5c287eac95 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -344,9 +344,16 @@ static void slcan_transmit(struct work_struct *work)
  */
 static void slcan_write_wakeup(struct tty_struct *tty)
 {
-	struct slcan *sl = tty->disc_data;
+	struct slcan *sl;
+
+	rcu_read_lock();
+	sl = rcu_dereference(tty->disc_data);
+	if (!sl)
+		goto out;
 
 	schedule_work(&sl->tx_work);
+out:
+	rcu_read_unlock();
 }
 
 /* Send a can_frame to a TTY queue. */
@@ -644,10 +651,11 @@ static void slcan_close(struct tty_struct *tty)
 		return;
 
 	spin_lock_bh(&sl->lock);
-	tty->disc_data = NULL;
+	rcu_assign_pointer(tty->disc_data, NULL);
 	sl->tty = NULL;
 	spin_unlock_bh(&sl->lock);
 
+	synchronize_rcu();
 	flush_work(&sl->tx_work);
 
 	/* Flush network side */
diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index 2a91c192659f..61d7e0d1d77d 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -452,9 +452,16 @@ static void slip_transmit(struct work_struct *work)
  */
 static void slip_write_wakeup(struct tty_struct *tty)
 {
-	struct slip *sl = tty->disc_data;
+	struct slip *sl;
+
+	rcu_read_lock();
+	sl = rcu_dereference(tty->disc_data);
+	if (!sl)
+		goto out;
 
 	schedule_work(&sl->tx_work);
+out:
+	rcu_read_unlock();
 }
 
 static void sl_tx_timeout(struct net_device *dev)
@@ -882,10 +889,11 @@ static void slip_close(struct tty_struct *tty)
 		return;
 
 	spin_lock_bh(&sl->lock);
-	tty->disc_data = NULL;
+	rcu_assign_pointer(tty->disc_data, NULL);
 	sl->tty = NULL;
 	spin_unlock_bh(&sl->lock);
 
+	synchronize_rcu();
 	flush_work(&sl->tx_work);
 
 	/* VSV = very important to remove timers */
-- 
cgit 


From c80794323e82ac6ab45052ebba5757ce47b4b588 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Tue, 21 Jan 2020 15:09:40 +0000
Subject: net: Fix packet reordering caused by GRO and listified RX cooperation

Commit 323ebb61e32b ("net: use listified RX for handling GRO_NORMAL
skbs") introduces batching of GRO_NORMAL packets in napi_frags_finish,
and commit 6570bc79c0df ("net: core: use listified Rx for GRO_NORMAL in
napi_gro_receive()") adds the same to napi_skb_finish. However,
dev_gro_receive (that is called just before napi_{frags,skb}_finish) can
also pass skbs to the networking stack: e.g., when the GRO session is
flushed, napi_gro_complete is called, which passes pp directly to
netif_receive_skb_internal, skipping napi->rx_list. It means that the
packet stored in pp will be handled by the stack earlier than the
packets that arrived before, but are still waiting in napi->rx_list. It
leads to TCP reorderings that can be observed in the TCPOFOQueue counter
in netstat.

This commit fixes the reordering issue by making napi_gro_complete also
use napi->rx_list, so that all packets going through GRO will keep their
order. In order to keep napi_gro_flush working properly, gro_normal_list
calls are moved after the flush to clear napi->rx_list.

iwlwifi calls napi_gro_flush directly and does the same thing that is
done by gro_normal_list, so the same change is applied there:
napi_gro_flush is moved to be before the flush of napi->rx_list.

A few other drivers also use napi_gro_flush (brocade/bna/bnad.c,
cortina/gemini.c, hisilicon/hns3/hns3_enet.c). The first two also use
napi_complete_done afterwards, which performs the gro_normal_list flush,
so they are fine. The latter calls napi_gro_receive right after
napi_gro_flush, so it can end up with non-empty napi->rx_list anyway.

Fixes: 323ebb61e32b ("net: use listified RX for handling GRO_NORMAL skbs")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Cc: Alexander Lobakin <alobakin@dlink.ru>
Cc: Edward Cree <ecree@solarflare.com>
Acked-by: Alexander Lobakin <alobakin@dlink.ru>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Acked-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireless/intel/iwlwifi/pcie/rx.c |  4 +-
 net/core/dev.c                               | 64 ++++++++++++++--------------
 2 files changed, 35 insertions(+), 33 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index 452da44a21e0..f0b8ff67a1bc 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -1529,13 +1529,13 @@ out:
 
 	napi = &rxq->napi;
 	if (napi->poll) {
+		napi_gro_flush(napi, false);
+
 		if (napi->rx_count) {
 			netif_receive_skb_list(&napi->rx_list);
 			INIT_LIST_HEAD(&napi->rx_list);
 			napi->rx_count = 0;
 		}
-
-		napi_gro_flush(napi, false);
 	}
 
 	iwl_pcie_rxq_restock(trans, rxq);
diff --git a/net/core/dev.c b/net/core/dev.c
index e82e9b82dfd9..cca03914108a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5491,9 +5491,29 @@ static void flush_all_backlogs(void)
 	put_online_cpus();
 }
 
+/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */
+static void gro_normal_list(struct napi_struct *napi)
+{
+	if (!napi->rx_count)
+		return;
+	netif_receive_skb_list_internal(&napi->rx_list);
+	INIT_LIST_HEAD(&napi->rx_list);
+	napi->rx_count = 0;
+}
+
+/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded,
+ * pass the whole batch up to the stack.
+ */
+static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb)
+{
+	list_add_tail(&skb->list, &napi->rx_list);
+	if (++napi->rx_count >= gro_normal_batch)
+		gro_normal_list(napi);
+}
+
 INDIRECT_CALLABLE_DECLARE(int inet_gro_complete(struct sk_buff *, int));
 INDIRECT_CALLABLE_DECLARE(int ipv6_gro_complete(struct sk_buff *, int));
-static int napi_gro_complete(struct sk_buff *skb)
+static int napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb)
 {
 	struct packet_offload *ptype;
 	__be16 type = skb->protocol;
@@ -5526,7 +5546,8 @@ static int napi_gro_complete(struct sk_buff *skb)
 	}
 
 out:
-	return netif_receive_skb_internal(skb);
+	gro_normal_one(napi, skb);
+	return NET_RX_SUCCESS;
 }
 
 static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index,
@@ -5539,7 +5560,7 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index,
 		if (flush_old && NAPI_GRO_CB(skb)->age == jiffies)
 			return;
 		skb_list_del_init(skb);
-		napi_gro_complete(skb);
+		napi_gro_complete(napi, skb);
 		napi->gro_hash[index].count--;
 	}
 
@@ -5641,7 +5662,7 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow)
 	}
 }
 
-static void gro_flush_oldest(struct list_head *head)
+static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head)
 {
 	struct sk_buff *oldest;
 
@@ -5657,7 +5678,7 @@ static void gro_flush_oldest(struct list_head *head)
 	 * SKB to the chain.
 	 */
 	skb_list_del_init(oldest);
-	napi_gro_complete(oldest);
+	napi_gro_complete(napi, oldest);
 }
 
 INDIRECT_CALLABLE_DECLARE(struct sk_buff *inet_gro_receive(struct list_head *,
@@ -5733,7 +5754,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 
 	if (pp) {
 		skb_list_del_init(pp);
-		napi_gro_complete(pp);
+		napi_gro_complete(napi, pp);
 		napi->gro_hash[hash].count--;
 	}
 
@@ -5744,7 +5765,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		goto normal;
 
 	if (unlikely(napi->gro_hash[hash].count >= MAX_GRO_SKBS)) {
-		gro_flush_oldest(gro_head);
+		gro_flush_oldest(napi, gro_head);
 	} else {
 		napi->gro_hash[hash].count++;
 	}
@@ -5802,26 +5823,6 @@ struct packet_offload *gro_find_complete_by_type(__be16 type)
 }
 EXPORT_SYMBOL(gro_find_complete_by_type);
 
-/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */
-static void gro_normal_list(struct napi_struct *napi)
-{
-	if (!napi->rx_count)
-		return;
-	netif_receive_skb_list_internal(&napi->rx_list);
-	INIT_LIST_HEAD(&napi->rx_list);
-	napi->rx_count = 0;
-}
-
-/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded,
- * pass the whole batch up to the stack.
- */
-static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb)
-{
-	list_add_tail(&skb->list, &napi->rx_list);
-	if (++napi->rx_count >= gro_normal_batch)
-		gro_normal_list(napi);
-}
-
 static void napi_skb_free_stolen_head(struct sk_buff *skb)
 {
 	skb_dst_drop(skb);
@@ -6200,8 +6201,6 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 				 NAPIF_STATE_IN_BUSY_POLL)))
 		return false;
 
-	gro_normal_list(n);
-
 	if (n->gro_bitmask) {
 		unsigned long timeout = 0;
 
@@ -6217,6 +6216,9 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 			hrtimer_start(&n->timer, ns_to_ktime(timeout),
 				      HRTIMER_MODE_REL_PINNED);
 	}
+
+	gro_normal_list(n);
+
 	if (unlikely(!list_empty(&n->poll_list))) {
 		/* If n->poll_list is not empty, we need to mask irqs */
 		local_irq_save(flags);
@@ -6548,8 +6550,6 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 		goto out_unlock;
 	}
 
-	gro_normal_list(n);
-
 	if (n->gro_bitmask) {
 		/* flush too old packets
 		 * If HZ < 1000, flush all packets.
@@ -6557,6 +6557,8 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 		napi_gro_flush(n, HZ >= 1000);
 	}
 
+	gro_normal_list(n);
+
 	/* Some drivers may have called napi_schedule
 	 * prior to exhausting their budget.
 	 */
-- 
cgit 


From bda6a35505e28b70d48096c933d5949c9b6caf9a Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 22 Jan 2020 20:38:39 +0100
Subject: net: Add Jakub to MAINTAINERS for networking general.

Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index cf6ccca6e61c..7b96ebff3511 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11499,6 +11499,7 @@ F:	drivers/net/dsa/
 
 NETWORKING [GENERAL]
 M:	"David S. Miller" <davem@davemloft.net>
+M:	Jakub Kicinski <kuba@kernel.org>
 L:	netdev@vger.kernel.org
 W:	http://www.linuxfoundation.org/en/Net
 Q:	http://patchwork.ozlabs.org/project/netdev/list/
-- 
cgit 


From d39ca2590d10712f412add7a88e1dd467a7246f4 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 21 Jan 2020 16:50:49 +0100
Subject: Revert "udp: do rmem bulk free even if the rx sk queue is empty"

This reverts commit 0d4a6608f68c7532dcbfec2ea1150c9761767d03.

Williem reported that after commit 0d4a6608f68c ("udp: do rmem bulk
free even if the rx sk queue is empty") the memory allocated by
an almost idle system with many UDP sockets can grow a lot.

For stable kernel keep the solution as simple as possible and revert
the offending commit.

Reported-by: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Diagnosed-by: Eric Dumazet <eric.dumazet@gmail.com>
Fixes: 0d4a6608f68c ("udp: do rmem bulk free even if the rx sk queue is empty")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 93a355b6b092..030d43c7c957 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1368,7 +1368,8 @@ static void udp_rmem_release(struct sock *sk, int size, int partial,
 	if (likely(partial)) {
 		up->forward_deficit += size;
 		size = up->forward_deficit;
-		if (size < (sk->sk_rcvbuf >> 2))
+		if (size < (sk->sk_rcvbuf >> 2) &&
+		    !skb_queue_empty(&up->reader_queue))
 			return;
 	} else {
 		size += up->forward_deficit;
-- 
cgit 


From 36d79af7fb59d6d9106feb9c1855eb93d6d53fe6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 21 Jan 2020 11:02:20 -0800
Subject: net_sched: use validated TCA_KIND attribute in tc_new_tfilter()

sysbot found another issue in tc_new_tfilter().
We probably should use @name which contains the sanitized
version of TCA_KIND.

BUG: KMSAN: uninit-value in string_nocheck lib/vsprintf.c:608 [inline]
BUG: KMSAN: uninit-value in string+0x522/0x690 lib/vsprintf.c:689
CPU: 1 PID: 10753 Comm: syz-executor.1 Not tainted 5.5.0-rc5-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 string_nocheck lib/vsprintf.c:608 [inline]
 string+0x522/0x690 lib/vsprintf.c:689
 vsnprintf+0x207d/0x31b0 lib/vsprintf.c:2574
 __request_module+0x2ad/0x11c0 kernel/kmod.c:143
 tcf_proto_lookup_ops+0x241/0x720 net/sched/cls_api.c:139
 tcf_proto_create net/sched/cls_api.c:262 [inline]
 tc_new_tfilter+0x2a4e/0x5010 net/sched/cls_api.c:2058
 rtnetlink_rcv_msg+0xcb7/0x1570 net/core/rtnetlink.c:5415
 netlink_rcv_skb+0x451/0x650 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:5442
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0xf9e/0x1100 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x1248/0x14d0 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:639 [inline]
 sock_sendmsg net/socket.c:659 [inline]
 ____sys_sendmsg+0x12b6/0x1350 net/socket.c:2330
 ___sys_sendmsg net/socket.c:2384 [inline]
 __sys_sendmsg+0x451/0x5f0 net/socket.c:2417
 __do_sys_sendmsg net/socket.c:2426 [inline]
 __se_sys_sendmsg+0x97/0xb0 net/socket.c:2424
 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2424
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x45b349
Code: ad b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f88b3948c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00007f88b39496d4 RCX: 000000000045b349
RDX: 0000000000000000 RSI: 00000000200001c0 RDI: 0000000000000003
RBP: 000000000075bfc8 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 000000000000099f R14: 00000000004cb163 R15: 000000000075bfd4

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:144 [inline]
 kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:127
 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:82
 slab_alloc_node mm/slub.c:2774 [inline]
 __kmalloc_node_track_caller+0xb40/0x1200 mm/slub.c:4382
 __kmalloc_reserve net/core/skbuff.c:141 [inline]
 __alloc_skb+0x2fd/0xac0 net/core/skbuff.c:209
 alloc_skb include/linux/skbuff.h:1049 [inline]
 netlink_alloc_large_skb net/netlink/af_netlink.c:1174 [inline]
 netlink_sendmsg+0x7d3/0x14d0 net/netlink/af_netlink.c:1892
 sock_sendmsg_nosec net/socket.c:639 [inline]
 sock_sendmsg net/socket.c:659 [inline]
 ____sys_sendmsg+0x12b6/0x1350 net/socket.c:2330
 ___sys_sendmsg net/socket.c:2384 [inline]
 __sys_sendmsg+0x451/0x5f0 net/socket.c:2417
 __do_sys_sendmsg net/socket.c:2426 [inline]
 __se_sys_sendmsg+0x97/0xb0 net/socket.c:2424
 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2424
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 6f96c3c6904c ("net_sched: fix backward compatibility for TCA_KIND")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 76e0d122616a..c2cdd0fc2e70 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2055,9 +2055,8 @@ replay:
 							       &chain_info));
 
 		mutex_unlock(&chain->filter_chain_lock);
-		tp_new = tcf_proto_create(nla_data(tca[TCA_KIND]),
-					  protocol, prio, chain, rtnl_held,
-					  extack);
+		tp_new = tcf_proto_create(name, protocol, prio, chain,
+					  rtnl_held, extack);
 		if (IS_ERR(tp_new)) {
 			err = PTR_ERR(tp_new);
 			goto errout_tp;
-- 
cgit 


From 5311a69aaca30fa849c3cc46fb25f75727fb72d0 Mon Sep 17 00:00:00 2001
From: William Dauchy <w.dauchy@criteo.com>
Date: Tue, 21 Jan 2020 21:49:54 +0100
Subject: net, ip6_tunnel: fix namespaces move

in the same manner as commit d0f418516022 ("net, ip_tunnel: fix
namespaces move"), fix namespace moving as it was broken since commit
8d79266bc48c ("ip6_tunnel: add collect_md mode to IPv6 tunnel"), but for
ipv6 this time; there is no reason to keep it for ip6_tunnel.

Fixes: 8d79266bc48c ("ip6_tunnel: add collect_md mode to IPv6 tunnel")
Signed-off-by: William Dauchy <w.dauchy@criteo.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 2f376dbc37d5..b5dd20c4599b 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1877,10 +1877,8 @@ static int ip6_tnl_dev_init(struct net_device *dev)
 	if (err)
 		return err;
 	ip6_tnl_link_config(t);
-	if (t->parms.collect_md) {
-		dev->features |= NETIF_F_NETNS_LOCAL;
+	if (t->parms.collect_md)
 		netif_keep_dst(dev);
-	}
 	return 0;
 }
 
-- 
cgit 


From 3adb4eaa1b4cbadc7858679334d19e840e7df6db Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 22 Jan 2020 20:23:15 +0100
Subject: MAINTAINERS: Make Russell King designated reviewer of phylib

phylink and phylib are interconnected. It makes sense for phylib and
phy driver patches to be also reviewed by the phylink maintainer.
So add Russell King as a designed reviewer of phylib.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 7b96ebff3511..f2b57c4166e0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6197,6 +6197,7 @@ ETHERNET PHY LIBRARY
 M:	Andrew Lunn <andrew@lunn.ch>
 M:	Florian Fainelli <f.fainelli@gmail.com>
 M:	Heiner Kallweit <hkallweit1@gmail.com>
+R:	Russell King <linux@armlinux.org.uk>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/ABI/testing/sysfs-class-net-phydev
-- 
cgit 


From d6bce2137f5d6bb1093e96d2f801479099b28094 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Wed, 22 Jan 2020 15:07:27 +1100
Subject: airo: Fix possible info leak in AIROOLDIOCTL/SIOCDEVPRIVATE

The driver for Cisco Aironet 4500 and 4800 series cards (airo.c),
implements AIROOLDIOCTL/SIOCDEVPRIVATE in airo_ioctl().

The ioctl handler copies an aironet_ioctl struct from userspace, which
includes a command and a length. Some of the commands are handled in
readrids(), which kmalloc()'s a buffer of RIDSIZE (2048) bytes.

That buffer is then passed to PC4500_readrid(), which has two cases.
The else case does some setup and then reads up to RIDSIZE bytes from
the hardware into the kmalloc()'ed buffer.

Here len == RIDSIZE, pBuf is the kmalloc()'ed buffer:

	// read the rid length field
	bap_read(ai, pBuf, 2, BAP1);
	// length for remaining part of rid
	len = min(len, (int)le16_to_cpu(*(__le16*)pBuf)) - 2;
	...
	// read remainder of the rid
	rc = bap_read(ai, ((__le16*)pBuf)+1, len, BAP1);

PC4500_readrid() then returns to readrids() which does:

	len = comp->len;
	if (copy_to_user(comp->data, iobuf, min(len, (int)RIDSIZE))) {

Where comp->len is the user controlled length field.

So if the "rid length field" returned by the hardware is < 2048, and
the user requests 2048 bytes in comp->len, we will leak the previous
contents of the kmalloc()'ed buffer to userspace.

Fix it by kzalloc()'ing the buffer.

Found by Ilja by code inspection, not tested as I don't have the
required hardware.

Reported-by: Ilja Van Sprundel <ivansprundel@ioactive.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireless/cisco/airo.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c
index f43c06569ea1..d69c2ee7e206 100644
--- a/drivers/net/wireless/cisco/airo.c
+++ b/drivers/net/wireless/cisco/airo.c
@@ -7813,7 +7813,7 @@ static int readrids(struct net_device *dev, aironet_ioctl *comp) {
 		return -EINVAL;
 	}
 
-	if ((iobuf = kmalloc(RIDSIZE, GFP_KERNEL)) == NULL)
+	if ((iobuf = kzalloc(RIDSIZE, GFP_KERNEL)) == NULL)
 		return -ENOMEM;
 
 	PC4500_readrid(ai,ridcode,iobuf,RIDSIZE, 1);
-- 
cgit 


From 78f7a7566f5eb59321e99b55a6fdb16ea05b37d1 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Wed, 22 Jan 2020 15:07:28 +1100
Subject: airo: Add missing CAP_NET_ADMIN check in AIROOLDIOCTL/SIOCDEVPRIVATE

The driver for Cisco Aironet 4500 and 4800 series cards (airo.c),
implements AIROOLDIOCTL/SIOCDEVPRIVATE in airo_ioctl().

The ioctl handler copies an aironet_ioctl struct from userspace, which
includes a command. Some of the commands are handled in readrids(),
where the user controlled command is converted into a driver-internal
value called "ridcode".

There are two command values, AIROGWEPKTMP and AIROGWEPKNV, which
correspond to ridcode values of RID_WEP_TEMP and RID_WEP_PERM
respectively. These commands both have checks that the user has
CAP_NET_ADMIN, with the comment that "Only super-user can read WEP
keys", otherwise they return -EPERM.

However there is another command value, AIRORRID, that lets the user
specify the ridcode value directly, with no other checks. This means
the user can bypass the CAP_NET_ADMIN check on AIROGWEPKTMP and
AIROGWEPKNV.

Fix it by moving the CAP_NET_ADMIN check out of the command handling
and instead do it later based on the ridcode. That way regardless of
whether the ridcode is set via AIROGWEPKTMP or AIROGWEPKNV, or passed
in using AIRORID, we always do the CAP_NET_ADMIN check.

Found by Ilja by code inspection, not tested as I don't have the
required hardware.

Reported-by: Ilja Van Sprundel <ivansprundel@ioactive.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireless/cisco/airo.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c
index d69c2ee7e206..c4c8f1b62e1e 100644
--- a/drivers/net/wireless/cisco/airo.c
+++ b/drivers/net/wireless/cisco/airo.c
@@ -7790,16 +7790,8 @@ static int readrids(struct net_device *dev, aironet_ioctl *comp) {
 	case AIROGVLIST:    ridcode = RID_APLIST;       break;
 	case AIROGDRVNAM:   ridcode = RID_DRVNAME;      break;
 	case AIROGEHTENC:   ridcode = RID_ETHERENCAP;   break;
-	case AIROGWEPKTMP:  ridcode = RID_WEP_TEMP;
-		/* Only super-user can read WEP keys */
-		if (!capable(CAP_NET_ADMIN))
-			return -EPERM;
-		break;
-	case AIROGWEPKNV:   ridcode = RID_WEP_PERM;
-		/* Only super-user can read WEP keys */
-		if (!capable(CAP_NET_ADMIN))
-			return -EPERM;
-		break;
+	case AIROGWEPKTMP:  ridcode = RID_WEP_TEMP;	break;
+	case AIROGWEPKNV:   ridcode = RID_WEP_PERM;	break;
 	case AIROGSTAT:     ridcode = RID_STATUS;       break;
 	case AIROGSTATSD32: ridcode = RID_STATSDELTA;   break;
 	case AIROGSTATSC32: ridcode = RID_STATS;        break;
@@ -7813,6 +7805,12 @@ static int readrids(struct net_device *dev, aironet_ioctl *comp) {
 		return -EINVAL;
 	}
 
+	if (ridcode == RID_WEP_TEMP || ridcode == RID_WEP_PERM) {
+		/* Only super-user can read WEP keys */
+		if (!capable(CAP_NET_ADMIN))
+			return -EPERM;
+	}
+
 	if ((iobuf = kzalloc(RIDSIZE, GFP_KERNEL)) == NULL)
 		return -ENOMEM;
 
-- 
cgit 


From d836f5c69d87473ff65c06a6123e5b2cf5e56f5b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 21 Jan 2020 22:47:29 -0800
Subject: net: rtnetlink: validate IFLA_MTU attribute in rtnl_create_link()

rtnl_create_link() needs to apply dev->min_mtu and dev->max_mtu
checks that we apply in do_setlink()

Otherwise malicious users can crash the kernel, for example after
an integer overflow :

BUG: KASAN: use-after-free in memset include/linux/string.h:365 [inline]
BUG: KASAN: use-after-free in __alloc_skb+0x37b/0x5e0 net/core/skbuff.c:238
Write of size 32 at addr ffff88819f20b9c0 by task swapper/0/0

CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.5.0-rc1-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x197/0x210 lib/dump_stack.c:118
 print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374
 __kasan_report.cold+0x1b/0x41 mm/kasan/report.c:506
 kasan_report+0x12/0x20 mm/kasan/common.c:639
 check_memory_region_inline mm/kasan/generic.c:185 [inline]
 check_memory_region+0x134/0x1a0 mm/kasan/generic.c:192
 memset+0x24/0x40 mm/kasan/common.c:108
 memset include/linux/string.h:365 [inline]
 __alloc_skb+0x37b/0x5e0 net/core/skbuff.c:238
 alloc_skb include/linux/skbuff.h:1049 [inline]
 alloc_skb_with_frags+0x93/0x590 net/core/skbuff.c:5664
 sock_alloc_send_pskb+0x7ad/0x920 net/core/sock.c:2242
 sock_alloc_send_skb+0x32/0x40 net/core/sock.c:2259
 mld_newpack+0x1d7/0x7f0 net/ipv6/mcast.c:1609
 add_grhead.isra.0+0x299/0x370 net/ipv6/mcast.c:1713
 add_grec+0x7db/0x10b0 net/ipv6/mcast.c:1844
 mld_send_cr net/ipv6/mcast.c:1970 [inline]
 mld_ifc_timer_expire+0x3d3/0x950 net/ipv6/mcast.c:2477
 call_timer_fn+0x1ac/0x780 kernel/time/timer.c:1404
 expire_timers kernel/time/timer.c:1449 [inline]
 __run_timers kernel/time/timer.c:1773 [inline]
 __run_timers kernel/time/timer.c:1740 [inline]
 run_timer_softirq+0x6c3/0x1790 kernel/time/timer.c:1786
 __do_softirq+0x262/0x98c kernel/softirq.c:292
 invoke_softirq kernel/softirq.c:373 [inline]
 irq_exit+0x19b/0x1e0 kernel/softirq.c:413
 exiting_irq arch/x86/include/asm/apic.h:536 [inline]
 smp_apic_timer_interrupt+0x1a3/0x610 arch/x86/kernel/apic/apic.c:1137
 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:829
 </IRQ>
RIP: 0010:native_safe_halt+0xe/0x10 arch/x86/include/asm/irqflags.h:61
Code: 98 6b ea f9 eb 8a cc cc cc cc cc cc e9 07 00 00 00 0f 00 2d 44 1c 60 00 f4 c3 66 90 e9 07 00 00 00 0f 00 2d 34 1c 60 00 fb f4 <c3> cc 55 48 89 e5 41 57 41 56 41 55 41 54 53 e8 4e 5d 9a f9 e8 79
RSP: 0018:ffffffff89807ce8 EFLAGS: 00000286 ORIG_RAX: ffffffffffffff13
RAX: 1ffffffff13266ae RBX: ffffffff8987a1c0 RCX: 0000000000000000
RDX: dffffc0000000000 RSI: 0000000000000006 RDI: ffffffff8987aa54
RBP: ffffffff89807d18 R08: ffffffff8987a1c0 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: dffffc0000000000
R13: ffffffff8a799980 R14: 0000000000000000 R15: 0000000000000000
 arch_cpu_idle+0xa/0x10 arch/x86/kernel/process.c:690
 default_idle_call+0x84/0xb0 kernel/sched/idle.c:94
 cpuidle_idle_call kernel/sched/idle.c:154 [inline]
 do_idle+0x3c8/0x6e0 kernel/sched/idle.c:269
 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:361
 rest_init+0x23b/0x371 init/main.c:451
 arch_call_rest_init+0xe/0x1b
 start_kernel+0x904/0x943 init/main.c:784
 x86_64_start_reservations+0x29/0x2b arch/x86/kernel/head64.c:490
 x86_64_start_kernel+0x77/0x7b arch/x86/kernel/head64.c:471
 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:242

The buggy address belongs to the page:
page:ffffea00067c82c0 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0
raw: 057ffe0000000000 ffffea00067c82c8 ffffea00067c82c8 0000000000000000
raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff88819f20b880: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ffff88819f20b900: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
>ffff88819f20b980: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
                                           ^
 ffff88819f20ba00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ffff88819f20ba80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff

Fixes: 61e84623ace3 ("net: centralize net_device min/max MTU checking")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  2 ++
 net/core/dev.c            | 29 +++++++++++++++++++----------
 net/core/rtnetlink.c      | 13 +++++++++++--
 3 files changed, 32 insertions(+), 12 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ae5e260911e2..cac56fb59af8 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3698,6 +3698,8 @@ int dev_set_alias(struct net_device *, const char *, size_t);
 int dev_get_alias(const struct net_device *, char *, size_t);
 int dev_change_net_namespace(struct net_device *, struct net *, const char *);
 int __dev_set_mtu(struct net_device *, int);
+int dev_validate_mtu(struct net_device *dev, int mtu,
+		     struct netlink_ext_ack *extack);
 int dev_set_mtu_ext(struct net_device *dev, int mtu,
 		    struct netlink_ext_ack *extack);
 int dev_set_mtu(struct net_device *, int);
diff --git a/net/core/dev.c b/net/core/dev.c
index cca03914108a..81befd0c2510 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8196,6 +8196,22 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu)
 }
 EXPORT_SYMBOL(__dev_set_mtu);
 
+int dev_validate_mtu(struct net_device *dev, int new_mtu,
+		     struct netlink_ext_ack *extack)
+{
+	/* MTU must be positive, and in range */
+	if (new_mtu < 0 || new_mtu < dev->min_mtu) {
+		NL_SET_ERR_MSG(extack, "mtu less than device minimum");
+		return -EINVAL;
+	}
+
+	if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) {
+		NL_SET_ERR_MSG(extack, "mtu greater than device maximum");
+		return -EINVAL;
+	}
+	return 0;
+}
+
 /**
  *	dev_set_mtu_ext - Change maximum transfer unit
  *	@dev: device
@@ -8212,16 +8228,9 @@ int dev_set_mtu_ext(struct net_device *dev, int new_mtu,
 	if (new_mtu == dev->mtu)
 		return 0;
 
-	/* MTU must be positive, and in range */
-	if (new_mtu < 0 || new_mtu < dev->min_mtu) {
-		NL_SET_ERR_MSG(extack, "mtu less than device minimum");
-		return -EINVAL;
-	}
-
-	if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) {
-		NL_SET_ERR_MSG(extack, "mtu greater than device maximum");
-		return -EINVAL;
-	}
+	err = dev_validate_mtu(dev, new_mtu, extack);
+	if (err)
+		return err;
 
 	if (!netif_device_present(dev))
 		return -ENODEV;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 02916f43bf63..d9001b5c48eb 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3048,8 +3048,17 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname,
 	dev->rtnl_link_ops = ops;
 	dev->rtnl_link_state = RTNL_LINK_INITIALIZING;
 
-	if (tb[IFLA_MTU])
-		dev->mtu = nla_get_u32(tb[IFLA_MTU]);
+	if (tb[IFLA_MTU]) {
+		u32 mtu = nla_get_u32(tb[IFLA_MTU]);
+		int err;
+
+		err = dev_validate_mtu(dev, mtu, extack);
+		if (err) {
+			free_netdev(dev);
+			return ERR_PTR(err);
+		}
+		dev->mtu = mtu;
+	}
 	if (tb[IFLA_ADDRESS]) {
 		memcpy(dev->dev_addr, nla_data(tb[IFLA_ADDRESS]),
 				nla_len(tb[IFLA_ADDRESS]));
-- 
cgit 


From 940ba14986657a50c15f694efca1beba31fa568f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 21 Jan 2020 23:17:14 -0800
Subject: gtp: make sure only SOCK_DGRAM UDP sockets are accepted

A malicious user could use RAW sockets and fool
GTP using them as standard SOCK_DGRAM UDP sockets.

BUG: KMSAN: uninit-value in udp_tunnel_encap_enable include/net/udp_tunnel.h:174 [inline]
BUG: KMSAN: uninit-value in setup_udp_tunnel_sock+0x45e/0x6f0 net/ipv4/udp_tunnel.c:85
CPU: 0 PID: 11262 Comm: syz-executor613 Not tainted 5.5.0-rc5-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x220 lib/dump_stack.c:118
 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:118
 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:215
 udp_tunnel_encap_enable include/net/udp_tunnel.h:174 [inline]
 setup_udp_tunnel_sock+0x45e/0x6f0 net/ipv4/udp_tunnel.c:85
 gtp_encap_enable_socket+0x37f/0x5a0 drivers/net/gtp.c:827
 gtp_encap_enable drivers/net/gtp.c:844 [inline]
 gtp_newlink+0xfb/0x1e50 drivers/net/gtp.c:666
 __rtnl_newlink net/core/rtnetlink.c:3305 [inline]
 rtnl_newlink+0x2973/0x3920 net/core/rtnetlink.c:3363
 rtnetlink_rcv_msg+0x1153/0x1570 net/core/rtnetlink.c:5424
 netlink_rcv_skb+0x451/0x650 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:5442
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0xf9e/0x1100 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x1248/0x14d0 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:639 [inline]
 sock_sendmsg net/socket.c:659 [inline]
 ____sys_sendmsg+0x12b6/0x1350 net/socket.c:2330
 ___sys_sendmsg net/socket.c:2384 [inline]
 __sys_sendmsg+0x451/0x5f0 net/socket.c:2417
 __do_sys_sendmsg net/socket.c:2426 [inline]
 __se_sys_sendmsg+0x97/0xb0 net/socket.c:2424
 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2424
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x441359
Code: e8 ac e8 ff ff 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb 08 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007fff1cd0ac28 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000441359
RDX: 0000000000000000 RSI: 0000000020000100 RDI: 0000000000000003
RBP: 00000000006cb018 R08: 00000000004002c8 R09: 00000000004002c8
R10: 00000000004002c8 R11: 0000000000000246 R12: 00000000004020d0
R13: 0000000000402160 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at:
 kmsan_save_stack_with_flags+0x3c/0x90 mm/kmsan/kmsan.c:144
 kmsan_internal_alloc_meta_for_pages mm/kmsan/kmsan_shadow.c:307 [inline]
 kmsan_alloc_page+0x12a/0x310 mm/kmsan/kmsan_shadow.c:336
 __alloc_pages_nodemask+0x57f2/0x5f60 mm/page_alloc.c:4800
 alloc_pages_current+0x67d/0x990 mm/mempolicy.c:2207
 alloc_pages include/linux/gfp.h:534 [inline]
 alloc_slab_page+0x111/0x12f0 mm/slub.c:1511
 allocate_slab mm/slub.c:1656 [inline]
 new_slab+0x2bc/0x1130 mm/slub.c:1722
 new_slab_objects mm/slub.c:2473 [inline]
 ___slab_alloc+0x1533/0x1f30 mm/slub.c:2624
 __slab_alloc mm/slub.c:2664 [inline]
 slab_alloc_node mm/slub.c:2738 [inline]
 slab_alloc mm/slub.c:2783 [inline]
 kmem_cache_alloc+0xb23/0xd70 mm/slub.c:2788
 sk_prot_alloc+0xf2/0x620 net/core/sock.c:1597
 sk_alloc+0xf0/0xbe0 net/core/sock.c:1657
 inet_create+0x7c7/0x1370 net/ipv4/af_inet.c:321
 __sock_create+0x8eb/0xf00 net/socket.c:1420
 sock_create net/socket.c:1471 [inline]
 __sys_socket+0x1a1/0x600 net/socket.c:1513
 __do_sys_socket net/socket.c:1522 [inline]
 __se_sys_socket+0x8d/0xb0 net/socket.c:1520
 __x64_sys_socket+0x4a/0x70 net/socket.c:1520
 do_syscall_64+0xb8/0x160 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Pablo Neira <pablo@netfilter.org>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/gtp.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index f6222ada6818..9b3ba98726d7 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -804,19 +804,21 @@ static struct sock *gtp_encap_enable_socket(int fd, int type,
 		return NULL;
 	}
 
-	if (sock->sk->sk_protocol != IPPROTO_UDP) {
+	sk = sock->sk;
+	if (sk->sk_protocol != IPPROTO_UDP ||
+	    sk->sk_type != SOCK_DGRAM ||
+	    (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)) {
 		pr_debug("socket fd=%d not UDP\n", fd);
 		sk = ERR_PTR(-EINVAL);
 		goto out_sock;
 	}
 
-	lock_sock(sock->sk);
-	if (sock->sk->sk_user_data) {
+	lock_sock(sk);
+	if (sk->sk_user_data) {
 		sk = ERR_PTR(-EBUSY);
 		goto out_rel_sock;
 	}
 
-	sk = sock->sk;
 	sock_hold(sk);
 
 	tuncfg.sk_user_data = gtp;
-- 
cgit 


From a39142728d0e60a76b67db3cbc187d61fde7b46d Mon Sep 17 00:00:00 2001
From: Hayes Wang <hayeswang@realtek.com>
Date: Wed, 22 Jan 2020 16:02:05 +0800
Subject: r8152: fix runtime resume for linking change

Fix the runtime resume doesn't work normally for linking change.

1. Reset the settings and status of runtime suspend.
2. Sync the linking status.
3. Poll the linking change.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 031cb8fff909..115559707683 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -365,8 +365,10 @@
 #define DEBUG_LTSSM		0x0082
 
 /* PLA_EXTRA_STATUS */
+#define CUR_LINK_OK		BIT(15)
 #define U3P3_CHECK_EN		BIT(7)	/* RTL_VER_05 only */
 #define LINK_CHANGE_FLAG	BIT(8)
+#define POLL_LINK_CHG		BIT(0)
 
 /* USB_USB2PHY */
 #define USB2PHY_SUSPEND		0x0001
@@ -5387,6 +5389,16 @@ static void r8153_init(struct r8152 *tp)
 		else
 			ocp_data |= DYNAMIC_BURST;
 		ocp_write_byte(tp, MCU_TYPE_USB, USB_CSR_DUMMY1, ocp_data);
+
+		r8153_queue_wake(tp, false);
+
+		ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_EXTRA_STATUS);
+		if (rtl8152_get_speed(tp) & LINK_STATUS)
+			ocp_data |= CUR_LINK_OK;
+		else
+			ocp_data &= ~CUR_LINK_OK;
+		ocp_data |= POLL_LINK_CHG;
+		ocp_write_word(tp, MCU_TYPE_PLA, PLA_EXTRA_STATUS, ocp_data);
 	}
 
 	ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, USB_CSR_DUMMY2);
@@ -5416,6 +5428,7 @@ static void r8153_init(struct r8152 *tp)
 	ocp_write_word(tp, MCU_TYPE_USB, USB_CONNECT_TIMER, 0x0001);
 
 	r8153_power_cut_en(tp, false);
+	rtl_runtime_suspend_enable(tp, false);
 	r8153_u1u2en(tp, true);
 	r8153_mac_clk_spd(tp, false);
 	usb_enable_lpm(tp->udev);
@@ -5484,6 +5497,14 @@ static void r8153b_init(struct r8152 *tp)
 	r8153b_ups_en(tp, false);
 	r8153_queue_wake(tp, false);
 	rtl_runtime_suspend_enable(tp, false);
+
+	ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_EXTRA_STATUS);
+	if (rtl8152_get_speed(tp) & LINK_STATUS)
+		ocp_data |= CUR_LINK_OK;
+	else
+		ocp_data &= ~CUR_LINK_OK;
+	ocp_data |= POLL_LINK_CHG;
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_EXTRA_STATUS, ocp_data);
 	r8153b_u1u2en(tp, true);
 	usb_enable_lpm(tp->udev);
 
-- 
cgit 


From f99cd20eda12b1920ffc284a736437c016b3a5a2 Mon Sep 17 00:00:00 2001
From: Hayes Wang <hayeswang@realtek.com>
Date: Wed, 22 Jan 2020 16:02:06 +0800
Subject: r8152: reset flow control patch when linking on for RTL8153B

When linking ON, the patch of flow control has to be reset. This
makes sure the patch works normally.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 115559707683..504db2348a3e 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -2865,6 +2865,17 @@ static int rtl8153_enable(struct r8152 *tp)
 	r8153_set_rx_early_timeout(tp);
 	r8153_set_rx_early_size(tp);
 
+	if (tp->version == RTL_VER_09) {
+		u32 ocp_data;
+
+		ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_FW_TASK);
+		ocp_data &= ~FC_PATCH_TASK;
+		ocp_write_word(tp, MCU_TYPE_USB, USB_FW_TASK, ocp_data);
+		usleep_range(1000, 2000);
+		ocp_data |= FC_PATCH_TASK;
+		ocp_write_word(tp, MCU_TYPE_USB, USB_FW_TASK, ocp_data);
+	}
+
 	return rtl_enable(tp);
 }
 
-- 
cgit 


From 9583a3638dc07cc1878f41265e85ed497f72efcb Mon Sep 17 00:00:00 2001
From: Hayes Wang <hayeswang@realtek.com>
Date: Wed, 22 Jan 2020 16:02:07 +0800
Subject: r8152: get default setting of WOL before initializing

Initailization would reset runtime suspend by tp->saved_wolopts, so
the tp->saved_wolopts should be set before initializing.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 504db2348a3e..c3217a5c2fe1 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -6739,6 +6739,11 @@ static int rtl8152_probe(struct usb_interface *intf,
 
 	intf->needs_remote_wakeup = 1;
 
+	if (!rtl_can_wakeup(tp))
+		__rtl_set_wol(tp, 0);
+	else
+		tp->saved_wolopts = __rtl_get_wol(tp);
+
 	tp->rtl_ops.init(tp);
 #if IS_BUILTIN(CONFIG_USB_RTL8152)
 	/* Retry in case request_firmware() is not ready yet. */
@@ -6756,10 +6761,6 @@ static int rtl8152_probe(struct usb_interface *intf,
 		goto out1;
 	}
 
-	if (!rtl_can_wakeup(tp))
-		__rtl_set_wol(tp, 0);
-
-	tp->saved_wolopts = __rtl_get_wol(tp);
 	if (tp->saved_wolopts)
 		device_set_wakeup_enable(&udev->dev, true);
 	else
-- 
cgit 


From 809a7fc6593f288d6f820ef6cc57b9d69b5f9474 Mon Sep 17 00:00:00 2001
From: Hayes Wang <hayeswang@realtek.com>
Date: Wed, 22 Jan 2020 16:02:08 +0800
Subject: r8152: disable U2P3 for RTL8153B

Enable U2P3 may miss zero packet for bulk-in.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index c3217a5c2fe1..bc6b2f8aaa7e 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -3389,7 +3389,6 @@ static void rtl8153b_runtime_enable(struct r8152 *tp, bool enable)
 		r8153b_ups_en(tp, false);
 		r8153_queue_wake(tp, false);
 		rtl_runtime_suspend_enable(tp, false);
-		r8153_u2p3en(tp, true);
 		r8153b_u1u2en(tp, true);
 	}
 }
@@ -4688,7 +4687,6 @@ static void r8153b_hw_phy_cfg(struct r8152 *tp)
 
 	r8153_aldps_en(tp, true);
 	r8152b_enable_fc(tp);
-	r8153_u2p3en(tp, true);
 
 	set_bit(PHY_RESET, &tp->flags);
 }
@@ -5018,7 +5016,6 @@ static void rtl8153b_up(struct r8152 *tp)
 	ocp_write_dword(tp, MCU_TYPE_USB, USB_RX_BUF_TH, RX_THR_B);
 
 	r8153_aldps_en(tp, true);
-	r8153_u2p3en(tp, true);
 	r8153b_u1u2en(tp, true);
 }
 
-- 
cgit 


From 08997b5eec08a2c29367f19a74abdea54b299406 Mon Sep 17 00:00:00 2001
From: Hayes Wang <hayeswang@realtek.com>
Date: Wed, 22 Jan 2020 16:02:09 +0800
Subject: r8152: Disable PLA MCU clock speed down

PLA MCU clock speed down could only be enabled when tx/rx are disabled.
Otherwise, the packet loss may occur.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index bc6b2f8aaa7e..1fb85c79bd33 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -324,6 +324,7 @@
 #define MAC_CLK_SPDWN_EN	BIT(15)
 
 /* PLA_MAC_PWR_CTRL3 */
+#define PLA_MCU_SPDWN_EN	BIT(14)
 #define PKT_AVAIL_SPDWN_EN	0x0100
 #define SUSPEND_SPDWN_EN	0x0004
 #define U1U2_SPDWN_EN		0x0002
@@ -5005,6 +5006,8 @@ static void rtl8153_down(struct r8152 *tp)
 
 static void rtl8153b_up(struct r8152 *tp)
 {
+	u32 ocp_data;
+
 	if (test_bit(RTL8152_UNPLUG, &tp->flags))
 		return;
 
@@ -5015,17 +5018,27 @@ static void rtl8153b_up(struct r8152 *tp)
 	r8153_first_init(tp);
 	ocp_write_dword(tp, MCU_TYPE_USB, USB_RX_BUF_TH, RX_THR_B);
 
+	ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3);
+	ocp_data &= ~PLA_MCU_SPDWN_EN;
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, ocp_data);
+
 	r8153_aldps_en(tp, true);
 	r8153b_u1u2en(tp, true);
 }
 
 static void rtl8153b_down(struct r8152 *tp)
 {
+	u32 ocp_data;
+
 	if (test_bit(RTL8152_UNPLUG, &tp->flags)) {
 		rtl_drop_queued_tx(tp);
 		return;
 	}
 
+	ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3);
+	ocp_data |= PLA_MCU_SPDWN_EN;
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, ocp_data);
+
 	r8153b_u1u2en(tp, false);
 	r8153_u2p3en(tp, false);
 	r8153b_power_cut_en(tp, false);
@@ -5521,6 +5534,10 @@ static void r8153b_init(struct r8152 *tp)
 	ocp_data |= MAC_CLK_SPDWN_EN;
 	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL2, ocp_data);
 
+	ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3);
+	ocp_data &= ~PLA_MCU_SPDWN_EN;
+	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, ocp_data);
+
 	set_bit(GREEN_ETHERNET, &tp->flags);
 
 	/* rx aggregation */
-- 
cgit 


From d7f1b59655efb5a285d227c8f9853a98eab5c2fd Mon Sep 17 00:00:00 2001
From: Hayes Wang <hayeswang@realtek.com>
Date: Wed, 22 Jan 2020 16:02:10 +0800
Subject: r8152: disable test IO for RTL8153B

For RTL8153B with QFN32, disable test IO. Otherwise, it may cause
abnormal behavior for the device randomly.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 1fb85c79bd33..7efeddad1fc8 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -312,6 +312,7 @@
 /* PLA_PHY_PWR */
 #define TX_10M_IDLE_EN		0x0080
 #define PFM_PWM_SWITCH		0x0040
+#define TEST_IO_OFF		BIT(4)
 
 /* PLA_MAC_PWR_CTRL */
 #define D3_CLK_GATED_EN		0x00004000
@@ -5538,6 +5539,15 @@ static void r8153b_init(struct r8152 *tp)
 	ocp_data &= ~PLA_MCU_SPDWN_EN;
 	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, ocp_data);
 
+	if (tp->version == RTL_VER_09) {
+		/* Disable Test IO for 32QFN */
+		if (ocp_read_byte(tp, MCU_TYPE_PLA, 0xdc00) & BIT(5)) {
+			ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_PHY_PWR);
+			ocp_data |= TEST_IO_OFF;
+			ocp_write_word(tp, MCU_TYPE_PLA, PLA_PHY_PWR, ocp_data);
+		}
+	}
+
 	set_bit(GREEN_ETHERNET, &tp->flags);
 
 	/* rx aggregation */
-- 
cgit 


From a0246dafe684a6d5ad31ccd59af0334ccf0cc7b2 Mon Sep 17 00:00:00 2001
From: Hayes Wang <hayeswang@realtek.com>
Date: Wed, 22 Jan 2020 16:02:11 +0800
Subject: r8152: don't enable U1U2 with USB_SPEED_HIGH for RTL8153B

For certain platforms, it causes USB reset periodically.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 7efeddad1fc8..b1a00f29455b 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -3391,7 +3391,8 @@ static void rtl8153b_runtime_enable(struct r8152 *tp, bool enable)
 		r8153b_ups_en(tp, false);
 		r8153_queue_wake(tp, false);
 		rtl_runtime_suspend_enable(tp, false);
-		r8153b_u1u2en(tp, true);
+		if (tp->udev->speed != USB_SPEED_HIGH)
+			r8153b_u1u2en(tp, true);
 	}
 }
 
@@ -5024,7 +5025,9 @@ static void rtl8153b_up(struct r8152 *tp)
 	ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, ocp_data);
 
 	r8153_aldps_en(tp, true);
-	r8153b_u1u2en(tp, true);
+
+	if (tp->udev->speed != USB_SPEED_HIGH)
+		r8153b_u1u2en(tp, true);
 }
 
 static void rtl8153b_down(struct r8152 *tp)
@@ -5527,7 +5530,9 @@ static void r8153b_init(struct r8152 *tp)
 		ocp_data &= ~CUR_LINK_OK;
 	ocp_data |= POLL_LINK_CHG;
 	ocp_write_word(tp, MCU_TYPE_PLA, PLA_EXTRA_STATUS, ocp_data);
-	r8153b_u1u2en(tp, true);
+
+	if (tp->udev->speed != USB_SPEED_HIGH)
+		r8153b_u1u2en(tp, true);
 	usb_enable_lpm(tp->udev);
 
 	/* MAC clock speed down */
-- 
cgit 


From 19813162895a696c5814d76e5f8fb6203d70f6e0 Mon Sep 17 00:00:00 2001
From: Hayes Wang <hayeswang@realtek.com>
Date: Wed, 22 Jan 2020 16:02:12 +0800
Subject: r8152: avoid the MCU to clear the lanwake

Avoid the MCU to clear the lanwake after suspending. It may cause the
WOL fail. Disable LANWAKE_CLR_EN before suspending. Besides,enable it
and reset the lanwake status when resuming or initializing.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index b1a00f29455b..c037fc7adcea 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -68,6 +68,7 @@
 #define PLA_LED_FEATURE		0xdd92
 #define PLA_PHYAR		0xde00
 #define PLA_BOOT_CTRL		0xe004
+#define PLA_LWAKE_CTRL_REG	0xe007
 #define PLA_GPHY_INTR_IMR	0xe022
 #define PLA_EEE_CR		0xe040
 #define PLA_EEEP_CR		0xe080
@@ -95,6 +96,7 @@
 #define PLA_TALLYCNT		0xe890
 #define PLA_SFF_STS_7		0xe8de
 #define PLA_PHYSTATUS		0xe908
+#define PLA_CONFIG6		0xe90a /* CONFIG6 */
 #define PLA_BP_BA		0xfc26
 #define PLA_BP_0		0xfc28
 #define PLA_BP_1		0xfc2a
@@ -300,6 +302,9 @@
 #define LINK_ON_WAKE_EN		0x0010
 #define LINK_OFF_WAKE_EN	0x0008
 
+/* PLA_CONFIG6 */
+#define LANWAKE_CLR_EN		BIT(0)
+
 /* PLA_CONFIG5 */
 #define BWF_EN			0x0040
 #define MWF_EN			0x0020
@@ -356,6 +361,9 @@
 /* PLA_BOOT_CTRL */
 #define AUTOLOAD_DONE		0x0002
 
+/* PLA_LWAKE_CTRL_REG */
+#define LANWAKE_PIN		BIT(7)
+
 /* PLA_SUSPEND_FLAG */
 #define LINK_CHG_EVENT		BIT(0)
 
@@ -4968,6 +4976,8 @@ static void rtl8152_down(struct r8152 *tp)
 
 static void rtl8153_up(struct r8152 *tp)
 {
+	u32 ocp_data;
+
 	if (test_bit(RTL8152_UNPLUG, &tp->flags))
 		return;
 
@@ -4975,6 +4985,15 @@ static void rtl8153_up(struct r8152 *tp)
 	r8153_u2p3en(tp, false);
 	r8153_aldps_en(tp, false);
 	r8153_first_init(tp);
+
+	ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6);
+	ocp_data |= LANWAKE_CLR_EN;
+	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6, ocp_data);
+
+	ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_LWAKE_CTRL_REG);
+	ocp_data &= ~LANWAKE_PIN;
+	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_LWAKE_CTRL_REG, ocp_data);
+
 	r8153_aldps_en(tp, true);
 
 	switch (tp->version) {
@@ -4993,11 +5012,17 @@ static void rtl8153_up(struct r8152 *tp)
 
 static void rtl8153_down(struct r8152 *tp)
 {
+	u32 ocp_data;
+
 	if (test_bit(RTL8152_UNPLUG, &tp->flags)) {
 		rtl_drop_queued_tx(tp);
 		return;
 	}
 
+	ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6);
+	ocp_data &= ~LANWAKE_CLR_EN;
+	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6, ocp_data);
+
 	r8153_u1u2en(tp, false);
 	r8153_u2p3en(tp, false);
 	r8153_power_cut_en(tp, false);
@@ -5458,6 +5483,14 @@ static void r8153_init(struct r8152 *tp)
 	r8153_mac_clk_spd(tp, false);
 	usb_enable_lpm(tp->udev);
 
+	ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6);
+	ocp_data |= LANWAKE_CLR_EN;
+	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6, ocp_data);
+
+	ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_LWAKE_CTRL_REG);
+	ocp_data &= ~LANWAKE_PIN;
+	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_LWAKE_CTRL_REG, ocp_data);
+
 	/* rx aggregation */
 	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_USB_CTRL);
 	ocp_data &= ~(RX_AGG_DISABLE | RX_ZERO_EN);
-- 
cgit 


From aa475d935272481c9ffb1ae54eeca5c1819fbe1a Mon Sep 17 00:00:00 2001
From: Hayes Wang <hayeswang@realtek.com>
Date: Wed, 22 Jan 2020 16:02:13 +0800
Subject: r8152: disable DelayPhyPwrChg

When enabling this, the device would wait an internal signal which
wouldn't be triggered. Then, the device couldn't enter P3 mode, so
the power consumption is increased.

Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index c037fc7adcea..3f425f974d03 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -31,7 +31,7 @@
 #define NETNEXT_VERSION		"11"
 
 /* Information for net */
-#define NET_VERSION		"10"
+#define NET_VERSION		"11"
 
 #define DRIVER_VERSION		"v1." NETNEXT_VERSION "." NET_VERSION
 #define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
@@ -109,6 +109,7 @@
 #define PLA_BP_EN		0xfc38
 
 #define USB_USB2PHY		0xb41e
+#define USB_SSPHYLINK1		0xb426
 #define USB_SSPHYLINK2		0xb428
 #define USB_U2P3_CTRL		0xb460
 #define USB_CSR_DUMMY1		0xb464
@@ -384,6 +385,9 @@
 #define USB2PHY_SUSPEND		0x0001
 #define USB2PHY_L1		0x0002
 
+/* USB_SSPHYLINK1 */
+#define DELAY_PHY_PWR_CHG	BIT(1)
+
 /* USB_SSPHYLINK2 */
 #define pwd_dn_scale_mask	0x3ffe
 #define pwd_dn_scale(x)		((x) << 1)
@@ -4994,6 +4998,10 @@ static void rtl8153_up(struct r8152 *tp)
 	ocp_data &= ~LANWAKE_PIN;
 	ocp_write_byte(tp, MCU_TYPE_PLA, PLA_LWAKE_CTRL_REG, ocp_data);
 
+	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_SSPHYLINK1);
+	ocp_data &= ~DELAY_PHY_PWR_CHG;
+	ocp_write_word(tp, MCU_TYPE_USB, USB_SSPHYLINK1, ocp_data);
+
 	r8153_aldps_en(tp, true);
 
 	switch (tp->version) {
-- 
cgit 


From 971de2e572118c1128bff295341e37b6c8b8f108 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 22 Jan 2020 20:09:52 +0200
Subject: mlxsw: spectrum_acl: Fix use-after-free during reload

During reload (or module unload), the router block is de-initialized.
Among other things, this results in the removal of a default multicast
route from each active virtual router (VRF). These default routes are
configured during initialization to trap packets to the CPU. In
Spectrum-2, unlike Spectrum-1, multicast routes are implemented using
ACL rules.

Since the router block is de-initialized before the ACL block, it is
possible that the ACL rules corresponding to the default routes are
deleted while being accessed by the ACL delayed work that queries rules'
activity from the device. This can result in a rare use-after-free [1].

Fix this by protecting the rules list accessed by the delayed work with
a lock. We cannot use a spinlock as the activity read operation is
blocking.

[1]
[  123.331662] ==================================================================
[  123.339920] BUG: KASAN: use-after-free in mlxsw_sp_acl_rule_activity_update_work+0x330/0x3b0
[  123.349381] Read of size 8 at addr ffff8881f3bb4520 by task kworker/0:2/78
[  123.357080]
[  123.358773] CPU: 0 PID: 78 Comm: kworker/0:2 Not tainted 5.5.0-rc5-custom-33108-gf5df95d3ef41 #2209
[  123.368898] Hardware name: Mellanox Technologies Ltd. MSN3700C/VMOD0008, BIOS 5.11 10/10/2018
[  123.378456] Workqueue: mlxsw_core mlxsw_sp_acl_rule_activity_update_work
[  123.385970] Call Trace:
[  123.388734]  dump_stack+0xc6/0x11e
[  123.392568]  print_address_description.constprop.4+0x21/0x340
[  123.403236]  __kasan_report.cold.8+0x76/0xb1
[  123.414884]  kasan_report+0xe/0x20
[  123.418716]  mlxsw_sp_acl_rule_activity_update_work+0x330/0x3b0
[  123.444034]  process_one_work+0xb06/0x19a0
[  123.453731]  worker_thread+0x91/0xe90
[  123.467348]  kthread+0x348/0x410
[  123.476847]  ret_from_fork+0x24/0x30
[  123.480863]
[  123.482545] Allocated by task 73:
[  123.486273]  save_stack+0x19/0x80
[  123.490000]  __kasan_kmalloc.constprop.6+0xc1/0xd0
[  123.495379]  mlxsw_sp_acl_rule_create+0xa7/0x230
[  123.500566]  mlxsw_sp2_mr_tcam_route_create+0xf6/0x3e0
[  123.506334]  mlxsw_sp_mr_tcam_route_create+0x5b4/0x820
[  123.512102]  mlxsw_sp_mr_table_create+0x3b5/0x690
[  123.517389]  mlxsw_sp_vr_get+0x289/0x4d0
[  123.521797]  mlxsw_sp_fib_node_get+0xa2/0x990
[  123.526692]  mlxsw_sp_router_fib4_event_work+0x54c/0x2d60
[  123.532752]  process_one_work+0xb06/0x19a0
[  123.537352]  worker_thread+0x91/0xe90
[  123.541471]  kthread+0x348/0x410
[  123.545103]  ret_from_fork+0x24/0x30
[  123.549113]
[  123.550795] Freed by task 518:
[  123.554231]  save_stack+0x19/0x80
[  123.557958]  __kasan_slab_free+0x125/0x170
[  123.562556]  kfree+0xd7/0x3a0
[  123.565895]  mlxsw_sp_acl_rule_destroy+0x63/0xd0
[  123.571081]  mlxsw_sp2_mr_tcam_route_destroy+0xd5/0x130
[  123.576946]  mlxsw_sp_mr_tcam_route_destroy+0xba/0x260
[  123.582714]  mlxsw_sp_mr_table_destroy+0x1ab/0x290
[  123.588091]  mlxsw_sp_vr_put+0x1db/0x350
[  123.592496]  mlxsw_sp_fib_node_put+0x298/0x4c0
[  123.597486]  mlxsw_sp_vr_fib_flush+0x15b/0x360
[  123.602476]  mlxsw_sp_router_fib_flush+0xba/0x470
[  123.607756]  mlxsw_sp_vrs_fini+0xaa/0x120
[  123.612260]  mlxsw_sp_router_fini+0x137/0x384
[  123.617152]  mlxsw_sp_fini+0x30a/0x4a0
[  123.621374]  mlxsw_core_bus_device_unregister+0x159/0x600
[  123.627435]  mlxsw_devlink_core_bus_device_reload_down+0x7e/0xb0
[  123.634176]  devlink_reload+0xb4/0x380
[  123.638391]  devlink_nl_cmd_reload+0x610/0x700
[  123.643382]  genl_rcv_msg+0x6a8/0xdc0
[  123.647497]  netlink_rcv_skb+0x134/0x3a0
[  123.651904]  genl_rcv+0x29/0x40
[  123.655436]  netlink_unicast+0x4d4/0x700
[  123.659843]  netlink_sendmsg+0x7c0/0xc70
[  123.664251]  __sys_sendto+0x265/0x3c0
[  123.668367]  __x64_sys_sendto+0xe2/0x1b0
[  123.672773]  do_syscall_64+0xa0/0x530
[  123.676892]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  123.682552]
[  123.684238] The buggy address belongs to the object at ffff8881f3bb4500
[  123.684238]  which belongs to the cache kmalloc-128 of size 128
[  123.698261] The buggy address is located 32 bytes inside of
[  123.698261]  128-byte region [ffff8881f3bb4500, ffff8881f3bb4580)
[  123.711303] The buggy address belongs to the page:
[  123.716682] page:ffffea0007ceed00 refcount:1 mapcount:0 mapping:ffff888236403500 index:0x0
[  123.725958] raw: 0200000000000200 dead000000000100 dead000000000122 ffff888236403500
[  123.734646] raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000
[  123.743315] page dumped because: kasan: bad access detected
[  123.749562]
[  123.751241] Memory state around the buggy address:
[  123.756620]  ffff8881f3bb4400: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[  123.764716]  ffff8881f3bb4480: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  123.772812] >ffff8881f3bb4500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  123.780904]                                ^
[  123.785697]  ffff8881f3bb4580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  123.793793]  ffff8881f3bb4600: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[  123.801883] ==================================================================

Fixes: cf7221a4f5a5 ("mlxsw: spectrum_router: Add Multicast routing support for Spectrum-2")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 150b3a144b83..3d3cca596116 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -8,6 +8,7 @@
 #include <linux/string.h>
 #include <linux/rhashtable.h>
 #include <linux/netdevice.h>
+#include <linux/mutex.h>
 #include <net/net_namespace.h>
 #include <net/tc_act/tc_vlan.h>
 
@@ -25,6 +26,7 @@ struct mlxsw_sp_acl {
 	struct mlxsw_sp_fid *dummy_fid;
 	struct rhashtable ruleset_ht;
 	struct list_head rules;
+	struct mutex rules_lock; /* Protects rules list */
 	struct {
 		struct delayed_work dw;
 		unsigned long interval;	/* ms */
@@ -701,7 +703,9 @@ int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp,
 			goto err_ruleset_block_bind;
 	}
 
+	mutex_lock(&mlxsw_sp->acl->rules_lock);
 	list_add_tail(&rule->list, &mlxsw_sp->acl->rules);
+	mutex_unlock(&mlxsw_sp->acl->rules_lock);
 	block->rule_count++;
 	block->egress_blocker_rule_count += rule->rulei->egress_bind_blocker;
 	return 0;
@@ -723,7 +727,9 @@ void mlxsw_sp_acl_rule_del(struct mlxsw_sp *mlxsw_sp,
 
 	block->egress_blocker_rule_count -= rule->rulei->egress_bind_blocker;
 	ruleset->ht_key.block->rule_count--;
+	mutex_lock(&mlxsw_sp->acl->rules_lock);
 	list_del(&rule->list);
+	mutex_unlock(&mlxsw_sp->acl->rules_lock);
 	if (!ruleset->ht_key.chain_index &&
 	    mlxsw_sp_acl_ruleset_is_singular(ruleset))
 		mlxsw_sp_acl_ruleset_block_unbind(mlxsw_sp, ruleset,
@@ -783,19 +789,18 @@ static int mlxsw_sp_acl_rules_activity_update(struct mlxsw_sp_acl *acl)
 	struct mlxsw_sp_acl_rule *rule;
 	int err;
 
-	/* Protect internal structures from changes */
-	rtnl_lock();
+	mutex_lock(&acl->rules_lock);
 	list_for_each_entry(rule, &acl->rules, list) {
 		err = mlxsw_sp_acl_rule_activity_update(acl->mlxsw_sp,
 							rule);
 		if (err)
 			goto err_rule_update;
 	}
-	rtnl_unlock();
+	mutex_unlock(&acl->rules_lock);
 	return 0;
 
 err_rule_update:
-	rtnl_unlock();
+	mutex_unlock(&acl->rules_lock);
 	return err;
 }
 
@@ -880,6 +885,7 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
 	acl->dummy_fid = fid;
 
 	INIT_LIST_HEAD(&acl->rules);
+	mutex_init(&acl->rules_lock);
 	err = mlxsw_sp_acl_tcam_init(mlxsw_sp, &acl->tcam);
 	if (err)
 		goto err_acl_ops_init;
@@ -892,6 +898,7 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
 	return 0;
 
 err_acl_ops_init:
+	mutex_destroy(&acl->rules_lock);
 	mlxsw_sp_fid_put(fid);
 err_fid_get:
 	rhashtable_destroy(&acl->ruleset_ht);
@@ -908,6 +915,7 @@ void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp)
 
 	cancel_delayed_work_sync(&mlxsw_sp->acl->rule_activity_update.dw);
 	mlxsw_sp_acl_tcam_fini(mlxsw_sp, &acl->tcam);
+	mutex_destroy(&acl->rules_lock);
 	WARN_ON(!list_empty(&acl->rules));
 	mlxsw_sp_fid_put(acl->dummy_fid);
 	rhashtable_destroy(&acl->ruleset_ht);
-- 
cgit 


From 1efba987c48629c0c64703bb4ea76ca1a3771d17 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 22 Jan 2020 09:07:35 -0800
Subject: tun: add mutex_unlock() call and napi.skb clearing in tun_get_user()

If both IFF_NAPI_FRAGS mode and XDP are enabled, and the XDP program
consumes the skb, we need to clear the napi.skb (or risk
a use-after-free) and release the mutex (or risk a deadlock)

WARNING: lock held when returning to user space!
5.5.0-rc6-syzkaller #0 Not tainted
------------------------------------------------
syz-executor.0/455 is leaving the kernel with locks still held!
1 lock held by syz-executor.0/455:
 #0: ffff888098f6e748 (&tfile->napi_mutex){+.+.}, at: tun_get_user+0x1604/0x3fc0 drivers/net/tun.c:1835

Fixes: 90e33d459407 ("tun: enable napi_gro_frags() for TUN/TAP driver")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Petar Penkov <ppenkov@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 683d371e6e82..35e884a8242d 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1936,6 +1936,10 @@ drop:
 			if (ret != XDP_PASS) {
 				rcu_read_unlock();
 				local_bh_enable();
+				if (frags) {
+					tfile->napi.skb = NULL;
+					mutex_unlock(&tfile->napi_mutex);
+				}
 				return total_len;
 			}
 		}
-- 
cgit 


From bb48eb9b12a95db9d679025927269d4adda6dbd1 Mon Sep 17 00:00:00 2001
From: Kristian Evensen <kristian.evensen@gmail.com>
Date: Thu, 23 Jan 2020 13:20:18 +0100
Subject: fou: Fix IPv6 netlink policy

When submitting v2 of "fou: Support binding FoU socket" (1713cb37bf67),
I accidentally sent the wrong version of the patch and one fix was
missing. In the initial version of the patch, as well as the version 2
that I submitted, I incorrectly used ".type" for the two V6-attributes.
The correct is to use ".len".

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Fixes: 1713cb37bf67 ("fou: Support binding FoU socket")
Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/fou.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 30fa771d382a..dcc79ff54b41 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -662,8 +662,8 @@ static const struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = {
 	[FOU_ATTR_REMCSUM_NOPARTIAL]	= { .type = NLA_FLAG, },
 	[FOU_ATTR_LOCAL_V4]		= { .type = NLA_U32, },
 	[FOU_ATTR_PEER_V4]		= { .type = NLA_U32, },
-	[FOU_ATTR_LOCAL_V6]		= { .type = sizeof(struct in6_addr), },
-	[FOU_ATTR_PEER_V6]		= { .type = sizeof(struct in6_addr), },
+	[FOU_ATTR_LOCAL_V6]		= { .len = sizeof(struct in6_addr), },
+	[FOU_ATTR_PEER_V6]		= { .len = sizeof(struct in6_addr), },
 	[FOU_ATTR_PEER_PORT]		= { .type = NLA_U16, },
 	[FOU_ATTR_IFINDEX]		= { .type = NLA_S32, },
 };
-- 
cgit 


From 22e984493a41bf8081f13d9ed84def3ca8cfd427 Mon Sep 17 00:00:00 2001
From: Manish Chopra <manishc@marvell.com>
Date: Wed, 22 Jan 2020 01:43:38 -0800
Subject: qlcnic: Fix CPU soft lockup while collecting firmware dump

Driver while collecting firmware dump takes longer time to
collect/process some of the firmware dump entries/memories.
Bigger capture masks makes it worse as it results in larger
amount of data being collected and results in CPU soft lockup.
Place cond_resched() in some of the driver flows that are
expectedly time consuming to relinquish the CPU to avoid CPU
soft lockup panic.

Signed-off-by: Shahed Shaikh <shshaikh@marvell.com>
Tested-by: Yonggen Xu <Yonggen.Xu@dell.com>
Signed-off-by: Manish Chopra <manishc@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c | 1 +
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c  | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
index a496390b8632..07f9067affc6 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
@@ -2043,6 +2043,7 @@ static void qlcnic_83xx_exec_template_cmd(struct qlcnic_adapter *p_dev,
 			break;
 		}
 		entry += p_hdr->size;
+		cond_resched();
 	}
 	p_dev->ahw->reset.seq_index = index;
 }
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c
index afa10a163da1..f34ae8c75bc5 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c
@@ -703,6 +703,7 @@ static u32 qlcnic_read_memory_test_agent(struct qlcnic_adapter *adapter,
 		addr += 16;
 		reg_read -= 16;
 		ret += 16;
+		cond_resched();
 	}
 out:
 	mutex_unlock(&adapter->ahw->mem_lock);
@@ -1383,6 +1384,7 @@ int qlcnic_dump_fw(struct qlcnic_adapter *adapter)
 		buf_offset += entry->hdr.cap_size;
 		entry_offset += entry->hdr.offset;
 		buffer = fw_dump->data + buf_offset;
+		cond_resched();
 	}
 
 	fw_dump->clr = 1;
-- 
cgit 


From 2934d2c67838ba442fbd0b0560ba641044a5ceba Mon Sep 17 00:00:00 2001
From: Madalin Bucur <madalin.bucur@oss.nxp.com>
Date: Wed, 22 Jan 2020 15:20:27 +0200
Subject: dt-bindings: net: add fsl,erratum-a011043

Add an entry for erratum A011043: the MDIO_CFG[MDIO_RD_ER]
bit may be falsely set when reading internal PCS registers.
MDIO reads to internal PCS registers may result in having
the MDIO_CFG[MDIO_RD_ER] bit set, even when there is no
error and read data (MDIO_DATA[MDIO_DATA]) is correct.
Software may get false read error when reading internal
PCS registers through MDIO. As a workaround, all internal
MDIO accesses should ignore the MDIO_CFG[MDIO_RD_ER] bit.

Signed-off-by: Madalin Bucur <madalin.bucur@oss.nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/fsl-fman.txt | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/fsl-fman.txt b/Documentation/devicetree/bindings/net/fsl-fman.txt
index 299c0dcd67db..250f8d8cdce4 100644
--- a/Documentation/devicetree/bindings/net/fsl-fman.txt
+++ b/Documentation/devicetree/bindings/net/fsl-fman.txt
@@ -403,6 +403,19 @@ PROPERTIES
 		The settings and programming routines for internal/external
 		MDIO are different. Must be included for internal MDIO.
 
+- fsl,erratum-a011043
+		Usage: optional
+		Value type: <boolean>
+		Definition: Indicates the presence of the A011043 erratum
+		describing that the MDIO_CFG[MDIO_RD_ER] bit may be falsely
+		set when reading internal PCS registers. MDIO reads to
+		internal PCS registers may result in having the
+		MDIO_CFG[MDIO_RD_ER] bit set, even when there is no error and
+		read data (MDIO_DATA[MDIO_DATA]) is correct.
+		Software may get false read error when reading internal
+		PCS registers through MDIO. As a workaround, all internal
+		MDIO accesses should ignore the MDIO_CFG[MDIO_RD_ER] bit.
+
 For internal PHY device on internal mdio bus, a PHY node should be created.
 See the definition of the PHY node in booting-without-of.txt for an
 example of how to define a PHY (Internal PHY has no interrupt line).
-- 
cgit 


From 73d527aef68f7644e59f22ce7f9ac75e7b533aea Mon Sep 17 00:00:00 2001
From: Madalin Bucur <madalin.bucur@oss.nxp.com>
Date: Wed, 22 Jan 2020 15:20:28 +0200
Subject: powerpc/fsl/dts: add fsl,erratum-a011043

Add fsl,erratum-a011043 to internal MDIO buses.
Software may get false read error when reading internal
PCS registers through MDIO. As a workaround, all internal
MDIO accesses should ignore the MDIO_CFG[MDIO_RD_ER] bit.

