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

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

From: Anna-Maria Gleixner anna-maria@linutronix.de

commit 48d0c9becc7f3c66874c100c126459a9da0fdced upstream.

The POSIX specification defines that relative CLOCK_REALTIME timers are not affected by clock modifications. Those timers have to use CLOCK_MONOTONIC to ensure POSIX compliance.

The introduction of the additional HRTIMER_MODE_PINNED mode broke this requirement for pinned timers.

There is no user space visible impact because user space timers are not using pinned mode, but for consistency reasons this needs to be fixed.

Check whether the mode has the HRTIMER_MODE_REL bit set instead of comparing with HRTIMER_MODE_ABS.

Signed-off-by: Anna-Maria Gleixner anna-maria@linutronix.de Cc: Christoph Hellwig hch@lst.de Cc: John Stultz john.stultz@linaro.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Cc: keescook@chromium.org Fixes: 597d0275736d ("timers: Framework for identifying pinned timers") Link: http://lkml.kernel.org/r/20171221104205.7269-7-anna-maria@linutronix.de Signed-off-by: Ingo Molnar mingo@kernel.org Cc: Mike Galbraith efault@gmx.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- kernel/time/hrtimer.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

--- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1106,7 +1106,12 @@ static void __hrtimer_init(struct hrtime

cpu_base = raw_cpu_ptr(&hrtimer_bases);

- if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS) + /* + * POSIX magic: Relative CLOCK_REALTIME timers are not affected by + * clock modifications, so they needs to become CLOCK_MONOTONIC to + * ensure POSIX compliance. + */ + if (clock_id == CLOCK_REALTIME && mode & HRTIMER_MODE_REL) clock_id = CLOCK_MONOTONIC;

base = hrtimer_clockid_to_base(clock_id);

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

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

From: Christophe JAILLET christophe.jaillet@wanadoo.fr

[ Upstream commit 1f704fd0d14043e76e80f6b8b2251b9b2cedcca6 ]

A semaphore is acquired before this check, so we must release it before leaving.

Link: http://lkml.kernel.org/r/20171211211009.4971-1-christophe.jaillet@wanadoo.fr Fixes: b7f0554a56f2 ("mm: fail get_vaddr_frames() for filesystem-dax mappings") Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr Acked-by: Michal Hocko mhocko@suse.com Cc: Dan Williams dan.j.williams@intel.com Cc: Christian Borntraeger borntraeger@de.ibm.com Cc: David Sterba dsterba@suse.com Cc: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/frame_vector.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/mm/frame_vector.c +++ b/mm/frame_vector.c @@ -62,8 +62,10 @@ int get_vaddr_frames(unsigned long start * get_user_pages_longterm() and disallow it for filesystem-dax * mappings. */ - if (vma_is_fsdax(vma)) - return -EOPNOTSUPP; + if (vma_is_fsdax(vma)) { + ret = -EOPNOTSUPP; + goto out; + }

if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) { vec->got_ref = true;

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

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

From: Andreas Platschek andreas.platschek@opentech.at

[ Upstream commit 2610acf46b9ed528ec2cacd717bc9d354e452b73 ]

Previously enabled clks are only disabled if clk_prepare_enable() fails. However, there are other error paths were the previously enabled clocks are not disabled.

To fix the problem, fsl_disable_clocks() now takes the number of clocks that shall be disabled + unprepared. For existing calls were all clocks were already successfully prepared + enabled, DMAMUX_NR is passed to disable + unprepare all clocks.

In error paths were only some clocks were successfully prepared + enabled the loop counter is passed, in order to disable + unprepare all successfully prepared + enabled clocks.

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

Signed-off-by: Andreas Platschek andreas.platschek@opentech.at Signed-off-by: Vinod Koul vinod.koul@intel.com Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/dma/fsl-edma.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-)

--- a/drivers/dma/fsl-edma.c +++ b/drivers/dma/fsl-edma.c @@ -863,11 +863,11 @@ static void fsl_edma_irq_exit( } }

-static void fsl_disable_clocks(struct fsl_edma_engine *fsl_edma) +static void fsl_disable_clocks(struct fsl_edma_engine *fsl_edma, int nr_clocks) { int i;

- for (i = 0; i < DMAMUX_NR; i++) + for (i = 0; i < nr_clocks; i++) clk_disable_unprepare(fsl_edma->muxclk[i]); }

@@ -904,25 +904,25 @@ static int fsl_edma_probe(struct platfor

res = platform_get_resource(pdev, IORESOURCE_MEM, 1 + i); fsl_edma->muxbase[i] = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(fsl_edma->muxbase[i])) + if (IS_ERR(fsl_edma->muxbase[i])) { + /* on error: disable all previously enabled clks */ + fsl_disable_clocks(fsl_edma, i); return PTR_ERR(fsl_edma->muxbase[i]); + }

sprintf(clkname, "dmamux%d", i); fsl_edma->muxclk[i] = devm_clk_get(&pdev->dev, clkname); if (IS_ERR(fsl_edma->muxclk[i])) { dev_err(&pdev->dev, "Missing DMAMUX block clock.\n"); + /* on error: disable all previously enabled clks */ + fsl_disable_clocks(fsl_edma, i); return PTR_ERR(fsl_edma->muxclk[i]); }

ret = clk_prepare_enable(fsl_edma->muxclk[i]); - if (ret) { - /* disable only clks which were enabled on error */ - for (; i >= 0; i--) - clk_disable_unprepare(fsl_edma->muxclk[i]); - - dev_err(&pdev->dev, "DMAMUX clk block failed.\n"); - return ret; - } + if (ret) + /* on error: disable all previously enabled clks */ + fsl_disable_clocks(fsl_edma, i);

}

@@ -976,7 +976,7 @@ static int fsl_edma_probe(struct platfor if (ret) { dev_err(&pdev->dev, "Can't register Freescale eDMA engine. (%d)\n", ret); - fsl_disable_clocks(fsl_edma); + fsl_disable_clocks(fsl_edma, DMAMUX_NR); return ret; }

@@ -985,7 +985,7 @@ static int fsl_edma_probe(struct platfor dev_err(&pdev->dev, "Can't register Freescale eDMA of_dma. (%d)\n", ret); dma_async_device_unregister(&fsl_edma->dma_dev); - fsl_disable_clocks(fsl_edma); + fsl_disable_clocks(fsl_edma, DMAMUX_NR); return ret; }

@@ -1015,7 +1015,7 @@ static int fsl_edma_remove(struct platfo fsl_edma_cleanup_vchan(&fsl_edma->dma_dev); of_dma_controller_free(np); dma_async_device_unregister(&fsl_edma->dma_dev); - fsl_disable_clocks(fsl_edma); + fsl_disable_clocks(fsl_edma, DMAMUX_NR);

return 0; }

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

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

From: James Smart jsmart2021@gmail.com

[ Upstream commit 4596e752db02d47038cd7c965419789ab15d1985 ]

There are two put references in the failure case of initial create_association. The first put actually frees the controller, thus the second put references freed memory.

Remove the unnecessary 2nd put.

Signed-off-by: James Smart james.smart@broadcom.com Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/nvme/host/fc.c | 1 - 1 file changed, 1 deletion(-)

--- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2876,7 +2876,6 @@ nvme_fc_init_ctrl(struct device *dev, st

/* initiate nvme ctrl ref counting teardown */ nvme_uninit_ctrl(&ctrl->ctrl); - nvme_put_ctrl(&ctrl->ctrl);

/* Remove core ctrl ref. */ nvme_put_ctrl(&ctrl->ctrl);

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

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

From: Igor Russkikh igor.russkikh@aquantia.com

[ Upstream commit e4d02ca04c6d48ab2226342a1c4ed54f1dbb72bd ]

Different hardware device Ids correspond to different maximum speed available. Extra checks were added for devices D108 and D109 to remove unsupported speeds from these device capabilities list.

Signed-off-by: Igor Russkikh igor.russkikh@aquantia.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/aquantia/atlantic/aq_hw.h | 4 +++- drivers/net/ethernet/aquantia/atlantic/aq_nic.c | 7 ++++--- drivers/net/ethernet/aquantia/atlantic/aq_nic.h | 2 +- drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c | 5 +++-- drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c | 13 ++++++++++++- drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c | 13 ++++++++++++- 6 files changed, 35 insertions(+), 9 deletions(-)

--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h @@ -85,7 +85,9 @@ struct aq_hw_ops { void (*destroy)(struct aq_hw_s *self);

int (*get_hw_caps)(struct aq_hw_s *self, - struct aq_hw_caps_s *aq_hw_caps); + struct aq_hw_caps_s *aq_hw_caps, + unsigned short device, + unsigned short subsystem_device);

int (*hw_ring_tx_xmit)(struct aq_hw_s *self, struct aq_ring_s *aq_ring, unsigned int frags); --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -222,7 +222,7 @@ static struct net_device *aq_nic_ndev_al

struct aq_nic_s *aq_nic_alloc_cold(const struct net_device_ops *ndev_ops, const struct ethtool_ops *et_ops, - struct device *dev, + struct pci_dev *pdev, struct aq_pci_func_s *aq_pci_func, unsigned int port, const struct aq_hw_ops *aq_hw_ops) @@ -242,7 +242,7 @@ struct aq_nic_s *aq_nic_alloc_cold(const ndev->netdev_ops = ndev_ops; ndev->ethtool_ops = et_ops;

- SET_NETDEV_DEV(ndev, dev); + SET_NETDEV_DEV(ndev, &pdev->dev);

ndev->if_port = port; self->ndev = ndev; @@ -254,7 +254,8 @@ struct aq_nic_s *aq_nic_alloc_cold(const

self->aq_hw = self->aq_hw_ops.create(aq_pci_func, self->port, &self->aq_hw_ops); - err = self->aq_hw_ops.get_hw_caps(self->aq_hw, &self->aq_hw_caps); + err = self->aq_hw_ops.get_hw_caps(self->aq_hw, &self->aq_hw_caps, + pdev->device, pdev->subsystem_device); if (err < 0) goto err_exit;

--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h @@ -71,7 +71,7 @@ struct aq_nic_cfg_s {

struct aq_nic_s *aq_nic_alloc_cold(const struct net_device_ops *ndev_ops, const struct ethtool_ops *et_ops, - struct device *dev, + struct pci_dev *pdev, struct aq_pci_func_s *aq_pci_func, unsigned int port, const struct aq_hw_ops *aq_hw_ops); --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -51,7 +51,8 @@ struct aq_pci_func_s *aq_pci_func_alloc( pci_set_drvdata(pdev, self); self->pdev = pdev;

- err = aq_hw_ops->get_hw_caps(NULL, &self->aq_hw_caps); + err = aq_hw_ops->get_hw_caps(NULL, &self->aq_hw_caps, pdev->device, + pdev->subsystem_device); if (err < 0) goto err_exit;

@@ -59,7 +60,7 @@ struct aq_pci_func_s *aq_pci_func_alloc(

for (port = 0; port < self->ports; ++port) { struct aq_nic_s *aq_nic = aq_nic_alloc_cold(ndev_ops, eth_ops, - &pdev->dev, self, + pdev, self, port, aq_hw_ops);

if (!aq_nic) { --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c @@ -18,9 +18,20 @@ #include "hw_atl_a0_internal.h"

static int hw_atl_a0_get_hw_caps(struct aq_hw_s *self, - struct aq_hw_caps_s *aq_hw_caps) + struct aq_hw_caps_s *aq_hw_caps, + unsigned short device, + unsigned short subsystem_device) { memcpy(aq_hw_caps, &hw_atl_a0_hw_caps_, sizeof(*aq_hw_caps)); + + if (device == HW_ATL_DEVICE_ID_D108 && subsystem_device == 0x0001) + aq_hw_caps->link_speed_msk &= ~HW_ATL_A0_RATE_10G; + + if (device == HW_ATL_DEVICE_ID_D109 && subsystem_device == 0x0001) { + aq_hw_caps->link_speed_msk &= ~HW_ATL_A0_RATE_10G; + aq_hw_caps->link_speed_msk &= ~HW_ATL_A0_RATE_5G; + } + return 0; }

--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -18,9 +18,20 @@ #include "hw_atl_b0_internal.h"

static int hw_atl_b0_get_hw_caps(struct aq_hw_s *self, - struct aq_hw_caps_s *aq_hw_caps) + struct aq_hw_caps_s *aq_hw_caps, + unsigned short device, + unsigned short subsystem_device) { memcpy(aq_hw_caps, &hw_atl_b0_hw_caps_, sizeof(*aq_hw_caps)); + + if (device == HW_ATL_DEVICE_ID_D108 && subsystem_device == 0x0001) + aq_hw_caps->link_speed_msk &= ~HW_ATL_B0_RATE_10G; + + if (device == HW_ATL_DEVICE_ID_D109 && subsystem_device == 0x0001) { + aq_hw_caps->link_speed_msk &= ~HW_ATL_B0_RATE_10G; + aq_hw_caps->link_speed_msk &= ~HW_ATL_B0_RATE_5G; + } + return 0; }

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

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

From: Sascha Hauer s.hauer@pengutronix.de

[ Upstream commit fdf2e821052958a114618a95ab18a300d0b080cb ]

When erased subpages are read then the BCH decoder returns STATUS_ERASED if they are all empty, or STATUS_UNCORRECTABLE if there are bitflips. When there are bitflips, we have to set these bits again to show the upper layers a completely erased page. When a bitflip happens in the exact byte where the bad block marker is, then this byte is swapped with another byte in block_mark_swapping(). The correction code then detects a bitflip in another subpage and no longer corrects the bitflip where it really happens.

Correct this behaviour by calling block_mark_swapping() after the bitflips have been corrected.

In our case UBIFS failed with this bug because it expects erased pages to be really empty:

UBIFS error (pid 187): ubifs_scan: corrupt empty space at LEB 36:118735 UBIFS error (pid 187): ubifs_scanned_corruption: corruption at LEB 36:118735 UBIFS error (pid 187): ubifs_scanned_corruption: first 8192 bytes from LEB 36:118735 UBIFS error (pid 187): ubifs_scan: LEB 36 scanning failed UBIFS error (pid 187): do_commit: commit failed, error -117

Signed-off-by: Sascha Hauer s.hauer@pengutronix.de Reviewed-by: Richard Weinberger richard@nod.at Acked-by: Boris Brezillon boris.brezillon@free-electrons.com Signed-off-by: Richard Weinberger richard@nod.at Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/mtd/nand/gpmi-nand/gpmi-nand.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c @@ -1067,9 +1067,6 @@ static int gpmi_ecc_read_page(struct mtd return ret; }

- /* handle the block mark swapping */ - block_mark_swapping(this, payload_virt, auxiliary_virt); - /* Loop over status bytes, accumulating ECC status. */ status = auxiliary_virt + nfc_geo->auxiliary_status_offset;

@@ -1158,6 +1155,9 @@ static int gpmi_ecc_read_page(struct mtd max_bitflips = max_t(unsigned int, max_bitflips, *status); }

+ /* handle the block mark swapping */ + block_mark_swapping(this, buf, auxiliary_virt); + if (oob_required) { /* * It's time to deliver the OOB bytes. See gpmi_ecc_read_oob()

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

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

From: Brendan McGrath redmcg@redmandi.dyndns.org

[ Upstream commit 588753f1eb18978512b1c9b85fddb457d46f9033 ]

One example of when an ICMPv6 packet is required to be looped back is when a host acts as both a Multicast Listener and a Multicast Router.

A Multicast Router will listen on address ff02::16 for MLDv2 messages.

Currently, MLDv2 messages originating from a Multicast Listener running on the same host as the Multicast Router are not being delivered to the Multicast Router. This is due to dst.input being assigned the default value of dst_discard.

This results in the packet being looped back but discarded before being delivered to the Multicast Router.

This patch sets dst.input to ip6_input to ensure a looped back packet is delivered to the Multicast Router.

