[ Upstream commit 1196364f21ffe5d1e6d83cafd6a2edb89404a3ae ]

calc_vmlinuz_load_addr.c requires SZ_64K to be defined for alignment purposes. It included "../../../../include/linux/sizes.h" to define that size, however "sizes.h" tries to include <linux/const.h> which assumes linux system headers. These may not exist eg. the following error was encountered when building Linux for OpenWrt under macOS:

In file included from arch/mips/boot/compressed/calc_vmlinuz_load_addr.c:16: arch/mips/boot/compressed/../../../../include/linux/sizes.h:11:10: fatal error: 'linux/const.h' file not found ^~~~~~~~~~

Change makefile to force building on local linux headers instead of system headers. Also change eye-watering relative reference in include file spec.

Thanks to Jo-Philip Wich & Petr Štetiar for assistance in tracking this down & fixing.

Suggested-by: Jo-Philipp Wich jo@mein.io Signed-off-by: Petr Štetiar ynezz@true.cz Signed-off-by: Kevin Darbyshire-Bryant ldir@darbyshire-bryant.me.uk Signed-off-by: Paul Burton paul.burton@mips.com Cc: linux-mips@vger.kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/mips/boot/compressed/Makefile | 2 ++ arch/mips/boot/compressed/calc_vmlinuz_load_addr.c | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile index 90aca95fe314..ad31c76c7a29 100644 --- a/arch/mips/boot/compressed/Makefile +++ b/arch/mips/boot/compressed/Makefile @@ -75,6 +75,8 @@ OBJCOPYFLAGS_piggy.o := --add-section=.image=$(obj)/vmlinux.bin.z \ $(obj)/piggy.o: $(obj)/dummy.o $(obj)/vmlinux.bin.z FORCE $(call if_changed,objcopy)

+HOSTCFLAGS_calc_vmlinuz_load_addr.o += $(LINUXINCLUDE) + # Calculate the load address of the compressed kernel image hostprogs-y := calc_vmlinuz_load_addr

diff --git a/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c b/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c index 542c3ede9722..d14f75ec8273 100644 --- a/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c +++ b/arch/mips/boot/compressed/calc_vmlinuz_load_addr.c @@ -13,7 +13,7 @@ #include <stdint.h> #include <stdio.h> #include <stdlib.h> -#include "../../../../include/linux/sizes.h" +#include <linux/sizes.h>

int main(int argc, char *argv[]) {

[ Upstream commit 2b8066c3deb9140fdf258417a51479b2aeaa7622 ]

If probe() fails anywhere beyond the point where sdma_get_firmware() is called, then a kernel oops may occur.

Problematic sequence of events: 1. probe() calls sdma_get_firmware(), which schedules the firmware callback to run when firmware becomes available, using the sdma instance structure as the context 2. probe() encounters an error, which deallocates the sdma instance structure 3. firmware becomes available, firmware callback is called with deallocated sdma instance structure 4. use after free - kernel oops !

Solution: only attempt to load firmware when we're certain that probe() will succeed. This guarantees that the firmware callback's context will remain valid.

Note that the remove() path is unaffected by this issue: the firmware loader will increment the driver module's use count, ensuring that the module cannot be unloaded while the firmware callback is pending or running.

Signed-off-by: Sven Van Asbroeck TheSven73@gmail.com Reviewed-by: Robin Gong yibin.gong@nxp.com [vkoul: fixed braces for if condition] Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/imx-sdma.c | 48 ++++++++++++++++++++++++------------------ 1 file changed, 27 insertions(+), 21 deletions(-)

diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index 84856ac75a09..9f240b2d85a5 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -1821,27 +1821,6 @@ static int sdma_probe(struct platform_device *pdev) if (pdata && pdata->script_addrs) sdma_add_scripts(sdma, pdata->script_addrs);

- if (pdata) { - ret = sdma_get_firmware(sdma, pdata->fw_name); - if (ret) - dev_warn(&pdev->dev, "failed to get firmware from platform data\n"); - } else { - /* - * Because that device tree does not encode ROM script address, - * the RAM script in firmware is mandatory for device tree - * probe, otherwise it fails. - */ - ret = of_property_read_string(np, "fsl,sdma-ram-script-name", - &fw_name); - if (ret) - dev_warn(&pdev->dev, "failed to get firmware name\n"); - else { - ret = sdma_get_firmware(sdma, fw_name); - if (ret) - dev_warn(&pdev->dev, "failed to get firmware from device tree\n"); - } - } - sdma->dma_device.dev = &pdev->dev;

sdma->dma_device.device_alloc_chan_resources = sdma_alloc_chan_resources; @@ -1883,6 +1862,33 @@ static int sdma_probe(struct platform_device *pdev) of_node_put(spba_bus); }

+ /* + * Kick off firmware loading as the very last step: + * attempt to load firmware only if we're not on the error path, because + * the firmware callback requires a fully functional and allocated sdma + * instance. + */ + if (pdata) { + ret = sdma_get_firmware(sdma, pdata->fw_name); + if (ret) + dev_warn(&pdev->dev, "failed to get firmware from platform data\n"); + } else { + /* + * Because that device tree does not encode ROM script address, + * the RAM script in firmware is mandatory for device tree + * probe, otherwise it fails. + */ + ret = of_property_read_string(np, "fsl,sdma-ram-script-name", + &fw_name); + if (ret) { + dev_warn(&pdev->dev, "failed to get firmware name\n"); + } else { + ret = sdma_get_firmware(sdma, fw_name); + if (ret) + dev_warn(&pdev->dev, "failed to get firmware from device tree\n"); + } + } + return 0;

err_register:

[ Upstream commit 2f90c7e5d09437a4d8d5546feaae9f1cf48cfbe1 ]

Right now, if an error is encountered during the SREV register read (i.e. an EIO in ath9k_regread()), that error code gets passed all the way to __ath9k_hw_init(), where it is visible during the "Chip rev not supported" message.

ath9k_htc 1-1.4:1.0: ath9k_htc: HTC initialized with 33 credits ath: phy2: Mac Chip Rev 0x0f.3 is not supported by this driver ath: phy2: Unable to initialize hardware; initialization status: -95 ath: phy2: Unable to initialize hardware; initialization status: -95 ath9k_htc: Failed to initialize the device

Check for -EIO explicitly in ath9k_hw_read_revisions() and return a boolean based on the success of the operation. Check for that in __ath9k_hw_init() and abort with a more debugging-friendly message if reading the revisions wasn't successful.

ath9k_htc 1-1.4:1.0: ath9k_htc: HTC initialized with 33 credits ath: phy2: Failed to read SREV register ath: phy2: Could not read hardware revision ath: phy2: Unable to initialize hardware; initialization status: -95 ath: phy2: Unable to initialize hardware; initialization status: -95 ath9k_htc: Failed to initialize the device

This helps when debugging by directly showing the first point of failure and it could prevent possible errors if a 0x0f.3 revision is ever supported.

Signed-off-by: Tim Schumacher timschumi@gmx.de Signed-off-by: Kalle Valo kvalo@codeaurora.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/ath/ath9k/hw.c | 32 +++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c index 951bac2caf12..e7fca78cdd96 100644 --- a/drivers/net/wireless/ath/ath9k/hw.c +++ b/drivers/net/wireless/ath/ath9k/hw.c @@ -250,8 +250,9 @@ void ath9k_hw_get_channel_centers(struct ath_hw *ah, /* Chip Revisions */ /******************/

-static void ath9k_hw_read_revisions(struct ath_hw *ah) +static bool ath9k_hw_read_revisions(struct ath_hw *ah) { + u32 srev; u32 val;

if (ah->get_mac_revision) @@ -267,25 +268,33 @@ static void ath9k_hw_read_revisions(struct ath_hw *ah) val = REG_READ(ah, AR_SREV); ah->hw_version.macRev = MS(val, AR_SREV_REVISION2); } - return; + return true; case AR9300_DEVID_AR9340: ah->hw_version.macVersion = AR_SREV_VERSION_9340; - return; + return true; case AR9300_DEVID_QCA955X: ah->hw_version.macVersion = AR_SREV_VERSION_9550; - return; + return true; case AR9300_DEVID_AR953X: ah->hw_version.macVersion = AR_SREV_VERSION_9531; - return; + return true; case AR9300_DEVID_QCA956X: ah->hw_version.macVersion = AR_SREV_VERSION_9561; - return; + return true; }

- val = REG_READ(ah, AR_SREV) & AR_SREV_ID; + srev = REG_READ(ah, AR_SREV); + + if (srev == -EIO) { + ath_err(ath9k_hw_common(ah), + "Failed to read SREV register"); + return false; + } + + val = srev & AR_SREV_ID;

if (val == 0xFF) { - val = REG_READ(ah, AR_SREV); + val = srev; ah->hw_version.macVersion = (val & AR_SREV_VERSION2) >> AR_SREV_TYPE2_S; ah->hw_version.macRev = MS(val, AR_SREV_REVISION2); @@ -304,6 +313,8 @@ static void ath9k_hw_read_revisions(struct ath_hw *ah) if (ah->hw_version.macVersion == AR_SREV_VERSION_5416_PCIE) ah->is_pciexpress = true; } + + return true; }

/************************************/ @@ -557,7 +568,10 @@ static int __ath9k_hw_init(struct ath_hw *ah) struct ath_common *common = ath9k_hw_common(ah); int r = 0;

- ath9k_hw_read_revisions(ah); + if (!ath9k_hw_read_revisions(ah)) { + ath_err(common, "Could not read hardware revisions"); + return -EOPNOTSUPP; + }

switch (ah->hw_version.macVersion) { case AR_SREV_VERSION_5416_PCI:

[ Upstream commit d8792393a783158cbb2c39939cb897dc5e5299b6 ]

Increase pulse width range from 1-2usec to 0-4usec. During data traffic HW occasionally fails detecting radar pulses, so that SW cannot get enough radar reports to achieve the success rate.

Tested ath10k hw and fw: * QCA9888(10.4-3.5.1-00052) * QCA4019(10.4-3.2.1.1-00017) * QCA9984(10.4-3.6-00104) * QCA988X(10.2.4-1.0-00041)

Tested ath9k hw: AR9300

Tested-by: Tamizh chelvam tamizhr@codeaurora.org Signed-off-by: Tamizh chelvam tamizhr@codeaurora.org Signed-off-by: Anilkumar Kolli akolli@codeaurora.org Signed-off-by: Kalle Valo kvalo@codeaurora.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/ath/dfs_pattern_detector.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/dfs_pattern_detector.c b/drivers/net/wireless/ath/dfs_pattern_detector.c index 4100ffd42a43..78146607f16e 100644 --- a/drivers/net/wireless/ath/dfs_pattern_detector.c +++ b/drivers/net/wireless/ath/dfs_pattern_detector.c @@ -111,7 +111,7 @@ static const struct radar_detector_specs jp_radar_ref_types[] = { JP_PATTERN(0, 0, 1, 1428, 1428, 1, 18, 29, false), JP_PATTERN(1, 2, 3, 3846, 3846, 1, 18, 29, false), JP_PATTERN(2, 0, 1, 1388, 1388, 1, 18, 50, false), - JP_PATTERN(3, 1, 2, 4000, 4000, 1, 18, 50, false), + JP_PATTERN(3, 0, 4, 4000, 4000, 1, 18, 50, false), JP_PATTERN(4, 0, 5, 150, 230, 1, 23, 50, false), JP_PATTERN(5, 6, 10, 200, 500, 1, 16, 50, false), JP_PATTERN(6, 11, 20, 200, 500, 1, 12, 50, false),

[ Upstream commit 6cf97230cd5f36b7665099083272595c55d72be7 ]

dvb_usb_device_exit() frees and uses the device name in that order. Fix by storing the name in a buffer before freeing it.

Signed-off-by: Oliver Neukum oneukum@suse.com Reported-by: syzbot+26ec41e9f788b3eba396@syzkaller.appspotmail.com Signed-off-by: Sean Young sean@mess.org Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/usb/dvb-usb/dvb-usb-init.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/media/usb/dvb-usb/dvb-usb-init.c b/drivers/media/usb/dvb-usb/dvb-usb-init.c index 84308569e7dc..b3413404f91a 100644 --- a/drivers/media/usb/dvb-usb/dvb-usb-init.c +++ b/drivers/media/usb/dvb-usb/dvb-usb-init.c @@ -287,12 +287,15 @@ EXPORT_SYMBOL(dvb_usb_device_init); void dvb_usb_device_exit(struct usb_interface *intf) { struct dvb_usb_device *d = usb_get_intfdata(intf); - const char *name = "generic DVB-USB module"; + const char *default_name = "generic DVB-USB module"; + char name[40];

usb_set_intfdata(intf, NULL); if (d != NULL && d->desc != NULL) { - name = d->desc->name; + strscpy(name, d->desc->name, sizeof(name)); dvb_usb_exit(d); + } else { + strscpy(name, default_name, sizeof(name)); } info("%s successfully deinitialized and disconnected.", name);

[ Upstream commit 0c7aa32966dab0b8a7424e1b34c7f206817953ec ]

The commit d790b7eda953 ("[media] vb2-dma-sg: move dma_(un)map_sg here") left dma_desc_nent unset. It previously contained the number of DMA descriptors as returned from dma_map_sg().

We can now (since the commit referred to above) obtain the same value from the sg_table and drop dma_desc_nent altogether.

Tested on OLPC XO-1.75 machine. Doesn't affect the OLPC XO-1's Cafe driver, since that one doesn't do DMA.

[mchehab+samsung@kernel.org: fix a checkpatch warning]

Fixes: d790b7eda953 ("[media] vb2-dma-sg: move dma_(un)map_sg here") Signed-off-by: Lubomir Rintel lkundrak@v3.sk Signed-off-by: Sakari Ailus sakari.ailus@linux.intel.com Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/platform/marvell-ccic/mcam-core.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/media/platform/marvell-ccic/mcam-core.c b/drivers/media/platform/marvell-ccic/mcam-core.c index af59bf4dca2d..a74bfb9afc8d 100644 --- a/drivers/media/platform/marvell-ccic/mcam-core.c +++ b/drivers/media/platform/marvell-ccic/mcam-core.c @@ -209,7 +209,6 @@ struct mcam_vb_buffer { struct list_head queue; struct mcam_dma_desc *dma_desc; /* Descriptor virtual address */ dma_addr_t dma_desc_pa; /* Descriptor physical address */ - int dma_desc_nent; /* Number of mapped descriptors */ };

static inline struct mcam_vb_buffer *vb_to_mvb(struct vb2_v4l2_buffer *vb) @@ -616,9 +615,11 @@ static void mcam_dma_contig_done(struct mcam_camera *cam, int frame) static void mcam_sg_next_buffer(struct mcam_camera *cam) { struct mcam_vb_buffer *buf; + struct sg_table *sg_table;

buf = list_first_entry(&cam->buffers, struct mcam_vb_buffer, queue); list_del_init(&buf->queue); + sg_table = vb2_dma_sg_plane_desc(&buf->vb_buf.vb2_buf, 0); /* * Very Bad Not Good Things happen if you don't clear * C1_DESC_ENA before making any descriptor changes. @@ -626,7 +627,7 @@ static void mcam_sg_next_buffer(struct mcam_camera *cam) mcam_reg_clear_bit(cam, REG_CTRL1, C1_DESC_ENA); mcam_reg_write(cam, REG_DMA_DESC_Y, buf->dma_desc_pa); mcam_reg_write(cam, REG_DESC_LEN_Y, - buf->dma_desc_nent*sizeof(struct mcam_dma_desc)); + sg_table->nents * sizeof(struct mcam_dma_desc)); mcam_reg_write(cam, REG_DESC_LEN_U, 0); mcam_reg_write(cam, REG_DESC_LEN_V, 0); mcam_reg_set_bit(cam, REG_CTRL1, C1_DESC_ENA);

[ Upstream commit f49308878d7202e07d8761238e01bd0e5fce2750 ]

In v4l2-compliance utility, test MEDIA_IOC_ENUM_ENTITIES will check whether reserved field of media_links_enum filled with zero.

However, for 32 bit program, the reserved field is missing copy from kernel space to user space in media_device_enum_links32 function.

This patch adds the cleaning a reserved field logic in media_device_enum_links32 function.

Signed-off-by: Jungo Lin jungo.lin@mediatek.com Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/media-device.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c index 6f46c59415fe..6062c0cfa632 100644 --- a/drivers/media/media-device.c +++ b/drivers/media/media-device.c @@ -474,6 +474,7 @@ static long media_device_enum_links32(struct media_device *mdev, { struct media_links_enum links; compat_uptr_t pads_ptr, links_ptr; + int ret;

memset(&links, 0, sizeof(links));

@@ -485,7 +486,13 @@ static long media_device_enum_links32(struct media_device *mdev, links.pads = compat_ptr(pads_ptr); links.links = compat_ptr(links_ptr);

- return media_device_enum_links(mdev, &links); + ret = media_device_enum_links(mdev, &links); + if (ret) + return ret; + + memset(ulinks->reserved, 0, sizeof(ulinks->reserved)); + + return 0; }

#define MEDIA_IOC_ENUM_LINKS32 _IOWR('|', 0x02, struct media_links_enum32)

[ Upstream commit 0620ec6c62a5a07625b65f699adc5d1b90394ee6 ]

In case we don't use a given address entry we need to clear it because it could contain previous values that are no longer valid.

Found out while running stmmac selftests.

Signed-off-by: Jose Abreu joabreu@synopsys.com Cc: Joao Pinto jpinto@synopsys.com Cc: David S. Miller davem@davemloft.net Cc: Giuseppe Cavallaro peppe.cavallaro@st.com Cc: Alexandre Torgue alexandre.torgue@st.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 51019b794be5..f46f2bfc2cc0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -173,14 +173,20 @@ static void dwmac4_set_filter(struct mac_device_info *hw, * are required */ value |= GMAC_PACKET_FILTER_PR; - } else if (!netdev_uc_empty(dev)) { - int reg = 1; + } else { struct netdev_hw_addr *ha; + int reg = 1;

netdev_for_each_uc_addr(ha, dev) { dwmac4_set_umac_addr(hw, ha->addr, reg); reg++; } + + while (reg <= GMAC_MAX_PERFECT_ADDRESSES) { + writel(0, ioaddr + GMAC_ADDR_HIGH(reg)); + writel(0, ioaddr + GMAC_ADDR_LOW(reg)); + reg++; + } }

writel(value, ioaddr + GMAC_PACKET_FILTER);

[ Upstream commit 7c80eb1c7e2b8420477fbc998971d62a648035d9 ]

In both functions, if pfkey_xfrm_policy2msg failed we leaked the newly allocated sk_buff. Free it on error.

Fixes: 55569ce256ce ("Fix conversion between IPSEC_MODE_xxx and XFRM_MODE_xxx.") Reported-by: syzbot+4f0529365f7f2208d9f0@syzkaller.appspotmail.com Signed-off-by: Jeremy Sowden jeremy@azazel.net Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/key/af_key.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/key/af_key.c b/net/key/af_key.c index 3ba903ff2bb0..36db179d848e 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2463,8 +2463,10 @@ static int key_pol_get_resp(struct sock *sk, struct xfrm_policy *xp, const struc goto out; } err = pfkey_xfrm_policy2msg(out_skb, xp, dir); - if (err < 0) + if (err < 0) { + kfree_skb(out_skb); goto out; + }

out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = hdr->sadb_msg_version; @@ -2717,8 +2719,10 @@ static int dump_sp(struct xfrm_policy *xp, int dir, int count, void *ptr) return PTR_ERR(out_skb);

err = pfkey_xfrm_policy2msg(out_skb, xp, dir); - if (err < 0) + if (err < 0) { + kfree_skb(out_skb); return err; + }

out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = pfk->dump.msg_version;

[ Upstream commit 518fa4e0e0da97ea2e17c95ab57647ce748a96e2 ]

You can't memset the contents of a __user pointer. Instead, call copy_to_user to copy links.reserved (which is zeroed) to the user memory.

This fixes this sparse warning:

SPARSE:drivers/media/mc/mc-device.c drivers/media/mc/mc-device.c:521:16: warning: incorrect type in argument 1 (different address spaces)

Fixes: f49308878d720 ("media: media_device_enum_links32: clean a reserved field")

Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Reviewed-by: Sakari Ailus sakari.ailus@linux.intel.com Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/media-device.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c index 6062c0cfa632..73a2dba475d0 100644 --- a/drivers/media/media-device.c +++ b/drivers/media/media-device.c @@ -490,8 +490,9 @@ static long media_device_enum_links32(struct media_device *mdev, if (ret) return ret;

- memset(ulinks->reserved, 0, sizeof(ulinks->reserved)); - + if (copy_to_user(ulinks->reserved, links.reserved, + sizeof(ulinks->reserved))) + return -EFAULT; return 0; }

[ Upstream commit 82c76aca81187b3d28a6fb3062f6916450ce955e ]

In general, we don't want MAC drivers calling phy_attach_direct with the net_device being NULL. Add checks against this in all the functions calling it: phy_attach() and phy_connect_direct().

Signed-off-by: Ioana Ciornei ioana.ciornei@nxp.com Suggested-by: Andrew Lunn andrew@lunn.ch Reviewed-by: Andrew Lunn andrew@lunn.ch Reviewed-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/phy/phy_device.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 5048a6df6a8e..5c2c72b1ef8b 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -673,6 +673,9 @@ int phy_connect_direct(struct net_device *dev, struct phy_device *phydev, { int rc;

+ if (!dev) + return -EINVAL; + rc = phy_attach_direct(dev, phydev, phydev->dev_flags, interface); if (rc) return rc; @@ -965,6 +968,9 @@ struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, struct device *d; int rc;

+ if (!dev) + return ERR_PTR(-EINVAL); + /* Search the list of PHY devices on the mdio bus for the * PHY with the requested name */

[ Upstream commit c9cca7034b34a2d82e9a03b757de2485c294851c ]

The MPC885 reference manual states:

SEC Lite-initiated 8xx writes can occur only on 32-bit-word boundaries, but reads can occur on any byte boundary. Writing back a header read from a non-32-bit-word boundary will yield unpredictable results.

In order to ensure that, cra_alignmask is set to 3 for SEC1.

Signed-off-by: Christophe Leroy christophe.leroy@c-s.fr Fixes: 9c4a79653b35 ("crypto: talitos - Freescale integrated security engine (SEC) driver") Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/crypto/talitos.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c index e7864aa494a1..ea8595d2c3d8 100644 --- a/drivers/crypto/talitos.c +++ b/drivers/crypto/talitos.c @@ -3119,7 +3119,10 @@ static struct talitos_crypto_alg *talitos_alg_alloc(struct device *dev, alg->cra_priority = t_alg->algt.priority; else alg->cra_priority = TALITOS_CRA_PRIORITY; - alg->cra_alignmask = 0; + if (has_ftr_sec1(priv)) + alg->cra_alignmask = 3; + else + alg->cra_alignmask = 0; alg->cra_ctxsize = sizeof(struct talitos_ctx); alg->cra_flags |= CRYPTO_ALG_KERN_DRIVER_ONLY;

[ Upstream commit d9349850e188b8b59e5322fda17ff389a1c0cd7d ]

The sequence

static DEFINE_WW_CLASS(test_ww_class);

struct ww_acquire_ctx ww_ctx; struct ww_mutex ww_lock_a; struct ww_mutex ww_lock_b; struct ww_mutex ww_lock_c; struct mutex lock_c;

ww_acquire_init(&ww_ctx, &test_ww_class);

ww_mutex_init(&ww_lock_a, &test_ww_class); ww_mutex_init(&ww_lock_b, &test_ww_class); ww_mutex_init(&ww_lock_c, &test_ww_class);

mutex_init(&lock_c);

ww_mutex_lock(&ww_lock_a, &ww_ctx);

mutex_lock(&lock_c);

ww_mutex_lock(&ww_lock_b, &ww_ctx); ww_mutex_lock(&ww_lock_c, &ww_ctx);

mutex_unlock(&lock_c); (*)

ww_mutex_unlock(&ww_lock_c); ww_mutex_unlock(&ww_lock_b); ww_mutex_unlock(&ww_lock_a);

ww_acquire_fini(&ww_ctx); (**)

will trigger the following error in __lock_release() when calling mutex_release() at **:

DEBUG_LOCKS_WARN_ON(depth <= 0)

The problem is that the hlock merging happening at * updates the references for test_ww_class incorrectly to 3 whereas it should've updated it to 4 (representing all the instances for ww_ctx and ww_lock_[abc]).

Fix this by updating the references during merging correctly taking into account that we can have non-zero references (both for the hlock that we merge into another hlock or for the hlock we are merging into).

Signed-off-by: Imre Deak imre.deak@intel.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= ville.syrjala@linux.intel.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Thomas Gleixner tglx@linutronix.de Cc: Will Deacon will.deacon@arm.com Link: https://lkml.kernel.org/r/20190524201509.9199-2-imre.deak@intel.com Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/locking/lockdep.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 26fc428476b9..4b27aaffdf35 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -3260,17 +3260,17 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, if (depth) { hlock = curr->held_locks + depth - 1; if (hlock->class_idx == class_idx && nest_lock) { - if (hlock->references) { - /* - * Check: unsigned int references:12, overflow. - */ - if (DEBUG_LOCKS_WARN_ON(hlock->references == (1 << 12)-1)) - return 0; + if (!references) + references++;

+ if (!hlock->references) hlock->references++; - } else { - hlock->references = 2; - } + + hlock->references += references; + + /* Overflow */ + if (DEBUG_LOCKS_WARN_ON(hlock->references < references)) + return 0;

return 1; }

[ Upstream commit 04507c0a9385cc8280f794a36bfff567c8cc1042 ]

To set frequency on specific cpus using cpupower, following syntax can be used : cpupower -c #i frequency-set -f #f -r

While setting frequency using cpupower frequency-set command, if we use '-r' option, it is expected to set frequency for all cpus related to cpu #i. But it is observed to be missing the last cpu in related cpu list. This patch fixes the problem.

Signed-off-by: Abhishek Goel huntbag@linux.vnet.ibm.com Reviewed-by: Thomas Renninger trenn@suse.de Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/power/cpupower/utils/cpufreq-set.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/tools/power/cpupower/utils/cpufreq-set.c b/tools/power/cpupower/utils/cpufreq-set.c index 1eef0aed6423..08a405593a79 100644 --- a/tools/power/cpupower/utils/cpufreq-set.c +++ b/tools/power/cpupower/utils/cpufreq-set.c @@ -306,6 +306,8 @@ int cmd_freq_set(int argc, char **argv) bitmask_setbit(cpus_chosen, cpus->cpu); cpus = cpus->next; } + /* Set the last cpu in related cpus list */ + bitmask_setbit(cpus_chosen, cpus->cpu); cpufreq_put_related_cpus(cpus); } }

[ Upstream commit 7de44285c1f69ccfbe8be1d6a16fcd956681fee6 ]

It is possible that the interrupt handler fires and frees up space in the TX ring in between checking for sufficient TX ring space and stopping the TX queue in axienet_start_xmit. If this happens, the queue wake from the interrupt handler will occur before the queue is stopped, causing a lost wakeup and the adapter's transmit hanging.

To avoid this, after stopping the queue, check again whether there is sufficient space in the TX ring. If so, wake up the queue again.