Signed-off-by: Madalin Bucur <madalin.bucur@oss.nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0-best-effort.dtsi | 1 +
 arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0.dtsi             | 1 +
 arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi | 1 +
 arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1.dtsi             | 1 +
 arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-0.dtsi              | 1 +
 arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-1.dtsi              | 1 +
 arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-2.dtsi              | 1 +
 arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-3.dtsi              | 1 +
 arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-4.dtsi              | 1 +
 arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-5.dtsi              | 1 +
 arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-0.dtsi             | 1 +
 arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-1.dtsi             | 1 +
 arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-0.dtsi              | 1 +
 arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-1.dtsi              | 1 +
 arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-2.dtsi              | 1 +
 arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-3.dtsi              | 1 +
 arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-4.dtsi              | 1 +
 arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-5.dtsi              | 1 +
 18 files changed, 18 insertions(+)

diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0-best-effort.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0-best-effort.dtsi
index e1a961f05dcd..baa0c503e741 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0-best-effort.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0-best-effort.dtsi
@@ -63,6 +63,7 @@ fman@400000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe1000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy0: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0.dtsi
index c288f3c6c637..93095600e808 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-0.dtsi
@@ -60,6 +60,7 @@ fman@400000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xf1000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy6: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi
index 94f3e7175012..ff4bd38f0645 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi
@@ -63,6 +63,7 @@ fman@400000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe3000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy1: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1.dtsi
index 94a76982d214..1fa38ed6f59e 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1.dtsi
@@ -60,6 +60,7 @@ fman@400000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xf3000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy7: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-0.dtsi
index b5ff5f71c6b8..a8cc9780c0c4 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-0.dtsi
@@ -59,6 +59,7 @@ fman@400000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe1000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy0: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-1.dtsi
index ee44182c6348..8b8bd70c9382 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-1.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-1.dtsi
@@ -59,6 +59,7 @@ fman@400000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe3000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy1: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-2.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-2.dtsi
index f05f0d775039..619c880b54d8 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-2.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-2.dtsi
@@ -59,6 +59,7 @@ fman@400000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe5000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy2: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-3.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-3.dtsi
index a9114ec51075..d7ebb73a400d 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-3.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-3.dtsi
@@ -59,6 +59,7 @@ fman@400000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe7000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy3: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-4.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-4.dtsi
index 44dd00ac7367..b151d696a069 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-4.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-4.dtsi
@@ -59,6 +59,7 @@ fman@400000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe9000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy4: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-5.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-5.dtsi
index 5b1b84b58602..adc0ae0013a3 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-5.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-1g-5.dtsi
@@ -59,6 +59,7 @@ fman@400000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xeb000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy5: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-0.dtsi
index 0e1daaef9e74..435047e0e250 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-0.dtsi
@@ -60,6 +60,7 @@ fman@500000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xf1000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy14: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-1.dtsi
index 68c5ef779266..c098657cca0a 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-1.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-10g-1.dtsi
@@ -60,6 +60,7 @@ fman@500000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xf3000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy15: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-0.dtsi
index 605363cc1117..9d06824815f3 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-0.dtsi
@@ -59,6 +59,7 @@ fman@500000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe1000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy8: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-1.dtsi
index 1955dfa13634..70e947730c4b 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-1.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-1.dtsi
@@ -59,6 +59,7 @@ fman@500000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe3000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy9: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-2.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-2.dtsi
index 2c1476454ee0..ad96e6529595 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-2.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-2.dtsi
@@ -59,6 +59,7 @@ fman@500000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe5000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy10: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-3.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-3.dtsi
index b8b541ff5fb0..034bc4b71f7a 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-3.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-3.dtsi
@@ -59,6 +59,7 @@ fman@500000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe7000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy11: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-4.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-4.dtsi
index 4b2cfddd1b15..93ca23d82b39 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-4.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-4.dtsi
@@ -59,6 +59,7 @@ fman@500000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xe9000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy12: ethernet-phy@0 {
 			reg = <0x0>;
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-5.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-5.dtsi
index 0a52ddf7cc17..23b3117a2fd2 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-5.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1-1g-5.dtsi
@@ -59,6 +59,7 @@ fman@500000 {
 		#size-cells = <0>;
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xeb000 0x1000>;
+		fsl,erratum-a011043; /* must ignore read errors */
 
 		pcsphy13: ethernet-phy@0 {
 			reg = <0x0>;
-- 
cgit 


From 1d3ca681b9d9575ccf696ebc2840a1ebb1fd4074 Mon Sep 17 00:00:00 2001
From: Madalin Bucur <madalin.bucur@oss.nxp.com>
Date: Wed, 22 Jan 2020 15:20:29 +0200
Subject: net/fsl: treat fsl,erratum-a011043

When fsl,erratum-a011043 is set, adjust for erratum A011043:
MDIO reads to internal PCS registers may result in having
the MDIO_CFG[MDIO_RD_ER] bit set, even when there is no
error and read data (MDIO_DATA[MDIO_DATA]) is correct.
Software may get false read error when reading internal
PCS registers through MDIO. As a workaround, all internal
MDIO accesses should ignore the MDIO_CFG[MDIO_RD_ER] bit.

Signed-off-by: Madalin Bucur <madalin.bucur@oss.nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/xgmac_mdio.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c
index e03b30c60dcf..c82c85ef5fb3 100644
--- a/drivers/net/ethernet/freescale/xgmac_mdio.c
+++ b/drivers/net/ethernet/freescale/xgmac_mdio.c
@@ -49,6 +49,7 @@ struct tgec_mdio_controller {
 struct mdio_fsl_priv {
 	struct	tgec_mdio_controller __iomem *mdio_base;
 	bool	is_little_endian;
+	bool	has_a011043;
 };
 
 static u32 xgmac_read32(void __iomem *regs,
@@ -226,7 +227,8 @@ static int xgmac_mdio_read(struct mii_bus *bus, int phy_id, int regnum)
 		return ret;
 
 	/* Return all Fs if nothing was there */
-	if (xgmac_read32(&regs->mdio_stat, endian) & MDIO_STAT_RD_ER) {
+	if ((xgmac_read32(&regs->mdio_stat, endian) & MDIO_STAT_RD_ER) &&
+	    !priv->has_a011043) {
 		dev_err(&bus->dev,
 			"Error while reading PHY%d reg at %d.%hhu\n",
 			phy_id, dev_addr, regnum);
@@ -274,6 +276,9 @@ static int xgmac_mdio_probe(struct platform_device *pdev)
 	priv->is_little_endian = of_property_read_bool(pdev->dev.of_node,
 						       "little-endian");
 
+	priv->has_a011043 = of_property_read_bool(pdev->dev.of_node,
+						  "fsl,erratum-a011043");
+
 	ret = of_mdiobus_register(bus, np);
 	if (ret) {
 		dev_err(&pdev->dev, "cannot register MDIO bus\n");
-- 
cgit 


From 457bfc0a4bf531487ecc3cf82ec728a5e114fb1e Mon Sep 17 00:00:00 2001
From: Madalin Bucur <madalin.bucur@oss.nxp.com>
Date: Wed, 22 Jan 2020 16:15:14 +0200
Subject: net: fsl/fman: rename IF_MODE_XGMII to IF_MODE_10G

As the only 10G PHY interface type defined at the moment the code
was developed was XGMII, although the PHY interface mode used was
not XGMII, XGMII was used in the code to denote 10G. This patch
renames the 10G interface mode to remove the ambiguity.

Signed-off-by: Madalin Bucur <madalin.bucur@oss.nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fman/fman_memac.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c
index 41c6fa200e74..e1901874c19f 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.c
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.c
@@ -110,7 +110,7 @@ do {									\
 /* Interface Mode Register (IF_MODE) */
 
 #define IF_MODE_MASK		0x00000003 /* 30-31 Mask on i/f mode bits */
-#define IF_MODE_XGMII		0x00000000 /* 30-31 XGMII (10G) interface */
+#define IF_MODE_10G		0x00000000 /* 30-31 10G interface */
 #define IF_MODE_GMII		0x00000002 /* 30-31 GMII (1G) interface */
 #define IF_MODE_RGMII		0x00000004
 #define IF_MODE_RGMII_AUTO	0x00008000
@@ -440,7 +440,7 @@ static int init(struct memac_regs __iomem *regs, struct memac_cfg *cfg,
 	tmp = 0;
 	switch (phy_if) {
 	case PHY_INTERFACE_MODE_XGMII:
-		tmp |= IF_MODE_XGMII;
+		tmp |= IF_MODE_10G;
 		break;
 	default:
 		tmp |= IF_MODE_GMII;
-- 
cgit 


From 865ad2f2201dc18685ba2686f13217f8b3a9c52c Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@telegraphics.com.au>
Date: Thu, 23 Jan 2020 09:07:26 +1100
Subject: net/sonic: Add mutual exclusion for accessing shared state

The netif_stop_queue() call in sonic_send_packet() races with the
netif_wake_queue() call in sonic_interrupt(). This causes issues
like "NETDEV WATCHDOG: eth0 (macsonic): transmit queue 0 timed out".
Fix this by disabling interrupts when accessing tx_skb[] and next_tx.
Update a comment to clarify the synchronization properties.

Fixes: efcce839360f ("[PATCH] macsonic/jazzsonic network drivers update")
Tested-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/natsemi/sonic.c | 49 +++++++++++++++++++++++++-----------
 drivers/net/ethernet/natsemi/sonic.h |  1 +
 2 files changed, 36 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c
index b339125b2f09..8a7cff516281 100644
--- a/drivers/net/ethernet/natsemi/sonic.c
+++ b/drivers/net/ethernet/natsemi/sonic.c
@@ -64,6 +64,8 @@ static int sonic_open(struct net_device *dev)
 
 	netif_dbg(lp, ifup, dev, "%s: initializing sonic driver\n", __func__);
 
+	spin_lock_init(&lp->lock);
+
 	for (i = 0; i < SONIC_NUM_RRS; i++) {
 		struct sk_buff *skb = netdev_alloc_skb(dev, SONIC_RBSIZE + 2);
 		if (skb == NULL) {
@@ -206,8 +208,6 @@ static void sonic_tx_timeout(struct net_device *dev)
  *   wake the tx queue
  * Concurrently with all of this, the SONIC is potentially writing to
  * the status flags of the TDs.
- * Until some mutual exclusion is added, this code will not work with SMP. However,
- * MIPS Jazz machines and m68k Macs were all uni-processor machines.
  */
 
 static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev)
@@ -215,7 +215,8 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev)
 	struct sonic_local *lp = netdev_priv(dev);
 	dma_addr_t laddr;
 	int length;
-	int entry = lp->next_tx;
+	int entry;
+	unsigned long flags;
 
 	netif_dbg(lp, tx_queued, dev, "%s: skb=%p\n", __func__, skb);
 
@@ -237,6 +238,10 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_OK;
 	}
 
+	spin_lock_irqsave(&lp->lock, flags);
+
+	entry = lp->next_tx;
+
 	sonic_tda_put(dev, entry, SONIC_TD_STATUS, 0);       /* clear status */
 	sonic_tda_put(dev, entry, SONIC_TD_FRAG_COUNT, 1);   /* single fragment */
 	sonic_tda_put(dev, entry, SONIC_TD_PKTSIZE, length); /* length of packet */
@@ -246,10 +251,6 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev)
 	sonic_tda_put(dev, entry, SONIC_TD_LINK,
 		sonic_tda_get(dev, entry, SONIC_TD_LINK) | SONIC_EOL);
 
-	/*
-	 * Must set tx_skb[entry] only after clearing status, and
-	 * before clearing EOL and before stopping queue
-	 */
 	wmb();
 	lp->tx_len[entry] = length;
 	lp->tx_laddr[entry] = laddr;
@@ -272,6 +273,8 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev)
 
 	SONIC_WRITE(SONIC_CMD, SONIC_CR_TXP);
 
+	spin_unlock_irqrestore(&lp->lock, flags);
+
 	return NETDEV_TX_OK;
 }
 
@@ -284,9 +287,21 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
 	struct net_device *dev = dev_id;
 	struct sonic_local *lp = netdev_priv(dev);
 	int status;
+	unsigned long flags;
+
+	/* The lock has two purposes. Firstly, it synchronizes sonic_interrupt()
+	 * with sonic_send_packet() so that the two functions can share state.
+	 * Secondly, it makes sonic_interrupt() re-entrant, as that is required
+	 * by macsonic which must use two IRQs with different priority levels.
+	 */
+	spin_lock_irqsave(&lp->lock, flags);
+
+	status = SONIC_READ(SONIC_ISR) & SONIC_IMR_DEFAULT;
+	if (!status) {
+		spin_unlock_irqrestore(&lp->lock, flags);
 
-	if (!(status = SONIC_READ(SONIC_ISR) & SONIC_IMR_DEFAULT))
 		return IRQ_NONE;
+	}
 
 	do {
 		if (status & SONIC_INT_PKTRX) {
@@ -300,11 +315,12 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
 			int td_status;
 			int freed_some = 0;
 
-			/* At this point, cur_tx is the index of a TD that is one of:
-			 *   unallocated/freed                          (status set   & tx_skb[entry] clear)
-			 *   allocated and sent                         (status set   & tx_skb[entry] set  )
-			 *   allocated and not yet sent                 (status clear & tx_skb[entry] set  )
-			 *   still being allocated by sonic_send_packet (status clear & tx_skb[entry] clear)
+			/* The state of a Transmit Descriptor may be inferred
+			 * from { tx_skb[entry], td_status } as follows.
+			 * { clear, clear } => the TD has never been used
+			 * { set,   clear } => the TD was handed to SONIC
+			 * { set,   set   } => the TD was handed back
+			 * { clear, set   } => the TD is available for re-use
 			 */
 
 			netif_dbg(lp, intr, dev, "%s: tx done\n", __func__);
@@ -406,7 +422,12 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
 		/* load CAM done */
 		if (status & SONIC_INT_LCD)
 			SONIC_WRITE(SONIC_ISR, SONIC_INT_LCD); /* clear the interrupt */
-	} while((status = SONIC_READ(SONIC_ISR) & SONIC_IMR_DEFAULT));
+
+		status = SONIC_READ(SONIC_ISR) & SONIC_IMR_DEFAULT;
+	} while (status);
+
+	spin_unlock_irqrestore(&lp->lock, flags);
+
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/net/ethernet/natsemi/sonic.h b/drivers/net/ethernet/natsemi/sonic.h
index 2b27f7049acb..f9506863e9d1 100644
--- a/drivers/net/ethernet/natsemi/sonic.h
+++ b/drivers/net/ethernet/natsemi/sonic.h
@@ -322,6 +322,7 @@ struct sonic_local {
 	int msg_enable;
 	struct device *device;         /* generic device */
 	struct net_device_stats stats;
+	spinlock_t lock;
 };
 
 #define TX_TIMEOUT (3 * HZ)
-- 
cgit 


From 5fedabf5a70be26b19d7520f09f12a62274317c6 Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@telegraphics.com.au>
Date: Thu, 23 Jan 2020 09:07:26 +1100
Subject: net/sonic: Clear interrupt flags immediately

The chip can change a packet's descriptor status flags at any time.
However, an active interrupt flag gets cleared rather late. This
allows a race condition that could theoretically lose an interrupt.
Fix this by clearing asserted interrupt flags immediately.

Fixes: efcce839360f ("[PATCH] macsonic/jazzsonic network drivers update")
Tested-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/natsemi/sonic.c | 28 ++++++----------------------
 1 file changed, 6 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c
index 8a7cff516281..1109070a5154 100644
--- a/drivers/net/ethernet/natsemi/sonic.c
+++ b/drivers/net/ethernet/natsemi/sonic.c
@@ -304,10 +304,11 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
 	}
 
 	do {
+		SONIC_WRITE(SONIC_ISR, status); /* clear the interrupt(s) */
+
 		if (status & SONIC_INT_PKTRX) {
 			netif_dbg(lp, intr, dev, "%s: packet rx\n", __func__);
 			sonic_rx(dev);	/* got packet(s) */
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_PKTRX); /* clear the interrupt */
 		}
 
 		if (status & SONIC_INT_TXDN) {
@@ -362,7 +363,6 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
 			if (freed_some || lp->tx_skb[entry] == NULL)
 				netif_wake_queue(dev);  /* The ring is no longer full */
 			lp->cur_tx = entry;
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_TXDN); /* clear the interrupt */
 		}
 
 		/*
@@ -372,42 +372,31 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
 			netif_dbg(lp, rx_err, dev, "%s: rx fifo overrun\n",
 				  __func__);
 			lp->stats.rx_fifo_errors++;
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_RFO); /* clear the interrupt */
 		}
 		if (status & SONIC_INT_RDE) {
 			netif_dbg(lp, rx_err, dev, "%s: rx descriptors exhausted\n",
 				  __func__);
 			lp->stats.rx_dropped++;
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_RDE); /* clear the interrupt */
 		}
 		if (status & SONIC_INT_RBAE) {
 			netif_dbg(lp, rx_err, dev, "%s: rx buffer area exceeded\n",
 				  __func__);
 			lp->stats.rx_dropped++;
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_RBAE); /* clear the interrupt */
 		}
 
 		/* counter overruns; all counters are 16bit wide */
-		if (status & SONIC_INT_FAE) {
+		if (status & SONIC_INT_FAE)
 			lp->stats.rx_frame_errors += 65536;
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_FAE); /* clear the interrupt */
-		}
-		if (status & SONIC_INT_CRC) {
+		if (status & SONIC_INT_CRC)
 			lp->stats.rx_crc_errors += 65536;
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_CRC); /* clear the interrupt */
-		}
-		if (status & SONIC_INT_MP) {
+		if (status & SONIC_INT_MP)
 			lp->stats.rx_missed_errors += 65536;
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_MP); /* clear the interrupt */
-		}
 
 		/* transmit error */
-		if (status & SONIC_INT_TXER) {
+		if (status & SONIC_INT_TXER)
 			if (SONIC_READ(SONIC_TCR) & SONIC_TCR_FU)
 				netif_dbg(lp, tx_err, dev, "%s: tx fifo underrun\n",
 					  __func__);
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_TXER); /* clear the interrupt */
-		}
 
 		/* bus retry */
 		if (status & SONIC_INT_BR) {
@@ -416,13 +405,8 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
 			/* ... to help debug DMA problems causing endless interrupts. */
 			/* Bounce the eth interface to turn on the interrupt again. */
 			SONIC_WRITE(SONIC_IMR, 0);
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_BR); /* clear the interrupt */
 		}
 
-		/* load CAM done */
-		if (status & SONIC_INT_LCD)
-			SONIC_WRITE(SONIC_ISR, SONIC_INT_LCD); /* clear the interrupt */
-
 		status = SONIC_READ(SONIC_ISR) & SONIC_IMR_DEFAULT;
 	} while (status);
 
-- 
cgit 


From e3885f576196ddfc670b3d53e745de96ffcb49ab Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@telegraphics.com.au>
Date: Thu, 23 Jan 2020 09:07:26 +1100
Subject: net/sonic: Use MMIO accessors

The driver accesses descriptor memory which is simultaneously accessed by
the chip, so the compiler must not be allowed to re-order CPU accesses.
sonic_buf_get() used 'volatile' to prevent that. sonic_buf_put() should
have done so too but was overlooked.

Fixes: efcce839360f ("[PATCH] macsonic/jazzsonic network drivers update")
Tested-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/natsemi/sonic.h | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/natsemi/sonic.h b/drivers/net/ethernet/natsemi/sonic.h
index f9506863e9d1..fb160dfdf4ca 100644
--- a/drivers/net/ethernet/natsemi/sonic.h
+++ b/drivers/net/ethernet/natsemi/sonic.h
@@ -345,30 +345,30 @@ static void sonic_msg_init(struct net_device *dev);
    as far as we can tell. */
 /* OpenBSD calls this "SWO".  I'd like to think that sonic_buf_put()
    is a much better name. */
-static inline void sonic_buf_put(void* base, int bitmode,
+static inline void sonic_buf_put(u16 *base, int bitmode,
 				 int offset, __u16 val)
 {
 	if (bitmode)
 #ifdef __BIG_ENDIAN
-		((__u16 *) base + (offset*2))[1] = val;
+		__raw_writew(val, base + (offset * 2) + 1);
 #else
-		((__u16 *) base + (offset*2))[0] = val;
+		__raw_writew(val, base + (offset * 2) + 0);
 #endif
 	else
-	 	((__u16 *) base)[offset] = val;
+		__raw_writew(val, base + (offset * 1) + 0);
 }
 
-static inline __u16 sonic_buf_get(void* base, int bitmode,
+static inline __u16 sonic_buf_get(u16 *base, int bitmode,
 				  int offset)
 {
 	if (bitmode)
 #ifdef __BIG_ENDIAN
-		return ((volatile __u16 *) base + (offset*2))[1];
+		return __raw_readw(base + (offset * 2) + 1);
 #else
-		return ((volatile __u16 *) base + (offset*2))[0];
+		return __raw_readw(base + (offset * 2) + 0);
 #endif
 	else
-		return ((volatile __u16 *) base)[offset];
+		return __raw_readw(base + (offset * 1) + 0);
 }
 
 /* Inlines that you should actually use for reading/writing DMA buffers */
-- 
cgit 


From 427db97df1ee721c20bdc9a66db8a9e1da719855 Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@telegraphics.com.au>
Date: Thu, 23 Jan 2020 09:07:26 +1100
Subject: net/sonic: Fix interface error stats collection

The tx_aborted_errors statistic should count packets flagged with EXD,
EXC, FU, or BCM bits because those bits denote an aborted transmission.
That corresponds to the bitmask 0x0446, not 0x0642. Use macros for these
constants to avoid mistakes. Better to leave out FIFO Underruns (FU) as
there's a separate counter for that purpose.

Don't lump all these errors in with the general tx_errors counter as
that's used for tx timeout events.

On the rx side, don't count RDE and RBAE interrupts as dropped packets.
These interrupts don't indicate a lost packet, just a lack of resources.
When a lack of resources results in a lost packet, this gets reported
in the rx_missed_errors counter (along with RFO events).

Don't double-count rx_frame_errors and rx_crc_errors.

Don't use the general rx_errors counter for events that already have
special counters.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Tested-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/natsemi/sonic.c | 21 +++++++--------------
 drivers/net/ethernet/natsemi/sonic.h |  1 +
 2 files changed, 8 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c
index 1109070a5154..b31c7af32dfa 100644
--- a/drivers/net/ethernet/natsemi/sonic.c
+++ b/drivers/net/ethernet/natsemi/sonic.c
@@ -330,18 +330,19 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
 				if ((td_status = sonic_tda_get(dev, entry, SONIC_TD_STATUS)) == 0)
 					break;
 
-				if (td_status & 0x0001) {
+				if (td_status & SONIC_TCR_PTX) {
 					lp->stats.tx_packets++;
 					lp->stats.tx_bytes += sonic_tda_get(dev, entry, SONIC_TD_PKTSIZE);
 				} else {
-					lp->stats.tx_errors++;
-					if (td_status & 0x0642)
+					if (td_status & (SONIC_TCR_EXD |
+					    SONIC_TCR_EXC | SONIC_TCR_BCM))
 						lp->stats.tx_aborted_errors++;
-					if (td_status & 0x0180)
+					if (td_status &
+					    (SONIC_TCR_NCRS | SONIC_TCR_CRLS))
 						lp->stats.tx_carrier_errors++;
-					if (td_status & 0x0020)
+					if (td_status & SONIC_TCR_OWC)
 						lp->stats.tx_window_errors++;
-					if (td_status & 0x0004)
+					if (td_status & SONIC_TCR_FU)
 						lp->stats.tx_fifo_errors++;
 				}
 
@@ -371,17 +372,14 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
 		if (status & SONIC_INT_RFO) {
 			netif_dbg(lp, rx_err, dev, "%s: rx fifo overrun\n",
 				  __func__);
-			lp->stats.rx_fifo_errors++;
 		}
 		if (status & SONIC_INT_RDE) {
 			netif_dbg(lp, rx_err, dev, "%s: rx descriptors exhausted\n",
 				  __func__);
-			lp->stats.rx_dropped++;
 		}
 		if (status & SONIC_INT_RBAE) {
 			netif_dbg(lp, rx_err, dev, "%s: rx buffer area exceeded\n",
 				  __func__);
-			lp->stats.rx_dropped++;
 		}
 
 		/* counter overruns; all counters are 16bit wide */
@@ -473,11 +471,6 @@ static void sonic_rx(struct net_device *dev)
 			sonic_rra_put(dev, entry, SONIC_RR_BUFADR_H, bufadr_h);
 		} else {
 			/* This should only happen, if we enable accepting broken packets. */
-			lp->stats.rx_errors++;
-			if (status & SONIC_RCR_FAER)
-				lp->stats.rx_frame_errors++;
-			if (status & SONIC_RCR_CRCR)
-				lp->stats.rx_crc_errors++;
 		}
 		if (status & SONIC_RCR_LPKT) {
 			/*
diff --git a/drivers/net/ethernet/natsemi/sonic.h b/drivers/net/ethernet/natsemi/sonic.h
index fb160dfdf4ca..9e4ff8dd032d 100644
--- a/drivers/net/ethernet/natsemi/sonic.h
+++ b/drivers/net/ethernet/natsemi/sonic.h
@@ -175,6 +175,7 @@
 #define SONIC_TCR_NCRS          0x0100
 #define SONIC_TCR_CRLS          0x0080
 #define SONIC_TCR_EXC           0x0040
+#define SONIC_TCR_OWC           0x0020
 #define SONIC_TCR_PMB           0x0008
 #define SONIC_TCR_FU            0x0004
 #define SONIC_TCR_BCM           0x0002
-- 
cgit 


From 9e311820f67e740f4fb8dcb82b4c4b5b05bdd1a5 Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@telegraphics.com.au>
Date: Thu, 23 Jan 2020 09:07:26 +1100
Subject: net/sonic: Fix receive buffer handling

The SONIC can sometimes advance its rx buffer pointer (RRP register)
without advancing its rx descriptor pointer (CRDA register). As a result
the index of the current rx descriptor may not equal that of the current
rx buffer. The driver mistakenly assumes that they are always equal.
This assumption leads to incorrect packet lengths and possible packet
duplication. Avoid this by calling a new function to locate the buffer
corresponding to a given descriptor.