Signed-off-by: Brendan McGrath redmcg@redmandi.dyndns.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/route.c | 1 + 1 file changed, 1 insertion(+)

--- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1755,6 +1755,7 @@ struct dst_entry *icmp6_dst_alloc(struct }

rt->dst.flags |= DST_HOST; + rt->dst.input = ip6_input; rt->dst.output = ip6_output; rt->rt6i_gateway = fl6->daddr; rt->rt6i_dst.addr = fl6->daddr;

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

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

From: Chunyan Zhang zhang.lyra@gmail.com

[ Upstream commit 36b0cb84ee858f02c256d26f0cb4229c78e3399e ]

An additional 'ip' will be pushed to the stack, for restoring the DACR later, if CONFIG_CPU_SW_DOMAIN_PAN defined.

However, the fixup still get the err_ptr by add #8*4 to sp, which results in the fact that the code area pointed by the LR will be overwritten, or the kernel will crash if CONFIG_DEBUG_RODATA is enabled.

This patch fixes the stack mismatch.

Fixes: a5e090acbf54 ("ARM: software-based priviledged-no-access support") Signed-off-by: Lvqiang Huang Lvqiang.Huang@spreadtrum.com Signed-off-by: Chunyan Zhang zhang.lyra@gmail.com Signed-off-by: Russell King rmk+kernel@armlinux.org.uk Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm/lib/csumpartialcopyuser.S | 4 ++++ 1 file changed, 4 insertions(+)

--- a/arch/arm/lib/csumpartialcopyuser.S +++ b/arch/arm/lib/csumpartialcopyuser.S @@ -85,7 +85,11 @@ .pushsection .text.fixup,"ax" .align 4 9001: mov r4, #-EFAULT +#ifdef CONFIG_CPU_SW_DOMAIN_PAN + ldr r5, [sp, #9*4] @ *err_ptr +#else ldr r5, [sp, #8*4] @ *err_ptr +#endif str r4, [r5] ldmia sp, {r1, r2} @ retrieve dst, len add r2, r2, r1

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

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

From: Xin Long lucien.xin@gmail.com

[ Upstream commit 5c468674d17056148da06218d4da5d04baf22eac ]

Now when reneging events in sctp_ulpq_renege(), the variable freed could be increased by a __u16 value twice while freed is of __u16 type. It means freed may overflow at the second addition.

This patch is to fix it by using __u32 type for 'freed', while at it, also to remove 'if (chunk)' check, as all renege commands are generated in sctp_eat_data and it can't be NULL.

Reported-by: Marcelo Ricardo Leitner marcelo.leitner@gmail.com Signed-off-by: Xin Long lucien.xin@gmail.com Acked-by: Neil Horman nhorman@tuxdriver.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sctp/ulpqueue.c | 24 ++++++++---------------- 1 file changed, 8 insertions(+), 16 deletions(-)

--- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -1084,29 +1084,21 @@ void sctp_ulpq_partial_delivery(struct s void sctp_ulpq_renege(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, gfp_t gfp) { - struct sctp_association *asoc; - __u16 needed, freed; + struct sctp_association *asoc = ulpq->asoc; + __u32 freed = 0; + __u16 needed;

- asoc = ulpq->asoc; - - if (chunk) { - needed = ntohs(chunk->chunk_hdr->length); - needed -= sizeof(struct sctp_data_chunk); - } else - needed = SCTP_DEFAULT_MAXWINDOW; - - freed = 0; + needed = ntohs(chunk->chunk_hdr->length) - + sizeof(struct sctp_data_chunk);

if (skb_queue_empty(&asoc->base.sk->sk_receive_queue)) { freed = sctp_ulpq_renege_order(ulpq, needed); - if (freed < needed) { + if (freed < needed) freed += sctp_ulpq_renege_frags(ulpq, needed - freed); - } } /* If able to free enough room, accept this chunk. */ - if (chunk && (freed >= needed)) { - int retval; - retval = sctp_ulpq_tail_data(ulpq, chunk, gfp); + if (freed >= needed) { + int retval = sctp_ulpq_tail_data(ulpq, chunk, gfp); /* * Enter partial delivery if chunk has not been * delivered; otherwise, drain the reassembly queue.

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

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

From: Alexey Khoroshilov khoroshilov@ispras.ru

[ Upstream commit ab14436065c8066c265540312742390d6d07ddd2 ]

There are several error paths in xgene_mdio_probe(), where clk is left undisabled. The patch fixes them.

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

Signed-off-by: Alexey Khoroshilov khoroshilov@ispras.ru Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/phy/mdio-xgene.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-)

--- a/drivers/net/phy/mdio-xgene.c +++ b/drivers/net/phy/mdio-xgene.c @@ -194,8 +194,11 @@ static int xgene_mdio_reset(struct xgene }

ret = xgene_enet_ecc_init(pdata); - if (ret) + if (ret) { + if (pdata->dev->of_node) + clk_disable_unprepare(pdata->clk); return ret; + } xgene_gmac_reset(pdata);

return 0; @@ -388,8 +391,10 @@ static int xgene_mdio_probe(struct platf return ret;

mdio_bus = mdiobus_alloc(); - if (!mdio_bus) - return -ENOMEM; + if (!mdio_bus) { + ret = -ENOMEM; + goto out_clk; + }

mdio_bus->name = "APM X-Gene MDIO bus";

@@ -418,7 +423,7 @@ static int xgene_mdio_probe(struct platf mdio_bus->phy_mask = ~0; ret = mdiobus_register(mdio_bus); if (ret) - goto out; + goto out_mdiobus;

acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_HANDLE(dev), 1, acpi_register_phy, NULL, mdio_bus, NULL); @@ -426,16 +431,20 @@ static int xgene_mdio_probe(struct platf }

if (ret) - goto out; + goto out_mdiobus;

pdata->mdio_bus = mdio_bus; xgene_mdio_status = true;

return 0;

-out: +out_mdiobus: mdiobus_free(mdio_bus);

+out_clk: + if (dev->of_node) + clk_disable_unprepare(pdata->clk); + return ret; }

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

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

From: Herbert Xu herbert@gondor.apana.org.au

[ Upstream commit acf568ee859f098279eadf551612f103afdacb4e ]

This is an old bugbear of mine:

https://www.mail-archive.com/netdev@vger.kernel.org/msg03894.html

By crafting special packets, it is possible to cause recursion in our kernel when processing transport-mode packets at levels that are only limited by packet size.

The easiest one is with DNAT, but an even worse one is where UDP encapsulation is used in which case you just have to insert an UDP encapsulation header in between each level of recursion.

This patch avoids this problem by reinjecting tranport-mode packets through a tasklet.

Fixes: b05e106698d9 ("[IPV4/6]: Netfilter IPsec input hooks") Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/xfrm.h | 3 ++ net/ipv4/xfrm4_input.c | 12 +++++++++- net/ipv6/xfrm6_input.c | 10 +++++++- net/xfrm/xfrm_input.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 80 insertions(+), 2 deletions(-)

--- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1570,6 +1570,9 @@ int xfrm_init_state(struct xfrm_state *x int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb); int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int xfrm_input_resume(struct sk_buff *skb, int nexthdr); +int xfrm_trans_queue(struct sk_buff *skb, + int (*finish)(struct net *, struct sock *, + struct sk_buff *)); int xfrm_output_resume(struct sk_buff *skb, int err); int xfrm_output(struct sock *sk, struct sk_buff *skb); int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb); --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -23,6 +23,12 @@ int xfrm4_extract_input(struct xfrm_stat return xfrm4_extract_header(skb); }

+static int xfrm4_rcv_encap_finish2(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + return dst_input(skb); +} + static inline int xfrm4_rcv_encap_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { @@ -33,7 +39,11 @@ static inline int xfrm4_rcv_encap_finish iph->tos, skb->dev)) goto drop; } - return dst_input(skb); + + if (xfrm_trans_queue(skb, xfrm4_rcv_encap_finish2)) + goto drop; + + return 0; drop: kfree_skb(skb); return NET_RX_DROP; --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -32,6 +32,14 @@ int xfrm6_rcv_spi(struct sk_buff *skb, i } EXPORT_SYMBOL(xfrm6_rcv_spi);

+static int xfrm6_transport_finish2(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + if (xfrm_trans_queue(skb, ip6_rcv_finish)) + __kfree_skb(skb); + return -1; +} + int xfrm6_transport_finish(struct sk_buff *skb, int async) { struct xfrm_offload *xo = xfrm_offload(skb); @@ -56,7 +64,7 @@ int xfrm6_transport_finish(struct sk_buf

NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, dev_net(skb->dev), NULL, skb, skb->dev, NULL, - ip6_rcv_finish); + xfrm6_transport_finish2); return -1; }

--- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -8,15 +8,29 @@ * */

+#include <linux/bottom_half.h> +#include <linux/interrupt.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/netdevice.h> +#include <linux/percpu.h> #include <net/dst.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/ip_tunnels.h> #include <net/ip6_tunnel.h>

+struct xfrm_trans_tasklet { + struct tasklet_struct tasklet; + struct sk_buff_head queue; +}; + +struct xfrm_trans_cb { + int (*finish)(struct net *net, struct sock *sk, struct sk_buff *skb); +}; + +#define XFRM_TRANS_SKB_CB(__skb) ((struct xfrm_trans_cb *)&((__skb)->cb[0])) + static struct kmem_cache *secpath_cachep __read_mostly;

static DEFINE_SPINLOCK(xfrm_input_afinfo_lock); @@ -25,6 +39,8 @@ static struct xfrm_input_afinfo const __ static struct gro_cells gro_cells; static struct net_device xfrm_napi_dev;

+static DEFINE_PER_CPU(struct xfrm_trans_tasklet, xfrm_trans_tasklet); + int xfrm_input_register_afinfo(const struct xfrm_input_afinfo *afinfo) { int err = 0; @@ -477,9 +493,41 @@ int xfrm_input_resume(struct sk_buff *sk } EXPORT_SYMBOL(xfrm_input_resume);

+static void xfrm_trans_reinject(unsigned long data) +{ + struct xfrm_trans_tasklet *trans = (void *)data; + struct sk_buff_head queue; + struct sk_buff *skb; + + __skb_queue_head_init(&queue); + skb_queue_splice_init(&trans->queue, &queue); + + while ((skb = __skb_dequeue(&queue))) + XFRM_TRANS_SKB_CB(skb)->finish(dev_net(skb->dev), NULL, skb); +} + +int xfrm_trans_queue(struct sk_buff *skb, + int (*finish)(struct net *, struct sock *, + struct sk_buff *)) +{ + struct xfrm_trans_tasklet *trans; + + trans = this_cpu_ptr(&xfrm_trans_tasklet); + + if (skb_queue_len(&trans->queue) >= netdev_max_backlog) + return -ENOBUFS; + + XFRM_TRANS_SKB_CB(skb)->finish = finish; + skb_queue_tail(&trans->queue, skb); + tasklet_schedule(&trans->tasklet); + return 0; +} +EXPORT_SYMBOL(xfrm_trans_queue); + void __init xfrm_input_init(void) { int err; + int i;

init_dummy_netdev(&xfrm_napi_dev); err = gro_cells_init(&gro_cells, &xfrm_napi_dev); @@ -490,4 +538,13 @@ void __init xfrm_input_init(void) sizeof(struct sec_path), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + + for_each_possible_cpu(i) { + struct xfrm_trans_tasklet *trans; + + trans = &per_cpu(xfrm_trans_tasklet, i); + __skb_queue_head_init(&trans->queue); + tasklet_init(&trans->tasklet, xfrm_trans_reinject, + (unsigned long)trans); + } }

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

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

From: Jia-Ju Bai baijiaju1990@163.com

[ Upstream commit 162bd5e5fd921785077b5862d8f2ffabe2fe11e5 ]

The driver may sleep under a spinlock. The function call path is: hwsim_get_radio_nl (acquire the spinlock) nlmsg_new(GFP_KERNEL) --> may sleep

To fix it, GFP_KERNEL is replaced with GFP_ATOMIC.

This bug is found by my static analysis tool(DSAC) and checked by my code review.

Signed-off-by: Jia-Ju Bai baijiaju1990@163.com Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/wireless/mac80211_hwsim.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -3220,7 +3220,7 @@ static int hwsim_get_radio_nl(struct sk_ if (!net_eq(wiphy_net(data->hw->wiphy), genl_info_net(info))) continue;

- skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb) { res = -ENOMEM; goto out_err;

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

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

From: Abhijeet Kumar abhijeet.kumar@intel.com

[ Upstream commit d070f7c703ef26e3db613f24206823f916272fc6 ]

In skylake platform, we hear a loud pop noise(0 dB) at start of audio capture power up sequence. This patch removes the pop noise from the recording by adding a delay before enabling ADC.

Signed-off-by: Abhijeet Kumar abhijeet.kumar@intel.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/soc/codecs/nau8825.c | 1 + 1 file changed, 1 insertion(+)

--- a/sound/soc/codecs/nau8825.c +++ b/sound/soc/codecs/nau8825.c @@ -905,6 +905,7 @@ static int nau8825_adc_event(struct snd_

switch (event) { case SND_SOC_DAPM_POST_PMU: + msleep(125); regmap_update_bits(nau8825->regmap, NAU8825_REG_ENA_CTRL, NAU8825_ENABLE_ADC, NAU8825_ENABLE_ADC); break;

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

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

From: John Stultz john.stultz@linaro.org

[ Upstream commit f292b9b28097d8fe870336108e91bd95a14294bf ]

In trying to add support for drm_hwcomposer to HiKey, I've needed to utilize the ION CMA heap, and I've noticed problems with allocations on newer kernels failing.

It seems back with 204f672255c2 ("ion: Use CMA APIs directly"), the ion_cma_heap code was modified to use the CMA API, but kept the arguments as buffer lengths rather then number of pages.

This results in errors as we don't have enough pages in CMA to satisfy the exaggerated requests.

This patch converts the ion_cma_heap CMA API usage to properly request pages.

It also fixes a minor issue in the allocation where in the error path, the cma_release is called with the buffer->size value which hasn't yet been set.

Cc: Laura Abbott labbott@redhat.com Cc: Sumit Semwal sumit.semwal@linaro.org Cc: Benjamin Gaignard benjamin.gaignard@linaro.org Cc: Archit Taneja architt@codeaurora.org Cc: Greg KH gregkh@linuxfoundation.org Cc: Daniel Vetter daniel@ffwll.ch Cc: Dmitry Shmidt dimitrysh@google.com Cc: Todd Kjos tkjos@google.com Cc: Amit Pundir amit.pundir@linaro.org Fixes: 204f672255c2 ("staging: android: ion: Use CMA APIs directly") Acked-by: Laura Abbott labbott@redhat.com Signed-off-by: John Stultz john.stultz@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/staging/android/ion/Kconfig | 2 +- drivers/staging/android/ion/ion_cma_heap.c | 15 +++++++++++---- 2 files changed, 12 insertions(+), 5 deletions(-)

--- a/drivers/staging/android/ion/Kconfig +++ b/drivers/staging/android/ion/Kconfig @@ -37,7 +37,7 @@ config ION_CHUNK_HEAP

config ION_CMA_HEAP bool "Ion CMA heap support" - depends on ION && CMA + depends on ION && DMA_CMA help Choose this option to enable CMA heaps with Ion. This heap is backed by the Contiguous Memory Allocator (CMA). If your system has these --- a/drivers/staging/android/ion/ion_cma_heap.c +++ b/drivers/staging/android/ion/ion_cma_heap.c @@ -39,9 +39,15 @@ static int ion_cma_allocate(struct ion_h struct ion_cma_heap *cma_heap = to_cma_heap(heap); struct sg_table *table; struct page *pages; + unsigned long size = PAGE_ALIGN(len); + unsigned long nr_pages = size >> PAGE_SHIFT; + unsigned long align = get_order(size); int ret;

- pages = cma_alloc(cma_heap->cma, len, 0, GFP_KERNEL); + if (align > CONFIG_CMA_ALIGNMENT) + align = CONFIG_CMA_ALIGNMENT; + + pages = cma_alloc(cma_heap->cma, nr_pages, align, GFP_KERNEL); if (!pages) return -ENOMEM;

@@ -53,7 +59,7 @@ static int ion_cma_allocate(struct ion_h if (ret) goto free_mem;

- sg_set_page(table->sgl, pages, len, 0); + sg_set_page(table->sgl, pages, size, 0);

buffer->priv_virt = pages; buffer->sg_table = table; @@ -62,7 +68,7 @@ static int ion_cma_allocate(struct ion_h free_mem: kfree(table); err: - cma_release(cma_heap->cma, pages, buffer->size); + cma_release(cma_heap->cma, pages, nr_pages); return -ENOMEM; }

@@ -70,9 +76,10 @@ static void ion_cma_free(struct ion_buff { struct ion_cma_heap *cma_heap = to_cma_heap(buffer->heap); struct page *pages = buffer->priv_virt; + unsigned long nr_pages = PAGE_ALIGN(buffer->size) >> PAGE_SHIFT;

/* release memory */ - cma_release(cma_heap->cma, pages, buffer->size); + cma_release(cma_heap->cma, pages, nr_pages); /* release sg table */ sg_free_table(buffer->sg_table); kfree(buffer->sg_table);

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

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

From: Sean Wang sean.wang@mediatek.com

[ Upstream commit 7352e252b5bf40d59342494a70354a2d436fd0cd ]

The current solution would setup fixed and force link of 1Gbps to the both GMAC on the default. However, The GMAC should always be put to link down state when the GMAC is disabled on certain target boards. Otherwise, the driver possibly receives unexpected data from the floating hardware connection through the unused GMAC. Although the driver had been added certain protection in RX path to get rid of such kind of unexpected data sent to the upper stack.