Signed-off-by: Robert Hancock hancock@sedsystems.ca Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/ethernet/xilinx/xilinx_axienet_main.c | 20 ++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index a8afc92cbfca..5f21ddff9e0f 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -612,6 +612,10 @@ static void axienet_start_xmit_done(struct net_device *ndev)

ndev->stats.tx_packets += packets; ndev->stats.tx_bytes += size; + + /* Matches barrier in axienet_start_xmit */ + smp_mb(); + netif_wake_queue(ndev); }

@@ -666,9 +670,19 @@ static int axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev) cur_p = &lp->tx_bd_v[lp->tx_bd_tail];

if (axienet_check_tx_bd_space(lp, num_frag)) { - if (!netif_queue_stopped(ndev)) - netif_stop_queue(ndev); - return NETDEV_TX_BUSY; + if (netif_queue_stopped(ndev)) + return NETDEV_TX_BUSY; + + netif_stop_queue(ndev); + + /* Matches barrier in axienet_start_xmit_done */ + smp_mb(); + + /* Space might have just been freed - check again */ + if (axienet_check_tx_bd_space(lp, num_frag)) + return NETDEV_TX_BUSY; + + netif_wake_queue(ndev); }

if (skb->ip_summed == CHECKSUM_PARTIAL) {

[ Upstream commit e45c48a9a4d20ebc7b639a62c3ef8f4b08007027 ]

This patch adds the necessary intelligence to properly compute the value of 'old' and 'head' when operating in snapshot mode. That way we can get the latest information in the AUX buffer and be compatible with the generic AUX ring buffer mechanic.

Tester notes:

Leo, have you had the chance to test/review this one? Suzuki?

Sure. I applied this patch on the perf/core branch (with latest commit 3e4fbf36c1e3 'perf augmented_raw_syscalls: Move reading filename to the loop') and passed testing with below steps:

# perf record -e cs_etm/@tmc_etr0/ -S -m,64 --per-thread ./sort & [1] 19097 Bubble sorting array of 30000 elements

# kill -USR2 19097 # kill -USR2 19097 # kill -USR2 19097 [ perf record: Woken up 4 times to write data ] [ perf record: Captured and wrote 0.753 MB perf.data ]

Signed-off-by: Mathieu Poirier mathieu.poirier@linaro.org Tested-by: Leo Yan leo.yan@linaro.org Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Jiri Olsa jolsa@redhat.com Cc: Peter Zijlstra peterz@infradead.org Cc: Suzuki Poulouse suzuki.poulose@arm.com Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/20190605161633.12245-1-mathieu.poirier@linaro.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/arch/arm/util/cs-etm.c | 127 +++++++++++++++++++++++++++++- 1 file changed, 123 insertions(+), 4 deletions(-)

diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 47d584da5819..f6cff278aa5d 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -41,6 +41,8 @@ struct cs_etm_recording { struct auxtrace_record itr; struct perf_pmu *cs_etm_pmu; struct perf_evlist *evlist; + int wrapped_cnt; + bool *wrapped; bool snapshot_mode; size_t snapshot_size; }; @@ -458,16 +460,131 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, return 0; }

-static int cs_etm_find_snapshot(struct auxtrace_record *itr __maybe_unused, +static int cs_etm_alloc_wrapped_array(struct cs_etm_recording *ptr, int idx) +{ + bool *wrapped; + int cnt = ptr->wrapped_cnt; + + /* Make @ptr->wrapped as big as @idx */ + while (cnt <= idx) + cnt++; + + /* + * Free'ed in cs_etm_recording_free(). Using realloc() to avoid + * cross compilation problems where the host's system supports + * reallocarray() but not the target. + */ + wrapped = realloc(ptr->wrapped, cnt * sizeof(bool)); + if (!wrapped) + return -ENOMEM; + + wrapped[cnt - 1] = false; + ptr->wrapped_cnt = cnt; + ptr->wrapped = wrapped; + + return 0; +} + +static bool cs_etm_buffer_has_wrapped(unsigned char *buffer, + size_t buffer_size, u64 head) +{ + u64 i, watermark; + u64 *buf = (u64 *)buffer; + size_t buf_size = buffer_size; + + /* + * We want to look the very last 512 byte (chosen arbitrarily) in + * the ring buffer. + */ + watermark = buf_size - 512; + + /* + * @head is continuously increasing - if its value is equal or greater + * than the size of the ring buffer, it has wrapped around. + */ + if (head >= buffer_size) + return true; + + /* + * The value of @head is somewhere within the size of the ring buffer. + * This can be that there hasn't been enough data to fill the ring + * buffer yet or the trace time was so long that @head has numerically + * wrapped around. To find we need to check if we have data at the very + * end of the ring buffer. We can reliably do this because mmap'ed + * pages are zeroed out and there is a fresh mapping with every new + * session. + */ + + /* @head is less than 512 byte from the end of the ring buffer */ + if (head > watermark) + watermark = head; + + /* + * Speed things up by using 64 bit transactions (see "u64 *buf" above) + */ + watermark >>= 3; + buf_size >>= 3; + + /* + * If we find trace data at the end of the ring buffer, @head has + * been there and has numerically wrapped around at least once. + */ + for (i = watermark; i < buf_size; i++) + if (buf[i]) + return true; + + return false; +} + +static int cs_etm_find_snapshot(struct auxtrace_record *itr, int idx, struct auxtrace_mmap *mm, - unsigned char *data __maybe_unused, + unsigned char *data, u64 *head, u64 *old) { + int err; + bool wrapped; + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + + /* + * Allocate memory to keep track of wrapping if this is the first + * time we deal with this *mm. + */ + if (idx >= ptr->wrapped_cnt) { + err = cs_etm_alloc_wrapped_array(ptr, idx); + if (err) + return err; + } + + /* + * Check to see if *head has wrapped around. If it hasn't only the + * amount of data between *head and *old is snapshot'ed to avoid + * bloating the perf.data file with zeros. But as soon as *head has + * wrapped around the entire size of the AUX ring buffer it taken. + */ + wrapped = ptr->wrapped[idx]; + if (!wrapped && cs_etm_buffer_has_wrapped(data, mm->len, *head)) { + wrapped = true; + ptr->wrapped[idx] = true; + } + pr_debug3("%s: mmap index %d old head %zu new head %zu size %zu\n", __func__, idx, (size_t)*old, (size_t)*head, mm->len);

- *old = *head; - *head += mm->len; + /* No wrap has occurred, we can just use *head and *old. */ + if (!wrapped) + return 0; + + /* + * *head has wrapped around - adjust *head and *old to pickup the + * entire content of the AUX buffer. + */ + if (*head >= mm->len) { + *old = *head - mm->len; + } else { + *head += mm->len; + *old = *head - mm->len; + }

return 0; } @@ -508,6 +625,8 @@ static void cs_etm_recording_free(struct auxtrace_record *itr) { struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); + + zfree(&ptr->wrapped); free(ptr); }

[ Upstream commit 64ea3e9094a1f13b96c33244a3fb3a0f45690bd2 ]

Commit 384ebe1c2849 ("gpio/omap: Add DT support to GPIO driver") added the register definition tables to the gpio-omap driver. Subsequently to that commit, commit 4e962e8998cc ("gpio/omap: remove cpu_is_omapxxxx() checks from *_runtime_resume()") added definitions for irqstatus_raw* registers to the legacy OMAP4 definitions, but missed the DT definitions.

This causes an unintentional change of behaviour for the 1.101 errata workaround on OMAP4 platforms. Fix this oversight.

Fixes: 4e962e8998cc ("gpio/omap: remove cpu_is_omapxxxx() checks from *_runtime_resume()") Signed-off-by: Russell King rmk+kernel@armlinux.org.uk Signed-off-by: Grygorii Strashko grygorii.strashko@ti.com Tested-by: Tony Lindgren tony@atomide.com Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpio/gpio-omap.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c index 038882183bdf..bd12b433f964 100644 --- a/drivers/gpio/gpio-omap.c +++ b/drivers/gpio/gpio-omap.c @@ -1585,6 +1585,8 @@ static struct omap_gpio_reg_offs omap4_gpio_regs = { .clr_dataout = OMAP4_GPIO_CLEARDATAOUT, .irqstatus = OMAP4_GPIO_IRQSTATUS0, .irqstatus2 = OMAP4_GPIO_IRQSTATUS1, + .irqstatus_raw0 = OMAP4_GPIO_IRQSTATUSRAW0, + .irqstatus_raw1 = OMAP4_GPIO_IRQSTATUSRAW1, .irqenable = OMAP4_GPIO_IRQSTATUSSET0, .irqenable2 = OMAP4_GPIO_IRQSTATUSSET1, .set_irqenable = OMAP4_GPIO_IRQSTATUSSET0,

[ Upstream commit db057679de3e9e6a03c1bcd5aee09b0d25fd9f5b ]

On buses like SlimBus and SoundWire which does not support gather_writes yet in regmap, A bulk write on paged register would be silently ignored after programming page. This is because local variable 'ret' value in regmap_raw_write_impl() gets reset to 0 once page register is written successfully and the code below checks for 'ret' value to be -ENOTSUPP before linearising the write buffer to send to bus->write().

Fix this by resetting the 'ret' value to -ENOTSUPP in cases where gather_writes() is not supported or single register write is not possible.

Signed-off-by: Srinivas Kandagatla srinivas.kandagatla@linaro.org Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/base/regmap/regmap.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 69c84fddfe8a..1799a1dfa46e 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1506,6 +1506,8 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, map->format.reg_bytes + map->format.pad_bytes, val, val_len); + else + ret = -ENOTSUPP;

/* If that didn't work fall back on linearising by hand. */ if (ret == -ENOTSUPP) {

[ Upstream commit 6da9f775175e516fc7229ceaa9b54f8f56aa7924 ]

When debugging options are turned on, the rcu_read_lock() function might not be inlined. This results in lockdep's print_lock() function printing "rcu_read_lock+0x0/0x70" instead of rcu_read_lock()'s caller. For example:

[ 10.579995] ============================= [ 10.584033] WARNING: suspicious RCU usage [ 10.588074] 4.18.0.memcg_v2+ #1 Not tainted [ 10.593162] ----------------------------- [ 10.597203] include/linux/rcupdate.h:281 Illegal context switch in RCU read-side critical section! [ 10.606220] [ 10.606220] other info that might help us debug this: [ 10.606220] [ 10.614280] [ 10.614280] rcu_scheduler_active = 2, debug_locks = 1 [ 10.620853] 3 locks held by systemd/1: [ 10.624632] #0: (____ptrval____) (&type->i_mutex_dir_key#5){.+.+}, at: lookup_slow+0x42/0x70 [ 10.633232] #1: (____ptrval____) (rcu_read_lock){....}, at: rcu_read_lock+0x0/0x70 [ 10.640954] #2: (____ptrval____) (rcu_read_lock){....}, at: rcu_read_lock+0x0/0x70

These "rcu_read_lock+0x0/0x70" strings are not providing any useful information. This commit therefore forces inlining of the rcu_read_lock() function so that rcu_read_lock()'s caller is instead shown.

Signed-off-by: Waiman Long longman@redhat.com Signed-off-by: Paul E. McKenney paulmck@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/rcupdate.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index aa2935779e43..96037ba940ee 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -866,7 +866,7 @@ static inline void rcu_preempt_sleep_check(void) * read-side critical sections may be preempted and they may also block, but * only when acquiring spinlocks that are subject to priority inheritance. */ -static inline void rcu_read_lock(void) +static __always_inline void rcu_read_lock(void) { __rcu_read_lock(); __acquire(RCU);

[ Upstream commit b8d6d0079757cbd1b69724cfd1c08e2171c68cee ]

After commit b38ff4075a80, the following command does not work anymore: $ ip xfrm state add src 10.125.0.2 dst 10.125.0.1 proto esp spi 34 reqid 1 \ mode tunnel enc 'cbc(aes)' 0xb0abdba8b782ad9d364ec81e3a7d82a1 auth-trunc \ 'hmac(sha1)' 0xe26609ebd00acb6a4d51fca13e49ea78a72c73e6 96 flag align4

In fact, the selector is not mandatory, allow the user to provide an empty selector.

Fixes: b38ff4075a80 ("xfrm: Fix xfrm sel prefix length validation") CC: Anirudh Gupta anirudh.gupta@sophos.com Signed-off-by: Nicolas Dichtel nicolas.dichtel@6wind.com Acked-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/xfrm/xfrm_user.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index df4b7fc721f6..f3e9d500fa5a 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -166,6 +166,9 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, }

switch (p->sel.family) { + case AF_UNSPEC: + break; + case AF_INET: if (p->sel.prefixlen_d > 32 || p->sel.prefixlen_s > 32) goto out;

[ Upstream commit 098eadce3c622c07b328d0a43dda379b38cf7c5e ]

Vhost_net was known to suffer from HOL[1] issues which is not easy to fix. Several downstream disable the feature by default. What's more, the datapath was split and datacopy path got the support of batching and XDP support recently which makes it faster than zerocopy part for small packets transmission.

It looks to me that disable zerocopy by default is more appropriate. It cold be enabled by default again in the future if we fix the above issues.

[1] https://patchwork.kernel.org/patch/3787671/

Signed-off-by: Jason Wang jasowang@redhat.com Acked-by: Michael S. Tsirkin mst@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/vhost/net.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 681d0eade82f..75e1089dfb01 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -30,7 +30,7 @@

#include "vhost.h"

-static int experimental_zcopytx = 1; +static int experimental_zcopytx = 0; module_param(experimental_zcopytx, int, 0444); MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;" " 1 -Enable; 0 - Disable");

[ Upstream commit 585fb3d93d32dbe89e718b85009f9c322cc554cd ]

In edac_create_csrow_object(), the reference to the object is not released when adding the device to the device hierarchy fails (device_add()). This may result in a memory leak.

Signed-off-by: Pan Bian bianpan2016@163.com Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Cc: James Morse james.morse@arm.com Cc: Mauro Carvalho Chehab mchehab@kernel.org Cc: linux-edac linux-edac@vger.kernel.org Link: https://lkml.kernel.org/r/1555554438-103953-1-git-send-email-bianpan2016@163... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/edac/edac_mc_sysfs.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index 40d792e96b75..203ebe348b77 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -426,6 +426,8 @@ static inline int nr_pages_per_csrow(struct csrow_info *csrow) static int edac_create_csrow_object(struct mem_ctl_info *mci, struct csrow_info *csrow, int index) { + int err; + csrow->dev.type = &csrow_attr_type; csrow->dev.bus = mci->bus; csrow->dev.groups = csrow_dev_groups; @@ -438,7 +440,11 @@ static int edac_create_csrow_object(struct mem_ctl_info *mci, edac_dbg(0, "creating (virtual) csrow node %s\n", dev_name(&csrow->dev));

- return device_add(&csrow->dev); + err = device_add(&csrow->dev); + if (err) + put_device(&csrow->dev); + + return err; }

/* Create a CSROW object under specifed edac_mc_device */

[ Upstream commit b2ce5617dad254230551feda3599f2cc68e53ad8 ]

When building with CONFIG_VIDEO_ADV7511 and CONFIG_DRM_I2C_ADV7511 enabled as loadable modules, we see the following warning:

drivers/gpu/drm/bridge/adv7511/adv7511.ko drivers/media/i2c/adv7511.ko

Rework so that the file is named adv7511-v4l2.c.

Signed-off-by: Anders Roxell anders.roxell@linaro.org Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/i2c/Makefile | 2 +- drivers/media/i2c/{adv7511.c => adv7511-v4l2.c} | 5 +++++ 2 files changed, 6 insertions(+), 1 deletion(-) rename drivers/media/i2c/{adv7511.c => adv7511-v4l2.c} (99%)

diff --git a/drivers/media/i2c/Makefile b/drivers/media/i2c/Makefile index 92773b2e6225..bfe0afc209b8 100644 --- a/drivers/media/i2c/Makefile +++ b/drivers/media/i2c/Makefile @@ -29,7 +29,7 @@ obj-$(CONFIG_VIDEO_ADV7393) += adv7393.o obj-$(CONFIG_VIDEO_ADV7604) += adv7604.o obj-$(CONFIG_VIDEO_ADV7842) += adv7842.o obj-$(CONFIG_VIDEO_AD9389B) += ad9389b.o -obj-$(CONFIG_VIDEO_ADV7511) += adv7511.o +obj-$(CONFIG_VIDEO_ADV7511) += adv7511-v4l2.o obj-$(CONFIG_VIDEO_VPX3220) += vpx3220.o obj-$(CONFIG_VIDEO_VS6624) += vs6624.o obj-$(CONFIG_VIDEO_BT819) += bt819.o diff --git a/drivers/media/i2c/adv7511.c b/drivers/media/i2c/adv7511-v4l2.c similarity index 99% rename from drivers/media/i2c/adv7511.c rename to drivers/media/i2c/adv7511-v4l2.c index 5f1c8ee8a50e..b87c9e7ff146 100644 --- a/drivers/media/i2c/adv7511.c +++ b/drivers/media/i2c/adv7511-v4l2.c @@ -17,6 +17,11 @@ * SOFTWARE. */

+/* + * This file is named adv7511-v4l2.c so it doesn't conflict with the Analog + * Device ADV7511 (config fragment CONFIG_DRM_I2C_ADV7511). + */ +

#include <linux/kernel.h> #include <linux/module.h>

[ Upstream commit a9314773a91a1d3b36270085246a6715a326ff00 ]

With CONFIG_PROC_FS=n the following warning is emitted:

kernel/time/timer_list.c:361:36: warning: unused variable 'timer_list_sops' [-Wunused-const-variable] static const struct seq_operations timer_list_sops = {

Add #ifdef guard around procfs specific code.

Signed-off-by: Nathan Huckleberry nhuck@google.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Nick Desaulniers ndesaulniers@google.com Cc: john.stultz@linaro.org Cc: sboyd@kernel.org Cc: clang-built-linux@googlegroups.com Link: https://github.com/ClangBuiltLinux/linux/issues/534 Link: https://lkml.kernel.org/r/20190614181604.112297-1-nhuck@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/time/timer_list.c | 36 +++++++++++++++++++----------------- 1 file changed, 19 insertions(+), 17 deletions(-)

diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index 1407ed20ea93..b7c5d230b4b2 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -299,23 +299,6 @@ static inline void timer_list_header(struct seq_file *m, u64 now) SEQ_printf(m, "\n"); }

-static int timer_list_show(struct seq_file *m, void *v) -{ - struct timer_list_iter *iter = v; - - if (iter->cpu == -1 && !iter->second_pass) - timer_list_header(m, iter->now); - else if (!iter->second_pass) - print_cpu(m, iter->cpu, iter->now); -#ifdef CONFIG_GENERIC_CLOCKEVENTS - else if (iter->cpu == -1 && iter->second_pass) - timer_list_show_tickdevices_header(m); - else - print_tickdevice(m, tick_get_device(iter->cpu), iter->cpu); -#endif - return 0; -} - void sysrq_timer_list_show(void) { u64 now = ktime_to_ns(ktime_get()); @@ -334,6 +317,24 @@ void sysrq_timer_list_show(void) return; }

+#ifdef CONFIG_PROC_FS +static int timer_list_show(struct seq_file *m, void *v) +{ + struct timer_list_iter *iter = v; + + if (iter->cpu == -1 && !iter->second_pass) + timer_list_header(m, iter->now); + else if (!iter->second_pass) + print_cpu(m, iter->cpu, iter->now); +#ifdef CONFIG_GENERIC_CLOCKEVENTS + else if (iter->cpu == -1 && iter->second_pass) + timer_list_show_tickdevices_header(m); + else + print_tickdevice(m, tick_get_device(iter->cpu), iter->cpu); +#endif + return 0; +} + static void *move_iter(struct timer_list_iter *iter, loff_t offset) { for (; offset; offset--) { @@ -405,3 +406,4 @@ static int __init init_timer_list_procfs(void) return 0; } __initcall(init_timer_list_procfs); +#endif

[ Upstream commit 56d159a4ec6d8da7313aac6fcbb95d8fffe689ba ]

Sequence number handling assumed that the BIT processor frame number starts counting at 1, but this is not true for the MPEG-2 decoder, which starts at 0. Fix the sequence counter offset detection to handle this.

Signed-off-by: Philipp Zabel p.zabel@pengutronix.de Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/platform/coda/coda-bit.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c index 717ee9a6a80e..1b8024f86b0f 100644 --- a/drivers/media/platform/coda/coda-bit.c +++ b/drivers/media/platform/coda/coda-bit.c @@ -1581,6 +1581,7 @@ static int __coda_start_decoding(struct coda_ctx *ctx) coda_write(dev, 0, CODA_REG_BIT_BIT_STREAM_PARAM); return -ETIMEDOUT; } + ctx->sequence_offset = ~0U; ctx->initialized = 1;

/* Update kfifo out pointer from coda bitstream read pointer */ @@ -1971,7 +1972,9 @@ static void coda_finish_decode(struct coda_ctx *ctx) v4l2_err(&dev->v4l2_dev, "decoded frame index out of range: %d\n", decoded_idx); } else { - val = coda_read(dev, CODA_RET_DEC_PIC_FRAME_NUM) - 1; + val = coda_read(dev, CODA_RET_DEC_PIC_FRAME_NUM); + if (ctx->sequence_offset == -1) + ctx->sequence_offset = val; val -= ctx->sequence_offset; spin_lock_irqsave(&ctx->buffer_meta_lock, flags); if (!list_empty(&ctx->buffer_meta_list)) {

[ Upstream commit 4079e8ccabc3b6d1b503f2376123cb515d14921f ]

Do not schedule rx_tasklet when the usb dongle is disconnected. Moreover do not grub rx_lock in mt7601u_kill_rx since usb_poison_urb can run concurrently with urb completion and we can unlink urbs from rx ring in any order. This patch fixes the common kernel warning reported when the device is removed.

[ 24.921354] usb 3-14: USB disconnect, device number 7 [ 24.921593] ------------[ cut here ]------------ [ 24.921594] RX urb mismatch [ 24.921675] WARNING: CPU: 4 PID: 163 at drivers/net/wireless/mediatek/mt7601u/dma.c:200 mt7601u_complete_rx+0xcb/0xd0 [mt7601u] [ 24.921769] CPU: 4 PID: 163 Comm: kworker/4:2 Tainted: G OE 4.19.31-041931-generic #201903231635 [ 24.921770] Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./Z97 Extreme4, BIOS P1.30 05/23/2014 [ 24.921782] Workqueue: usb_hub_wq hub_event [ 24.921797] RIP: 0010:mt7601u_complete_rx+0xcb/0xd0 [mt7601u] [ 24.921800] RSP: 0018:ffff9bd9cfd03d08 EFLAGS: 00010086 [ 24.921802] RAX: 0000000000000000 RBX: ffff9bd9bf043540 RCX: 0000000000000006 [ 24.921803] RDX: 0000000000000007 RSI: 0000000000000096 RDI: ffff9bd9cfd16420 [ 24.921804] RBP: ffff9bd9cfd03d28 R08: 0000000000000002 R09: 00000000000003a8 [ 24.921805] R10: 0000002f485fca34 R11: 0000000000000000 R12: ffff9bd9bf043c1c [ 24.921806] R13: ffff9bd9c62fa3c0 R14: 0000000000000082 R15: 0000000000000000 [ 24.921807] FS: 0000000000000000(0000) GS:ffff9bd9cfd00000(0000) knlGS:0000000000000000 [ 24.921808] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 24.921808] CR2: 00007fb2648b0000 CR3: 0000000142c0a004 CR4: 00000000001606e0 [ 24.921809] Call Trace: [ 24.921812] <IRQ> [ 24.921819] __usb_hcd_giveback_urb+0x8b/0x140 [ 24.921821] usb_hcd_giveback_urb+0xca/0xe0 [ 24.921828] xhci_giveback_urb_in_irq.isra.42+0x82/0xf0 [ 24.921834] handle_cmd_completion+0xe02/0x10d0 [ 24.921837] xhci_irq+0x274/0x4a0 [ 24.921838] xhci_msi_irq+0x11/0x20 [ 24.921851] __handle_irq_event_percpu+0x44/0x190 [ 24.921856] handle_irq_event_percpu+0x32/0x80 [ 24.921861] handle_irq_event+0x3b/0x5a [ 24.921867] handle_edge_irq+0x80/0x190 [ 24.921874] handle_irq+0x20/0x30 [ 24.921889] do_IRQ+0x4e/0xe0 [ 24.921891] common_interrupt+0xf/0xf [ 24.921892] </IRQ> [ 24.921900] RIP: 0010:usb_hcd_flush_endpoint+0x78/0x180 [ 24.921354] usb 3-14: USB disconnect, device number 7

Signed-off-by: Lorenzo Bianconi lorenzo@kernel.org Signed-off-by: Kalle Valo kvalo@codeaurora.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/mediatek/mt7601u/dma.c | 33 +++++++++++---------- 1 file changed, 18 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt7601u/dma.c b/drivers/net/wireless/mediatek/mt7601u/dma.c index a8bc064bc14f..838ad9a4be51 100644 --- a/drivers/net/wireless/mediatek/mt7601u/dma.c +++ b/drivers/net/wireless/mediatek/mt7601u/dma.c @@ -193,10 +193,23 @@ static void mt7601u_complete_rx(struct urb *urb) struct mt7601u_rx_queue *q = &dev->rx_q; unsigned long flags;

- spin_lock_irqsave(&dev->rx_lock, flags); + /* do no schedule rx tasklet if urb has been unlinked + * or the device has been removed + */ + switch (urb->status) { + case -ECONNRESET: + case -ESHUTDOWN: + case -ENOENT: + return; + default: + dev_err_ratelimited(dev->dev, "rx urb failed: %d\n", + urb->status); + /* fall through */ + case 0: + break; + }

- if (mt7601u_urb_has_error(urb)) - dev_err(dev->dev, "Error: RX urb failed:%d\n", urb->status); + spin_lock_irqsave(&dev->rx_lock, flags); if (WARN_ONCE(q->e[q->end].urb != urb, "RX urb mismatch")) goto out;

@@ -363,19 +376,9 @@ int mt7601u_dma_enqueue_tx(struct mt7601u_dev *dev, struct sk_buff *skb, static void mt7601u_kill_rx(struct mt7601u_dev *dev) { int i; - unsigned long flags;

- spin_lock_irqsave(&dev->rx_lock, flags); - - for (i = 0; i < dev->rx_q.entries; i++) { - int next = dev->rx_q.end; - - spin_unlock_irqrestore(&dev->rx_lock, flags); - usb_poison_urb(dev->rx_q.e[next].urb); - spin_lock_irqsave(&dev->rx_lock, flags); - } - - spin_unlock_irqrestore(&dev->rx_lock, flags); + for (i = 0; i < dev->rx_q.entries; i++) + usb_poison_urb(dev->rx_q.e[i].urb); }

static int mt7601u_submit_rx_buf(struct mt7601u_dev *dev,

[ Upstream commit 23377c200b2eb48a60d0f228b2a2e75ed6ee6060 ]

When the device is disconnected while passing traffic it is possible to receive out of order urbs causing a memory leak since the skb linked to the current tx urb is not removed. Fix the issue deallocating the skb cleaning up the tx ring. Moreover this patch fixes the following kernel warning