Fixes: efcce839360f ("[PATCH] macsonic/jazzsonic network drivers update")
Tested-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/natsemi/sonic.c | 35 ++++++++++++++++++++++++++++++-----
 drivers/net/ethernet/natsemi/sonic.h |  5 +++--
 2 files changed, 33 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c
index b31c7af32dfa..c666bbf15116 100644
--- a/drivers/net/ethernet/natsemi/sonic.c
+++ b/drivers/net/ethernet/natsemi/sonic.c
@@ -413,6 +413,21 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+/* Return the array index corresponding to a given Receive Buffer pointer. */
+static int index_from_addr(struct sonic_local *lp, dma_addr_t addr,
+			   unsigned int last)
+{
+	unsigned int i = last;
+
+	do {
+		i = (i + 1) & SONIC_RRS_MASK;
+		if (addr == lp->rx_laddr[i])
+			return i;
+	} while (i != last);
+
+	return -ENOENT;
+}
+
 /*
  * We have a good packet(s), pass it/them up the network stack.
  */
@@ -432,6 +447,16 @@ static void sonic_rx(struct net_device *dev)
 
 		status = sonic_rda_get(dev, entry, SONIC_RD_STATUS);
 		if (status & SONIC_RCR_PRX) {
+			u32 addr = (sonic_rda_get(dev, entry,
+						  SONIC_RD_PKTPTR_H) << 16) |
+				   sonic_rda_get(dev, entry, SONIC_RD_PKTPTR_L);
+			int i = index_from_addr(lp, addr, entry);
+
+			if (i < 0) {
+				WARN_ONCE(1, "failed to find buffer!\n");
+				break;
+			}
+
 			/* Malloc up new buffer. */
 			new_skb = netdev_alloc_skb(dev, SONIC_RBSIZE + 2);
 			if (new_skb == NULL) {
@@ -453,7 +478,7 @@ static void sonic_rx(struct net_device *dev)
 
 			/* now we have a new skb to replace it, pass the used one up the stack */
 			dma_unmap_single(lp->device, lp->rx_laddr[entry], SONIC_RBSIZE, DMA_FROM_DEVICE);
-			used_skb = lp->rx_skb[entry];
+			used_skb = lp->rx_skb[i];
 			pkt_len = sonic_rda_get(dev, entry, SONIC_RD_PKTLEN);
 			skb_trim(used_skb, pkt_len);
 			used_skb->protocol = eth_type_trans(used_skb, dev);
@@ -462,13 +487,13 @@ static void sonic_rx(struct net_device *dev)
 			lp->stats.rx_bytes += pkt_len;
 
 			/* and insert the new skb */
-			lp->rx_laddr[entry] = new_laddr;
-			lp->rx_skb[entry] = new_skb;
+			lp->rx_laddr[i] = new_laddr;
+			lp->rx_skb[i] = new_skb;
 
 			bufadr_l = (unsigned long)new_laddr & 0xffff;
 			bufadr_h = (unsigned long)new_laddr >> 16;
-			sonic_rra_put(dev, entry, SONIC_RR_BUFADR_L, bufadr_l);
-			sonic_rra_put(dev, entry, SONIC_RR_BUFADR_H, bufadr_h);
+			sonic_rra_put(dev, i, SONIC_RR_BUFADR_L, bufadr_l);
+			sonic_rra_put(dev, i, SONIC_RR_BUFADR_H, bufadr_h);
 		} else {
 			/* This should only happen, if we enable accepting broken packets. */
 		}
diff --git a/drivers/net/ethernet/natsemi/sonic.h b/drivers/net/ethernet/natsemi/sonic.h
index 9e4ff8dd032d..e6d47e45c5c2 100644
--- a/drivers/net/ethernet/natsemi/sonic.h
+++ b/drivers/net/ethernet/natsemi/sonic.h
@@ -275,8 +275,9 @@
 #define SONIC_NUM_RDS   SONIC_NUM_RRS /* number of receive descriptors */
 #define SONIC_NUM_TDS   16            /* number of transmit descriptors */
 
-#define SONIC_RDS_MASK  (SONIC_NUM_RDS-1)
-#define SONIC_TDS_MASK  (SONIC_NUM_TDS-1)
+#define SONIC_RRS_MASK  (SONIC_NUM_RRS - 1)
+#define SONIC_RDS_MASK  (SONIC_NUM_RDS - 1)
+#define SONIC_TDS_MASK  (SONIC_NUM_TDS - 1)
 
 #define SONIC_RBSIZE	1520          /* size of one resource buffer */
 
-- 
cgit 


From eaabfd19b2c787bbe88dc32424b9a43d67293422 Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@telegraphics.com.au>
Date: Thu, 23 Jan 2020 09:07:26 +1100
Subject: net/sonic: Avoid needless receive descriptor EOL flag updates

The while loop in sonic_rx() traverses the rx descriptor ring. It stops
when it reaches a descriptor that the SONIC has not used. Each iteration
advances the EOL flag so the SONIC can keep using more descriptors.
Therefore, the while loop has no definite termination condition.

The algorithm described in the National Semiconductor literature is quite
different. It consumes descriptors up to the one with its EOL flag set
(which will also have its "in use" flag set). All freed descriptors are
then returned to the ring at once, by adjusting the EOL flags (and link
pointers).

Adopt the algorithm from datasheet as it's simpler, terminates quickly
and avoids a lot of pointless descriptor EOL flag changes.

Fixes: efcce839360f ("[PATCH] macsonic/jazzsonic network drivers update")
Tested-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/natsemi/sonic.c | 21 +++++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c
index c666bbf15116..2cee702f49b8 100644
--- a/drivers/net/ethernet/natsemi/sonic.c
+++ b/drivers/net/ethernet/natsemi/sonic.c
@@ -436,6 +436,7 @@ static void sonic_rx(struct net_device *dev)
 	struct sonic_local *lp = netdev_priv(dev);
 	int status;
 	int entry = lp->cur_rx;
+	int prev_entry = lp->eol_rx;
 
 	while (sonic_rda_get(dev, entry, SONIC_RD_IN_USE) == 0) {
 		struct sk_buff *used_skb;
@@ -516,13 +517,21 @@ static void sonic_rx(struct net_device *dev)
 		/*
 		 * give back the descriptor
 		 */
-		sonic_rda_put(dev, entry, SONIC_RD_LINK,
-			sonic_rda_get(dev, entry, SONIC_RD_LINK) | SONIC_EOL);
 		sonic_rda_put(dev, entry, SONIC_RD_IN_USE, 1);
-		sonic_rda_put(dev, lp->eol_rx, SONIC_RD_LINK,
-			sonic_rda_get(dev, lp->eol_rx, SONIC_RD_LINK) & ~SONIC_EOL);
-		lp->eol_rx = entry;
-		lp->cur_rx = entry = (entry + 1) & SONIC_RDS_MASK;
+
+		prev_entry = entry;
+		entry = (entry + 1) & SONIC_RDS_MASK;
+	}
+
+	lp->cur_rx = entry;
+
+	if (prev_entry != lp->eol_rx) {
+		/* Advance the EOL flag to put descriptors back into service */
+		sonic_rda_put(dev, prev_entry, SONIC_RD_LINK, SONIC_EOL |
+			      sonic_rda_get(dev, prev_entry, SONIC_RD_LINK));
+		sonic_rda_put(dev, lp->eol_rx, SONIC_RD_LINK, ~SONIC_EOL &
+			      sonic_rda_get(dev, lp->eol_rx, SONIC_RD_LINK));
+		lp->eol_rx = prev_entry;
 	}
 	/*
 	 * If any worth-while packets have been received, netif_rx()
-- 
cgit 


From 94b166349503957079ef5e7d6f667f157aea014a Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@telegraphics.com.au>
Date: Thu, 23 Jan 2020 09:07:26 +1100
Subject: net/sonic: Improve receive descriptor status flag check

After sonic_tx_timeout() calls sonic_init(), it can happen that
sonic_rx() will subsequently encounter a receive descriptor with no
flags set. Remove the comment that says that this can't happen.

When giving a receive descriptor to the SONIC, clear the descriptor
status field. That way, any rx descriptor with flags set can only be
a newly received packet.

Don't process a descriptor without the LPKT bit set. The buffer is
still in use by the SONIC.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Tested-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/natsemi/sonic.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c
index 2cee702f49b8..9d2bddc4951b 100644
--- a/drivers/net/ethernet/natsemi/sonic.c
+++ b/drivers/net/ethernet/natsemi/sonic.c
@@ -434,7 +434,6 @@ static int index_from_addr(struct sonic_local *lp, dma_addr_t addr,
 static void sonic_rx(struct net_device *dev)
 {
 	struct sonic_local *lp = netdev_priv(dev);
-	int status;
 	int entry = lp->cur_rx;
 	int prev_entry = lp->eol_rx;
 
@@ -445,9 +444,10 @@ static void sonic_rx(struct net_device *dev)
 		u16 bufadr_l;
 		u16 bufadr_h;
 		int pkt_len;
+		u16 status = sonic_rda_get(dev, entry, SONIC_RD_STATUS);
 
-		status = sonic_rda_get(dev, entry, SONIC_RD_STATUS);
-		if (status & SONIC_RCR_PRX) {
+		/* If the RD has LPKT set, the chip has finished with the RB */
+		if ((status & SONIC_RCR_PRX) && (status & SONIC_RCR_LPKT)) {
 			u32 addr = (sonic_rda_get(dev, entry,
 						  SONIC_RD_PKTPTR_H) << 16) |
 				   sonic_rda_get(dev, entry, SONIC_RD_PKTPTR_L);
@@ -495,10 +495,6 @@ static void sonic_rx(struct net_device *dev)
 			bufadr_h = (unsigned long)new_laddr >> 16;
 			sonic_rra_put(dev, i, SONIC_RR_BUFADR_L, bufadr_l);
 			sonic_rra_put(dev, i, SONIC_RR_BUFADR_H, bufadr_h);
-		} else {
-			/* This should only happen, if we enable accepting broken packets. */
-		}
-		if (status & SONIC_RCR_LPKT) {
 			/*
 			 * this was the last packet out of the current receive buffer
 			 * give the buffer back to the SONIC
@@ -511,12 +507,11 @@ static void sonic_rx(struct net_device *dev)
 					  __func__);
 				SONIC_WRITE(SONIC_ISR, SONIC_INT_RBE); /* clear the flag */
 			}
-		} else
-			printk(KERN_ERR "%s: rx desc without RCR_LPKT. Shouldn't happen !?\n",
-			     dev->name);
+		}
 		/*
 		 * give back the descriptor
 		 */
+		sonic_rda_put(dev, entry, SONIC_RD_STATUS, 0);
 		sonic_rda_put(dev, entry, SONIC_RD_IN_USE, 1);
 
 		prev_entry = entry;
-- 
cgit 


From 89ba879e95582d3bba55081e45b5409e883312ca Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@telegraphics.com.au>
Date: Thu, 23 Jan 2020 09:07:26 +1100
Subject: net/sonic: Fix receive buffer replenishment

As soon as the driver is finished with a receive buffer it allocs a new
one and overwrites the corresponding RRA entry with a new buffer pointer.

Problem is, the buffer pointer is split across two word-sized registers.
It can't be updated in one atomic store. So this operation races with the
chip while it stores received packets and advances its RRP register.
This could result in memory corruption by a DMA write.

Avoid this problem by adding buffers only at the location given by the
RWP register, in accordance with the National Semiconductor datasheet.

Re-factor this code into separate functions to calculate a RRA pointer
and to update the RWP.

Fixes: efcce839360f ("[PATCH] macsonic/jazzsonic network drivers update")
Tested-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/natsemi/sonic.c | 150 +++++++++++++++++++++--------------
 drivers/net/ethernet/natsemi/sonic.h |  18 ++++-
 2 files changed, 105 insertions(+), 63 deletions(-)

diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c
index 9d2bddc4951b..26848acec63d 100644
--- a/drivers/net/ethernet/natsemi/sonic.c
+++ b/drivers/net/ethernet/natsemi/sonic.c
@@ -428,6 +428,59 @@ static int index_from_addr(struct sonic_local *lp, dma_addr_t addr,
 	return -ENOENT;
 }
 
+/* Allocate and map a new skb to be used as a receive buffer. */
+static bool sonic_alloc_rb(struct net_device *dev, struct sonic_local *lp,
+			   struct sk_buff **new_skb, dma_addr_t *new_addr)
+{
+	*new_skb = netdev_alloc_skb(dev, SONIC_RBSIZE + 2);
+	if (!*new_skb)
+		return false;
+
+	if (SONIC_BUS_SCALE(lp->dma_bitmode) == 2)
+		skb_reserve(*new_skb, 2);
+
+	*new_addr = dma_map_single(lp->device, skb_put(*new_skb, SONIC_RBSIZE),
+				   SONIC_RBSIZE, DMA_FROM_DEVICE);
+	if (!*new_addr) {
+		dev_kfree_skb(*new_skb);
+		*new_skb = NULL;
+		return false;
+	}
+
+	return true;
+}
+
+/* Place a new receive resource in the Receive Resource Area and update RWP. */
+static void sonic_update_rra(struct net_device *dev, struct sonic_local *lp,
+			     dma_addr_t old_addr, dma_addr_t new_addr)
+{
+	unsigned int entry = sonic_rr_entry(dev, SONIC_READ(SONIC_RWP));
+	unsigned int end = sonic_rr_entry(dev, SONIC_READ(SONIC_RRP));
+	u32 buf;
+
+	/* The resources in the range [RRP, RWP) belong to the SONIC. This loop
+	 * scans the other resources in the RRA, those in the range [RWP, RRP).
+	 */
+	do {
+		buf = (sonic_rra_get(dev, entry, SONIC_RR_BUFADR_H) << 16) |
+		      sonic_rra_get(dev, entry, SONIC_RR_BUFADR_L);
+
+		if (buf == old_addr)
+			break;
+
+		entry = (entry + 1) & SONIC_RRS_MASK;
+	} while (entry != end);
+
+	WARN_ONCE(buf != old_addr, "failed to find resource!\n");
+
+	sonic_rra_put(dev, entry, SONIC_RR_BUFADR_H, new_addr >> 16);
+	sonic_rra_put(dev, entry, SONIC_RR_BUFADR_L, new_addr & 0xffff);
+
+	entry = (entry + 1) & SONIC_RRS_MASK;
+
+	SONIC_WRITE(SONIC_RWP, sonic_rr_addr(dev, entry));
+}
+
 /*
  * We have a good packet(s), pass it/them up the network stack.
  */
@@ -436,18 +489,15 @@ static void sonic_rx(struct net_device *dev)
 	struct sonic_local *lp = netdev_priv(dev);
 	int entry = lp->cur_rx;
 	int prev_entry = lp->eol_rx;
+	bool rbe = false;
 
 	while (sonic_rda_get(dev, entry, SONIC_RD_IN_USE) == 0) {
-		struct sk_buff *used_skb;
-		struct sk_buff *new_skb;
-		dma_addr_t new_laddr;
-		u16 bufadr_l;
-		u16 bufadr_h;
-		int pkt_len;
 		u16 status = sonic_rda_get(dev, entry, SONIC_RD_STATUS);
 
 		/* If the RD has LPKT set, the chip has finished with the RB */
 		if ((status & SONIC_RCR_PRX) && (status & SONIC_RCR_LPKT)) {
+			struct sk_buff *new_skb;
+			dma_addr_t new_laddr;
 			u32 addr = (sonic_rda_get(dev, entry,
 						  SONIC_RD_PKTPTR_H) << 16) |
 				   sonic_rda_get(dev, entry, SONIC_RD_PKTPTR_L);
@@ -458,55 +508,35 @@ static void sonic_rx(struct net_device *dev)
 				break;
 			}
 
-			/* Malloc up new buffer. */
-			new_skb = netdev_alloc_skb(dev, SONIC_RBSIZE + 2);
-			if (new_skb == NULL) {
+			if (sonic_alloc_rb(dev, lp, &new_skb, &new_laddr)) {
+				struct sk_buff *used_skb = lp->rx_skb[i];
+				int pkt_len;
+
+				/* Pass the used buffer up the stack */
+				dma_unmap_single(lp->device, addr, SONIC_RBSIZE,
+						 DMA_FROM_DEVICE);
+
+				pkt_len = sonic_rda_get(dev, entry,
+							SONIC_RD_PKTLEN);
+				skb_trim(used_skb, pkt_len);
+				used_skb->protocol = eth_type_trans(used_skb,
+								    dev);
+				netif_rx(used_skb);
+				lp->stats.rx_packets++;
+				lp->stats.rx_bytes += pkt_len;
+
+				lp->rx_skb[i] = new_skb;
+				lp->rx_laddr[i] = new_laddr;
+			} else {
+				/* Failed to obtain a new buffer so re-use it */
+				new_laddr = addr;
 				lp->stats.rx_dropped++;
-				break;
 			}
-			/* provide 16 byte IP header alignment unless DMA requires otherwise */
-			if(SONIC_BUS_SCALE(lp->dma_bitmode) == 2)
-				skb_reserve(new_skb, 2);
-
-			new_laddr = dma_map_single(lp->device, skb_put(new_skb, SONIC_RBSIZE),
-		                               SONIC_RBSIZE, DMA_FROM_DEVICE);
-			if (!new_laddr) {
-				dev_kfree_skb(new_skb);
-				printk(KERN_ERR "%s: Failed to map rx buffer, dropping packet.\n", dev->name);
-				lp->stats.rx_dropped++;
-				break;
-			}
-
-			/* now we have a new skb to replace it, pass the used one up the stack */
-			dma_unmap_single(lp->device, lp->rx_laddr[entry], SONIC_RBSIZE, DMA_FROM_DEVICE);
-			used_skb = lp->rx_skb[i];
-			pkt_len = sonic_rda_get(dev, entry, SONIC_RD_PKTLEN);
-			skb_trim(used_skb, pkt_len);
-			used_skb->protocol = eth_type_trans(used_skb, dev);
-			netif_rx(used_skb);
-			lp->stats.rx_packets++;
-			lp->stats.rx_bytes += pkt_len;
-
-			/* and insert the new skb */
-			lp->rx_laddr[i] = new_laddr;
-			lp->rx_skb[i] = new_skb;
-
-			bufadr_l = (unsigned long)new_laddr & 0xffff;
-			bufadr_h = (unsigned long)new_laddr >> 16;
-			sonic_rra_put(dev, i, SONIC_RR_BUFADR_L, bufadr_l);
-			sonic_rra_put(dev, i, SONIC_RR_BUFADR_H, bufadr_h);
-			/*
-			 * this was the last packet out of the current receive buffer
-			 * give the buffer back to the SONIC
+			/* If RBE is already asserted when RWP advances then
+			 * it's safe to clear RBE after processing this packet.
 			 */
-			lp->cur_rwp += SIZEOF_SONIC_RR * SONIC_BUS_SCALE(lp->dma_bitmode);
-			if (lp->cur_rwp >= lp->rra_end) lp->cur_rwp = lp->rra_laddr & 0xffff;
-			SONIC_WRITE(SONIC_RWP, lp->cur_rwp);
-			if (SONIC_READ(SONIC_ISR) & SONIC_INT_RBE) {
-				netif_dbg(lp, rx_err, dev, "%s: rx buffer exhausted\n",
-					  __func__);
-				SONIC_WRITE(SONIC_ISR, SONIC_INT_RBE); /* clear the flag */
-			}
+			rbe = rbe || SONIC_READ(SONIC_ISR) & SONIC_INT_RBE;
+			sonic_update_rra(dev, lp, addr, new_laddr);
 		}
 		/*
 		 * give back the descriptor
@@ -528,6 +558,9 @@ static void sonic_rx(struct net_device *dev)
 			      sonic_rda_get(dev, lp->eol_rx, SONIC_RD_LINK));
 		lp->eol_rx = prev_entry;
 	}
+
+	if (rbe)
+		SONIC_WRITE(SONIC_ISR, SONIC_INT_RBE);
 	/*
 	 * If any worth-while packets have been received, netif_rx()
 	 * has done a mark_bh(NET_BH) for us and will work on them
@@ -642,15 +675,10 @@ static int sonic_init(struct net_device *dev)
 	}
 
 	/* initialize all RRA registers */
-	lp->rra_end = (lp->rra_laddr + SONIC_NUM_RRS * SIZEOF_SONIC_RR *
-					SONIC_BUS_SCALE(lp->dma_bitmode)) & 0xffff;
-	lp->cur_rwp = (lp->rra_laddr + (SONIC_NUM_RRS - 1) * SIZEOF_SONIC_RR *
-					SONIC_BUS_SCALE(lp->dma_bitmode)) & 0xffff;
-
-	SONIC_WRITE(SONIC_RSA, lp->rra_laddr & 0xffff);
-	SONIC_WRITE(SONIC_REA, lp->rra_end);
-	SONIC_WRITE(SONIC_RRP, lp->rra_laddr & 0xffff);
-	SONIC_WRITE(SONIC_RWP, lp->cur_rwp);
+	SONIC_WRITE(SONIC_RSA, sonic_rr_addr(dev, 0));
+	SONIC_WRITE(SONIC_REA, sonic_rr_addr(dev, SONIC_NUM_RRS));
+	SONIC_WRITE(SONIC_RRP, sonic_rr_addr(dev, 0));
+	SONIC_WRITE(SONIC_RWP, sonic_rr_addr(dev, SONIC_NUM_RRS - 1));
 	SONIC_WRITE(SONIC_URRA, lp->rra_laddr >> 16);
 	SONIC_WRITE(SONIC_EOBC, (SONIC_RBSIZE >> 1) - (lp->dma_bitmode ? 2 : 1));
 
diff --git a/drivers/net/ethernet/natsemi/sonic.h b/drivers/net/ethernet/natsemi/sonic.h
index e6d47e45c5c2..cc2f7b4b77e3 100644
--- a/drivers/net/ethernet/natsemi/sonic.h
+++ b/drivers/net/ethernet/natsemi/sonic.h
@@ -314,8 +314,6 @@ struct sonic_local {
 	u32 rda_laddr;              /* logical DMA address of RDA */
 	dma_addr_t rx_laddr[SONIC_NUM_RRS]; /* logical DMA addresses of rx skbuffs */
 	dma_addr_t tx_laddr[SONIC_NUM_TDS]; /* logical DMA addresses of tx skbuffs */
-	unsigned int rra_end;
-	unsigned int cur_rwp;
 	unsigned int cur_rx;
 	unsigned int cur_tx;           /* first unacked transmit packet */
 	unsigned int eol_rx;
@@ -450,6 +448,22 @@ static inline __u16 sonic_rra_get(struct net_device* dev, int entry,
 			     (entry * SIZEOF_SONIC_RR) + offset);
 }
 
+static inline u16 sonic_rr_addr(struct net_device *dev, int entry)
+{
+	struct sonic_local *lp = netdev_priv(dev);
+
+	return lp->rra_laddr +
+	       entry * SIZEOF_SONIC_RR * SONIC_BUS_SCALE(lp->dma_bitmode);
+}
+
+static inline u16 sonic_rr_entry(struct net_device *dev, u16 addr)
+{
+	struct sonic_local *lp = netdev_priv(dev);
+
+	return (addr - (u16)lp->rra_laddr) / (SIZEOF_SONIC_RR *
+					      SONIC_BUS_SCALE(lp->dma_bitmode));
+}
+
 static const char version[] =
     "sonic.c:v0.92 20.9.98 tsbogend@alpha.franken.de\n";
 
-- 
cgit 


From 3f4b7e6a2be982fd8820a2b54d46dd9c351db899 Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@telegraphics.com.au>
Date: Thu, 23 Jan 2020 09:07:26 +1100
Subject: net/sonic: Quiesce SONIC before re-initializing descriptor memory

Make sure the SONIC's DMA engine is idle before altering the transmit
and receive descriptors. Add a helper for this as it will be needed
again.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Tested-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/natsemi/sonic.c | 25 +++++++++++++++++++++++++
 drivers/net/ethernet/natsemi/sonic.h |  3 +++
 2 files changed, 28 insertions(+)

diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c
index 26848acec63d..42a6b87d8886 100644
--- a/drivers/net/ethernet/natsemi/sonic.c
+++ b/drivers/net/ethernet/natsemi/sonic.c
@@ -116,6 +116,24 @@ static int sonic_open(struct net_device *dev)
 	return 0;
 }
 
+/* Wait for the SONIC to become idle. */
+static void sonic_quiesce(struct net_device *dev, u16 mask)
+{
+	struct sonic_local * __maybe_unused lp = netdev_priv(dev);
+	int i;
+	u16 bits;
+
+	for (i = 0; i < 1000; ++i) {
+		bits = SONIC_READ(SONIC_CMD) & mask;
+		if (!bits)
+			return;
+		if (irqs_disabled() || in_interrupt())
+			udelay(20);
+		else
+			usleep_range(100, 200);
+	}
+	WARN_ONCE(1, "command deadline expired! 0x%04x\n", bits);
+}
 
 /*
  * Close the SONIC device
@@ -132,6 +150,9 @@ static int sonic_close(struct net_device *dev)
 	/*
 	 * stop the SONIC, disable interrupts
 	 */
+	SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS);
+	sonic_quiesce(dev, SONIC_CR_ALL);
+
 	SONIC_WRITE(SONIC_IMR, 0);
 	SONIC_WRITE(SONIC_ISR, 0x7fff);
 	SONIC_WRITE(SONIC_CMD, SONIC_CR_RST);
@@ -171,6 +192,9 @@ static void sonic_tx_timeout(struct net_device *dev)
 	 * put the Sonic into software-reset mode and
 	 * disable all interrupts before releasing DMA buffers
 	 */
+	SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS);
+	sonic_quiesce(dev, SONIC_CR_ALL);
+
 	SONIC_WRITE(SONIC_IMR, 0);
 	SONIC_WRITE(SONIC_ISR, 0x7fff);
 	SONIC_WRITE(SONIC_CMD, SONIC_CR_RST);
@@ -658,6 +682,7 @@ static int sonic_init(struct net_device *dev)
 	 */
 	SONIC_WRITE(SONIC_CMD, 0);
 	SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS);
+	sonic_quiesce(dev, SONIC_CR_ALL);
 
 	/*
 	 * initialize the receive resource area
diff --git a/drivers/net/ethernet/natsemi/sonic.h b/drivers/net/ethernet/natsemi/sonic.h
index cc2f7b4b77e3..1df6d2f06cc4 100644
--- a/drivers/net/ethernet/natsemi/sonic.h
+++ b/drivers/net/ethernet/natsemi/sonic.h
@@ -110,6 +110,9 @@
 #define SONIC_CR_TXP            0x0002
 #define SONIC_CR_HTX            0x0001
 
+#define SONIC_CR_ALL (SONIC_CR_LCAM | SONIC_CR_RRRA | \
+		      SONIC_CR_RXEN | SONIC_CR_TXP)
+
 /*
  * SONIC data configuration bits
  */
-- 
cgit 


From 27e0c31c5f27c1d1a1d9d135c123069f60dcf97b Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@telegraphics.com.au>
Date: Thu, 23 Jan 2020 09:07:26 +1100
Subject: net/sonic: Fix command register usage

There are several issues relating to command register usage during
chip initialization.

