From: Guoqing Jiang gqjiang@suse.com

[ Upstream commit 9c8043f337f14d1743006dfc59c03e80a42e3884 ]

To avoid memory leak, we need to free the cinfo which is allocated when node join cluster.

Reviewed-by: NeilBrown neilb@suse.com Signed-off-by: Guoqing Jiang gqjiang@suse.com Signed-off-by: Shaohua Li shli@fb.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/md/md-cluster.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index d6a1126d85ce..494d01d0e92a 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -821,6 +821,7 @@ static int leave(struct mddev *mddev) lockres_free(cinfo->no_new_dev_lockres); lockres_free(cinfo->bitmap_lockres); dlm_release_lockspace(cinfo->lockspace, 2); + kfree(cinfo); return 0; }

From: Andrea Arcangeli aarcange@redhat.com

[ Upstream commit 46aa6a302b53f543f8e8b8e1714dc5e449ad36a6 ]

linux/tools/testing/selftests/vm $ make

gcc -Wall -I ../../../../usr/include compaction_test.c -lrt -o /compaction_test /usr/lib/gcc/x86_64-pc-linux-gnu/4.9.4/../../../../x86_64-pc-linux-gnu/bin/ld: cannot open output file /compaction_test: Permission denied collect2: error: ld returned 1 exit status make: *** [../lib.mk:54: /compaction_test] Error 1

Since commit a8ba798bc8ec ("selftests: enable O and KBUILD_OUTPUT") selftests/vm build fails if run from the "selftests/vm" directory, but it works in the selftests/ directory. It's quicker to be able to do a local vm-only build after a tree wipe and this patch allows for it again.

Link: http://lkml.kernel.org/r/20170302173738.18994-4-aarcange@redhat.com Signed-off-by: Andrea Arcangeli aarcange@redhat.com Cc: Mike Rapoport rppt@linux.vnet.ibm.com Cc: "Dr. David Alan Gilbert" dgilbert@redhat.com Cc: Mike Kravetz mike.kravetz@oracle.com Cc: Pavel Emelyanov xemul@parallels.com Cc: Hillf Danton hillf.zj@alibaba-inc.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin alexander.levin@verizon.com --- tools/testing/selftests/vm/Makefile | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index e4bb1de1d526..b5f08e8cab33 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -1,5 +1,9 @@ # Makefile for vm selftests

+ifndef OUTPUT + OUTPUT := $(shell pwd) +endif + CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS) BINARIES = compaction_test BINARIES += hugepage-mmap

From: Doug Berger opendmb@gmail.com

[ Upstream commit eca4bad73409aedc6ff22f823c18b67a4f08c851 ]

The reserved gphy_rev value of 0x01ff must be tested before the old or new scheme for GPHY major versioning are tested, otherwise it will be treated as 0xff00 according to the old scheme.

Fixes: b04a2f5b9ff5 ("net: bcmgenet: add support for new GENET PHY revision scheme") Signed-off-by: Doug Berger opendmb@gmail.com Reviewed-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index f848f49c590d..f252ed25b75b 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3326,6 +3326,12 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv) */ gphy_rev = reg & 0xffff;

+ /* This is reserved so should require special treatment */ + if (gphy_rev == 0 || gphy_rev == 0x01ff) { + pr_warn("Invalid GPHY revision detected: 0x%04x\n", gphy_rev); + return; + } + /* This is the good old scheme, just GPHY major, no minor nor patch */ if ((gphy_rev & 0xf0) != 0) priv->gphy_rev = gphy_rev << 8; @@ -3334,12 +3340,6 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv) else if ((gphy_rev & 0xff00) != 0) priv->gphy_rev = gphy_rev;

- /* This is reserved so should require special treatment */ - else if (gphy_rev == 0 || gphy_rev == 0x01ff) { - pr_warn("Invalid GPHY revision detected: 0x%04x\n", gphy_rev); - return; - } - #ifdef CONFIG_PHYS_ADDR_T_64BIT if (!(params->flags & GENET_HAS_40BITS)) pr_warn("GENET does not support 40-bits PA\n");

From: NeilBrown neilb@suse.com

[ Upstream commit 928c6fb3a9bfd6c5b287aa3465226add551c13c0 ]

Current code will return 1 if the version is supported, and -1 if it isn't. This is confusing and inconsistent with the one place where this is used. So change to return 1 if it is supported, and zero if not. i.e. an error is never returned.

Signed-off-by: NeilBrown neilb@suse.com Signed-off-by: J. Bruce Fields bfields@redhat.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- fs/nfsd/nfssvc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 5be1fa6b676d..8a20b1932eed 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -151,7 +151,8 @@ int nfsd_vers(int vers, enum vers_op change)

int nfsd_minorversion(u32 minorversion, enum vers_op change) { - if (minorversion > NFSD_SUPPORTED_MINOR_VERSION) + if (minorversion > NFSD_SUPPORTED_MINOR_VERSION && + change != NFSD_AVAIL) return -1; switch(change) { case NFSD_SET:

From: Doug Berger opendmb@gmail.com

[ Upstream commit 6be371b053dc86f11465cc1abce2e99bda0a0574 ]

When using the internal PHY it must be powered up when the MII is probed or the PHY will not be detected. Since the PHY is powered up at reset this has not been a problem. However, when the kernel is restarted with kexec the PHY will likely be powered down when the kernel starts so it will not be detected and the Ethernet link will not be established.

This commit explicitly powers up the internal PHY when the GENET driver is probed to correct this behavior.

Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file") Signed-off-by: Doug Berger opendmb@gmail.com Reviewed-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 9217a0f4082f..74dd48f2bd89 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3384,6 +3384,7 @@ static int bcmgenet_probe(struct platform_device *pdev) const void *macaddr; struct resource *r; int err = -EIO; + const char *phy_mode_str;

/* Up to GENET_MAX_MQ_CNT + 1 TX queues and RX queues */ dev = alloc_etherdev_mqs(sizeof(*priv), GENET_MAX_MQ_CNT + 1, @@ -3489,6 +3490,13 @@ static int bcmgenet_probe(struct platform_device *pdev) priv->clk_eee = NULL; }

+ /* If this is an internal GPHY, power it on now, before UniMAC is + * brought out of reset as absolutely no UniMAC activity is allowed + */ + if (dn && !of_property_read_string(dn, "phy-mode", &phy_mode_str) && + !strcasecmp(phy_mode_str, "internal")) + bcmgenet_power_up(priv, GENET_POWER_PASSIVE); + err = reset_umac(priv); if (err) goto err_clk_disable;

From: Tahsin Erdogan tahsin@google.com

[ Upstream commit 4a3a485b1ed0e109718cc8c9d094fa0f552de9b2 ]

When WB_registered flag is not set, wb_queue_work() skips queuing the work, but does not perform the necessary clean up. In particular, if work->auto_free is true, it should free the memory.

The leak condition can be reprouced by following these steps:

mount /dev/sdb /mnt/sdb /* In qemu console: device_del sdb */ umount /dev/sdb

Above will result in a wb_queue_work() call on an unregistered wb and thus leak memory.

Reported-by: John Sperbeck jsperbeck@google.com Signed-off-by: Tahsin Erdogan tahsin@google.com Reviewed-by: Jan Kara jack@suse.cz Signed-off-by: Jens Axboe axboe@fb.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- fs/fs-writeback.c | 35 +++++++++++++++++++++-------------- 1 file changed, 21 insertions(+), 14 deletions(-)

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 60d6fc2e0e4b..22b30249fbcb 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -173,19 +173,33 @@ static void wb_wakeup(struct bdi_writeback *wb) spin_unlock_bh(&wb->work_lock); }

+static void finish_writeback_work(struct bdi_writeback *wb, + struct wb_writeback_work *work) +{ + struct wb_completion *done = work->done; + + if (work->auto_free) + kfree(work); + if (done && atomic_dec_and_test(&done->cnt)) + wake_up_all(&wb->bdi->wb_waitq); +} + static void wb_queue_work(struct bdi_writeback *wb, struct wb_writeback_work *work) { trace_writeback_queue(wb, work);

- spin_lock_bh(&wb->work_lock); - if (!test_bit(WB_registered, &wb->state)) - goto out_unlock; if (work->done) atomic_inc(&work->done->cnt); - list_add_tail(&work->list, &wb->work_list); - mod_delayed_work(bdi_wq, &wb->dwork, 0); -out_unlock: + + spin_lock_bh(&wb->work_lock); + + if (test_bit(WB_registered, &wb->state)) { + list_add_tail(&work->list, &wb->work_list); + mod_delayed_work(bdi_wq, &wb->dwork, 0); + } else + finish_writeback_work(wb, work); + spin_unlock_bh(&wb->work_lock); }

@@ -1839,16 +1853,9 @@ static long wb_do_writeback(struct bdi_writeback *wb)

set_bit(WB_writeback_running, &wb->state); while ((work = get_next_work_item(wb)) != NULL) { - struct wb_completion *done = work->done; - trace_writeback_exec(wb, work); - wrote += wb_writeback(wb, work); - - if (work->auto_free) - kfree(work); - if (done && atomic_dec_and_test(&done->cnt)) - wake_up_all(&wb->bdi->wb_waitq); + finish_writeback_work(wb, work); }

/*

From: Tomi Valkeinen tomi.valkeinen@ti.com

[ Upstream commit 9fa1d7537242bd580ffa99c4725a0407096aad26 ]

omap_gem_dmabuf_mmap() returns an error (with a WARN) when called for a buffer which is allocated with dma_alloc_*(). This prevents dmabuf mmap from working on SoCs without DMM, e.g. AM4 and OMAP3.

I could not find any reason for omap_gem_dmabuf_mmap() rejecting such buffers, and just removing the if() fixes the limitation.

Signed-off-by: Tomi Valkeinen tomi.valkeinen@ti.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c | 3 --- 1 file changed, 3 deletions(-)

diff --git a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c index 27c297672076..d2d1c9a34da1 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c +++ b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c @@ -142,9 +142,6 @@ static int omap_gem_dmabuf_mmap(struct dma_buf *buffer, struct drm_gem_object *obj = buffer->priv; int ret = 0;

- if (WARN_ON(!obj->filp)) - return -EINVAL; - ret = drm_gem_mmap_obj(obj, omap_gem_mmap_size(obj), vma); if (ret < 0) return ret;

From: Johan Hovold johan@kernel.org

[ Upstream commit 6e526fdff7be4f13b24f929a04c0e9ae6761291e ]

Make sure to check the number of endpoints to avoid dereferencing a NULL-pointer or accessing memory beyond the endpoint array should a malicious device lack the expected endpoints.

The endpoints are specifically dereferenced in the i2400m_bootrom_init path during probe (e.g. in i2400mu_tx_bulk_out).

Fixes: f398e4240fce ("i2400m/USB: probe/disconnect, dev init/shutdown and reset backends") Cc: Inaky Perez-Gonzalez inaky@linux.intel.com

Signed-off-by: Johan Hovold johan@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/net/wimax/i2400m/usb.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wimax/i2400m/usb.c b/drivers/net/wimax/i2400m/usb.c index e7f5910a6519..f8eb66ef2944 100644 --- a/drivers/net/wimax/i2400m/usb.c +++ b/drivers/net/wimax/i2400m/usb.c @@ -467,6 +467,9 @@ int i2400mu_probe(struct usb_interface *iface, struct i2400mu *i2400mu; struct usb_device *usb_dev = interface_to_usbdev(iface);

+ if (iface->cur_altsetting->desc.bNumEndpoints < 4) + return -ENODEV; + if (usb_dev->speed != USB_SPEED_HIGH) dev_err(dev, "device not connected as high speed\n");

From: Jiri Pirko jiri@mellanox.com

[ Upstream commit f004ec065b4879d6bc9ba0211af2169b3ce3097f ]

The num_rec field is 8 bit, so the maximal count number is 255. This fixes vlans not being enabled for wider ranges than 255.

Fixes: b2e345f9a454 ("mlxsw: reg: Add Switch Port VID and Switch Port VLAN Membership registers definitions") Signed-off-by: Jiri Pirko jiri@mellanox.com Reviewed-by: Ido Schimmel idosch@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/net/ethernet/mellanox/mlxsw/reg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 236fb5d2ad69..3f2bf9ef2b2b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -599,7 +599,7 @@ static inline void mlxsw_reg_spvid_pack(char *payload, u8 local_port, u16 pvid) #define MLXSW_REG_SPVM_ID 0x200F #define MLXSW_REG_SPVM_BASE_LEN 0x04 /* base length, without records */ #define MLXSW_REG_SPVM_REC_LEN 0x04 /* record length */ -#define MLXSW_REG_SPVM_REC_MAX_COUNT 256 +#define MLXSW_REG_SPVM_REC_MAX_COUNT 255 #define MLXSW_REG_SPVM_LEN (MLXSW_REG_SPVM_BASE_LEN + \ MLXSW_REG_SPVM_REC_LEN * MLXSW_REG_SPVM_REC_MAX_COUNT)

From: Jiri Pirko jiri@mellanox.com

[ Upstream commit e9093b1183bbac462d2caef3eac165778c0b1bf1 ]

The num_rec field is 8 bit, so the maximal count number is 255. This fixes vlans learning not being enabled for wider ranges than 255.

