4.14.256-rc1 review

From: Quinn Tran <[email protected]>

[ Upstream commit 0b7a9fd934a68ebfc1019811b7bdc1742072ad7b ]

When user uses issue_lip to do link bounce, driver sends additional target reset to remote device before resetting the link. The target reset would affect other paths with active I/Os. This patch will remove the unnecessary target reset.

---
 drivers/scsi/qla2xxx/qla_gbl.h |  2 --
 drivers/scsi/qla2xxx/qla_mr.c  | 23 -----------------------
 drivers/scsi/qla2xxx/qla_os.c  | 27 ++-------------------------
 3 files changed, 2 insertions(+), 50 deletions(-)

index 89706341514e2..a9df91f7c1543 100644
@@ -132,7 +132,6 @@ extern int ql2xasynctmfenable;
 extern int ql2xgffidenable;
 extern int ql2xenabledif;
 extern int ql2xenablehba_err_chk;
-extern int ql2xtargetreset;
 extern int ql2xdontresethba;
 extern uint64_t ql2xmaxlun;
 extern int ql2xmdcapmask;

@@ -724,7 +723,6 @@ extern void qlafx00_abort_iocb(srb_t *, struct abort_iocb_entry_fx00 *);
 extern void qlafx00_fxdisc_iocb(srb_t *, struct fxdisc_entry_fx00 *);
 extern void qlafx00_timer_routine(scsi_qla_host_t *);
 extern int qlafx00_rescan_isp(scsi_qla_host_t *);
-extern int qlafx00_loop_reset(scsi_qla_host_t *vha);
 
 /* qla82xx related functions */
 

index e23a3d4c36f39..66ee206026612 100644
@@ -739,29 +739,6 @@ qlafx00_lun_reset(fc_port_t *fcport, uint64_t l, int tag)
 	return qla2x00_async_tm_cmd(fcport, TCF_LUN_RESET, l, tag);
 }
 
-int
-qlafx00_loop_reset(scsi_qla_host_t *vha)
-{
-	int ret;
-	struct fc_port *fcport;
-	struct qla_hw_data *ha = vha->hw;
-
-	if (ql2xtargetreset) {
-		list_for_each_entry(fcport, &vha->vp_fcports, list) {
-			if (fcport->port_type != FCT_TARGET)
-				continue;
-
-			ret = ha->isp_ops->target_reset(fcport, 0, 0);
-			if (ret != QLA_SUCCESS) {
-				ql_dbg(ql_dbg_taskm, vha, 0x803d,
-				    "Bus Reset failed: Reset=%d "
-				    "d_id=%x.\n", ret, fcport->d_id.b24);
-			}
-		}
-	}
-	return QLA_SUCCESS;
-}
-
 int
 qlafx00_iospace_config(struct qla_hw_data *ha)
 {

index ea60c6e603c06..d0f52c123bfb3 100644
@@ -188,12 +188,6 @@ MODULE_PARM_DESC(ql2xdbwr,
 		" 0 -- Regular doorbell.\n"
 		" 1 -- CAMRAM doorbell (faster).\n");
 
-int ql2xtargetreset = 1;
-module_param(ql2xtargetreset, int, S_IRUGO);
-MODULE_PARM_DESC(ql2xtargetreset,
-		 "Enable target reset."
-		 "Default is 1 - use hw defaults.");
-
 int ql2xgffidenable;
 module_param(ql2xgffidenable, int, S_IRUGO);
 MODULE_PARM_DESC(ql2xgffidenable,

@@ -1652,27 +1646,10 @@ int
 qla2x00_loop_reset(scsi_qla_host_t *vha)
 {
 	int ret;
-	struct fc_port *fcport;
 	struct qla_hw_data *ha = vha->hw;
 
-	if (IS_QLAFX00(ha)) {
-		return qlafx00_loop_reset(vha);
-	}
-
-	if (ql2xtargetreset == 1 && ha->flags.enable_target_reset) {
-		list_for_each_entry(fcport, &vha->vp_fcports, list) {
-			if (fcport->port_type != FCT_TARGET)
-				continue;
-
-			ret = ha->isp_ops->target_reset(fcport, 0, 0);
-			if (ret != QLA_SUCCESS) {
-				ql_dbg(ql_dbg_taskm, vha, 0x802c,
-				    "Bus Reset failed: Reset=%d "
-				    "d_id=%x.\n", ret, fcport->d_id.b24);
-			}
-		}
-	}
-
+	if (IS_QLAFX00(ha))
+		return QLA_SUCCESS;
 
 	if (ha->flags.enable_lip_full_login && !IS_CNA_CAPABLE(ha)) {
 		atomic_set(&vha->loop_state, LOOP_DOWN);

2.33.0

From: Christophe JAILLET <[email protected]>

[ Upstream commit 7f98960c046ee1136e7096aee168eda03aef8a5d ]

A successful 'clk_prepare()' call should be balanced by a corresponding 'clk_unprepare()' call in the error handling path of the probe, as already done in the remove function.

More specifically, 'clk_prepare_enable()' is used, but 'clk_disable()' is also already called. So just the unprepare step has still to be done.

Update the error handling path accordingly.

---
 drivers/i2c/busses/i2c-xlr.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

index 484bfa15d58ee..dc9e20941efd1 100644
@@ -434,11 +434,15 @@ static int xlr_i2c_probe(struct platform_device *pdev)
 	i2c_set_adapdata(&priv->adap, priv);
 	ret = i2c_add_numbered_adapter(&priv->adap);
 	if (ret < 0)
-		return ret;
+		goto err_unprepare_clk;
 
 	platform_set_drvdata(pdev, priv);
 	dev_info(&priv->adap.dev, "Added I2C Bus.\n");
 	return 0;
+
+err_unprepare_clk:
+	clk_unprepare(clk);
+	return ret;
 }
 
 static int xlr_i2c_remove(struct platform_device *pdev)

2.33.0

From: YueHaibing <[email protected]>

[ Upstream commit 4745ea2628bb43a7ec34b71763b5a56407b33990 ]

Return NULL instead of passing to ERR_PTR while err is zero, this fix smatch warnings:
drivers/xen/xen-pciback/conf_space_capability.c:163
pm_ctrl_init() warn: passing zero to 'ERR_PTR'

---
 drivers/xen/xen-pciback/conf_space_capability.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index e5694133ebe57..42f0f64fcba47 100644
@@ -160,7 +160,7 @@ static void *pm_ctrl_init(struct pci_dev *dev, int offset)
 	}
 
 out:
-	return ERR_PTR(err);
+	return err ? ERR_PTR(err) : NULL;
 }
 
 static const struct config_field caplist_pm[] = {

2.33.0

From: Maxim Kiselev <[email protected]>

[ Upstream commit d52bcb47bdf971a59a2467975d2405fcfcb2fa19 ]

This patch allows to use 0 for coal->rx_coalesce_usecs param to disable rx irq coalescing.

Previously we could enable rx irq coalescing via ethtool (For ex: ethtool -C eth0 rx-usecs 2000) but we couldn't disable it because this part rejects 0 value:

       if (!coal->rx_coalesce_usecs)
               return -EINVAL;

---
 drivers/net/ethernet/ti/davinci_emac.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

index e1ee9da38df7e..da536385075aa 100644
@@ -426,8 +426,20 @@ static int emac_set_coalesce(struct net_device *ndev,
 	u32 int_ctrl, num_interrupts = 0;
 	u32 prescale = 0, addnl_dvdr = 1, coal_intvl = 0;
 
-	if (!coal->rx_coalesce_usecs)
-		return -EINVAL;
+	if (!coal->rx_coalesce_usecs) {
+		priv->coal_intvl = 0;
+
+		switch (priv->version) {
+		case EMAC_VERSION_2:
+			emac_ctrl_write(EMAC_DM646X_CMINTCTRL, 0);
+			break;
+		default:
+			emac_ctrl_write(EMAC_CTRL_EWINTTCNT, 0);
+			break;
+		}
+
+		return 0;
+	}
 
 	coal_intvl = coal->rx_coalesce_usecs;
 

2.33.0

From: Ziyang Xuan <[email protected]>

[ Upstream commit 563bcbae3ba233c275c244bfce2efe12938f5363 ]

The real_dev of a vlan net_device may be freed after unregister_vlan_dev(). Access the real_dev continually by vlan_dev_real_dev() will trigger the UAF problem for the real_dev like following:

==================================================================

BUG: KASAN: use-after-free in vlan_dev_real_dev+0xf9/0x120
Call Trace:
 kasan_report.cold+0x83/0xdf
 vlan_dev_real_dev+0xf9/0x120
 is_eth_port_of_netdev_filter.part.0+0xb1/0x2c0
 is_eth_port_of_netdev_filter+0x28/0x40
 ib_enum_roce_netdev+0x1a3/0x300
 ib_enum_all_roce_netdevs+0xc7/0x140
 netdevice_event_work_handler+0x9d/0x210

...