[ 57.480771] usb 1-1: USB disconnect, device number 2 [ 57.483451] ------------[ cut here ]------------ [ 57.483462] TX urb mismatch [ 57.483481] WARNING: CPU: 1 PID: 32 at drivers/net/wireless/mediatek/mt7601u/dma.c:245 mt7601u_complete_tx+0x165/00 [ 57.483483] Modules linked in: [ 57.483496] CPU: 1 PID: 32 Comm: kworker/1:1 Not tainted 5.2.0-rc1+ #72 [ 57.483498] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.12.0-2.fc30 04/01/2014 [ 57.483502] Workqueue: usb_hub_wq hub_event [ 57.483507] RIP: 0010:mt7601u_complete_tx+0x165/0x1e0 [ 57.483510] Code: 8b b5 10 04 00 00 8b 8d 14 04 00 00 eb 8b 80 3d b1 cb e1 00 00 75 9e 48 c7 c7 a4 ea 05 82 c6 05 f [ 57.483513] RSP: 0000:ffffc900000a0d28 EFLAGS: 00010092 [ 57.483516] RAX: 000000000000000f RBX: ffff88802c0a62c0 RCX: ffffc900000a0c2c [ 57.483518] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffffff810a8371 [ 57.483520] RBP: ffff88803ced6858 R08: 0000000000000000 R09: 0000000000000001 [ 57.483540] R10: 0000000000000002 R11: 0000000000000000 R12: 0000000000000046 [ 57.483542] R13: ffff88802c0a6c88 R14: ffff88803baab540 R15: ffff88803a0cc078 [ 57.483548] FS: 0000000000000000(0000) GS:ffff88803eb00000(0000) knlGS:0000000000000000 [ 57.483550] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 57.483552] CR2: 000055e7f6780100 CR3: 0000000028c86000 CR4: 00000000000006a0 [ 57.483554] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 57.483556] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 57.483559] Call Trace: [ 57.483561] <IRQ> [ 57.483565] __usb_hcd_giveback_urb+0x77/0xe0 [ 57.483570] xhci_giveback_urb_in_irq.isra.0+0x8b/0x140 [ 57.483574] handle_cmd_completion+0xf5b/0x12c0 [ 57.483577] xhci_irq+0x1f6/0x1810 [ 57.483581] ? lockdep_hardirqs_on+0x9e/0x180 [ 57.483584] ? _raw_spin_unlock_irq+0x24/0x30 [ 57.483588] __handle_irq_event_percpu+0x3a/0x260 [ 57.483592] handle_irq_event_percpu+0x1c/0x60 [ 57.483595] handle_irq_event+0x2f/0x4c [ 57.483599] handle_edge_irq+0x7e/0x1a0 [ 57.483603] handle_irq+0x17/0x20 [ 57.483607] do_IRQ+0x54/0x110 [ 57.483610] common_interrupt+0xf/0xf [ 57.483612] </IRQ>

Acked-by: Jakub Kicinski kubakici@wp.pl Signed-off-by: Lorenzo Bianconi lorenzo@kernel.org Signed-off-by: Kalle Valo kvalo@codeaurora.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/mediatek/mt7601u/dma.c | 21 ++++++++++++++++----- drivers/net/wireless/mediatek/mt7601u/tx.c | 4 ++-- 2 files changed, 18 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt7601u/dma.c b/drivers/net/wireless/mediatek/mt7601u/dma.c index 838ad9a4be51..56cad16e70ca 100644 --- a/drivers/net/wireless/mediatek/mt7601u/dma.c +++ b/drivers/net/wireless/mediatek/mt7601u/dma.c @@ -241,14 +241,25 @@ static void mt7601u_complete_tx(struct urb *urb) struct sk_buff *skb; unsigned long flags;

- spin_lock_irqsave(&dev->tx_lock, flags); + switch (urb->status) { + case -ECONNRESET: + case -ESHUTDOWN: + case -ENOENT: + return; + default: + dev_err_ratelimited(dev->dev, "tx urb failed: %d\n", + urb->status); + /* fall through */ + case 0: + break; + }

- if (mt7601u_urb_has_error(urb)) - dev_err(dev->dev, "Error: TX urb failed:%d\n", urb->status); + spin_lock_irqsave(&dev->tx_lock, flags); if (WARN_ONCE(q->e[q->start].urb != urb, "TX urb mismatch")) goto out;

skb = q->e[q->start].skb; + q->e[q->start].skb = NULL; trace_mt_tx_dma_done(dev, skb);

__skb_queue_tail(&dev->tx_skb_done, skb); @@ -448,10 +459,10 @@ static void mt7601u_free_tx_queue(struct mt7601u_tx_queue *q) { int i;

- WARN_ON(q->used); - for (i = 0; i < q->entries; i++) { usb_poison_urb(q->e[i].urb); + if (q->e[i].skb) + mt7601u_tx_status(q->dev, q->e[i].skb); usb_free_urb(q->e[i].urb); } } diff --git a/drivers/net/wireless/mediatek/mt7601u/tx.c b/drivers/net/wireless/mediatek/mt7601u/tx.c index ad77bec1ba0f..2cb1883c0d33 100644 --- a/drivers/net/wireless/mediatek/mt7601u/tx.c +++ b/drivers/net/wireless/mediatek/mt7601u/tx.c @@ -117,9 +117,9 @@ void mt7601u_tx_status(struct mt7601u_dev *dev, struct sk_buff *skb) info->status.rates[0].idx = -1; info->flags |= IEEE80211_TX_STAT_ACK;

- spin_lock(&dev->mac_lock); + spin_lock_bh(&dev->mac_lock); ieee80211_tx_status(dev->hw, skb); - spin_unlock(&dev->mac_lock); + spin_unlock_bh(&dev->mac_lock); }

static int mt7601u_skb_rooms(struct mt7601u_dev *dev, struct sk_buff *skb)

[ Upstream commit 9f94c7f947e919c343b30f080285af53d0fa9902 ]

Attempting to profile 1024 or more CPUs with perf causes two errors:

perf record -a [ perf record: Woken up X times to write data ] way too many cpu caches.. [ perf record: Captured and wrote X MB perf.data (X samples) ]

perf report -C 1024 Error: failed to set cpu bitmap Requested CPU 1024 too large. Consider raising MAX_NR_CPUS

Increasing MAX_NR_CPUS from 1024 to 2048 and redefining MAX_CACHES as MAX_NR_CPUS * 4 returns normal functionality to perf:

perf record -a [ perf record: Woken up X times to write data ] [ perf record: Captured and wrote X MB perf.data (X samples) ]

perf report -C 1024 ...

Signed-off-by: Kyle Meyer kyle.meyer@hpe.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Jiri Olsa jolsa@redhat.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Link: http://lkml.kernel.org/r/20190620193630.154025-1-meyerk@stormcage.eag.rdlabs... Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/perf.h | 2 +- tools/perf/util/header.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 8f8d895d5b74..3b9d56125ee2 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -23,7 +23,7 @@ static inline unsigned long long rdclock(void) }

#ifndef MAX_NR_CPUS -#define MAX_NR_CPUS 1024 +#define MAX_NR_CPUS 2048 #endif

extern const char *input_name; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index de9b369d2d2e..283148104ffb 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1008,7 +1008,7 @@ static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp) return 0; }

-#define MAX_CACHES 2000 +#define MAX_CACHES (MAX_NR_CPUS * 4)

static int write_cache(int fd, struct perf_header *h __maybe_unused, struct perf_evlist *evlist __maybe_unused)

[ Upstream commit 6282edb72bed5324352522d732080d4c1b9dfed6 ]

Exynos SoCs based on CA7/CA15 have 2 timer interfaces: custom Exynos MCT (Multi Core Timer) and standard ARM Architected Timers.

There are use cases, where both timer interfaces are used simultanously. One of such examples is using Exynos MCT for the main system timer and ARM Architected Timers for the KVM and virtualized guests (KVM requires arch timers).

Exynos Multi-Core Timer driver (exynos_mct) must be however started before ARM Architected Timers (arch_timer), because they both share some common hardware blocks (global system counter) and turning on MCT is needed to get ARM Architected Timer working properly.

To ensure selecting Exynos MCT as the main system timer, increase MCT timer rating. To ensure proper starting order of both timers during suspend/resume cycle, increase MCT hotplug priority over ARM Archictected Timers.

Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com Reviewed-by: Krzysztof Kozlowski krzk@kernel.org Reviewed-by: Chanwoo Choi cw00.choi@samsung.com Signed-off-by: Daniel Lezcano daniel.lezcano@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/clocksource/exynos_mct.c | 4 ++-- include/linux/cpuhotplug.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c index fb0cf8b74516..d32248e2ceab 100644 --- a/drivers/clocksource/exynos_mct.c +++ b/drivers/clocksource/exynos_mct.c @@ -211,7 +211,7 @@ static void exynos4_frc_resume(struct clocksource *cs)

static struct clocksource mct_frc = { .name = "mct-frc", - .rating = 400, + .rating = 450, /* use value higher than ARM arch timer */ .read = exynos4_frc_read, .mask = CLOCKSOURCE_MASK(32), .flags = CLOCK_SOURCE_IS_CONTINUOUS, @@ -466,7 +466,7 @@ static int exynos4_mct_starting_cpu(unsigned int cpu) evt->set_state_oneshot_stopped = set_state_shutdown; evt->tick_resume = set_state_shutdown; evt->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT; - evt->rating = 450; + evt->rating = 500; /* use value higher than ARM arch timer */

exynos4_mct_write(TICK_BASE_CNT, mevt->base + MCT_L_TCNTB_OFFSET);

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index c9447a689522..1ab0273560ae 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -77,10 +77,10 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING, CPUHP_AP_PERF_ARM_STARTING, CPUHP_AP_ARM_L2X0_STARTING, + CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING, CPUHP_AP_ARM_ARCH_TIMER_STARTING, CPUHP_AP_ARM_GLOBAL_TIMER_STARTING, CPUHP_AP_JCORE_TIMER_STARTING, - CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING, CPUHP_AP_ARM_TWD_STARTING, CPUHP_AP_METAG_TIMER_STARTING, CPUHP_AP_QCOM_TIMER_STARTING,

[ Upstream commit ef4d6a8556b637ad27c8c2a2cff1dda3da38e9a9 ]

Check if the syndrome provided by the caller is zero, and act accordingly.

Signed-off-by: Ferdinand Blomqvist ferdinand.blomqvist@gmail.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Link: https://lkml.kernel.org/r/20190620141039.9874-6-ferdinand.blomqvist@gmail.co... Signed-off-by: Sasha Levin sashal@kernel.org --- lib/reed_solomon/decode_rs.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/lib/reed_solomon/decode_rs.c b/lib/reed_solomon/decode_rs.c index 8eed0f9ac495..a5d313381539 100644 --- a/lib/reed_solomon/decode_rs.c +++ b/lib/reed_solomon/decode_rs.c @@ -42,8 +42,18 @@ BUG_ON(pad < 0 || pad >= nn);

/* Does the caller provide the syndrome ? */ - if (s != NULL) - goto decode; + if (s != NULL) { + for (i = 0; i < nroots; i++) { + /* The syndrome is in index form, + * so nn represents zero + */ + if (s[i] != nn) + goto decode; + } + + /* syndrome is zero, no errors to correct */ + return 0; + }

/* form the syndromes; i.e., evaluate data(x) at roots of * g(x) */

[ Upstream commit 90acc0653d2bee203174e66d519fbaaa513502de ]

Build testing with some core crypto options disabled revealed a few modules that are missing CRYPTO_HASH:

crypto/asymmetric_keys/x509_public_key.o: In function `x509_get_sig_params': x509_public_key.c:(.text+0x4c7): undefined reference to `crypto_alloc_shash' x509_public_key.c:(.text+0x5e5): undefined reference to `crypto_shash_digest' crypto/asymmetric_keys/pkcs7_verify.o: In function `pkcs7_digest.isra.0': pkcs7_verify.c:(.text+0xab): undefined reference to `crypto_alloc_shash' pkcs7_verify.c:(.text+0x1b2): undefined reference to `crypto_shash_digest' pkcs7_verify.c:(.text+0x3c1): undefined reference to `crypto_shash_update' pkcs7_verify.c:(.text+0x411): undefined reference to `crypto_shash_finup'

This normally doesn't show up in randconfig tests because there is a large number of other options that select CRYPTO_HASH.

Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Sasha Levin sashal@kernel.org --- crypto/asymmetric_keys/Kconfig | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/crypto/asymmetric_keys/Kconfig b/crypto/asymmetric_keys/Kconfig index 331f6baf2df8..13f3de68b479 100644 --- a/crypto/asymmetric_keys/Kconfig +++ b/crypto/asymmetric_keys/Kconfig @@ -14,6 +14,7 @@ config ASYMMETRIC_PUBLIC_KEY_SUBTYPE select MPILIB select CRYPTO_HASH_INFO select CRYPTO_AKCIPHER + select CRYPTO_HASH help This option provides support for asymmetric public key type handling. If signature generation and/or verification are to be used, @@ -33,6 +34,7 @@ config X509_CERTIFICATE_PARSER config PKCS7_MESSAGE_PARSER tristate "PKCS#7 message parser" depends on X509_CERTIFICATE_PARSER + select CRYPTO_HASH select ASN1 select OID_REGISTRY help @@ -55,6 +57,7 @@ config SIGNED_PE_FILE_VERIFICATION bool "Support for PE file signature verification" depends on PKCS7_MESSAGE_PARSER=y depends on SYSTEM_DATA_VERIFICATION + select CRYPTO_HASH select ASN1 select OID_REGISTRY help

[ Upstream commit b387e9b58679c60f5b1e4313939bd4878204fc37 ]

When system memory is in heavy pressure, bch_gc_thread_start() from run_cache_set() may fail due to out of memory. In such condition, c->gc_thread is assigned to -ENOMEM, not NULL pointer. Then in following failure code path bch_cache_set_error(), when cache_set_flush() gets called, the code piece to stop c->gc_thread is broken, if (!IS_ERR_OR_NULL(c->gc_thread)) kthread_stop(c->gc_thread);

And KASAN catches such NULL pointer deference problem, with the warning information:

[ 561.207881] ================================================================== [ 561.207900] BUG: KASAN: null-ptr-deref in kthread_stop+0x3b/0x440 [ 561.207904] Write of size 4 at addr 000000000000001c by task kworker/15:1/313

[ 561.207913] CPU: 15 PID: 313 Comm: kworker/15:1 Tainted: G W 5.0.0-vanilla+ #3 [ 561.207916] Hardware name: Lenovo ThinkSystem SR650 -[7X05CTO1WW]-/-[7X05CTO1WW]-, BIOS -[IVE136T-2.10]- 03/22/2019 [ 561.207935] Workqueue: events cache_set_flush [bcache] [ 561.207940] Call Trace: [ 561.207948] dump_stack+0x9a/0xeb [ 561.207955] ? kthread_stop+0x3b/0x440 [ 561.207960] ? kthread_stop+0x3b/0x440 [ 561.207965] kasan_report+0x176/0x192 [ 561.207973] ? kthread_stop+0x3b/0x440 [ 561.207981] kthread_stop+0x3b/0x440 [ 561.207995] cache_set_flush+0xd4/0x6d0 [bcache] [ 561.208008] process_one_work+0x856/0x1620 [ 561.208015] ? find_held_lock+0x39/0x1d0 [ 561.208028] ? drain_workqueue+0x380/0x380 [ 561.208048] worker_thread+0x87/0xb80 [ 561.208058] ? __kthread_parkme+0xb6/0x180 [ 561.208067] ? process_one_work+0x1620/0x1620 [ 561.208072] kthread+0x326/0x3e0 [ 561.208079] ? kthread_create_worker_on_cpu+0xc0/0xc0 [ 561.208090] ret_from_fork+0x3a/0x50 [ 561.208110] ================================================================== [ 561.208113] Disabling lock debugging due to kernel taint [ 561.208115] irq event stamp: 11800231 [ 561.208126] hardirqs last enabled at (11800231): [<ffffffff83008538>] do_syscall_64+0x18/0x410 [ 561.208127] BUG: unable to handle kernel NULL pointer dereference at 000000000000001c [ 561.208129] #PF error: [WRITE] [ 561.312253] hardirqs last disabled at (11800230): [<ffffffff830052ff>] trace_hardirqs_off_thunk+0x1a/0x1c [ 561.312259] softirqs last enabled at (11799832): [<ffffffff850005c7>] __do_softirq+0x5c7/0x8c3 [ 561.405975] PGD 0 P4D 0 [ 561.442494] softirqs last disabled at (11799821): [<ffffffff831add2c>] irq_exit+0x1ac/0x1e0 [ 561.791359] Oops: 0002 [#1] SMP KASAN NOPTI [ 561.791362] CPU: 15 PID: 313 Comm: kworker/15:1 Tainted: G B W 5.0.0-vanilla+ #3 [ 561.791363] Hardware name: Lenovo ThinkSystem SR650 -[7X05CTO1WW]-/-[7X05CTO1WW]-, BIOS -[IVE136T-2.10]- 03/22/2019 [ 561.791371] Workqueue: events cache_set_flush [bcache] [ 561.791374] RIP: 0010:kthread_stop+0x3b/0x440 [ 561.791376] Code: 00 00 65 8b 05 26 d5 e0 7c 89 c0 48 0f a3 05 ec aa df 02 0f 82 dc 02 00 00 4c 8d 63 20 be 04 00 00 00 4c 89 e7 e8 65 c5 53 00 <f0> ff 43 20 48 8d 7b 24 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 [ 561.791377] RSP: 0018:ffff88872fc8fd10 EFLAGS: 00010286 [ 561.838895] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree. [ 561.838916] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree. [ 561.838934] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree. [ 561.838948] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree. [ 561.838966] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree. [ 561.838979] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree. [ 561.838996] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree. [ 563.067028] RAX: 0000000000000000 RBX: fffffffffffffffc RCX: ffffffff832dd314 [ 563.067030] RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000297 [ 563.067032] RBP: ffff88872fc8fe88 R08: fffffbfff0b8213d R09: fffffbfff0b8213d [ 563.067034] R10: 0000000000000001 R11: fffffbfff0b8213c R12: 000000000000001c [ 563.408618] R13: ffff88dc61cc0f68 R14: ffff888102b94900 R15: ffff88dc61cc0f68 [ 563.408620] FS: 0000000000000000(0000) GS:ffff888f7dc00000(0000) knlGS:0000000000000000 [ 563.408622] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 563.408623] CR2: 000000000000001c CR3: 0000000f48a1a004 CR4: 00000000007606e0 [ 563.408625] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 563.408627] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 563.904795] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree. [ 563.915796] PKRU: 55555554 [ 563.915797] Call Trace: [ 563.915807] cache_set_flush+0xd4/0x6d0 [bcache] [ 563.915812] process_one_work+0x856/0x1620 [ 564.001226] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree. [ 564.033563] ? find_held_lock+0x39/0x1d0 [ 564.033567] ? drain_workqueue+0x380/0x380 [ 564.033574] worker_thread+0x87/0xb80 [ 564.062823] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree. [ 564.118042] ? __kthread_parkme+0xb6/0x180 [ 564.118046] ? process_one_work+0x1620/0x1620 [ 564.118048] kthread+0x326/0x3e0 [ 564.118050] ? kthread_create_worker_on_cpu+0xc0/0xc0 [ 564.167066] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree. [ 564.252441] ret_from_fork+0x3a/0x50 [ 564.252447] Modules linked in: msr rpcrdma sunrpc rdma_ucm ib_iser ib_umad rdma_cm ib_ipoib i40iw configfs iw_cm ib_cm libiscsi scsi_transport_iscsi mlx4_ib ib_uverbs mlx4_en ib_core nls_iso8859_1 nls_cp437 vfat fat intel_rapl skx_edac x86_pkg_temp_thermal coretemp iTCO_wdt iTCO_vendor_support crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel ses raid0 aesni_intel cdc_ether enclosure usbnet ipmi_ssif joydev aes_x86_64 i40e scsi_transport_sas mii bcache md_mod crypto_simd mei_me ioatdma crc64 ptp cryptd pcspkr i2c_i801 mlx4_core glue_helper pps_core mei lpc_ich dca wmi ipmi_si ipmi_devintf nd_pmem dax_pmem nd_btt ipmi_msghandler device_dax pcc_cpufreq button hid_generic usbhid mgag200 i2c_algo_bit drm_kms_helper syscopyarea sysfillrect xhci_pci sysimgblt fb_sys_fops xhci_hcd ttm megaraid_sas drm usbcore nfit libnvdimm sg dm_multipath dm_mod scsi_dh_rdac scsi_dh_emc scsi_dh_alua efivarfs [ 564.299390] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree. [ 564.348360] CR2: 000000000000001c [ 564.348362] ---[ end trace b7f0e5cc7b2103b0 ]---

Therefore, it is not enough to only check whether c->gc_thread is NULL, we should use IS_ERR_OR_NULL() to check both NULL pointer and error value.

This patch changes the above buggy code piece in this way, if (!IS_ERR_OR_NULL(c->gc_thread)) kthread_stop(c->gc_thread);

Signed-off-by: Coly Li colyli@suse.de Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/md/bcache/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 9f2588eaaf5f..c5bc3e5e921e 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1405,7 +1405,7 @@ static void cache_set_flush(struct closure *cl) kobject_put(&c->internal); kobject_del(&c->kobj);

- if (c->gc_thread) + if (!IS_ERR_OR_NULL(c->gc_thread)) kthread_stop(c->gc_thread);

if (!IS_ERR_OR_NULL(c->root))

[ Upstream commit 78226f6eaac80bf30256a33a4926c194ceefdf36 ]

This is for fixing bug KMSAN: uninit-value in ax88772_bind

Tested by https://groups.google.com/d/msg/syzkaller-bugs/aFQurGotng4/eB_HlNhhCwAJ

Reported-by: syzbot+8a3fc6674bbc3978ed4e@syzkaller.appspotmail.com

syzbot found the following crash on:

HEAD commit: f75e4cfe kmsan: use kmsan_handle_urb() in urb.c git tree: kmsan console output: https://syzkaller.appspot.com/x/log.txt?x=136d720ea00000 kernel config: https://syzkaller.appspot.com/x/.config?x=602468164ccdc30a dashboard link: https://syzkaller.appspot.com/bug?extid=8a3fc6674bbc3978ed4e compiler: clang version 9.0.0 (/home/glider/llvm/clang 06d00afa61eef8f7f501ebdb4e8612ea43ec2d78) syz repro: https://syzkaller.appspot.com/x/repro.syz?x=12788316a00000 C reproducer: https://syzkaller.appspot.com/x/repro.c?x=120359aaa00000

================================================================== BUG: KMSAN: uninit-value in is_valid_ether_addr include/linux/etherdevice.h:200 [inline] BUG: KMSAN: uninit-value in asix_set_netdev_dev_addr drivers/net/usb/asix_devices.c:73 [inline] BUG: KMSAN: uninit-value in ax88772_bind+0x93d/0x11e0 drivers/net/usb/asix_devices.c:724 CPU: 0 PID: 3348 Comm: kworker/0:2 Not tainted 5.1.0+ #1 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: usb_hub_wq hub_event Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x191/0x1f0 lib/dump_stack.c:113 kmsan_report+0x130/0x2a0 mm/kmsan/kmsan.c:622 __msan_warning+0x75/0xe0 mm/kmsan/kmsan_instr.c:310 is_valid_ether_addr include/linux/etherdevice.h:200 [inline] asix_set_netdev_dev_addr drivers/net/usb/asix_devices.c:73 [inline] ax88772_bind+0x93d/0x11e0 drivers/net/usb/asix_devices.c:724 usbnet_probe+0x10f5/0x3940 drivers/net/usb/usbnet.c:1728 usb_probe_interface+0xd66/0x1320 drivers/usb/core/driver.c:361 really_probe+0xdae/0x1d80 drivers/base/dd.c:513 driver_probe_device+0x1b3/0x4f0 drivers/base/dd.c:671 __device_attach_driver+0x5b8/0x790 drivers/base/dd.c:778 bus_for_each_drv+0x28e/0x3b0 drivers/base/bus.c:454 __device_attach+0x454/0x730 drivers/base/dd.c:844 device_initial_probe+0x4a/0x60 drivers/base/dd.c:891 bus_probe_device+0x137/0x390 drivers/base/bus.c:514 device_add+0x288d/0x30e0 drivers/base/core.c:2106 usb_set_configuration+0x30dc/0x3750 drivers/usb/core/message.c:2027 generic_probe+0xe7/0x280 drivers/usb/core/generic.c:210 usb_probe_device+0x14c/0x200 drivers/usb/core/driver.c:266 really_probe+0xdae/0x1d80 drivers/base/dd.c:513 driver_probe_device+0x1b3/0x4f0 drivers/base/dd.c:671 __device_attach_driver+0x5b8/0x790 drivers/base/dd.c:778 bus_for_each_drv+0x28e/0x3b0 drivers/base/bus.c:454 __device_attach+0x454/0x730 drivers/base/dd.c:844 device_initial_probe+0x4a/0x60 drivers/base/dd.c:891 bus_probe_device+0x137/0x390 drivers/base/bus.c:514 device_add+0x288d/0x30e0 drivers/base/core.c:2106 usb_new_device+0x23e5/0x2ff0 drivers/usb/core/hub.c:2534 hub_port_connect drivers/usb/core/hub.c:5089 [inline] hub_port_connect_change drivers/usb/core/hub.c:5204 [inline] port_event drivers/usb/core/hub.c:5350 [inline] hub_event+0x48d1/0x7290 drivers/usb/core/hub.c:5432 process_one_work+0x1572/0x1f00 kernel/workqueue.c:2269 process_scheduled_works kernel/workqueue.c:2331 [inline] worker_thread+0x189c/0x2460 kernel/workqueue.c:2417 kthread+0x4b5/0x4f0 kernel/kthread.c:254 ret_from_fork+0x35/0x40 arch/x86/entry/entry_64.S:355

Signed-off-by: Phong Tran tranmanphong@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/asix_devices.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 393fd3ed6b94..4b12b6da3fab 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -237,7 +237,7 @@ static void asix_phy_reset(struct usbnet *dev, unsigned int reset_bits) static int ax88172_bind(struct usbnet *dev, struct usb_interface *intf) { int ret = 0; - u8 buf[ETH_ALEN]; + u8 buf[ETH_ALEN] = {0}; int i; unsigned long gpio_bits = dev->driver_info->data;

@@ -687,7 +687,7 @@ static int asix_resume(struct usb_interface *intf) static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf) { int ret, i; - u8 buf[ETH_ALEN], chipcode = 0; + u8 buf[ETH_ALEN] = {0}, chipcode = 0; u32 phyid; struct asix_common_private *priv;

@@ -1064,7 +1064,7 @@ static const struct net_device_ops ax88178_netdev_ops = { static int ax88178_bind(struct usbnet *dev, struct usb_interface *intf) { int ret; - u8 buf[ETH_ALEN]; + u8 buf[ETH_ALEN] = {0};

usbnet_get_endpoints(dev,intf);

[ Upstream commit 4ce9146e0370fcd573f0372d9b4e5a211112567c ]

Syzkaller found that it is possible to provoke a memory leak by never freeing rx_skb in struct bcsp_struct.

Fix by freeing in bcsp_close()

Signed-off-by: Tomas Bortoli tomasbortoli@gmail.com Reported-by: syzbot+98162c885993b72f19c4@syzkaller.appspotmail.com Signed-off-by: Marcel Holtmann marcel@holtmann.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/bluetooth/hci_bcsp.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/bluetooth/hci_bcsp.c b/drivers/bluetooth/hci_bcsp.c index a2c921faaa12..34e04bf87a62 100644 --- a/drivers/bluetooth/hci_bcsp.c +++ b/drivers/bluetooth/hci_bcsp.c @@ -759,6 +759,11 @@ static int bcsp_close(struct hci_uart *hu) skb_queue_purge(&bcsp->rel); skb_queue_purge(&bcsp->unrel);

+ if (bcsp->rx_skb) { + kfree_skb(bcsp->rx_skb); + bcsp->rx_skb = NULL; + } + kfree(bcsp); return 0; }

[ Upstream commit 28261da8a26f4915aa257d12d506c6ba179d961f ]

Because of both sides doing L2CAP disconnection at the same time, it was possible to receive L2CAP Disconnection Response with CID that was already freed. That caused problems if CID was already reused and L2CAP Connection Request with same CID was sent out. Before this patch kernel deleted channel context regardless of the state of the channel.

Example where leftover Disconnection Response (frame #402) causes local device to delete L2CAP channel which was not yet connected. This in turn confuses remote device's stack because same CID is re-used without properly disconnecting.