Fixes: a4feea74cd7a ("mlxsw: reg: Add Switch Port VLAN MAC Learning register definition") Signed-off-by: Jiri Pirko jiri@mellanox.com Reviewed-by: Ido Schimmel idosch@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/net/ethernet/mellanox/mlxsw/reg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 3f2bf9ef2b2b..c7fe61f1f89f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -1139,7 +1139,7 @@ static inline void mlxsw_reg_sfmr_pack(char *payload, #define MLXSW_REG_SPVMLR_ID 0x2020 #define MLXSW_REG_SPVMLR_BASE_LEN 0x04 /* base length, without records */ #define MLXSW_REG_SPVMLR_REC_LEN 0x04 /* record length */ -#define MLXSW_REG_SPVMLR_REC_MAX_COUNT 256 +#define MLXSW_REG_SPVMLR_REC_MAX_COUNT 255 #define MLXSW_REG_SPVMLR_LEN (MLXSW_REG_SPVMLR_BASE_LEN + \ MLXSW_REG_SPVMLR_REC_LEN * \ MLXSW_REG_SPVMLR_REC_MAX_COUNT)

From: Stafford Horne shorne@gmail.com

[ Upstream commit 154e67cd8e8f964809d0e75e44bb121b169c75b3 ]

Was getting the following error with allmodconfig:

ERROR: "__get_user_bad" [lib/test_user_copy.ko] undefined!

This was simply a missing break statement, causing an unwanted fall through.

Signed-off-by: Stafford Horne shorne@gmail.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- arch/openrisc/include/asm/uaccess.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/openrisc/include/asm/uaccess.h b/arch/openrisc/include/asm/uaccess.h index 5cc6b4f1b795..1a836afb636d 100644 --- a/arch/openrisc/include/asm/uaccess.h +++ b/arch/openrisc/include/asm/uaccess.h @@ -215,7 +215,7 @@ do { \ case 1: __get_user_asm(x, ptr, retval, "l.lbz"); break; \ case 2: __get_user_asm(x, ptr, retval, "l.lhz"); break; \ case 4: __get_user_asm(x, ptr, retval, "l.lwz"); break; \ - case 8: __get_user_asm2(x, ptr, retval); \ + case 8: __get_user_asm2(x, ptr, retval); break; \ default: (x) = __get_user_bad(); \ } \ } while (0)

From: Don Brace don.brace@microsemi.com

[ Upstream commit 85b29008d8af6d94a0723aaa8d93cfb6e041158b ]

- Add in a new case for volume offline. Resolves internal testing bug for multilun array management. - Return correct status for failed TURs.

Reviewed-by: Scott Benesh scott.benesh@microsemi.com Reviewed-by: Scott Teel scott.teel@microsemi.com Signed-off-by: Don Brace don.brace@microsemi.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/scsi/hpsa.c | 35 ++++++++++++++++------------------- drivers/scsi/hpsa_cmd.h | 2 ++ 2 files changed, 18 insertions(+), 19 deletions(-)

diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index e9ce74afd13f..09f0de8fb2d9 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -3466,7 +3466,7 @@ exit_failed: * # (integer code indicating one of several NOT READY states * describing why a volume is to be kept offline) */ -static int hpsa_volume_offline(struct ctlr_info *h, +static unsigned char hpsa_volume_offline(struct ctlr_info *h, unsigned char scsi3addr[]) { struct CommandList *c; @@ -3486,7 +3486,7 @@ static int hpsa_volume_offline(struct ctlr_info *h, rc = hpsa_scsi_do_simple_cmd(h, c, DEFAULT_REPLY_QUEUE, NO_TIMEOUT); if (rc) { cmd_free(h, c); - return 0; + return HPSA_VPD_LV_STATUS_UNSUPPORTED; } sense = c->err_info->SenseInfo; if (c->err_info->SenseLen > sizeof(c->err_info->SenseInfo)) @@ -3497,19 +3497,13 @@ static int hpsa_volume_offline(struct ctlr_info *h, cmd_status = c->err_info->CommandStatus; scsi_status = c->err_info->ScsiStatus; cmd_free(h, c); - /* Is the volume 'not ready'? */ - if (cmd_status != CMD_TARGET_STATUS || - scsi_status != SAM_STAT_CHECK_CONDITION || - sense_key != NOT_READY || - asc != ASC_LUN_NOT_READY) { - return 0; - }

/* Determine the reason for not ready state */ ldstat = hpsa_get_volume_status(h, scsi3addr);

/* Keep volume offline in certain cases: */ switch (ldstat) { + case HPSA_LV_FAILED: case HPSA_LV_UNDERGOING_ERASE: case HPSA_LV_NOT_AVAILABLE: case HPSA_LV_UNDERGOING_RPI: @@ -3531,7 +3525,7 @@ static int hpsa_volume_offline(struct ctlr_info *h, default: break; } - return 0; + return HPSA_LV_OK; }

/* @@ -3615,10 +3609,10 @@ static int hpsa_update_device_info(struct ctlr_info *h, /* Do an inquiry to the device to see what it is. */ if (hpsa_scsi_do_inquiry(h, scsi3addr, 0, inq_buff, (unsigned char) OBDR_TAPE_INQ_SIZE) != 0) { - /* Inquiry failed (msg printed already) */ dev_err(&h->pdev->dev, - "hpsa_update_device_info: inquiry failed\n"); - rc = -EIO; + "%s: inquiry failed, device will be skipped.\n", + __func__); + rc = HPSA_INQUIRY_FAILED; goto bail_out; }

@@ -3638,15 +3632,19 @@ static int hpsa_update_device_info(struct ctlr_info *h,

if (this_device->devtype == TYPE_DISK && is_logical_dev_addr_mode(scsi3addr)) { - int volume_offline; + unsigned char volume_offline;

hpsa_get_raid_level(h, scsi3addr, &this_device->raid_level); if (h->fw_support & MISC_FW_RAID_OFFLOAD_BASIC) hpsa_get_ioaccel_status(h, scsi3addr, this_device); volume_offline = hpsa_volume_offline(h, scsi3addr); - if (volume_offline < 0 || volume_offline > 0xff) - volume_offline = HPSA_VPD_LV_STATUS_UNSUPPORTED; - this_device->volume_offline = volume_offline & 0xff; + if (volume_offline == HPSA_LV_FAILED) { + rc = HPSA_LV_FAILED; + dev_err(&h->pdev->dev, + "%s: LV failed, device will be skipped.\n", + __func__); + goto bail_out; + } } else { this_device->raid_level = RAID_UNKNOWN; this_device->offload_config = 0; @@ -4115,8 +4113,7 @@ static void hpsa_update_scsi_devices(struct ctlr_info *h) goto out; } if (rc) { - dev_warn(&h->pdev->dev, - "Inquiry failed, skipping device.\n"); + h->drv_req_rescan = 1; continue; }

diff --git a/drivers/scsi/hpsa_cmd.h b/drivers/scsi/hpsa_cmd.h index d92ef0d352b5..26488e2a7f02 100644 --- a/drivers/scsi/hpsa_cmd.h +++ b/drivers/scsi/hpsa_cmd.h @@ -155,6 +155,7 @@ #define CFGTBL_BusType_Fibre2G 0x00000200l

/* VPD Inquiry types */ +#define HPSA_INQUIRY_FAILED 0x02 #define HPSA_VPD_SUPPORTED_PAGES 0x00 #define HPSA_VPD_LV_DEVICE_GEOMETRY 0xC1 #define HPSA_VPD_LV_IOACCEL_STATUS 0xC2 @@ -164,6 +165,7 @@ /* Logical volume states */ #define HPSA_VPD_LV_STATUS_UNSUPPORTED 0xff #define HPSA_LV_OK 0x0 +#define HPSA_LV_FAILED 0x01 #define HPSA_LV_NOT_AVAILABLE 0x0b #define HPSA_LV_UNDERGOING_ERASE 0x0F #define HPSA_LV_UNDERGOING_RPI 0x12

From: Daniel Bristot de Oliveira bristot@redhat.com

[ Upstream commit 5ac69d37784b237707a7b15d199cdb6c6fdb6780 ]

Currently, the replenishment timer is set to fire at the deadline of a task. Although that works for implicit deadline tasks because the deadline is equals to the begin of the next period, that is not correct for constrained deadline tasks (deadline < period).

For instance:

f.c: --------------- %< --------------- int main (void) { for(;;); } --------------- >% ---------------

# gcc -o f f.c

# trace-cmd record -e sched:sched_switch \ -e syscalls:sys_exit_sched_setattr \ chrt -d --sched-runtime 490000000 \ --sched-deadline 500000000 \ --sched-period 1000000000 0 ./f

# trace-cmd report | grep "{pid of ./f}"

After setting parameters, the task is replenished and continue running until being throttled:

f-11295 [003] 13322.113776: sys_exit_sched_setattr: 0x0

The task is throttled after running 492318 ms, as expected:

f-11295 [003] 13322.606094: sched_switch: f:11295 [-1] R ==> watchdog/3:32 [0]

But then, the task is replenished 500719 ms after the first replenishment:

<idle>-0 [003] 13322.614495: sched_switch: swapper/3:0 [120] R ==> f:11295 [-1]

Running for 490277 ms:

f-11295 [003] 13323.104772: sched_switch: f:11295 [-1] R ==> swapper/3:0 [120]

Hence, in the first period, the task runs 2 * runtime, and that is a bug.

During the first replenishment, the next deadline is set one period away. So the runtime / period starts to be respected. However, as the second replenishment took place in the wrong instant, the next replenishment will also be held in a wrong instant of time. Rather than occurring in the nth period away from the first activation, it is taking place in the (nth period - relative deadline).

Signed-off-by: Daniel Bristot de Oliveira bristot@redhat.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Luca Abeni luca.abeni@santannapisa.it Reviewed-by: Steven Rostedt (VMware) rostedt@goodmis.org Reviewed-by: Juri Lelli juri.lelli@arm.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Mike Galbraith efault@gmx.de Cc: Peter Zijlstra peterz@infradead.org Cc: Romulo Silva de Oliveira romulo.deoliveira@ufsc.br Cc: Steven Rostedt rostedt@goodmis.org Cc: Thomas Gleixner tglx@linutronix.de Cc: Tommaso Cucinotta tommaso.cucinotta@sssup.it Link: http://lkml.kernel.org/r/ac50d89887c25285b47465638354b63362f8adff.1488392936... Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin alexander.levin@verizon.com --- kernel/sched/deadline.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index e984f059e5fc..a428f7e6f5e9 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -510,10 +510,15 @@ static void update_dl_entity(struct sched_dl_entity *dl_se, } }

+static inline u64 dl_next_period(struct sched_dl_entity *dl_se) +{ + return dl_se->deadline - dl_se->dl_deadline + dl_se->dl_period; +} + /* * If the entity depleted all its runtime, and if we want it to sleep * while waiting for some new execution time to become available, we - * set the bandwidth enforcement timer to the replenishment instant + * set the bandwidth replenishment timer to the replenishment instant * and try to activate it. * * Notice that it is important for the caller to know if the timer @@ -535,7 +540,7 @@ static int start_dl_timer(struct task_struct *p) * that it is actually coming from rq->clock and not from * hrtimer's time base reading. */ - act = ns_to_ktime(dl_se->deadline); + act = ns_to_ktime(dl_next_period(dl_se)); now = hrtimer_cb_get_time(timer); delta = ktime_to_ns(now) - rq_clock(rq); act = ktime_add_ns(act, delta);

From: Daniel Bristot de Oliveira bristot@redhat.com

[ Upstream commit df8eac8cafce7d086be3bd5cf5a838fa37594dfb ]

During the activation, CBS checks if it can reuse the current task's runtime and period. If the deadline of the task is in the past, CBS cannot use the runtime, and so it replenishes the task. This rule works fine for implicit deadline tasks (deadline == period), and the CBS was designed for implicit deadline tasks. However, a task with constrained deadline (deadine < period) might be awakened after the deadline, but before the next period. In this case, replenishing the task would allow it to run for runtime / deadline. As in this case deadline < period, CBS enables a task to run for more than the runtime / period. In a very loaded system, this can cause a domino effect, making other tasks miss their deadlines.

To avoid this problem, in the activation of a constrained deadline task after the deadline but before the next period, throttle the task and set the replenishing timer to the begin of the next period, unless it is boosted.

Reproducer:

--------------- %< --------------- int main (int argc, char **argv) { int ret; int flags = 0; unsigned long l = 0; struct timespec ts; struct sched_attr attr;

memset(&attr, 0, sizeof(attr)); attr.size = sizeof(attr);

attr.sched_policy = SCHED_DEADLINE; attr.sched_runtime = 2 * 1000 * 1000; /* 2 ms */ attr.sched_deadline = 2 * 1000 * 1000; /* 2 ms */ attr.sched_period = 2 * 1000 * 1000 * 1000; /* 2 s */

ts.tv_sec = 0; ts.tv_nsec = 2000 * 1000; /* 2 ms */

ret = sched_setattr(0, &attr, flags);

if (ret < 0) { perror("sched_setattr"); exit(-1); }

for(;;) { /* XXX: you may need to adjust the loop */ for (l = 0; l < 150000; l++); /* * The ideia is to go to sleep right before the deadline * and then wake up before the next period to receive * a new replenishment. */ nanosleep(&ts, NULL); }

exit(0); } --------------- >% ---------------

On my box, this reproducer uses almost 50% of the CPU time, which is obviously wrong for a task with 2/2000 reservation.