Signed-off-by: Sean Wang sean.wang@mediatek.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-)

--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -1959,11 +1959,12 @@ static int mtk_hw_init(struct mtk_eth *e /* set GE2 TUNE */ regmap_write(eth->pctl, GPIO_BIAS_CTRL, 0x0);

- /* GE1, Force 1000M/FD, FC ON */ - mtk_w32(eth, MAC_MCR_FIXED_LINK, MTK_MAC_MCR(0)); - - /* GE2, Force 1000M/FD, FC ON */ - mtk_w32(eth, MAC_MCR_FIXED_LINK, MTK_MAC_MCR(1)); + /* Set linkdown as the default for each GMAC. Its own MCR would be set + * up with the more appropriate value when mtk_phy_link_adjust call is + * being invoked. + */ + for (i = 0; i < MTK_MAC_COUNT; i++) + mtk_w32(eth, 0, MTK_MAC_MCR(i));

/* Indicates CDM to parse the MTK special tag from CPU * which also is working out for untag packets.

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

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

From: Xin Long lucien.xin@gmail.com

[ Upstream commit a93bf0ff449064e6b7f44e58522e940f88c0d966 ]

Unlike ip tunnels, now vxlan doesn't do any pmtu update for upper dst pmtu, even if it doesn't match the lower dst pmtu any more.

The problem can be reproduced when reducing the vxlan lower dev's pmtu when running netperf. In jianlin's testing, the performance went to 1/7 of the previous.

This patch is to update the upper dst pmtu to match the lower dst pmtu on tx path so that packets can be sent out even when lower dev's pmtu has been changed.

It also works for metadata dst.

Note that this patch doesn't process any pmtu icmp packet. But even in the future, the support for pmtu icmp packets process of udp tunnels will also needs this.

The same thing will be done for geneve in another patch.

Signed-off-by: Xin Long lucien.xin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/vxlan.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+)

--- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2155,6 +2155,13 @@ static void vxlan_xmit_one(struct sk_buf }

ndst = &rt->dst; + if (skb_dst(skb)) { + int mtu = dst_mtu(ndst) - VXLAN_HEADROOM; + + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, + skb, mtu); + } + tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); err = vxlan_build_skb(skb, ndst, sizeof(struct iphdr), @@ -2190,6 +2197,13 @@ static void vxlan_xmit_one(struct sk_buf goto out_unlock; }

+ if (skb_dst(skb)) { + int mtu = dst_mtu(ndst) - VXLAN6_HEADROOM; + + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, + skb, mtu); + } + tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip6_dst_hoplimit(ndst); skb_scrub_packet(skb, xnet);

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

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

From: Xin Long lucien.xin@gmail.com

[ Upstream commit 2c52129a7d74d017320804c6928de770815c5f4a ]

The same fix as the patch "ip_gre: remove the incorrect mtu limit for ipgre tap" is also needed for ip6_gre.

Fixes: 61e84623ace3 ("net: centralize net_device min/max MTU checking") Signed-off-by: Xin Long lucien.xin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/ip6_gre.c | 1 + 1 file changed, 1 insertion(+)

--- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1335,6 +1335,7 @@ static void ip6gre_tap_setup(struct net_

ether_setup(dev);

+ dev->max_mtu = 0; dev->netdev_ops = &ip6gre_tap_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free;

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

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

From: Fredrik Hallenberg megahallon@gmail.com

[ Upstream commit 200922c93f008e03ddc804c6dacdf26ca1ba86d7 ]

When using GMAC4 the value written in PTP_SSIR should be shifted however the shifted value is also used in subsequent calculations which results in a bad timestamp value.

Signed-off-by: Fredrik Hallenberg megahallon@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -34,6 +34,7 @@ static u32 stmmac_config_sub_second_incr { u32 value = readl(ioaddr + PTP_TCR); unsigned long data; + u32 reg_value;

/* For GMAC3.x, 4.x versions, convert the ptp_clock to nano second * formula = (1/ptp_clock) * 1000000000 @@ -50,10 +51,11 @@ static u32 stmmac_config_sub_second_incr

data &= PTP_SSIR_SSINC_MASK;

+ reg_value = data; if (gmac4) - data = data << GMAC4_PTP_SSIR_SSINC_SHIFT; + reg_value <<= GMAC4_PTP_SSIR_SSINC_SHIFT;

- writel(data, ioaddr + PTP_SSIR); + writel(reg_value, ioaddr + PTP_SSIR);

return data; }

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

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

From: Huy Nguyen huyn@mellanox.com

[ Upstream commit ff0891915cd7b24ab27eee9b360c0452853bf9f6 ]

Fix bug that allows ets bw sum to be 0% when ets tc type exists.

Fixes: 08fb1dacdd76 ('net/mlx5e: Support DCBNL IEEE ETS') Signed-off-by: Moshe Shemesh moshe@mellanox.com Reviewed-by: Huy Nguyen huyn@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -259,6 +259,7 @@ int mlx5e_dcbnl_ieee_setets_core(struct static int mlx5e_dbcnl_validate_ets(struct net_device *netdev, struct ieee_ets *ets) { + bool have_ets_tc = false; int bw_sum = 0; int i;

@@ -273,11 +274,14 @@ static int mlx5e_dbcnl_validate_ets(stru }

/* Validate Bandwidth Sum */ - for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) - if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) { + have_ets_tc = true; bw_sum += ets->tc_tx_bw[i]; + } + }

- if (bw_sum != 0 && bw_sum != 100) { + if (have_ets_tc && bw_sum != 100) { netdev_err(netdev, "Failed to validate ETS: BW sum is illegal\n"); return -EINVAL;

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

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

From: Moshe Shemesh moshe@mellanox.com

[ Upstream commit a2fba188fd5eadd6061bef4f2f2577a43231ebf3 ]

During unload, on mlx5_stop_eqs we move command interface from events mode to polling mode, but if command interface EQ destroy fail we move back to events mode. That's wrong since even if we fail to destroy command interface EQ, we do release its irq, so no interrupts will be received.

Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Signed-off-by: Moshe Shemesh moshe@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -802,11 +802,9 @@ void mlx5_stop_eqs(struct mlx5_core_dev mlx5_cmd_use_polling(dev);

err = mlx5_destroy_unmap_eq(dev, &table->cmd_eq); - if (err) { + if (err) mlx5_core_err(dev, "failed to destroy command eq, err(%d)\n", err); - mlx5_cmd_use_events(dev); - } }

int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,

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

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

From: Boris Ostrovsky boris.ostrovsky@oracle.com

[ Upstream commit b3cf8528bb21febb650a7ecbf080d0647be40b9f ]

Commit f5775e0b6116 ("x86/xen: discard RAM regions above the maximum reservation") left host memory not assigned to dom0 as available for memory hotplug.

Unfortunately this also meant that those regions could be used by others. Specifically, commit fa564ad96366 ("x86/PCI: Enable a 64bit BAR on AMD Family 15h (Models 00-1f, 30-3f, 60-7f)") may try to map those addresses as MMIO.

To prevent this mark unallocated host memory as E820_TYPE_UNUSABLE (thus effectively reverting f5775e0b6116) and keep track of that region as a hostmem resource that can be used for the hotplug.

Signed-off-by: Boris Ostrovsky boris.ostrovsky@oracle.com Reviewed-by: Juergen Gross jgross@suse.com Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/xen/enlighten.c | 81 +++++++++++++++++++++++++++++++++++++++++++++++ arch/x86/xen/setup.c | 6 +-- drivers/xen/balloon.c | 65 ++++++++++++++++++++++++++++++++----- include/xen/balloon.h | 5 ++ 4 files changed, 144 insertions(+), 13 deletions(-)

--- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1,8 +1,12 @@ +#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG +#include <linux/bootmem.h> +#endif #include <linux/cpu.h> #include <linux/kexec.h>

#include <xen/features.h> #include <xen/page.h> +#include <xen/interface/memory.h>

#include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> @@ -331,3 +335,80 @@ void xen_arch_unregister_cpu(int num) } EXPORT_SYMBOL(xen_arch_unregister_cpu); #endif + +#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG +void __init arch_xen_balloon_init(struct resource *hostmem_resource) +{ + struct xen_memory_map memmap; + int rc; + unsigned int i, last_guest_ram; + phys_addr_t max_addr = PFN_PHYS(max_pfn); + struct e820_table *xen_e820_table; + const struct e820_entry *entry; + struct resource *res; + + if (!xen_initial_domain()) + return; + + xen_e820_table = kmalloc(sizeof(*xen_e820_table), GFP_KERNEL); + if (!xen_e820_table) + return; + + memmap.nr_entries = ARRAY_SIZE(xen_e820_table->entries); + set_xen_guest_handle(memmap.buffer, xen_e820_table->entries); + rc = HYPERVISOR_memory_op(XENMEM_machine_memory_map, &memmap); + if (rc) { + pr_warn("%s: Can't read host e820 (%d)\n", __func__, rc); + goto out; + } + + last_guest_ram = 0; + for (i = 0; i < memmap.nr_entries; i++) { + if (xen_e820_table->entries[i].addr >= max_addr) + break; + if (xen_e820_table->entries[i].type == E820_TYPE_RAM) + last_guest_ram = i; + } + + entry = &xen_e820_table->entries[last_guest_ram]; + if (max_addr >= entry->addr + entry->size) + goto out; /* No unallocated host RAM. */ + + hostmem_resource->start = max_addr; + hostmem_resource->end = entry->addr + entry->size; + + /* + * Mark non-RAM regions between the end of dom0 RAM and end of host RAM + * as unavailable. The rest of that region can be used for hotplug-based + * ballooning. + */ + for (; i < memmap.nr_entries; i++) { + entry = &xen_e820_table->entries[i]; + + if (entry->type == E820_TYPE_RAM) + continue; + + if (entry->addr >= hostmem_resource->end) + break; + + res = kzalloc(sizeof(*res), GFP_KERNEL); + if (!res) + goto out; + + res->name = "Unavailable host RAM"; + res->start = entry->addr; + res->end = (entry->addr + entry->size < hostmem_resource->end) ? + entry->addr + entry->size : hostmem_resource->end; + rc = insert_resource(hostmem_resource, res); + if (rc) { + pr_warn("%s: Can't insert [%llx - %llx) (%d)\n", + __func__, res->start, res->end, rc); + kfree(res); + goto out; + } + } + + out: + kfree(xen_e820_table); +} +#endif /* CONFIG_XEN_BALLOON_MEMORY_HOTPLUG */ --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -808,7 +808,6 @@ char * __init xen_memory_setup(void) addr = xen_e820_table.entries[0].addr; size = xen_e820_table.entries[0].size; while (i < xen_e820_table.nr_entries) { - bool discard = false;

chunk_size = size; type = xen_e820_table.entries[i].type; @@ -824,11 +823,10 @@ char * __init xen_memory_setup(void) xen_add_extra_mem(pfn_s, n_pfns); xen_max_p2m_pfn = pfn_s + n_pfns; } else - discard = true; + type = E820_TYPE_UNUSABLE; }

- if (!discard) - xen_align_and_add_e820_region(addr, chunk_size, type); + xen_align_and_add_e820_region(addr, chunk_size, type);

addr += chunk_size; size -= chunk_size; --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -257,10 +257,25 @@ static void release_memory_resource(stru kfree(resource); }

+/* + * Host memory not allocated to dom0. We can use this range for hotplug-based + * ballooning. + * + * It's a type-less resource. Setting IORESOURCE_MEM will make resource + * management algorithms (arch_remove_reservations()) look into guest e820, + * which we don't want. + */ +static struct resource hostmem_resource = { + .name = "Host RAM", +}; + +void __attribute__((weak)) __init arch_xen_balloon_init(struct resource *res) +{} + static struct resource *additional_memory_resource(phys_addr_t size) { - struct resource *res; - int ret; + struct resource *res, *res_hostmem; + int ret = -ENOMEM;

res = kzalloc(sizeof(*res), GFP_KERNEL); if (!res) @@ -269,13 +284,42 @@ static struct resource *additional_memor res->name = "System RAM"; res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;

- ret = allocate_resource(&iomem_resource, res, - size, 0, -1, - PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL); - if (ret < 0) { - pr_err("Cannot allocate new System RAM resource\n"); - kfree(res); - return NULL; + res_hostmem = kzalloc(sizeof(*res), GFP_KERNEL); + if (res_hostmem) { + /* Try to grab a range from hostmem */ + res_hostmem->name = "Host memory"; + ret = allocate_resource(&hostmem_resource, res_hostmem, + size, 0, -1, + PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL); + } + + if (!ret) { + /* + * Insert this resource into iomem. Because hostmem_resource + * tracks portion of guest e820 marked as UNUSABLE noone else + * should try to use it. + */ + res->start = res_hostmem->start; + res->end = res_hostmem->end; + ret = insert_resource(&iomem_resource, res); + if (ret < 0) { + pr_err("Can't insert iomem_resource [%llx - %llx]\n", + res->start, res->end); + release_memory_resource(res_hostmem); + res_hostmem = NULL; + res->start = res->end = 0; + } + } + + if (ret) { + ret = allocate_resource(&iomem_resource, res, + size, 0, -1, + PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL); + if (ret < 0) { + pr_err("Cannot allocate new System RAM resource\n"); + kfree(res); + return NULL; + } }

#ifdef CONFIG_SPARSEMEM @@ -287,6 +331,7 @@ static struct resource *additional_memor pr_err("New System RAM resource outside addressable RAM (%lu > %lu)\n", pfn, limit); release_memory_resource(res); + release_memory_resource(res_hostmem); return NULL; } } @@ -765,6 +810,8 @@ static int __init balloon_init(void) set_online_page_callback(&xen_online_page); register_memory_notifier(&xen_memory_nb); register_sysctl_table(xen_root); + + arch_xen_balloon_init(&hostmem_resource); #endif

#ifdef CONFIG_XEN_PV --- a/include/xen/balloon.h +++ b/include/xen/balloon.h @@ -44,3 +44,8 @@ static inline void xen_balloon_init(void { } #endif + +#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG +struct resource; +void arch_xen_balloon_init(struct resource *hostmem_resource); +#endif

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

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

From: Cathy Avery cavery@redhat.com

[ Upstream commit d1b8b2391c24751e44f618fcf86fb55d9a9247fd ]

When an I/O is returned with an srb_status of SRB_STATUS_INVALID_LUN which has zero good_bytes it must be assigned an error. Otherwise the I/O will be continuously requeued and will cause a deadlock in the case where disks are being hot added and removed. sd_probe_async will wait forever for its I/O to complete while holding scsi_sd_probe_domain.

Also returning the default error of DID_TARGET_FAILURE causes multipath to not retry the I/O resulting in applications receiving I/O errors before a failover can occur.