Freed by task 9288:
 kasan_save_stack+0x1b/0x40
 kasan_set_track+0x1c/0x30
 kasan_set_free_info+0x20/0x30
 __kasan_slab_free+0xfc/0x130
 slab_free_freelist_hook+0xdd/0x240
 kfree+0xe4/0x690
 kvfree+0x42/0x50
 device_release+0x9f/0x240
 kobject_put+0x1c8/0x530
 put_device+0x1b/0x30
 free_netdev+0x370/0x540
 ppp_destroy_interface+0x313/0x3d0

...

Move the put_device(real_dev) to vlan_dev_free(). Ensure real_dev not be freed before vlan_dev unregistered.

---
 net/8021q/vlan.c     | 3 ---
 net/8021q/vlan_dev.c | 3 +++
 2 files changed, 3 insertions(+), 3 deletions(-)

index 0efdf83f78e7a..a8cee80e07a70 100644
@@ -112,9 +112,6 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head)
 	}
 
 	vlan_vid_del(real_dev, vlan->vlan_proto, vlan_id);
-
-	/* Get rid of the vlan's reference to real_dev */
-	dev_put(real_dev);
 }
 
 int vlan_check_real_dev(struct net_device *real_dev,

index ed3717dc2d201..d28c22e59996c 100644
@@ -814,6 +814,9 @@ static void vlan_dev_free(struct net_device *dev)
 
 	free_percpu(vlan->vlan_pcpu_stats);
 	vlan->vlan_pcpu_stats = NULL;
+
+	/* Get rid of the vlan's reference to real_dev */
+	dev_put(vlan->real_dev);
 }
 
 void vlan_setup(struct net_device *dev)

2.33.0

This patch is known to be broken, it should not be backported

Jason

It is already in a bunch of branches :(

What is the upstream revert of this commit in Linus's tree?

thanks,

greg k-h

It isn't in a Linus released kernel yet, Ziyang and Petr are working on fixing it.

Jason

Ok, dropping it from the 4.14 and 4.19 queues now, hopefully it gets fixed in Linus's tree soon.

thanks,

greg k-h

From: Hans de Goede <[email protected]>

[ Upstream commit 009a789443fe4c8e6b1ecb7c16b4865c026184cd ]

The handling of PMIC register reads through writing 0 to address 4 of the OpRegion is wrong. Instead of returning the read value through the value64, which is a no-op for function == ACPI_WRITE calls, store the value and then on a subsequent function == ACPI_READ with address == 3 (the address for the value field of the OpRegion) return the stored value.

This has been tested on a Xiaomi Mi Pad 2 and makes the ACPI battery dev there mostly functional (unfortunately there are still other issues).

Here are the SET() / GET() functions of the PMIC ACPI device, which use this OpRegion, which clearly show the new behavior to be correct:

OperationRegion (REGS, 0x8F, Zero, 0x50)
Field (REGS, ByteAcc, NoLock, Preserve)

{
    CLNT,   8,
    SA,     8,
    OFF,    8,
    VAL,    8,
    RWM,    8
}

Method (GET, 3, Serialized)

{
    If ((AVBE == One))
    {
        CLNT = Arg0
        SA = Arg1
        OFF = Arg2
        RWM = Zero
        If ((AVBG == One))
        {
            GPRW = Zero
        }
    }

    Return (VAL) /* \_SB_.PCI0.I2C7.PMI5.VAL_ */
}

Method (SET, 4, Serialized)
{
If ((AVBE == One))
{
CLNT = Arg0
SA = Arg1
OFF = Arg2
VAL = Arg3
RWM = One
If ((AVBG == One))
{
GPRW = One
}
}
}

---
 drivers/acpi/pmic/intel_pmic.c | 51 +++++++++++++++++++---------------
 1 file changed, 28 insertions(+), 23 deletions(-)

index ca18e0d23df97..db63d3463617a 100644
@@ -216,31 +216,36 @@ static acpi_status intel_pmic_regs_handler(u32 function,
 		void *handler_context, void *region_context)
 {
 	struct intel_pmic_opregion *opregion = region_context;
-	int result = 0;
+	int result = -EINVAL;
+
+	if (function == ACPI_WRITE) {
+		switch (address) {
+		case 0:
+			return AE_OK;
+		case 1:
+			opregion->ctx.addr |= (*value64 & 0xff) << 8;
+			return AE_OK;
+		case 2:
+			opregion->ctx.addr |= *value64 & 0xff;
+			return AE_OK;
+		case 3:
+			opregion->ctx.val = *value64 & 0xff;
+			return AE_OK;
+		case 4:
+			if (*value64) {
+				result = regmap_write(opregion->regmap, opregion->ctx.addr,
+						      opregion->ctx.val);
+			} else {
+				result = regmap_read(opregion->regmap, opregion->ctx.addr,
+						     &opregion->ctx.val);
+			}
+			opregion->ctx.addr = 0;
+		}
+	}
 
-	switch (address) {
-	case 0:
-		return AE_OK;
-	case 1:
-		opregion->ctx.addr |= (*value64 & 0xff) << 8;
+	if (function == ACPI_READ && address == 3) {
+		*value64 = opregion->ctx.val;
 		return AE_OK;
-	case 2:
-		opregion->ctx.addr |= *value64 & 0xff;
-		return AE_OK;
-	case 3:
-		opregion->ctx.val = *value64 & 0xff;
-		return AE_OK;
-	case 4:
-		if (*value64) {
-			result = regmap_write(opregion->regmap, opregion->ctx.addr,
-					      opregion->ctx.val);
-		} else {
-			result = regmap_read(opregion->regmap, opregion->ctx.addr,
-					     &opregion->ctx.val);
-			if (result == 0)
-				*value64 = opregion->ctx.val;
-		}
-		memset(&opregion->ctx, 0x00, sizeof(opregion->ctx));
 	}
 
 	if (result < 0) {

2.33.0

From: Huang Guobin <[email protected]>

[ Upstream commit b93c6a911a3fe926b00add28f3b932007827c4ca ]

When I do fuzz test for bonding device interface, I got the following use-after-free Calltrace:

==================================================================

BUG: KASAN: use-after-free in bond_enslave+0x1521/0x24f0
Read of size 8 at addr ffff88825bc11c00 by task ifenslave/7365

CPU: 5 PID: 7365 Comm: ifenslave Tainted: G            E     5.15.0-rc1+ #13
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1 04/01/2014
Call Trace:
 dump_stack_lvl+0x6c/0x8b
 print_address_description.constprop.0+0x48/0x70
 kasan_report.cold+0x82/0xdb
 __asan_load8+0x69/0x90
 bond_enslave+0x1521/0x24f0
 bond_do_ioctl+0x3e0/0x450
 dev_ifsioc+0x2ba/0x970
 dev_ioctl+0x112/0x710
 sock_do_ioctl+0x118/0x1b0
 sock_ioctl+0x2e0/0x490
 __x64_sys_ioctl+0x118/0x150
 do_syscall_64+0x35/0xb0
 entry_SYSCALL_64_after_hwframe+0x44/0xae
RIP: 0033:0x7f19159cf577
Code: b3 66 90 48 8b 05 11 89 2c 00 64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 78
RSP: 002b:00007ffeb3083c78 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00007ffeb3084bca RCX: 00007f19159cf577
RDX: 00007ffeb3083ce0 RSI: 0000000000008990 RDI: 0000000000000003
RBP: 00007ffeb3084bc4 R08: 0000000000000040 R09: 0000000000000000
R10: 00007ffeb3084bc0 R11: 0000000000000246 R12: 00007ffeb3083ce0
R13: 0000000000000000 R14: 0000000000000000 R15: 00007ffeb3083cb0

Allocated by task 7365:
 kasan_save_stack+0x23/0x50
 __kasan_kmalloc+0x83/0xa0
 kmem_cache_alloc_trace+0x22e/0x470
 bond_enslave+0x2e1/0x24f0
 bond_do_ioctl+0x3e0/0x450
 dev_ifsioc+0x2ba/0x970
 dev_ioctl+0x112/0x710
 sock_do_ioctl+0x118/0x1b0
 sock_ioctl+0x2e0/0x490
 __x64_sys_ioctl+0x118/0x150
 do_syscall_64+0x35/0xb0
 entry_SYSCALL_64_after_hwframe+0x44/0xae

Freed by task 7365:
 kasan_save_stack+0x23/0x50
 kasan_set_track+0x20/0x30
 kasan_set_free_info+0x24/0x40
 __kasan_slab_free+0xf2/0x130
 kfree+0xd1/0x5c0
 slave_kobj_release+0x61/0x90
 kobject_put+0x102/0x180
 bond_sysfs_slave_add+0x7a/0xa0
 bond_enslave+0x11b6/0x24f0
 bond_do_ioctl+0x3e0/0x450
 dev_ifsioc+0x2ba/0x970
 dev_ioctl+0x112/0x710
 sock_do_ioctl+0x118/0x1b0
 sock_ioctl+0x2e0/0x490
 __x64_sys_ioctl+0x118/0x150
 do_syscall_64+0x35/0xb0
 entry_SYSCALL_64_after_hwframe+0x44/0xae

Last potentially related work creation:
 kasan_save_stack+0x23/0x50
 kasan_record_aux_stack+0xb7/0xd0
 insert_work+0x43/0x190
 __queue_work+0x2e3/0x970
 delayed_work_timer_fn+0x3e/0x50
 call_timer_fn+0x148/0x470
 run_timer_softirq+0x8a8/0xc50
 __do_softirq+0x107/0x55f