Signed-off-by: Daniel Bristot de Oliveira bristot@redhat.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: Juri Lelli juri.lelli@arm.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Luca Abeni luca.abeni@santannapisa.it Cc: Mike Galbraith efault@gmx.de Cc: Peter Zijlstra peterz@infradead.org Cc: Romulo Silva de Oliveira romulo.deoliveira@ufsc.br Cc: Steven Rostedt rostedt@goodmis.org Cc: Thomas Gleixner tglx@linutronix.de Cc: Tommaso Cucinotta tommaso.cucinotta@sssup.it Link: http://lkml.kernel.org/r/edf58354e01db46bf42df8d2dd32418833f68c89.1488392936... Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin alexander.levin@verizon.com --- kernel/sched/deadline.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index a428f7e6f5e9..95cc139af11b 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -704,6 +704,37 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se) timer->function = dl_task_timer; }

+/* + * During the activation, CBS checks if it can reuse the current task's + * runtime and period. If the deadline of the task is in the past, CBS + * cannot use the runtime, and so it replenishes the task. This rule + * works fine for implicit deadline tasks (deadline == period), and the + * CBS was designed for implicit deadline tasks. However, a task with + * constrained deadline (deadine < period) might be awakened after the + * deadline, but before the next period. In this case, replenishing the + * task would allow it to run for runtime / deadline. As in this case + * deadline < period, CBS enables a task to run for more than the + * runtime / period. In a very loaded system, this can cause a domino + * effect, making other tasks miss their deadlines. + * + * To avoid this problem, in the activation of a constrained deadline + * task after the deadline but before the next period, throttle the + * task and set the replenishing timer to the begin of the next period, + * unless it is boosted. + */ +static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se) +{ + struct task_struct *p = dl_task_of(dl_se); + struct rq *rq = rq_of_dl_rq(dl_rq_of_se(dl_se)); + + if (dl_time_before(dl_se->deadline, rq_clock(rq)) && + dl_time_before(rq_clock(rq), dl_next_period(dl_se))) { + if (unlikely(dl_se->dl_boosted || !start_dl_timer(p))) + return; + dl_se->dl_throttled = 1; + } +} + static int dl_runtime_exceeded(struct sched_dl_entity *dl_se) { @@ -958,6 +989,11 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se) __dequeue_dl_entity(dl_se); }

+static inline bool dl_is_constrained(struct sched_dl_entity *dl_se) +{ + return dl_se->dl_deadline < dl_se->dl_period; +} + static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) { struct task_struct *pi_task = rt_mutex_get_top_task(p); @@ -984,6 +1020,15 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) }

/* + * Check if a constrained deadline task was activated + * after the deadline but before the next period. + * If that is the case, the task will be throttled and + * the replenishment timer will be set to the next period. + */ + if (!p->dl.dl_throttled && dl_is_constrained(&p->dl)) + dl_check_constrained_dl(&p->dl); + + /* * If p is throttled, we do nothing. In fact, if it exhausted * its budget it needs a replenishment and, since it now is on * its rq, the bandwidth timer callback (which clearly has not

From: "Steven Rostedt (VMware)" rostedt@goodmis.org

[ Upstream commit 2317d5f1c34913bac5971d93d69fb6c31bb74670 ]

I was testing Daniel's changes with his test case, and tweaked it a little. Instead of having the runtime equal to the deadline, I increased the deadline ten fold.

Daniel's test case had:

attr.sched_runtime = 2 * 1000 * 1000; /* 2 ms */ attr.sched_deadline = 2 * 1000 * 1000; /* 2 ms */ attr.sched_period = 2 * 1000 * 1000 * 1000; /* 2 s */

To make it more interesting, I changed it to:

attr.sched_runtime = 2 * 1000 * 1000; /* 2 ms */ attr.sched_deadline = 20 * 1000 * 1000; /* 20 ms */ attr.sched_period = 2 * 1000 * 1000 * 1000; /* 2 s */

The results were rather surprising. The behavior that Daniel's patch was fixing came back. The task started using much more than .1% of the CPU. More like 20%.

Looking into this I found that it was due to the dl_entity_overflow() constantly returning true. That's because it uses the relative period against relative runtime vs the absolute deadline against absolute runtime.

runtime / (deadline - t) > dl_runtime / dl_period

There's even a comment mentioning this, and saying that when relative deadline equals relative period, that the equation is the same as using deadline instead of period. That comment is backwards! What we really want is:

runtime / (deadline - t) > dl_runtime / dl_deadline

We care about if the runtime can make its deadline, not its period. And then we can say "when the deadline equals the period, the equation is the same as using dl_period instead of dl_deadline".

After correcting this, now when the task gets enqueued, it can throttle correctly, and Daniel's fix to the throttling of sleeping deadline tasks works even when the runtime and deadline are not the same.

Signed-off-by: Steven Rostedt (VMware) rostedt@goodmis.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Daniel Bristot de Oliveira bristot@redhat.com Cc: Juri Lelli juri.lelli@arm.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Luca Abeni luca.abeni@santannapisa.it Cc: Mike Galbraith efault@gmx.de Cc: Peter Zijlstra peterz@infradead.org Cc: Romulo Silva de Oliveira romulo.deoliveira@ufsc.br Cc: Steven Rostedt rostedt@goodmis.org Cc: Thomas Gleixner tglx@linutronix.de Cc: Tommaso Cucinotta tommaso.cucinotta@sssup.it Link: http://lkml.kernel.org/r/02135a27f1ae3fe5fd032568a5a2f370e190e8d7.1488392936... Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin alexander.levin@verizon.com --- kernel/sched/deadline.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 95cc139af11b..a996f7356216 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -441,13 +441,13 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * * This function returns true if: * - * runtime / (deadline - t) > dl_runtime / dl_period , + * runtime / (deadline - t) > dl_runtime / dl_deadline , * * IOW we can't recycle current parameters. * - * Notice that the bandwidth check is done against the period. For + * Notice that the bandwidth check is done against the deadline. For * task with deadline equal to period this is the same of using - * dl_deadline instead of dl_period in the equation above. + * dl_period instead of dl_deadline in the equation above. */ static bool dl_entity_overflow(struct sched_dl_entity *dl_se, struct sched_dl_entity *pi_se, u64 t) @@ -472,7 +472,7 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se, * of anything below microseconds resolution is actually fiction * (but still we want to give the user that illusion >;). */ - left = (pi_se->dl_period >> DL_SCALE) * (dl_se->runtime >> DL_SCALE); + left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE); right = ((dl_se->deadline - t) >> DL_SCALE) * (pi_se->dl_runtime >> DL_SCALE);

From: Alex Deucher alexander.deucher@amd.com

[ Upstream commit 66822d815ae61ecb2d9dba9031517e8a8476969d ]

Higher sclks seem to be unstable on some boards.

bug: https://bugs.freedesktop.org/show_bug.cgi?id=100222

Signed-off-by: Alex Deucher alexander.deucher@amd.com Cc: stable@vger.kernel.org Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/gpu/drm/radeon/si_dpm.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index c42430bd3ac2..d9007cc37be1 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -3030,9 +3030,13 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev, max_mclk = 80000; } } else if (rdev->family == CHIP_OLAND) { - if ((rdev->pdev->device == 0x6604) && - (rdev->pdev->subsystem_vendor == 0x1028) && - (rdev->pdev->subsystem_device == 0x066F)) { + if ((rdev->pdev->revision == 0xC7) || + (rdev->pdev->revision == 0x80) || + (rdev->pdev->revision == 0x81) || + (rdev->pdev->revision == 0x83) || + (rdev->pdev->revision == 0x87) || + (rdev->pdev->device == 0x6604) || + (rdev->pdev->device == 0x6605)) { max_sclk = 75000; } }

From: Tina Ruchandani ruchandani.tina@gmail.com

[ Upstream commit 8a79790bf0b7da216627ffb85f52cfb4adbf1e4e ]

get_seconds() returns real wall-clock seconds. On 32-bit systems this value will overflow in year 2038 and beyond. This patch changes afs's vlocation record to use ktime_get_real_seconds() instead, for the fields time_of_death and update_at.

Signed-off-by: Tina Ruchandani ruchandani.tina@gmail.com Signed-off-by: David Howells dhowells@redhat.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- fs/afs/callback.c | 7 ++++--- fs/afs/internal.h | 7 ++++--- fs/afs/server.c | 6 +++--- fs/afs/vlocation.c | 16 +++++++++------- 4 files changed, 20 insertions(+), 16 deletions(-)

diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 7ef637d7f3a5..7d54efd73519 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -362,7 +362,7 @@ static void afs_callback_updater(struct work_struct *work) { struct afs_server *server; struct afs_vnode *vnode, *xvnode; - time_t now; + time64_t now; long timeout; int ret;

@@ -370,7 +370,7 @@ static void afs_callback_updater(struct work_struct *work)

_enter("");

- now = get_seconds(); + now = ktime_get_real_seconds();

/* find the first vnode to update */ spin_lock(&server->cb_lock); @@ -424,7 +424,8 @@ static void afs_callback_updater(struct work_struct *work)

/* and then reschedule */ _debug("reschedule"); - vnode->update_at = get_seconds() + afs_vnode_update_timeout; + vnode->update_at = ktime_get_real_seconds() + + afs_vnode_update_timeout;

spin_lock(&server->cb_lock);

diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 5cb5c320b966..c671cdb3acad 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -11,6 +11,7 @@

#include <linux/compiler.h> #include <linux/kernel.h> +#include <linux/ktime.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/skbuff.h> @@ -247,7 +248,7 @@ struct afs_cache_vhash { */ struct afs_vlocation { atomic_t usage; - time_t time_of_death; /* time at which put reduced usage to 0 */ + time64_t time_of_death; /* time at which put reduced usage to 0 */ struct list_head link; /* link in cell volume location list */ struct list_head grave; /* link in master graveyard list */ struct list_head update; /* link in master update list */ @@ -258,7 +259,7 @@ struct afs_vlocation { struct afs_cache_vlocation vldb; /* volume information DB record */ struct afs_volume *vols[3]; /* volume access record pointer (index by type) */ wait_queue_head_t waitq; /* status change waitqueue */ - time_t update_at; /* time at which record should be updated */ + time64_t update_at; /* time at which record should be updated */ spinlock_t lock; /* access lock */ afs_vlocation_state_t state; /* volume location state */ unsigned short upd_rej_cnt; /* ENOMEDIUM count during update */ @@ -271,7 +272,7 @@ struct afs_vlocation { */ struct afs_server { atomic_t usage; - time_t time_of_death; /* time at which put reduced usage to 0 */ + time64_t time_of_death; /* time at which put reduced usage to 0 */ struct in_addr addr; /* server address */ struct afs_cell *cell; /* cell in which server resides */ struct list_head link; /* link in cell's server list */ diff --git a/fs/afs/server.c b/fs/afs/server.c index f342acf3547d..3bc1a46f0bd6 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -237,7 +237,7 @@ void afs_put_server(struct afs_server *server) spin_lock(&afs_server_graveyard_lock); if (atomic_read(&server->usage) == 0) { list_move_tail(&server->grave, &afs_server_graveyard); - server->time_of_death = get_seconds(); + server->time_of_death = ktime_get_real_seconds(); queue_delayed_work(afs_wq, &afs_server_reaper, afs_server_timeout * HZ); } @@ -272,9 +272,9 @@ static void afs_reap_server(struct work_struct *work) LIST_HEAD(corpses); struct afs_server *server; unsigned long delay, expiry; - time_t now; + time64_t now;

- now = get_seconds(); + now = ktime_get_real_seconds(); spin_lock(&afs_server_graveyard_lock);

while (!list_empty(&afs_server_graveyard)) { diff --git a/fs/afs/vlocation.c b/fs/afs/vlocation.c index 52976785a32c..ee9015c0db5a 100644 --- a/fs/afs/vlocation.c +++ b/fs/afs/vlocation.c @@ -340,7 +340,8 @@ static void afs_vlocation_queue_for_updates(struct afs_vlocation *vl) struct afs_vlocation *xvl;

/* wait at least 10 minutes before updating... */ - vl->update_at = get_seconds() + afs_vlocation_update_timeout; + vl->update_at = ktime_get_real_seconds() + + afs_vlocation_update_timeout;

spin_lock(&afs_vlocation_updates_lock);

@@ -506,7 +507,7 @@ void afs_put_vlocation(struct afs_vlocation *vl) if (atomic_read(&vl->usage) == 0) { _debug("buried"); list_move_tail(&vl->grave, &afs_vlocation_graveyard); - vl->time_of_death = get_seconds(); + vl->time_of_death = ktime_get_real_seconds(); queue_delayed_work(afs_wq, &afs_vlocation_reap, afs_vlocation_timeout * HZ);

@@ -543,11 +544,11 @@ static void afs_vlocation_reaper(struct work_struct *work) LIST_HEAD(corpses); struct afs_vlocation *vl; unsigned long delay, expiry; - time_t now; + time64_t now;

_enter("");

- now = get_seconds(); + now = ktime_get_real_seconds(); spin_lock(&afs_vlocation_graveyard_lock);

while (!list_empty(&afs_vlocation_graveyard)) { @@ -622,13 +623,13 @@ static void afs_vlocation_updater(struct work_struct *work) { struct afs_cache_vlocation vldb; struct afs_vlocation *vl, *xvl; - time_t now; + time64_t now; long timeout; int ret;

_enter("");

- now = get_seconds(); + now = ktime_get_real_seconds();

/* find a record to update */ spin_lock(&afs_vlocation_updates_lock); @@ -684,7 +685,8 @@ static void afs_vlocation_updater(struct work_struct *work)

/* and then reschedule */ _debug("reschedule"); - vl->update_at = get_seconds() + afs_vlocation_update_timeout; + vl->update_at = ktime_get_real_seconds() + + afs_vlocation_update_timeout;

spin_lock(&afs_vlocation_updates_lock);

From: David Howells dhowells@redhat.com

[ Upstream commit 58fed94dfb17e89556b5705f20f90e5b2971b6a1 ]

Flush outstanding writes in afs when an fd is closed. This is what NFS and CIFS do.