Signed-off-by: Cathy Avery cavery@redhat.com Signed-off-by: Long Li longli@microsoft.com Reviewed-by: Stephen Hemminger stephen@networkplumber.org Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/scsi/storvsc_drv.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -952,10 +952,11 @@ static void storvsc_handle_error(struct case TEST_UNIT_READY: break; default: - set_host_byte(scmnd, DID_TARGET_FAILURE); + set_host_byte(scmnd, DID_ERROR); } break; case SRB_STATUS_INVALID_LUN: + set_host_byte(scmnd, DID_NO_CONNECT); do_work = true; process_err_fn = storvsc_remove_lun; break;

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

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

From: Gabriel Krisman Bertazi krisman@collabora.co.uk

[ Upstream commit 8bc0d7ac934b6f2d0dc8f38a3104d281c9db1e98 ]

Current code advertises (on the modifiers blob property) support for CCS modifier for pipe C on GLK, only to reject it later when validating the request before the atomic commit.

This fixes the tests igt@kms_ccs@pipe-c-*, which should skip on GLK for pipe C (see bug 104096).

A relevant discussion is archived at:

https://lists.freedesktop.org/archives/intel-gfx/2017-December/150646.html

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=104096 Signed-off-by: Gabriel Krisman Bertazi krisman@collabora.co.uk Cc: Ben Widawsky ben@bwidawsk.net Reviewed-by: Ben Widawsky ben@bwidawsk.net Signed-off-by: Rodrigo Vivi rodrigo.vivi@intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20171220002410.5604-1-krisman@... (cherry picked from commit f0cbd8bd877f3d8c5b80a6b1add9ca9010d7f9d8) Signed-off-by: Jani Nikula jani.nikula@intel.com Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/i915/intel_display.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -13240,7 +13240,7 @@ intel_primary_plane_create(struct drm_i9 primary->frontbuffer_bit = INTEL_FRONTBUFFER_PRIMARY(pipe); primary->check_plane = intel_check_primary_plane;

- if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) { + if (INTEL_GEN(dev_priv) >= 10) { intel_primary_formats = skl_primary_formats; num_formats = ARRAY_SIZE(skl_primary_formats); modifiers = skl_format_modifiers_ccs;

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

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

From: Arnd Bergmann arnd@arndb.de

[ Upstream commit 506e8a912661c97b41adc8a286b875d01323ec45 ]

dtc warns about two 'clocks' properties that have an extraneous '1' at the end:

arch/arm/boot/dts/ls1021a-qds.dtb: Warning (clocks_property): arch/arm/boot/dts/ls1021a-twr.dtb: Warning (clocks_property): Property 'clocks', cell 1 is not a phandle reference in /soc/i2c@2180000/mux@77/i2c@4/sgtl5000@2a arch/arm/boot/dts/ls1021a-qds.dtb: Warning (clocks_property): Missing property '#clock-cells' in node /soc/interrupt-controller@1400000 or bad phandle (referred from /soc/i2c@2180000/mux@77/i2c@4/sgtl5000@2a:clocks[1]) Property 'clocks', cell 1 is not a phandle reference in /soc/i2c@2190000/sgtl5000@a arch/arm/boot/dts/ls1021a-twr.dtb: Warning (clocks_property): Missing property '#clock-cells' in node /soc/interrupt-controller@1400000 or bad phandle (referred from /soc/i2c@2190000/sgtl5000@a:clocks[1])

The clocks that get referenced here are fixed-rate, so they do not take any argument, and dtc interprets the next cell as a phandle, which is invalid.

Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm/boot/dts/ls1021a-qds.dts | 2 +- arch/arm/boot/dts/ls1021a-twr.dts | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)

--- a/arch/arm/boot/dts/ls1021a-qds.dts +++ b/arch/arm/boot/dts/ls1021a-qds.dts @@ -215,7 +215,7 @@ reg = <0x2a>; VDDA-supply = <&reg_3p3v>; VDDIO-supply = <&reg_3p3v>; - clocks = <&sys_mclk 1>; + clocks = <&sys_mclk>; }; }; }; --- a/arch/arm/boot/dts/ls1021a-twr.dts +++ b/arch/arm/boot/dts/ls1021a-twr.dts @@ -187,7 +187,7 @@ reg = <0x0a>; VDDA-supply = <&reg_3p3v>; VDDIO-supply = <&reg_3p3v>; - clocks = <&sys_mclk 1>; + clocks = <&sys_mclk>; }; };

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

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

From: James Hogan jhogan@kernel.org

[ Upstream commit bbc25bee37d2b32cf3a1fab9195b6da3a185614a ]

Current MIPS64r6 toolchains aren't able to generate efficient DMULU/DMUHU based code for the C implementation of umul_ppmm(), which performs an unsigned 64 x 64 bit multiply and returns the upper and lower 64-bit halves of the 128-bit result. Instead it widens the 64-bit inputs to 128-bits and emits a __multi3 intrinsic call to perform a 128 x 128 multiply. This is both inefficient, and it results in a link error since we don't include __multi3 in MIPS linux.

For example commit 90a53e4432b1 ("cfg80211: implement regdb signature checking") merged in v4.15-rc1 recently broke the 64r6_defconfig and 64r6el_defconfig builds by indirectly selecting MPILIB. The same build errors can be reproduced on older kernels by enabling e.g. CRYPTO_RSA:

lib/mpi/generic_mpih-mul1.o: In function `mpihelp_mul_1': lib/mpi/generic_mpih-mul1.c:50: undefined reference to `__multi3' lib/mpi/generic_mpih-mul2.o: In function `mpihelp_addmul_1': lib/mpi/generic_mpih-mul2.c:49: undefined reference to `__multi3' lib/mpi/generic_mpih-mul3.o: In function `mpihelp_submul_1': lib/mpi/generic_mpih-mul3.c:49: undefined reference to `__multi3' lib/mpi/mpih-div.o In function `mpihelp_divrem': lib/mpi/mpih-div.c:205: undefined reference to `__multi3' lib/mpi/mpih-div.c:142: undefined reference to `__multi3'

Therefore add an efficient MIPS64r6 implementation of umul_ppmm() using inline assembly and the DMULU/DMUHU instructions, to prevent __multi3 calls being emitted.

Fixes: 7fd08ca58ae6 ("MIPS: Add build support for the MIPS R6 ISA") Signed-off-by: James Hogan jhogan@kernel.org Cc: Ralf Baechle ralf@linux-mips.org Cc: Herbert Xu herbert@gondor.apana.org.au Cc: "David S. Miller" davem@davemloft.net Cc: linux-mips@linux-mips.org Cc: linux-crypto@vger.kernel.org Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- lib/mpi/longlong.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-)

--- a/lib/mpi/longlong.h +++ b/lib/mpi/longlong.h @@ -671,7 +671,23 @@ do { \ ************** MIPS/64 ************** ***************************************/ #if (defined(__mips) && __mips >= 3) && W_TYPE_SIZE == 64 -#if (__GNUC__ >= 5) || (__GNUC__ >= 4 && __GNUC_MINOR__ >= 4) +#if defined(__mips_isa_rev) && __mips_isa_rev >= 6 +/* + * GCC ends up emitting a __multi3 intrinsic call for MIPS64r6 with the plain C + * code below, so we special case MIPS64r6 until the compiler can do better. + */ +#define umul_ppmm(w1, w0, u, v) \ +do { \ + __asm__ ("dmulu %0,%1,%2" \ + : "=d" ((UDItype)(w0)) \ + : "d" ((UDItype)(u)), \ + "d" ((UDItype)(v))); \ + __asm__ ("dmuhu %0,%1,%2" \ + : "=d" ((UDItype)(w1)) \ + : "d" ((UDItype)(u)), \ + "d" ((UDItype)(v))); \ +} while (0) +#elif (__GNUC__ >= 5) || (__GNUC__ >= 4 && __GNUC_MINOR__ >= 4) #define umul_ppmm(w1, w0, u, v) \ do { \ typedef unsigned int __ll_UTItype __attribute__((mode(TI))); \

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

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

From: Ofer Heifetz oferh@marvell.com

[ Upstream commit 1eb7b40386c97f6c4d1c62931bf306f4535a4bd6 ]

When an invalidation request is needed we currently override the context .send and .handle_result helpers. This is wrong as under high load other requests can already be queued and overriding the context helpers will make them execute the wrong .send and .handle_result functions.

This commit fixes this by adding a needs_inv flag in the request to choose the action to perform when sending requests or handling their results. This flag will be set when needed (i.e. when the context flag will be set).

Fixes: 1b44c5a60c13 ("crypto: inside-secure - add SafeXcel EIP197 crypto engine driver") Signed-off-by: Ofer Heifetz oferh@marvell.com [Antoine: commit message, and removed non related changes from the original commit] Signed-off-by: Antoine Tenart antoine.tenart@free-electrons.com Signed-off-by: Herbert Xu herbert@gondor.apana.org.au

Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/crypto/inside-secure/safexcel_cipher.c | 71 ++++++++++++++++++++----- drivers/crypto/inside-secure/safexcel_hash.c | 67 ++++++++++++++++++----- 2 files changed, 111 insertions(+), 27 deletions(-)

--- a/drivers/crypto/inside-secure/safexcel_cipher.c +++ b/drivers/crypto/inside-secure/safexcel_cipher.c @@ -14,6 +14,7 @@

#include <crypto/aes.h> #include <crypto/skcipher.h> +#include <crypto/internal/skcipher.h>

#include "safexcel.h"

@@ -33,6 +34,10 @@ struct safexcel_cipher_ctx { unsigned int key_len; };

+struct safexcel_cipher_req { + bool needs_inv; +}; + static void safexcel_cipher_token(struct safexcel_cipher_ctx *ctx, struct crypto_async_request *async, struct safexcel_command_desc *cdesc, @@ -126,9 +131,9 @@ static int safexcel_context_control(stru return 0; }

-static int safexcel_handle_result(struct safexcel_crypto_priv *priv, int ring, - struct crypto_async_request *async, - bool *should_complete, int *ret) +static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int ring, + struct crypto_async_request *async, + bool *should_complete, int *ret) { struct skcipher_request *req = skcipher_request_cast(async); struct safexcel_result_desc *rdesc; @@ -265,7 +270,6 @@ static int safexcel_aes_send(struct cryp spin_unlock_bh(&priv->ring[ring].egress_lock);

request->req = &req->base; - ctx->base.handle_result = safexcel_handle_result;

*commands = n_cdesc; *results = n_rdesc; @@ -341,8 +345,6 @@ static int safexcel_handle_inv_result(st

ring = safexcel_select_ring(priv); ctx->base.ring = ring; - ctx->base.needs_inv = false; - ctx->base.send = safexcel_aes_send;

spin_lock_bh(&priv->ring[ring].queue_lock); enq_ret = crypto_enqueue_request(&priv->ring[ring].queue, async); @@ -359,6 +361,26 @@ static int safexcel_handle_inv_result(st return ndesc; }

+static int safexcel_handle_result(struct safexcel_crypto_priv *priv, int ring, + struct crypto_async_request *async, + bool *should_complete, int *ret) +{ + struct skcipher_request *req = skcipher_request_cast(async); + struct safexcel_cipher_req *sreq = skcipher_request_ctx(req); + int err; + + if (sreq->needs_inv) { + sreq->needs_inv = false; + err = safexcel_handle_inv_result(priv, ring, async, + should_complete, ret); + } else { + err = safexcel_handle_req_result(priv, ring, async, + should_complete, ret); + } + + return err; +} + static int safexcel_cipher_send_inv(struct crypto_async_request *async, int ring, struct safexcel_request *request, int *commands, int *results) @@ -368,8 +390,6 @@ static int safexcel_cipher_send_inv(stru struct safexcel_crypto_priv *priv = ctx->priv; int ret;

- ctx->base.handle_result = safexcel_handle_inv_result; - ret = safexcel_invalidate_cache(async, &ctx->base, priv, ctx->base.ctxr_dma, ring, request); if (unlikely(ret)) @@ -381,11 +401,29 @@ static int safexcel_cipher_send_inv(stru return 0; }

+static int safexcel_send(struct crypto_async_request *async, + int ring, struct safexcel_request *request, + int *commands, int *results) +{ + struct skcipher_request *req = skcipher_request_cast(async); + struct safexcel_cipher_req *sreq = skcipher_request_ctx(req); + int ret; + + if (sreq->needs_inv) + ret = safexcel_cipher_send_inv(async, ring, request, + commands, results); + else + ret = safexcel_aes_send(async, ring, request, + commands, results); + return ret; +} + static int safexcel_cipher_exit_inv(struct crypto_tfm *tfm) { struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm); struct safexcel_crypto_priv *priv = ctx->priv; struct skcipher_request req; + struct safexcel_cipher_req *sreq = skcipher_request_ctx(&req); struct safexcel_inv_result result = {}; int ring = ctx->base.ring;

@@ -399,7 +437,7 @@ static int safexcel_cipher_exit_inv(stru skcipher_request_set_tfm(&req, __crypto_skcipher_cast(tfm)); ctx = crypto_tfm_ctx(req.base.tfm); ctx->base.exit_inv = true; - ctx->base.send = safexcel_cipher_send_inv; + sreq->needs_inv = true;

spin_lock_bh(&priv->ring[ring].queue_lock); crypto_enqueue_request(&priv->ring[ring].queue, &req.base); @@ -424,19 +462,21 @@ static int safexcel_aes(struct skcipher_ enum safexcel_cipher_direction dir, u32 mode) { struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(req->base.tfm); + struct safexcel_cipher_req *sreq = skcipher_request_ctx(req); struct safexcel_crypto_priv *priv = ctx->priv; int ret, ring;

+ sreq->needs_inv = false; ctx->direction = dir; ctx->mode = mode;

if (ctx->base.ctxr) { - if (ctx->base.needs_inv) - ctx->base.send = safexcel_cipher_send_inv; + if (ctx->base.needs_inv) { + sreq->needs_inv = true; + ctx->base.needs_inv = false; + } } else { ctx->base.ring = safexcel_select_ring(priv); - ctx->base.send = safexcel_aes_send; - ctx->base.ctxr = dma_pool_zalloc(priv->context_pool, EIP197_GFP_FLAGS(req->base), &ctx->base.ctxr_dma); @@ -476,6 +516,11 @@ static int safexcel_skcipher_cra_init(st alg.skcipher.base);

ctx->priv = tmpl->priv; + ctx->base.send = safexcel_send; + ctx->base.handle_result = safexcel_handle_result; + + crypto_skcipher_set_reqsize(__crypto_skcipher_cast(tfm), + sizeof(struct safexcel_cipher_req));

return 0; } --- a/drivers/crypto/inside-secure/safexcel_hash.c +++ b/drivers/crypto/inside-secure/safexcel_hash.c @@ -32,6 +32,7 @@ struct safexcel_ahash_req { bool last_req; bool finish; bool hmac; + bool needs_inv;

int nents;

@@ -121,9 +122,9 @@ static void safexcel_context_control(str } }

-static int safexcel_handle_result(struct safexcel_crypto_priv *priv, int ring, - struct crypto_async_request *async, - bool *should_complete, int *ret) +static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int ring, + struct crypto_async_request *async, + bool *should_complete, int *ret) { struct safexcel_result_desc *rdesc; struct ahash_request *areq = ahash_request_cast(async); @@ -169,9 +170,9 @@ static int safexcel_handle_result(struct return 1; }

-static int safexcel_ahash_send(struct crypto_async_request *async, int ring, - struct safexcel_request *request, int *commands, - int *results) +static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring, + struct safexcel_request *request, + int *commands, int *results) { struct ahash_request *areq = ahash_request_cast(async); struct crypto_ahash *ahash = crypto_ahash_reqtfm(areq); @@ -310,7 +311,6 @@ send_command:

req->processed += len; request->req = &areq->base; - ctx->base.handle_result = safexcel_handle_result;

*commands = n_cdesc; *results = 1; @@ -394,8 +394,6 @@ static int safexcel_handle_inv_result(st

ring = safexcel_select_ring(priv); ctx->base.ring = ring; - ctx->base.needs_inv = false; - ctx->base.send = safexcel_ahash_send;

spin_lock_bh(&priv->ring[ring].queue_lock); enq_ret = crypto_enqueue_request(&priv->ring[ring].queue, async); @@ -412,6 +410,26 @@ static int safexcel_handle_inv_result(st return 1; }