Firstly, the SONIC sometimes comes out of software reset with the
Start Timer bit set. This gets logged as,

    macsonic macsonic eth0: sonic_init: status=24, i=101

Avoid this by giving the Stop Timer command earlier than later.

Secondly, the loop that waits for the Read RRA command to complete has
the break condition inverted. That's why the for loop iterates until
its termination condition. Call the helper for this instead.

Finally, give the Receiver Enable command after clearing interrupts,
not before, to avoid the possibility of losing an interrupt.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Tested-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/natsemi/sonic.c | 18 +++---------------
 1 file changed, 3 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c
index 42a6b87d8886..914cec2ccc28 100644
--- a/drivers/net/ethernet/natsemi/sonic.c
+++ b/drivers/net/ethernet/natsemi/sonic.c
@@ -664,7 +664,6 @@ static void sonic_multicast_list(struct net_device *dev)
  */
 static int sonic_init(struct net_device *dev)
 {
-	unsigned int cmd;
 	struct sonic_local *lp = netdev_priv(dev);
 	int i;
 
@@ -681,7 +680,7 @@ static int sonic_init(struct net_device *dev)
 	 * enable interrupts, then completely initialize the SONIC
 	 */
 	SONIC_WRITE(SONIC_CMD, 0);
-	SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS);
+	SONIC_WRITE(SONIC_CMD, SONIC_CR_RXDIS | SONIC_CR_STP);
 	sonic_quiesce(dev, SONIC_CR_ALL);
 
 	/*
@@ -711,14 +710,7 @@ static int sonic_init(struct net_device *dev)
 	netif_dbg(lp, ifup, dev, "%s: issuing RRRA command\n", __func__);
 
 	SONIC_WRITE(SONIC_CMD, SONIC_CR_RRRA);
-	i = 0;
-	while (i++ < 100) {
-		if (SONIC_READ(SONIC_CMD) & SONIC_CR_RRRA)
-			break;
-	}
-
-	netif_dbg(lp, ifup, dev, "%s: status=%x, i=%d\n", __func__,
-		  SONIC_READ(SONIC_CMD), i);
+	sonic_quiesce(dev, SONIC_CR_RRRA);
 
 	/*
 	 * Initialize the receive descriptors so that they
@@ -806,15 +798,11 @@ static int sonic_init(struct net_device *dev)
 	 * enable receiver, disable loopback
 	 * and enable all interrupts
 	 */
-	SONIC_WRITE(SONIC_CMD, SONIC_CR_RXEN | SONIC_CR_STP);
 	SONIC_WRITE(SONIC_RCR, SONIC_RCR_DEFAULT);
 	SONIC_WRITE(SONIC_TCR, SONIC_TCR_DEFAULT);
 	SONIC_WRITE(SONIC_ISR, 0x7fff);
 	SONIC_WRITE(SONIC_IMR, SONIC_IMR_DEFAULT);
-
-	cmd = SONIC_READ(SONIC_CMD);
-	if ((cmd & SONIC_CR_RXEN) == 0 || (cmd & SONIC_CR_STP) == 0)
-		printk(KERN_ERR "sonic_init: failed, status=%x\n", cmd);
+	SONIC_WRITE(SONIC_CMD, SONIC_CR_RXEN);
 
 	netif_dbg(lp, ifup, dev, "%s: new status=%x\n", __func__,
 		  SONIC_READ(SONIC_CMD));
-- 
cgit 


From 772f66421d5aa0b9f256056f513bbc38ac132271 Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@telegraphics.com.au>
Date: Thu, 23 Jan 2020 09:07:26 +1100
Subject: net/sonic: Fix CAM initialization

Section 4.3.1 of the datasheet says,

    This bit [TXP] must not be set if a Load CAM operation is in
    progress (LCAM is set). The SONIC will lock up if both bits are
    set simultaneously.

Testing has shown that the driver sometimes attempts to set LCAM
while TXP is set. Avoid this by waiting for command completion
before and after giving the LCAM command.

After issuing the Load CAM command, poll for !SONIC_CR_LCAM rather than
SONIC_INT_LCD, because the SONIC_CR_TXP bit can't be used until
!SONIC_CR_LCAM.

When in reset mode, take the opportunity to reset the CAM Enable
register.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Tested-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/natsemi/sonic.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c
index 914cec2ccc28..27b6f6585527 100644
--- a/drivers/net/ethernet/natsemi/sonic.c
+++ b/drivers/net/ethernet/natsemi/sonic.c
@@ -634,6 +634,8 @@ static void sonic_multicast_list(struct net_device *dev)
 		    (netdev_mc_count(dev) > 15)) {
 			rcr |= SONIC_RCR_AMC;
 		} else {
+			unsigned long flags;
+
 			netif_dbg(lp, ifup, dev, "%s: mc_count %d\n", __func__,
 				  netdev_mc_count(dev));
 			sonic_set_cam_enable(dev, 1);  /* always enable our own address */
@@ -647,9 +649,14 @@ static void sonic_multicast_list(struct net_device *dev)
 				i++;
 			}
 			SONIC_WRITE(SONIC_CDC, 16);
-			/* issue Load CAM command */
 			SONIC_WRITE(SONIC_CDP, lp->cda_laddr & 0xffff);
+
+			/* LCAM and TXP commands can't be used simultaneously */
+			spin_lock_irqsave(&lp->lock, flags);
+			sonic_quiesce(dev, SONIC_CR_TXP);
 			SONIC_WRITE(SONIC_CMD, SONIC_CR_LCAM);
+			sonic_quiesce(dev, SONIC_CR_LCAM);
+			spin_unlock_irqrestore(&lp->lock, flags);
 		}
 	}
 
@@ -675,6 +682,9 @@ static int sonic_init(struct net_device *dev)
 	SONIC_WRITE(SONIC_ISR, 0x7fff);
 	SONIC_WRITE(SONIC_CMD, SONIC_CR_RST);
 
+	/* While in reset mode, clear CAM Enable register */
+	SONIC_WRITE(SONIC_CE, 0);
+
 	/*
 	 * clear software reset flag, disable receiver, clear and
 	 * enable interrupts, then completely initialize the SONIC
@@ -785,14 +795,7 @@ static int sonic_init(struct net_device *dev)
 	 * load the CAM
 	 */
 	SONIC_WRITE(SONIC_CMD, SONIC_CR_LCAM);
-
-	i = 0;
-	while (i++ < 100) {
-		if (SONIC_READ(SONIC_ISR) & SONIC_INT_LCD)
-			break;
-	}
-	netif_dbg(lp, ifup, dev, "%s: CMD=%x, ISR=%x, i=%d\n", __func__,
-		  SONIC_READ(SONIC_CMD), SONIC_READ(SONIC_ISR), i);
+	sonic_quiesce(dev, SONIC_CR_LCAM);
 
 	/*
 	 * enable receiver, disable loopback
-- 
cgit 


From 686f85d71d095f1d26b807e23b0f0bfd22042c45 Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@telegraphics.com.au>
Date: Thu, 23 Jan 2020 09:07:26 +1100
Subject: net/sonic: Prevent tx watchdog timeout

Section 5.5.3.2 of the datasheet says,

    If FIFO Underrun, Byte Count Mismatch, Excessive Collision, or
    Excessive Deferral (if enabled) errors occur, transmission ceases.

In this situation, the chip asserts a TXER interrupt rather than TXDN.
But the handler for the TXDN is the only way that the transmit queue
gets restarted. Hence, an aborted transmission can result in a watchdog
timeout.

This problem can be reproduced on congested link, as that can result in
excessive transmitter collisions. Another way to reproduce this is with
a FIFO Underrun, which may be caused by DMA latency.

In event of a TXER interrupt, prevent a watchdog timeout by restarting
transmission.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Tested-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/natsemi/sonic.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c
index 27b6f6585527..05e760444a92 100644
--- a/drivers/net/ethernet/natsemi/sonic.c
+++ b/drivers/net/ethernet/natsemi/sonic.c
@@ -415,10 +415,19 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
 			lp->stats.rx_missed_errors += 65536;
 
 		/* transmit error */
-		if (status & SONIC_INT_TXER)
-			if (SONIC_READ(SONIC_TCR) & SONIC_TCR_FU)
-				netif_dbg(lp, tx_err, dev, "%s: tx fifo underrun\n",
-					  __func__);
+		if (status & SONIC_INT_TXER) {
+			u16 tcr = SONIC_READ(SONIC_TCR);
+
+			netif_dbg(lp, tx_err, dev, "%s: TXER intr, TCR %04x\n",
+				  __func__, tcr);
+
+			if (tcr & (SONIC_TCR_EXD | SONIC_TCR_EXC |
+				   SONIC_TCR_FU | SONIC_TCR_BCM)) {
+				/* Aborted transmission. Try again. */
+				netif_stop_queue(dev);
+				SONIC_WRITE(SONIC_CMD, SONIC_CR_TXP);
+			}
+		}
 
 		/* bus retry */
 		if (status & SONIC_INT_BR) {
-- 
cgit 


From 61678d28d4a45ef376f5d02a839cc37509ae9281 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 22 Jan 2020 15:42:02 -0800
Subject: net_sched: fix datalen for ematch

syzbot reported an out-of-bound access in em_nbyte. As initially
analyzed by Eric, this is because em_nbyte sets its own em->datalen
in em_nbyte_change() other than the one specified by user, but this
value gets overwritten later by its caller tcf_em_validate().
We should leave em->datalen untouched to respect their choices.

I audit all the in-tree ematch users, all of those implement
->change() set em->datalen, so we can just avoid setting it twice
in this case.

Reported-and-tested-by: syzbot+5af9a90dad568aa9f611@syzkaller.appspotmail.com
Reported-by: syzbot+2f07903a5b05e7f36410@syzkaller.appspotmail.com
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/ematch.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/ematch.c b/net/sched/ematch.c
index 8f2ad706784d..d0140a92694a 100644
--- a/net/sched/ematch.c
+++ b/net/sched/ematch.c
@@ -263,12 +263,12 @@ static int tcf_em_validate(struct tcf_proto *tp,
 				}
 				em->data = (unsigned long) v;
 			}
+			em->datalen = data_len;
 		}
 	}
 
 	em->matchid = em_hdr->matchid;
 	em->flags = em_hdr->flags;
-	em->datalen = data_len;
 	em->net = net;
 
 	err = 0;
-- 
cgit 


From 959b1825d9ab5081f7446ed3f4329384c7818af7 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 23 Jan 2020 00:14:29 +0000
Subject: i40e: fix spelling mistake "to" -> "too"

There is a spelling mistake in a hw_dbg message. Fix it.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/i40e/i40e_common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index d4055037af89..45b90eb11adb 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1113,7 +1113,7 @@ i40e_status i40e_read_pba_string(struct i40e_hw *hw, u8 *pba_num,
 	 */
 	pba_size--;
 	if (pba_num_size < (((u32)pba_size * 2) + 1)) {
-		hw_dbg(hw, "Buffer to small for PBA data.\n");
+		hw_dbg(hw, "Buffer too small for PBA data.\n");
 		return I40E_ERR_PARAM;
 	}
 
-- 
cgit 


From 971485a0d681954677ec6a7ed990359aceabc06e Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 23 Jan 2020 00:43:28 +0000
Subject: ipvs: fix spelling mistake "to" -> "too"

There is a spelling mistake in a IP_VS_ERR_RL message. Fix it.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netfilter/ipvs/ip_vs_sync.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 8dc892a9dc91..605e0f68f8bd 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1239,7 +1239,7 @@ static void ip_vs_process_message(struct netns_ipvs *ipvs, __u8 *buffer,
 
 			p = msg_end;
 			if (p + sizeof(s->v4) > buffer+buflen) {
-				IP_VS_ERR_RL("BACKUP, Dropping buffer, to small\n");
+				IP_VS_ERR_RL("BACKUP, Dropping buffer, too small\n");
 				return;
 			}
 			s = (union ip_vs_sync_conn *)p;
-- 
cgit 


From 43d88774d138496c88920e2bb012f5fd098ee6ad Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 23 Jan 2020 00:45:55 +0000
Subject: caif_usb: fix spelling mistake "to" -> "too"

There is a spelling mistake in a pr_warn message. Fix it.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/caif/caif_usb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/caif/caif_usb.c b/net/caif/caif_usb.c
index 76bd67891fb3..a0116b9503d9 100644
--- a/net/caif/caif_usb.c
+++ b/net/caif/caif_usb.c
@@ -62,7 +62,7 @@ static int cfusbl_transmit(struct cflayer *layr, struct cfpkt *pkt)
 	hpad = (info->hdr_len + CFUSB_PAD_DESCR_SZ) & (CFUSB_ALIGNMENT - 1);
 
 	if (skb_headroom(skb) < ETH_HLEN + CFUSB_PAD_DESCR_SZ + hpad) {
-		pr_warn("Headroom to small\n");
+		pr_warn("Headroom too small\n");
 		kfree_skb(skb);
 		return -EIO;
 	}
-- 
cgit 


From 4d299f183314aa79131abdfa2c528f8807010ea8 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 23 Jan 2020 09:27:30 +0000
Subject: net/rose: fix spelling mistake "to" -> "too"

There is a spelling mistake in a printk message. Fix it.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rose/af_rose.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 46b8ff24020d..1e8eeb044b07 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1475,7 +1475,7 @@ static int __init rose_proto_init(void)
 	int rc;
 
 	if (rose_ndevs > 0x7FFFFFFF/sizeof(struct net_device *)) {
-		printk(KERN_ERR "ROSE: rose_proto_init - rose_ndevs parameter to large\n");
+		printk(KERN_ERR "ROSE: rose_proto_init - rose_ndevs parameter too large\n");
 		rc = -EINVAL;
 		goto out;
 	}
-- 
cgit 


From 2bec445f9bf35e52e395b971df48d3e1e5dc704a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 22 Jan 2020 21:03:00 -0800
Subject: tcp: do not leave dangling pointers in tp->highest_sack

Latest commit 853697504de0 ("tcp: Fix highest_sack and highest_sack_seq")
apparently allowed syzbot to trigger various crashes in TCP stack [1]

I believe this commit only made things easier for syzbot to find
its way into triggering use-after-frees. But really the bugs
could lead to bad TCP behavior or even plain crashes even for
non malicious peers.

I have audited all calls to tcp_rtx_queue_unlink() and
tcp_rtx_queue_unlink_and_free() and made sure tp->highest_sack would be updated
if we are removing from rtx queue the skb that tp->highest_sack points to.

These updates were missing in three locations :

1) tcp_clean_rtx_queue() [This one seems quite serious,
                          I have no idea why this was not caught earlier]

2) tcp_rtx_queue_purge() [Probably not a big deal for normal operations]

3) tcp_send_synack()     [Probably not a big deal for normal operations]

[1]
BUG: KASAN: use-after-free in tcp_highest_sack_seq include/net/tcp.h:1864 [inline]
BUG: KASAN: use-after-free in tcp_highest_sack_seq include/net/tcp.h:1856 [inline]
BUG: KASAN: use-after-free in tcp_check_sack_reordering+0x33c/0x3a0 net/ipv4/tcp_input.c:891
Read of size 4 at addr ffff8880a488d068 by task ksoftirqd/1/16

CPU: 1 PID: 16 Comm: ksoftirqd/1 Not tainted 5.5.0-rc5-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x197/0x210 lib/dump_stack.c:118
 print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374
 __kasan_report.cold+0x1b/0x41 mm/kasan/report.c:506
 kasan_report+0x12/0x20 mm/kasan/common.c:639
 __asan_report_load4_noabort+0x14/0x20 mm/kasan/generic_report.c:134
 tcp_highest_sack_seq include/net/tcp.h:1864 [inline]
 tcp_highest_sack_seq include/net/tcp.h:1856 [inline]
 tcp_check_sack_reordering+0x33c/0x3a0 net/ipv4/tcp_input.c:891
 tcp_try_undo_partial net/ipv4/tcp_input.c:2730 [inline]
 tcp_fastretrans_alert+0xf74/0x23f0 net/ipv4/tcp_input.c:2847
 tcp_ack+0x2577/0x5bf0 net/ipv4/tcp_input.c:3710
 tcp_rcv_established+0x6dd/0x1e90 net/ipv4/tcp_input.c:5706
 tcp_v4_do_rcv+0x619/0x8d0 net/ipv4/tcp_ipv4.c:1619
 tcp_v4_rcv+0x307f/0x3b40 net/ipv4/tcp_ipv4.c:2001
 ip_protocol_deliver_rcu+0x5a/0x880 net/ipv4/ip_input.c:204
 ip_local_deliver_finish+0x23b/0x380 net/ipv4/ip_input.c:231
 NF_HOOK include/linux/netfilter.h:307 [inline]
 NF_HOOK include/linux/netfilter.h:301 [inline]
 ip_local_deliver+0x1e9/0x520 net/ipv4/ip_input.c:252
 dst_input include/net/dst.h:442 [inline]
 ip_rcv_finish+0x1db/0x2f0 net/ipv4/ip_input.c:428
 NF_HOOK include/linux/netfilter.h:307 [inline]
 NF_HOOK include/linux/netfilter.h:301 [inline]
 ip_rcv+0xe8/0x3f0 net/ipv4/ip_input.c:538
 __netif_receive_skb_one_core+0x113/0x1a0 net/core/dev.c:5148
 __netif_receive_skb+0x2c/0x1d0 net/core/dev.c:5262
 process_backlog+0x206/0x750 net/core/dev.c:6093
 napi_poll net/core/dev.c:6530 [inline]
 net_rx_action+0x508/0x1120 net/core/dev.c:6598
 __do_softirq+0x262/0x98c kernel/softirq.c:292
 run_ksoftirqd kernel/softirq.c:603 [inline]
 run_ksoftirqd+0x8e/0x110 kernel/softirq.c:595
 smpboot_thread_fn+0x6a3/0xa40 kernel/smpboot.c:165
 kthread+0x361/0x430 kernel/kthread.c:255
 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352

Allocated by task 10091:
 save_stack+0x23/0x90 mm/kasan/common.c:72
 set_track mm/kasan/common.c:80 [inline]
 __kasan_kmalloc mm/kasan/common.c:513 [inline]
 __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:486
 kasan_slab_alloc+0xf/0x20 mm/kasan/common.c:521
 slab_post_alloc_hook mm/slab.h:584 [inline]
 slab_alloc_node mm/slab.c:3263 [inline]
 kmem_cache_alloc_node+0x138/0x740 mm/slab.c:3575
 __alloc_skb+0xd5/0x5e0 net/core/skbuff.c:198
 alloc_skb_fclone include/linux/skbuff.h:1099 [inline]
 sk_stream_alloc_skb net/ipv4/tcp.c:875 [inline]
 sk_stream_alloc_skb+0x113/0xc90 net/ipv4/tcp.c:852
 tcp_sendmsg_locked+0xcf9/0x3470 net/ipv4/tcp.c:1282
 tcp_sendmsg+0x30/0x50 net/ipv4/tcp.c:1432
 inet_sendmsg+0x9e/0xe0 net/ipv4/af_inet.c:807
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:672
 __sys_sendto+0x262/0x380 net/socket.c:1998
 __do_sys_sendto net/socket.c:2010 [inline]
 __se_sys_sendto net/socket.c:2006 [inline]
 __x64_sys_sendto+0xe1/0x1a0 net/socket.c:2006
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 10095:
 save_stack+0x23/0x90 mm/kasan/common.c:72
 set_track mm/kasan/common.c:80 [inline]
 kasan_set_free_info mm/kasan/common.c:335 [inline]
 __kasan_slab_free+0x102/0x150 mm/kasan/common.c:474
 kasan_slab_free+0xe/0x10 mm/kasan/common.c:483
 __cache_free mm/slab.c:3426 [inline]
 kmem_cache_free+0x86/0x320 mm/slab.c:3694
 kfree_skbmem+0x178/0x1c0 net/core/skbuff.c:645
 __kfree_skb+0x1e/0x30 net/core/skbuff.c:681
 sk_eat_skb include/net/sock.h:2453 [inline]
 tcp_recvmsg+0x1252/0x2930 net/ipv4/tcp.c:2166
 inet_recvmsg+0x136/0x610 net/ipv4/af_inet.c:838
 sock_recvmsg_nosec net/socket.c:886 [inline]
 sock_recvmsg net/socket.c:904 [inline]
 sock_recvmsg+0xce/0x110 net/socket.c:900
 __sys_recvfrom+0x1ff/0x350 net/socket.c:2055
 __do_sys_recvfrom net/socket.c:2073 [inline]
 __se_sys_recvfrom net/socket.c:2069 [inline]
 __x64_sys_recvfrom+0xe1/0x1a0 net/socket.c:2069
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

The buggy address belongs to the object at ffff8880a488d040
 which belongs to the cache skbuff_fclone_cache of size 456
The buggy address is located 40 bytes inside of
 456-byte region [ffff8880a488d040, ffff8880a488d208)
The buggy address belongs to the page:
page:ffffea0002922340 refcount:1 mapcount:0 mapping:ffff88821b057000 index:0x0
raw: 00fffe0000000200 ffffea00022a5788 ffffea0002624a48 ffff88821b057000
raw: 0000000000000000 ffff8880a488d040 0000000100000006 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff8880a488cf00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff8880a488cf80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff8880a488d000: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb
                                                          ^
 ffff8880a488d080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8880a488d100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

Fixes: 853697504de0 ("tcp: Fix highest_sack and highest_sack_seq")
Fixes: 50895b9de1d3 ("tcp: highest_sack fix")
Fixes: 737ff314563c ("tcp: use sequence distance to detect reordering")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Cambda Zhu <cambda@linux.alibaba.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c        | 1 +
 net/ipv4/tcp_input.c  | 1 +
 net/ipv4/tcp_output.c | 1 +
 3 files changed, 3 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 04273d6aa36b..a7d766e6390e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2524,6 +2524,7 @@ static void tcp_rtx_queue_purge(struct sock *sk)
 {
 	struct rb_node *p = rb_first(&sk->tcp_rtx_queue);
 
+	tcp_sk(sk)->highest_sack = NULL;
 	while (p) {
 		struct sk_buff *skb = rb_to_skb(p);
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5347ab2c9c58..2a976f57f7e7 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3164,6 +3164,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
 			tp->retransmit_skb_hint = NULL;
 		if (unlikely(skb == tp->lost_skb_hint))
 			tp->lost_skb_hint = NULL;
+		tcp_highest_sack_replace(sk, skb, next);
 		tcp_rtx_queue_unlink_and_free(skb, sk);
 	}
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 58c92a7d671c..b62b59b18db9 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3232,6 +3232,7 @@ int tcp_send_synack(struct sock *sk)
 			if (!nskb)
 				return -ENOMEM;
 			INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor);
+			tcp_highest_sack_replace(sk, skb, nskb);
 			tcp_rtx_queue_unlink_and_free(skb, sk);
 			__skb_header_release(nskb);
 			tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb);
-- 
cgit 


From 70a87287c821e9721b62463777f55ba588ac4623 Mon Sep 17 00:00:00 2001
From: Vasily Averin <vvs@virtuozzo.com>
Date: Thu, 23 Jan 2020 10:11:08 +0300
Subject: seq_tab_next() should increase position index

if seq_file .next fuction does not change position index,
read after some lseek can generate unexpected output.

https://bugzilla.kernel.org/show_bug.cgi?id=206283
Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index aca9f7a20a2a..4144c230dc97 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -70,8 +70,7 @@ static void *seq_tab_start(struct seq_file *seq, loff_t *pos)
 static void *seq_tab_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	v = seq_tab_get_idx(seq->private, *pos + 1);
-	if (v)
-		++*pos;
+	++(*pos);
 	return v;
 }
 
-- 
cgit 


From 66018a102f7756cf72db4d2704e1b93969d9d332 Mon Sep 17 00:00:00 2001
From: Vasily Averin <vvs@virtuozzo.com>
Date: Thu, 23 Jan 2020 10:11:13 +0300
Subject: l2t_seq_next should increase position index

if seq_file .next fuction does not change position index,
read after some lseek can generate unexpected output.

https://bugzilla.kernel.org/show_bug.cgi?id=206283
Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/l2t.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
index e9e45006632d..1a16449e9deb 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
@@ -678,8 +678,7 @@ static void *l2t_seq_start(struct seq_file *seq, loff_t *pos)
 static void *l2t_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	v = l2t_get_idx(seq, *pos);
-	if (v)
-		++*pos;
+	++(*pos);
 	return v;
 }
 
-- 
cgit 


From 8bf7092021f283944f0c5f4c364853201c45c611 Mon Sep 17 00:00:00 2001
From: Vasily Averin <vvs@virtuozzo.com>
Date: Thu, 23 Jan 2020 10:11:20 +0300
Subject: vcc_seq_next should increase position index

if seq_file .next fuction does not change position index,
read after some lseek can generate unexpected output.