Btmon capture before patch: ** snip **

ACL Data RX: Handle 43 flags 0x02 dlen 8 #394 [hci1] 10.748949

Channel: 65 len 4 [PSM 3 mode 0] {chan 2} RFCOMM: Disconnect (DISC) (0x43) Address: 0x03 cr 1 dlci 0x00 Control: 0x53 poll/final 1 Length: 0 FCS: 0xfd < ACL Data TX: Handle 43 flags 0x00 dlen 8 #395 [hci1] 10.749062 Channel: 65 len 4 [PSM 3 mode 0] {chan 2} RFCOMM: Unnumbered Ack (UA) (0x63) Address: 0x03 cr 1 dlci 0x00 Control: 0x73 poll/final 1 Length: 0 FCS: 0xd7 < ACL Data TX: Handle 43 flags 0x00 dlen 12 #396 [hci1] 10.749073 L2CAP: Disconnection Request (0x06) ident 17 len 4 Destination CID: 65 Source CID: 65

HCI Event: Number of Completed Packets (0x13) plen 5 #397 [hci1] 10.752391

Num handles: 1 Handle: 43 Count: 1

HCI Event: Number of Completed Packets (0x13) plen 5 #398 [hci1] 10.753394

Num handles: 1 Handle: 43 Count: 1

ACL Data RX: Handle 43 flags 0x02 dlen 12 #399 [hci1] 10.756499

L2CAP: Disconnection Request (0x06) ident 26 len 4 Destination CID: 65 Source CID: 65 < ACL Data TX: Handle 43 flags 0x00 dlen 12 #400 [hci1] 10.756548 L2CAP: Disconnection Response (0x07) ident 26 len 4 Destination CID: 65 Source CID: 65 < ACL Data TX: Handle 43 flags 0x00 dlen 12 #401 [hci1] 10.757459 L2CAP: Connection Request (0x02) ident 18 len 4 PSM: 1 (0x0001) Source CID: 65

ACL Data RX: Handle 43 flags 0x02 dlen 12 #402 [hci1] 10.759148

L2CAP: Disconnection Response (0x07) ident 17 len 4 Destination CID: 65 Source CID: 65 = bluetoothd: 00:1E:AB:4C:56:54: error updating services: Input/o.. 10.759447

HCI Event: Number of Completed Packets (0x13) plen 5 #403 [hci1] 10.759386

Num handles: 1 Handle: 43 Count: 1

ACL Data RX: Handle 43 flags 0x02 dlen 12 #404 [hci1] 10.760397

L2CAP: Connection Request (0x02) ident 27 len 4 PSM: 3 (0x0003) Source CID: 65 < ACL Data TX: Handle 43 flags 0x00 dlen 16 #405 [hci1] 10.760441 L2CAP: Connection Response (0x03) ident 27 len 8 Destination CID: 65 Source CID: 65 Result: Connection successful (0x0000) Status: No further information available (0x0000) < ACL Data TX: Handle 43 flags 0x00 dlen 27 #406 [hci1] 10.760449 L2CAP: Configure Request (0x04) ident 19 len 19 Destination CID: 65 Flags: 0x0000 Option: Maximum Transmission Unit (0x01) [mandatory] MTU: 1013 Option: Retransmission and Flow Control (0x04) [mandatory] Mode: Basic (0x00) TX window size: 0 Max transmit: 0 Retransmission timeout: 0 Monitor timeout: 0 Maximum PDU size: 0

HCI Event: Number of Completed Packets (0x13) plen 5 #407 [hci1] 10.761399

Num handles: 1 Handle: 43 Count: 1

ACL Data RX: Handle 43 flags 0x02 dlen 16 #408 [hci1] 10.762942

L2CAP: Connection Response (0x03) ident 18 len 8 Destination CID: 66 Source CID: 65 Result: Connection successful (0x0000) Status: No further information available (0x0000) *snip*

Similar case after the patch: *snip*

ACL Data RX: Handle 43 flags 0x02 dlen 8 #22702 [hci0] 1664.411056

Channel: 65 len 4 [PSM 3 mode 0] {chan 3} RFCOMM: Disconnect (DISC) (0x43) Address: 0x03 cr 1 dlci 0x00 Control: 0x53 poll/final 1 Length: 0 FCS: 0xfd < ACL Data TX: Handle 43 flags 0x00 dlen 8 #22703 [hci0] 1664.411136 Channel: 65 len 4 [PSM 3 mode 0] {chan 3} RFCOMM: Unnumbered Ack (UA) (0x63) Address: 0x03 cr 1 dlci 0x00 Control: 0x73 poll/final 1 Length: 0 FCS: 0xd7 < ACL Data TX: Handle 43 flags 0x00 dlen 12 #22704 [hci0] 1664.411143 L2CAP: Disconnection Request (0x06) ident 11 len 4 Destination CID: 65 Source CID: 65

HCI Event: Number of Completed Pac.. (0x13) plen 5 #22705 [hci0] 1664.414009

Num handles: 1 Handle: 43 Count: 1

HCI Event: Number of Completed Pac.. (0x13) plen 5 #22706 [hci0] 1664.415007

Num handles: 1 Handle: 43 Count: 1

ACL Data RX: Handle 43 flags 0x02 dlen 12 #22707 [hci0] 1664.418674

L2CAP: Disconnection Request (0x06) ident 17 len 4 Destination CID: 65 Source CID: 65 < ACL Data TX: Handle 43 flags 0x00 dlen 12 #22708 [hci0] 1664.418762 L2CAP: Disconnection Response (0x07) ident 17 len 4 Destination CID: 65 Source CID: 65 < ACL Data TX: Handle 43 flags 0x00 dlen 12 #22709 [hci0] 1664.421073 L2CAP: Connection Request (0x02) ident 12 len 4 PSM: 1 (0x0001) Source CID: 65

ACL Data RX: Handle 43 flags 0x02 dlen 12 #22710 [hci0] 1664.421371

L2CAP: Disconnection Response (0x07) ident 11 len 4 Destination CID: 65 Source CID: 65

HCI Event: Number of Completed Pac.. (0x13) plen 5 #22711 [hci0] 1664.424082

Num handles: 1 Handle: 43 Count: 1

HCI Event: Number of Completed Pac.. (0x13) plen 5 #22712 [hci0] 1664.425040

Num handles: 1 Handle: 43 Count: 1

ACL Data RX: Handle 43 flags 0x02 dlen 12 #22713 [hci0] 1664.426103

L2CAP: Connection Request (0x02) ident 18 len 4 PSM: 3 (0x0003) Source CID: 65 < ACL Data TX: Handle 43 flags 0x00 dlen 16 #22714 [hci0] 1664.426186 L2CAP: Connection Response (0x03) ident 18 len 8 Destination CID: 66 Source CID: 65 Result: Connection successful (0x0000) Status: No further information available (0x0000) < ACL Data TX: Handle 43 flags 0x00 dlen 27 #22715 [hci0] 1664.426196 L2CAP: Configure Request (0x04) ident 13 len 19 Destination CID: 65 Flags: 0x0000 Option: Maximum Transmission Unit (0x01) [mandatory] MTU: 1013 Option: Retransmission and Flow Control (0x04) [mandatory] Mode: Basic (0x00) TX window size: 0 Max transmit: 0 Retransmission timeout: 0 Monitor timeout: 0 Maximum PDU size: 0

ACL Data RX: Handle 43 flags 0x02 dlen 16 #22716 [hci0] 1664.428804

L2CAP: Connection Response (0x03) ident 12 len 8 Destination CID: 66 Source CID: 65 Result: Connection successful (0x0000) Status: No further information available (0x0000) *snip*

Fix is to check that channel is in state BT_DISCONN before deleting the channel.

This bug was found while fuzzing Bluez's OBEX implementation using Synopsys Defensics.

Reported-by: Matti Kamunen matti.kamunen@synopsys.com Reported-by: Ari Timonen ari.timonen@synopsys.com Signed-off-by: Matias Karhumaa matias.karhumaa@gmail.com Signed-off-by: Marcel Holtmann marcel@holtmann.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/bluetooth/l2cap_core.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index ec9b5d159591..48d23abfe799 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4374,6 +4374,12 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn,

l2cap_chan_lock(chan);

+ if (chan->state != BT_DISCONN) { + l2cap_chan_unlock(chan); + mutex_unlock(&conn->chan_lock); + return 0; + } + l2cap_chan_hold(chan); l2cap_chan_del(chan, 0);

[ Upstream commit 3f167e1921865b379a9becf03828e7202c7b4917 ]

ipv4_pdp_add() is called in RCU read-side critical section. So GFP_KERNEL should not be used in the function. This patch make ipv4_pdp_add() to use GFP_ATOMIC instead of GFP_KERNEL.

Test commands: gtp-link add gtp1 & gtp-tunnel add gtp1 v1 100 200 1.1.1.1 2.2.2.2

Splat looks like: [ 130.618881] ============================= [ 130.626382] WARNING: suspicious RCU usage [ 130.626994] 5.2.0-rc6+ #50 Not tainted [ 130.627622] ----------------------------- [ 130.628223] ./include/linux/rcupdate.h:266 Illegal context switch in RCU read-side critical section! [ 130.629684] [ 130.629684] other info that might help us debug this: [ 130.629684] [ 130.631022] [ 130.631022] rcu_scheduler_active = 2, debug_locks = 1 [ 130.632136] 4 locks held by gtp-tunnel/1025: [ 130.632925] #0: 000000002b93c8b7 (cb_lock){++++}, at: genl_rcv+0x15/0x40 [ 130.634159] #1: 00000000f17bc999 (genl_mutex){+.+.}, at: genl_rcv_msg+0xfb/0x130 [ 130.635487] #2: 00000000c644ed8e (rtnl_mutex){+.+.}, at: gtp_genl_new_pdp+0x18c/0x1150 [gtp] [ 130.636936] #3: 0000000007a1cde7 (rcu_read_lock){....}, at: gtp_genl_new_pdp+0x187/0x1150 [gtp] [ 130.638348] [ 130.638348] stack backtrace: [ 130.639062] CPU: 1 PID: 1025 Comm: gtp-tunnel Not tainted 5.2.0-rc6+ #50 [ 130.641318] Call Trace: [ 130.641707] dump_stack+0x7c/0xbb [ 130.642252] ___might_sleep+0x2c0/0x3b0 [ 130.642862] kmem_cache_alloc_trace+0x1cd/0x2b0 [ 130.643591] gtp_genl_new_pdp+0x6c5/0x1150 [gtp] [ 130.644371] genl_family_rcv_msg+0x63a/0x1030 [ 130.645074] ? mutex_lock_io_nested+0x1090/0x1090 [ 130.645845] ? genl_unregister_family+0x630/0x630 [ 130.646592] ? debug_show_all_locks+0x2d0/0x2d0 [ 130.647293] ? check_flags.part.40+0x440/0x440 [ 130.648099] genl_rcv_msg+0xa3/0x130 [ ... ]

Fixes: 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)") Signed-off-by: Taehee Yoo ap420073@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/gtp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index cb206e5526c4..60df6e391ad2 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -952,7 +952,7 @@ static int ipv4_pdp_add(struct net_device *dev, struct genl_info *info)

}

- pctx = kmalloc(sizeof(struct pdp_ctx), GFP_KERNEL); + pctx = kmalloc(sizeof(*pctx), GFP_ATOMIC); if (pctx == NULL) return -ENOMEM;

From: Juergen Gross jgross@suse.com

commit a1078e821b605813b63bf6bca414a85f804d5c66 upstream.

Instead of trying to allocate pages with GFP_USER in add_ballooned_pages() check the available free memory via si_mem_available(). GFP_USER is far less limiting memory exhaustion than the test via si_mem_available().

This will avoid dom0 running out of memory due to excessive foreign page mappings especially on ARM and on x86 in PVH mode, as those don't have a pre-ballooned area which can be used for foreign mappings.

As the normal ballooning suffers from the same problem don't balloon down more than si_mem_available() pages in one iteration. At the same time limit the default maximum number of retries.

This is part of XSA-300.

Signed-off-by: Juergen Gross jgross@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/xen/balloon.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-)

--- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -591,8 +591,15 @@ static void balloon_process(struct work_ state = reserve_additional_memory(); }

- if (credit < 0) - state = decrease_reservation(-credit, GFP_BALLOON); + if (credit < 0) { + long n_pages; + + n_pages = min(-credit, si_mem_available()); + state = decrease_reservation(n_pages, GFP_BALLOON); + if (state == BP_DONE && n_pages != -credit && + n_pages < totalreserve_pages) + state = BP_EAGAIN; + }

state = update_schedule(state);

@@ -631,6 +638,9 @@ static int add_ballooned_pages(int nr_pa } }

+ if (si_mem_available() < nr_pages) + return -ENOMEM; + st = decrease_reservation(nr_pages, GFP_USER); if (st != BP_DONE) return -ENOMEM; @@ -754,7 +764,7 @@ static int __init balloon_init(void) balloon_stats.schedule_delay = 1; balloon_stats.max_schedule_delay = 32; balloon_stats.retry_count = 1; - balloon_stats.max_retry_count = RETRY_UNLIMITED; + balloon_stats.max_retry_count = 4;

#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG set_online_page_callback(&xen_online_page);

From: Finn Thain fthain@telegraphics.com.au

commit 57f31326518e98ee4cabf9a04efe00ed57c54147 upstream.

The reselection interrupt gets disabled during selection and must be re-enabled when hostdata->connected becomes NULL. If it isn't re-enabled a disconnected command may time-out or the target may wedge the bus while trying to reselect the host. This can happen after a command is aborted.

Fix this by enabling the reselection interrupt in NCR5380_main() after calls to NCR5380_select() and NCR5380_information_transfer() return.

Cc: Michael Schmitz schmitzmic@gmail.com Cc: stable@vger.kernel.org # v4.9+ Fixes: 8b00c3d5d40d ("ncr5380: Implement new eh_abort_handler") Signed-off-by: Finn Thain fthain@telegraphics.com.au Tested-by: Stan Johnson userm57@yahoo.com Tested-by: Michael Schmitz schmitzmic@gmail.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/scsi/NCR5380.c | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-)

--- a/drivers/scsi/NCR5380.c +++ b/drivers/scsi/NCR5380.c @@ -813,6 +813,8 @@ static void NCR5380_main(struct work_str NCR5380_information_transfer(instance); done = 0; } + if (!hostdata->connected) + NCR5380_write(SELECT_ENABLE_REG, hostdata->id_mask); spin_unlock_irq(&hostdata->lock); if (!done) cond_resched(); @@ -1208,8 +1210,6 @@ static struct scsi_cmnd *NCR5380_select( spin_lock_irq(&hostdata->lock); NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE); NCR5380_reselect(instance); - if (!hostdata->connected) - NCR5380_write(SELECT_ENABLE_REG, hostdata->id_mask); shost_printk(KERN_ERR, instance, "reselection after won arbitration?\n"); goto out; } @@ -1217,7 +1217,6 @@ static struct scsi_cmnd *NCR5380_select( if (err < 0) { spin_lock_irq(&hostdata->lock); NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE); - NCR5380_write(SELECT_ENABLE_REG, hostdata->id_mask);

/* Can't touch cmd if it has been reclaimed by the scsi ML */ if (!hostdata->selecting) @@ -1255,7 +1254,6 @@ static struct scsi_cmnd *NCR5380_select( if (err < 0) { shost_printk(KERN_ERR, instance, "select: REQ timeout\n"); NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE); - NCR5380_write(SELECT_ENABLE_REG, hostdata->id_mask); goto out; } if (!hostdata->selecting) { @@ -1906,9 +1904,6 @@ static void NCR5380_information_transfer */ NCR5380_write(TARGET_COMMAND_REG, 0);

- /* Enable reselect interrupts */ - NCR5380_write(SELECT_ENABLE_REG, hostdata->id_mask); - maybe_release_dma_irq(instance); return; case MESSAGE_REJECT: @@ -1940,8 +1935,6 @@ static void NCR5380_information_transfer */ NCR5380_write(TARGET_COMMAND_REG, 0);

- /* Enable reselect interrupts */ - NCR5380_write(SELECT_ENABLE_REG, hostdata->id_mask); #ifdef SUN3_SCSI_VME dregs->csr |= CSR_DMA_ENABLE; #endif @@ -2049,7 +2042,6 @@ static void NCR5380_information_transfer cmd->result = DID_ERROR << 16; complete_cmd(instance, cmd); maybe_release_dma_irq(instance); - NCR5380_write(SELECT_ENABLE_REG, hostdata->id_mask); return; } msgout = NOP;

From: Eric Biggers ebiggers@google.com

commit 5c6bc4dfa515738149998bb0db2481a4fdead979 upstream.

Changing ghash_mod_init() to be subsys_initcall made it start running before the alignment fault handler has been installed on ARM. In kernel builds where the keys in the ghash test vectors happened to be misaligned in the kernel image, this exposed the longstanding bug that ghash_setkey() is incorrectly casting the key buffer (which can have any alignment) to be128 for passing to gf128mul_init_4k_lle().

Fix this by memcpy()ing the key to a temporary buffer.

Don't fix it by setting an alignmask on the algorithm instead because that would unnecessarily force alignment of the data too.

Fixes: 2cdc6899a88e ("crypto: ghash - Add GHASH digest algorithm for GCM") Reported-by: Peter Robinson pbrobinson@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Eric Biggers ebiggers@google.com Tested-by: Peter Robinson pbrobinson@gmail.com Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- crypto/ghash-generic.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

--- a/crypto/ghash-generic.c +++ b/crypto/ghash-generic.c @@ -34,6 +34,7 @@ static int ghash_setkey(struct crypto_sh const u8 *key, unsigned int keylen) { struct ghash_ctx *ctx = crypto_shash_ctx(tfm); + be128 k;

if (keylen != GHASH_BLOCK_SIZE) { crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); @@ -42,7 +43,12 @@ static int ghash_setkey(struct crypto_sh

if (ctx->gf128) gf128mul_free_4k(ctx->gf128); - ctx->gf128 = gf128mul_init_4k_lle((be128 *)key); + + BUILD_BUG_ON(sizeof(k) != GHASH_BLOCK_SIZE); + memcpy(&k, key, GHASH_BLOCK_SIZE); /* avoid violating alignment rules */ + ctx->gf128 = gf128mul_init_4k_lle(&k); + memzero_explicit(&k, GHASH_BLOCK_SIZE); + if (!ctx->gf128) return -ENOMEM;

From: Elena Petrova lenaptr@google.com

commit 6bd934de1e393466b319d29c4427598fda096c57 upstream.

The sha256-ce finup implementation for ARM64 produces wrong digest for empty input (len=0). Expected: the actual digest, result: initial value of SHA internal state. The error is in sha256_ce_finup: for empty data `finalize` will be 1, so the code is relying on sha2_ce_transform to make the final round. However, in sha256_base_do_update, the block function will not be called when len == 0.

Fix it by setting finalize to 0 if data is empty.

Fixes: 03802f6a80b3a ("crypto: arm64/sha2-ce - move SHA-224/256 ARMv8 implementation to base layer") Cc: stable@vger.kernel.org Signed-off-by: Elena Petrova lenaptr@google.com Reviewed-by: Ard Biesheuvel ard.biesheuvel@linaro.org Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/arm64/crypto/sha2-ce-glue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/arm64/crypto/sha2-ce-glue.c +++ b/arch/arm64/crypto/sha2-ce-glue.c @@ -52,7 +52,7 @@ static int sha256_ce_finup(struct shash_ unsigned int len, u8 *out) { struct sha256_ce_state *sctx = shash_desc_ctx(desc); - bool finalize = !sctx->sst.count && !(len % SHA256_BLOCK_SIZE); + bool finalize = !sctx->sst.count && !(len % SHA256_BLOCK_SIZE) && len;

/* * Allow the asm code to perform the finalization if there is no

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

commit 95566aa75cd6b3b404502c06f66956b5481194b3 upstream.

There is a possible double free issue in ppc4xx_trng_probe():

85: dev->trng_base = of_iomap(trng, 0); 86: of_node_put(trng); ---> released here 87: if (!dev->trng_base) 88: goto err_out; ... 110: ierr_out: 111: of_node_put(trng); ---> double released here ...

This issue was detected by using the Coccinelle software. We fix it by removing the unnecessary of_node_put().

Fixes: 5343e674f32f ("crypto4xx: integrate ppc4xx-rng into crypto4xx") Signed-off-by: Wen Yang wen.yang99@zte.com.cn Cc: stable@vger.kernel.org Cc: "David S. Miller" davem@davemloft.net Cc: Thomas Gleixner tglx@linutronix.de Cc: Greg Kroah-Hartman gregkh@linuxfoundation.org Cc: Allison Randal allison@lohutok.net Cc: Armijn Hemel armijn@tjaldur.nl Cc: Julia Lawall Julia.Lawall@lip6.fr Cc: linux-crypto@vger.kernel.org Cc: linux-kernel@vger.kernel.org Acked-by: Julia Lawall julia.lawall@lip6.fr Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/crypto/amcc/crypto4xx_trng.c | 1 - 1 file changed, 1 deletion(-)

--- a/drivers/crypto/amcc/crypto4xx_trng.c +++ b/drivers/crypto/amcc/crypto4xx_trng.c @@ -111,7 +111,6 @@ void ppc4xx_trng_probe(struct crypto4xx_ return;

err_out: - of_node_put(trng); iounmap(dev->trng_base); kfree(rng); dev->trng_base = NULL;

From: Krzysztof Kozlowski krzk@kernel.org

commit 16da0eb5ab6ef2dd1d33431199126e63db9997cc upstream.

On S2MPS11 device, the buck7 and buck8 regulator voltages start at 750 mV, not 600 mV. Using wrong minimal value caused shifting of these regulator values by 150 mV (e.g. buck7 usually configured to v1.35 V was reported as 1.2 V).

On most of the boards these regulators are left in default state so this was only affecting reported voltage. However if any driver wanted to change them, then effectively it would set voltage 150 mV higher than intended.

Cc: stable@vger.kernel.org Fixes: cb74685ecb39 ("regulator: s2mps11: Add samsung s2mps11 regulator driver") Signed-off-by: Krzysztof Kozlowski krzk@kernel.org Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/regulator/s2mps11.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/regulator/s2mps11.c +++ b/drivers/regulator/s2mps11.c @@ -386,8 +386,8 @@ static const struct regulator_desc s2mps regulator_desc_s2mps11_buck1_4(4), regulator_desc_s2mps11_buck5, regulator_desc_s2mps11_buck67810(6, MIN_600_MV, STEP_6_25_MV), - regulator_desc_s2mps11_buck67810(7, MIN_600_MV, STEP_12_5_MV), - regulator_desc_s2mps11_buck67810(8, MIN_600_MV, STEP_12_5_MV), + regulator_desc_s2mps11_buck67810(7, MIN_750_MV, STEP_12_5_MV), + regulator_desc_s2mps11_buck67810(8, MIN_750_MV, STEP_12_5_MV), regulator_desc_s2mps11_buck9, regulator_desc_s2mps11_buck67810(10, MIN_750_MV, STEP_12_5_MV), };

From: Emmanuel Grumbach emmanuel.grumbach@intel.com

commit 3b57a10ca14c619707398dc58fe5ece18c95b20b upstream.

Sometimes the register status can include interrupts that were masked. We can, for example, get the RF-Kill bit set in the interrupt status register although this interrupt was masked. Then if we get the ALIVE interrupt (for example) that was not masked, we need to *not* service the RF-Kill interrupt. Fix this in the MSI-X interrupt handler.

Cc: stable@vger.kernel.org Signed-off-by: Emmanuel Grumbach emmanuel.grumbach@intel.com Signed-off-by: Luca Coelho luciano.coelho@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/net/wireless/intel/iwlwifi/pcie/rx.c | 27 +++++++++++++++++++++------ 1 file changed, 21 insertions(+), 6 deletions(-)

--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c @@ -1901,10 +1901,18 @@ irqreturn_t iwl_pcie_irq_msix_handler(in return IRQ_NONE; }

- if (iwl_have_debug_level(IWL_DL_ISR)) - IWL_DEBUG_ISR(trans, "ISR inta_fh 0x%08x, enabled 0x%08x\n", - inta_fh, + if (iwl_have_debug_level(IWL_DL_ISR)) { + IWL_DEBUG_ISR(trans, + "ISR inta_fh 0x%08x, enabled (sw) 0x%08x (hw) 0x%08x\n", + inta_fh, trans_pcie->fh_mask, iwl_read32(trans, CSR_MSIX_FH_INT_MASK_AD)); + if (inta_fh & ~trans_pcie->fh_mask) + IWL_DEBUG_ISR(trans, + "We got a masked interrupt (0x%08x)\n", + inta_fh & ~trans_pcie->fh_mask); + } + + inta_fh &= trans_pcie->fh_mask;

if ((trans_pcie->shared_vec_mask & IWL_SHARED_IRQ_NON_RX) && inta_fh & MSIX_FH_INT_CAUSES_Q0) { @@ -1943,11 +1951,18 @@ irqreturn_t iwl_pcie_irq_msix_handler(in }

/* After checking FH register check HW register */ - if (iwl_have_debug_level(IWL_DL_ISR)) + if (iwl_have_debug_level(IWL_DL_ISR)) { IWL_DEBUG_ISR(trans, - "ISR inta_hw 0x%08x, enabled 0x%08x\n", - inta_hw, + "ISR inta_hw 0x%08x, enabled (sw) 0x%08x (hw) 0x%08x\n", + inta_hw, trans_pcie->hw_mask, iwl_read32(trans, CSR_MSIX_HW_INT_MASK_AD)); + if (inta_hw & ~trans_pcie->hw_mask) + IWL_DEBUG_ISR(trans, + "We got a masked interrupt 0x%08x\n", + inta_hw & ~trans_pcie->hw_mask); + } + + inta_hw &= trans_pcie->hw_mask;

/* Alive notification via Rx interrupt will do the real work */ if (inta_hw & MSIX_HW_INT_CAUSES_REG_ALIVE) {

From: Trond Myklebust trond.myklebust@hammerspace.com

commit 44942b4e457beda00981f616402a1a791e8c616e upstream.

According to the open() manpage, Linux reserves the access mode 3 to mean "check for read and write permission on the file and return a file descriptor that can't be used for reading or writing."

Currently, the NFSv4 code will ask the server to open the file, and will use an incorrect share access mode of 0. Since it has an incorrect share access mode, the client later forgets to send a corresponding close, meaning it can leak stateids on the server.

Fixes: ce4ef7c0a8a05 ("NFS: Split out NFS v4 file operations") Cc: stable@vger.kernel.org # 3.6+ Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/nfs/inode.c | 1 + fs/nfs/nfs4file.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-)

--- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -950,6 +950,7 @@ int nfs_open(struct inode *inode, struct nfs_fscache_open_file(inode, filp); return 0; } +EXPORT_SYMBOL_GPL(nfs_open);

/* * This function is called whenever some part of NFS notices that --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -49,7 +49,7 @@ nfs4_file_open(struct inode *inode, stru return err;

if ((openflags & O_ACCMODE) == 3) - openflags--; + return nfs_open(inode, filp);

/* We can't create new files here */ openflags &= ~(O_CREAT|O_EXCL);

From: Takashi Iwai tiwai@suse.de

commit ede34f397ddb063b145b9e7d79c6026f819ded13 upstream.

The fix for the racy writes and ioctls to sequencer widened the application of client->ioctl_mutex to the whole write loop. Although it does unlock/relock for the lengthy operation like the event dup, the loop keeps the ioctl_mutex for the whole time in other situations. This may take quite long time if the user-space would give a huge buffer, and this is a likely cause of some weird behavior spotted by syzcaller fuzzer.

This patch puts a simple workaround, just adding a mutex break in the loop when a large number of events have been processed. This shouldn't hit any performance drop because the threshold is set high enough for usual operations.