Second to last potentially related work creation:
 kasan_save_stack+0x23/0x50
 kasan_record_aux_stack+0xb7/0xd0
 insert_work+0x43/0x190
 __queue_work+0x2e3/0x970
 __queue_delayed_work+0x130/0x180
 queue_delayed_work_on+0xa7/0xb0
 bond_enslave+0xe25/0x24f0
 bond_do_ioctl+0x3e0/0x450
 dev_ifsioc+0x2ba/0x970
 dev_ioctl+0x112/0x710
 sock_do_ioctl+0x118/0x1b0
 sock_ioctl+0x2e0/0x490
 __x64_sys_ioctl+0x118/0x150
 do_syscall_64+0x35/0xb0
 entry_SYSCALL_64_after_hwframe+0x44/0xae

The buggy address belongs to the object at ffff88825bc11c00
 which belongs to the cache kmalloc-1k of size 1024
The buggy address is located 0 bytes inside of
 1024-byte region [ffff88825bc11c00, ffff88825bc12000)
The buggy address belongs to the page:
page:ffffea00096f0400 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x25bc10
head:ffffea00096f0400 order:3 compound_mapcount:0 compound_pincount:0
flags: 0x57ff00000010200(slab|head|node=1|zone=2|lastcpupid=0x7ff)
raw: 057ff00000010200 ffffea0009a71c08 ffff888240001968 ffff88810004dbc0
raw: 0000000000000000 00000000000a000a 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff88825bc11b00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff88825bc11b80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff88825bc11c00: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                   ^
 ffff88825bc11c80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff88825bc11d00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================

Put new_slave in bond_sysfs_slave_add() will cause use-after-free problems when new_slave is accessed in the subsequent error handling process. Since new_slave will be put in the subsequent error handling process, remove the unnecessary put to fix it.
In addition, when sysfs_create_file() fails, if some files have been crea- ted successfully, we need to call sysfs_remove_file() to remove them. Since there are sysfs_create_files() & sysfs_remove_files() can be used, use these two functions instead.

---
 drivers/net/bonding/bond_sysfs_slave.c | 36 ++++++++------------------
 1 file changed, 11 insertions(+), 25 deletions(-)

index 68bbac4715c35..1e1e77a40f182 100644
@@ -112,15 +112,15 @@ static ssize_t ad_partner_oper_port_state_show(struct slave *slave, char *buf)
 }
 static SLAVE_ATTR_RO(ad_partner_oper_port_state);
 
-static const struct slave_attribute *slave_attrs[] = {
-	&slave_attr_state,
-	&slave_attr_mii_status,
-	&slave_attr_link_failure_count,
-	&slave_attr_perm_hwaddr,
-	&slave_attr_queue_id,
-	&slave_attr_ad_aggregator_id,
-	&slave_attr_ad_actor_oper_port_state,
-	&slave_attr_ad_partner_oper_port_state,
+static const struct attribute *slave_attrs[] = {
+	&slave_attr_state.attr,
+	&slave_attr_mii_status.attr,
+	&slave_attr_link_failure_count.attr,
+	&slave_attr_perm_hwaddr.attr,
+	&slave_attr_queue_id.attr,
+	&slave_attr_ad_aggregator_id.attr,
+	&slave_attr_ad_actor_oper_port_state.attr,
+	&slave_attr_ad_partner_oper_port_state.attr,
 	NULL
 };
 

@@ -141,24 +141,10 @@ const struct sysfs_ops slave_sysfs_ops = {
 
 int bond_sysfs_slave_add(struct slave *slave)
 {
-	const struct slave_attribute **a;
-	int err;
-
-	for (a = slave_attrs; *a; ++a) {
-		err = sysfs_create_file(&slave->kobj, &((*a)->attr));
-		if (err) {
-			kobject_put(&slave->kobj);
-			return err;
-		}
-	}
-
-	return 0;
+	return sysfs_create_files(&slave->kobj, slave_attrs);
 }
 
 void bond_sysfs_slave_del(struct slave *slave)
 {
-	const struct slave_attribute **a;
-
-	for (a = slave_attrs; *a; ++a)
-		sysfs_remove_file(&slave->kobj, &((*a)->attr));
+	sysfs_remove_files(&slave->kobj, slave_attrs);
 }

2.33.0

From: Miaohe Lin <[email protected]>

[ Upstream commit afe8605ca45424629fdddfd85984b442c763dc47 ]

There is one possible race window between zs_pool_dec_isolated() and zs_unregister_migration() because wait_for_isolated_drain() checks the isolated count without holding class->lock and there is no order inside zs_pool_dec_isolated(). Thus the below race window could be possible:

zs_pool_dec_isolated zs_unregister_migration

    check pool->destroying != 0
				  pool->destroying = true;
				  smp_mb();
				  wait_for_isolated_drain()
				    wait for pool->isolated_pages == 0
    atomic_long_dec(&pool->isolated_pages);
    atomic_long_read(&pool->isolated_pages) == 0

Since we observe the pool->destroying (false) before atomic_long_dec() for pool->isolated_pages, waking pool->migration_wait up is missed.

Fix this by ensure checking pool->destroying happens after the atomic_long_dec(&pool->isolated_pages).

---
 mm/zsmalloc.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

index 633ebcac82f8d..6cdb49ae00010 100644
@@ -1901,10 +1901,11 @@ static inline void zs_pool_dec_isolated(struct zs_pool *pool)
 	VM_BUG_ON(atomic_long_read(&pool->isolated_pages) <= 0);
 	atomic_long_dec(&pool->isolated_pages);
 	/*
-	 * There's no possibility of racing, since wait_for_isolated_drain()
-	 * checks the isolated count under &class->lock after enqueuing
-	 * on migration_wait.
+	 * Checking pool->destroying must happen after atomic_long_dec()
+	 * for pool->isolated_pages above. Paired with the smp_mb() in
+	 * zs_unregister_migration().
 	 */
+	smp_mb__after_atomic();
 	if (atomic_long_read(&pool->isolated_pages) == 0 && pool->destroying)
 		wake_up_all(&pool->migration_wait);
 }

2.33.0

From: Eric Dumazet <[email protected]>

[ Upstream commit 8ac9dfd58b138f7e82098a4e0a0d46858b12215b ]

Both ifindex and LLC_SK_DEV_HASH_ENTRIES are signed.

This means that (ifindex % LLC_SK_DEV_HASH_ENTRIES) is negative if @ifindex is negative.

We could simply make LLC_SK_DEV_HASH_ENTRIES unsigned.

In this patch I chose to use hash_32() to get more entropy from @ifindex, like llc_sk_laddr_hashfn().

UBSAN: array-index-out-of-bounds in ./include/net/llc.h:75:26
index -43 is out of range for type 'hlist_head [64]'
CPU: 1 PID: 20999 Comm: syz-executor.3 Not tainted 5.15.0-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106
 ubsan_epilogue+0xb/0x5a lib/ubsan.c:151
 __ubsan_handle_out_of_bounds.cold+0x62/0x6c lib/ubsan.c:291
 llc_sk_dev_hash include/net/llc.h:75 [inline]
 llc_sap_add_socket+0x49c/0x520 net/llc/llc_conn.c:697
 llc_ui_bind+0x680/0xd70 net/llc/af_llc.c:404
 __sys_bind+0x1e9/0x250 net/socket.c:1693
 __do_sys_bind net/socket.c:1704 [inline]
 __se_sys_bind net/socket.c:1702 [inline]
 __x64_sys_bind+0x6f/0xb0 net/socket.c:1702
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x44/0xae
RIP: 0033:0x7fa503407ae9

---
 include/net/llc.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index df282d9b40170..9c10b121b49b0 100644
@@ -72,7 +72,9 @@ struct llc_sap {
 static inline
 struct hlist_head *llc_sk_dev_hash(struct llc_sap *sap, int ifindex)
 {
-	return &sap->sk_dev_hash[ifindex % LLC_SK_DEV_HASH_ENTRIES];
+	u32 bucket = hash_32(ifindex, LLC_SK_DEV_HASH_BITS);
+
+	return &sap->sk_dev_hash[bucket];
 }
 
 static inline

2.33.0

From: Chengfeng Ye <[email protected]>

[ Upstream commit 9fec40f850658e00a14a7dd9e06f7fbc7e59cc4a ]

skb is already freed by dev_kfree_skb in pn533_fill_fragment_skbs, but follow error handler branch when pn533_fill_fragment_skbs() fails, skb is freed again, results in double free issue. Fix this by not free skb in error path of pn533_fill_fragment_skbs.