https://bugzilla.kernel.org/show_bug.cgi?id=206283
Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/atm/proc.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/atm/proc.c b/net/atm/proc.c
index d79221fd4dae..c31896707313 100644
--- a/net/atm/proc.c
+++ b/net/atm/proc.c
@@ -134,8 +134,7 @@ static void vcc_seq_stop(struct seq_file *seq, void *v)
 static void *vcc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	v = vcc_walk(seq, 1);
-	if (v)
-		(*pos)++;
+	(*pos)++;
 	return v;
 }
 
-- 
cgit 


From 1e3f9f073c47bee7c23e77316b07bc12338c5bba Mon Sep 17 00:00:00 2001
From: Vasily Averin <vvs@virtuozzo.com>
Date: Thu, 23 Jan 2020 10:11:28 +0300
Subject: neigh_stat_seq_next() should increase position index

if seq_file .next fuction does not change position index,
read after some lseek can generate unexpected output.

https://bugzilla.kernel.org/show_bug.cgi?id=206283
Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 920784a9b7ff..789a73aa7bd8 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -3290,6 +3290,7 @@ static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 		*pos = cpu+1;
 		return per_cpu_ptr(tbl->stats, cpu);
 	}
+	(*pos)++;
 	return NULL;
 }
 
-- 
cgit 


From a3ea86739f1bc7e121d921842f0f4a8ab1af94d9 Mon Sep 17 00:00:00 2001
From: Vasily Averin <vvs@virtuozzo.com>
Date: Thu, 23 Jan 2020 10:11:35 +0300
Subject: rt_cpu_seq_next should increase position index

if seq_file .next fuction does not change position index,
read after some lseek can generate unexpected output.

https://bugzilla.kernel.org/show_bug.cgi?id=206283
Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 87e979f2b74a..e356ea779227 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -271,6 +271,7 @@ static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 		*pos = cpu+1;
 		return &per_cpu(rt_cache_stat, cpu);
 	}
+	(*pos)++;
 	return NULL;
 
 }
-- 
cgit 


From 4fc427e0515811250647d44de38d87d7b0e0790f Mon Sep 17 00:00:00 2001
From: Vasily Averin <vvs@virtuozzo.com>
Date: Thu, 23 Jan 2020 10:12:06 +0300
Subject: ipv6_route_seq_next should increase position index

if seq_file .next fuction does not change position index,
read after some lseek can generate unexpected output.

https://bugzilla.kernel.org/show_bug.cgi?id=206283
Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_fib.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 7bae6a91b487..cfae0a1529a1 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -2495,14 +2495,13 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	struct net *net = seq_file_net(seq);
 	struct ipv6_route_iter *iter = seq->private;
 
+	++(*pos);
 	if (!v)
 		goto iter_table;
 
 	n = rcu_dereference_bh(((struct fib6_info *)v)->fib6_next);
-	if (n) {
-		++*pos;
+	if (n)
 		return n;
-	}
 
 iter_table:
 	ipv6_route_check_sernum(iter);
@@ -2510,8 +2509,6 @@ iter_table:
 	r = fib6_walk_continue(&iter->w);
 	spin_unlock_bh(&iter->tbl->tb6_lock);
 	if (r > 0) {
-		if (v)
-			++*pos;
 		return iter->w.leaf;
 	} else if (r < 0) {
 		fib6_walker_unlink(net, &iter->w);
-- 
cgit 


From ab658b9fa7a2c467f79eac8b53ea308b8f98113d Mon Sep 17 00:00:00 2001
From: Jiri Wiesner <jwiesner@suse.com>
Date: Sat, 18 Jan 2020 13:10:50 +0100
Subject: netfilter: conntrack: sctp: use distinct states for new SCTP
 connections

The netlink notifications triggered by the INIT and INIT_ACK chunks
for a tracked SCTP association do not include protocol information
for the corresponding connection - SCTP state and verification tags
for the original and reply direction are missing. Since the connection
tracking implementation allows user space programs to receive
notifications about a connection and then create a new connection
based on the values received in a notification, it makes sense that
INIT and INIT_ACK notifications should contain the SCTP state
and verification tags available at the time when a notification
is sent. The missing verification tags cause a newly created
netfilter connection to fail to verify the tags of SCTP packets
when this connection has been created from the values previously
received in an INIT or INIT_ACK notification.

A PROTOINFO event is cached in sctp_packet() when the state
of a connection changes. The CLOSED and COOKIE_WAIT state will
be used for connections that have seen an INIT and INIT_ACK chunk,
respectively. The distinct states will cause a connection state
change in sctp_packet().

Signed-off-by: Jiri Wiesner <jwiesner@suse.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_proto_sctp.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 0399ae8f1188..4f897b14b606 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -114,7 +114,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = {
 	{
 /*	ORIGINAL	*/
 /*                  sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */
-/* init         */ {sCW, sCW, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA},
+/* init         */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA},
 /* init_ack     */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},
 /* abort        */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL},
 /* shutdown     */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS},
@@ -130,7 +130,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = {
 /*	REPLY	*/
 /*                  sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */
 /* init         */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* INIT in sCL Big TODO */
-/* init_ack     */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},
+/* init_ack     */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},
 /* abort        */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL},
 /* shutdown     */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR},
 /* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA},
@@ -316,7 +316,7 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb,
 			ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = sh->vtag;
 		}
 
-		ct->proto.sctp.state = new_state;
+		ct->proto.sctp.state = SCTP_CONNTRACK_NONE;
 	}
 
 	return true;
-- 
cgit 


From c83de17dd6308fb74696923e5245de0e3c427206 Mon Sep 17 00:00:00 2001
From: wenxu <wenxu@ucloud.cn>
Date: Sun, 19 Jan 2020 13:18:30 +0800
Subject: netfilter: nf_tables_offload: fix check the chain offload flag

In the nft_indr_block_cb the chain should check the flag with
NFT_CHAIN_HW_OFFLOAD.

Fixes: 9a32669fecfb ("netfilter: nf_tables_offload: support indr block call")
Signed-off-by: wenxu <wenxu@ucloud.cn>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_offload.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c
index a9ea29afb09f..2bb28483af22 100644
--- a/net/netfilter/nf_tables_offload.c
+++ b/net/netfilter/nf_tables_offload.c
@@ -564,7 +564,7 @@ static void nft_indr_block_cb(struct net_device *dev,
 
 	mutex_lock(&net->nft.commit_mutex);
 	chain = __nft_offload_get_chain(dev);
-	if (chain) {
+	if (chain && chain->flags & NFT_CHAIN_HW_OFFLOAD) {
 		struct nft_base_chain *basechain;
 
 		basechain = nft_base_chain(chain);
-- 
cgit 


From 826035498ec14b77b62a44f0cb6b94d45530db6f Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 21 Jan 2020 16:07:00 +0100
Subject: netfilter: nf_tables: add __nft_chain_type_get()

This new helper function validates that unknown family and chain type
coming from userspace do not trigger an out-of-bound array access. Bail
out in case __nft_chain_type_get() returns NULL from
nft_chain_parse_hook().

Fixes: 9370761c56b6 ("netfilter: nf_tables: convert built-in tables/chains to chain types")
Reported-by: syzbot+156a04714799b1d480bc@syzkaller.appspotmail.com
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 29 +++++++++++++++++++++--------
 1 file changed, 21 insertions(+), 8 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 65f51a2e9c2a..4aa01c1253b1 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -552,15 +552,28 @@ static inline u64 nf_tables_alloc_handle(struct nft_table *table)
 
 static const struct nft_chain_type *chain_type[NFPROTO_NUMPROTO][NFT_CHAIN_T_MAX];
 
+static const struct nft_chain_type *
+__nft_chain_type_get(u8 family, enum nft_chain_types type)
+{
+	if (family >= NFPROTO_NUMPROTO ||
+	    type >= NFT_CHAIN_T_MAX)
+		return NULL;
+
+	return chain_type[family][type];
+}
+
 static const struct nft_chain_type *
 __nf_tables_chain_type_lookup(const struct nlattr *nla, u8 family)
 {
+	const struct nft_chain_type *type;
 	int i;
 
 	for (i = 0; i < NFT_CHAIN_T_MAX; i++) {
-		if (chain_type[family][i] != NULL &&
-		    !nla_strcmp(nla, chain_type[family][i]->name))
-			return chain_type[family][i];
+		type = __nft_chain_type_get(family, i);
+		if (!type)
+			continue;
+		if (!nla_strcmp(nla, type->name))
+			return type;
 	}
 	return NULL;
 }
@@ -1162,11 +1175,8 @@ static void nf_tables_table_destroy(struct nft_ctx *ctx)
 
 void nft_register_chain_type(const struct nft_chain_type *ctype)
 {
-	if (WARN_ON(ctype->family >= NFPROTO_NUMPROTO))
-		return;
-
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	if (WARN_ON(chain_type[ctype->family][ctype->type] != NULL)) {
+	if (WARN_ON(__nft_chain_type_get(ctype->family, ctype->type))) {
 		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 		return;
 	}
@@ -1768,7 +1778,10 @@ static int nft_chain_parse_hook(struct net *net,
 	hook->num = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM]));
 	hook->priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY]));
 
-	type = chain_type[family][NFT_CHAIN_T_DEFAULT];
+	type = __nft_chain_type_get(family, NFT_CHAIN_T_DEFAULT);
+	if (!type)
+		return -EOPNOTSUPP;
+
 	if (nla[NFTA_CHAIN_TYPE]) {
 		type = nf_tables_chain_type_lookup(net, nla[NFTA_CHAIN_TYPE],
 						   family, autoload);
-- 
cgit 


From eb014de4fd418de1a277913cba244e47274fe392 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 21 Jan 2020 16:48:03 +0100
Subject: netfilter: nf_tables: autoload modules from the abort path

This patch introduces a list of pending module requests. This new module
list is composed of nft_module_request objects that contain the module
name and one status field that tells if the module has been already
loaded (the 'done' field).

In the first pass, from the preparation phase, the netlink command finds
that a module is missing on this list. Then, a module request is
allocated and added to this list and nft_request_module() returns
-EAGAIN. This triggers the abort path with the autoload parameter set on
from nfnetlink, request_module() is called and the module request enters
the 'done' state. Since the mutex is released when loading modules from
the abort phase, the module list is zapped so this is iteration occurs
over a local list. Therefore, the request_module() calls happen when
object lists are in consistent state (after fulling aborting the
transaction) and the commit list is empty.

On the second pass, the netlink command will find that it already tried
to load the module, so it does not request it again and
nft_request_module() returns 0. Then, there is a look up to find the
object that the command was missing. If the module was successfully
loaded, the command proceeds normally since it finds the missing object
in place, otherwise -ENOENT is reported to userspace.

This patch also updates nfnetlink to include the reason to enter the
abort phase, which is required for this new autoload module rationale.

Fixes: ec7470b834fe ("netfilter: nf_tables: store transaction list locally while requesting module")
Reported-by: syzbot+29125d208b3dae9a7019@syzkaller.appspotmail.com
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/nfnetlink.h |   2 +-
 include/net/netns/nftables.h        |   1 +
 net/netfilter/nf_tables_api.c       | 126 ++++++++++++++++++++++++------------
 net/netfilter/nfnetlink.c           |   6 +-
 4 files changed, 91 insertions(+), 44 deletions(-)

diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index cf09ab37b45b..851425c3178f 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -31,7 +31,7 @@ struct nfnetlink_subsystem {
 	const struct nfnl_callback *cb;	/* callback for individual types */
 	struct module *owner;
 	int (*commit)(struct net *net, struct sk_buff *skb);
-	int (*abort)(struct net *net, struct sk_buff *skb);
+	int (*abort)(struct net *net, struct sk_buff *skb, bool autoload);
 	void (*cleanup)(struct net *net);
 	bool (*valid_genid)(struct net *net, u32 genid);
 };
diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h
index 286fd960896f..a1a8d45adb42 100644
--- a/include/net/netns/nftables.h
+++ b/include/net/netns/nftables.h
@@ -7,6 +7,7 @@
 struct netns_nftables {
 	struct list_head	tables;
 	struct list_head	commit_list;
+	struct list_head	module_list;
 	struct mutex		commit_mutex;
 	unsigned int		base_seq;
 	u8			gencursor;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 4aa01c1253b1..7e63b481cc86 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -578,35 +578,45 @@ __nf_tables_chain_type_lookup(const struct nlattr *nla, u8 family)
 	return NULL;
 }
 
-/*
- * Loading a module requires dropping mutex that guards the transaction.
- * A different client might race to start a new transaction meanwhile. Zap the
- * list of pending transaction and then restore it once the mutex is grabbed
- * again. Users of this function return EAGAIN which implicitly triggers the
- * transaction abort path to clean up the list of pending transactions.
- */
+struct nft_module_request {
+	struct list_head	list;
+	char			module[MODULE_NAME_LEN];
+	bool			done;
+};
+
 #ifdef CONFIG_MODULES
-static void nft_request_module(struct net *net, const char *fmt, ...)
+static int nft_request_module(struct net *net, const char *fmt, ...)
 {
 	char module_name[MODULE_NAME_LEN];
-	LIST_HEAD(commit_list);
+	struct nft_module_request *req;
 	va_list args;
 	int ret;
 
-	list_splice_init(&net->nft.commit_list, &commit_list);
-
 	va_start(args, fmt);
 	ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args);
 	va_end(args);
 	if (ret >= MODULE_NAME_LEN)
-		return;
+		return 0;
 
-	mutex_unlock(&net->nft.commit_mutex);
-	request_module("%s", module_name);
-	mutex_lock(&net->nft.commit_mutex);
+	list_for_each_entry(req, &net->nft.module_list, list) {
+		if (!strcmp(req->module, module_name)) {
+			if (req->done)
+				return 0;
 
-	WARN_ON_ONCE(!list_empty(&net->nft.commit_list));
-	list_splice(&commit_list, &net->nft.commit_list);
+			/* A request to load this module already exists. */
+			return -EAGAIN;
+		}
+	}
+
+	req = kmalloc(sizeof(*req), GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
+
+	req->done = false;
+	strlcpy(req->module, module_name, MODULE_NAME_LEN);
+	list_add_tail(&req->list, &net->nft.module_list);
+
+	return -EAGAIN;
 }
 #endif
 
@@ -630,10 +640,9 @@ nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla,
 	lockdep_nfnl_nft_mutex_not_held();
 #ifdef CONFIG_MODULES
 	if (autoload) {
-		nft_request_module(net, "nft-chain-%u-%.*s", family,
-				   nla_len(nla), (const char *)nla_data(nla));
-		type = __nf_tables_chain_type_lookup(nla, family);
-		if (type != NULL)
+		if (nft_request_module(net, "nft-chain-%u-%.*s", family,
+				       nla_len(nla),
+				       (const char *)nla_data(nla)) == -EAGAIN)
 			return ERR_PTR(-EAGAIN);
 	}
 #endif
@@ -2341,9 +2350,8 @@ static const struct nft_expr_type *__nft_expr_type_get(u8 family,
 static int nft_expr_type_request_module(struct net *net, u8 family,
 					struct nlattr *nla)
 {
-	nft_request_module(net, "nft-expr-%u-%.*s", family,
-			   nla_len(nla), (char *)nla_data(nla));
-	if (__nft_expr_type_get(family, nla))
+	if (nft_request_module(net, "nft-expr-%u-%.*s", family,
+			       nla_len(nla), (char *)nla_data(nla)) == -EAGAIN)
 		return -EAGAIN;
 
 	return 0;
@@ -2369,9 +2377,9 @@ static const struct nft_expr_type *nft_expr_type_get(struct net *net,
 		if (nft_expr_type_request_module(net, family, nla) == -EAGAIN)
 			return ERR_PTR(-EAGAIN);
 
-		nft_request_module(net, "nft-expr-%.*s",
-				   nla_len(nla), (char *)nla_data(nla));
-		if (__nft_expr_type_get(family, nla))
+		if (nft_request_module(net, "nft-expr-%.*s",
+				       nla_len(nla),
+				       (char *)nla_data(nla)) == -EAGAIN)
 			return ERR_PTR(-EAGAIN);
 	}
 #endif
@@ -2462,9 +2470,10 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx,
 			err = PTR_ERR(ops);
 #ifdef CONFIG_MODULES
 			if (err == -EAGAIN)
-				nft_expr_type_request_module(ctx->net,
-							     ctx->family,
-							     tb[NFTA_EXPR_NAME]);
+				if (nft_expr_type_request_module(ctx->net,
+								 ctx->family,
+								 tb[NFTA_EXPR_NAME]) != -EAGAIN)
+					err = -ENOENT;
 #endif
 			goto err1;
 		}
@@ -3301,8 +3310,7 @@ nft_select_set_ops(const struct nft_ctx *ctx,
 	lockdep_nfnl_nft_mutex_not_held();
 #ifdef CONFIG_MODULES
 	if (list_empty(&nf_tables_set_types)) {
-		nft_request_module(ctx->net, "nft-set");
-		if (!list_empty(&nf_tables_set_types))
+		if (nft_request_module(ctx->net, "nft-set") == -EAGAIN)
 			return ERR_PTR(-EAGAIN);
 	}
 #endif
@@ -5428,8 +5436,7 @@ nft_obj_type_get(struct net *net, u32 objtype)
 	lockdep_nfnl_nft_mutex_not_held();
 #ifdef CONFIG_MODULES
 	if (type == NULL) {
-		nft_request_module(net, "nft-obj-%u", objtype);
-		if (__nft_obj_type_get(objtype))
+		if (nft_request_module(net, "nft-obj-%u", objtype) == -EAGAIN)
 			return ERR_PTR(-EAGAIN);
 	}
 #endif
@@ -6002,8 +6009,7 @@ nft_flowtable_type_get(struct net *net, u8 family)
 	lockdep_nfnl_nft_mutex_not_held();
 #ifdef CONFIG_MODULES
 	if (type == NULL) {
-		nft_request_module(net, "nf-flowtable-%u", family);
-		if (__nft_flowtable_type_get(family))
+		if (nft_request_module(net, "nf-flowtable-%u", family) == -EAGAIN)
 			return ERR_PTR(-EAGAIN);
 	}
 #endif
@@ -7005,6 +7011,18 @@ static void nft_chain_del(struct nft_chain *chain)
 	list_del_rcu(&chain->list);
 }
 
+static void nf_tables_module_autoload_cleanup(struct net *net)
+{
+	struct nft_module_request *req, *next;
+
+	WARN_ON_ONCE(!list_empty(&net->nft.commit_list));
+	list_for_each_entry_safe(req, next, &net->nft.module_list, list) {
+		WARN_ON_ONCE(!req->done);
+		list_del(&req->list);
+		kfree(req);
+	}
+}
+
 static void nf_tables_commit_release(struct net *net)
 {
 	struct nft_trans *trans;
@@ -7017,6 +7035,7 @@ static void nf_tables_commit_release(struct net *net)
 	 * to prevent expensive synchronize_rcu() in commit phase.
 	 */
 	if (list_empty(&net->nft.commit_list)) {
+		nf_tables_module_autoload_cleanup(net);
 		mutex_unlock(&net->nft.commit_mutex);
 		return;
 	}
@@ -7031,6 +7050,7 @@ static void nf_tables_commit_release(struct net *net)
 	list_splice_tail_init(&net->nft.commit_list, &nf_tables_destroy_list);
 	spin_unlock(&nf_tables_destroy_list_lock);
 
+	nf_tables_module_autoload_cleanup(net);
 	mutex_unlock(&net->nft.commit_mutex);
 
 	schedule_work(&trans_destroy_work);
@@ -7222,6 +7242,26 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 	return 0;
 }
 
+static void nf_tables_module_autoload(struct net *net)
+{
+	struct nft_module_request *req, *next;
+	LIST_HEAD(module_list);
+
+	list_splice_init(&net->nft.module_list, &module_list);
+	mutex_unlock(&net->nft.commit_mutex);
+	list_for_each_entry_safe(req, next, &module_list, list) {
+		if (req->done) {
+			list_del(&req->list);
+			kfree(req);
+		} else {
+			request_module("%s", req->module);
+			req->done = true;
+		}
+	}
+	mutex_lock(&net->nft.commit_mutex);
+	list_splice(&module_list, &net->nft.module_list);
+}
+
 static void nf_tables_abort_release(struct nft_trans *trans)
 {
 	switch (trans->msg_type) {
@@ -7251,7 +7291,7 @@ static void nf_tables_abort_release(struct nft_trans *trans)
 	kfree(trans);
 }
 
-static int __nf_tables_abort(struct net *net)
+static int __nf_tables_abort(struct net *net, bool autoload)
 {
 	struct nft_trans *trans, *next;
 	struct nft_trans_elem *te;
@@ -7373,6 +7413,11 @@ static int __nf_tables_abort(struct net *net)
 		nf_tables_abort_release(trans);
 	}
 
+	if (autoload)
+		nf_tables_module_autoload(net);
+	else
+		nf_tables_module_autoload_cleanup(net);
+
 	return 0;
 }
 
@@ -7381,9 +7426,9 @@ static void nf_tables_cleanup(struct net *net)
 	nft_validate_state_update(net, NFT_VALIDATE_SKIP);
 }
 
-static int nf_tables_abort(struct net *net, struct sk_buff *skb)
+static int nf_tables_abort(struct net *net, struct sk_buff *skb, bool autoload)
 {
-	int ret = __nf_tables_abort(net);
+	int ret = __nf_tables_abort(net, autoload);
 
 	mutex_unlock(&net->nft.commit_mutex);
 
@@ -7978,6 +8023,7 @@ static int __net_init nf_tables_init_net(struct net *net)
 {
 	INIT_LIST_HEAD(&net->nft.tables);
 	INIT_LIST_HEAD(&net->nft.commit_list);
+	INIT_LIST_HEAD(&net->nft.module_list);
 	mutex_init(&net->nft.commit_mutex);
 	net->nft.base_seq = 1;
 	net->nft.validate_state = NFT_VALIDATE_SKIP;
@@ -7989,7 +8035,7 @@ static void __net_exit nf_tables_exit_net(struct net *net)
 {
 	mutex_lock(&net->nft.commit_mutex);
 	if (!list_empty(&net->nft.commit_list))
-		__nf_tables_abort(net);
+		__nf_tables_abort(net, false);
 	__nft_release_tables(net);
 	mutex_unlock(&net->nft.commit_mutex);
 	WARN_ON_ONCE(!list_empty(&net->nft.tables));
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 4abbb452cf6c..99127e2d95a8 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -476,7 +476,7 @@ ack:
 	}
 done:
 	if (status & NFNL_BATCH_REPLAY) {
-		ss->abort(net, oskb);
+		ss->abort(net, oskb, true);
 		nfnl_err_reset(&err_list);
 		kfree_skb(skb);
 		module_put(ss->owner);
@@ -487,11 +487,11 @@ done:
 			status |= NFNL_BATCH_REPLAY;
 			goto done;
 		} else if (err) {
-			ss->abort(net, oskb);
+			ss->abort(net, oskb, false);
 			netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL);
 		}
 	} else {
-		ss->abort(net, oskb);
+		ss->abort(net, oskb, false);
 	}
 	if (ss->cleanup)
 		ss->cleanup(net);
-- 
cgit 


From 189c9b1e94539b11c80636bc13e9cf47529e7bba Mon Sep 17 00:00:00 2001
From: Praveen Chaudhary <praveen5582@gmail.com>
Date: Thu, 23 Jan 2020 12:33:28 -0800
Subject: net: Fix skb->csum update in inet_proto_csum_replace16().

skb->csum is updated incorrectly, when manipulation for
NF_NAT_MANIP_SRC\DST is done on IPV6 packet.

Fix:
There is no need to update skb->csum in inet_proto_csum_replace16(),
because update in two fields a.) IPv6 src/dst address and b.) L4 header
checksum cancels each other for skb->csum calculation. Whereas
inet_proto_csum_replace4 function needs to update skb->csum, because
update in 3 fields a.) IPv4 src/dst address, b.) IPv4 Header checksum
and c.) L4 header checksum results in same diff as L4 Header checksum
for skb->csum calculation.