Reported-by: Marc Dionne marc.c.dionne@gmail.com Signed-off-by: David Howells dhowells@redhat.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- fs/afs/file.c | 1 + fs/afs/internal.h | 1 + fs/afs/write.c | 14 ++++++++++++++ 3 files changed, 16 insertions(+)

diff --git a/fs/afs/file.c b/fs/afs/file.c index 999bc3caec92..cf8a07e282a6 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -29,6 +29,7 @@ static int afs_readpages(struct file *filp, struct address_space *mapping,

const struct file_operations afs_file_operations = { .open = afs_open, + .flush = afs_flush, .release = afs_release, .llseek = generic_file_llseek, .read_iter = generic_file_read_iter, diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 71d5982312f3..5cb5c320b966 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -749,6 +749,7 @@ extern int afs_writepages(struct address_space *, struct writeback_control *); extern void afs_pages_written_back(struct afs_vnode *, struct afs_call *); extern ssize_t afs_file_write(struct kiocb *, struct iov_iter *); extern int afs_writeback_all(struct afs_vnode *); +extern int afs_flush(struct file *, fl_owner_t); extern int afs_fsync(struct file *, loff_t, loff_t, int);

diff --git a/fs/afs/write.c b/fs/afs/write.c index 777ea2bbf401..cc46e8c1d46e 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -741,6 +741,20 @@ out: }

/* + * Flush out all outstanding writes on a file opened for writing when it is + * closed. + */ +int afs_flush(struct file *file, fl_owner_t id) +{ + _enter(""); + + if ((file->f_mode & FMODE_WRITE) == 0) + return 0; + + return vfs_fsync(file, 0); +} + +/* * notification that a previously read-only page is about to become writable * - if it returns an error, the caller will deliver a bus error signal */

From: David Howells dhowells@redhat.com

[ Upstream commit 146a1192783697810b63a1e41c4d59fc93387340 ]

afs_fs_store_data() works out of the size of the write it's going to make, but it uses 32-bit unsigned subtraction in one place that gets automatically cast to loff_t.

However, if to < offset, then the number goes negative, but as the result isn't signed, this doesn't get sign-extended to 64-bits when placed in a loff_t.

Fix by casting the operands to loff_t.

Signed-off-by: David Howells dhowells@redhat.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- fs/afs/fsclient.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index c775fefe3ffe..0c8399e0fdac 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -1225,7 +1225,7 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb, _enter(",%x,{%x:%u},,", key_serial(wb->key), vnode->fid.vid, vnode->fid.vnode);

- size = to - offset; + size = (loff_t)to - (loff_t)offset; if (first != last) size += (loff_t)(last - first) << PAGE_SHIFT; pos = (loff_t)first << PAGE_SHIFT;

From: Marc Dionne marc.dionne@auristor.com

[ Upstream commit ab94f5d0dd6fd82e7eeca5e7c8096eaea0a0261f ]

The inode timestamps should be set from the client time in the status received from the server, rather than the server time which is meant for internal server use.

Set AFS_SET_MTIME and populate the mtime for operations that take an input status, such as file/dir creation and StoreData. If an input time is not provided the server will set the vnode times based on the current server time.

In a situation where the server has some skew with the client, this could lead to the client seeing a timestamp in the future for a file that it just created or wrote.

Signed-off-by: Marc Dionne marc.dionne@auristor.com Signed-off-by: David Howells dhowells@redhat.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- fs/afs/fsclient.c | 18 +++++++++--------- fs/afs/inode.c | 2 +- 2 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 0c8399e0fdac..10ce44214005 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -105,7 +105,7 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp, vnode->vfs_inode.i_mode = mode; }

- vnode->vfs_inode.i_ctime.tv_sec = status->mtime_server; + vnode->vfs_inode.i_ctime.tv_sec = status->mtime_client; vnode->vfs_inode.i_mtime = vnode->vfs_inode.i_ctime; vnode->vfs_inode.i_atime = vnode->vfs_inode.i_ctime; vnode->vfs_inode.i_version = data_version; @@ -703,8 +703,8 @@ int afs_fs_create(struct afs_server *server, memset(bp, 0, padsz); bp = (void *) bp + padsz; } - *bp++ = htonl(AFS_SET_MODE); - *bp++ = 0; /* mtime */ + *bp++ = htonl(AFS_SET_MODE | AFS_SET_MTIME); + *bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */ *bp++ = 0; /* owner */ *bp++ = 0; /* group */ *bp++ = htonl(mode & S_IALLUGO); /* unix mode */ @@ -981,8 +981,8 @@ int afs_fs_symlink(struct afs_server *server, memset(bp, 0, c_padsz); bp = (void *) bp + c_padsz; } - *bp++ = htonl(AFS_SET_MODE); - *bp++ = 0; /* mtime */ + *bp++ = htonl(AFS_SET_MODE | AFS_SET_MTIME); + *bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */ *bp++ = 0; /* owner */ *bp++ = 0; /* group */ *bp++ = htonl(S_IRWXUGO); /* unix mode */ @@ -1192,8 +1192,8 @@ static int afs_fs_store_data64(struct afs_server *server, *bp++ = htonl(vnode->fid.vnode); *bp++ = htonl(vnode->fid.unique);

- *bp++ = 0; /* mask */ - *bp++ = 0; /* mtime */ + *bp++ = htonl(AFS_SET_MTIME); /* mask */ + *bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */ *bp++ = 0; /* owner */ *bp++ = 0; /* group */ *bp++ = 0; /* unix mode */ @@ -1269,8 +1269,8 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb, *bp++ = htonl(vnode->fid.vnode); *bp++ = htonl(vnode->fid.unique);

- *bp++ = 0; /* mask */ - *bp++ = 0; /* mtime */ + *bp++ = htonl(AFS_SET_MTIME); /* mask */ + *bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */ *bp++ = 0; /* owner */ *bp++ = 0; /* group */ *bp++ = 0; /* unix mode */ diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 2d706612f1f5..f8fa92b1d43c 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -71,7 +71,7 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key) inode->i_uid = vnode->status.owner; inode->i_gid = vnode->status.group; inode->i_size = vnode->status.size; - inode->i_ctime.tv_sec = vnode->status.mtime_server; + inode->i_ctime.tv_sec = vnode->status.mtime_client; inode->i_ctime.tv_nsec = 0; inode->i_atime = inode->i_mtime = inode->i_ctime; inode->i_blocks = 0;

From: David Howells dhowells@redhat.com

[ Upstream commit 7286a35e893176169b09715096a4aca557e2ccd2 ]

Fix afs_kill_pages() in two ways:

(1) If a writeback has been partially flushed, then if we try and kill the pages it contains, some of them may no longer be undergoing writeback and end_page_writeback() will assert.

Fix this by checking to see whether the page in question is actually undergoing writeback before ending that writeback.

(2) The loop that scans for pages to kill doesn't increase the first page index, and so the loop may not terminate, but it will try to process the same pages over and over again.

Fix this by increasing the first page index to one after the last page we processed.

Signed-off-by: David Howells dhowells@redhat.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- fs/afs/write.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/fs/afs/write.c b/fs/afs/write.c index d89595155ec9..5cfc05ca184c 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -299,10 +299,14 @@ static void afs_kill_pages(struct afs_vnode *vnode, bool error, ASSERTCMP(pv.nr, ==, count);

for (loop = 0; loop < count; loop++) { - ClearPageUptodate(pv.pages[loop]); + struct page *page = pv.pages[loop]; + ClearPageUptodate(page); if (error) - SetPageError(pv.pages[loop]); - end_page_writeback(pv.pages[loop]); + SetPageError(page); + if (PageWriteback(page)) + end_page_writeback(page); + if (page->index >= first) + first = page->index + 1; }

__pagevec_release(&pv);

From: Jack Morgenstein jackm@dev.mellanox.co.il

[ Upstream commit 4cbe4dac82e423ecc9a0ba46af24a860853259f4 ]

Some Hypervisors detach VFs from VMs by instantly causing an FLR event to be generated for a VF.

In the mlx4 case, this will cause that VF's comm channel to be disabled before the VM has an opportunity to invoke the VF device's "shutdown" method.

For such Hypervisors, there is a race condition between the VF's shutdown method and its internal-error detection/reset thread.

The internal-error detection/reset thread (which runs every 5 seconds) also detects a disabled comm channel. If the internal-error detection/reset flow wins the race, we still get delays (while that flow tries repeatedly to detect comm-channel recovery).

The cited commit fixed the command timeout problem when the internal-error detection/reset flow loses the race.

This commit avoids the unneeded delays when the internal-error detection/reset flow wins.

Fixes: d585df1c5ccf ("net/mlx4_core: Avoid command timeouts during VF driver device shutdown") Signed-off-by: Jack Morgenstein jackm@dev.mellanox.co.il Reported-by: Simon Xiao sixiao@microsoft.com Signed-off-by: Tariq Toukan tariqt@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/net/ethernet/mellanox/mlx4/cmd.c | 11 +++++++++++ drivers/net/ethernet/mellanox/mlx4/main.c | 11 +++++++++++ include/linux/mlx4/device.h | 1 + 3 files changed, 23 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index d48d5793407d..fc222df47aa9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -2278,6 +2278,17 @@ static int sync_toggles(struct mlx4_dev *dev) rd_toggle = swab32(readl(&priv->mfunc.comm->slave_read)); if (wr_toggle == 0xffffffff || rd_toggle == 0xffffffff) { /* PCI might be offline */ + + /* If device removal has been requested, + * do not continue retrying. + */ + if (dev->persist->interface_state & + MLX4_INTERFACE_STATE_NOWAIT) { + mlx4_warn(dev, + "communication channel is offline\n"); + return -EIO; + } + msleep(100); wr_toggle = swab32(readl(&priv->mfunc.comm-> slave_write)); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 99361352ed0d..a7d3144c2388 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -1763,6 +1763,14 @@ static int mlx4_comm_check_offline(struct mlx4_dev *dev) (u32)(1 << COMM_CHAN_OFFLINE_OFFSET)); if (!offline_bit) return 0; + + /* If device removal has been requested, + * do not continue retrying. + */ + if (dev->persist->interface_state & + MLX4_INTERFACE_STATE_NOWAIT) + break; + /* There are cases as part of AER/Reset flow that PF needs * around 100 msec to load. We therefore sleep for 100 msec * to allow other tasks to make use of that CPU during this @@ -3690,6 +3698,9 @@ static void mlx4_remove_one(struct pci_dev *pdev) struct mlx4_priv *priv = mlx4_priv(dev); int active_vfs = 0;

+ if (mlx4_is_slave(dev)) + persist->interface_state |= MLX4_INTERFACE_STATE_NOWAIT; + mutex_lock(&persist->interface_state_mutex); persist->interface_state |= MLX4_INTERFACE_STATE_DELETION; mutex_unlock(&persist->interface_state_mutex); diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index d3133be12d92..7fde8af9b87e 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -460,6 +460,7 @@ enum { enum { MLX4_INTERFACE_STATE_UP = 1 << 0, MLX4_INTERFACE_STATE_DELETION = 1 << 1, + MLX4_INTERFACE_STATE_NOWAIT = 1 << 2, };

#define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \

From: Zygo Blaxell ce3g8jdj@umail.furryterror.org

[ Upstream commit e1699d2d7bf6e6cce3e1baff19f9dd4595a58664 ]

This is a story about 4 distinct (and very old) btrfs bugs.

Commit c8b978188c ("Btrfs: Add zlib compression support") added three data corruption bugs for inline extents (bugs #1-3).

Commit 93c82d5750 ("Btrfs: zero page past end of inline file items") fixed bug #1: uncompressed inline extents followed by a hole and more extents could get non-zero data in the hole as they were read. The fix was to add a memset in btrfs_get_extent to zero out the hole.