---
 drivers/nfc/pn533/pn533.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

index e3026e20f1696..52a1a2cae6c74 100644
@@ -2084,7 +2084,7 @@ static int pn533_fill_fragment_skbs(struct pn533 *dev, struct sk_buff *skb)
 		frag = pn533_alloc_skb(dev, frag_size);
 		if (!frag) {
 			skb_queue_purge(&dev->fragment_skb);
-			break;
+			return -ENOMEM;
 		}
 
 		if (!dev->tgt_mode) {

@@ -2154,7 +2154,7 @@ static int pn533_transceive(struct nfc_dev *nfc_dev,
 		/* jumbo frame ? */
 		if (skb->len > PN533_CMD_DATAEXCH_DATA_MAXLEN) {
 			rc = pn533_fill_fragment_skbs(dev, skb);
-			if (rc <= 0)
+			if (rc < 0)
 				goto error;
 
 			skb = skb_dequeue(&dev->fragment_skb);

@@ -2226,7 +2226,7 @@ static int pn533_tm_send(struct nfc_dev *nfc_dev, struct sk_buff *skb)
 	/* let's split in multiple chunks if size's too big */
 	if (skb->len > PN533_CMD_DATAEXCH_DATA_MAXLEN) {
 		rc = pn533_fill_fragment_skbs(dev, skb);
-		if (rc <= 0)
+		if (rc < 0)
 			goto error;
 
 		/* get the first skb */

2.33.0

From: Eiichi Tsukata <[email protected]>

[ Upstream commit c7cd82b90599fa10915f41e3dd9098a77d0aa7b6 ]

Currently vosck_connect() increments sock refcount for nonblocking socket each time it's called, which can lead to memory leak if it's called multiple times because connect timeout function decrements sock refcount only once.

Fixes it by making vsock_connect() return -EALREADY immediately when sock state is already SS_CONNECTING.

---
 net/vmw_vsock/af_vsock.c | 2 ++
 1 file changed, 2 insertions(+)

index 02a171916dd2b..8b211d164beea 100644
@@ -1166,6 +1166,8 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
 		 * non-blocking call.
 		 */
 		err = -EALREADY;
+		if (flags & O_NONBLOCK)
+			goto out;
 		break;
 	default:
 		if ((sk->sk_state == TCP_LISTEN) ||

2.33.0

From: Johan Hovold <[email protected]>

commit 9aaa81c3366e8393a62374e3a1c67c69edc07b8a upstream.

Chipidea core was calling the interrupt handler from non-IRQ context with interrupts enabled, something which can lead to a deadlock if there's an actual interrupt trying to take a lock that's already held (e.g. the controller lock in udc_irq()).

Add a wrapper that can be used to fake interrupts instead of calling the handler directly.

---
 drivers/usb/chipidea/core.c |   19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

@@ -535,7 +535,7 @@ int hw_device_reset(struct ci_hdrc *ci)
 	return 0;
 }
 
-static irqreturn_t ci_irq(int irq, void *data)
+static irqreturn_t ci_irq_handler(int irq, void *data)
 {
 	struct ci_hdrc *ci = data;
 	irqreturn_t ret = IRQ_NONE;

@@ -588,6 +588,15 @@ static irqreturn_t ci_irq(int irq, void
 	return ret;
 }
 
+static void ci_irq(struct ci_hdrc *ci)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	ci_irq_handler(ci->irq, ci);
+	local_irq_restore(flags);
+}
+
 static int ci_cable_notifier(struct notifier_block *nb, unsigned long event,
 			     void *ptr)
 {

@@ -597,7 +606,7 @@ static int ci_cable_notifier(struct noti
 	cbl->connected = event;
 	cbl->changed = true;
 
-	ci_irq(ci->irq, ci);
+	ci_irq(ci);
 	return NOTIFY_DONE;
 }
 

@@ -1051,7 +1060,7 @@ static int ci_hdrc_probe(struct platform
 		}
 	}
 
-	ret = devm_request_irq(dev, ci->irq, ci_irq, IRQF_SHARED,
+	ret = devm_request_irq(dev, ci->irq, ci_irq_handler, IRQF_SHARED,
 			ci->platdata->name, ci);
 	if (ret)
 		goto stop;

@@ -1175,11 +1184,11 @@ static void ci_extcon_wakeup_int(struct
 
 	if (!IS_ERR(cable_id->edev) && ci->is_otg &&
 		(otgsc & OTGSC_IDIE) && (otgsc & OTGSC_IDIS))
-		ci_irq(ci->irq, ci);
+		ci_irq(ci);
 
 	if (!IS_ERR(cable_vbus->edev) && ci->is_otg &&
 		(otgsc & OTGSC_BSVIE) && (otgsc & OTGSC_BSVIS))
-		ci_irq(ci->irq, ci);
+		ci_irq(ci);
 }
 
 static int ci_controller_resume(struct device *dev)

From: Michał Mirosław <[email protected]>

commit 0d08e7bf0d0d1a29aff7b16ef516f7415eb1aa05 upstream.

Currently __set_fixmap() bails out with a warning when called in early boot from early_iounmap(). Fix it, and while at it, make the comment a bit easier to understand.

---
 arch/arm/mm/mmu.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -416,9 +416,9 @@ void __set_fixmap(enum fixed_addresses i
 		     FIXADDR_END);
 	BUG_ON(idx >= __end_of_fixed_addresses);
 
-	/* we only support device mappings until pgprot_kernel has been set */
+	/* We support only device mappings before pgprot_kernel is set. */
 	if (WARN_ON(pgprot_val(prot) != pgprot_val(FIXMAP_PAGE_IO) &&
-		    pgprot_val(pgprot_kernel) == 0))
+		    pgprot_val(prot) && pgprot_val(pgprot_kernel) == 0))
 		return;
 
 	if (pgprot_val(prot))

From: Arnd Bergmann <[email protected]>

commit 418ace9992a7647c446ed3186df40cf165b67298 upstream.

Naresh and Antonio ran into a build failure with latest Debian armhf compilers, with lots of output like

tmp/ccY3nOAs.s:2215: Error: selected processor does not support `cpsid i' in ARM mode

As it turns out, $(cc-option) fails early here when the FPU is not selected before CPU architecture is selected, as the compiler option check runs before enabling -msoft-float, which causes a problem when testing a target architecture level without an FPU:

cc1: error: '-mfloat-abi=hard': selected architecture lacks an FPU

Passing e.g. -march=armv6k+fp in place of -march=armv6k would avoid this issue, but the fallback logic is already broken because all supported compilers (gcc-5 and higher) are much more recent than these options, and building with -march=armv5t as a fallback no longer works.

The best way forward that I see is to just remove all the checks, which also has the nice side-effect of slightly improving the startup time for 'make'.

The -mtune=marvell-f option was apparently never supported by any mainline compiler, and the custom Codesourcery gcc build that did support is now too old to build kernels, so just use -mtune=xscale unconditionally for those.

This should be safe to apply on all stable kernels, and will be required in order to keep building them with gcc-11 and higher.

---
 arch/arm/Makefile |   22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

@@ -66,15 +66,15 @@ KBUILD_CFLAGS	+= $(call cc-option,-fno-i
 # Note that GCC does not numerically define an architecture version
 # macro, but instead defines a whole series of macros which makes
 # testing for a specific architecture or later rather impossible.
-arch-$(CONFIG_CPU_32v7M)	=-D__LINUX_ARM_ARCH__=7 -march=armv7-m -Wa,-march=armv7-m
-arch-$(CONFIG_CPU_32v7)		=-D__LINUX_ARM_ARCH__=7 $(call cc-option,-march=armv7-a,-march=armv5t -Wa$(comma)-march=armv7-a)
-arch-$(CONFIG_CPU_32v6)		=-D__LINUX_ARM_ARCH__=6 $(call cc-option,-march=armv6,-march=armv5t -Wa$(comma)-march=armv6)
+arch-$(CONFIG_CPU_32v7M)	=-D__LINUX_ARM_ARCH__=7 -march=armv7-m
+arch-$(CONFIG_CPU_32v7)		=-D__LINUX_ARM_ARCH__=7 -march=armv7-a
+arch-$(CONFIG_CPU_32v6)		=-D__LINUX_ARM_ARCH__=6 -march=armv6
 # Only override the compiler option if ARMv6. The ARMv6K extensions are
 # always available in ARMv7
 ifeq ($(CONFIG_CPU_32v6),y)
-arch-$(CONFIG_CPU_32v6K)	=-D__LINUX_ARM_ARCH__=6 $(call cc-option,-march=armv6k,-march=armv5t -Wa$(comma)-march=armv6k)
+arch-$(CONFIG_CPU_32v6K)	=-D__LINUX_ARM_ARCH__=6 -march=armv6k
 endif
-arch-$(CONFIG_CPU_32v5)		=-D__LINUX_ARM_ARCH__=5 $(call cc-option,-march=armv5te,-march=armv4t)
+arch-$(CONFIG_CPU_32v5)		=-D__LINUX_ARM_ARCH__=5 -march=armv5te
 arch-$(CONFIG_CPU_32v4T)	=-D__LINUX_ARM_ARCH__=4 -march=armv4t
 arch-$(CONFIG_CPU_32v4)		=-D__LINUX_ARM_ARCH__=4 -march=armv4
 arch-$(CONFIG_CPU_32v3)		=-D__LINUX_ARM_ARCH__=3 -march=armv3