+static int safexcel_handle_result(struct safexcel_crypto_priv *priv, int ring, + struct crypto_async_request *async, + bool *should_complete, int *ret) +{ + struct ahash_request *areq = ahash_request_cast(async); + struct safexcel_ahash_req *req = ahash_request_ctx(areq); + int err; + + if (req->needs_inv) { + req->needs_inv = false; + err = safexcel_handle_inv_result(priv, ring, async, + should_complete, ret); + } else { + err = safexcel_handle_req_result(priv, ring, async, + should_complete, ret); + } + + return err; +} + static int safexcel_ahash_send_inv(struct crypto_async_request *async, int ring, struct safexcel_request *request, int *commands, int *results) @@ -420,7 +438,6 @@ static int safexcel_ahash_send_inv(struc struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq)); int ret;

- ctx->base.handle_result = safexcel_handle_inv_result; ret = safexcel_invalidate_cache(async, &ctx->base, ctx->priv, ctx->base.ctxr_dma, ring, request); if (unlikely(ret)) @@ -432,11 +449,29 @@ static int safexcel_ahash_send_inv(struc return 0; }

+static int safexcel_ahash_send(struct crypto_async_request *async, + int ring, struct safexcel_request *request, + int *commands, int *results) +{ + struct ahash_request *areq = ahash_request_cast(async); + struct safexcel_ahash_req *req = ahash_request_ctx(areq); + int ret; + + if (req->needs_inv) + ret = safexcel_ahash_send_inv(async, ring, request, + commands, results); + else + ret = safexcel_ahash_send_req(async, ring, request, + commands, results); + return ret; +} + static int safexcel_ahash_exit_inv(struct crypto_tfm *tfm) { struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(tfm); struct safexcel_crypto_priv *priv = ctx->priv; struct ahash_request req; + struct safexcel_ahash_req *rctx = ahash_request_ctx(&req); struct safexcel_inv_result result = {}; int ring = ctx->base.ring;

@@ -450,7 +485,7 @@ static int safexcel_ahash_exit_inv(struc ahash_request_set_tfm(&req, __crypto_ahash_cast(tfm)); ctx = crypto_tfm_ctx(req.base.tfm); ctx->base.exit_inv = true; - ctx->base.send = safexcel_ahash_send_inv; + rctx->needs_inv = true;

spin_lock_bh(&priv->ring[ring].queue_lock); crypto_enqueue_request(&priv->ring[ring].queue, &req.base); @@ -501,14 +536,16 @@ static int safexcel_ahash_enqueue(struct struct safexcel_crypto_priv *priv = ctx->priv; int ret, ring;

- ctx->base.send = safexcel_ahash_send; + req->needs_inv = false;

if (req->processed && ctx->digest == CONTEXT_CONTROL_DIGEST_PRECOMPUTED) ctx->base.needs_inv = safexcel_ahash_needs_inv_get(areq);

if (ctx->base.ctxr) { - if (ctx->base.needs_inv) - ctx->base.send = safexcel_ahash_send_inv; + if (ctx->base.needs_inv) { + ctx->base.needs_inv = false; + req->needs_inv = true; + } } else { ctx->base.ring = safexcel_select_ring(priv); ctx->base.ctxr = dma_pool_zalloc(priv->context_pool, @@ -642,6 +679,8 @@ static int safexcel_ahash_cra_init(struc struct safexcel_alg_template, alg.ahash);

ctx->priv = tmpl->priv; + ctx->base.send = safexcel_ahash_send; + ctx->base.handle_result = safexcel_handle_result;

crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm), sizeof(struct safexcel_ahash_req));

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

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

From: Tommi Rantala tommi.t.rantala@nokia.com

[ Upstream commit 19142551b2be4a9e13838099fde1351386e5e007 ]

Fix memory leak in tipc_enable_bearer() if enable_media() fails, and cleanup with bearer_disable() if tipc_mon_create() fails.

Acked-by: Ying Xue ying.xue@windriver.com Acked-by: Jon Maloy jon.maloy@ericsson.com Signed-off-by: Tommi Rantala tommi.t.rantala@nokia.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/tipc/bearer.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -324,6 +324,7 @@ restart: if (res) { pr_warn("Bearer <%s> rejected, enable failure (%d)\n", name, -res); + kfree(b); return -EINVAL; }

@@ -347,8 +348,10 @@ restart: if (skb) tipc_bearer_xmit_skb(net, bearer_id, skb, &b->bcast_addr);

- if (tipc_mon_create(net, bearer_id)) + if (tipc_mon_create(net, bearer_id)) { + bearer_disable(net, b); return -ENOMEM; + }

pr_info("Enabled bearer <%s>, discovery domain %s, priority %u\n", name,

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

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

From: Siva Reddy Kallam siva.kallam@broadcom.com

[ Upstream commit 4419bb1cedcda0272e1dc410345c5a1d1da0e367 ]

One of AMD based server with 5762 hangs with jumbo frame traffic. This AMD platform has southbridge limitation which is restricting MRRS to 4000. As a work around, driver to restricts the MRRS to 2048 for this particular 5762 NX1 card.

Signed-off-by: Siva Reddy Kallam siva.kallam@broadcom.com Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/tg3.c | 10 ++++++++++ drivers/net/ethernet/broadcom/tg3.h | 4 ++++ 2 files changed, 14 insertions(+)

--- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -10052,6 +10052,16 @@ static int tg3_reset_hw(struct tg3 *tp,

tw32(GRC_MODE, tp->grc_mode | val);

+ /* On one of the AMD platform, MRRS is restricted to 4000 because of + * south bridge limitation. As a workaround, Driver is setting MRRS + * to 2048 instead of default 4096. + */ + if (tp->pdev->subsystem_vendor == PCI_VENDOR_ID_DELL && + tp->pdev->subsystem_device == TG3PCI_SUBDEVICE_ID_DELL_5762) { + val = tr32(TG3PCI_DEV_STATUS_CTRL) & ~MAX_READ_REQ_MASK; + tw32(TG3PCI_DEV_STATUS_CTRL, val | MAX_READ_REQ_SIZE_2048); + } + /* Setup the timer prescalar register. Clock is always 66Mhz. */ val = tr32(GRC_MISC_CFG); val &= ~0xff; --- a/drivers/net/ethernet/broadcom/tg3.h +++ b/drivers/net/ethernet/broadcom/tg3.h @@ -96,6 +96,7 @@ #define TG3PCI_SUBDEVICE_ID_DELL_JAGUAR 0x0106 #define TG3PCI_SUBDEVICE_ID_DELL_MERLOT 0x0109 #define TG3PCI_SUBDEVICE_ID_DELL_SLIM_MERLOT 0x010a +#define TG3PCI_SUBDEVICE_ID_DELL_5762 0x07f0 #define TG3PCI_SUBVENDOR_ID_COMPAQ PCI_VENDOR_ID_COMPAQ #define TG3PCI_SUBDEVICE_ID_COMPAQ_BANSHEE 0x007c #define TG3PCI_SUBDEVICE_ID_COMPAQ_BANSHEE_2 0x009a @@ -281,6 +282,9 @@ #define TG3PCI_STD_RING_PROD_IDX 0x00000098 /* 64-bit */ #define TG3PCI_RCV_RET_RING_CON_IDX 0x000000a0 /* 64-bit */ /* 0xa8 --> 0xb8 unused */ +#define TG3PCI_DEV_STATUS_CTRL 0x000000b4 +#define MAX_READ_REQ_SIZE_2048 0x00004000 +#define MAX_READ_REQ_MASK 0x00007000 #define TG3PCI_DUAL_MAC_CTRL 0x000000b8 #define DUAL_MAC_CTRL_CH_MASK 0x00000003 #define DUAL_MAC_CTRL_ID 0x00000004

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

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

From: "Guilherme G. Piccoli" gpiccoli@linux.vnet.ibm.com

[ Upstream commit f7084059a9cb9e56a186e1677b1dcffd76c2cd24 ]

While in recovery process of PCI error (called EEH on PowerPC arch), another PCI transaction could be corrupted causing a situation of nested PCI errors. Also, this scenario could be reproduced with error injection mechanisms (for debug purposes).

We observe that in case of nested PCI errors, bnx2x might attempt to initialize its shmem and cause a kernel crash due to bad addresses read from MCP. Multiple different stack traces were observed depending on the point the second PCI error happens.

This patch avoids the crashes by:

* failing PCI recovery in case of nested errors (since multiple PCI errors in a row are not expected to lead to a functional adapter anyway), and by,

* preventing access to adapter FW when MCP is failed (we mark it as failed when shmem cannot get initialized properly).

Reported-by: Abdul Haleem abdhalee@linux.vnet.ibm.com Signed-off-by: Guilherme G. Piccoli gpiccoli@linux.vnet.ibm.com Acked-by: Shahed Shaikh Shahed.Shaikh@cavium.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 4 ++-- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 14 +++++++++++++- 2 files changed, 15 insertions(+), 3 deletions(-)

--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -3030,7 +3030,7 @@ int bnx2x_nic_unload(struct bnx2x *bp, i

del_timer_sync(&bp->timer);

- if (IS_PF(bp)) { + if (IS_PF(bp) && !BP_NOMCP(bp)) { /* Set ALWAYS_ALIVE bit in shmem */ bp->fw_drv_pulse_wr_seq |= DRV_PULSE_ALWAYS_ALIVE; bnx2x_drv_pulse(bp); @@ -3116,7 +3116,7 @@ int bnx2x_nic_unload(struct bnx2x *bp, i bp->cnic_loaded = false;

/* Clear driver version indication in shmem */ - if (IS_PF(bp)) + if (IS_PF(bp) && !BP_NOMCP(bp)) bnx2x_update_mng_version(bp);

/* Check if there are pending parity attentions. If there are - set --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -9578,6 +9578,15 @@ static int bnx2x_init_shmem(struct bnx2x

do { bp->common.shmem_base = REG_RD(bp, MISC_REG_SHARED_MEM_ADDR); + + /* If we read all 0xFFs, means we are in PCI error state and + * should bail out to avoid crashes on adapter's FW reads. + */ + if (bp->common.shmem_base == 0xFFFFFFFF) { + bp->flags |= NO_MCP_FLAG; + return -ENODEV; + } + if (bp->common.shmem_base) { val = SHMEM_RD(bp, validity_map[BP_PORT(bp)]); if (val & SHR_MEM_VALIDITY_MB) @@ -14315,7 +14324,10 @@ static pci_ers_result_t bnx2x_io_slot_re BNX2X_ERR("IO slot reset --> driver unload\n");

/* MCP should have been reset; Need to wait for validity */ - bnx2x_init_shmem(bp); + if (bnx2x_init_shmem(bp)) { + rtnl_unlock(); + return PCI_ERS_RESULT_DISCONNECT; + }

if (IS_PF(bp) && SHMEM2_HAS(bp, drv_capabilities_flag)) { u32 v;

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

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

From: Matthieu CASTET matthieu.castet@parrot.com

[ Upstream commit 2b83ff96f51d0b039c4561b9f95c824d7bddb85c ]

With the current code, the following sequence won't work : echo timer > trigger

echo 0 > delay_off * at this point we call ** led_delay_off_store ** led_blink_set --- drivers/leds/led-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/leds/led-core.c +++ b/drivers/leds/led-core.c @@ -187,7 +187,7 @@ void led_blink_set(struct led_classdev * unsigned long *delay_on, unsigned long *delay_off) { - del_timer_sync(&led_cdev->blink_timer); + led_stop_software_blink(led_cdev);

clear_bit(LED_BLINK_ONESHOT, &led_cdev->work_flags); clear_bit(LED_BLINK_ONESHOT_STOP, &led_cdev->work_flags);

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

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

From: Guenter Roeck linux@roeck-us.net

[ Upstream commit 11bca0a83f83f6093d816295668e74ef24595944 ]

An interrupt storm on a bad interrupt will cause the kernel log to be clogged.

[ 60.089234] ->handle_irq(): ffffffffbe2f803f, [ 60.090455] 0xffffffffbf2af380 [ 60.090510] handle_bad_irq+0x0/0x2e5 [ 60.090522] ->irq_data.chip(): ffffffffbf2af380, [ 60.090553] IRQ_NOPROBE set [ 60.090584] ->handle_irq(): ffffffffbe2f803f, [ 60.090590] handle_bad_irq+0x0/0x2e5 [ 60.090596] ->irq_data.chip(): ffffffffbf2af380, [ 60.090602] 0xffffffffbf2af380 [ 60.090608] ->action(): (null) [ 60.090779] handle_bad_irq+0x0/0x2e5

This was seen when running an upstream kernel on Acer Chromebook R11. The system was unstable as result.

Guard the log message with __printk_ratelimit to reduce the impact. This won't prevent the interrupt storm from happening, but at least the system remains stable.

Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Thomas Gleixner tglx@linutronix.de Cc: Dmitry Torokhov dtor@chromium.org Cc: Joe Perches joe@perches.com Cc: Andy Shevchenko andriy.shevchenko@linux.intel.com Cc: Mika Westerberg mika.westerberg@linux.intel.com Link: https://bugzilla.kernel.org/show_bug.cgi?id=197953 Link: https://lkml.kernel.org/r/1512234784-21038-1-git-send-email-linux@roeck-us.n... Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/irq/debug.h | 5 +++++ 1 file changed, 5 insertions(+)

--- a/kernel/irq/debug.h +++ b/kernel/irq/debug.h @@ -12,6 +12,11 @@

static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc) { + static DEFINE_RATELIMIT_STATE(ratelimit, 5 * HZ, 5); + + if (!__ratelimit(&ratelimit)) + return; + printk("irq %d, desc: %p, depth: %d, count: %d, unhandled: %d\n", irq, desc, desc->depth, desc->irq_count, desc->irqs_unhandled); printk("->handle_irq(): %p, ", desc->handle_irq);

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

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

From: Stefan Haberland sth@linux.vnet.ibm.com

[ Upstream commit 8a9bd4f8ebc6800bfc0596e28631ff6809a2f615 ]

We store per path and per device configuration data to identify the path or device correctly. The per path configuration data might get mixed up if the original request gets into error recovery and is started with a random path mask.

This would lead to a wrong identification of a path in case of a CUIR event for example.

Fix by copying the path mask from the original request to the error recovery request in case it is a path verification request.

Signed-off-by: Stefan Haberland sth@linux.vnet.ibm.com Reviewed-by: Jan Hoeppner hoeppner@linux.vnet.ibm.com Signed-off-by: Martin Schwidefsky schwidefsky@de.ibm.com Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/s390/block/dasd_3990_erp.c | 10 ++++++++++ 1 file changed, 10 insertions(+)

--- a/drivers/s390/block/dasd_3990_erp.c +++ b/drivers/s390/block/dasd_3990_erp.c @@ -2803,6 +2803,16 @@ dasd_3990_erp_action(struct dasd_ccw_req erp = dasd_3990_erp_handle_match_erp(cqr, erp); }

+ + /* + * For path verification work we need to stick with the path that was + * originally chosen so that the per path configuration data is + * assigned correctly. + */ + if (test_bit(DASD_CQR_VERIFY_PATH, &erp->flags) && cqr->lpm) { + erp->lpm = cqr->lpm; + } + if (device->features & DASD_FEATURE_ERPLOG) { /* print current erp_chain */ dev_err(&device->cdev->dev,

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

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

From: Xin Long lucien.xin@gmail.com

[ Upstream commit 2fa771be953a17f8e0a9c39103464c2574444c62 ]

Commit 582442d6d5bc ("ipv6: Allow the MTU of ipip6 tunnel to be set below 1280") fixed a mtu setting issue. It works for ipip6 tunnel.

But ip6gre dev updates the mtu also with ip6_tnl_change_mtu. Since the inner packet over ip6gre can be ipv4 and it's mtu should also be allowed to set below 1280, the same issue also exists on ip6gre.

This patch is to fix it by simply changing to check if parms.proto is IPPROTO_IPV6 in ip6_tnl_change_mtu instead, to make ip6gre to go to 'else' branch.