Commit 166ae5a418 ("btrfs: fix inline compressed read err corruption") fixed bug #2: compressed inline extents which contained non-zero bytes might be replaced with zero bytes in some cases. This patch removed an unhelpful memset from uncompress_inline, but the case where memset is required was missed.

There is also a memset in the decompression code, but this only covers decompressed data that is shorter than the ram_bytes from the extent ref record. This memset doesn't cover the region between the end of the decompressed data and the end of the page. It has also moved around a few times over the years, so there's no single patch to refer to.

This patch fixes bug #3: compressed inline extents followed by a hole and more extents could get non-zero data in the hole as they were read (i.e. bug #3 is the same as bug #1, but s/uncompressed/compressed/). The fix is the same: zero out the hole in the compressed case too, by putting a memset back in uncompress_inline, but this time with correct parameters.

The last and oldest bug, bug #0, is the cause of the offending inline extent/hole/extent pattern. Bug #0 is a subtle and mostly-harmless quirk of behavior somewhere in the btrfs write code. In a few special cases, an inline extent and hole are allowed to persist where they normally would be combined with later extents in the file.

A fast reproducer for bug #0 is presented below. A few offending extents are also created in the wild during large rsync transfers with the -S flag. A Linux kernel build (git checkout; make allyesconfig; make -j8) will produce a handful of offending files as well. Once an offending file is created, it can present different content to userspace each time it is read.

Bug #0 is at least 4 and possibly 8 years old. I verified every vX.Y kernel back to v3.5 has this behavior. There are fossil records of this bug's effects in commits all the way back to v2.6.32. I have no reason to believe bug #0 wasn't present at the beginning of btrfs compression support in v2.6.29, but I can't easily test kernels that old to be sure.

It is not clear whether bug #0 is worth fixing. A fix would likely require injecting extra reads into currently write-only paths, and most of the exceptional cases caused by bug #0 are already handled now.

Whether we like them or not, bug #0's inline extents followed by holes are part of the btrfs de-facto disk format now, and we need to be able to read them without data corruption or an infoleak. So enough about bug #0, let's get back to bug #3 (this patch).

An example of on-disk structure leading to data corruption found in the wild:

item 61 key (606890 INODE_ITEM 0) itemoff 9662 itemsize 160 inode generation 50 transid 50 size 47424 nbytes 49141 block group 0 mode 100644 links 1 uid 0 gid 0 rdev 0 flags 0x0(none) item 62 key (606890 INODE_REF 603050) itemoff 9642 itemsize 20 inode ref index 3 namelen 10 name: DB_File.so item 63 key (606890 EXTENT_DATA 0) itemoff 8280 itemsize 1362 inline extent data size 1341 ram 4085 compress(zlib) item 64 key (606890 EXTENT_DATA 4096) itemoff 8227 itemsize 53 extent data disk byte 5367308288 nr 20480 extent data offset 0 nr 45056 ram 45056 extent compression(zlib)

Different data appears in userspace during each read of the 11 bytes between 4085 and 4096. The extent in item 63 is not long enough to fill the first page of the file, so a memset is required to fill the space between item 63 (ending at 4085) and item 64 (beginning at 4096) with zero.

Here is a reproducer from Liu Bo, which demonstrates another method of creating the same inline extent and hole pattern:

Using 'page_poison=on' kernel command line (or enable CONFIG_PAGE_POISONING) run the following:

# touch foo # chattr +c foo # xfs_io -f -c "pwrite -W 0 1000" foo # xfs_io -f -c "falloc 4 8188" foo # od -x foo # echo 3 >/proc/sys/vm/drop_caches # od -x foo

This produce the following on my box:

Correct output: file contains 1000 data bytes followed by zeros:

0000000 cdcd cdcd cdcd cdcd cdcd cdcd cdcd cdcd * 0001740 cdcd cdcd cdcd cdcd 0000 0000 0000 0000 0001760 0000 0000 0000 0000 0000 0000 0000 0000 * 0020000

Actual output: the data after the first 1000 bytes will be different each run:

0000000 cdcd cdcd cdcd cdcd cdcd cdcd cdcd cdcd * 0001740 cdcd cdcd cdcd cdcd 6c63 7400 635f 006d 0001760 5f74 6f43 7400 435f 0053 5f74 7363 7400 0002000 435f 0056 5f74 6164 7400 645f 0062 5f74 (...)

Signed-off-by: Zygo Blaxell ce3g8jdj@umail.furryterror.org Reviewed-by: Liu Bo bo.li.liu@oracle.com Reviewed-by: Chris Mason clm@fb.com Signed-off-by: Chris Mason clm@fb.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- fs/btrfs/inode.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index bebd6517355d..af1da85da509 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6735,6 +6735,20 @@ static noinline int uncompress_inline(struct btrfs_path *path, max_size = min_t(unsigned long, PAGE_CACHE_SIZE, max_size); ret = btrfs_decompress(compress_type, tmp, page, extent_offset, inline_size, max_size); + + /* + * decompression code contains a memset to fill in any space between the end + * of the uncompressed data and the end of max_size in case the decompressed + * data ends up shorter than ram_bytes. That doesn't cover the hole between + * the end of an inline extent and the beginning of the next block, so we + * cover that region here. + */ + + if (max_size + pg_offset < PAGE_SIZE) { + char *map = kmap(page); + memset(map + pg_offset + max_size, 0, PAGE_SIZE - max_size - pg_offset); + kunmap(page); + } kfree(tmp); return ret; }

From: Mike Christie mchristi@redhat.com

[ Upstream commit 207ee84133c00a8a2a5bdec94df4a5b37d78881c ]

If tcmu-runner is processing a STPG and needs to change the kernel's ALUA state then we cannot use the same work queue for task management requests and ALUA transitions, because we could deadlock. The problem occurs when a STPG times out before tcmu-runner is able to call into target_tg_pt_gp_alua_access_state_store-> core_alua_do_port_transition -> core_alua_do_transition_tg_pt -> queue_work. In this case, the tmr is on the work queue waiting for the STPG to complete, but the STPG transition is now queued behind the waiting tmr.

Note: This bug will also be fixed by this patch: http://www.spinics.net/lists/target-devel/msg14560.html which switches the tmr code to use the system workqueues.

For both, I am not sure if we need a dedicated workqueue since it is not a performance path and I do not think we need WQ_MEM_RECLAIM to make forward progress to free up memory like the block layer does.

Signed-off-by: Mike Christie mchristi@redhat.com Signed-off-by: Nicholas Bellinger nab@linux-iscsi.org Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/target/target_core_alua.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c index 49aba4a31747..3dad73448ea5 100644 --- a/drivers/target/target_core_alua.c +++ b/drivers/target/target_core_alua.c @@ -1118,13 +1118,11 @@ static int core_alua_do_transition_tg_pt( unsigned long transition_tmo;

transition_tmo = tg_pt_gp->tg_pt_gp_implicit_trans_secs * HZ; - queue_delayed_work(tg_pt_gp->tg_pt_gp_dev->tmr_wq, - &tg_pt_gp->tg_pt_gp_transition_work, - transition_tmo); + schedule_delayed_work(&tg_pt_gp->tg_pt_gp_transition_work, + transition_tmo); } else { tg_pt_gp->tg_pt_gp_transition_complete = &wait; - queue_delayed_work(tg_pt_gp->tg_pt_gp_dev->tmr_wq, - &tg_pt_gp->tg_pt_gp_transition_work, 0); + schedule_delayed_work(&tg_pt_gp->tg_pt_gp_transition_work, 0); wait_for_completion(&wait); tg_pt_gp->tg_pt_gp_transition_complete = NULL; }

From: Robert Stonehouse rstonehouse@solarflare.com

[ Upstream commit cbad52e92ad7f01f0be4ca58bde59462dc1afe3a ]

Fixes: 535a61777f44e ("sfc: suppress handled MCDI failures when changing the MAC address") Signed-off-by: Bert Kenward bkenward@solarflare.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/net/ethernet/sfc/ef10.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index cbe9a330117a..063aca17e698 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -4307,7 +4307,7 @@ static int efx_ef10_set_mac_address(struct efx_nic *efx) * MCFW do not support VFs. */ rc = efx_ef10_vport_set_mac_address(efx); - } else { + } else if (rc) { efx_mcdi_display_error(efx, MC_CMD_VADAPTOR_SET_MAC, sizeof(inbuf), NULL, 0, rc); }

From: Ladislav Michl ladis@linux-mips.org

[ Upstream commit c98769475575c8a585f5b3952f4b5f90266f699b ]

While usb_control_msg function expects timeout in miliseconds, a value of HZ is used. Replace it with USB_CTRL_GET_TIMEOUT and also fix error message which looks like: udlfb: Read EDID byte 78 failed err ffffff92 as error is either negative errno or number of bytes transferred use %d format specifier.

Returned EDID is in second byte, so return error when less than two bytes are received.

Fixes: 18dffdf8913a ("staging: udlfb: enhance EDID and mode handling support") Signed-off-by: Ladislav Michl ladis@linux-mips.org Cc: Bernie Thompson bernie@plugable.com Signed-off-by: Bartlomiej Zolnierkiewicz b.zolnierkie@samsung.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/video/fbdev/udlfb.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/video/fbdev/udlfb.c b/drivers/video/fbdev/udlfb.c index e9c2f7ba3c8e..53326badfb61 100644 --- a/drivers/video/fbdev/udlfb.c +++ b/drivers/video/fbdev/udlfb.c @@ -769,11 +769,11 @@ static int dlfb_get_edid(struct dlfb_data *dev, char *edid, int len)

for (i = 0; i < len; i++) { ret = usb_control_msg(dev->udev, - usb_rcvctrlpipe(dev->udev, 0), (0x02), - (0x80 | (0x02 << 5)), i << 8, 0xA1, rbuf, 2, - HZ); - if (ret < 1) { - pr_err("Read EDID byte %d failed err %x\n", i, ret); + usb_rcvctrlpipe(dev->udev, 0), 0x02, + (0x80 | (0x02 << 5)), i << 8, 0xA1, + rbuf, 2, USB_CTRL_GET_TIMEOUT); + if (ret < 2) { + pr_err("Read EDID byte %d failed: %d\n", i, ret); i--; break; }

From: Christophe JAILLET christophe.jaillet@wanadoo.fr

[ Upstream commit 451f130602619a17c8883dd0b71b11624faffd51 ]

We should go through the error handling code instead of returning -ENOMEM directly.

Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr Cc: Tejun Heo tj@kernel.org Signed-off-by: Bartlomiej Zolnierkiewicz b.zolnierkie@samsung.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/video/fbdev/au1200fb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/video/fbdev/au1200fb.c b/drivers/video/fbdev/au1200fb.c index f9507b1894df..e5897fce3c03 100644 --- a/drivers/video/fbdev/au1200fb.c +++ b/drivers/video/fbdev/au1200fb.c @@ -1699,7 +1699,8 @@ static int au1200fb_drv_probe(struct platform_device *dev) if (!fbdev->fb_mem) { print_err("fail to allocate frambuffer (size: %dK))", fbdev->fb_len / 1024); - return -ENOMEM; + ret = -ENOMEM; + goto failed; }

/*

From: Philipp Zabel p.zabel@pengutronix.de

[ Upstream commit a3350f9c57ffad569c40f7320b89da1f3061c5bb ]

The pcf8563_clkout_recalc_rate function erroneously ignores the frequency index read from the CLKO register and always returns 32768 Hz.

Fixes: a39a6405d5f9 ("rtc: pcf8563: add CLKOUT to common clock framework") Signed-off-by: Philipp Zabel p.zabel@pengutronix.de Signed-off-by: Alexandre Belloni alexandre.belloni@free-electrons.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/rtc/rtc-pcf8563.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-pcf8563.c b/drivers/rtc/rtc-pcf8563.c index c8f95b8e463a..45b5a3d47ccf 100644 --- a/drivers/rtc/rtc-pcf8563.c +++ b/drivers/rtc/rtc-pcf8563.c @@ -427,7 +427,7 @@ static unsigned long pcf8563_clkout_recalc_rate(struct clk_hw *hw, return 0;

buf &= PCF8563_REG_CLKO_F_MASK; - return clkout_rates[ret]; + return clkout_rates[buf]; }

static long pcf8563_clkout_round_rate(struct clk_hw *hw, unsigned long rate,

From: Peter Ujfalusi peter.ujfalusi@ti.com

[ Upstream commit 288e7560e4d3e259aa28f8f58a8dfe63627a1bf6 ]

The used 0x1f mask is only valid for am335x family of SoC, different family using this type of crossbar might have different number of electable events. In case of am43xx family 0x3f mask should have been used for example. Instead of trying to handle each family's mask, just use u8 type to store the mux value since the event offsets are aligned to byte offset.