[ pablo@netfilter.org: a few comestic documentation edits ]
Signed-off-by: Praveen Chaudhary <pchaudhary@linkedin.com>
Signed-off-by: Zhenggen Xu <zxu@linkedin.com>
Signed-off-by: Andy Stracner <astracner@linkedin.com>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/core/utils.c | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/net/core/utils.c b/net/core/utils.c
index 6b6e51db9f3b..1f31a39236d5 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -438,6 +438,23 @@ void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb,
 }
 EXPORT_SYMBOL(inet_proto_csum_replace4);
 
+/**
+ * inet_proto_csum_replace16 - update layer 4 header checksum field
+ * @sum: Layer 4 header checksum field
+ * @skb: sk_buff for the packet
+ * @from: old IPv6 address
+ * @to: new IPv6 address
+ * @pseudohdr: True if layer 4 header checksum includes pseudoheader
+ *
+ * Update layer 4 header as per the update in IPv6 src/dst address.
+ *
+ * There is no need to update skb->csum in this function, because update in two
+ * fields a.) IPv6 src/dst address and b.) L4 header checksum cancels each other
+ * for skb->csum calculation. Whereas inet_proto_csum_replace4 function needs to
+ * update skb->csum, because update in 3 fields a.) IPv4 src/dst address,
+ * b.) IPv4 Header checksum and c.) L4 header checksum results in same diff as
+ * L4 Header checksum for skb->csum calculation.
+ */
 void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb,
 			       const __be32 *from, const __be32 *to,
 			       bool pseudohdr)
@@ -449,9 +466,6 @@ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb,
 	if (skb->ip_summed != CHECKSUM_PARTIAL) {
 		*sum = csum_fold(csum_partial(diff, sizeof(diff),
 				 ~csum_unfold(*sum)));
-		if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr)
-			skb->csum = ~csum_partial(diff, sizeof(diff),
-						  ~skb->csum);
 	} else if (pseudohdr)
 		*sum = ~csum_fold(csum_partial(diff, sizeof(diff),
 				  csum_unfold(*sum)));
-- 
cgit 


From 93b8a7ecb7287cc9b0196f12a25b57c2462d11dc Mon Sep 17 00:00:00 2001
From: Paul Blakey <paulb@mellanox.com>
Date: Tue, 31 Dec 2019 17:04:15 +0200
Subject: net/mlx5: Fix lowest FDB pool size

The pool sizes represent the pool sizes in the fw. when we request
a pool size from fw, it will return the next possible group.
We track how many pools the fw has left and start requesting groups
from the big to the small.
When we start request 4k group, which doesn't exists in fw, fw
wants to allocate the next possible size, 64k, but will fail since
its exhausted. The correct smallest pool size in fw is 128 and not 4k.

Fixes: e52c28024008 ("net/mlx5: E-Switch, Add chains and priorities")
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 243a5440867e..b8fe44ea44c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -866,7 +866,7 @@ out:
  */
 #define ESW_SIZE (16 * 1024 * 1024)
 const unsigned int ESW_POOLS[4] = { 4 * 1024 * 1024, 1 * 1024 * 1024,
-				    64 * 1024, 4 * 1024 };
+				    64 * 1024, 128 };
 
 static int
 get_sz_from_pool(struct mlx5_eswitch *esw)
-- 
cgit 


From 505a7f5478062c6cd11e22022d9f1bf64cd8eab3 Mon Sep 17 00:00:00 2001
From: Meir Lichtinger <meirl@mellanox.com>
Date: Thu, 12 Dec 2019 16:09:33 +0200
Subject: net/mlx5: Update the list of the PCI supported devices

Add the upcoming ConnectX-7 device ID.

Fixes: 85327a9c4150 ("net/mlx5: Update the list of the PCI supported devices")
Signed-off-by: Meir Lichtinger <meirl@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index cf7b8da0f010..f554cfddcf4e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1563,6 +1563,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, 0x101d) },			/* ConnectX-6 Dx */
 	{ PCI_VDEVICE(MELLANOX, 0x101e), MLX5_PCI_DEV_IS_VF},	/* ConnectX Family mlx5Gen Virtual Function */
 	{ PCI_VDEVICE(MELLANOX, 0x101f) },			/* ConnectX-6 LX */
+	{ PCI_VDEVICE(MELLANOX, 0x1021) },			/* ConnectX-7 */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d2) },			/* BlueField integrated ConnectX-5 network controller */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF},	/* BlueField integrated ConnectX-5 network controller VF */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d6) },			/* BlueField-2 integrated ConnectX-6 Dx network controller */
-- 
cgit 


From b850a82114df9b0ec1d191dc64eed1f20a772e0f Mon Sep 17 00:00:00 2001
From: Erez Shitrit <erezsh@mellanox.com>
Date: Wed, 8 Jan 2020 14:17:32 +0200
Subject: net/mlx5: DR, Enable counter on non-fwd-dest objects

The current code handles only counters that attached to dest, we still
have the cases where we have counter on non-dest, like over drop etc.

Fixes: 6a48faeeca10 ("net/mlx5: Add direct rule fs_cmd implementation")
Signed-off-by: Hamdan Igbaria <hamdani@mellanox.com>
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/steering/fs_dr.c   | 42 +++++++++++++++-------
 1 file changed, 29 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
index 3d587d0bdbbe..1e32e2443f73 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
@@ -352,26 +352,16 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
 		list_for_each_entry(dst, &fte->node.children, node.list) {
 			enum mlx5_flow_destination_type type = dst->dest_attr.type;
-			u32 id;
 
 			if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
 				err = -ENOSPC;
 				goto free_actions;
 			}
 
-			switch (type) {
-			case MLX5_FLOW_DESTINATION_TYPE_COUNTER:
-				id = dst->dest_attr.counter_id;
+			if (type == MLX5_FLOW_DESTINATION_TYPE_COUNTER)
+				continue;
 
-				tmp_action =
-					mlx5dr_action_create_flow_counter(id);
-				if (!tmp_action) {
-					err = -ENOMEM;
-					goto free_actions;
-				}
-				fs_dr_actions[fs_dr_num_actions++] = tmp_action;
-				actions[num_actions++] = tmp_action;
-				break;
+			switch (type) {
 			case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE:
 				tmp_action = create_ft_action(dev, dst);
 				if (!tmp_action) {
@@ -397,6 +387,32 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 		}
 	}
 
+	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
+		list_for_each_entry(dst, &fte->node.children, node.list) {
+			u32 id;
+
+			if (dst->dest_attr.type !=
+			    MLX5_FLOW_DESTINATION_TYPE_COUNTER)
+				continue;
+
+			if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
+				err = -ENOSPC;
+				goto free_actions;
+			}
+
+			id = dst->dest_attr.counter_id;
+			tmp_action =
+				mlx5dr_action_create_flow_counter(id);
+			if (!tmp_action) {
+				err = -ENOMEM;
+				goto free_actions;
+			}
+
+			fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+			actions[num_actions++] = tmp_action;
+		}
+	}
+
 	params.match_sz = match_sz;
 	params.match_buf = (u64 *)fte->val;
 
-- 
cgit 


From e401a1848be87123a2b2049addbf21138cb47081 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Sun, 12 Jan 2020 13:43:37 +0200
Subject: net/mlx5: E-Switch, Prevent ingress rate configuration of uplink rep

Since the implementation relies on limiting the VF transmit rate to
simulate ingress rate limiting, and since either uplink representor or
ecpf are not associated with a VF, we limit the rate limit configuration
for those ports.

Fixes: fcb64c0f5640 ("net/mlx5: E-Switch, add ingress rate support")
Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 024e1cddfd0e..7e32b9e3667c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -4036,6 +4036,13 @@ static int apply_police_params(struct mlx5e_priv *priv, u32 rate,
 	u32 rate_mbps;
 	int err;
 
+	vport_num = rpriv->rep->vport;
+	if (vport_num >= MLX5_VPORT_ECPF) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Ingress rate limit is supported only for Eswitch ports connected to VFs");
+		return -EOPNOTSUPP;
+	}
+
 	esw = priv->mdev->priv.eswitch;
 	/* rate is given in bytes/sec.
 	 * First convert to bits/sec and then round to the nearest mbit/secs.
@@ -4044,8 +4051,6 @@ static int apply_police_params(struct mlx5e_priv *priv, u32 rate,
 	 * 1 mbit/sec.
 	 */
 	rate_mbps = rate ? max_t(u32, (rate * 8 + 500000) / 1000000, 1) : 0;
-	vport_num = rpriv->rep->vport;
-
 	err = mlx5_esw_modify_vport_rate(esw, vport_num, rate_mbps);
 	if (err)
 		NL_SET_ERR_MSG_MOD(extack, "failed applying action to hardware");
-- 
cgit 


From c0702a4bd41829f05638ec2dab70f6bb8d8010ce Mon Sep 17 00:00:00 2001
From: Erez Shitrit <erezsh@mellanox.com>
Date: Sun, 12 Jan 2020 08:57:59 +0200
Subject: net/mlx5: DR, use non preemptible call to get the current cpu number

Use raw_smp_processor_id instead of smp_processor_id() otherwise we will
get the following trace in debug-kernel:
	BUG: using smp_processor_id() in preemptible [00000000] code: devlink
	caller is dr_create_cq.constprop.2+0x31d/0x970 [mlx5_core]
	Call Trace:
	dump_stack+0x9a/0xf0
	debug_smp_processor_id+0x1f3/0x200
	dr_create_cq.constprop.2+0x31d/0x970
	genl_family_rcv_msg+0x5fd/0x1170
	genl_rcv_msg+0xb8/0x160
	netlink_rcv_skb+0x11e/0x340

Fixes: 297cccebdc5a ("net/mlx5: DR, Expose an internal API to issue RDMA operations")
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
index 51803eef13dd..c7f10d4f8f8d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /* Copyright (c) 2019 Mellanox Technologies. */
 
+#include <linux/smp.h>
 #include "dr_types.h"
 
 #define QUEUE_SIZE 128
@@ -729,7 +730,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
 	if (!in)
 		goto err_cqwq;
 
-	vector = smp_processor_id() % mlx5_comp_vectors_count(mdev);
+	vector = raw_smp_processor_id() % mlx5_comp_vectors_count(mdev);
 	err = mlx5_vector2eqn(mdev, vector, &eqn, &irqn);
 	if (err) {
 		kvfree(in);
-- 
cgit 


From 3b83b6c2e024d85b770ddb1e19a513b5d7587f6f Mon Sep 17 00:00:00 2001
From: Dmytro Linkin <dmitrolin@mellanox.com>
Date: Mon, 13 Jan 2020 13:46:13 +0200
Subject: net/mlx5e: Clear VF config when switching modes

Currently VF in LEGACY mode are not able to go up. Also in OFFLOADS
mode, when switching to it first time, VF can go up independently to
his representor, which is not expected.
Perform clearing of VF config when switching modes and set link state
to AUTO as default value. Also, when switching to OFFLOADS mode set
link state to DOWN, which allow VF link state to be controlled by its
REP.

Fixes: 1ab2068a4c66 ("net/mlx5: Implement vports admin state backup/restore")
Fixes: 556b9d16d3f5 ("net/mlx5: Clear VF's configuration on disabling SRIOV")
Signed-off-by: Dmytro Linkin <dmitrolin@mellanox.com>
Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c          |  4 +++-
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 11 ++++++++---
 2 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 2c965ad0d744..3df3604e8929 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1928,8 +1928,10 @@ static void mlx5_eswitch_clear_vf_vports_info(struct mlx5_eswitch *esw)
 	struct mlx5_vport *vport;
 	int i;
 
-	mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs)
+	mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) {
 		memset(&vport->info, 0, sizeof(vport->info));
+		vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO;
+	}
 }
 
 /* Public E-Switch API */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index b8fe44ea44c3..3e6412783078 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1377,7 +1377,7 @@ static int esw_offloads_start(struct mlx5_eswitch *esw,
 		return -EINVAL;
 	}
 
-	mlx5_eswitch_disable(esw, false);
+	mlx5_eswitch_disable(esw, true);
 	mlx5_eswitch_update_num_of_vfs(esw, esw->dev->priv.sriov.num_vfs);
 	err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_OFFLOADS);
 	if (err) {
@@ -2220,7 +2220,8 @@ int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type
 
 int esw_offloads_enable(struct mlx5_eswitch *esw)
 {
-	int err;
+	struct mlx5_vport *vport;
+	int err, i;
 
 	if (MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat) &&
 	    MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, decap))
@@ -2237,6 +2238,10 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 	if (err)
 		goto err_vport_metadata;
 
+	/* Representor will control the vport link state */
+	mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs)
+		vport->info.link_state = MLX5_VPORT_ADMIN_STATE_DOWN;
+
 	err = mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_VPORT_UC_ADDR_CHANGE);
 	if (err)
 		goto err_vports;
@@ -2266,7 +2271,7 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw,
 {
 	int err, err1;
 
-	mlx5_eswitch_disable(esw, false);
+	mlx5_eswitch_disable(esw, true);
 	err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_LEGACY);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy");
-- 
cgit 


From ffbd9ca94e2ebbfe802d4b28bab5ba19818de853 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Sun, 12 Jan 2020 16:22:14 +0200
Subject: net/mlx5e: kTLS, Fix corner-case checks in TX resync flow

There are the following cases:

1. Packet ends before start marker: bypass offload.
2. Packet starts before start marker and ends after it: drop,
   not supported, breaks contract with kernel.
3. packet ends before tls record info starts: drop,
   this packet was already acknowledged and its record info
   was released.

Add the above as comment in code.

Mind possible wraparounds of the TCP seq, replace the simple comparison
with a call to the TCP before() method.

In addition, remove logic that handles negative sync_len values,
as it became impossible.

Fixes: d2ead1f360e8 ("net/mlx5e: Add kTLS TX HW offload support")
Fixes: 46a3ea98074e ("net/mlx5e: kTLS, Enhance TX resync flow")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c | 33 +++++++++++++---------
 1 file changed, 19 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index 778dab1af8fc..8dbb92176bd7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -180,7 +180,7 @@ mlx5e_ktls_tx_post_param_wqes(struct mlx5e_txqsq *sq,
 
 struct tx_sync_info {
 	u64 rcd_sn;
-	s32 sync_len;
+	u32 sync_len;
 	int nr_frags;
 	skb_frag_t frags[MAX_SKB_FRAGS];
 };
@@ -193,13 +193,14 @@ enum mlx5e_ktls_sync_retval {
 
 static enum mlx5e_ktls_sync_retval
 tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx,
-		 u32 tcp_seq, struct tx_sync_info *info)
+		 u32 tcp_seq, int datalen, struct tx_sync_info *info)
 {
 	struct tls_offload_context_tx *tx_ctx = priv_tx->tx_ctx;
 	enum mlx5e_ktls_sync_retval ret = MLX5E_KTLS_SYNC_DONE;
 	struct tls_record_info *record;
 	int remaining, i = 0;
 	unsigned long flags;
+	bool ends_before;
 
 	spin_lock_irqsave(&tx_ctx->lock, flags);
 	record = tls_get_record(tx_ctx, tcp_seq, &info->rcd_sn);
@@ -209,9 +210,21 @@ tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx,
 		goto out;
 	}
 
-	if (unlikely(tcp_seq < tls_record_start_seq(record))) {
-		ret = tls_record_is_start_marker(record) ?
-			MLX5E_KTLS_SYNC_SKIP_NO_DATA : MLX5E_KTLS_SYNC_FAIL;
+	/* There are the following cases:
+	 * 1. packet ends before start marker: bypass offload.
+	 * 2. packet starts before start marker and ends after it: drop,
+	 *    not supported, breaks contract with kernel.
+	 * 3. packet ends before tls record info starts: drop,
+	 *    this packet was already acknowledged and its record info
+	 *    was released.
+	 */
+	ends_before = before(tcp_seq + datalen, tls_record_start_seq(record));
+
+	if (unlikely(tls_record_is_start_marker(record))) {
+		ret = ends_before ? MLX5E_KTLS_SYNC_SKIP_NO_DATA : MLX5E_KTLS_SYNC_FAIL;
+		goto out;
+	} else if (ends_before) {
+		ret = MLX5E_KTLS_SYNC_FAIL;
 		goto out;
 	}
 
@@ -337,7 +350,7 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx,
 	u8 num_wqebbs;
 	int i = 0;
 
-	ret = tx_sync_info_get(priv_tx, seq, &info);
+	ret = tx_sync_info_get(priv_tx, seq, datalen, &info);
 	if (unlikely(ret != MLX5E_KTLS_SYNC_DONE)) {
 		if (ret == MLX5E_KTLS_SYNC_SKIP_NO_DATA) {
 			stats->tls_skip_no_sync_data++;
@@ -351,14 +364,6 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx,
 		goto err_out;
 	}
 
-	if (unlikely(info.sync_len < 0)) {
-		if (likely(datalen <= -info.sync_len))
-			return MLX5E_KTLS_SYNC_DONE;
-
-		stats->tls_drop_bypass_req++;
-		goto err_out;
-	}
-
 	stats->tls_ooo++;
 
 	tx_post_resync_params(sq, priv_tx, info.rcd_sn);
-- 
cgit 


From 1e92899791358dba94a9db7cc3b6004636b5a2f6 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Mon, 13 Jan 2020 14:46:09 +0200
Subject: net/mlx5e: kTLS, Remove redundant posts in TX resync flow

The call to tx_post_resync_params() is done earlier in the flow,
the post of the control WQEs is unnecessarily repeated. Remove it.

Fixes: 700ec4974240 ("net/mlx5e: kTLS, Fix missing SQ edge fill")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index 8dbb92176bd7..592e921aa167 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -383,8 +383,6 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx,
 	if (unlikely(contig_wqebbs_room < num_wqebbs))
 		mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
 
-	tx_post_resync_params(sq, priv_tx, info.rcd_sn);
-
 	for (; i < info.nr_frags; i++) {
 		unsigned int orig_fsz, frag_offset = 0, n = 0;
 		skb_frag_t *f = &info.frags[i];
-- 
cgit 


From 342508c1c7540e281fd36151c175ba5ff954a99f Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Mon, 20 Jan 2020 13:42:00 +0200
Subject: net/mlx5e: kTLS, Do not send decrypted-marked SKBs via non-accel path

When TCP out-of-order is identified (unexpected tcp seq mismatch), driver
analyzes the packet and decides what handling should it get:
1. go to accelerated path (to be encrypted in HW),
2. go to regular xmit path (send w/o encryption),
3. drop.

Packets marked with skb->decrypted by the TLS stack in the TX flow skips
SW encryption, and rely on the HW offload.
Verify that such packets are never sent un-encrypted on the wire.
Add a WARN to catch such bugs, and prefer dropping the packet in these cases.

Fixes: 46a3ea98074e ("net/mlx5e: kTLS, Enhance TX resync flow")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index 592e921aa167..f260dd96873b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -458,12 +458,18 @@ struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev,
 		enum mlx5e_ktls_sync_retval ret =
 			mlx5e_ktls_tx_handle_ooo(priv_tx, sq, datalen, seq);
 
-		if (likely(ret == MLX5E_KTLS_SYNC_DONE))
+		switch (ret) {
+		case MLX5E_KTLS_SYNC_DONE:
 			*wqe = mlx5e_sq_fetch_wqe(sq, sizeof(**wqe), pi);
-		else if (ret == MLX5E_KTLS_SYNC_FAIL)
+			break;
+		case MLX5E_KTLS_SYNC_SKIP_NO_DATA:
+			if (likely(!skb->decrypted))
+				goto out;
+			WARN_ON_ONCE(1);
+			/* fall-through */
+		default: /* MLX5E_KTLS_SYNC_FAIL */
 			goto err_out;
-		else /* ret == MLX5E_KTLS_SYNC_SKIP_NO_DATA */
-			goto out;
+		}
 	}
 
 	priv_tx->expected_seq = seq + datalen;
-- 
cgit 


From b9f0b2f634c0765999bec5547bc7a4ac08fda3ff Mon Sep 17 00:00:00 2001
From: Ajay Gupta <ajayg@nvidia.com>
Date: Wed, 22 Jan 2020 17:16:35 -0800
Subject: net: stmmac: platform: fix probe for ACPI devices

Use generic device API to get phy mode to fix probe failure
with ACPI based devices.

Signed-off-by: Ajay Gupta <ajayg@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 4775f49d7f3b..d10ac54bf385 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -412,9 +412,9 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
 		*mac = NULL;
 	}
 
-	rc = of_get_phy_mode(np, &plat->phy_interface);
-	if (rc)
-		return ERR_PTR(rc);
+	plat->phy_interface = device_get_phy_mode(&pdev->dev);
+	if (plat->phy_interface < 0)
+		return ERR_PTR(plat->phy_interface);
 
 	plat->interface = stmmac_of_get_mac_mode(np);
 	if (plat->interface < 0)
-- 
cgit 


From 61b1f2aff41141cd39686285c9b290a07e1e3051 Mon Sep 17 00:00:00 2001
From: Jon Maloy <jmaloy@redhat.com>
Date: Thu, 23 Jan 2020 10:09:39 -0500
Subject: tipc: change maintainer email address

Reflecting new realities.

Signed-off-by: Jon Maloy <jmaloy@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index b6476496a135..56765f542244 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16603,7 +16603,7 @@ F:	kernel/time/ntp.c
 F:	tools/testing/selftests/timers/
 
 TIPC NETWORK LAYER
-M:	Jon Maloy <jon.maloy@ericsson.com>
+M:	Jon Maloy <jmaloy@redhat.com>
 M:	Ying Xue <ying.xue@windriver.com>
 L:	netdev@vger.kernel.org (core kernel code)
 L:	tipc-discussion@lists.sourceforge.net (user apps, general discussion)
-- 
cgit 


From 148965df1a990af98b2c84092c2a2274c7489284 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 23 Jan 2020 09:49:34 -0800
Subject: net: bcmgenet: Use netif_tx_napi_add() for TX NAPI

Before commit 7587935cfa11 ("net: bcmgenet: move NAPI initialization to
ring initialization") moved the code, this used to be
netif_tx_napi_add(), but we lost that small semantic change in the
process, restore that.

Fixes: 7587935cfa11 ("net: bcmgenet: move NAPI initialization to ring initialization")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Doug Berger <opendmb@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 120fa05a39ff..0a8624be44a9 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2164,8 +2164,8 @@ static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv,
 				  DMA_END_ADDR);
 
 	/* Initialize Tx NAPI */
-	netif_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll,
-		       NAPI_POLL_WEIGHT);
+	netif_tx_napi_add(priv->dev, &ring->napi, bcmgenet_tx_poll,
+			  NAPI_POLL_WEIGHT);
 }
 
 /* Initialize a RDMA ring */
-- 
cgit 


From 3546d8f1bbe992488ed91592cf6bf76e7114791a Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Fri, 24 Jan 2020 20:41:44 +1100
Subject: net: cxgb3_main: Add CAP_NET_ADMIN check to CHELSIO_GET_MEM

The cxgb3 driver for "Chelsio T3-based gigabit and 10Gb Ethernet
adapters" implements a custom ioctl as SIOCCHIOCTL/SIOCDEVPRIVATE in
cxgb_extension_ioctl().

One of the subcommands of the ioctl is CHELSIO_GET_MEM, which appears
to read memory directly out of the adapter and return it to userspace.
It's not entirely clear what the contents of the adapter memory
contains, but the assumption is that it shouldn't be accessible to all
users.

So add a CAP_NET_ADMIN check to the CHELSIO_GET_MEM case. Put it after
the is_offload() check, which matches two of the other subcommands in
the same function which also check for is_offload() and CAP_NET_ADMIN.

Found by Ilja by code inspection, not tested as I don't have the
required hardware.

Reported-by: Ilja Van Sprundel <ivansprundel@ioactive.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index 58f89f6a040f..97ff8608f0ab 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -2448,6 +2448,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr)
 
 		if (!is_offload(adapter))
 			return -EOPNOTSUPP;
+		if (!capable(CAP_NET_ADMIN))
+			return -EPERM;
 		if (!(adapter->flags & FULL_INIT_DONE))
 			return -EIO;	/* need the memory controllers */
 		if (copy_from_user(&t, useraddr, sizeof(t)))
-- 
cgit 


From fa865ba183d61c1ec8cbcab8573159c3b72b89a4 Mon Sep 17 00:00:00 2001
From: Wenwen Wang <wenwen@cs.uga.edu>
Date: Sat, 25 Jan 2020 14:33:29 +0000
Subject: firestream: fix memory leaks

In fs_open(), 'vcc' is allocated through kmalloc() and assigned to
'atm_vcc->dev_data.' In the following execution, if an error occurs, e.g.,
there is no more free channel, an error code EBUSY or ENOMEM will be
returned. However, 'vcc' is not deallocated, leading to memory leaks. Note
that, in normal cases where fs_open() returns 0, 'vcc' will be deallocated
in fs_close(). But, if fs_open() fails, there is no guarantee that
fs_close() will be invoked.

To fix this issue, deallocate 'vcc' before the error code is returned.

Signed-off-by: Wenwen Wang <wenwen@cs.uga.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/atm/firestream.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c
index aad00d2b28f5..cc87004d5e2d 100644
--- a/drivers/atm/firestream.c
+++ b/drivers/atm/firestream.c
@@ -912,6 +912,7 @@ static int fs_open(struct atm_vcc *atm_vcc)
 			}
 			if (!to) {
 				printk ("No more free channels for FS50..\n");
+				kfree(vcc);
 				return -EBUSY;
 			}
 			vcc->channo = dev->channo;
@@ -922,6 +923,7 @@ static int fs_open(struct atm_vcc *atm_vcc)
 			if (((DO_DIRECTION(rxtp) && dev->atm_vccs[vcc->channo])) ||
 			    ( DO_DIRECTION(txtp) && test_bit (vcc->channo, dev->tx_inuse))) {
 				printk ("Channel is in use for FS155.\n");
+				kfree(vcc);
 				return -EBUSY;
 			}
 		}
@@ -935,6 +937,7 @@ static int fs_open(struct atm_vcc *atm_vcc)
 			    tc, sizeof (struct fs_transmit_config));
 		if (!tc) {
 			fs_dprintk (FS_DEBUG_OPEN, "fs: can't alloc transmit_config.\n");
+			kfree(vcc);
 			return -ENOMEM;
 		}
 
-- 
cgit