@@ -88,7 +88,7 @@ tune-$(CONFIG_CPU_ARM720T)	=-mtune=arm7t
 tune-$(CONFIG_CPU_ARM740T)	=-mtune=arm7tdmi
 tune-$(CONFIG_CPU_ARM9TDMI)	=-mtune=arm9tdmi
 tune-$(CONFIG_CPU_ARM940T)	=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_ARM946E)	=$(call cc-option,-mtune=arm9e,-mtune=arm9tdmi)
+tune-$(CONFIG_CPU_ARM946E)	=-mtune=arm9e
 tune-$(CONFIG_CPU_ARM920T)	=-mtune=arm9tdmi
 tune-$(CONFIG_CPU_ARM922T)	=-mtune=arm9tdmi
 tune-$(CONFIG_CPU_ARM925T)	=-mtune=arm9tdmi

@@ -96,11 +96,11 @@ tune-$(CONFIG_CPU_ARM926T)	=-mtune=arm9t
 tune-$(CONFIG_CPU_FA526)	=-mtune=arm9tdmi
 tune-$(CONFIG_CPU_SA110)	=-mtune=strongarm110
 tune-$(CONFIG_CPU_SA1100)	=-mtune=strongarm1100
-tune-$(CONFIG_CPU_XSCALE)	=$(call cc-option,-mtune=xscale,-mtune=strongarm110) -Wa,-mcpu=xscale
-tune-$(CONFIG_CPU_XSC3)		=$(call cc-option,-mtune=xscale,-mtune=strongarm110) -Wa,-mcpu=xscale
-tune-$(CONFIG_CPU_FEROCEON)	=$(call cc-option,-mtune=marvell-f,-mtune=xscale)
-tune-$(CONFIG_CPU_V6)		=$(call cc-option,-mtune=arm1136j-s,-mtune=strongarm)
-tune-$(CONFIG_CPU_V6K)		=$(call cc-option,-mtune=arm1136j-s,-mtune=strongarm)
+tune-$(CONFIG_CPU_XSCALE)	=-mtune=xscale
+tune-$(CONFIG_CPU_XSC3)		=-mtune=xscale
+tune-$(CONFIG_CPU_FEROCEON)	=-mtune=xscale
+tune-$(CONFIG_CPU_V6)		=-mtune=arm1136j-s
+tune-$(CONFIG_CPU_V6K)		=-mtune=arm1136j-s
 
 # Evaluate tune cc-option calls now
 tune-y := $(tune-y)

From: "Naveen N. Rao" <[email protected]>

upstream commit 4549c3ea3160fa8b3f37dfe2f957657bb265eda9

Add a helper to check if a given offset is within the branch range for a powerpc conditional branch instruction, and update some sites to use the new helper.

---
 arch/powerpc/include/asm/code-patching.h |    1 +
 arch/powerpc/lib/code-patching.c         |    7 ++++++-
 arch/powerpc/net/bpf_jit.h               |    7 +------
 3 files changed, 8 insertions(+), 7 deletions(-)

@@ -25,6 +25,7 @@
 #define BRANCH_ABSOLUTE	0x2
 
 bool is_offset_in_branch_range(long offset);
+bool is_offset_in_cond_branch_range(long offset);
 unsigned int create_branch(const unsigned int *addr,
 			   unsigned long target, int flags);
 unsigned int create_cond_branch(const unsigned int *addr,

@@ -244,6 +244,11 @@ bool is_offset_in_branch_range(long offs
 	return (offset >= -0x2000000 && offset <= 0x1fffffc && !(offset & 0x3));
 }
 
+bool is_offset_in_cond_branch_range(long offset)
+{
+	return offset >= -0x8000 && offset <= 0x7fff && !(offset & 0x3);
+}
+
 /*
  * Helper to check if a given instruction is a conditional branch
  * Derived from the conditional checks in analyse_instr()

@@ -297,7 +302,7 @@ unsigned int create_cond_branch(const un
 		offset = offset - (unsigned long)addr;
 
 	/* Check we can represent the target in the instruction format */
-	if (offset < -0x8000 || offset > 0x7FFF || offset & 0x3)
+	if (!is_offset_in_cond_branch_range(offset))
 		return 0;
 
 	/* Mask out the flags and target, so they don't step on each other. */

@@ -221,11 +221,6 @@
 #define PPC_FUNC_ADDR(d,i) do { PPC_LI32(d, i); } while(0)
 #endif
 
-static inline bool is_nearbranch(int offset)
-{
-	return (offset < 32768) && (offset >= -32768);
-}
-
 /*
  * The fly in the ointment of code size changing from pass to pass is
  * avoided by padding the short branch case with a NOP.	 If code size differs

@@ -234,7 +229,7 @@ static inline bool is_nearbranch(int off
  * state.
  */
 #define PPC_BCC(cond, dest)	do {					      \
-		if (is_nearbranch((dest) - (ctx->idx * 4))) {		      \
+		if (is_offset_in_cond_branch_range((long)(dest) - (ctx->idx * 4))) {	\
 			PPC_BCC_SHORT(cond, dest);			      \
 			PPC_NOP();					      \
 		} else {						      \

From: "Naveen N. Rao" <[email protected]>

upstream commit 3832ba4e283d7052b783dab8311df7e3590fed93

Add checks to ensure that we never emit branch instructions with truncated branch offsets.

---
 arch/powerpc/net/bpf_jit.h        |   26 ++++++++++++++++++++------
 arch/powerpc/net/bpf_jit_comp64.c |   10 +++++++---
 2 files changed, 27 insertions(+), 9 deletions(-)

@@ -15,6 +15,7 @@
 #ifndef __ASSEMBLY__
 
 #include <asm/types.h>
+#include <asm/code-patching.h>
 
 #ifdef PPC64_ELF_ABI_v1
 #define FUNCTION_DESCR_SIZE	24

@@ -176,13 +177,26 @@
 #define PPC_NEG(d, a)		EMIT(PPC_INST_NEG | ___PPC_RT(d) | ___PPC_RA(a))
 
 /* Long jump; (unconditional 'branch') */
-#define PPC_JMP(dest)		EMIT(PPC_INST_BRANCH |			      \
-				     (((dest) - (ctx->idx * 4)) & 0x03fffffc))
+#define PPC_JMP(dest)							      \
+	do {								      \
+		long offset = (long)(dest) - (ctx->idx * 4);		      \
+		if (!is_offset_in_branch_range(offset)) {		      \
+			pr_err_ratelimited("Branch offset 0x%lx (@%u) out of range\n", offset, ctx->idx);			\
+			return -ERANGE;					      \
+		}							      \
+		EMIT(PPC_INST_BRANCH | (offset & 0x03fffffc));		      \
+	} while (0)
 /* "cond" here covers BO:BI fields. */
-#define PPC_BCC_SHORT(cond, dest)	EMIT(PPC_INST_BRANCH_COND |	      \
-					     (((cond) & 0x3ff) << 16) |	      \
-					     (((dest) - (ctx->idx * 4)) &     \
-					      0xfffc))
+#define PPC_BCC_SHORT(cond, dest)					      \
+	do {								      \
+		long offset = (long)(dest) - (ctx->idx * 4);		      \
+		if (!is_offset_in_cond_branch_range(offset)) {		      \
+			pr_err_ratelimited("Conditional branch offset 0x%lx (@%u) out of range\n", offset, ctx->idx);		\
+			return -ERANGE;					      \
+		}							      \
+		EMIT(PPC_INST_BRANCH_COND | (((cond) & 0x3ff) << 16) | (offset & 0xfffc));					\
+	} while (0)
+
 /* Sign-extended 32-bit immediate load */
 #define PPC_LI32(d, i)		do {					      \
 		if ((int)(uintptr_t)(i) >= -32768 &&			      \

@@ -235,7 +235,7 @@ static void bpf_jit_emit_func_call(u32 *
 	PPC_BLRL();
 }
 
-static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out)
+static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out)
 {
 	/*
 	 * By now, the eBPF program has already setup parameters in r3, r4 and r5

@@ -296,7 +296,9 @@ static void bpf_jit_emit_tail_call(u32 *
 	bpf_jit_emit_common_epilogue(image, ctx);
 
 	PPC_BCTR();
+
 	/* out: */
+	return 0;
 }
 
 /* Assemble the body code between the prologue & epilogue */

@@ -306,7 +308,7 @@ static int bpf_jit_build_body(struct bpf
 {
 	const struct bpf_insn *insn = fp->insnsi;
 	int flen = fp->len;
-	int i;
+	int i, ret;
 
 	/* Start of epilogue code - will only be valid 2nd pass onwards */
 	u32 exit_addr = addrs[flen];

@@ -956,7 +958,9 @@ common_load:
 		 */
 		case BPF_JMP | BPF_TAIL_CALL:
 			ctx->seen |= SEEN_TAILCALL;
-			bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]);
+			ret = bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]);
+			if (ret < 0)
+				return ret;
 			break;
 
 		default:

From: "Naveen N. Rao" <[email protected]>

upstream commit 5855c4c1f415ca3ba1046e77c0b3d3dfc96c9025

We aren't handling subtraction involving an immediate value of 0x80000000 properly. Fix the same.