Fixes: 7bd800915677 ("ALSA: seq: More protection for concurrent write and ioctl races") Reported-by: syzbot+97aae04ce27e39cbfca9@syzkaller.appspotmail.com Reported-by: syzbot+4c595632b98bb8ffcc66@syzkaller.appspotmail.com Cc: stable@vger.kernel.org Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- sound/core/seq/seq_clientmgr.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-)

--- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -1001,7 +1001,7 @@ static ssize_t snd_seq_write(struct file { struct snd_seq_client *client = file->private_data; int written = 0, len; - int err; + int err, handled; struct snd_seq_event event;

if (!(snd_seq_file_flags(file) & SNDRV_SEQ_LFLG_OUTPUT)) @@ -1014,6 +1014,8 @@ static ssize_t snd_seq_write(struct file if (!client->accept_output || client->pool == NULL) return -ENXIO;

+ repeat: + handled = 0; /* allocate the pool now if the pool is not allocated yet */ mutex_lock(&client->ioctl_mutex); if (client->pool->size > 0 && !snd_seq_write_pool_allocated(client)) { @@ -1073,12 +1075,19 @@ static ssize_t snd_seq_write(struct file 0, 0, &client->ioctl_mutex); if (err < 0) break; + handled++;

__skip_event: /* Update pointers and counts */ count -= len; buf += len; written += len; + + /* let's have a coffee break if too many events are queued */ + if (++handled >= 200) { + mutex_unlock(&client->ioctl_mutex); + goto repeat; + } }

out:

From: Boris Brezillon boris.brezillon@collabora.com

commit 07d89227a983df957a6a7c56f7c040cde9ac571f upstream.

cfg->type can be overridden by v4l2_ctrl_fill() and the new value is stored in the local type var. Fix the tests to use this local var.

Fixes: 0996517cf8ea ("V4L/DVB: v4l2: Add new control handling framework") Cc: stable@vger.kernel.org Signed-off-by: Boris Brezillon boris.brezillon@collabora.com [hverkuil-cisco@xs4all.nl: change to !qmenu and !qmenu_int (checkpatch)] Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/media/v4l2-core/v4l2-ctrls.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-)

--- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -2103,16 +2103,15 @@ struct v4l2_ctrl *v4l2_ctrl_new_custom(s v4l2_ctrl_fill(cfg->id, &name, &type, &min, &max, &step, &def, &flags);

- is_menu = (cfg->type == V4L2_CTRL_TYPE_MENU || - cfg->type == V4L2_CTRL_TYPE_INTEGER_MENU); + is_menu = (type == V4L2_CTRL_TYPE_MENU || + type == V4L2_CTRL_TYPE_INTEGER_MENU); if (is_menu) WARN_ON(step); else WARN_ON(cfg->menu_skip_mask); - if (cfg->type == V4L2_CTRL_TYPE_MENU && qmenu == NULL) + if (type == V4L2_CTRL_TYPE_MENU && !qmenu) { qmenu = v4l2_ctrl_get_menu(cfg->id); - else if (cfg->type == V4L2_CTRL_TYPE_INTEGER_MENU && - qmenu_int == NULL) { + } else if (type == V4L2_CTRL_TYPE_INTEGER_MENU && !qmenu_int) { handler_set_err(hdl, -EINVAL); return NULL; }

From: Like Xu like.xu@linux.intel.com

commit 6fc3977ccc5d3c22e851f2dce2d3ce2a0a843842 upstream.

If a perf_event creation fails due to any reason of the host perf subsystem, it has no chance to log the corresponding event for guest which may cause abnormal sampling data in guest result. In debug mode, this message helps to understand the state of vPMC and we may not limit the number of occurrences but not in a spamming style.

Suggested-by: Joe Perches joe@perches.com Signed-off-by: Like Xu like.xu@linux.intel.com Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/kvm/pmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -124,8 +124,8 @@ static void pmc_reprogram_counter(struct intr ? kvm_perf_overflow_intr : kvm_perf_overflow, pmc); if (IS_ERR(event)) { - printk_once("kvm_pmu: event creation failed %ld\n", - PTR_ERR(event)); + pr_debug_ratelimited("kvm_pmu: event creation failed %ld for pmc->idx = %d\n", + PTR_ERR(event), pmc->idx); return; }

From: Radoslaw Burny rburny@google.com

commit 5ec27ec735ba0477d48c80561cc5e856f0c5dfaf upstream.

Normally, the inode's i_uid/i_gid are translated relative to s_user_ns, but this is not a correct behavior for proc. Since sysctl permission check in test_perm is done against GLOBAL_ROOT_[UG]ID, it makes more sense to use these values in u_[ug]id of proc inodes. In other words: although uid/gid in the inode is not read during test_perm, the inode logically belongs to the root of the namespace. I have confirmed this with Eric Biederman at LPC and in this thread: https://lore.kernel.org/lkml/87k1kzjdff.fsf@xmission.com

Consequences ============

Since the i_[ug]id values of proc nodes are not used for permissions checks, this change usually makes no functional difference. However, it causes an issue in a setup where:

* a namespace container is created without root user in container - hence the i_[ug]id of proc nodes are set to INVALID_[UG]ID

* container creator tries to configure it by writing /proc/sys files, e.g. writing /proc/sys/kernel/shmmax to configure shared memory limit

Kernel does not allow to open an inode for writing if its i_[ug]id are invalid, making it impossible to write shmmax and thus - configure the container.

Using a container with no root mapping is apparently rare, but we do use this configuration at Google. Also, we use a generic tool to configure the container limits, and the inability to write any of them causes a failure.

History =======

The invalid uids/gids in inodes first appeared due to 81754357770e (fs: Update i_[ug]id_(read|write) to translate relative to s_user_ns). However, AFAIK, this did not immediately cause any issues. The inability to write to these "invalid" inodes was only caused by a later commit 0bd23d09b874 (vfs: Don't modify inodes with a uid or gid unknown to the vfs).

Tested: Used a repro program that creates a user namespace without any mapping and stat'ed /proc/$PID/root/proc/sys/kernel/shmmax from outside. Before the change, it shows the overflow uid, with the change it's 0. The overflow uid indicates that the uid in the inode is not correct and thus it is not possible to open the file for writing.

Link: http://lkml.kernel.org/r/20190708115130.250149-1-rburny@google.com Fixes: 0bd23d09b874 ("vfs: Don't modify inodes with a uid or gid unknown to the vfs") Signed-off-by: Radoslaw Burny rburny@google.com Acked-by: Luis Chamberlain mcgrof@kernel.org Cc: Kees Cook keescook@chromium.org Cc: "Eric W . Biederman" ebiederm@xmission.com Cc: Seth Forshee seth.forshee@canonical.com Cc: John Sperbeck jsperbeck@google.com Cc: Alexey Dobriyan adobriyan@gmail.com Cc: stable@vger.kernel.org [4.8+] Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/proc/proc_sysctl.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -500,6 +500,10 @@ static struct inode *proc_sys_make_inode

if (root->set_ownership) root->set_ownership(head, table, &inode->i_uid, &inode->i_gid); + else { + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; + }

return inode; }

From: Daniel Jordan daniel.m.jordan@oracle.com

commit cf144f81a99d1a3928f90b0936accfd3f45c9a0a upstream.

Testing padata with the tcrypt module on a 5.2 kernel...

# modprobe tcrypt alg="pcrypt(rfc4106(gcm(aes)))" type=3 # modprobe tcrypt mode=211 sec=1

...produces this splat:

INFO: task modprobe:10075 blocked for more than 120 seconds. Not tainted 5.2.0-base+ #16 modprobe D 0 10075 10064 0x80004080 Call Trace: ? __schedule+0x4dd/0x610 ? ring_buffer_unlock_commit+0x23/0x100 schedule+0x6c/0x90 schedule_timeout+0x3b/0x320 ? trace_buffer_unlock_commit_regs+0x4f/0x1f0 wait_for_common+0x160/0x1a0 ? wake_up_q+0x80/0x80 { crypto_wait_req } # entries in braces added by hand { do_one_aead_op } { test_aead_jiffies } test_aead_speed.constprop.17+0x681/0xf30 [tcrypt] do_test+0x4053/0x6a2b [tcrypt] ? 0xffffffffa00f4000 tcrypt_mod_init+0x50/0x1000 [tcrypt] ...

The second modprobe command never finishes because in padata_reorder, CPU0's load of reorder_objects is executed before the unlocking store in spin_unlock_bh(pd->lock), causing CPU0 to miss CPU1's increment:

CPU0 CPU1

padata_reorder padata_do_serial LOAD reorder_objects // 0 INC reorder_objects // 1 padata_reorder TRYLOCK pd->lock // failed UNLOCK pd->lock

CPU0 deletes the timer before returning from padata_reorder and since no other job is submitted to padata, modprobe waits indefinitely.

Add a pair of full barriers to guarantee proper ordering:

CPU0 CPU1

padata_reorder padata_do_serial UNLOCK pd->lock smp_mb() LOAD reorder_objects INC reorder_objects smp_mb__after_atomic() padata_reorder TRYLOCK pd->lock

smp_mb__after_atomic is needed so the read part of the trylock operation comes after the INC, as Andrea points out. Thanks also to Andrea for help with writing a litmus test.

Fixes: 16295bec6398 ("padata: Generic parallelization/serialization interface") Signed-off-by: Daniel Jordan daniel.m.jordan@oracle.com Cc: stable@vger.kernel.org Cc: Andrea Parri andrea.parri@amarulasolutions.com Cc: Boqun Feng boqun.feng@gmail.com Cc: Herbert Xu herbert@gondor.apana.org.au Cc: Paul E. McKenney paulmck@linux.ibm.com Cc: Peter Zijlstra peterz@infradead.org Cc: Steffen Klassert steffen.klassert@secunet.com Cc: linux-arch@vger.kernel.org Cc: linux-crypto@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- kernel/padata.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)

--- a/kernel/padata.c +++ b/kernel/padata.c @@ -274,7 +274,12 @@ static void padata_reorder(struct parall * The next object that needs serialization might have arrived to * the reorder queues in the meantime, we will be called again * from the timer function if no one else cares for it. + * + * Ensure reorder_objects is read after pd->lock is dropped so we see + * an increment from another task in padata_do_serial. Pairs with + * smp_mb__after_atomic in padata_do_serial. */ + smp_mb(); if (atomic_read(&pd->reorder_objects) && !(pinst->flags & PADATA_RESET)) mod_timer(&pd->timer, jiffies + HZ); @@ -343,6 +348,13 @@ void padata_do_serial(struct padata_priv list_add_tail(&padata->list, &pqueue->reorder.list); spin_unlock(&pqueue->reorder.lock);

+ /* + * Ensure the atomic_inc of reorder_objects above is ordered correctly + * with the trylock of pd->lock in padata_reorder. Pairs with smp_mb + * in padata_reorder. + */ + smp_mb__after_atomic(); + put_cpu();

padata_reorder(pd);

From: Mika Westerberg mika.westerberg@linux.intel.com

commit 000dd5316e1c756a1c028f22e01d06a38249dd4d upstream.

PME polling does not take into account that a device that is directly connected to the host bridge may go into D3cold as well. This leads to a situation where the PME poll thread reads from a config space of a device that is in D3cold and gets incorrect information because the config space is not accessible.

Here is an example from Intel Ice Lake system where two PCIe root ports are in D3cold (I've instrumented the kernel to log the PMCSR register contents):

[ 62.971442] pcieport 0000:00:07.1: Check PME status, PMCSR=0xffff [ 62.971504] pcieport 0000:00:07.0: Check PME status, PMCSR=0xffff

Since 0xffff is interpreted so that PME is pending, the root ports will be runtime resumed. This repeats over and over again essentially blocking all runtime power management.

Prevent this from happening by checking whether the device is in D3cold before its PME status is read.

Fixes: 71a83bd727cc ("PCI/PM: add runtime PM support to PCIe port") Signed-off-by: Mika Westerberg mika.westerberg@linux.intel.com Reviewed-by: Lukas Wunner lukas@wunner.de Cc: 3.6+ stable@vger.kernel.org # v3.6+ Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/pci/pci.c | 7 +++++++ 1 file changed, 7 insertions(+)

--- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1786,6 +1786,13 @@ static void pci_pme_list_scan(struct wor */ if (bridge && bridge->current_state != PCI_D0) continue; + /* + * If the device is in D3cold it should not be + * polled either. + */ + if (pme_dev->dev->current_state == PCI_D3cold) + continue; + pci_pme_wakeup(pme_dev->dev, NULL); } else { list_del(&pme_dev->list);

From: Dan Williams dan.j.williams@intel.com

commit 7e3e888dfc138089f4c15a81b418e88f0978f744 upstream.

At namespace creation time there is the potential for the "expected to be zero" fields of a 'pfn' info-block to be filled with indeterminate data. While the kernel buffer is zeroed on allocation it is immediately overwritten by nd_pfn_validate() filling it with the current contents of the on-media info-block location. For fields like, 'flags' and the 'padding' it potentially means that future implementations can not rely on those fields being zero.

In preparation to stop using the 'start_pad' and 'end_trunc' fields for section alignment, arrange for fields that are not explicitly initialized to be guaranteed zero. Bump the minor version to indicate it is safe to assume the 'padding' and 'flags' are zero. Otherwise, this corruption is expected to benign since all other critical fields are explicitly initialized.

Note The cc: stable is about spreading this new policy to as many kernels as possible not fixing an issue in those kernels. It is not until the change titled "libnvdimm/pfn: Stop padding pmem namespaces to section alignment" where this improper initialization becomes a problem. So if someone decides to backport "libnvdimm/pfn: Stop padding pmem namespaces to section alignment" (which is not tagged for stable), make sure this pre-requisite is flagged.

Link: http://lkml.kernel.org/r/156092356065.979959.6681003754765958296.stgit@dwill... Fixes: 32ab0a3f5170 ("libnvdimm, pmem: 'struct page' for pmem") Signed-off-by: Dan Williams dan.j.williams@intel.com Tested-by: Aneesh Kumar K.V aneesh.kumar@linux.ibm.com [ppc64] Cc: stable@vger.kernel.org Cc: David Hildenbrand david@redhat.com Cc: Jane Chu jane.chu@oracle.com Cc: Jeff Moyer jmoyer@redhat.com Cc: Jérôme Glisse jglisse@redhat.com Cc: Jonathan Corbet corbet@lwn.net Cc: Logan Gunthorpe logang@deltatee.com Cc: Michal Hocko mhocko@suse.com Cc: Mike Rapoport rppt@linux.ibm.com Cc: Oscar Salvador osalvador@suse.de Cc: Pavel Tatashin pasha.tatashin@soleen.com Cc: Toshi Kani toshi.kani@hpe.com Cc: Vlastimil Babka vbabka@suse.cz Cc: Wei Yang richardw.yang@linux.intel.com Cc: Jason Gunthorpe jgg@mellanox.com Cc: Christoph Hellwig hch@lst.de Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/nvdimm/dax_devs.c | 2 +- drivers/nvdimm/pfn.h | 1 + drivers/nvdimm/pfn_devs.c | 18 +++++++++++++++--- 3 files changed, 17 insertions(+), 4 deletions(-)

--- a/drivers/nvdimm/dax_devs.c +++ b/drivers/nvdimm/dax_devs.c @@ -118,7 +118,7 @@ int nd_dax_probe(struct device *dev, str nvdimm_bus_unlock(&ndns->dev); if (!dax_dev) return -ENOMEM; - pfn_sb = devm_kzalloc(dev, sizeof(*pfn_sb), GFP_KERNEL); + pfn_sb = devm_kmalloc(dev, sizeof(*pfn_sb), GFP_KERNEL); nd_pfn->pfn_sb = pfn_sb; rc = nd_pfn_validate(nd_pfn, DAX_SIG); dev_dbg(dev, "%s: dax: %s\n", __func__, --- a/drivers/nvdimm/pfn.h +++ b/drivers/nvdimm/pfn.h @@ -36,6 +36,7 @@ struct nd_pfn_sb { __le32 end_trunc; /* minor-version-2 record the base alignment of the mapping */ __le32 align; + /* minor-version-3 guarantee the padding and flags are zero */ u8 padding[4000]; __le64 checksum; }; --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -349,6 +349,15 @@ struct device *nd_pfn_create(struct nd_r return dev; }

+/** + * nd_pfn_validate - read and validate info-block + * @nd_pfn: fsdax namespace runtime state / properties + * @sig: 'devdax' or 'fsdax' signature + * + * Upon return the info-block buffer contents (->pfn_sb) are + * indeterminate when validation fails, and a coherent info-block + * otherwise. + */ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig) { u64 checksum, offset; @@ -486,7 +495,7 @@ int nd_pfn_probe(struct device *dev, str nvdimm_bus_unlock(&ndns->dev); if (!pfn_dev) return -ENOMEM; - pfn_sb = devm_kzalloc(dev, sizeof(*pfn_sb), GFP_KERNEL); + pfn_sb = devm_kmalloc(dev, sizeof(*pfn_sb), GFP_KERNEL); nd_pfn = to_nd_pfn(pfn_dev); nd_pfn->pfn_sb = pfn_sb; rc = nd_pfn_validate(nd_pfn, PFN_SIG); @@ -584,7 +593,7 @@ static int nd_pfn_init(struct nd_pfn *nd u64 checksum; int rc;

- pfn_sb = devm_kzalloc(&nd_pfn->dev, sizeof(*pfn_sb), GFP_KERNEL); + pfn_sb = devm_kmalloc(&nd_pfn->dev, sizeof(*pfn_sb), GFP_KERNEL); if (!pfn_sb) return -ENOMEM;

@@ -593,11 +602,14 @@ static int nd_pfn_init(struct nd_pfn *nd sig = DAX_SIG; else sig = PFN_SIG; + rc = nd_pfn_validate(nd_pfn, sig); if (rc != -ENODEV) return rc;

/* no info block, do init */; + memset(pfn_sb, 0, sizeof(*pfn_sb)); + nd_region = to_nd_region(nd_pfn->dev.parent); if (nd_region->ro) { dev_info(&nd_pfn->dev, @@ -673,7 +685,7 @@ static int nd_pfn_init(struct nd_pfn *nd memcpy(pfn_sb->uuid, nd_pfn->uuid, 16); memcpy(pfn_sb->parent_uuid, nd_dev_to_uuid(&ndns->dev), 16); pfn_sb->version_major = cpu_to_le16(1); - pfn_sb->version_minor = cpu_to_le16(2); + pfn_sb->version_minor = cpu_to_le16(3); pfn_sb->start_pad = cpu_to_le32(start_pad); pfn_sb->end_trunc = cpu_to_le32(end_trunc); pfn_sb->align = cpu_to_le32(nd_pfn->align);

[ Upstream commit f3554aeb991214cbfafd17d55e2bfddb50282e32 ]

This fixes a divide by zero error in the setup_format_params function of the floppy driver.

Two consecutive ioctls can trigger the bug: The first one should set the drive geometry with such .sect and .rate values for the F_SECT_PER_TRACK to become zero. Next, the floppy format operation should be called.

A floppy disk is not required to be inserted. An unprivileged user could trigger the bug if the device is accessible.

The patch checks F_SECT_PER_TRACK for a non-zero value in the set_geometry function. The proper check should involve a reasonable upper limit for the .sect and .rate fields, but it could change the UAPI.

The patch also checks F_SECT_PER_TRACK in the setup_format_params, and cancels the formatting operation in case of zero.

The bug was found by syzkaller.

Signed-off-by: Denis Efremov efremov@ispras.ru Tested-by: Willy Tarreau w@1wt.eu Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/block/floppy.c | 5 +++++ 1 file changed, 5 insertions(+)

--- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -2114,6 +2114,9 @@ static void setup_format_params(int trac raw_cmd->kernel_data = floppy_track_buffer; raw_cmd->length = 4 * F_SECT_PER_TRACK;

+ if (!F_SECT_PER_TRACK) + return; + /* allow for about 30ms for data transport per track */ head_shift = (F_SECT_PER_TRACK + 5) / 6;

@@ -3236,6 +3239,8 @@ static int set_geometry(unsigned int cmd /* sanity checking for parameters. */ if (g->sect <= 0 || g->head <= 0 || + /* check for zero in F_SECT_PER_TRACK */ + (unsigned char)((g->sect << 2) >> FD_SIZECODE(g)) == 0 || g->track <= 0 || g->track > UDP->tracks >> STRETCH(g) || /* check if reserved bits are set */ (g->stretch & ~(FD_STRETCH | FD_SWAPSIDES | FD_SECTBASEMASK)) != 0)

[ Upstream commit 9b04609b784027968348796a18f601aed9db3789 ]

This fixes the invalid pointer dereference in the drive_name function of the floppy driver.

The native_format field of the struct floppy_drive_params is used as floppy_type array index in the drive_name function. Thus, the field should be checked the same way as the autodetect field.

To trigger the bug, one could use a value out of range and set the drive parameters with the FDSETDRVPRM ioctl. Next, FDGETDRVTYP ioctl should be used to call the drive_name. A floppy disk is not required to be inserted.

CAP_SYS_ADMIN is required to call FDSETDRVPRM.

The patch adds the check for a value of the native_format field to be in the '0 <= x < ARRAY_SIZE(floppy_type)' range of the floppy_type array indices.

The bug was found by syzkaller.

Signed-off-by: Denis Efremov efremov@ispras.ru Tested-by: Willy Tarreau w@1wt.eu Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/block/floppy.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-)

--- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -3384,7 +3384,8 @@ static int fd_getgeo(struct block_device return 0; }

-static bool valid_floppy_drive_params(const short autodetect[8]) +static bool valid_floppy_drive_params(const short autodetect[8], + int native_format) { size_t floppy_type_size = ARRAY_SIZE(floppy_type); size_t i = 0; @@ -3395,6 +3396,9 @@ static bool valid_floppy_drive_params(co return false; }

+ if (native_format < 0 || native_format >= floppy_type_size) + return false; + return true; }

@@ -3524,7 +3528,8 @@ static int fd_locked_ioctl(struct block_ SUPBOUND(size, strlen((const char *)outparam) + 1); break; case FDSETDRVPRM: - if (!valid_floppy_drive_params(inparam.dp.autodetect)) + if (!valid_floppy_drive_params(inparam.dp.autodetect, + inparam.dp.native_format)) return -EINVAL; *UDP = inparam.dp; break; @@ -3723,7 +3728,7 @@ static int compat_setdrvprm(int drive, return -EPERM; if (copy_from_user(&v, arg, sizeof(struct compat_floppy_drive_params))) return -EFAULT; - if (!valid_floppy_drive_params(v.autodetect)) + if (!valid_floppy_drive_params(v.autodetect, v.native_format)) return -EINVAL; mutex_lock(&floppy_mutex); UDP->cmos = v.cmos;

From: Jan Harkes jaharkes@cs.cmu.edu

commit 7fa0a1da3dadfd9216df7745a1331fdaa0940d1c upstream.

Patch series "Coda updates".

The following patch series is a collection of various fixes for Coda, most of which were collected from linux-fsdevel or linux-kernel but which have as yet not found their way upstream.

This patch (of 22):

Various file systems expect that vma->vm_file points at their own file handle, several use file_inode(vma->vm_file) to get at their inode or use vma->vm_file->private_data. However the way Coda wrapped mmap on a host file broke this assumption, vm_file was still pointing at the Coda file and the host file systems would scribble over Coda's inode and private file data.

This patch fixes the incorrect expectation and wraps vm_ops->open and vm_ops->close to allow Coda to track when the vm_area_struct is destroyed so we still release the reference on the Coda file handle at the right time.

[This patch differs from the original upstream patch because older stable kernels do not have the call_mmap vfs helper so we call f_ops->mmap directly.]

Link: http://lkml.kernel.org/r/0e850c6e59c0b147dc2dcd51a3af004c948c3697.1558117389... Signed-off-by: Jan Harkes jaharkes@cs.cmu.edu Cc: Arnd Bergmann arnd@arndb.de Cc: Colin Ian King colin.king@canonical.com Cc: Dan Carpenter dan.carpenter@oracle.com Cc: David Howells dhowells@redhat.com Cc: Fabian Frederick fabf@skynet.be Cc: Mikko Rapeli mikko.rapeli@iki.fi Cc: Sam Protsenko semen.protsenko@linaro.org Cc: Yann Droneaud ydroneaud@opteya.com Cc: Zhouyang Jia jiazhouyang09@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Jan Harkes jaharkes@cs.cmu.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/coda/file.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 68 insertions(+), 1 deletion(-)

--- a/fs/coda/file.c +++ b/fs/coda/file.c @@ -60,6 +60,41 @@ coda_file_write_iter(struct kiocb *iocb, return ret; }

+struct coda_vm_ops { + atomic_t refcnt; + struct file *coda_file; + const struct vm_operations_struct *host_vm_ops; + struct vm_operations_struct vm_ops; +}; + +static void +coda_vm_open(struct vm_area_struct *vma) +{ + struct coda_vm_ops *cvm_ops = + container_of(vma->vm_ops, struct coda_vm_ops, vm_ops); + + atomic_inc(&cvm_ops->refcnt); + + if (cvm_ops->host_vm_ops && cvm_ops->host_vm_ops->open) + cvm_ops->host_vm_ops->open(vma); +} + +static void +coda_vm_close(struct vm_area_struct *vma) +{ + struct coda_vm_ops *cvm_ops = + container_of(vma->vm_ops, struct coda_vm_ops, vm_ops); + + if (cvm_ops->host_vm_ops && cvm_ops->host_vm_ops->close) + cvm_ops->host_vm_ops->close(vma); + + if (atomic_dec_and_test(&cvm_ops->refcnt)) { + vma->vm_ops = cvm_ops->host_vm_ops; + fput(cvm_ops->coda_file); + kfree(cvm_ops); + } +} + static int coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma) { @@ -67,6 +102,8 @@ coda_file_mmap(struct file *coda_file, s struct coda_inode_info *cii; struct file *host_file; struct inode *coda_inode, *host_inode; + struct coda_vm_ops *cvm_ops; + int ret;

cfi = CODA_FTOC(coda_file); BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC); @@ -75,6 +112,13 @@ coda_file_mmap(struct file *coda_file, s if (!host_file->f_op->mmap) return -ENODEV;

+ if (WARN_ON(coda_file != vma->vm_file)) + return -EIO; + + cvm_ops = kmalloc(sizeof(struct coda_vm_ops), GFP_KERNEL); + if (!cvm_ops) + return -ENOMEM; + coda_inode = file_inode(coda_file); host_inode = file_inode(host_file);

@@ -88,6 +132,7 @@ coda_file_mmap(struct file *coda_file, s * the container file on us! */ else if (coda_inode->i_mapping != host_inode->i_mapping) { spin_unlock(&cii->c_lock); + kfree(cvm_ops); return -EBUSY; }

@@ -96,7 +141,29 @@ coda_file_mmap(struct file *coda_file, s cfi->cfi_mapcount++; spin_unlock(&cii->c_lock);

- return host_file->f_op->mmap(host_file, vma); + vma->vm_file = get_file(host_file); + ret = host_file->f_op->mmap(host_file, vma); + + if (ret) { + /* if call_mmap fails, our caller will put coda_file so we + * should drop the reference to the host_file that we got. + */ + fput(host_file); + kfree(cvm_ops); + } else { + /* here we add redirects for the open/close vm_operations */ + cvm_ops->host_vm_ops = vma->vm_ops; + if (vma->vm_ops) + cvm_ops->vm_ops = *vma->vm_ops; + + cvm_ops->vm_ops.open = coda_vm_open; + cvm_ops->vm_ops.close = coda_vm_close; + cvm_ops->coda_file = coda_file; + atomic_set(&cvm_ops->refcnt, 1); + + vma->vm_ops = &cvm_ops->vm_ops; + } + return ret; }

int coda_open(struct inode *coda_inode, struct file *coda_file)

From: Hook, Gary Gary.Hook@amd.com

commit 52393d617af7b554f03531e6756facf2ea687d2e upstream.