Fixes: 42dbdcc6bf965 ("dmaengine: ti-dma-crossbar: Add support for crossbar on AM33xx/AM43xx") Signed-off-by: Peter Ujfalusi peter.ujfalusi@ti.com Signed-off-by: Vinod Koul vinod.koul@intel.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/dma/ti-dma-crossbar.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/dma/ti-dma-crossbar.c b/drivers/dma/ti-dma-crossbar.c index 149ec2bd9bc6..8100ede095d5 100644 --- a/drivers/dma/ti-dma-crossbar.c +++ b/drivers/dma/ti-dma-crossbar.c @@ -46,12 +46,12 @@ struct ti_am335x_xbar_data {

struct ti_am335x_xbar_map { u16 dma_line; - u16 mux_val; + u8 mux_val; };

-static inline void ti_am335x_xbar_write(void __iomem *iomem, int event, u16 val) +static inline void ti_am335x_xbar_write(void __iomem *iomem, int event, u8 val) { - writeb_relaxed(val & 0x1f, iomem + event); + writeb_relaxed(val, iomem + event); }

static void ti_am335x_xbar_free(struct device *dev, void *route_data) @@ -102,7 +102,7 @@ static void *ti_am335x_xbar_route_allocate(struct of_phandle_args *dma_spec, }

map->dma_line = (u16)dma_spec->args[0]; - map->mux_val = (u16)dma_spec->args[2]; + map->mux_val = (u8)dma_spec->args[2];

dma_spec->args[2] = 0; dma_spec->args_count = 2;

From: KUWAZAWA Takuya albatross0@gmail.com

[ Upstream commit c5504f724c86ee925e7ffb80aa342cfd57959b13 ]

Information about ipvs in different network namespace can be seen via procfs.

How to reproduce:

# ip netns add ns01 # ip netns add ns02 # ip netns exec ns01 ip a add dev lo 127.0.0.1/8 # ip netns exec ns02 ip a add dev lo 127.0.0.1/8 # ip netns exec ns01 ipvsadm -A -t 10.1.1.1:80 # ip netns exec ns02 ipvsadm -A -t 10.1.1.2:80

The ipvsadm displays information about its own network namespace only.

# ip netns exec ns01 ipvsadm -Ln IP Virtual Server version 1.2.1 (size=4096) Prot LocalAddress:Port Scheduler Flags -> RemoteAddress:Port Forward Weight ActiveConn InActConn TCP 10.1.1.1:80 wlc

# ip netns exec ns02 ipvsadm -Ln IP Virtual Server version 1.2.1 (size=4096) Prot LocalAddress:Port Scheduler Flags -> RemoteAddress:Port Forward Weight ActiveConn InActConn TCP 10.1.1.2:80 wlc

But I can see information about other network namespace via procfs.

# ip netns exec ns01 cat /proc/net/ip_vs IP Virtual Server version 1.2.1 (size=4096) Prot LocalAddress:Port Scheduler Flags -> RemoteAddress:Port Forward Weight ActiveConn InActConn TCP 0A010101:0050 wlc TCP 0A010102:0050 wlc

# ip netns exec ns02 cat /proc/net/ip_vs IP Virtual Server version 1.2.1 (size=4096) Prot LocalAddress:Port Scheduler Flags -> RemoteAddress:Port Forward Weight ActiveConn InActConn TCP 0A010102:0050 wlc

Signed-off-by: KUWAZAWA Takuya albatross0@gmail.com Acked-by: Julian Anastasov ja@ssi.bg Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin alexander.levin@verizon.com --- net/netfilter/ipvs/ip_vs_ctl.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index e7c1b052c2a3..2c937c16dc27 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1999,12 +1999,16 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v) seq_puts(seq, " -> RemoteAddress:Port Forward Weight ActiveConn InActConn\n"); } else { + struct net *net = seq_file_net(seq); + struct netns_ipvs *ipvs = net_ipvs(net); const struct ip_vs_service *svc = v; const struct ip_vs_iter *iter = seq->private; const struct ip_vs_dest *dest; struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler); char *sched_name = sched ? sched->name : "none";

+ if (svc->ipvs != ipvs) + return 0; if (iter->table == ip_vs_svc_table) { #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6)

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

[ Upstream commit 6b148a7ce72a7f87c81cbcde48af014abc0516a9 ]

IPIC Status is provided by register IPIC_SERSR and not by IPIC_SERMR which is the mask register.

Signed-off-by: Christophe Leroy christophe.leroy@c-s.fr Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Sasha Levin alexander.levin@verizon.com --- arch/powerpc/sysdev/ipic.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c index f76ee39cb337..800a591695c0 100644 --- a/arch/powerpc/sysdev/ipic.c +++ b/arch/powerpc/sysdev/ipic.c @@ -845,12 +845,12 @@ void ipic_disable_mcp(enum ipic_mcp_irq mcp_irq)

u32 ipic_get_mcp_status(void) { - return ipic_read(primary_ipic->regs, IPIC_SERMR); + return ipic_read(primary_ipic->regs, IPIC_SERSR); }

void ipic_clear_mcp_status(u32 mask) { - ipic_write(primary_ipic->regs, IPIC_SERMR, mask); + ipic_write(primary_ipic->regs, IPIC_SERSR, mask); }

/* Return an interrupt vector or NO_IRQ if no interrupt is pending. */

From: Markus Elfring elfring@users.sourceforge.net

[ Upstream commit f6c8a317ab208aee223776327c06f23342492d54 ]

Source code review for a specific software refactoring showed the need for another correction because the error code "-1" was returned so far if a call of the function "sony_call_snc_handle" failed here. Thus assign the return value from these two function calls also to the variable "err" and provide it in case of a failure.

Fixes: d6f15ed876b83a1a0eba1d0473eef58acc95444a ("sony-laptop: use soft rfkill status stored in hw") Suggested-by: Andy Shevchenko andy.shevchenko@gmail.com Link: https://lkml.org/lkml/2017/10/31/463 Link: https://lkml.kernel.org/r/CAHp75VcMkXCioCzmLE0+BTmkqc5RSOx9yPO0ectVHMrMvewgwg@mail.gmail.com Signed-off-by: Markus Elfring elfring@users.sourceforge.net Signed-off-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/platform/x86/sony-laptop.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c index f73c29558cd3..1e12cd55a4a9 100644 --- a/drivers/platform/x86/sony-laptop.c +++ b/drivers/platform/x86/sony-laptop.c @@ -1655,17 +1655,19 @@ static int sony_nc_setup_rfkill(struct acpi_device *device, if (!rfk) return -ENOMEM;

- if (sony_call_snc_handle(sony_rfkill_handle, 0x200, &result) < 0) { + err = sony_call_snc_handle(sony_rfkill_handle, 0x200, &result); + if (err < 0) { rfkill_destroy(rfk); - return -1; + return err; } hwblock = !(result & 0x1);

- if (sony_call_snc_handle(sony_rfkill_handle, - sony_rfkill_address[nc_type], - &result) < 0) { + err = sony_call_snc_handle(sony_rfkill_handle, + sony_rfkill_address[nc_type], + &result); + if (err < 0) { rfkill_destroy(rfk); - return -1; + return err; } swblock = !(result & 0x2);

From: tangwenji tang.wenji@zte.com.cn

[ Upstream commit 24528f089d0a444070aa4f715ace537e8d6bf168 ]

When is pr_reg->isid_present_at_reg is false,this function should return.

This fixes a regression originally introduced by:

commit d2843c173ee53cf4c12e7dfedc069a5bc76f0ac5 Author: Andy Grover agrover@redhat.com Date: Thu May 16 10:40:55 2013 -0700

target: Alter core_pr_dump_initiator_port for ease of use

Signed-off-by: tangwenji tang.wenji@zte.com.cn Signed-off-by: Nicholas Bellinger nab@linux-iscsi.org Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/target/target_core_pr.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index e7933115087a..e38b4582d43e 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -56,8 +56,10 @@ void core_pr_dump_initiator_port( char *buf, u32 size) { - if (!pr_reg->isid_present_at_reg) + if (!pr_reg->isid_present_at_reg) { buf[0] = '\0'; + return; + }

snprintf(buf, size, ",i,0x%s", pr_reg->pr_reg_isid); }

From: Jiang Yi jiangyilism@gmail.com

[ Upstream commit 594e25e73440863981032d76c9b1e33409ceff6e ]

The function fd_execute_unmap() in target_core_file.c calles

ret = file->f_op->fallocate(file, mode, pos, len);

Some filesystems implement fallocate() to return error if length is zero (e.g. btrfs) but according to SCSI Block Commands spec UNMAP should return success for zero length.

Signed-off-by: Jiang Yi jiangyilism@gmail.com Signed-off-by: Nicholas Bellinger nab@linux-iscsi.org Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/target/target_core_file.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index 041a56987845..2e35db7f4aac 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -466,6 +466,10 @@ fd_execute_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb) struct inode *inode = file->f_mapping->host; int ret;

+ if (!nolb) { + return 0; + } + if (cmd->se_dev->dev_attrib.pi_prot_type) { ret = fd_do_prot_unmap(cmd, lba, nolb); if (ret)

From: Robert Baronescu robert.baronescu@nxp.com

[ Upstream commit 7aacbfcb331ceff3ac43096d563a1f93ed46e35e ]

Fix the way the length of the buffers used for encryption / decryption are computed. For e.g. in case of encryption, input buffer does not contain an authentication tag.

Signed-off-by: Robert Baronescu robert.baronescu@nxp.com Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Sasha Levin alexander.levin@verizon.com --- crypto/tcrypt.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c index 46a4a757d478..f522828d45c9 100644 --- a/crypto/tcrypt.c +++ b/crypto/tcrypt.c @@ -410,7 +410,7 @@ static void test_aead_speed(const char *algo, int enc, unsigned int secs, }

sg_init_aead(sg, xbuf, - *b_size + (enc ? authsize : 0)); + *b_size + (enc ? 0 : authsize));

sg_init_aead(sgout, xoutbuf, *b_size + (enc ? authsize : 0)); @@ -418,7 +418,9 @@ static void test_aead_speed(const char *algo, int enc, unsigned int secs, sg_set_buf(&sg[0], assoc, aad_size); sg_set_buf(&sgout[0], assoc, aad_size);

- aead_request_set_crypt(req, sg, sgout, *b_size, iv); + aead_request_set_crypt(req, sg, sgout, + *b_size + (enc ? 0 : authsize), + iv); aead_request_set_ad(req, aad_size);

if (secs)

From: Jan Kara jack@suse.cz

[ Upstream commit 592e254502041f953e84d091eae2c68cba04c10b ]

_calc_vm_trans() does not handle the situation when some of the passed flags are 0 (which can happen if these VM flags do not make sense for the architecture). Improve the _calc_vm_trans() macro to return 0 in such situation. Since all passed flags are constant, this does not add any runtime overhead.

Signed-off-by: Jan Kara jack@suse.cz Signed-off-by: Dan Williams dan.j.williams@intel.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- include/linux/mman.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/mman.h b/include/linux/mman.h index 16373c8f5f57..369bc3405a6d 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -63,8 +63,9 @@ static inline int arch_validate_prot(unsigned long prot) * ("bit1" and "bit2" must be single bits) */ #define _calc_vm_trans(x, bit1, bit2) \ + ((!(bit1) || !(bit2)) ? 0 : \ ((bit1) <= (bit2) ? ((x) & (bit1)) * ((bit2) / (bit1)) \ - : ((x) & (bit1)) / ((bit1) / (bit2))) + : ((x) & (bit1)) / ((bit1) / (bit2))))

/* * Combine the mmap "prot" argument into "vm_flags" used internally.

From: Daniel Lezcano daniel.lezcano@linaro.org

[ Upstream commit 07209fcf33542c1ff1e29df2dbdf8f29cdaacb10 ]

There is a particular situation when the cooling device is cpufreq and the heat dissipation is not efficient enough where the temperature increases little by little until reaching the critical threshold and leading to a SoC reset.

The behavior is reproducible on a hikey6220 with bad heat dissipation (eg. stacked with other boards).

Running a simple C program doing while(1); for each CPU of the SoC makes the temperature to reach the passive regulation trip point and ends up to the maximum allowed temperature followed by a reset.

This issue has been also reported by running the libhugetlbfs test suite.

What is observed is a ping pong between two cpu frequencies, 1.2GHz and 900MHz while the temperature continues to grow.

It appears the step wise governor calls get_target_state() the first time with the throttle set to true and the trend to 'raising'. The code selects logically the next state, so the cpu frequency decreases from 1.2GHz to 900MHz, so far so good. The temperature decreases immediately but still stays greater than the trip point, then get_target_state() is called again, this time with the throttle set to true *and* the trend to 'dropping'. From there the algorithm assumes we have to step down the state and the cpu frequency jumps back to 1.2GHz. But the temperature is still higher than the trip point, so get_target_state() is called with throttle=1 and trend='raising' again, we jump to 900MHz, then get_target_state() is called with throttle=1 and trend='dropping', we jump to 1.2GHz, etc ... but the temperature does not stabilizes and continues to increase.

[ 237.922654] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=1,throttle=1 [ 237.922678] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=1,throttle=1 [ 237.922690] thermal cooling_device0: cur_state=0 [ 237.922701] thermal cooling_device0: old_target=0, target=1 [ 238.026656] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=2,throttle=1 [ 238.026680] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=2,throttle=1 [ 238.026694] thermal cooling_device0: cur_state=1 [ 238.026707] thermal cooling_device0: old_target=1, target=0 [ 238.134647] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=1,throttle=1 [ 238.134667] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=1,throttle=1 [ 238.134679] thermal cooling_device0: cur_state=0 [ 238.134690] thermal cooling_device0: old_target=0, target=1

In this situation the temperature continues to increase while the trend is oscillating between 'dropping' and 'raising'. We need to keep the current state untouched if the throttle is set, so the temperature can decrease or a higher state could be selected, thus preventing this oscillation.