Signed-off-by: Xin Long lucien.xin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/ip6_tunnel.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1684,11 +1684,11 @@ int ip6_tnl_change_mtu(struct net_device { struct ip6_tnl *tnl = netdev_priv(dev);

- if (tnl->parms.proto == IPPROTO_IPIP) { - if (new_mtu < ETH_MIN_MTU) + if (tnl->parms.proto == IPPROTO_IPV6) { + if (new_mtu < IPV6_MIN_MTU) return -EINVAL; } else { - if (new_mtu < IPV6_MIN_MTU) + if (new_mtu < ETH_MIN_MTU) return -EINVAL; } if (new_mtu > 0xFFF8 - dev->hard_header_len)

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

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

From: Leon Romanovsky leonro@mellanox.com

[ Upstream commit 5a371cf87e145b86efd32007e46146e78c1eff6d ]

ibmr.device is being set only after ib_alloc_mr() is successfully complete. Therefore, in case imlx4_mr_enable() returns with error, the error flow unwinder calls to mlx4_free_priv_pages(), which uses ibmr.device.

Such usage causes to NULL dereference oops and to fix it, the IB device should be set in the mr struct earlier stage (e.g. prior to calling mlx4_free_priv_pages()).

Fixes: 1b2cd0fc673c ("IB/mlx4: Support the new memory registration API") Signed-off-by: Nitzan Carmi nitzanc@mellanox.com Signed-off-by: Leon Romanovsky leonro@mellanox.com Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/infiniband/hw/mlx4/mr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/infiniband/hw/mlx4/mr.c +++ b/drivers/infiniband/hw/mlx4/mr.c @@ -406,7 +406,6 @@ struct ib_mr *mlx4_ib_alloc_mr(struct ib goto err_free_mr;

mr->max_pages = max_num_sg; - err = mlx4_mr_enable(dev->dev, &mr->mmr); if (err) goto err_free_pl; @@ -417,6 +416,7 @@ struct ib_mr *mlx4_ib_alloc_mr(struct ib return &mr->ibmr;

err_free_pl: + mr->ibmr.device = pd->device; mlx4_free_priv_pages(mr); err_free_mr: (void) mlx4_mr_free(dev->dev, &mr->mmr);

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

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

From: Aliaksei Karaliou akaraliou.dev@gmail.com

[ Upstream commit 2196881566225f3c3428d1a5f847a992944daa5b ]

xfs_qm_destroy_quotainfo() does not destroy quotainfo->qi_tree_lock while destroys quotainfo->qi_quotaofflock.

Signed-off-by: Aliaksei Karaliou akaraliou.dev@gmail.com Reviewed-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/xfs/xfs_qm.c | 1 + 1 file changed, 1 insertion(+)

--- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -736,6 +736,7 @@ xfs_qm_destroy_quotainfo( IRELE(qi->qi_pquotaip); qi->qi_pquotaip = NULL; } + mutex_destroy(&qi->qi_tree_lock); mutex_destroy(&qi->qi_quotaofflock); kmem_free(qi); mp->m_quotainfo = NULL;

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

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

From: Gao Feng gfree.wind@vip.163.com

[ Upstream commit d02fd6e7d2933ede6478a15f9e4ce8a93845824e ]

Because the macvlan_uninit would free the macvlan port, so there is one double free case in macvlan_common_newlink. When the macvlan port is just created, then register_netdevice or netdev_upper_dev_link failed and they would invoke macvlan_uninit. Then it would reach the macvlan_port_destroy which triggers the double free.

Signed-off-by: Gao Feng gfree.wind@vip.163.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/macvlan.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

--- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1441,9 +1441,14 @@ int macvlan_common_newlink(struct net *s return 0;

unregister_netdev: + /* macvlan_uninit would free the macvlan port */ unregister_netdevice(dev); + return err; destroy_macvlan_port: - if (create) + /* the macvlan port may be freed by macvlan_uninit when fail to register. + * so we destroy the macvlan port only when it's valid. + */ + if (create && macvlan_port_get_rtnl(dev)) macvlan_port_destroy(port->dev); return err; }

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

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

From: Leon Romanovsky leonro@mellanox.com

[ Upstream commit f8978bd95cf92f869f3d9b34c1b699f49253b8c6 ]

Holding locks is mandatory when calling __ib_device_get_by_index, otherwise there are races during the list iteration with device removal.

Since the locks are static to device.c, __ib_device_get_by_index can never be called correctly by any user out side the file.

Make the function static and provide a safe function that gets the correct locks and returns a kref'd pointer. Fix all callers.

Fixes: e5c9469efcb1 ("RDMA/netlink: Add nldev device doit implementation") Fixes: c3f66f7b0052 ("RDMA/netlink: Implement nldev port doit callback") Fixes: 7d02f605f0dc ("RDMA/netlink: Add nldev port dumpit implementation") Reviewed-by: Mark Bloch markb@mellanox.com Signed-off-by: Leon Romanovsky leonro@mellanox.com Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/infiniband/core/core_priv.h | 2 - drivers/infiniband/core/device.c | 18 +++++++++++- drivers/infiniband/core/nldev.c | 54 ++++++++++++++++++++++++------------ 3 files changed, 54 insertions(+), 20 deletions(-)

--- a/drivers/infiniband/core/core_priv.h +++ b/drivers/infiniband/core/core_priv.h @@ -314,7 +314,7 @@ static inline int ib_mad_enforce_securit } #endif

-struct ib_device *__ib_device_get_by_index(u32 ifindex); +struct ib_device *ib_device_get_by_index(u32 ifindex); /* RDMA device netlink */ void nldev_init(void); void nldev_exit(void); --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -134,7 +134,7 @@ static int ib_device_check_mandatory(str return 0; }

-struct ib_device *__ib_device_get_by_index(u32 index) +static struct ib_device *__ib_device_get_by_index(u32 index) { struct ib_device *device;

@@ -145,6 +145,22 @@ struct ib_device *__ib_device_get_by_ind return NULL; }

+/* + * Caller is responsible to return refrerence count by calling put_device() + */ +struct ib_device *ib_device_get_by_index(u32 index) +{ + struct ib_device *device; + + down_read(&lists_rwsem); + device = __ib_device_get_by_index(index); + if (device) + get_device(&device->dev); + + up_read(&lists_rwsem); + return device; +} + static struct ib_device *__ib_device_get_by_name(const char *name) { struct ib_device *device; --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -142,27 +142,34 @@ static int nldev_get_doit(struct sk_buff

index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);

- device = __ib_device_get_by_index(index); + device = ib_device_get_by_index(index); if (!device) return -EINVAL;

msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; + if (!msg) { + err = -ENOMEM; + goto err; + }

nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET), 0, 0);

err = fill_dev_info(msg, device); - if (err) { - nlmsg_free(msg); - return err; - } + if (err) + goto err_free;

nlmsg_end(msg, nlh);

+ put_device(&device->dev); return rdma_nl_unicast(msg, NETLINK_CB(skb).portid); + +err_free: + nlmsg_free(msg); +err: + put_device(&device->dev); + return err; }

static int _nldev_get_dumpit(struct ib_device *device, @@ -220,31 +227,40 @@ static int nldev_port_get_doit(struct sk return -EINVAL;

index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); - device = __ib_device_get_by_index(index); + device = ib_device_get_by_index(index); if (!device) return -EINVAL;

port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]); - if (!rdma_is_port_valid(device, port)) - return -EINVAL; + if (!rdma_is_port_valid(device, port)) { + err = -EINVAL; + goto err; + }

msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; + if (!msg) { + err = -ENOMEM; + goto err; + }

nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET), 0, 0);

err = fill_port_info(msg, device, port); - if (err) { - nlmsg_free(msg); - return err; - } + if (err) + goto err_free;

nlmsg_end(msg, nlh); + put_device(&device->dev);

return rdma_nl_unicast(msg, NETLINK_CB(skb).portid); + +err_free: + nlmsg_free(msg); +err: + put_device(&device->dev); + return err; }

static int nldev_port_get_dumpit(struct sk_buff *skb, @@ -265,7 +281,7 @@ static int nldev_port_get_dumpit(struct return -EINVAL;

ifindex = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); - device = __ib_device_get_by_index(ifindex); + device = ib_device_get_by_index(ifindex); if (!device) return -EINVAL;

@@ -299,7 +315,9 @@ static int nldev_port_get_dumpit(struct nlmsg_end(skb, nlh); }

-out: cb->args[0] = idx; +out: + put_device(&device->dev); + cb->args[0] = idx; return skb->len; }

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

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

From: Felix Janda felix.janda@posteo.de

[ Upstream commit c0bace798436bca0fdc221ff61143f1376a9c3de ]

libc-compat.h aims to prevent symbol collisions between uapi and libc headers for each supported libc. This requires continuous coordination between them.

The goal of this commit is to improve the situation for libcs (such as musl) which are not yet supported and/or do not wish to be explicitly supported, while not affecting supported libcs. More precisely, with this commit, unsupported libcs can request the suppression of any specific uapi definition by defining the correspondings _UAPI_DEF_* macro as 0. This can fix symbol collisions for them, as long as the libc headers are included before the uapi headers. Inclusion in the other order is outside the scope of this commit.

All infrastructure in order to enable this fallback for unsupported libcs is already in place, except that libc-compat.h unconditionally defines all _UAPI_DEF_* macros to 1 for all unsupported libcs so that any previous definitions are ignored. In order to fix this, this commit merely makes these definitions conditional.

This commit together with the musl libc commit

http://git.musl-libc.org/cgit/musl/commit/?id=04983f2272382af92eb8f8838964ff...

fixes for example the following compiler errors when <linux/in6.h> is included after musl's <netinet/in.h>:

./linux/in6.h:32:8: error: redefinition of 'struct in6_addr' ./linux/in6.h:49:8: error: redefinition of 'struct sockaddr_in6' ./linux/in6.h:59:8: error: redefinition of 'struct ipv6_mreq'

The comments referencing glibc are still correct, but this file is not only used for glibc any more.

Signed-off-by: Felix Janda felix.janda@posteo.de Reviewed-by: Hauke Mehrtens hauke@hauke-m.de Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/uapi/linux/libc-compat.h | 55 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 54 insertions(+), 1 deletion(-)

--- a/include/uapi/linux/libc-compat.h +++ b/include/uapi/linux/libc-compat.h @@ -168,46 +168,99 @@

/* If we did not see any headers from any supported C libraries, * or we are being included in the kernel, then define everything - * that we need. */ + * that we need. Check for previous __UAPI_* definitions to give + * unsupported C libraries a way to opt out of any kernel definition. */ #else /* !defined(__GLIBC__) */

/* Definitions for if.h */ +#ifndef __UAPI_DEF_IF_IFCONF #define __UAPI_DEF_IF_IFCONF 1 +#endif +#ifndef __UAPI_DEF_IF_IFMAP #define __UAPI_DEF_IF_IFMAP 1 +#endif +#ifndef __UAPI_DEF_IF_IFNAMSIZ #define __UAPI_DEF_IF_IFNAMSIZ 1 +#endif +#ifndef __UAPI_DEF_IF_IFREQ #define __UAPI_DEF_IF_IFREQ 1 +#endif /* Everything up to IFF_DYNAMIC, matches net/if.h until glibc 2.23 */ +#ifndef __UAPI_DEF_IF_NET_DEVICE_FLAGS #define __UAPI_DEF_IF_NET_DEVICE_FLAGS 1 +#endif /* For the future if glibc adds IFF_LOWER_UP, IFF_DORMANT and IFF_ECHO */ +#ifndef __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO #define __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO 1 +#endif

/* Definitions for in.h */ +#ifndef __UAPI_DEF_IN_ADDR #define __UAPI_DEF_IN_ADDR 1 +#endif +#ifndef __UAPI_DEF_IN_IPPROTO #define __UAPI_DEF_IN_IPPROTO 1 +#endif +#ifndef __UAPI_DEF_IN_PKTINFO #define __UAPI_DEF_IN_PKTINFO 1 +#endif +#ifndef __UAPI_DEF_IP_MREQ #define __UAPI_DEF_IP_MREQ 1 +#endif +#ifndef __UAPI_DEF_SOCKADDR_IN #define __UAPI_DEF_SOCKADDR_IN 1 +#endif +#ifndef __UAPI_DEF_IN_CLASS #define __UAPI_DEF_IN_CLASS 1 +#endif

/* Definitions for in6.h */ +#ifndef __UAPI_DEF_IN6_ADDR #define __UAPI_DEF_IN6_ADDR 1 +#endif +#ifndef __UAPI_DEF_IN6_ADDR_ALT #define __UAPI_DEF_IN6_ADDR_ALT 1 +#endif +#ifndef __UAPI_DEF_SOCKADDR_IN6 #define __UAPI_DEF_SOCKADDR_IN6 1 +#endif +#ifndef __UAPI_DEF_IPV6_MREQ #define __UAPI_DEF_IPV6_MREQ 1 +#endif +#ifndef __UAPI_DEF_IPPROTO_V6 #define __UAPI_DEF_IPPROTO_V6 1 +#endif +#ifndef __UAPI_DEF_IPV6_OPTIONS #define __UAPI_DEF_IPV6_OPTIONS 1 +#endif +#ifndef __UAPI_DEF_IN6_PKTINFO #define __UAPI_DEF_IN6_PKTINFO 1 +#endif +#ifndef __UAPI_DEF_IP6_MTUINFO #define __UAPI_DEF_IP6_MTUINFO 1 +#endif

/* Definitions for ipx.h */ +#ifndef __UAPI_DEF_SOCKADDR_IPX #define __UAPI_DEF_SOCKADDR_IPX 1 +#endif +#ifndef __UAPI_DEF_IPX_ROUTE_DEFINITION #define __UAPI_DEF_IPX_ROUTE_DEFINITION 1 +#endif +#ifndef __UAPI_DEF_IPX_INTERFACE_DEFINITION #define __UAPI_DEF_IPX_INTERFACE_DEFINITION 1 +#endif +#ifndef __UAPI_DEF_IPX_CONFIG_DATA #define __UAPI_DEF_IPX_CONFIG_DATA 1 +#endif +#ifndef __UAPI_DEF_IPX_ROUTE_DEF #define __UAPI_DEF_IPX_ROUTE_DEF 1 +#endif

/* Definitions for xattr.h */ +#ifndef __UAPI_DEF_XATTR #define __UAPI_DEF_XATTR 1 +#endif

#endif /* __GLIBC__ */

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

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

From: Jacob Keller jacob.e.keller@intel.com

[ Upstream commit 458867b2ca0c987445c5d9adccd1642970e1ba07 ]

In some circumstances, such as with bridging, it is possible that the stack will add a devices own MAC address to its unicast address list.

If, later, the stack deletes this address, then the i40e driver will receive a request to remove this address.

The driver stores its current MAC address as part of the MAC/VLAN hash array, since it is convenient and matches exactly how the hardware expects to be told which traffic to receive.

This causes a problem, since for more devices, the MAC address is stored separately, and requests to delete a unicast address should not have the ability to remove the filter for the MAC address.

Fix this by forcing a check on every address sync to ensure we do not remove the device address.

There is a very narrow possibility of a race between .set_mac and .set_rx_mode, if we don't change netdev->dev_addr before updating our internal MAC list in .set_mac. This might be possible if .set_rx_mode is going to remove MAC "XYZ" from the list, at the same time as .set_mac changes our dev_addr to MAC "XYZ", we might possibly queue a delete, then an add in .set_mac, then queue a delete in .set_rx_mode's dev_uc_sync and then update netdev->dev_addr. We can avoid this by moving the copy into dev_addr prior to the changes to the MAC filter list.

A similar race on the other side does not cause problems, as if we're changing our MAC form A to B, and we race with .set_rx_mode, it could queue a delete from A, we'd update our address, and allow the delete. This seems like a race, but in reality we're about to queue a delete of A anyways, so it would not cause any issues.

A race in the initialization code is unlikely because the netdevice has not yet been fully initialized and the stack should not be adding or removing addresses yet.

Note that we don't (yet) need similar code for the VF driver because it does not make use of __dev_uc_sync and __dev_mc_sync, but instead roles its own method for handling updates to the MAC/VLAN list, which already has code to protect against removal of the hardware address.