The error code read from the queue status register is only 6 bits wide, but we need to verify its value is within range before indexing the error messages.

Fixes: 81422badb3907 ("crypto: ccp - Make syslog errors human-readable") Cc: stable@vger.kernel.org Reported-by: Cfir Cohen cfir@google.com Signed-off-by: Gary R Hook gary.hook@amd.com Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/crypto/ccp/ccp-dev.c | 102 ++++++++++++++++++++++--------------------- drivers/crypto/ccp/ccp-dev.h | 2 2 files changed, 55 insertions(+), 49 deletions(-)

--- a/drivers/crypto/ccp/ccp-dev.c +++ b/drivers/crypto/ccp/ccp-dev.c @@ -40,57 +40,63 @@ struct ccp_tasklet_data { struct ccp_cmd *cmd; };

-/* Human-readable error strings */ -char *ccp_error_codes[] = { - "", - "ERR 01: ILLEGAL_ENGINE", - "ERR 02: ILLEGAL_KEY_ID", - "ERR 03: ILLEGAL_FUNCTION_TYPE", - "ERR 04: ILLEGAL_FUNCTION_MODE", - "ERR 05: ILLEGAL_FUNCTION_ENCRYPT", - "ERR 06: ILLEGAL_FUNCTION_SIZE", - "ERR 07: Zlib_MISSING_INIT_EOM", - "ERR 08: ILLEGAL_FUNCTION_RSVD", - "ERR 09: ILLEGAL_BUFFER_LENGTH", - "ERR 10: VLSB_FAULT", - "ERR 11: ILLEGAL_MEM_ADDR", - "ERR 12: ILLEGAL_MEM_SEL", - "ERR 13: ILLEGAL_CONTEXT_ID", - "ERR 14: ILLEGAL_KEY_ADDR", - "ERR 15: 0xF Reserved", - "ERR 16: Zlib_ILLEGAL_MULTI_QUEUE", - "ERR 17: Zlib_ILLEGAL_JOBID_CHANGE", - "ERR 18: CMD_TIMEOUT", - "ERR 19: IDMA0_AXI_SLVERR", - "ERR 20: IDMA0_AXI_DECERR", - "ERR 21: 0x15 Reserved", - "ERR 22: IDMA1_AXI_SLAVE_FAULT", - "ERR 23: IDMA1_AIXI_DECERR", - "ERR 24: 0x18 Reserved", - "ERR 25: ZLIBVHB_AXI_SLVERR", - "ERR 26: ZLIBVHB_AXI_DECERR", - "ERR 27: 0x1B Reserved", - "ERR 27: ZLIB_UNEXPECTED_EOM", - "ERR 27: ZLIB_EXTRA_DATA", - "ERR 30: ZLIB_BTYPE", - "ERR 31: ZLIB_UNDEFINED_SYMBOL", - "ERR 32: ZLIB_UNDEFINED_DISTANCE_S", - "ERR 33: ZLIB_CODE_LENGTH_SYMBOL", - "ERR 34: ZLIB _VHB_ILLEGAL_FETCH", - "ERR 35: ZLIB_UNCOMPRESSED_LEN", - "ERR 36: ZLIB_LIMIT_REACHED", - "ERR 37: ZLIB_CHECKSUM_MISMATCH0", - "ERR 38: ODMA0_AXI_SLVERR", - "ERR 39: ODMA0_AXI_DECERR", - "ERR 40: 0x28 Reserved", - "ERR 41: ODMA1_AXI_SLVERR", - "ERR 42: ODMA1_AXI_DECERR", - "ERR 43: LSB_PARITY_ERR", + /* Human-readable error strings */ +#define CCP_MAX_ERROR_CODE 64 + static char *ccp_error_codes[] = { + "", + "ILLEGAL_ENGINE", + "ILLEGAL_KEY_ID", + "ILLEGAL_FUNCTION_TYPE", + "ILLEGAL_FUNCTION_MODE", + "ILLEGAL_FUNCTION_ENCRYPT", + "ILLEGAL_FUNCTION_SIZE", + "Zlib_MISSING_INIT_EOM", + "ILLEGAL_FUNCTION_RSVD", + "ILLEGAL_BUFFER_LENGTH", + "VLSB_FAULT", + "ILLEGAL_MEM_ADDR", + "ILLEGAL_MEM_SEL", + "ILLEGAL_CONTEXT_ID", + "ILLEGAL_KEY_ADDR", + "0xF Reserved", + "Zlib_ILLEGAL_MULTI_QUEUE", + "Zlib_ILLEGAL_JOBID_CHANGE", + "CMD_TIMEOUT", + "IDMA0_AXI_SLVERR", + "IDMA0_AXI_DECERR", + "0x15 Reserved", + "IDMA1_AXI_SLAVE_FAULT", + "IDMA1_AIXI_DECERR", + "0x18 Reserved", + "ZLIBVHB_AXI_SLVERR", + "ZLIBVHB_AXI_DECERR", + "0x1B Reserved", + "ZLIB_UNEXPECTED_EOM", + "ZLIB_EXTRA_DATA", + "ZLIB_BTYPE", + "ZLIB_UNDEFINED_SYMBOL", + "ZLIB_UNDEFINED_DISTANCE_S", + "ZLIB_CODE_LENGTH_SYMBOL", + "ZLIB _VHB_ILLEGAL_FETCH", + "ZLIB_UNCOMPRESSED_LEN", + "ZLIB_LIMIT_REACHED", + "ZLIB_CHECKSUM_MISMATCH0", + "ODMA0_AXI_SLVERR", + "ODMA0_AXI_DECERR", + "0x28 Reserved", + "ODMA1_AXI_SLVERR", + "ODMA1_AXI_DECERR", };

-void ccp_log_error(struct ccp_device *d, int e) +void ccp_log_error(struct ccp_device *d, unsigned int e) { - dev_err(d->dev, "CCP error: %s (0x%x)\n", ccp_error_codes[e], e); + if (WARN_ON(e >= CCP_MAX_ERROR_CODE)) + return; + + if (e < ARRAY_SIZE(ccp_error_codes)) + dev_err(d->dev, "CCP error %d: %s\n", e, ccp_error_codes[e]); + else + dev_err(d->dev, "CCP error %d: Unknown Error\n", e); }

/* List of CCPs, CCP count, read-write access lock, and access functions --- a/drivers/crypto/ccp/ccp-dev.h +++ b/drivers/crypto/ccp/ccp-dev.h @@ -607,7 +607,7 @@ void ccp_platform_exit(void); void ccp_add_device(struct ccp_device *ccp); void ccp_del_device(struct ccp_device *ccp);

-extern void ccp_log_error(struct ccp_device *, int); +extern void ccp_log_error(struct ccp_device *, unsigned int);

struct ccp_device *ccp_alloc_struct(struct device *dev); bool ccp_queues_suspended(struct ccp_device *ccp);

From: Dexuan Cui decui@microsoft.com

commit 4df591b20b80cb77920953812d894db259d85bd7 upstream.

Fix a use-after-free in hv_eject_device_work().

Fixes: 05f151a73ec2 ("PCI: hv: Fix a memory leak in hv_eject_device_work()") Signed-off-by: Dexuan Cui decui@microsoft.com Signed-off-by: Lorenzo Pieralisi lorenzo.pieralisi@arm.com Reviewed-by: Michael Kelley mikelley@microsoft.com Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/pci/host/pci-hyperv.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-)

--- a/drivers/pci/host/pci-hyperv.c +++ b/drivers/pci/host/pci-hyperv.c @@ -1575,6 +1575,7 @@ static void hv_pci_devices_present(struc static void hv_eject_device_work(struct work_struct *work) { struct pci_eject_response *ejct_pkt; + struct hv_pcibus_device *hbus; struct hv_pci_dev *hpdev; struct pci_dev *pdev; unsigned long flags; @@ -1585,6 +1586,7 @@ static void hv_eject_device_work(struct } ctxt;

hpdev = container_of(work, struct hv_pci_dev, wrk); + hbus = hpdev->hbus;

if (hpdev->state != hv_pcichild_ejecting) { put_pcichild(hpdev, hv_pcidev_ref_pnp); @@ -1598,8 +1600,7 @@ static void hv_eject_device_work(struct * because hbus->pci_bus may not exist yet. */ wslot = wslot_to_devfn(hpdev->desc.win_slot.slot); - pdev = pci_get_domain_bus_and_slot(hpdev->hbus->sysdata.domain, 0, - wslot); + pdev = pci_get_domain_bus_and_slot(hbus->sysdata.domain, 0, wslot); if (pdev) { pci_lock_rescan_remove(); pci_stop_and_remove_bus_device(pdev); @@ -1607,22 +1608,24 @@ static void hv_eject_device_work(struct pci_unlock_rescan_remove(); }

- spin_lock_irqsave(&hpdev->hbus->device_list_lock, flags); + spin_lock_irqsave(&hbus->device_list_lock, flags); list_del(&hpdev->list_entry); - spin_unlock_irqrestore(&hpdev->hbus->device_list_lock, flags); + spin_unlock_irqrestore(&hbus->device_list_lock, flags);

memset(&ctxt, 0, sizeof(ctxt)); ejct_pkt = (struct pci_eject_response *)&ctxt.pkt.message; ejct_pkt->message_type.type = PCI_EJECTION_COMPLETE; ejct_pkt->wslot.slot = hpdev->desc.win_slot.slot; - vmbus_sendpacket(hpdev->hbus->hdev->channel, ejct_pkt, + vmbus_sendpacket(hbus->hdev->channel, ejct_pkt, sizeof(*ejct_pkt), (unsigned long)&ctxt.pkt, VM_PKT_DATA_INBAND, 0);

put_pcichild(hpdev, hv_pcidev_ref_childlist); put_pcichild(hpdev, hv_pcidev_ref_initial); put_pcichild(hpdev, hv_pcidev_ref_pnp); - put_hvpcibus(hpdev->hbus); + + /* hpdev has been freed. Do not use it any more. */ + put_hvpcibus(hbus); }

/**

From: Florian Fainelli f.fainelli@gmail.com

commit 0a987645672ebde7844a9c0732a5a25f3d4bb6c6 upstream.

Commit a78ff1112263 ("um: add extended processor state save/restore support") and b6024b21fec8 ("um: extend fpstate to _xstate to support YMM registers") forced the use of the x86 FP _xstate and PTRACE_GETREGSET/SETREGSET. On older hosts, we would neither be able to build UML nor run it anymore with these two commits applied because we don't have definitions for struct _xstate nor these two ptrace requests.

We can determine at build time which fp context structure to check against, just like we can keep using the old i387 fp save/restore if PTRACE_GETRESET/SETREGSET are not defined.

Fixes: a78ff1112263 ("um: add extended processor state save/restore support") Fixes: b6024b21fec8 ("um: extend fpstate to _xstate to support YMM registers") Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: Richard Weinberger richard@nod.at Signed-off-by: Alessio Balsini balsini@android.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/x86/um/os-Linux/registers.c | 12 ++++++++---- arch/x86/um/user-offsets.c | 4 ++++ 2 files changed, 12 insertions(+), 4 deletions(-)

--- a/arch/x86/um/os-Linux/registers.c +++ b/arch/x86/um/os-Linux/registers.c @@ -26,6 +26,7 @@ int save_i387_registers(int pid, unsigne

int save_fp_registers(int pid, unsigned long *fp_regs) { +#ifdef PTRACE_GETREGSET struct iovec iov;

if (have_xstate_support) { @@ -34,9 +35,9 @@ int save_fp_registers(int pid, unsigned if (ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov) < 0) return -errno; return 0; - } else { + } else +#endif return save_i387_registers(pid, fp_regs); - } }

int restore_i387_registers(int pid, unsigned long *fp_regs) @@ -48,6 +49,7 @@ int restore_i387_registers(int pid, unsi

int restore_fp_registers(int pid, unsigned long *fp_regs) { +#ifdef PTRACE_SETREGSET struct iovec iov;

if (have_xstate_support) { @@ -56,9 +58,9 @@ int restore_fp_registers(int pid, unsign if (ptrace(PTRACE_SETREGSET, pid, NT_X86_XSTATE, &iov) < 0) return -errno; return 0; - } else { + } else +#endif return restore_i387_registers(pid, fp_regs); - } }

#ifdef __i386__ @@ -122,6 +124,7 @@ int put_fp_registers(int pid, unsigned l

void arch_init_registers(int pid) { +#ifdef PTRACE_GETREGSET struct _xstate fp_regs; struct iovec iov;

@@ -129,6 +132,7 @@ void arch_init_registers(int pid) iov.iov_len = sizeof(struct _xstate); if (ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov) == 0) have_xstate_support = 1; +#endif } #endif

--- a/arch/x86/um/user-offsets.c +++ b/arch/x86/um/user-offsets.c @@ -50,7 +50,11 @@ void foo(void) DEFINE(HOST_GS, GS); DEFINE(HOST_ORIG_AX, ORIG_EAX); #else +#if defined(PTRACE_GETREGSET) && defined(PTRACE_SETREGSET) DEFINE(HOST_FP_SIZE, sizeof(struct _xstate) / sizeof(unsigned long)); +#else + DEFINE(HOST_FP_SIZE, sizeof(struct _fpstate) / sizeof(unsigned long)); +#endif DEFINE_LONGS(HOST_BX, RBX); DEFINE_LONGS(HOST_CX, RCX); DEFINE_LONGS(HOST_DI, RDI);

From: Helge Deller deller@gmx.de

commit 34c32fc603311a72cb558e5e337555434f64c27b upstream.

On parisc the privilege level of a process is stored in the lowest two bits of the instruction pointers (IAOQ0 and IAOQ1). On Linux we use privilege level 0 for the kernel and privilege level 3 for user-space. So userspace should not be allowed to modify IAOQ0 or IAOQ1 of a ptraced process to change it's privilege level to e.g. 0 to try to gain kernel privileges.

This patch prevents such modifications in the regset support functions by always setting the two lowest bits to one (which relates to privilege level 3 for user-space) if IAOQ0 or IAOQ1 are modified via ptrace regset calls.

Link: https://bugs.gentoo.org/481768 Cc: stable@vger.kernel.org # v4.7+ Tested-by: Rolf Eike Beer eike-kernel@sf-tec.de Signed-off-by: Helge Deller deller@gmx.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/parisc/kernel/ptrace.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -499,7 +499,8 @@ static void set_reg(struct pt_regs *regs return; case RI(iaoq[0]): case RI(iaoq[1]): - regs->iaoq[num - RI(iaoq[0])] = val; + /* set 2 lowest bits to ensure userspace privilege: */ + regs->iaoq[num - RI(iaoq[0])] = val | 3; return; case RI(sar): regs->sar = val; return;

From: Christophe Leroy christophe.leroy@c-s.fr

commit 6ecb78ef56e08d2119d337ae23cb951a640dc52d upstream.

Previously, only IBAT1 and IBAT2 were used to map kernel linear mem. Since commit 63b2bc619565 ("powerpc/mm/32s: Use BATs for STRICT_KERNEL_RWX"), we may have all 8 BATs used for mapping kernel text. But the suspend/restore functions only save/restore BATs 0 to 3, and clears BATs 4 to 7.

Make suspend and restore functions respectively save and reload the 8 BATs on CPUs having MMU_FTR_USE_HIGH_BATS feature.

Reported-by: Andreas Schwab schwab@linux-m68k.org Cc: stable@vger.kernel.org Signed-off-by: Christophe Leroy christophe.leroy@c-s.fr Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/powerpc/kernel/swsusp_32.S | 73 ++++++++++++++++++++++++++++---- arch/powerpc/platforms/powermac/sleep.S | 68 +++++++++++++++++++++++++++-- 2 files changed, 128 insertions(+), 13 deletions(-)

--- a/arch/powerpc/kernel/swsusp_32.S +++ b/arch/powerpc/kernel/swsusp_32.S @@ -23,11 +23,19 @@ #define SL_IBAT2 0x48 #define SL_DBAT3 0x50 #define SL_IBAT3 0x58 -#define SL_TB 0x60 -#define SL_R2 0x68 -#define SL_CR 0x6c -#define SL_LR 0x70 -#define SL_R12 0x74 /* r12 to r31 */ +#define SL_DBAT4 0x60 +#define SL_IBAT4 0x68 +#define SL_DBAT5 0x70 +#define SL_IBAT5 0x78 +#define SL_DBAT6 0x80 +#define SL_IBAT6 0x88 +#define SL_DBAT7 0x90 +#define SL_IBAT7 0x98 +#define SL_TB 0xa0 +#define SL_R2 0xa8 +#define SL_CR 0xac +#define SL_LR 0xb0 +#define SL_R12 0xb4 /* r12 to r31 */ #define SL_SIZE (SL_R12 + 80)

.section .data @@ -112,6 +120,41 @@ _GLOBAL(swsusp_arch_suspend) mfibatl r4,3 stw r4,SL_IBAT3+4(r11)

+BEGIN_MMU_FTR_SECTION + mfspr r4,SPRN_DBAT4U + stw r4,SL_DBAT4(r11) + mfspr r4,SPRN_DBAT4L + stw r4,SL_DBAT4+4(r11) + mfspr r4,SPRN_DBAT5U + stw r4,SL_DBAT5(r11) + mfspr r4,SPRN_DBAT5L + stw r4,SL_DBAT5+4(r11) + mfspr r4,SPRN_DBAT6U + stw r4,SL_DBAT6(r11) + mfspr r4,SPRN_DBAT6L + stw r4,SL_DBAT6+4(r11) + mfspr r4,SPRN_DBAT7U + stw r4,SL_DBAT7(r11) + mfspr r4,SPRN_DBAT7L + stw r4,SL_DBAT7+4(r11) + mfspr r4,SPRN_IBAT4U + stw r4,SL_IBAT4(r11) + mfspr r4,SPRN_IBAT4L + stw r4,SL_IBAT4+4(r11) + mfspr r4,SPRN_IBAT5U + stw r4,SL_IBAT5(r11) + mfspr r4,SPRN_IBAT5L + stw r4,SL_IBAT5+4(r11) + mfspr r4,SPRN_IBAT6U + stw r4,SL_IBAT6(r11) + mfspr r4,SPRN_IBAT6L + stw r4,SL_IBAT6+4(r11) + mfspr r4,SPRN_IBAT7U + stw r4,SL_IBAT7(r11) + mfspr r4,SPRN_IBAT7L + stw r4,SL_IBAT7+4(r11) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) + #if 0 /* Backup various CPU config stuffs */ bl __save_cpu_setup @@ -277,27 +320,41 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) mtibatu 3,r4 lwz r4,SL_IBAT3+4(r11) mtibatl 3,r4 -#endif - BEGIN_MMU_FTR_SECTION - li r4,0 + lwz r4,SL_DBAT4(r11) mtspr SPRN_DBAT4U,r4 + lwz r4,SL_DBAT4+4(r11) mtspr SPRN_DBAT4L,r4 + lwz r4,SL_DBAT5(r11) mtspr SPRN_DBAT5U,r4 + lwz r4,SL_DBAT5+4(r11) mtspr SPRN_DBAT5L,r4 + lwz r4,SL_DBAT6(r11) mtspr SPRN_DBAT6U,r4 + lwz r4,SL_DBAT6+4(r11) mtspr SPRN_DBAT6L,r4 + lwz r4,SL_DBAT7(r11) mtspr SPRN_DBAT7U,r4 + lwz r4,SL_DBAT7+4(r11) mtspr SPRN_DBAT7L,r4 + lwz r4,SL_IBAT4(r11) mtspr SPRN_IBAT4U,r4 + lwz r4,SL_IBAT4+4(r11) mtspr SPRN_IBAT4L,r4 + lwz r4,SL_IBAT5(r11) mtspr SPRN_IBAT5U,r4 + lwz r4,SL_IBAT5+4(r11) mtspr SPRN_IBAT5L,r4 + lwz r4,SL_IBAT6(r11) mtspr SPRN_IBAT6U,r4 + lwz r4,SL_IBAT6+4(r11) mtspr SPRN_IBAT6L,r4 + lwz r4,SL_IBAT7(r11) mtspr SPRN_IBAT7U,r4 + lwz r4,SL_IBAT7+4(r11) mtspr SPRN_IBAT7L,r4 END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) +#endif

/* Flush all TLBs */ lis r4,0x1000 --- a/arch/powerpc/platforms/powermac/sleep.S +++ b/arch/powerpc/platforms/powermac/sleep.S @@ -37,10 +37,18 @@ #define SL_IBAT2 0x48 #define SL_DBAT3 0x50 #define SL_IBAT3 0x58 -#define SL_TB 0x60 -#define SL_R2 0x68 -#define SL_CR 0x6c -#define SL_R12 0x70 /* r12 to r31 */ +#define SL_DBAT4 0x60 +#define SL_IBAT4 0x68 +#define SL_DBAT5 0x70 +#define SL_IBAT5 0x78 +#define SL_DBAT6 0x80 +#define SL_IBAT6 0x88 +#define SL_DBAT7 0x90 +#define SL_IBAT7 0x98 +#define SL_TB 0xa0 +#define SL_R2 0xa8 +#define SL_CR 0xac +#define SL_R12 0xb0 /* r12 to r31 */ #define SL_SIZE (SL_R12 + 80)

.section .text @@ -125,6 +133,41 @@ _GLOBAL(low_sleep_handler) mfibatl r4,3 stw r4,SL_IBAT3+4(r1)

+BEGIN_MMU_FTR_SECTION + mfspr r4,SPRN_DBAT4U + stw r4,SL_DBAT4(r1) + mfspr r4,SPRN_DBAT4L + stw r4,SL_DBAT4+4(r1) + mfspr r4,SPRN_DBAT5U + stw r4,SL_DBAT5(r1) + mfspr r4,SPRN_DBAT5L + stw r4,SL_DBAT5+4(r1) + mfspr r4,SPRN_DBAT6U + stw r4,SL_DBAT6(r1) + mfspr r4,SPRN_DBAT6L + stw r4,SL_DBAT6+4(r1) + mfspr r4,SPRN_DBAT7U + stw r4,SL_DBAT7(r1) + mfspr r4,SPRN_DBAT7L + stw r4,SL_DBAT7+4(r1) + mfspr r4,SPRN_IBAT4U + stw r4,SL_IBAT4(r1) + mfspr r4,SPRN_IBAT4L + stw r4,SL_IBAT4+4(r1) + mfspr r4,SPRN_IBAT5U + stw r4,SL_IBAT5(r1) + mfspr r4,SPRN_IBAT5L + stw r4,SL_IBAT5+4(r1) + mfspr r4,SPRN_IBAT6U + stw r4,SL_IBAT6(r1) + mfspr r4,SPRN_IBAT6L + stw r4,SL_IBAT6+4(r1) + mfspr r4,SPRN_IBAT7U + stw r4,SL_IBAT7(r1) + mfspr r4,SPRN_IBAT7L + stw r4,SL_IBAT7+4(r1) +END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) + /* Backup various CPU config stuffs */ bl __save_cpu_setup

@@ -325,22 +368,37 @@ grackle_wake_up: mtibatl 3,r4

BEGIN_MMU_FTR_SECTION - li r4,0 + lwz r4,SL_DBAT4(r1) mtspr SPRN_DBAT4U,r4 + lwz r4,SL_DBAT4+4(r1) mtspr SPRN_DBAT4L,r4 + lwz r4,SL_DBAT5(r1) mtspr SPRN_DBAT5U,r4 + lwz r4,SL_DBAT5+4(r1) mtspr SPRN_DBAT5L,r4 + lwz r4,SL_DBAT6(r1) mtspr SPRN_DBAT6U,r4 + lwz r4,SL_DBAT6+4(r1) mtspr SPRN_DBAT6L,r4 + lwz r4,SL_DBAT7(r1) mtspr SPRN_DBAT7U,r4 + lwz r4,SL_DBAT7+4(r1) mtspr SPRN_DBAT7L,r4 + lwz r4,SL_IBAT4(r1) mtspr SPRN_IBAT4U,r4 + lwz r4,SL_IBAT4+4(r1) mtspr SPRN_IBAT4L,r4 + lwz r4,SL_IBAT5(r1) mtspr SPRN_IBAT5U,r4 + lwz r4,SL_IBAT5+4(r1) mtspr SPRN_IBAT5L,r4 + lwz r4,SL_IBAT6(r1) mtspr SPRN_IBAT6U,r4 + lwz r4,SL_IBAT6+4(r1) mtspr SPRN_IBAT6L,r4 + lwz r4,SL_IBAT7(r1) mtspr SPRN_IBAT7U,r4 + lwz r4,SL_IBAT7+4(r1) mtspr SPRN_IBAT7L,r4 END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)

From: Dan Carpenter dan.carpenter@oracle.com

commit 0bdf8a8245fdea6f075a5fede833a5fcf1b3466c upstream.

ECRYPTFS_SIZE_AND_MARKER_BYTES is type size_t, so if "rc" is negative that gets type promoted to a high positive value and treated as success.

Fixes: 778aeb42a708 ("eCryptfs: Cleanup and optimize ecryptfs_lookup_interpose()") Signed-off-by: Dan Carpenter dan.carpenter@oracle.com [tyhicks: Use "if/else if" rather than "if/if"] Cc: stable@vger.kernel.org Signed-off-by: Tyler Hicks tyhicks@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/ecryptfs/crypto.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)

--- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -1034,8 +1034,10 @@ int ecryptfs_read_and_validate_header_re

rc = ecryptfs_read_lower(file_size, 0, ECRYPTFS_SIZE_AND_MARKER_BYTES, inode); - if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES) - return rc >= 0 ? -EINVAL : rc; + if (rc < 0) + return rc; + else if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES) + return -EINVAL; rc = ecryptfs_validate_marker(marker); if (!rc) ecryptfs_i_size_init(file_size, inode); @@ -1397,8 +1399,10 @@ int ecryptfs_read_and_validate_xattr_reg ecryptfs_inode_to_lower(inode), ECRYPTFS_XATTR_NAME, file_size, ECRYPTFS_SIZE_AND_MARKER_BYTES); - if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES) - return rc >= 0 ? -EINVAL : rc; + if (rc < 0) + return rc; + else if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES) + return -EINVAL; rc = ecryptfs_validate_marker(marker); if (!rc) ecryptfs_i_size_init(file_size, inode);

From: Szymon Janc szymon.janc@codecoup.pl

commit 1d87b88ba26eabd4745e158ecfd87c93a9b51dc2 upstream.

Microsoft Surface Precision Mouse provides bogus identity address when pairing. It connects with Static Random address but provides Public Address in SMP Identity Address Information PDU. Address has same value but type is different. Workaround this by dropping IRK if ID address discrepancy is detected.

HCI Event: LE Meta Event (0x3e) plen 19

LE Connection Complete (0x01) Status: Success (0x00) Handle: 75 Role: Master (0x00) Peer address type: Random (0x01) Peer address: E0:52:33:93:3B:21 (Static) Connection interval: 50.00 msec (0x0028) Connection latency: 0 (0x0000) Supervision timeout: 420 msec (0x002a) Master clock accuracy: 0x00

....