Keeping the next_target untouched when 'throttle' is true at 'dropping' time fixes the issue.

The following traces show the governor does not change the next state if trend==2 (dropping) and throttle==1.

[ 2306.127987] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=1,throttle=1 [ 2306.128009] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=1,throttle=1 [ 2306.128021] thermal cooling_device0: cur_state=0 [ 2306.128031] thermal cooling_device0: old_target=0, target=1 [ 2306.231991] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=2,throttle=1 [ 2306.232016] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=2,throttle=1 [ 2306.232030] thermal cooling_device0: cur_state=1 [ 2306.232042] thermal cooling_device0: old_target=1, target=1 [ 2306.335982] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=0,throttle=1 [ 2306.336006] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=0,throttle=1 [ 2306.336021] thermal cooling_device0: cur_state=1 [ 2306.336034] thermal cooling_device0: old_target=1, target=1 [ 2306.439984] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=2,throttle=1 [ 2306.440008] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=2,throttle=0 [ 2306.440022] thermal cooling_device0: cur_state=1 [ 2306.440034] thermal cooling_device0: old_target=1, target=0

[ ... ]

After a while, if the temperature continues to increase, the next state becomes 2 which is 720MHz on the hikey. That results in the temperature stabilizing around the trip point.

[ 2455.831982] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=1,throttle=1 [ 2455.832006] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=1,throttle=0 [ 2455.832019] thermal cooling_device0: cur_state=1 [ 2455.832032] thermal cooling_device0: old_target=1, target=1 [ 2455.935985] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=0,throttle=1 [ 2455.936013] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=0,throttle=0 [ 2455.936027] thermal cooling_device0: cur_state=1 [ 2455.936040] thermal cooling_device0: old_target=1, target=1 [ 2456.043984] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=0,throttle=1 [ 2456.044009] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=0,throttle=0 [ 2456.044023] thermal cooling_device0: cur_state=1 [ 2456.044036] thermal cooling_device0: old_target=1, target=1 [ 2456.148001] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=1,throttle=1 [ 2456.148028] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=1,throttle=1 [ 2456.148042] thermal cooling_device0: cur_state=1 [ 2456.148055] thermal cooling_device0: old_target=1, target=2 [ 2456.252009] thermal thermal_zone0: Trip0[type=1,temp=65000]:trend=2,throttle=1 [ 2456.252041] thermal thermal_zone0: Trip1[type=1,temp=75000]:trend=2,throttle=0 [ 2456.252058] thermal cooling_device0: cur_state=2 [ 2456.252075] thermal cooling_device0: old_target=2, target=1

IOW, this change is needed to keep the state for a cooling device if the temperature trend is oscillating while the temperature increases slightly.

Without this change, the situation above leads to a catastrophic crash by a hardware reset on hikey. This issue has been reported to happen on an OMAP dra7xx also.

Signed-off-by: Daniel Lezcano daniel.lezcano@linaro.org Cc: Keerthy j-keerthy@ti.com Cc: John Stultz john.stultz@linaro.org Cc: Leo Yan leo.yan@linaro.org Tested-by: Keerthy j-keerthy@ti.com Reviewed-by: Keerthy j-keerthy@ti.com Signed-off-by: Eduardo Valentin edubezval@gmail.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/thermal/step_wise.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/thermal/step_wise.c b/drivers/thermal/step_wise.c index ea9366ad3e6b..7814d18e8940 100644 --- a/drivers/thermal/step_wise.c +++ b/drivers/thermal/step_wise.c @@ -31,8 +31,7 @@ * If the temperature is higher than a trip point, * a. if the trend is THERMAL_TREND_RAISING, use higher cooling * state for this trip point - * b. if the trend is THERMAL_TREND_DROPPING, use lower cooling - * state for this trip point + * b. if the trend is THERMAL_TREND_DROPPING, do nothing * c. if the trend is THERMAL_TREND_RAISE_FULL, use upper limit * for this trip point * d. if the trend is THERMAL_TREND_DROP_FULL, use lower limit @@ -94,9 +93,11 @@ static unsigned long get_target_state(struct thermal_instance *instance, if (!throttle) next_target = THERMAL_NO_TARGET; } else { - next_target = cur_state - 1; - if (next_target > instance->upper) - next_target = instance->upper; + if (!throttle) { + next_target = cur_state - 1; + if (next_target > instance->upper) + next_target = instance->upper; + } } break; case THERMAL_TREND_DROP_FULL:

From: Bob Peterson rpeterso@redhat.com

[ Upstream commit cc555b09d8c3817aeebda43a14ab67049a5653f7 ]

This patch fixes a deadlock caused when the jdata flag is set for inodes that are already on the ordered write list. Since it is on the ordered write list, log_flush calls gfs2_ordered_write which calls filemap_fdatawrite. But since the inode had the jdata flag set, that calls gfs2_jdata_writepages, which tries to start a new transaction. A new transaction cannot be started because it tries to acquire the log_flush rwsem which is already locked by the log flush operation.

The bottom line is: We cannot switch an inode from ordered to jdata until we eliminate any ordered data pages (via log flush) or any log_flush operation afterward will create the circular dependency above. So we need to flush the log before setting the diskflags to switch the file mode, then we need to remove the inode from the ordered writes list.

Before this patch, the log flush was done for jdata->ordered, but that's wrong. If we're going from jdata to ordered, we don't need to call gfs2_log_flush because the call to filemap_fdatawrite will do it for us:

filemap_fdatawrite() -> __filemap_fdatawrite_range() __filemap_fdatawrite_range() -> do_writepages() do_writepages() -> gfs2_jdata_writepages() gfs2_jdata_writepages() -> gfs2_log_flush()

This patch modifies function do_gfs2_set_flags so that if a file has its jdata flag set, and it's already on the ordered write list, the log will be flushed and it will be removed from the list before setting the flag.

Signed-off-by: Bob Peterson rpeterso@redhat.com Signed-off-by: Andreas Gruenbacher agruenba@redhat.com Acked-by: Abhijith Das adas@redhat.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- fs/gfs2/file.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 5e425469f0c2..1543aa1b2a93 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -255,7 +255,7 @@ static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask) goto out; } if ((flags ^ new_flags) & GFS2_DIF_JDATA) { - if (flags & GFS2_DIF_JDATA) + if (new_flags & GFS2_DIF_JDATA) gfs2_log_flush(sdp, ip->i_gl, NORMAL_FLUSH); error = filemap_fdatawrite(inode->i_mapping); if (error) @@ -263,6 +263,8 @@ static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask) error = filemap_fdatawait(inode->i_mapping); if (error) goto out; + if (new_flags & GFS2_DIF_JDATA) + gfs2_ordered_del_inode(ip); } error = gfs2_trans_begin(sdp, RES_DINODE, 0); if (error)

From: Liang Chen liangchen.linux@gmail.com

[ Upstream commit 330a4db89d39a6b43f36da16824eaa7a7509d34d ]

mutex_destroy does nothing most of time, but it's better to call it to make the code future proof and it also has some meaning for like mutex debug.

As Coly pointed out in a previous review, bcache_exit() may not be able to handle all the references properly if userspace registers cache and backing devices right before bch_debug_init runs and bch_debug_init failes later. So not exposing userspace interface until everything is ready to avoid that issue.

Signed-off-by: Liang Chen liangchen.linux@gmail.com Reviewed-by: Michael Lyle mlyle@lyle.org Reviewed-by: Coly Li colyli@suse.de Reviewed-by: Eric Wheeler bcache@linux.ewheeler.net Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/md/bcache/super.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index c5ceea9222ff..8eaadd9869bc 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -2083,6 +2083,7 @@ static void bcache_exit(void) if (bcache_major) unregister_blkdev(bcache_major, "bcache"); unregister_reboot_notifier(&reboot); + mutex_destroy(&bch_register_lock); }

static int __init bcache_init(void) @@ -2101,14 +2102,15 @@ static int __init bcache_init(void) bcache_major = register_blkdev(0, "bcache"); if (bcache_major < 0) { unregister_reboot_notifier(&reboot); + mutex_destroy(&bch_register_lock); return bcache_major; }

if (!(bcache_wq = create_workqueue("bcache")) || !(bcache_kobj = kobject_create_and_add("bcache", fs_kobj)) || - sysfs_create_files(bcache_kobj, files) || bch_request_init() || - bch_debug_init(bcache_kobj)) + bch_debug_init(bcache_kobj) || + sysfs_create_files(bcache_kobj, files)) goto err;

return 0;

From: Martin Wilck mwilck@suse.de

[ Upstream commit 55ca38b4255bb336c2d35990bdb2b368e19b435a ]

I am resubmitting this patch on behalf of Martin Wilck with his permission.

The original patch can be found here: https://www.spinics.net/lists/linux-scsi/msg102083.html

This patch did not help until Hannes's commit 9441284fbc39 ("scsi-fixup-kernel-warning-during-rmmod") was applied to the kernel.

-------------------------------------- Original patch description from Martin: --------------------------------------

When the hpsa module is unloaded using rmmod, dangling symlinks remain under /sys/class/sas_phy. Fix this by calling sas_phy_delete() rather than sas_phy_free (which, according to comments, should not be called for PHYs that have been set up successfully, anyway).

Tested-by: Don Brace don.brace@microsemi.com Reviewed-by: Don Brace don.brace@microsemi.com Signed-off-by: Martin Wilck mwilck@suse.de Signed-off-by: Don Brace don.brace@microsemi.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/scsi/hpsa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 2feab0f93fdd..b37e85126f63 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -9335,9 +9335,9 @@ static void hpsa_free_sas_phy(struct hpsa_sas_phy *hpsa_sas_phy) struct sas_phy *phy = hpsa_sas_phy->phy;

sas_port_delete_phy(hpsa_sas_phy->parent_port->port, phy); - sas_phy_free(phy); if (hpsa_sas_phy->added_to_port) list_del(&hpsa_sas_phy->phy_list_entry); + sas_phy_delete(phy); kfree(hpsa_sas_phy); }

From: Alex Williamson alex.williamson@redhat.com

[ Upstream commit 16b6c8bb687cc3bec914de09061fcb8411951fda ]

When removing a device, for example a VF being removed due to SR-IOV teardown, a "soft" hot-unplug via 'echo 1 > remove' in sysfs, or an actual hot-unplug, we first remove the procfs and sysfs attributes for the device before attempting to release the device from any driver bound to it. Unbinding the driver from the device can take time. The device might need to write out data or it might be actively in use. If it's in use by userspace through a vfio driver, the unbind might block until the user releases the device. This leads to a potentially non-trivial amount of time where the device exists, but we've torn down the interfaces that userspace uses to examine devices, for instance lspci might generate this sort of error:

pcilib: Cannot open /sys/bus/pci/devices/0000:01:0a.3/config lspci: Unable to read the standard configuration space header of device 0000:01:0a.3

We don't seem to have any dependence on this teardown ordering in the kernel, so let's unbind the driver first, which is also more symmetric with the instantiation of the device in pci_bus_add_device().

Signed-off-by: Alex Williamson alex.williamson@redhat.com Signed-off-by: Bjorn Helgaas bhelgaas@google.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/pci/remove.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c index 8a280e9c2ad1..7e67af2bb366 100644 --- a/drivers/pci/remove.c +++ b/drivers/pci/remove.c @@ -20,9 +20,9 @@ static void pci_stop_dev(struct pci_dev *dev) pci_pme_active(dev, false);

if (dev->is_added) { + device_release_driver(&dev->dev); pci_proc_detach_device(dev); pci_remove_sysfs_dev_files(dev); - device_release_driver(&dev->dev); dev->is_added = 0; }

From: Hiroyuki Yokoyama hiroyuki.yokoyama.vx@renesas.com

[ Upstream commit 847449f23dcbff68234525f90dd53c7c7db18cad ]

SYS/RT/Audio DMAC includes independent data buffers for reading and writing. Therefore, the read transfer counter and write transfer counter have different values. TCR indicates read counter, and TCRB indicates write counter. The relationship is like below.

TCR TCRB [SOURCE] -> [DMAC] -> [SINK]

In the MEM_TO_DEV direction, what really matters is how much data has been written to the device. If the DMA is interrupted between read and write, then, the data doesn't end up in the destination, so shouldn't be counted. TCRB is thus the register we should use in this cases.

In the DEV_TO_MEM direction, the situation is more complex. Both the read and write side are important. What matters from a data consumer point of view is how much data has been written to memory. On the other hand, if the transfer is interrupted between read and write, we'll end up losing data. It can also be important to report.

In the MEM_TO_MEM direction, what matters is of course how much data has been written to memory from data consumer point of view. Here, because read and write have independent data buffers, it will take a while for TCR and TCRB to become equal. Thus we should check TCRB in this case, too.