Signed-off-by: Jacob Keller jacob.e.keller@intel.com Tested-by: Andrew Bowers andrewx.bowers@intel.com Signed-off-by: Jeff Kirsher jeffrey.t.kirsher@intel.com Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/intel/i40e/i40e_main.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-)

--- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1553,11 +1553,18 @@ static int i40e_set_mac(struct net_devic else netdev_info(netdev, "set new mac address %pM\n", addr->sa_data);

+ /* Copy the address first, so that we avoid a possible race with + * .set_rx_mode(). If we copy after changing the address in the filter + * list, we might open ourselves to a narrow race window where + * .set_rx_mode could delete our dev_addr filter and prevent traffic + * from passing. + */ + ether_addr_copy(netdev->dev_addr, addr->sa_data); + spin_lock_bh(&vsi->mac_filter_hash_lock); i40e_del_mac_filter(vsi, netdev->dev_addr); i40e_add_mac_filter(vsi, addr->sa_data); spin_unlock_bh(&vsi->mac_filter_hash_lock); - ether_addr_copy(netdev->dev_addr, addr->sa_data); if (vsi->type == I40E_VSI_MAIN) { i40e_status ret;

@@ -1739,6 +1746,14 @@ static int i40e_addr_unsync(struct net_d struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi;

+ /* Under some circumstances, we might receive a request to delete + * our own device address from our uc list. Because we store the + * device address in the VSI's MAC/VLAN filter list, we need to ignore + * such requests and not delete our device address from this list. + */ + if (ether_addr_equal(addr, netdev->dev_addr)) + return 0; + i40e_del_mac_filter(vsi, addr);

return 0;

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

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

From: Hao Chen flank3rsky@gmail.com

[ Upstream commit 3ea15452ee85754f70f3b9fa1f23165ef2e77ba7 ]

nl80211_nan_add_func() does not check if the required attribute NL80211_NAN_FUNC_FOLLOW_UP_DEST is present when processing NL80211_CMD_ADD_NAN_FUNCTION request. This request can be issued by users with CAP_NET_ADMIN privilege and may result in NULL dereference and a system crash. Add a check for the required attribute presence.

Signed-off-by: Hao Chen flank3rsky@gmail.com Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/wireless/nl80211.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -11301,7 +11301,8 @@ static int nl80211_nan_add_func(struct s break; case NL80211_NAN_FUNC_FOLLOW_UP: if (!tb[NL80211_NAN_FUNC_FOLLOW_UP_ID] || - !tb[NL80211_NAN_FUNC_FOLLOW_UP_REQ_ID]) { + !tb[NL80211_NAN_FUNC_FOLLOW_UP_REQ_ID] || + !tb[NL80211_NAN_FUNC_FOLLOW_UP_DEST]) { err = -EINVAL; goto out; }

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

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

From: Luu An Phu phu.luuan@nxp.com

[ Upstream commit 13454c14550065fcc1705d6bd4ee6d40e057099f ]

The flexcan_start_xmit() function compares the frame length with data register length to write frame content into data[0] and data[1] register. Data register length is 4 bytes and frame maximum length is 8 bytes.

Fix the check that compares frame length with 3. Because the register length is 4.

Signed-off-by: Luu An Phu phu.luuan@nxp.com Reviewed-by: Oliver Hartkopp socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/can/flexcan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -526,7 +526,7 @@ static int flexcan_start_xmit(struct sk_ data = be32_to_cpup((__be32 *)&cf->data[0]); flexcan_write(data, &priv->tx_mb->data[0]); } - if (cf->can_dlc > 3) { + if (cf->can_dlc > 4) { data = be32_to_cpup((__be32 *)&cf->data[4]); flexcan_write(data, &priv->tx_mb->data[1]); }

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

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

From: Ming Lei ming.lei@redhat.com

[ Upstream commit 454be724f6f99cc7e7bbf15067128be9868186c6 ]

Now we track legacy requests with .q_usage_counter in commit 055f6e18e08f ("block: Make q_usage_counter also track legacy requests"), but that commit never runs and drains legacy queue before waiting for this counter becoming zero, then IO hang is caused in the test of pulling disk during IO.

This patch fixes the issue by draining requests before waiting for q_usage_counter becoming zero, both Mauricio and chenxiang reported this issue, and observed that it can be fixed by this patch.

Link: https://marc.info/?l=linux-block&m=151192424731797&w=2 Fixes: 055f6e18e08f("block: Make q_usage_counter also track legacy requests") Cc: Wen Xiong wenxiong@us.ibm.com Tested-by: "chenxiang (M)" chenxiang66@hisilicon.com Tested-by: Mauricio Faria de Oliveira mauricfo@linux.vnet.ibm.com Signed-off-by: Ming Lei ming.lei@redhat.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- block/blk-core.c | 9 +++++++-- block/blk-mq.c | 2 ++ block/blk.h | 2 ++ 3 files changed, 11 insertions(+), 2 deletions(-)

--- a/block/blk-core.c +++ b/block/blk-core.c @@ -531,6 +531,13 @@ static void __blk_drain_queue(struct req } }

+void blk_drain_queue(struct request_queue *q) +{ + spin_lock_irq(q->queue_lock); + __blk_drain_queue(q, true); + spin_unlock_irq(q->queue_lock); +} + /** * blk_queue_bypass_start - enter queue bypass mode * @q: queue of interest @@ -655,8 +662,6 @@ void blk_cleanup_queue(struct request_qu */ blk_freeze_queue(q); spin_lock_irq(lock); - if (!q->mq_ops) - __blk_drain_queue(q, true); queue_flag_set(QUEUE_FLAG_DEAD, q); spin_unlock_irq(lock);

--- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -159,6 +159,8 @@ void blk_freeze_queue(struct request_que * exported to drivers as the only user for unfreeze is blk_mq. */ blk_freeze_queue_start(q); + if (!q->mq_ops) + blk_drain_queue(q); blk_mq_freeze_queue_wait(q); }

--- a/block/blk.h +++ b/block/blk.h @@ -362,4 +362,6 @@ static inline void blk_queue_bounce(stru } #endif /* CONFIG_BOUNCE */

+extern void blk_drain_queue(struct request_queue *q); + #endif /* BLK_INTERNAL_H */

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

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

From: John Fastabend john.fastabend@gmail.com

[ Upstream commit 5731a879d03bdaa00265f8ebc32dfd0e65d25276 ]

Add psock NULL check to handle a racing sock event that can get the sk_callback_lock before this case but after xchg happens causing the refcnt to hit zero and sock user data (psock) to be null and queued for garbage collection.

Also add a comment in the code because this is a bit subtle and not obvious in my opinion.

Signed-off-by: John Fastabend john.fastabend@gmail.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/bpf/sockmap.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)

--- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -588,8 +588,15 @@ static void sock_map_free(struct bpf_map

write_lock_bh(&sock->sk_callback_lock); psock = smap_psock_sk(sock); - smap_list_remove(psock, &stab->sock_map[i]); - smap_release_sock(psock, sock); + /* This check handles a racing sock event that can get the + * sk_callback_lock before this case but after xchg happens + * causing the refcnt to hit zero and sock user data (psock) + * to be null and queued for garbage collection. + */ + if (likely(psock)) { + smap_list_remove(psock, &stab->sock_map[i]); + smap_release_sock(psock, sock); + } write_unlock_bh(&sock->sk_callback_lock); } rcu_read_unlock();

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

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

From: Michael Ellerman mpe@ellerman.id.au

[ Upstream commit e2d5915293ffdff977ddcfc12b817b08c53ffa7a ]

The hotplug code uses its own workqueue to handle IRQ requests (pseries_hp_wq), however that workqueue is initialized after init_ras_IRQ(). That can lead to a kernel panic if any hotplug interrupts fire after init_ras_IRQ() but before pseries_hp_wq is initialised. eg:

UDP-Lite hash table entries: 2048 (order: 0, 65536 bytes) NET: Registered protocol family 1 Unpacking initramfs... (qemu) object_add memory-backend-ram,id=mem1,size=10G (qemu) device_add pc-dimm,id=dimm1,memdev=mem1 Unable to handle kernel paging request for data at address 0xf94d03007c421378 Faulting instruction address: 0xc00000000012d744 Oops: Kernel access of bad area, sig: 11 [#1] LE SMP NR_CPUS=2048 NUMA pSeries Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.15.0-rc2-ziviani+ #26 task: (ptrval) task.stack: (ptrval) NIP: c00000000012d744 LR: c00000000012d744 CTR: 0000000000000000 REGS: (ptrval) TRAP: 0380 Not tainted (4.15.0-rc2-ziviani+) MSR: 8000000000009033 <SF,EE,ME,IR,DR,RI,LE> CR: 28088042 XER: 20040000 CFAR: c00000000012d3c4 SOFTE: 0 ... NIP [c00000000012d744] __queue_work+0xd4/0x5c0 LR [c00000000012d744] __queue_work+0xd4/0x5c0 Call Trace: [c0000000fffefb90] [c00000000012d744] __queue_work+0xd4/0x5c0 (unreliable) [c0000000fffefc70] [c00000000012dce4] queue_work_on+0xb4/0xf0

This commit makes the RAS IRQ registration explicitly dependent on the creation of the pseries_hp_wq.

Reported-by: Min Deng mdeng@redhat.com Reported-by: Daniel Henrique Barboza danielhb@linux.vnet.ibm.com Tested-by: Jose Ricardo Ziviani joserz@linux.vnet.ibm.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Reviewed-by: David Gibson david@gibson.dropbear.id.au Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/platforms/pseries/dlpar.c | 21 ++++++++++++++++++--- arch/powerpc/platforms/pseries/pseries.h | 2 ++ arch/powerpc/platforms/pseries/ras.c | 3 ++- 3 files changed, 22 insertions(+), 4 deletions(-)

--- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -586,11 +586,26 @@ static ssize_t dlpar_show(struct class *

static CLASS_ATTR_RW(dlpar);

-static int __init pseries_dlpar_init(void) +int __init dlpar_workqueue_init(void) { + if (pseries_hp_wq) + return 0; + pseries_hp_wq = alloc_workqueue("pseries hotplug workqueue", - WQ_UNBOUND, 1); + WQ_UNBOUND, 1); + + return pseries_hp_wq ? 0 : -ENOMEM; +} + +static int __init dlpar_sysfs_init(void) +{ + int rc; + + rc = dlpar_workqueue_init(); + if (rc) + return rc; + return sysfs_create_file(kernel_kobj, &class_attr_dlpar.attr); } -machine_device_initcall(pseries, pseries_dlpar_init); +machine_device_initcall(pseries, dlpar_sysfs_init);

--- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -98,4 +98,6 @@ static inline unsigned long cmo_get_page return CMO_PageSize; }

+int dlpar_workqueue_init(void); + #endif /* _PSERIES_PSERIES_H */ --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -69,7 +69,8 @@ static int __init init_ras_IRQ(void) /* Hotplug Events */ np = of_find_node_by_path("/event-sources/hot-plug-events"); if (np != NULL) { - request_event_sources_irqs(np, ras_hotplug_interrupt, + if (dlpar_workqueue_init() == 0) + request_event_sources_irqs(np, ras_hotplug_interrupt, "RAS_HOTPLUG"); of_node_put(np); }

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

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

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

[ Upstream commit 9d0513d82f1a8fe17b41f113ac5922fa57dbaf5c ]

So one of the constification patches unearthed a type casting fragility of the underlying code:

276c87054751 ("x86/platform/intel-mid: Make 'bt_sfi_data' const")

converted the struct to be const while it is also used as a temporary container for important data that is used to fill 'parent' and 'name' fields in struct platform_device_info.

The compiler doesn't notice this due to an explicit type cast that loses the const - which fragility will be fixed separately.

This type cast turned a seemingly trivial const propagation patch into a hard to debug data corruptor and crasher bug.

Signed-off-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Cc: Bhumika Goyal bhumirks@gmail.com Cc: Darren Hart dvhart@infradead.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Cc: julia.lawall@lip6.fr Cc: platform-driver-x86@vger.kernel.org Link: http://lkml.kernel.org/r/20171228122523.21802-1-andriy.shevchenko@linux.inte... Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/platform/intel-mid/device_libs/platform_bt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/platform/intel-mid/device_libs/platform_bt.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_bt.c @@ -60,7 +60,7 @@ static int __init tng_bt_sfi_setup(struc return 0; }

-static const struct bt_sfi_data tng_bt_sfi_data __initdata = { +static struct bt_sfi_data tng_bt_sfi_data __initdata = { .setup = tng_bt_sfi_setup, };

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

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

From: Venkat Duvvuru venkatkumar.duvvuru@broadcom.com

[ Upstream commit 78f300049335ae81a5cc6b4b232481dc5e1f9d41 ]

In bnxt_vf_ndo_prep (which is called by bnxt_get_vf_config ndo), there is a check for "Invalid VF id". Currently, the check is done against max_vfs. However, the user doesn't always create max_vfs. So, the check should be against the created number of VFs. The number of bnxt_vf_info structures that are allocated in bnxt_alloc_vf_resources routine is the "number of requested VFs". So, if an "invalid VF id" falls between the requested number of VFs and the max_vfs, the driver will be dereferencing an invalid pointer.

Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.") Signed-off-by: Venkat Devvuru venkatkumar.duvvuru@broadcom.com Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -70,7 +70,7 @@ static int bnxt_vf_ndo_prep(struct bnxt netdev_err(bp->dev, "vf ndo called though sriov is disabled\n"); return -EINVAL; } - if (vf_id >= bp->pf.max_vfs) { + if (vf_id >= bp->pf.active_vfs) { netdev_err(bp->dev, "Invalid VF id %d\n", vf_id); return -EINVAL; }

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

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

From: Christophe JAILLET christophe.jaillet@wanadoo.fr

[ Upstream commit 56c0290202ab94a2f2780c449395d4ae8495fab4 ]

If the probing of the regulator is deferred, the memory allocated by 'mdiobus_alloc_size()' will be leaking. It should be freed before the next call to 'sun4i_mdio_probe()' which will reallocate it.

Fixes: 4bdcb1dd9feb ("net: Add MDIO bus driver for the Allwinner EMAC") Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/phy/mdio-sun4i.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/drivers/net/phy/mdio-sun4i.c +++ b/drivers/net/phy/mdio-sun4i.c @@ -118,8 +118,10 @@ static int sun4i_mdio_probe(struct platf

data->regulator = devm_regulator_get(&pdev->dev, "phy"); if (IS_ERR(data->regulator)) { - if (PTR_ERR(data->regulator) == -EPROBE_DEFER) - return -EPROBE_DEFER; + if (PTR_ERR(data->regulator) == -EPROBE_DEFER) { + ret = -EPROBE_DEFER; + goto err_out_free_mdiobus; + }

dev_info(&pdev->dev, "no regulator found\n"); data->regulator = NULL;

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

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

From: Ross Lagerwall ross.lagerwall@citrix.com

[ Upstream commit 951a010233625b77cde3430b4b8785a9a22968d1 ]

If the requested range has a hole, the calculation of the number of pages to unmap is off by one. Fix it.

Signed-off-by: Ross Lagerwall ross.lagerwall@citrix.com Reviewed-by: Boris Ostrovsky boris.ostrovsky@oracle.com Signed-off-by: Boris Ostrovsky boris.ostrovsky@oracle.com Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/xen/gntdev.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

--- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -380,10 +380,8 @@ static int unmap_grant_pages(struct gran } range = 0; while (range < pages) { - if (map->unmap_ops[offset+range].handle == -1) { - range--; + if (map->unmap_ops[offset+range].handle == -1) break; - } range++; } err = __unmap_grant_pages(map, offset, range);

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

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

From: Marcelo Ricardo Leitner marcelo.leitner@gmail.com

[ Upstream commit 5960cefab9df76600a1a7d4ff592c59e14616e88 ]

Hangbin Liu reported that some sockopt calls could cause the kernel to log a warning on memory allocation failure if the user supplied a large optlen value. That is because some of them called memdup_user() without a ceiling on optlen, allowing it to try to allocate really large buffers.

This patch adds a ceiling by limiting optlen to the maximum allowed that would still make sense for these sockopt.