ACL Data RX: Handle 75 flags 0x02 dlen 12

SMP: Identity Address Information (0x09) len 7 Address type: Public (0x00) Address: E0:52:33:93:3B:21

Signed-off-by: Szymon Janc szymon.janc@codecoup.pl Tested-by: Maarten Fonville maarten.fonville@gmail.com Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=199461 Cc: stable@vger.kernel.org Signed-off-by: Marcel Holtmann marcel@holtmann.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/bluetooth/smp.c | 13 +++++++++++++ 1 file changed, 13 insertions(+)

--- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -2514,6 +2514,19 @@ static int smp_cmd_ident_addr_info(struc goto distribute; }

+ /* Drop IRK if peer is using identity address during pairing but is + * providing different address as identity information. + * + * Microsoft Surface Precision Mouse is known to have this bug. + */ + if (hci_is_identity_address(&hcon->dst, hcon->dst_type) && + (bacmp(&info->bdaddr, &hcon->dst) || + info->addr_type != hcon->dst_type)) { + bt_dev_err(hcon->hdev, + "ignoring IRK with invalid identity address"); + goto distribute; + } + bacpy(&smp->id_addr, &info->bdaddr); smp->id_addr_type = info->addr_type;

From: Junxiao Bi junxiao.bi@oracle.com

commit bd293d071ffe65e645b4d8104f9d8fe15ea13862 upstream.

When thin-volume is built on loop device, if available memory is low, the following deadlock can be triggered:

One process P1 allocates memory with GFP_FS flag, direct alloc fails, memory reclaim invokes memory shrinker in dm_bufio, dm_bufio_shrink_scan() runs, mutex dm_bufio_client->lock is acquired, then P1 waits for dm_buffer IO to complete in __try_evict_buffer().

But this IO may never complete if issued to an underlying loop device that forwards it using direct-IO, which allocates memory using GFP_KERNEL (see: do_blockdev_direct_IO()). If allocation fails, memory reclaim will invoke memory shrinker in dm_bufio, dm_bufio_shrink_scan() will be invoked, and since the mutex is already held by P1 the loop thread will hang, and IO will never complete. Resulting in ABBA deadlock.

Cc: stable@vger.kernel.org Signed-off-by: Junxiao Bi junxiao.bi@oracle.com Signed-off-by: Mike Snitzer snitzer@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/md/dm-bufio.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

--- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1585,9 +1585,7 @@ dm_bufio_shrink_scan(struct shrinker *sh unsigned long freed;

c = container_of(shrink, struct dm_bufio_client, shrinker); - if (sc->gfp_mask & __GFP_FS) - dm_bufio_lock(c); - else if (!dm_bufio_trylock(c)) + if (!dm_bufio_trylock(c)) return SHRINK_STOP;

freed = __scan(c, sc->nr_to_scan, sc->gfp_mask);

[ Upstream commit 7f1e541fc8d57a143dd5df1d0a1276046e08c083 ]

Sometimes we know that it's safe to do potentially out-of-bounds access because we know it won't cross a page boundary. Still, KASAN will report this as a bug.

Add read_word_at_a_time() function which is supposed to be used in such cases. In read_word_at_a_time() KASAN performs relaxed check - only the first byte of access is validated.

Signed-off-by: Andrey Ryabinin aryabinin@virtuozzo.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/compiler.h | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/include/linux/compiler.h b/include/linux/compiler.h index ced454c03819..3050de0dac96 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -302,6 +302,7 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s * with an explicit memory barrier or atomic instruction that provides the * required ordering. */ +#include <linux/kasan-checks.h>

#define __READ_ONCE(x, check) \ ({ \ @@ -320,6 +321,13 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s */ #define READ_ONCE_NOCHECK(x) __READ_ONCE(x, 0)

+static __no_kasan_or_inline +unsigned long read_word_at_a_time(const void *addr) +{ + kasan_check_read(addr, 1); + return *(unsigned long *)addr; +} + #define WRITE_ONCE(x, val) \ ({ \ union { typeof(x) __val; char __c[1]; } __u = \

From: Theodore Ts'o tytso@mit.edu

commit 4e19d6b65fb4fc42e352ce9883649e049da14743 upstream.

The largedir feature was intended to allow ext4 directories to have unmapped directory blocks (e.g., directory holes). And so the released e2fsprogs no longer enforces this for largedir file systems; however, the corresponding change to the kernel-side code was not made.

This commit fixes this oversight.

Signed-off-by: Theodore Ts'o tytso@mit.edu Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/ext4/dir.c | 19 +++++++++---------- fs/ext4/namei.c | 45 +++++++++++++++++++++++++++++++++++++-------- 2 files changed, 46 insertions(+), 18 deletions(-)

--- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -106,7 +106,6 @@ static int ext4_readdir(struct file *fil struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct buffer_head *bh = NULL; - int dir_has_error = 0; struct fscrypt_str fstr = FSTR_INIT(NULL, 0);

if (ext4_encrypted_inode(inode)) { @@ -142,8 +141,6 @@ static int ext4_readdir(struct file *fil return err; }

- offset = ctx->pos & (sb->s_blocksize - 1); - while (ctx->pos < inode->i_size) { struct ext4_map_blocks map;

@@ -152,9 +149,18 @@ static int ext4_readdir(struct file *fil goto errout; } cond_resched(); + offset = ctx->pos & (sb->s_blocksize - 1); map.m_lblk = ctx->pos >> EXT4_BLOCK_SIZE_BITS(sb); map.m_len = 1; err = ext4_map_blocks(NULL, inode, &map, 0); + if (err == 0) { + /* m_len should never be zero but let's avoid + * an infinite loop if it somehow is */ + if (map.m_len == 0) + map.m_len = 1; + ctx->pos += map.m_len * sb->s_blocksize; + continue; + } if (err > 0) { pgoff_t index = map.m_pblk >> (PAGE_SHIFT - inode->i_blkbits); @@ -173,13 +179,6 @@ static int ext4_readdir(struct file *fil }

if (!bh) { - if (!dir_has_error) { - EXT4_ERROR_FILE(file, 0, - "directory contains a " - "hole at offset %llu", - (unsigned long long) ctx->pos); - dir_has_error = 1; - } /* corrupt size? Maybe no more blocks to read */ if (ctx->pos > inode->i_blocks << 9) break; --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -79,8 +79,18 @@ static struct buffer_head *ext4_append(h static int ext4_dx_csum_verify(struct inode *inode, struct ext4_dir_entry *dirent);

+/* + * Hints to ext4_read_dirblock regarding whether we expect a directory + * block being read to be an index block, or a block containing + * directory entries (and if the latter, whether it was found via a + * logical block in an htree index block). This is used to control + * what sort of sanity checkinig ext4_read_dirblock() will do on the + * directory block read from the storage device. EITHER will means + * the caller doesn't know what kind of directory block will be read, + * so no specific verification will be done. + */ typedef enum { - EITHER, INDEX, DIRENT + EITHER, INDEX, DIRENT, DIRENT_HTREE } dirblock_type_t;

#define ext4_read_dirblock(inode, block, type) \ @@ -106,11 +116,14 @@ static struct buffer_head *__ext4_read_d

return bh; } - if (!bh) { + if (!bh && (type == INDEX || type == DIRENT_HTREE)) { ext4_error_inode(inode, func, line, block, - "Directory hole found"); + "Directory hole found for htree %s block", + (type == INDEX) ? "index" : "leaf"); return ERR_PTR(-EFSCORRUPTED); } + if (!bh) + return NULL; dirent = (struct ext4_dir_entry *) bh->b_data; /* Determine whether or not we have an index block */ if (is_dx(inode)) { @@ -960,7 +973,7 @@ static int htree_dirblock_to_tree(struct

dxtrace(printk(KERN_INFO "In htree dirblock_to_tree: block %lu\n", (unsigned long)block)); - bh = ext4_read_dirblock(dir, block, DIRENT); + bh = ext4_read_dirblock(dir, block, DIRENT_HTREE); if (IS_ERR(bh)) return PTR_ERR(bh);

@@ -1537,7 +1550,7 @@ static struct buffer_head * ext4_dx_find return (struct buffer_head *) frame; do { block = dx_get_block(frame->at); - bh = ext4_read_dirblock(dir, block, DIRENT); + bh = ext4_read_dirblock(dir, block, DIRENT_HTREE); if (IS_ERR(bh)) goto errout;

@@ -2142,6 +2155,11 @@ static int ext4_add_entry(handle_t *hand blocks = dir->i_size >> sb->s_blocksize_bits; for (block = 0; block < blocks; block++) { bh = ext4_read_dirblock(dir, block, DIRENT); + if (bh == NULL) { + bh = ext4_bread(handle, dir, block, + EXT4_GET_BLOCKS_CREATE); + goto add_to_new_block; + } if (IS_ERR(bh)) { retval = PTR_ERR(bh); bh = NULL; @@ -2162,6 +2180,7 @@ static int ext4_add_entry(handle_t *hand brelse(bh); } bh = ext4_append(handle, dir, &block); +add_to_new_block: if (IS_ERR(bh)) { retval = PTR_ERR(bh); bh = NULL; @@ -2203,7 +2222,7 @@ static int ext4_dx_add_entry(handle_t *h return PTR_ERR(frame); entries = frame->entries; at = frame->at; - bh = ext4_read_dirblock(dir, dx_get_block(frame->at), DIRENT); + bh = ext4_read_dirblock(dir, dx_get_block(frame->at), DIRENT_HTREE); if (IS_ERR(bh)) { err = PTR_ERR(bh); bh = NULL; @@ -2719,7 +2738,10 @@ bool ext4_empty_dir(struct inode *inode) EXT4_ERROR_INODE(inode, "invalid size"); return true; } - bh = ext4_read_dirblock(inode, 0, EITHER); + /* The first directory block must not be a hole, + * so treat it as DIRENT_HTREE + */ + bh = ext4_read_dirblock(inode, 0, DIRENT_HTREE); if (IS_ERR(bh)) return true;

@@ -2741,6 +2763,10 @@ bool ext4_empty_dir(struct inode *inode) brelse(bh); lblock = offset >> EXT4_BLOCK_SIZE_BITS(sb); bh = ext4_read_dirblock(inode, lblock, EITHER); + if (bh == NULL) { + offset += sb->s_blocksize; + continue; + } if (IS_ERR(bh)) return true; de = (struct ext4_dir_entry_2 *) bh->b_data; @@ -3302,7 +3328,10 @@ static struct buffer_head *ext4_get_firs struct buffer_head *bh;

if (!ext4_has_inline_data(inode)) { - bh = ext4_read_dirblock(inode, 0, EITHER); + /* The first directory block must not be a hole, so + * treat it as DIRENT_HTREE + */ + bh = ext4_read_dirblock(inode, 0, DIRENT_HTREE); if (IS_ERR(bh)) { *retval = PTR_ERR(bh); return NULL;

From: "Guilherme G. Piccoli" gpiccoli@canonical.com

[ Upstream commit 3c91f25c2f72ba6001775a5932857c1d2131c531 ]

Currently bnx2x ptp worker tries to read a register with timestamp information in case of TX packet timestamping and in case it fails, the routine reschedules itself indefinitely. This was reported as a kworker always at 100% of CPU usage, which was narrowed down to be bnx2x ptp_task.

By following the ioctl handler, we could narrow down the problem to an NTP tool (chrony) requesting HW timestamping from bnx2x NIC with RX filter zeroed; this isn't reproducible for example with ptp4l (from linuxptp) since this tool requests a supported RX filter. It seems NIC FW timestamp mechanism cannot work well with RX_FILTER_NONE - driver's PTP filter init routine skips a register write to the adapter if there's not a supported filter request.

This patch addresses the problem of bnx2x ptp thread's everlasting reschedule by retrying the register read 10 times; between the read attempts the thread sleeps for an increasing amount of time starting in 1ms to give FW some time to perform the timestamping. If it still fails after all retries, we bail out in order to prevent an unbound resource consumption from bnx2x.

The patch also adds an ethtool statistic for accounting the skipped TX timestamp packets and it reduces the priority of timestamping error messages to prevent log flooding. The code was tested using both linuxptp and chrony.

Reported-and-tested-by: Przemyslaw Hausman przemyslaw.hausman@canonical.com Suggested-by: Sudarsana Reddy Kalluru skalluru@marvell.com Signed-off-by: Guilherme G. Piccoli gpiccoli@canonical.com Acked-by: Sudarsana Reddy Kalluru skalluru@marvell.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 5 ++- drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c | 4 +- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 33 ++++++++++++++------ drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h | 3 + 4 files changed, 34 insertions(+), 11 deletions(-)

--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -3863,9 +3863,12 @@ netdev_tx_t bnx2x_start_xmit(struct sk_b

if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { if (!(bp->flags & TX_TIMESTAMPING_EN)) { + bp->eth_stats.ptp_skip_tx_ts++; BNX2X_ERR("Tx timestamping was not enabled, this packet will not be timestamped\n"); } else if (bp->ptp_tx_skb) { - BNX2X_ERR("The device supports only a single outstanding packet to timestamp, this packet will not be timestamped\n"); + bp->eth_stats.ptp_skip_tx_ts++; + dev_err_once(&bp->dev->dev, + "Device supports only a single outstanding packet to timestamp, this packet won't be timestamped\n"); } else { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; /* schedule check for Tx timestamp */ --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -182,7 +182,9 @@ static const struct { { STATS_OFFSET32(driver_filtered_tx_pkt), 4, false, "driver_filtered_tx_pkt" }, { STATS_OFFSET32(eee_tx_lpi), - 4, true, "Tx LPI entry count"} + 4, true, "Tx LPI entry count"}, + { STATS_OFFSET32(ptp_skip_tx_ts), + 4, false, "ptp_skipped_tx_tstamp" }, };

#define BNX2X_NUM_STATS ARRAY_SIZE(bnx2x_stats_arr) --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -15261,11 +15261,24 @@ static void bnx2x_ptp_task(struct work_s u32 val_seq; u64 timestamp, ns; struct skb_shared_hwtstamps shhwtstamps; + bool bail = true; + int i;

- /* Read Tx timestamp registers */ - val_seq = REG_RD(bp, port ? NIG_REG_P1_TLLH_PTP_BUF_SEQID : - NIG_REG_P0_TLLH_PTP_BUF_SEQID); - if (val_seq & 0x10000) { + /* FW may take a while to complete timestamping; try a bit and if it's + * still not complete, may indicate an error state - bail out then. + */ + for (i = 0; i < 10; i++) { + /* Read Tx timestamp registers */ + val_seq = REG_RD(bp, port ? NIG_REG_P1_TLLH_PTP_BUF_SEQID : + NIG_REG_P0_TLLH_PTP_BUF_SEQID); + if (val_seq & 0x10000) { + bail = false; + break; + } + msleep(1 << i); + } + + if (!bail) { /* There is a valid timestamp value */ timestamp = REG_RD(bp, port ? NIG_REG_P1_TLLH_PTP_BUF_TS_MSB : NIG_REG_P0_TLLH_PTP_BUF_TS_MSB); @@ -15280,16 +15293,18 @@ static void bnx2x_ptp_task(struct work_s memset(&shhwtstamps, 0, sizeof(shhwtstamps)); shhwtstamps.hwtstamp = ns_to_ktime(ns); skb_tstamp_tx(bp->ptp_tx_skb, &shhwtstamps); - dev_kfree_skb_any(bp->ptp_tx_skb); - bp->ptp_tx_skb = NULL;

DP(BNX2X_MSG_PTP, "Tx timestamp, timestamp cycles = %llu, ns = %llu\n", timestamp, ns); } else { - DP(BNX2X_MSG_PTP, "There is no valid Tx timestamp yet\n"); - /* Reschedule to keep checking for a valid timestamp value */ - schedule_work(&bp->ptp_task); + DP(BNX2X_MSG_PTP, + "Tx timestamp is not recorded (register read=%u)\n", + val_seq); + bp->eth_stats.ptp_skip_tx_ts++; } + + dev_kfree_skb_any(bp->ptp_tx_skb); + bp->ptp_tx_skb = NULL; }

void bnx2x_set_rx_ts(struct bnx2x *bp, struct sk_buff *skb) --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h @@ -207,6 +207,9 @@ struct bnx2x_eth_stats { u32 driver_filtered_tx_pkt; /* src: Clear-on-Read register; Will not survive PMF Migration */ u32 eee_tx_lpi; + + /* PTP */ + u32 ptp_skip_tx_ts; };

struct bnx2x_eth_q_stats {

From: Eric Dumazet edumazet@google.com

[ Upstream commit e5b1c6c6277d5a283290a8c033c72544746f9b5b ]

im->tomb and/or im->sources might not be NULL, but we currently overwrite their values blindly.

Using swap() will make sure the following call to kfree_pmc(pmc) will properly free the psf structures.

Tested with the C repro provided by syzbot, which basically does :

socket(PF_INET, SOCK_DGRAM, IPPROTO_IP) = 3 setsockopt(3, SOL_IP, IP_ADD_MEMBERSHIP, "\340\0\0\2\177\0\0\1\0\0\0\0", 12) = 0 ioctl(3, SIOCSIFFLAGS, {ifr_name="lo", ifr_flags=0}) = 0 setsockopt(3, SOL_IP, IP_MSFILTER, "\340\0\0\2\177\0\0\1\1\0\0\0\1\0\0\0\377\377\377\377", 20) = 0 ioctl(3, SIOCSIFFLAGS, {ifr_name="lo", ifr_flags=IFF_UP}) = 0 exit_group(0) = ?

BUG: memory leak unreferenced object 0xffff88811450f140 (size 64): comm "softirq", pid 0, jiffies 4294942448 (age 32.070s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 ff ff ff ff 00 00 00 00 ................ 00 00 00 00 00 00 00 00 01 00 00 00 00 00 00 00 ................ backtrace: [<00000000c7bad083>] kmemleak_alloc_recursive include/linux/kmemleak.h:43 [inline] [<00000000c7bad083>] slab_post_alloc_hook mm/slab.h:439 [inline] [<00000000c7bad083>] slab_alloc mm/slab.c:3326 [inline] [<00000000c7bad083>] kmem_cache_alloc_trace+0x13d/0x280 mm/slab.c:3553 [<000000009acc4151>] kmalloc include/linux/slab.h:547 [inline] [<000000009acc4151>] kzalloc include/linux/slab.h:742 [inline] [<000000009acc4151>] ip_mc_add1_src net/ipv4/igmp.c:1976 [inline] [<000000009acc4151>] ip_mc_add_src+0x36b/0x400 net/ipv4/igmp.c:2100 [<000000004ac14566>] ip_mc_msfilter+0x22d/0x310 net/ipv4/igmp.c:2484 [<0000000052d8f995>] do_ip_setsockopt.isra.0+0x1795/0x1930 net/ipv4/ip_sockglue.c:959 [<000000004ee1e21f>] ip_setsockopt+0x3b/0xb0 net/ipv4/ip_sockglue.c:1248 [<0000000066cdfe74>] udp_setsockopt+0x4e/0x90 net/ipv4/udp.c:2618 [<000000009383a786>] sock_common_setsockopt+0x38/0x50 net/core/sock.c:3126 [<00000000d8ac0c94>] __sys_setsockopt+0x98/0x120 net/socket.c:2072 [<000000001b1e9666>] __do_sys_setsockopt net/socket.c:2083 [inline] [<000000001b1e9666>] __se_sys_setsockopt net/socket.c:2080 [inline] [<000000001b1e9666>] __x64_sys_setsockopt+0x26/0x30 net/socket.c:2080 [<00000000420d395e>] do_syscall_64+0x76/0x1a0 arch/x86/entry/common.c:301 [<000000007fd83a4b>] entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 24803f38a5c0 ("igmp: do not remove igmp souce list info when set link down") Signed-off-by: Eric Dumazet edumazet@google.com Cc: Hangbin Liu liuhangbin@gmail.com Reported-by: syzbot+6ca1abd0db68b5173a4f@syzkaller.appspotmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/igmp.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-)

--- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1212,12 +1212,8 @@ static void igmpv3_del_delrec(struct in_ im->interface = pmc->interface; im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; if (im->sfmode == MCAST_INCLUDE) { - im->tomb = pmc->tomb; - pmc->tomb = NULL; - - im->sources = pmc->sources; - pmc->sources = NULL; - + swap(im->tomb, pmc->tomb); + swap(im->sources, pmc->sources); for (psf = im->sources; psf; psf = psf->sf_next) psf->sf_crcount = im->crcount; }

From: Justin Chen justinpopo6@gmail.com

[ Upstream commit 35cbef9863640f06107144687bd13151bc2e8ce3 ]

Currently we silently ignore filters if we cannot meet the filter requirements. This will lead to the MAC dropping packets that are expected to pass. A better solution would be to set the NIC to promisc mode when the required filters cannot be met.

Also correct the number of MDF filters supported. It should be 17, not 16.

Signed-off-by: Justin Chen justinpopo6@gmail.com Reviewed-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 57 +++++++++++-------------- 1 file changed, 26 insertions(+), 31 deletions(-)

--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3002,39 +3002,42 @@ static void bcmgenet_timeout(struct net_ netif_tx_wake_all_queues(dev); }

-#define MAX_MC_COUNT 16 +#define MAX_MDF_FILTER 17

static inline void bcmgenet_set_mdf_addr(struct bcmgenet_priv *priv, unsigned char *addr, - int *i, - int *mc) + int *i) { - u32 reg; - bcmgenet_umac_writel(priv, addr[0] << 8 | addr[1], UMAC_MDF_ADDR + (*i * 4)); bcmgenet_umac_writel(priv, addr[2] << 24 | addr[3] << 16 | addr[4] << 8 | addr[5], UMAC_MDF_ADDR + ((*i + 1) * 4)); - reg = bcmgenet_umac_readl(priv, UMAC_MDF_CTRL); - reg |= (1 << (MAX_MC_COUNT - *mc)); - bcmgenet_umac_writel(priv, reg, UMAC_MDF_CTRL); *i += 2; - (*mc)++; }

static void bcmgenet_set_rx_mode(struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); struct netdev_hw_addr *ha; - int i, mc; + int i, nfilter; u32 reg;

netif_dbg(priv, hw, dev, "%s: %08X\n", __func__, dev->flags);

- /* Promiscuous mode */ + /* Number of filters needed */ + nfilter = netdev_uc_count(dev) + netdev_mc_count(dev) + 2; + + /* + * Turn on promicuous mode for three scenarios + * 1. IFF_PROMISC flag is set + * 2. IFF_ALLMULTI flag is set + * 3. The number of filters needed exceeds the number filters + * supported by the hardware. + */ reg = bcmgenet_umac_readl(priv, UMAC_CMD); - if (dev->flags & IFF_PROMISC) { + if ((dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) || + (nfilter > MAX_MDF_FILTER)) { reg |= CMD_PROMISC; bcmgenet_umac_writel(priv, reg, UMAC_CMD); bcmgenet_umac_writel(priv, 0, UMAC_MDF_CTRL); @@ -3044,32 +3047,24 @@ static void bcmgenet_set_rx_mode(struct bcmgenet_umac_writel(priv, reg, UMAC_CMD); }

- /* UniMac doesn't support ALLMULTI */ - if (dev->flags & IFF_ALLMULTI) { - netdev_warn(dev, "ALLMULTI is not supported\n"); - return; - } - /* update MDF filter */ i = 0; - mc = 0; /* Broadcast */ - bcmgenet_set_mdf_addr(priv, dev->broadcast, &i, &mc); + bcmgenet_set_mdf_addr(priv, dev->broadcast, &i); /* my own address.*/ - bcmgenet_set_mdf_addr(priv, dev->dev_addr, &i, &mc); - /* Unicast list*/ - if (netdev_uc_count(dev) > (MAX_MC_COUNT - mc)) - return; + bcmgenet_set_mdf_addr(priv, dev->dev_addr, &i);

- if (!netdev_uc_empty(dev)) - netdev_for_each_uc_addr(ha, dev) - bcmgenet_set_mdf_addr(priv, ha->addr, &i, &mc); - /* Multicast */ - if (netdev_mc_empty(dev) || netdev_mc_count(dev) >= (MAX_MC_COUNT - mc)) - return; + /* Unicast */ + netdev_for_each_uc_addr(ha, dev) + bcmgenet_set_mdf_addr(priv, ha->addr, &i);

+ /* Multicast */ netdev_for_each_mc_addr(ha, dev) - bcmgenet_set_mdf_addr(priv, ha->addr, &i, &mc); + bcmgenet_set_mdf_addr(priv, ha->addr, &i); + + /* Enable filters */ + reg = GENMASK(MAX_MDF_FILTER - 1, MAX_MDF_FILTER - nfilter); + bcmgenet_umac_writel(priv, reg, UMAC_MDF_CTRL); }

/* Set the hardware MAC address. */

From: Lorenzo Bianconi lorenzo.bianconi@redhat.com

[ Upstream commit 071c37983d99da07797294ea78e9da1a6e287144 ]

Neigh timer can be scheduled multiple times from userspace adding multiple neigh entries and forcing the neigh timer scheduling passing NTF_USE in the netlink requests. This will result in a refcount leak and in the following dump stack:

[ 32.465295] NEIGH: BUG, double timer add, state is 8 [ 32.465308] CPU: 0 PID: 416 Comm: double_timer_ad Not tainted 5.2.0+ #65 [ 32.465311] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.12.0-2.fc30 04/01/2014 [ 32.465313] Call Trace: [ 32.465318] dump_stack+0x7c/0xc0 [ 32.465323] __neigh_event_send+0x20c/0x880 [ 32.465326] ? ___neigh_create+0x846/0xfb0 [ 32.465329] ? neigh_lookup+0x2a9/0x410 [ 32.465332] ? neightbl_fill_info.constprop.0+0x800/0x800 [ 32.465334] neigh_add+0x4f8/0x5e0 [ 32.465337] ? neigh_xmit+0x620/0x620 [ 32.465341] ? find_held_lock+0x85/0xa0 [ 32.465345] rtnetlink_rcv_msg+0x204/0x570 [ 32.465348] ? rtnl_dellink+0x450/0x450 [ 32.465351] ? mark_held_locks+0x90/0x90 [ 32.465354] ? match_held_lock+0x1b/0x230 [ 32.465357] netlink_rcv_skb+0xc4/0x1d0 [ 32.465360] ? rtnl_dellink+0x450/0x450 [ 32.465363] ? netlink_ack+0x420/0x420 [ 32.465366] ? netlink_deliver_tap+0x115/0x560 [ 32.465369] ? __alloc_skb+0xc9/0x2f0 [ 32.465372] netlink_unicast+0x270/0x330 [ 32.465375] ? netlink_attachskb+0x2f0/0x2f0 [ 32.465378] netlink_sendmsg+0x34f/0x5a0 [ 32.465381] ? netlink_unicast+0x330/0x330 [ 32.465385] ? move_addr_to_kernel.part.0+0x20/0x20 [ 32.465388] ? netlink_unicast+0x330/0x330 [ 32.465391] sock_sendmsg+0x91/0xa0 [ 32.465394] ___sys_sendmsg+0x407/0x480 [ 32.465397] ? copy_msghdr_from_user+0x200/0x200 [ 32.465401] ? _raw_spin_unlock_irqrestore+0x37/0x40 [ 32.465404] ? lockdep_hardirqs_on+0x17d/0x250 [ 32.465407] ? __wake_up_common_lock+0xcb/0x110 [ 32.465410] ? __wake_up_common+0x230/0x230 [ 32.465413] ? netlink_bind+0x3e1/0x490 [ 32.465416] ? netlink_setsockopt+0x540/0x540 [ 32.465420] ? __fget_light+0x9c/0xf0 [ 32.465423] ? sockfd_lookup_light+0x8c/0xb0 [ 32.465426] __sys_sendmsg+0xa5/0x110 [ 32.465429] ? __ia32_sys_shutdown+0x30/0x30 [ 32.465432] ? __fd_install+0xe1/0x2c0 [ 32.465435] ? lockdep_hardirqs_off+0xb5/0x100 [ 32.465438] ? mark_held_locks+0x24/0x90 [ 32.465441] ? do_syscall_64+0xf/0x270 [ 32.465444] do_syscall_64+0x63/0x270 [ 32.465448] entry_SYSCALL_64_after_hwframe+0x49/0xbe

Fix the issue unscheduling neigh_timer if selected entry is in 'IN_TIMER' receiving a netlink request with NTF_USE flag set

Reported-by: Marek Majkowski marek@cloudflare.com Fixes: 0c5c2d308906 ("neigh: Allow for user space users of the neighbour table") Signed-off-by: Lorenzo Bianconi lorenzo.bianconi@redhat.com Reviewed-by: David Ahern dsahern@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/neighbour.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -982,6 +982,7 @@ int __neigh_event_send(struct neighbour

atomic_set(&neigh->probes, NEIGH_VAR(neigh->parms, UCAST_PROBES)); + neigh_del_timer(neigh); neigh->nud_state = NUD_INCOMPLETE; neigh->updated = now; next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME), @@ -998,6 +999,7 @@ int __neigh_event_send(struct neighbour } } else if (neigh->nud_state & NUD_STALE) { neigh_dbg(2, "neigh %p is delayed\n", neigh); + neigh_del_timer(neigh); neigh->nud_state = NUD_DELAY; neigh->updated = jiffies; neigh_add_timer(neigh, jiffies +

From: Yang Wei albin_yang@163.com

[ Upstream commit dd006fc434e107ef90f7de0db9907cbc1c521645 ]

The frags_q is not properly initialized, it may result in illegal memory access when conn_info is NULL. The "goto free_exit" should be replaced by "goto exit".