Thus, all cases we should check TCRB instead of TCR.

Without this patch, Sound Capture has noise after PluseAudio support (= 07b7acb51d2 ("ASoC: rsnd: update pointer more accurate")), because the recorder will use wrong residue counter which indicates transferred from sound device, but in reality the data was not yet put to memory and recorder will record it.

Signed-off-by: Hiroyuki Yokoyama hiroyuki.yokoyama.vx@renesas.com [Kuninori: added detail information in log] Signed-off-by: Kuninori Morimoto kuninori.morimoto.gx@renesas.com Reviewed-by: Geert Uytterhoeven geert+renesas@glider.be Reviewed-by: Laurent Pinchart laurent.pinchart@ideasonboard.com Signed-off-by: Vinod Koul vinod.koul@intel.com

Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/dma/sh/rcar-dmac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c index 7820d07e7bee..3e83d02d9ae3 100644 --- a/drivers/dma/sh/rcar-dmac.c +++ b/drivers/dma/sh/rcar-dmac.c @@ -1180,7 +1180,7 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan, }

/* Add the residue for the current chunk. */ - residue += rcar_dmac_chan_read(chan, RCAR_DMATCR) << desc->xfer_shift; + residue += rcar_dmac_chan_read(chan, RCAR_DMATCRB) << desc->xfer_shift;

return residue; }

From: Linus Walleij linus.walleij@linaro.org

[ Upstream commit 1c363531dd814dc4fe10865722bf6b0f72ce4673 ]

The build robot is complaining on Blackfin:

drivers/pinctrl/pinctrl-adi2.c: In function 'port_setup':

...

drivers/pinctrl/pinctrl-adi2.c:221:21: error: dereferencing

pointer to incomplete type 'struct gpio_port_t' writew(readw(&regs->port_fer) & ~BIT(offset), ^~ drivers/pinctrl/pinctrl-adi2.c: In function 'adi_gpio_ack_irq':

...

drivers/pinctrl/pinctrl-adi2.c:266:18: error: dereferencing

pointer to incomplete type 'struct bfin_pint_regs' if (readl(&regs->invert_set) & pintbit) ^~ It seems the driver need to include <asm/gpio.h> and <asm/irq.h> to compile.

The Blackfin architecture was re-defining the Kconfig PINCTRL symbol which is not OK, so replaced this with PINCTRL_BLACKFIN_ADI2 which selects PINCTRL and PINCTRL_ADI2 just like most arches do.

Further, the old GPIO driver symbol GPIO_ADI was possible to select at the same time as selecting PINCTRL. This was not working because the arch-local <asm/gpio.h> header contains an explicit #ifndef PINCTRL clause making compilation break if you combine them. The same is true for DEBUG_MMRS.

Make sure the ADI2 pinctrl driver is not selected at the same time as the old GPIO implementation. (This should be converted to use gpiolib or pincontrol and move to drivers/...) Also make sure the old GPIO_ADI driver or DEBUG_MMRS is not selected at the same time as the new PINCTRL implementation, and only make PINCTRL_ADI2 selectable for the Blackfin families that actually have it.

This way it is still possible to add e.g. I2C-based pin control expanders on the Blackfin.

Cc: Steven Miao realmz6@gmail.com Cc: Huanhuan Feng huanhuan.feng@analog.com Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Sasha Levin alexander.levin@verizon.com --- arch/blackfin/Kconfig | 7 +++++-- arch/blackfin/Kconfig.debug | 1 + drivers/pinctrl/Kconfig | 3 ++- 3 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig index af76634f8d98..934573cc1134 100644 --- a/arch/blackfin/Kconfig +++ b/arch/blackfin/Kconfig @@ -318,11 +318,14 @@ config BF53x

config GPIO_ADI def_bool y + depends on !PINCTRL depends on (BF51x || BF52x || BF53x || BF538 || BF539 || BF561)

-config PINCTRL +config PINCTRL_BLACKFIN_ADI2 def_bool y - depends on BF54x || BF60x + depends on (BF54x || BF60x) + select PINCTRL + select PINCTRL_ADI2

config MEM_MT48LC64M4A2FB_7E bool diff --git a/arch/blackfin/Kconfig.debug b/arch/blackfin/Kconfig.debug index f3337ee03621..a93cf06a4d6f 100644 --- a/arch/blackfin/Kconfig.debug +++ b/arch/blackfin/Kconfig.debug @@ -17,6 +17,7 @@ config DEBUG_VERBOSE

config DEBUG_MMRS tristate "Generate Blackfin MMR tree" + depends on !PINCTRL select DEBUG_FS help Create a tree of Blackfin MMRs via the debugfs tree. If diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig index 312c78b27a32..073b6d1e5efa 100644 --- a/drivers/pinctrl/Kconfig +++ b/drivers/pinctrl/Kconfig @@ -26,7 +26,8 @@ config DEBUG_PINCTRL

config PINCTRL_ADI2 bool "ADI pin controller driver" - depends on BLACKFIN + depends on (BF54x || BF60x) + depends on !GPIO_ADI select PINMUX select IRQ_DOMAIN help

From: Jia-Ju Bai baijiaju1990@163.com

[ Upstream commit 42c8eb3f6e15367981b274cb79ee4657e2c6949d ]

The driver may sleep under a spinlock, and the function call path is: vt6655_suspend (acquire the spinlock) pci_set_power_state __pci_start_power_transition (drivers/pci/pci.c) msleep --> may sleep

To fix it, pci_set_power_state is called without having a spinlock.

This bug is found by my static analysis tool and my code review.

Signed-off-by: Jia-Ju Bai baijiaju1990@163.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/staging/vt6655/device_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c index fefbf826c622..8fd8f3a2d1bf 100644 --- a/drivers/staging/vt6655/device_main.c +++ b/drivers/staging/vt6655/device_main.c @@ -1693,10 +1693,11 @@ static int vt6655_suspend(struct pci_dev *pcid, pm_message_t state) MACbShutdown(priv->PortOffset);

pci_disable_device(pcid); - pci_set_power_state(pcid, pci_choose_state(pcid, state));

spin_unlock_irqrestore(&priv->lock, flags);

+ pci_set_power_state(pcid, pci_choose_state(pcid, state)); + return 0; }

From: Kurt Garloff garloff@suse.de

[ Upstream commit 909cf3e16a5274fe2127cf3cea5c8dba77b2c412 ]

All EMC SYMMETRIX support REPORT_LUNS, even if configured to report SCSI-2 for whatever reason.

Signed-off-by: Kurt Garloff garloff@suse.de Signed-off-by: Hannes Reinecke hare@suse.de Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/scsi/scsi_devinfo.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index 11cdb172cfaf..60720e5b1ebc 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -160,7 +160,7 @@ static struct { {"DGC", "RAID", NULL, BLIST_SPARSELUN}, /* Dell PV 650F, storage on LUN 0 */ {"DGC", "DISK", NULL, BLIST_SPARSELUN}, /* Dell PV 650F, no storage on LUN 0 */ {"EMC", "Invista", "*", BLIST_SPARSELUN | BLIST_LARGELUN}, - {"EMC", "SYMMETRIX", NULL, BLIST_SPARSELUN | BLIST_LARGELUN | BLIST_FORCELUN}, + {"EMC", "SYMMETRIX", NULL, BLIST_SPARSELUN | BLIST_LARGELUN | BLIST_REPORTLUN2}, {"EMULEX", "MD21/S2 ESDI", NULL, BLIST_SINGLELUN}, {"easyRAID", "16P", NULL, BLIST_NOREPORTLUN}, {"easyRAID", "X6P", NULL, BLIST_NOREPORTLUN},

From: weiping zhang zhangweiping@didichuxing.com

[ Upstream commit 658e9a6dc1126f21fa417cd213e1cdbff8be0ba2 ]

/sys/class/scsi_disk/0:2:0:0/allow_restart can be changed to 0 unexpectedly by writing an invalid string such as the following:

echo asdf > /sys/class/scsi_disk/0:2:0:0/allow_restart

Signed-off-by: weiping zhang zhangweiping@didichuxing.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/scsi/sd.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 19bfa7646c2b..dd72205ba298 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -259,6 +259,7 @@ static ssize_t allow_restart_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { + bool v; struct scsi_disk *sdkp = to_scsi_disk(dev); struct scsi_device *sdp = sdkp->device;

@@ -268,7 +269,10 @@ allow_restart_store(struct device *dev, struct device_attribute *attr, if (sdp->type != TYPE_DISK) return -EINVAL;

- sdp->allow_restart = simple_strtoul(buf, NULL, 10); + if (kstrtobool(buf, &v)) + return -EINVAL; + + sdp->allow_restart = v;

return count; }

From: Jan Kara jack@suse.cz

[ Upstream commit abdc0eb06964fe1d2fea6dd1391b734d0590365d ]

When session starts beyond offset 2^31 the arithmetics in udf_check_vsd() would overflow. Make sure the computation is done in large enough type.

Reported-by: Cezary Sliwa sliwa@ifpan.edu.pl Signed-off-by: Jan Kara jack@suse.cz Signed-off-by: Sasha Levin alexander.levin@verizon.com --- fs/udf/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/udf/super.c b/fs/udf/super.c index 81155b9b445b..ee09c97f3ab2 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -705,7 +705,7 @@ static loff_t udf_check_vsd(struct super_block *sb) else sectorsize = sb->s_blocksize;

- sector += (sbi->s_session << sb->s_blocksize_bits); + sector += (((loff_t)sbi->s_session) << sb->s_blocksize_bits);

udf_debug("Starting at sector %u (%ld byte sectors)\n", (unsigned int)(sector >> sb->s_blocksize_bits),

From: Alex Vesker valex@mellanox.com

[ Upstream commit b4b678b06f6eef18bff44a338c01870234db0bc9 ]

When ndo_open and ndo_stop are called RTNL lock should be held. In this specific case ipoib_ib_dev_open calls the offloaded ndo_open which re-sets the number of TX queue assuming RTNL lock is held. Since RTNL lock is not held, RTNL assert will fail.

Signed-off-by: Alex Vesker valex@mellanox.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/infiniband/ulp/ipoib/ipoib_ib.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 8f8c3af9f4e8..d3f0a384faad 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -1044,10 +1044,15 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv, ipoib_ib_dev_down(dev);

if (level == IPOIB_FLUSH_HEAVY) { + rtnl_lock(); if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) ipoib_ib_dev_stop(dev); - if (ipoib_ib_dev_open(dev) != 0) + + result = ipoib_ib_dev_open(dev); + rtnl_unlock(); + if (result) return; + if (netif_queue_stopped(dev)) netif_start_queue(dev); }

From: Bart Van Assche bart.vanassche@wdc.com

[ Upstream commit c0b64f58e8d49570aa9ee55d880f92c20ff0166b ]

According to the C standard the behavior of computations with integer operands is as follows: * A computation involving unsigned operands can never overflow, because a result that cannot be represented by the resulting unsigned integer type is reduced modulo the number that is one greater than the largest value that can be represented by the resulting type. * The behavior for signed integer underflow and overflow is undefined.

Hence only use unsigned integers when checking for integer overflow.

This patch is what I came up with after having analyzed the following smatch warnings:

drivers/infiniband/core/cma.c:3448: cma_resolve_ib_udp() warn: signed overflow undefined. 'offset + conn_param->private_data_len < conn_param->private_data_len' drivers/infiniband/core/cma.c:3505: cma_connect_ib() warn: signed overflow undefined. 'offset + conn_param->private_data_len < conn_param->private_data_len'

Signed-off-by: Bart Van Assche bart.vanassche@wdc.com Acked-by: Sean Hefty sean.hefty@intel.com Signed-off-by: Doug Ledford dledford@redhat.com Signed-off-by: Sasha Levin alexander.levin@verizon.com --- drivers/infiniband/core/cma.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 43d5166db4c6..e354358db77b 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1353,7 +1353,7 @@ static struct rdma_id_private *cma_id_from_event(struct ib_cm_id *cm_id, return id_priv; }

-static inline int cma_user_data_offset(struct rdma_id_private *id_priv) +static inline u8 cma_user_data_offset(struct rdma_id_private *id_priv) { return cma_family(id_priv) == AF_IB ? 0 : sizeof(struct cma_hdr); } @@ -1731,7 +1731,8 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) struct rdma_id_private *listen_id, *conn_id; struct rdma_cm_event event; struct net_device *net_dev; - int offset, ret; + u8 offset; + int ret;

listen_id = cma_id_from_event(cm_id, ib_event, &net_dev); if (IS_ERR(listen_id)) @@ -3118,7 +3119,8 @@ static int cma_resolve_ib_udp(struct rdma_id_private *id_priv, struct ib_cm_sidr_req_param req; struct ib_cm_id *id; void *private_data; - int offset, ret; + u8 offset; + int ret;

memset(&req, 0, sizeof req); offset = cma_user_data_offset(id_priv); @@ -3175,7 +3177,8 @@ static int cma_connect_ib(struct rdma_id_private *id_priv, struct rdma_route *route; void *private_data; struct ib_cm_id *id; - int offset, ret; + u8 offset; + int ret;

memset(&req, 0, sizeof req); offset = cma_user_data_offset(id_priv);