---
 arch/powerpc/net/bpf_jit_comp64.c |   27 +++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

@@ -359,18 +359,25 @@ static int bpf_jit_build_body(struct bpf
 			PPC_SUB(dst_reg, dst_reg, src_reg);
 			goto bpf_alu32_trunc;
 		case BPF_ALU | BPF_ADD | BPF_K: /* (u32) dst += (u32) imm */
-		case BPF_ALU | BPF_SUB | BPF_K: /* (u32) dst -= (u32) imm */
 		case BPF_ALU64 | BPF_ADD | BPF_K: /* dst += imm */
+			if (!imm) {
+				goto bpf_alu32_trunc;
+			} else if (imm >= -32768 && imm < 32768) {
+				PPC_ADDI(dst_reg, dst_reg, IMM_L(imm));
+			} else {
+				PPC_LI32(b2p[TMP_REG_1], imm);
+				PPC_ADD(dst_reg, dst_reg, b2p[TMP_REG_1]);
+			}
+			goto bpf_alu32_trunc;
+		case BPF_ALU | BPF_SUB | BPF_K: /* (u32) dst -= (u32) imm */
 		case BPF_ALU64 | BPF_SUB | BPF_K: /* dst -= imm */
-			if (BPF_OP(code) == BPF_SUB)
-				imm = -imm;
-			if (imm) {
-				if (imm >= -32768 && imm < 32768)
-					PPC_ADDI(dst_reg, dst_reg, IMM_L(imm));
-				else {
-					PPC_LI32(b2p[TMP_REG_1], imm);
-					PPC_ADD(dst_reg, dst_reg, b2p[TMP_REG_1]);
-				}
+			if (!imm) {
+				goto bpf_alu32_trunc;
+			} else if (imm > -32768 && imm <= 32768) {
+				PPC_ADDI(dst_reg, dst_reg, IMM_L(-imm));
+			} else {
+				PPC_LI32(b2p[TMP_REG_1], imm);
+				PPC_SUB(dst_reg, dst_reg, b2p[TMP_REG_1]);
 			}
 			goto bpf_alu32_trunc;
 		case BPF_ALU | BPF_MUL | BPF_X: /* (u32) dst *= (u32) src */

From: Vasily Averin <[email protected]>

commit 0b28179a6138a5edd9d82ad2687c05b3773c387b upstream.

Patch series "memcg: prohibit unconditional exceeding the limit of dying tasks", v3.

Memory cgroup charging allows killed or exiting tasks to exceed the hard limit. It can be misused and allowed to trigger global OOM from inside a memcg-limited container. On the other hand if memcg fails allocation, called from inside #PF handler it triggers global OOM from inside pagefault_out_of_memory().

To prevent these problems this patchset:
(a) removes execution of out_of_memory() from pagefault_out_of_memory(), becasue nobody can explain why it is necessary.
(b) allow memcg to fail allocation of dying/killed tasks.

This patch (of 3):

Any allocation failure during the #PF path will return with VM_FAULT_OOM which in turn results in pagefault_out_of_memory which in turn executes out_out_memory() and can kill a random task.

An allocation might fail when the current task is the oom victim and there are no memory reserves left. The OOM killer is already handled at the page allocator level for the global OOM and at the charging level for the memcg one. Both have much more information about the scope of allocation/charge request. This means that either the OOM killer has been invoked properly and didn't lead to the allocation success or it has been skipped because it couldn't have been invoked. In both cases triggering it from here is pointless and even harmful.

It makes much more sense to let the killed task die rather than to wake up an eternally hungry oom-killer and send him to choose a fatter victim for breakfast.

---
 mm/oom_kill.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -1112,6 +1112,9 @@ void pagefault_out_of_memory(void)
 	if (mem_cgroup_oom_synchronize(true))
 		return;
 
+	if (fatal_signal_pending(current))
+		return;
+
 	if (!mutex_trylock(&oom_lock))
 		return;
 	out_of_memory(&oc);

From: Michal Hocko <[email protected]>

commit 60e2793d440a3ec95abb5d6d4fc034a4b480472d upstream.

Any allocation failure during the #PF path will return with VM_FAULT_OOM which in turn results in pagefault_out_of_memory. This can happen for 2 different reasons. a) Memcg is out of memory and we rely on mem_cgroup_oom_synchronize to perform the memcg OOM handling or b) normal allocation fails.

The latter is quite problematic because allocation paths already trigger out_of_memory and the page allocator tries really hard to not fail allocations. Anyway, if the OOM killer has been already invoked there is no reason to invoke it again from the #PF path. Especially when the OOM condition might be gone by that time and we have no way to find out other than allocate.

Moreover if the allocation failed and the OOM killer hasn't been invoked then we are unlikely to do the right thing from the #PF context because we have already lost the allocation context and restictions and therefore might oom kill a task from a different NUMA domain.

This all suggests that there is no legitimate reason to trigger out_of_memory from pagefault_out_of_memory so drop it. Just to be sure that no #PF path returns with VM_FAULT_OOM without allocation print a warning that this is happening before we restart the #PF.

[VvS: #PF allocation can hit into limit of cgroup v1 kmem controller. This is a local problem related to memcg, however, it causes unnecessary global OOM kills that are repeated over and over again and escalate into a real disaster. This has been broken since kmem accounting has been introduced for cgroup v1 (3.8). There was no kmem specific reclaim for the separate limit so the only way to handle kmem hard limit was to return with ENOMEM. In upstream the problem will be fixed by removing the outdated kmem limit, however stable and LTS kernels cannot do it and are still affected. This patch fixes the problem and should be backported into stable/LTS.]

---
 mm/oom_kill.c |   22 ++++++++--------------
 1 file changed, 8 insertions(+), 14 deletions(-)

@@ -1095,19 +1095,15 @@ bool out_of_memory(struct oom_control *o
 }
 
 /*
- * The pagefault handler calls here because it is out of memory, so kill a
- * memory-hogging task. If oom_lock is held by somebody else, a parallel oom
- * killing is already in progress so do nothing.
+ * The pagefault handler calls here because some allocation has failed. We have
+ * to take care of the memcg OOM here because this is the only safe context without
+ * any locks held but let the oom killer triggered from the allocation context care
+ * about the global OOM.
  */
 void pagefault_out_of_memory(void)
 {
-	struct oom_control oc = {
-		.zonelist = NULL,
-		.nodemask = NULL,
-		.memcg = NULL,
-		.gfp_mask = 0,
-		.order = 0,
-	};
+	static DEFINE_RATELIMIT_STATE(pfoom_rs, DEFAULT_RATELIMIT_INTERVAL,
+				      DEFAULT_RATELIMIT_BURST);
 
 	if (mem_cgroup_oom_synchronize(true))
 		return;

@@ -1115,8 +1111,6 @@ void pagefault_out_of_memory(void)
 	if (fatal_signal_pending(current))
 		return;
 
-	if (!mutex_trylock(&oom_lock))
-		return;
-	out_of_memory(&oc);
-	mutex_unlock(&oom_lock);
+	if (__ratelimit(&pfoom_rs))
+		pr_warn("Huh VM_FAULT_OOM leaked out to the #PF handler. Retrying PF\n");
 }

From: Vineeth Vijayan <[email protected]>

commit a4751f157c194431fae9e9c493f456df8272b871 upstream.

Check the validity of subchanel before reading other fields in the schib.

---
 drivers/s390/cio/css.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -337,8 +337,8 @@ static ssize_t dev_busid_show(struct dev
 	struct subchannel *sch = to_subchannel(dev);
 	struct pmcw *pmcw = &sch->schib.pmcw;
 
-	if ((pmcw->st == SUBCHANNEL_TYPE_IO ||
-	     pmcw->st == SUBCHANNEL_TYPE_MSG) && pmcw->dnv)
+	if ((pmcw->st == SUBCHANNEL_TYPE_IO && pmcw->dnv) ||
+	    (pmcw->st == SUBCHANNEL_TYPE_MSG && pmcw->w))
 		return sysfs_emit(buf, "0.%x.%04x\n", sch->schid.ssid,
 				  pmcw->dev);
 	else

From: Pali Rohár <[email protected]>

commit 460275f124fb072dca218a6b43b6370eebbab20d upstream.

Define a macro PCI_EXP_DEVCTL_PAYLOAD_* for every possible Max Payload Size in linux/pci_regs.h, in the same style as PCI_EXP_DEVCTL_READRQ_*.

---
 include/uapi/linux/pci_regs.h |    6 ++++++
 1 file changed, 6 insertions(+)

@@ -497,6 +497,12 @@
 #define  PCI_EXP_DEVCTL_URRE	0x0008	/* Unsupported Request Reporting En. */
 #define  PCI_EXP_DEVCTL_RELAX_EN 0x0010 /* Enable relaxed ordering */
 #define  PCI_EXP_DEVCTL_PAYLOAD	0x00e0	/* Max_Payload_Size */
+#define  PCI_EXP_DEVCTL_PAYLOAD_128B 0x0000 /* 128 Bytes */
+#define  PCI_EXP_DEVCTL_PAYLOAD_256B 0x0020 /* 256 Bytes */
+#define  PCI_EXP_DEVCTL_PAYLOAD_512B 0x0040 /* 512 Bytes */
+#define  PCI_EXP_DEVCTL_PAYLOAD_1024B 0x0060 /* 1024 Bytes */
+#define  PCI_EXP_DEVCTL_PAYLOAD_2048B 0x0080 /* 2048 Bytes */
+#define  PCI_EXP_DEVCTL_PAYLOAD_4096B 0x00a0 /* 4096 Bytes */
 #define  PCI_EXP_DEVCTL_EXT_TAG	0x0100	/* Extended Tag Field Enable */
 #define  PCI_EXP_DEVCTL_PHANTOM	0x0200	/* Phantom Functions Enable */
 #define  PCI_EXP_DEVCTL_AUX_PME	0x0400	/* Auxiliary Power PM Enable */

From: Shaoying Xu <[email protected]>

commit 39fec6889d15a658c3a3ebb06fd69d3584ddffd3 upstream.