Signed-off-by: Yang Wei albin_yang@163.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/nfc/nci/data.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -119,7 +119,7 @@ static int nci_queue_tx_data_frags(struc conn_info = nci_get_conn_info_by_conn_id(ndev, conn_id); if (!conn_info) { rc = -EPROTO; - goto free_exit; + goto exit; }

__skb_queue_head_init(&frags_q);

From: Takashi Iwai tiwai@suse.de

[ Upstream commit a261e3797506bd561700be643fe1a85bf81e9661 ]

The onboard sky2 NIC on ASUS P6T WS PRO doesn't work after PM resume due to the infamous IRQ problem. Disabling MSI works around it, so let's add it to the blacklist.

Unfortunately the BIOS on the machine doesn't fill the standard DMI_SYS_* entry, so we pick up DMI_BOARD_* entries instead.

BugLink: https://bugzilla.suse.com/show_bug.cgi?id=1142496 Reported-and-tested-by: Marcus Seyfarth m.seyfarth@gmail.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/marvell/sky2.c | 7 +++++++ 1 file changed, 7 insertions(+)

--- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -4939,6 +4939,13 @@ static const struct dmi_system_id msi_bl DMI_MATCH(DMI_PRODUCT_NAME, "P-79"), }, }, + { + .ident = "ASUS P6T", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), + DMI_MATCH(DMI_BOARD_NAME, "P6T"), + }, + }, {} };

From: Andreas Steinmetz ast@domdv.de

[ Upstream commit 095c02da80a41cf6d311c504d8955d6d1c2add10 ]

Fix use-after-free of skb when rx_handler returns RX_HANDLER_PASS.

Signed-off-by: Andreas Steinmetz ast@domdv.de Acked-by: Willem de Bruijn willemb@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/macsec.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)

--- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1105,10 +1105,9 @@ static rx_handler_result_t macsec_handle }

skb = skb_unshare(skb, GFP_ATOMIC); - if (!skb) { - *pskb = NULL; + *pskb = skb; + if (!skb) return RX_HANDLER_CONSUMED; - }

pulled_sci = pskb_may_pull(skb, macsec_extra_len(true)); if (!pulled_sci) {

From: Cong Wang xiyou.wangcong@gmail.com

[ Upstream commit c8c8218ec5af5d2598381883acbefbf604e56b5e ]

When the skb is associated with a new sock, just assigning it to skb->sk is not sufficient, we have to set its destructor to free the sock properly too.

Reported-by: syzbot+d6636a36d3c34bd88938@syzkaller.appspotmail.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 --- net/netrom/af_netrom.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -870,7 +870,7 @@ int nr_rx_frame(struct sk_buff *skb, str unsigned short frametype, flags, window, timeout; int ret;

- skb->sk = NULL; /* Initially we don't know who it's for */ + skb_orphan(skb);

/* * skb->data points to the netrom frame start @@ -969,6 +969,7 @@ int nr_rx_frame(struct sk_buff *skb, str window = skb->data[20];

skb->sk = make; + skb->destructor = sock_efree; make->sk_state = TCP_ESTABLISHED;

/* Fill in his circuit details */

From: Cong Wang xiyou.wangcong@gmail.com

[ Upstream commit 9d1bc24b52fb8c5d859f9a47084bf1179470e04c ]

bond_xmit_roundrobin() checks for IGMP packets but it parses the IP header even before checking skb->protocol.

We should validate the IP header with pskb_may_pull() before using iph->protocol.

Reported-and-tested-by: syzbot+e5be16aa39ad6e755391@syzkaller.appspotmail.com Fixes: a2fd940f4cff ("bonding: fix broken multicast with round-robin mode") Cc: Jay Vosburgh j.vosburgh@gmail.com Cc: Veaceslav Falico vfalico@gmail.com Cc: Andy Gospodarek andy@greyhouse.net 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 --- drivers/net/bonding/bond_main.c | 37 +++++++++++++++++++++++-------------- 1 file changed, 23 insertions(+), 14 deletions(-)

--- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3788,8 +3788,8 @@ static u32 bond_rr_gen_slave_id(struct b static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - struct iphdr *iph = ip_hdr(skb); struct slave *slave; + int slave_cnt; u32 slave_id;

/* Start with the curr_active_slave that joined the bond as the @@ -3798,23 +3798,32 @@ static int bond_xmit_roundrobin(struct s * send the join/membership reports. The curr_active_slave found * will send all of this type of traffic. */ - if (iph->protocol == IPPROTO_IGMP && skb->protocol == htons(ETH_P_IP)) { - slave = rcu_dereference(bond->curr_active_slave); - if (slave) - bond_dev_queue_xmit(bond, skb, slave->dev); - else - bond_xmit_slave_id(bond, skb, 0); - } else { - int slave_cnt = ACCESS_ONCE(bond->slave_cnt); + if (skb->protocol == htons(ETH_P_IP)) { + int noff = skb_network_offset(skb); + struct iphdr *iph; + + if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph)))) + goto non_igmp;

- if (likely(slave_cnt)) { - slave_id = bond_rr_gen_slave_id(bond); - bond_xmit_slave_id(bond, skb, slave_id % slave_cnt); - } else { - bond_tx_drop(bond_dev, skb); + iph = ip_hdr(skb); + if (iph->protocol == IPPROTO_IGMP) { + slave = rcu_dereference(bond->curr_active_slave); + if (slave) + bond_dev_queue_xmit(bond, skb, slave->dev); + else + bond_xmit_slave_id(bond, skb, 0); + return NETDEV_TX_OK; } }

+non_igmp: + slave_cnt = ACCESS_ONCE(bond->slave_cnt); + if (likely(slave_cnt)) { + slave_id = bond_rr_gen_slave_id(bond); + bond_xmit_slave_id(bond, skb, slave_id % slave_cnt); + } else { + bond_tx_drop(bond_dev, skb); + } return NETDEV_TX_OK; }

From: Nikolay Aleksandrov nikolay@cumulusnetworks.com

[ Upstream commit e57f61858b7cf478ed6fa23ed4b3876b1c9625c4 ]

We take a pointer to grec prior to calling pskb_may_pull and use it afterwards to get nsrcs so record nsrcs before the pull when handling igmp3 and we get a pointer to nsrcs and call pskb_may_pull when handling mld2 which again could lead to reading 2 bytes out-of-bounds.

================================================================== BUG: KASAN: use-after-free in br_multicast_rcv+0x480c/0x4ad0 [bridge] Read of size 2 at addr ffff8880421302b4 by task ksoftirqd/1/16

CPU: 1 PID: 16 Comm: ksoftirqd/1 Tainted: G OE 5.2.0-rc6+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 Call Trace: dump_stack+0x71/0xab print_address_description+0x6a/0x280 ? br_multicast_rcv+0x480c/0x4ad0 [bridge] __kasan_report+0x152/0x1aa ? br_multicast_rcv+0x480c/0x4ad0 [bridge] ? br_multicast_rcv+0x480c/0x4ad0 [bridge] kasan_report+0xe/0x20 br_multicast_rcv+0x480c/0x4ad0 [bridge] ? br_multicast_disable_port+0x150/0x150 [bridge] ? ktime_get_with_offset+0xb4/0x150 ? __kasan_kmalloc.constprop.6+0xa6/0xf0 ? __netif_receive_skb+0x1b0/0x1b0 ? br_fdb_update+0x10e/0x6e0 [bridge] ? br_handle_frame_finish+0x3c6/0x11d0 [bridge] br_handle_frame_finish+0x3c6/0x11d0 [bridge] ? br_pass_frame_up+0x3a0/0x3a0 [bridge] ? virtnet_probe+0x1c80/0x1c80 [virtio_net] br_handle_frame+0x731/0xd90 [bridge] ? select_idle_sibling+0x25/0x7d0 ? br_handle_frame_finish+0x11d0/0x11d0 [bridge] __netif_receive_skb_core+0xced/0x2d70 ? virtqueue_get_buf_ctx+0x230/0x1130 [virtio_ring] ? do_xdp_generic+0x20/0x20 ? virtqueue_napi_complete+0x39/0x70 [virtio_net] ? virtnet_poll+0x94d/0xc78 [virtio_net] ? receive_buf+0x5120/0x5120 [virtio_net] ? __netif_receive_skb_one_core+0x97/0x1d0 __netif_receive_skb_one_core+0x97/0x1d0 ? __netif_receive_skb_core+0x2d70/0x2d70 ? _raw_write_trylock+0x100/0x100 ? __queue_work+0x41e/0xbe0 process_backlog+0x19c/0x650 ? _raw_read_lock_irq+0x40/0x40 net_rx_action+0x71e/0xbc0 ? __switch_to_asm+0x40/0x70 ? napi_complete_done+0x360/0x360 ? __switch_to_asm+0x34/0x70 ? __switch_to_asm+0x40/0x70 ? __schedule+0x85e/0x14d0 __do_softirq+0x1db/0x5f9 ? takeover_tasklets+0x5f0/0x5f0 run_ksoftirqd+0x26/0x40 smpboot_thread_fn+0x443/0x680 ? sort_range+0x20/0x20 ? schedule+0x94/0x210 ? __kthread_parkme+0x78/0xf0 ? sort_range+0x20/0x20 kthread+0x2ae/0x3a0 ? kthread_create_worker_on_cpu+0xc0/0xc0 ret_from_fork+0x35/0x40

The buggy address belongs to the page: page:ffffea0001084c00 refcount:0 mapcount:-128 mapping:0000000000000000 index:0x0 flags: 0xffffc000000000() raw: 00ffffc000000000 ffffea0000cfca08 ffffea0001098608 0000000000000000 raw: 0000000000000000 0000000000000003 00000000ffffff7f 0000000000000000 page dumped because: kasan: bad access detected

Memory state around the buggy address: ffff888042130180: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff888042130200: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff

ffff888042130280: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff

^ ffff888042130300: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff888042130380: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ================================================================== Disabling lock debugging due to kernel taint

Fixes: bc8c20acaea1 ("bridge: multicast: treat igmpv3 report with INCLUDE and no sources as a leave") Reported-by: Martin Weinelt martin@linuxlounge.net Signed-off-by: Nikolay Aleksandrov nikolay@cumulusnetworks.com Tested-by: Martin Weinelt martin@linuxlounge.net Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/bridge/br_multicast.c | 27 ++++++++++++++++----------- 1 file changed, 16 insertions(+), 11 deletions(-)

--- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1036,6 +1036,7 @@ static int br_ip4_multicast_igmp3_report int type; int err = 0; __be32 group; + u16 nsrcs;

ih = igmpv3_report_hdr(skb); num = ntohs(ih->ngrec); @@ -1049,8 +1050,9 @@ static int br_ip4_multicast_igmp3_report grec = (void *)(skb->data + len - sizeof(*grec)); group = grec->grec_mca; type = grec->grec_type; + nsrcs = ntohs(grec->grec_nsrcs);

- len += ntohs(grec->grec_nsrcs) * 4; + len += nsrcs * 4; if (!pskb_may_pull(skb, len)) return -EINVAL;

@@ -1070,7 +1072,7 @@ static int br_ip4_multicast_igmp3_report

if ((type == IGMPV3_CHANGE_TO_INCLUDE || type == IGMPV3_MODE_IS_INCLUDE) && - ntohs(grec->grec_nsrcs) == 0) { + nsrcs == 0) { br_ip4_multicast_leave_group(br, port, group, vid); } else { err = br_ip4_multicast_add_group(br, port, group, vid); @@ -1103,23 +1105,26 @@ static int br_ip6_multicast_mld2_report( len = skb_transport_offset(skb) + sizeof(*icmp6h);

for (i = 0; i < num; i++) { - __be16 *nsrcs, _nsrcs; + __be16 *_nsrcs, __nsrcs; + u16 nsrcs;

- nsrcs = skb_header_pointer(skb, - len + offsetof(struct mld2_grec, - grec_nsrcs), - sizeof(_nsrcs), &_nsrcs); - if (!nsrcs) + _nsrcs = skb_header_pointer(skb, + len + offsetof(struct mld2_grec, + grec_nsrcs), + sizeof(__nsrcs), &__nsrcs); + if (!_nsrcs) return -EINVAL;

+ nsrcs = ntohs(*_nsrcs); + if (!pskb_may_pull(skb, len + sizeof(*grec) + - sizeof(struct in6_addr) * ntohs(*nsrcs))) + sizeof(struct in6_addr) * nsrcs)) return -EINVAL;

grec = (struct mld2_grec *)(skb->data + len); len += sizeof(*grec) + - sizeof(struct in6_addr) * ntohs(*nsrcs); + sizeof(struct in6_addr) * nsrcs;

/* We treat these as MLDv1 reports for now. */ switch (grec->grec_type) { @@ -1137,7 +1142,7 @@ static int br_ip6_multicast_mld2_report(

if ((grec->grec_type == MLD2_CHANGE_TO_INCLUDE || grec->grec_type == MLD2_MODE_IS_INCLUDE) && - ntohs(*nsrcs) == 0) { + nsrcs == 0) { br_ip6_multicast_leave_group(br, port, &grec->grec_mca, vid); } else {

From: Nikolay Aleksandrov nikolay@cumulusnetworks.com

[ Upstream commit 2446a68ae6a8cee6d480e2f5b52f5007c7c41312 ]

Don't cache eth dest pointer before calling pskb_may_pull.

Fixes: cf0f02d04a83 ("[BRIDGE]: use llc for receiving STP packets") Signed-off-by: Nikolay Aleksandrov nikolay@cumulusnetworks.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/bridge/br_stp_bpdu.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -147,7 +147,6 @@ void br_send_tcn_bpdu(struct net_bridge_ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb, struct net_device *dev) { - const unsigned char *dest = eth_hdr(skb)->h_dest; struct net_bridge_port *p; struct net_bridge *br; const unsigned char *buf; @@ -176,7 +175,7 @@ void br_stp_rcv(const struct stp_proto * if (p->state == BR_STATE_DISABLED) goto out;

- if (!ether_addr_equal(dest, br->group_addr)) + if (!ether_addr_equal(eth_hdr(skb)->h_dest, br->group_addr)) goto out;

if (p->flags & BR_BPDU_GUARD) {

In Family 17h, the number of cores sharing a cache level is obtained from the Cache Properties CPUID leaf (0x8000001d) by passing in the cache level in ECX. In prior families, a cache level of 2 was used to determine this information.

To get the right information, irrespective of Family, iterate over the cache levels using CPUID 0x8000001d. The last level cache is the last value to return a non-zero value in EAX.

Signed-off-by: Janakarajan Natarajan Janakarajan.Natarajan@amd.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Borislav Petkov bp@suse.de Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Arnaldo Carvalho de Melo acme@kernel.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Suravee Suthikulpanit suravee.suthikulpanit@amd.com Cc: Thomas Gleixner tglx@linutronix.de Link: http://lkml.kernel.org/r/5ab569025b39cdfaeca55b571d78c0fc800bdb69.1497452002... Signed-off-by: Ingo Molnar mingo@kernel.org --- arch/x86/events/amd/uncore.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index 094973313037..10f023799f11 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -378,11 +378,24 @@ static int amd_uncore_cpu_starting(unsigned int cpu)

if (amd_uncore_llc) { unsigned int apicid = cpu_data(cpu).apicid; - unsigned int nshared; + unsigned int nshared, subleaf, prev_eax = 0;

uncore = *per_cpu_ptr(amd_uncore_llc, cpu); - cpuid_count(0x8000001d, 2, &eax, &ebx, &ecx, &edx); - nshared = ((eax >> 14) & 0xfff) + 1; + /* + * Iterate over Cache Topology Definition leaves until no + * more cache descriptions are available. + */ + for (subleaf = 0; subleaf < 5; subleaf++) { + cpuid_count(0x8000001d, subleaf, &eax, &ebx, &ecx, &edx); + + /* EAX[0:4] gives type of cache */ + if (!(eax & 0x1f)) + break; + + prev_eax = eax; + } + nshared = ((prev_eax >> 14) & 0xfff) + 1; + uncore->id = apicid - (apicid % nshared);

uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_llc);

[ Upstream commit 8fd1ab747d2b1ec7ec663ad0b41a32eaa35117a8 ]

If the server that does not implement NFSv4.1 persistent session semantics reboots while we are performing an exclusive create, then the return value of NFS4ERR_DELAY when we replay the open during the grace period causes us to lose the verifier. When the grace period expires, and we present a new verifier, the server will then correctly reply NFS4ERR_EXIST.

This commit ensures that we always present the same verifier when replaying the OPEN.

Reported-by: Tigran Mkrtchyan tigran.mkrtchyan@desy.de Signed-off-by: Trond Myklebust trond.myklebust@primarydata.com Signed-off-by: Anna Schumaker Anna.Schumaker@Netapp.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/nfs4proc.c | 41 ++++++++++++++++++++++++++--------------- 1 file changed, 26 insertions(+), 15 deletions(-)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 6d0d94fc243d..ea29c608be89 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1121,6 +1121,12 @@ struct nfs4_opendata { int cancelled; };

+struct nfs4_open_createattrs { + struct nfs4_label *label; + struct iattr *sattr; + const __u32 verf[2]; +}; + static bool nfs4_clear_cap_atomic_open_v1(struct nfs_server *server, int err, struct nfs4_exception *exception) { @@ -1190,8 +1196,7 @@ static void nfs4_init_opendata_res(struct nfs4_opendata *p)

static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, struct nfs4_state_owner *sp, fmode_t fmode, int flags, - const struct iattr *attrs, - struct nfs4_label *label, + const struct nfs4_open_createattrs *c, enum open_claim_type4 claim, gfp_t gfp_mask) { @@ -1199,6 +1204,7 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, struct inode *dir = d_inode(parent); struct nfs_server *server = NFS_SERVER(dir); struct nfs_seqid *(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t); + struct nfs4_label *label = (c != NULL) ? c->label : NULL; struct nfs4_opendata *p;

p = kzalloc(sizeof(*p), gfp_mask); @@ -1255,15 +1261,11 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, case NFS4_OPEN_CLAIM_DELEG_PREV_FH: p->o_arg.fh = NFS_FH(d_inode(dentry)); } - if (attrs != NULL && attrs->ia_valid != 0) { - __u32 verf[2]; - + if (c != NULL && c->sattr != NULL && c->sattr->ia_valid != 0) { p->o_arg.u.attrs = &p->attrs; - memcpy(&p->attrs, attrs, sizeof(p->attrs)); + memcpy(&p->attrs, c->sattr, sizeof(p->attrs));

- verf[0] = jiffies; - verf[1] = current->pid; - memcpy(p->o_arg.u.verifier.data, verf, + memcpy(p->o_arg.u.verifier.data, c->verf, sizeof(p->o_arg.u.verifier.data)); } p->c_arg.fh = &p->o_res.fh; @@ -1814,7 +1816,7 @@ static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context struct nfs4_opendata *opendata;

opendata = nfs4_opendata_alloc(ctx->dentry, state->owner, 0, 0, - NULL, NULL, claim, GFP_NOFS); + NULL, claim, GFP_NOFS); if (opendata == NULL) return ERR_PTR(-ENOMEM); opendata->state = state; @@ -2759,8 +2761,7 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, static int _nfs4_do_open(struct inode *dir, struct nfs_open_context *ctx, int flags, - struct iattr *sattr, - struct nfs4_label *label, + const struct nfs4_open_createattrs *c, int *opened) { struct nfs4_state_owner *sp; @@ -2772,6 +2773,8 @@ static int _nfs4_do_open(struct inode *dir, struct nfs4_threshold **ctx_th = &ctx->mdsthreshold; fmode_t fmode = ctx->mode & (FMODE_READ|FMODE_WRITE|FMODE_EXEC); enum open_claim_type4 claim = NFS4_OPEN_CLAIM_NULL; + struct iattr *sattr = c->sattr; + struct nfs4_label *label = c->label; struct nfs4_label *olabel = NULL; int status;

@@ -2790,8 +2793,8 @@ static int _nfs4_do_open(struct inode *dir, status = -ENOMEM; if (d_really_is_positive(dentry)) claim = NFS4_OPEN_CLAIM_FH; - opendata = nfs4_opendata_alloc(dentry, sp, fmode, flags, sattr, - label, claim, GFP_KERNEL); + opendata = nfs4_opendata_alloc(dentry, sp, fmode, flags, + c, claim, GFP_KERNEL); if (opendata == NULL) goto err_put_state_owner;

@@ -2872,10 +2875,18 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir, struct nfs_server *server = NFS_SERVER(dir); struct nfs4_exception exception = { }; struct nfs4_state *res; + struct nfs4_open_createattrs c = { + .label = label, + .sattr = sattr, + .verf = { + [0] = (__u32)jiffies, + [1] = (__u32)current->pid, + }, + }; int status;

do { - status = _nfs4_do_open(dir, ctx, flags, sattr, label, opened); + status = _nfs4_do_open(dir, ctx, flags, &c, opened); res = ctx->state; trace_nfs4_open_file(ctx, flags, status); if (status == 0)

[ Upstream commit de766e570413bd0484af0b580299b495ada625c3 ]

Instead of granting client's full requests until we hit our DRC size limit and then failing CREATE_SESSIONs (and hence mounts) completely, start granting clients smaller slot tables as we approach the limit.

The factor chosen here is pretty much arbitrary.

Signed-off-by: J. Bruce Fields bfields@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfsd/nfs4state.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 3656f87d11e3..0aacd1c850c3 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1507,6 +1507,11 @@ static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca) spin_lock(&nfsd_drc_lock); avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION, nfsd_drc_max_mem - nfsd_drc_mem_used); + /* + * Never use more than a third of the remaining memory, + * unless it's the only way to give this client a slot: + */ + avail = clamp_t(int, avail, slotsize, avail/3); num = min_t(int, num, avail / slotsize); nfsd_drc_mem_used += num * slotsize; spin_unlock(&nfsd_drc_lock);

[ Upstream commit 3b2d4dcf71c4a91b420f835e52ddea8192300a3b ]

Since commit 10a68cdf10 (nfsd: fix performance-limiting session calculation) (Linux 5.1-rc1 and 4.19.31), shares from NFS servers with 1 TB of memory cannot be mounted anymore. The mount just hangs on the client.

The gist of commit 10a68cdf10 is the change below.

-avail = clamp_t(int, avail, slotsize, avail/3); +avail = clamp_t(int, avail, slotsize, total_avail/3);

Here are the macros.

#define min_t(type, x, y) __careful_cmp((type)(x), (type)(y), <) #define clamp_t(type, val, lo, hi) min_t(type, max_t(type, val, lo), hi)

`total_avail` is 8,434,659,328 on the 1 TB machine. `clamp_t()` casts the values to `int`, which for 32-bit integers can only hold values −2,147,483,648 (−2^31) through 2,147,483,647 (2^31 − 1).

`avail` (in the function signature) is just 65536, so that no overflow was happening. Before the commit the assignment would result in 21845, and `num = 4`.

When using `total_avail`, it is causing the assignment to be 18446744072226137429 (printed as %lu), and `num` is then 4164608182.

My next guess is, that `nfsd_drc_mem_used` is then exceeded, and the server thinks there is no memory available any more for this client.

Updating the arguments of `clamp_t()` and `min_t()` to `unsigned long` fixes the issue.

Now, `avail = 65536` (before commit 10a68cdf10 `avail = 21845`), but `num = 4` remains the same.

Fixes: c54f24e338ed (nfsd: fix performance-limiting session calculation) Cc: stable@vger.kernel.org Signed-off-by: Paul Menzel pmenzel@molgen.mpg.de Signed-off-by: J. Bruce Fields bfields@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfsd/nfs4state.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c4762d8aa9f8..032fcae3a94f 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1511,7 +1511,7 @@ static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca) * Never use more than a third of the remaining memory, * unless it's the only way to give this client a slot: */ - avail = clamp_t(int, avail, slotsize, total_avail/3); + avail = clamp_t(unsigned long, avail, slotsize, total_avail/3); num = min_t(int, num, avail / slotsize); nfsd_drc_mem_used += num * slotsize; spin_unlock(&nfsd_drc_lock);

[ Upstream commit 561759292774707b71ee61aecc07724905bb7ef1 ]

If the device rejects the control transfer to enable device-initiated U1/U2 entry, then the device will not initiate U1/U2 transition. To improve the performance, the downstream port should not initate transition to U1/U2 to avoid the delay from the device link command response (no packet can be transmitted while waiting for a response from the device). If the device has some quirks and does not implement U1/U2, it may reject all the link state change requests, and the downstream port may resend and flood the bus with more requests. This will affect the device performance even further. This patch disables the hub-initated U1/U2 if the device-initiated U1/U2 entry fails.

Reference: USB 3.2 spec 7.2.4.2.3

Signed-off-by: Thinh Nguyen thinhn@synopsys.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/usb/core/hub.c | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-)

diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 9f132fac7b2c..63646dc3ca27 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -3879,6 +3879,9 @@ static int usb_set_lpm_timeout(struct usb_device *udev, * control transfers to set the hub timeout or enable device-initiated U1/U2 * will be successful. * + * If the control transfer to enable device-initiated U1/U2 entry fails, then + * hub-initiated U1/U2 will be disabled. + * * If we cannot set the parent hub U1/U2 timeout, we attempt to let the xHCI * driver know about it. If that call fails, it should be harmless, and just * take up more slightly more bus bandwidth for unnecessary U1/U2 exit latency. @@ -3933,23 +3936,24 @@ static void usb_enable_link_state(struct usb_hcd *hcd, struct usb_device *udev, * host know that this link state won't be enabled. */ hcd->driver->disable_usb3_lpm_timeout(hcd, udev, state); - } else { - /* Only a configured device will accept the Set Feature - * U1/U2_ENABLE - */ - if (udev->actconfig) - usb_set_device_initiated_lpm(udev, state, true); + return; + }

- /* As soon as usb_set_lpm_timeout(timeout) returns 0, the - * hub-initiated LPM is enabled. Thus, LPM is enabled no - * matter the result of usb_set_device_initiated_lpm(). - * The only difference is whether device is able to initiate - * LPM. - */ + /* Only a configured device will accept the Set Feature + * U1/U2_ENABLE + */ + if (udev->actconfig && + usb_set_device_initiated_lpm(udev, state, true) == 0) { if (state == USB3_LPM_U1) udev->usb3_lpm_u1_enabled = 1; else if (state == USB3_LPM_U2) udev->usb3_lpm_u2_enabled = 1; + } else { + /* Don't request U1/U2 entry if the device + * cannot transition to U1/U2. + */ + usb_set_lpm_timeout(udev, state, 0); + hcd->driver->disable_usb3_lpm_timeout(hcd, udev, state); } }