Reported-by: Hangbin Liu haliu@redhat.com Signed-off-by: Marcelo Ricardo Leitner marcelo.leitner@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sctp/socket.c | 10 ++++++++++ 1 file changed, 10 insertions(+)

--- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3494,6 +3494,8 @@ static int sctp_setsockopt_hmac_ident(st

if (optlen < sizeof(struct sctp_hmacalgo)) return -EINVAL; + optlen = min_t(unsigned int, optlen, sizeof(struct sctp_hmacalgo) + + SCTP_AUTH_NUM_HMACS * sizeof(u16));

hmacs = memdup_user(optval, optlen); if (IS_ERR(hmacs)) @@ -3532,6 +3534,11 @@ static int sctp_setsockopt_auth_key(stru

if (optlen <= sizeof(struct sctp_authkey)) return -EINVAL; + /* authkey->sca_keylength is u16, so optlen can't be bigger than + * this. + */ + optlen = min_t(unsigned int, optlen, USHRT_MAX + + sizeof(struct sctp_authkey));

authkey = memdup_user(optval, optlen); if (IS_ERR(authkey)) @@ -3889,6 +3896,9 @@ static int sctp_setsockopt_reset_streams

if (optlen < sizeof(*params)) return -EINVAL; + /* srs_number_streams is u16, so optlen can't be bigger than this. */ + optlen = min_t(unsigned int, optlen, USHRT_MAX + + sizeof(__u16) * sizeof(*params));

params = memdup_user(optval, optlen); if (IS_ERR(params))

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

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

From: Yangbo Lu yangbo.lu@nxp.com

[ Upstream commit 11d827a993a969c3c6ec56758ff63a44ba19b466 ]

set_fipers() calling should be protected by spinlock in case that any interrupt breaks related registers setting and the function we expect. This patch is to move set_fipers() to spinlock protecting area in ptp_gianfar_adjtime().

Signed-off-by: Yangbo Lu yangbo.lu@nxp.com Acked-by: Richard Cochran richardcochran@gmail.com Reviewed-by: Fabio Estevam fabio.estevam@nxp.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/freescale/gianfar_ptp.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/drivers/net/ethernet/freescale/gianfar_ptp.c +++ b/drivers/net/ethernet/freescale/gianfar_ptp.c @@ -319,11 +319,10 @@ static int ptp_gianfar_adjtime(struct pt now = tmr_cnt_read(etsects); now += delta; tmr_cnt_write(etsects, now); + set_fipers(etsects);

spin_unlock_irqrestore(&etsects->lock, flags);

- set_fipers(etsects); - return 0; }

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

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

From: Jakub Kicinski jakub.kicinski@netronome.com

[ Upstream commit fc2336505fb49a8b932a0a67a9745c408b79992c ]

The link state and exception interrupts may be masked when we probe. The firmware should in theory prevent sending (and automasking) those interrupts if the device is disabled, but if my reading of the FW code is correct there are firmwares out there with race conditions in this area. The interrupt may also be masked if previous driver which used the device was malfunctioning and we didn't load the FW (there is no other good way to comprehensively reset the PF).

Note that FW unmasks the data interrupts by itself when vNIC is enabled, such helpful operation is not performed for LSC/EXN interrupts.

Always unmask the auxiliary interrupts after request_irq(). On the remove path add missing PCI write flush before free_irq().

Fixes: 4c3523623dc0 ("net: add driver for Netronome NFP4000/NFP6000 NIC VFs") Signed-off-by: Jakub Kicinski jakub.kicinski@netronome.com Reviewed-by: Dirk van der Merwe dirk.vandermerwe@netronome.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -568,6 +568,7 @@ nfp_net_aux_irq_request(struct nfp_net * return err; } nn_writeb(nn, ctrl_offset, entry->entry); + nfp_net_irq_unmask(nn, entry->entry);

return 0; } @@ -582,6 +583,7 @@ static void nfp_net_aux_irq_free(struct unsigned int vector_idx) { nn_writeb(nn, ctrl_offset, 0xff); + nn_pci_flush(nn); free_irq(nn->irq_entries[vector_idx].vector, nn); }

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

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

From: James Hogan jhogan@kernel.org

commit ebabcf17bcd7ce968b1631ebe08236275698f39b upstream.

GCC7 is a bit too eager to generate suboptimal __multi3 calls (128bit multiply with 128bit result) for MIPS64r6 builds, even in code which doesn't explicitly use 128bit types, such as the following:

unsigned long func(unsigned long a, unsigned long b) { return a > (~0UL) / b; }

Which GCC rearanges to:

return (unsigned __int128)a * (unsigned __int128)b > 0xffffffffffffffff;

Therefore implement __multi3, but only for MIPS64r6 with GCC7 as under normal circumstances we wouldn't expect any calls to __multi3 to be generated from kernel code.

Reported-by: Thomas Petazzoni thomas.petazzoni@free-electrons.com Signed-off-by: James Hogan jhogan@kernel.org Tested-by: Waldemar Brodkorb wbx@openadk.org Cc: Ralf Baechle ralf@linux-mips.org Cc: Maciej W. Rozycki macro@mips.com Cc: Matthew Fortune matthew.fortune@mips.com Cc: Florian Fainelli florian@openwrt.org Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17890/ Cc: Guenter Roeck linux@roeck-us.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/mips/lib/Makefile | 3 +- arch/mips/lib/libgcc.h | 17 +++++++++++++++ arch/mips/lib/multi3.c | 54 +++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 73 insertions(+), 1 deletion(-)

--- a/arch/mips/lib/Makefile +++ b/arch/mips/lib/Makefile @@ -16,4 +16,5 @@ obj-$(CONFIG_CPU_R3000) += r3k_dump_tlb obj-$(CONFIG_CPU_TX39XX) += r3k_dump_tlb.o

# libgcc-style stuff needed in the kernel -obj-y += ashldi3.o ashrdi3.o bswapsi.o bswapdi.o cmpdi2.o lshrdi3.o ucmpdi2.o +obj-y += ashldi3.o ashrdi3.o bswapsi.o bswapdi.o cmpdi2.o lshrdi3.o multi3.o \ + ucmpdi2.o --- a/arch/mips/lib/libgcc.h +++ b/arch/mips/lib/libgcc.h @@ -10,10 +10,18 @@ typedef int word_type __attribute__ ((mo struct DWstruct { int high, low; }; + +struct TWstruct { + long long high, low; +}; #elif defined(__LITTLE_ENDIAN) struct DWstruct { int low, high; }; + +struct TWstruct { + long long low, high; +}; #else #error I feel sick. #endif @@ -23,4 +31,13 @@ typedef union { long long ll; } DWunion;

+#if defined(CONFIG_64BIT) && defined(CONFIG_CPU_MIPSR6) +typedef int ti_type __attribute__((mode(TI))); + +typedef union { + struct TWstruct s; + ti_type ti; +} TWunion; +#endif + #endif /* __ASM_LIBGCC_H */ --- /dev/null +++ b/arch/mips/lib/multi3.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/export.h> + +#include "libgcc.h" + +/* + * GCC 7 suboptimally generates __multi3 calls for mips64r6, so for that + * specific case only we'll implement it here. + * + * See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82981 + */ +#if defined(CONFIG_64BIT) && defined(CONFIG_CPU_MIPSR6) && (__GNUC__ == 7) + +/* multiply 64-bit values, low 64-bits returned */ +static inline long long notrace dmulu(long long a, long long b) +{ + long long res; + + asm ("dmulu %0,%1,%2" : "=r" (res) : "r" (a), "r" (b)); + return res; +} + +/* multiply 64-bit unsigned values, high 64-bits of 128-bit result returned */ +static inline long long notrace dmuhu(long long a, long long b) +{ + long long res; + + asm ("dmuhu %0,%1,%2" : "=r" (res) : "r" (a), "r" (b)); + return res; +} + +/* multiply 128-bit values, low 128-bits returned */ +ti_type notrace __multi3(ti_type a, ti_type b) +{ + TWunion res, aa, bb; + + aa.ti = a; + bb.ti = b; + + /* + * a * b = (a.lo * b.lo) + * + 2^64 * (a.hi * b.lo + a.lo * b.hi) + * [+ 2^128 * (a.hi * b.hi)] + */ + res.s.low = dmulu(aa.s.low, bb.s.low); + res.s.high = dmuhu(aa.s.low, bb.s.low); + res.s.high += dmulu(aa.s.high, bb.s.low); + res.s.high += dmulu(aa.s.low, bb.s.high); + + return res.ti; +} +EXPORT_SYMBOL(__multi3); + +#endif /* 64BIT && CPU_MIPSR6 && GCC7 */

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

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

From: Antoine Tenart antoine.tenart@free-electrons.com

commit 910d1bf2c68fa1d7dcde0316cb91f62758407e8d upstream.

This patch describes the comphy available in the cp110 master and slave. This comphy provides serdes lanes used by various controllers such as the network one.

Signed-off-by: Antoine Tenart antoine.tenart@free-electrons.com Signed-off-by: Gregory CLEMENT gregory.clement@free-electrons.com Cc: Mikulas Patocka mpatocka@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi | 38 +++++++++++++++++++ arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi | 38 +++++++++++++++++++ 2 files changed, 76 insertions(+)

--- a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi @@ -111,6 +111,44 @@ }; };

+ cpm_comphy: phy@120000 { + compatible = "marvell,comphy-cp110"; + reg = <0x120000 0x6000>; + marvell,system-controller = <&cpm_syscon0>; + #address-cells = <1>; + #size-cells = <0>; + + cpm_comphy0: phy@0 { + reg = <0>; + #phy-cells = <1>; + }; + + cpm_comphy1: phy@1 { + reg = <1>; + #phy-cells = <1>; + }; + + cpm_comphy2: phy@2 { + reg = <2>; + #phy-cells = <1>; + }; + + cpm_comphy3: phy@3 { + reg = <3>; + #phy-cells = <1>; + }; + + cpm_comphy4: phy@4 { + reg = <4>; + #phy-cells = <1>; + }; + + cpm_comphy5: phy@5 { + reg = <5>; + #phy-cells = <1>; + }; + }; + cpm_mdio: mdio@12a200 { #address-cells = <1>; #size-cells = <0>; --- a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi @@ -111,6 +111,44 @@ }; };

+ cps_comphy: phy@120000 { + compatible = "marvell,comphy-cp110"; + reg = <0x120000 0x6000>; + marvell,system-controller = <&cps_syscon0>; + #address-cells = <1>; + #size-cells = <0>; + + cps_comphy0: phy@0 { + reg = <0>; + #phy-cells = <1>; + }; + + cps_comphy1: phy@1 { + reg = <1>; + #phy-cells = <1>; + }; + + cps_comphy2: phy@2 { + reg = <2>; + #phy-cells = <1>; + }; + + cps_comphy3: phy@3 { + reg = <3>; + #phy-cells = <1>; + }; + + cps_comphy4: phy@4 { + reg = <4>; + #phy-cells = <1>; + }; + + cps_comphy5: phy@5 { + reg = <5>; + #phy-cells = <1>; + }; + }; + cps_mdio: mdio@12a200 { #address-cells = <1>; #size-cells = <0>;

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

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

From: Roman Kapl code@rkapl.cz

commit d7aa04a5e82b4f254d306926c81eae8df69e5200 upstream.

If you flush (delete) a filter chain other than chain 0 (such as when deleting the device), the kernel may run into a use-after-free. The chain refcount must not be decremented unless we are sure we are done with the chain.

To reproduce the bug, run: ip link add dtest type dummy tc qdisc add dev dtest ingress tc filter add dev dtest chain 1 parent ffff: flower ip link del dtest

Introduced in: commit f93e1cdcf42c ("net/sched: fix filter flushing"), but unless you have KAsan or luck, you won't notice it until commit 0dadc117ac8b ("cls_flower: use tcf_exts_get_net() before call_rcu()")

Fixes: f93e1cdcf42c ("net/sched: fix filter flushing") Acked-by: Jiri Pirko jiri@mellanox.com Signed-off-by: Roman Kapl code@rkapl.cz Signed-off-by: David S. Miller davem@davemloft.net Cc: Cong Wang xiyou.wangcong@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/sched/cls_api.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

--- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -197,14 +197,15 @@ static struct tcf_chain *tcf_chain_creat

static void tcf_chain_flush(struct tcf_chain *chain) { - struct tcf_proto *tp; + struct tcf_proto *tp = rtnl_dereference(chain->filter_chain);

if (chain->p_filter_chain) RCU_INIT_POINTER(*chain->p_filter_chain, NULL); - while ((tp = rtnl_dereference(chain->filter_chain)) != NULL) { + while (tp) { RCU_INIT_POINTER(chain->filter_chain, tp->next); - tcf_chain_put(chain); tcf_proto_destroy(tp); + tp = rtnl_dereference(chain->filter_chain); + tcf_chain_put(chain); } }

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

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

From: Cong Wang xiyou.wangcong@gmail.com

commit efbf78973978b0d25af59bc26c8013a942af6e64 upstream.

Both Eric and Paolo noticed the rcu_barrier() we use in tcf_block_put_ext() could be a performance bottleneck when we have a lot of tc classes.

Paolo provided the following to demonstrate the issue:

tc qdisc add dev lo root htb for I in `seq 1 1000`; do tc class add dev lo parent 1: classid 1:$I htb rate 100kbit tc qdisc add dev lo parent 1:$I handle $((I + 1)): htb for J in `seq 1 10`; do tc filter add dev lo parent $((I + 1)): u32 match ip src 1.1.1.$J done done time tc qdisc del dev root

real 0m54.764s user 0m0.023s sys 0m0.000s

The rcu_barrier() there is to ensure we free the block after all chains are gone, that is, to queue tcf_block_put_final() at the tail of workqueue. We can achieve this ordering requirement by refcnt'ing tcf block instead, that is, the tcf block is freed only when the last chain in this block is gone. This also simplifies the code.

Paolo reported after this patch we get:

real 0m0.017s user 0m0.000s sys 0m0.017s

Tested-by: Paolo Abeni pabeni@redhat.com Cc: Eric Dumazet edumazet@google.com Cc: Jiri Pirko jiri@mellanox.com Cc: Jamal Hadi Salim jhs@mojatatu.com Signed-off-by: Cong Wang xiyou.wangcong@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- include/net/sch_generic.h | 1 - net/sched/cls_api.c | 29 +++++++++-------------------- 2 files changed, 9 insertions(+), 21 deletions(-)

--- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -273,7 +273,6 @@ struct tcf_chain {

struct tcf_block { struct list_head chain_list; - struct work_struct work; };

static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -211,8 +211,12 @@ static void tcf_chain_flush(struct tcf_c

static void tcf_chain_destroy(struct tcf_chain *chain) { + struct tcf_block *block = chain->block; + list_del(&chain->list); kfree(chain); + if (list_empty(&block->chain_list)) + kfree(block); }

static void tcf_chain_hold(struct tcf_chain *chain) @@ -276,26 +280,12 @@ err_chain_create: } EXPORT_SYMBOL(tcf_block_get);

-static void tcf_block_put_final(struct work_struct *work) -{ - struct tcf_block *block = container_of(work, struct tcf_block, work); - struct tcf_chain *chain, *tmp; - - rtnl_lock(); - - /* At this point, all the chains should have refcnt == 1. */ - list_for_each_entry_safe(chain, tmp, &block->chain_list, list) - tcf_chain_put(chain); - rtnl_unlock(); - kfree(block); -} - /* XXX: Standalone actions are not allowed to jump to any chain, and bound * actions should be all removed after flushing. */ void tcf_block_put(struct tcf_block *block) { - struct tcf_chain *chain; + struct tcf_chain *chain, *tmp;

if (!block) return; @@ -310,12 +300,11 @@ void tcf_block_put(struct tcf_block *blo list_for_each_entry(chain, &block->chain_list, list) tcf_chain_flush(chain);

- INIT_WORK(&block->work, tcf_block_put_final); - /* Wait for RCU callbacks to release the reference count and make - * sure their works have been queued before this. + /* At this point, all the chains should have refcnt >= 1. Block will be + * freed after all chains are gone. */ - rcu_barrier(); - tcf_queue_work(&block->work); + list_for_each_entry_safe(chain, tmp, &block->chain_list, list) + tcf_chain_put(chain); } EXPORT_SYMBOL(tcf_block_put);