Ext4 file system has default lazy inode table initialization setup once it is mounted. However, it has issue on computing the next schedule time that makes the timeout same amount in jiffies but different real time in secs if with various HZ values. Therefore, fix by measuring the current time in a more granular unit nanoseconds and make the next schedule time independent of the HZ value.

---
 fs/ext4/super.c |    9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

@@ -2952,8 +2952,8 @@ static int ext4_run_li_request(struct ex
 	struct ext4_group_desc *gdp = NULL;
 	ext4_group_t group, ngroups;
 	struct super_block *sb;
-	unsigned long timeout = 0;
 	int ret = 0;
+	u64 start_time;
 
 	sb = elr->lr_super;
 	ngroups = EXT4_SB(sb)->s_groups_count;

@@ -2973,13 +2973,12 @@ static int ext4_run_li_request(struct ex
 		ret = 1;
 
 	if (!ret) {
-		timeout = jiffies;
+		start_time = ktime_get_real_ns();
 		ret = ext4_init_inode_table(sb, group,
 					    elr->lr_timeout ? 0 : 1);
 		if (elr->lr_timeout == 0) {
-			timeout = (jiffies - timeout) *
-				  elr->lr_sbi->s_li_wait_mult;
-			elr->lr_timeout = timeout;
+			elr->lr_timeout = nsecs_to_jiffies((ktime_get_real_ns() - start_time) *
+				  elr->lr_sbi->s_li_wait_mult);
 		}
 		elr->lr_next_sched = jiffies + elr->lr_timeout;
 		elr->lr_next_group = group + 1;

From: Paul Burton <[email protected]>

commit 4030a6e6a6a4a42ff8c18414c9e0c93e24cc70b8 upstream.

Currently tgid_map is sized at PID_MAX_DEFAULT entries, which means that on systems where pid_max is configured higher than PID_MAX_DEFAULT the ftrace record-tgid option doesn't work so well. Any tasks with PIDs higher than PID_MAX_DEFAULT are simply not recorded in tgid_map, and don't show up in the saved_tgids file.

In particular since systemd v243 & above configure pid_max to its highest possible 1<<22 value by default on 64 bit systems this renders the record-tgids option of little use.

Increase the size of tgid_map to the configured pid_max instead, allowing it to cover the full range of PIDs up to the maximum value of PID_MAX_LIMIT if the system is configured that way.

On 64 bit systems with pid_max == PID_MAX_LIMIT this will increase the size of tgid_map from 256KiB to 16MiB. Whilst this 64x increase in memory overhead sounds significant 64 bit systems are presumably best placed to accommodate it, and since tgid_map is only allocated when the record-tgid option is actually used presumably the user would rather it spends sufficient memory to actually record the tgids they expect.

The size of tgid_map could also increase for CONFIG_BASE_SMALL=y configurations, but these seem unlikely to be systems upon which people are both configuring a large pid_max and running ftrace with record-tgid anyway.

Of note is that we only allocate tgid_map once, the first time that the record-tgid option is enabled. Therefore its size is only set once, to the value of pid_max at the time the record-tgid option is first enabled. If a user increases pid_max after that point, the saved_tgids file will not contain entries for any tasks with pids beyond the earlier value of pid_max.

---
 kernel/trace/trace.c |   62 ++++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 47 insertions(+), 15 deletions(-)

@@ -1723,8 +1723,15 @@ void tracing_reset_all_online_cpus(void)
 	}
 }
 
+/*
+ * The tgid_map array maps from pid to tgid; i.e. the value stored at index i
+ * is the tgid last observed corresponding to pid=i.
+ */
 static int *tgid_map;
 
+/* The maximum valid index into tgid_map. */
+static size_t tgid_map_max;
+
 #define SAVED_CMDLINES_DEFAULT 128
 #define NO_CMDLINE_MAP UINT_MAX
 static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;

@@ -1996,24 +2003,41 @@ void trace_find_cmdline(int pid, char co
 	preempt_enable();
 }
 
+static int *trace_find_tgid_ptr(int pid)
+{
+	/*
+	 * Pairs with the smp_store_release in set_tracer_flag() to ensure that
+	 * if we observe a non-NULL tgid_map then we also observe the correct
+	 * tgid_map_max.
+	 */
+	int *map = smp_load_acquire(&tgid_map);
+
+	if (unlikely(!map || pid > tgid_map_max))
+		return NULL;
+
+	return &map[pid];
+}
+
 int trace_find_tgid(int pid)
 {
-	if (unlikely(!tgid_map || !pid || pid > PID_MAX_DEFAULT))
-		return 0;
+	int *ptr = trace_find_tgid_ptr(pid);
 
-	return tgid_map[pid];
+	return ptr ? *ptr : 0;
 }
 
 static int trace_save_tgid(struct task_struct *tsk)
 {
+	int *ptr;
+
 	/* treat recording of idle task as a success */
 	if (!tsk->pid)
 		return 1;
 
-	if (unlikely(!tgid_map || tsk->pid > PID_MAX_DEFAULT))
+	ptr = trace_find_tgid_ptr(tsk->pid);
+	if (!ptr)
 		return 0;
 
-	tgid_map[tsk->pid] = tsk->tgid;
+	*ptr = tsk->tgid;
 	return 1;
 }
 

@@ -4353,6 +4377,8 @@ int trace_keep_overwrite(struct tracer *
 
 int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
 {
+	int *map;
+
 	if ((mask == TRACE_ITER_RECORD_TGID) ||
 	    (mask == TRACE_ITER_RECORD_CMD))
 		lockdep_assert_held(&event_mutex);

@@ -4375,9 +4401,19 @@ int set_tracer_flag(struct trace_array *
 		trace_event_enable_cmd_record(enabled);
 
 	if (mask == TRACE_ITER_RECORD_TGID) {
-		if (!tgid_map)
-			tgid_map = kzalloc((PID_MAX_DEFAULT + 1) * sizeof(*tgid_map),
-					   GFP_KERNEL);
+		if (!tgid_map) {
+			tgid_map_max = pid_max;
+			map = kzalloc((tgid_map_max + 1) * sizeof(*tgid_map),
+				      GFP_KERNEL);
+
+			/*
+			 * Pairs with smp_load_acquire() in
+			 * trace_find_tgid_ptr() to ensure that if it observes
+			 * the tgid_map we just allocated then it also observes
+			 * the corresponding tgid_map_max value.
+			 */
+			smp_store_release(&tgid_map, map);
+		}
 		if (!tgid_map) {
 			tr->trace_flags &= ~TRACE_ITER_RECORD_TGID;
 			return -ENOMEM;

@@ -4752,18 +4788,14 @@ static void *saved_tgids_next(struct seq
 {
 	int pid = ++(*pos);
 
-	if (pid > PID_MAX_DEFAULT)
-		return NULL;
-
-	return &tgid_map[pid];
+	return trace_find_tgid_ptr(pid);
 }
 
 static void *saved_tgids_start(struct seq_file *m, loff_t *pos)
 {
-	if (!tgid_map || *pos > PID_MAX_DEFAULT)
-		return NULL;
+	int pid = *pos;
 
-	return &tgid_map[*pos];
+	return trace_find_tgid_ptr(pid);
 }
 
 static void saved_tgids_stop(struct seq_file *m, void *v)

From: Sven Schnelle <[email protected]>

commit 3ec18fc7831e7d79e2d536dd1f3bc0d3ba425e8a upstream.

commit 8779e05ba8aa ("parisc: Fix ptrace check on syscall return") fixed testing of TI_FLAGS. This uncovered a bug in the test mask. syscall_restore_rfi is only used when the kernel needs to exit to usespace with single or block stepping and the recovery counter enabled. The test however used _TIF_SYSCALL_TRACE_MASK, which includes a lot of bits that shouldn't be tested here.

Fix this by using TIF_SINGLESTEP and TIF_BLOCKSTEP directly.

I encountered this bug by enabling syscall tracepoints. Both in qemu and on real hardware. As soon as i enabled the tracepoint (sys_exit_read, but i guess it doesn't really matter which one), i got random page faults in userspace almost immediately.

---
 arch/parisc/kernel/entry.S |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1850,7 +1850,7 @@ syscall_restore:
 
 	/* Are we being ptraced? */
 	LDREG	TI_FLAGS-THREAD_SZ_ALGN-FRAME_SIZE(%r30),%r19
-	ldi	_TIF_SYSCALL_TRACE_MASK,%r2
+	ldi	_TIF_SINGLESTEP|_TIF_BLOCKSTEP,%r2
 	and,COND(=)	%r19,%r2,%r0
 	b,n	syscall_restore_rfi
 

From: Thomas Gleixner <[email protected]>

commit 3735459037114d31e5acd9894fad9aed104231a0 upstream.

free_msi_irqs() frees the MSI entries before destroying the sysfs entries which are exposing them. Nothing prevents a concurrent free while a sysfs file is read and accesses the possibly freed entry.

Move the sysfs release ahead of freeing the entries.

---
 drivers/pci/msi.c |   24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

@@ -372,18 +372,6 @@ static void free_msi_irqs(struct pci_dev
 			for (i = 0; i < entry->nvec_used; i++)
 				BUG_ON(irq_has_action(entry->irq + i));
 
-	pci_msi_teardown_msi_irqs(dev);
-
-	list_for_each_entry_safe(entry, tmp, msi_list, list) {
-		if (entry->msi_attrib.is_msix) {
-			if (list_is_last(&entry->list, msi_list))
-				iounmap(entry->mask_base);
-		}
-
-		list_del(&entry->list);
-		free_msi_entry(entry);
-	}
-
 	if (dev->msi_irq_groups) {
 		sysfs_remove_groups(&dev->dev.kobj, dev->msi_irq_groups);
 		msi_attrs = dev->msi_irq_groups[0]->attrs;

@@ -399,6 +387,18 @@ static void free_msi_irqs(struct pci_dev
 		kfree(dev->msi_irq_groups);
 		dev->msi_irq_groups = NULL;
 	}
+
+	pci_msi_teardown_msi_irqs(dev);
+
+	list_for_each_entry_safe(entry, tmp, msi_list, list) {
+		if (entry->msi_attrib.is_msix) {
+			if (list_is_last(&entry->list, msi_list))
+				iounmap(entry->mask_base);
+		}
+
+		list_del(&entry->list);
+		free_msi_entry(entry);
+	}
 }
 
 static void pci_intx_for_msi(struct pci_dev *dev, int enable)

From: Michal Simek <[email protected]>

[ Upstream commit 812fa2f0e9d33564bd0131a69750e0d165f4c82a ]

Based on commit 65a2c14d4f00 ("dt-bindings: serial: convert Cadence UART bindings to YAML") compatible string should look like differently that's why fix it to be aligned with dt binding.

---
 arch/arm64/boot/dts/xilinx/zynqmp.dtsi | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index 0531843117f46..58028f23ad9aa 100644
@@ -573,7 +573,7 @@
 		};
 
 		uart0: serial@ff000000 {
-			compatible = "cdns,uart-r1p12", "xlnx,xuartps";
+			compatible = "xlnx,zynqmp-uart", "cdns,uart-r1p12";
 			status = "disabled";
 			interrupt-parent = <&gic>;
 			interrupts = <0 21 4>;

@@ -582,7 +582,7 @@
 		};
 
 		uart1: serial@ff010000 {
-			compatible = "cdns,uart-r1p12", "xlnx,xuartps";
+			compatible = "xlnx,zynqmp-uart", "cdns,uart-r1p12";
 			status = "disabled";
 			interrupt-parent = <&gic>;
 			interrupts = <0 22 4>;

2.33.0

From: James Smart <[email protected]>

[ Upstream commit 99154581b05c8fb22607afb7c3d66c1bace6aa5d ]

When parsing the txq list in lpfc_drain_txq(), the driver attempts to pass the requests to the adapter. If such an attempt fails, a local "fail_msg" string is set and a log message output. The job is then added to a completions list for cancellation.

Processing of any further jobs from the txq list continues, but since "fail_msg" remains set, jobs are added to the completions list regardless of whether a wqe was passed to the adapter. If successfully added to txcmplq, jobs are added to both lists resulting in list corruption.

Fix by clearing the fail_msg string after adding a job to the completions list. This stops the subsequent jobs from being added to the completions list unless they had an appropriate failure.

---
 drivers/scsi/lpfc/lpfc_sli.c | 1 +
 1 file changed, 1 insertion(+)

index 20deb6715c36e..6f9ba3272721a 100644
@@ -18777,6 +18777,7 @@ lpfc_drain_txq(struct lpfc_hba *phba)
 					fail_msg,
 					piocbq->iotag, piocbq->sli4_xritag);
 			list_add_tail(&piocbq->list, &completions);
+			fail_msg = NULL;
 		}
 		spin_unlock_irqrestore(&pring->ring_lock, iflags);
 	}

2.33.0

From: Yang Yingliang <[email protected]>

[ Upstream commit 14651496a3de6807a17c310f63c894ea0c5d858e ]

It will cause null-ptr-deref if platform_get_resource() returns NULL, we need check the return value.

---
 drivers/usb/musb/tusb6010.c | 5 +++++
 1 file changed, 5 insertions(+)

index 7d7cb1c5ec808..9a7b5b2d7ccc7 100644
@@ -1108,6 +1108,11 @@ static int tusb_musb_init(struct musb *musb)
 
 	/* dma address for async dma */
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!mem) {
+		pr_debug("no async dma resource?\n");
+		ret = -ENODEV;
+		goto done;
+	}
 	musb->async = mem->start;
 
 	/* dma address for sync dma */

2.33.0

From: Guo Zhi <[email protected]>

[ Upstream commit d4996c6eac4c81b8872043e9391563f67f13e406 ]

Pointers should be printed with %p or %px rather than cast to 'unsigned long' and printed with %lx.

Change %lx to %p to print the hashed pointer.

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

index 24e57e770432b..6efd17692a55a 100644
@@ -3370,8 +3370,8 @@ static void asc_prt_adv_board_info(struct seq_file *m, struct Scsi_Host *shost)
 		   shost->host_no);
 
 	seq_printf(m,
-		   " iop_base 0x%lx, cable_detect: %X, err_code %u\n",
-		   (unsigned long)v->iop_base,
+		   " iop_base 0x%p, cable_detect: %X, err_code %u\n",
+		   v->iop_base,
 		   AdvReadWordRegister(iop_base,IOPW_SCSI_CFG1) & CABLE_DETECT,
 		   v->err_code);
 

2.33.0

From: Roger Quadros <[email protected]>

[ Upstream commit 51b9e22ffd3c4c56cbb7caae9750f70e55ffa603 ]

gpmc,mux-add-data is not boolean.

Fixes the below errors flagged by dtbs_check.

"ethernet@4,0:gpmc,mux-add-data: True is not of type 'array'"

---
 arch/arm/boot/dts/omap-gpmc-smsc9221.dtsi         | 2 +-
 arch/arm/boot/dts/omap3-overo-tobiduo-common.dtsi | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

index 7f6aefd134514..e7534fe9c53cf 100644
@@ -29,7 +29,7 @@
 		compatible = "smsc,lan9221","smsc,lan9115";
 		bank-width = <2>;
 
-		gpmc,mux-add-data;
+		gpmc,mux-add-data = <0>;
 		gpmc,cs-on-ns = <0>;
 		gpmc,cs-rd-off-ns = <42>;
 		gpmc,cs-wr-off-ns = <36>;

index 82e98ee3023ad..3dbeb7a6c569c 100644
@@ -25,7 +25,7 @@
 		compatible = "smsc,lan9221","smsc,lan9115";
 		bank-width = <2>;
 
-		gpmc,mux-add-data;
+		gpmc,mux-add-data = <0>;
 		gpmc,cs-on-ns = <0>;
 		gpmc,cs-rd-off-ns = <42>;
 		gpmc,cs-wr-off-ns = <36>;

2.33.0

From: Yang Yingliang <[email protected]>

[ Upstream commit 9eff2b2e59fda25051ab36cd1cb5014661df657b ]

It will cause null-ptr-deref if platform_get_resource() returns NULL, we need check the return value.

---
 drivers/usb/host/ohci-tmio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 0cf4b6dc89720..4c7846dc5eed1 100644
@@ -199,7 +199,7 @@ static int ohci_hcd_tmio_drv_probe(struct platform_device *dev)
 	if (usb_disabled())
 		return -ENODEV;
 
-	if (!cell)
+	if (!cell || !regs || !config || !sram)
 		return -EINVAL;
 
 	if (irq < 0)

2.33.0

From: Guanghui Feng <[email protected]>

[ Upstream commit 3968ddcf05fb4b9409cd1859feb06a5b0550a1c1 ]

When running ltp testcase(ltp/testcases/kernel/pty/pty04.c) with arm64, there is a soft lockup, which look like this one:

  Workqueue: events_unbound flush_to_ldisc
  Call trace:
   dump_backtrace+0x0/0x1ec
   show_stack+0x24/0x30
   dump_stack+0xd0/0x128
   panic+0x15c/0x374
   watchdog_timer_fn+0x2b8/0x304
   __run_hrtimer+0x88/0x2c0
   __hrtimer_run_queues+0xa4/0x120
   hrtimer_interrupt+0xfc/0x270
   arch_timer_handler_phys+0x40/0x50
   handle_percpu_devid_irq+0x94/0x220
   __handle_domain_irq+0x88/0xf0
   gic_handle_irq+0x84/0xfc
   el1_irq+0xc8/0x180
   slip_unesc+0x80/0x214 [slip]
   tty_ldisc_receive_buf+0x64/0x80
   tty_port_default_receive_buf+0x50/0x90
   flush_to_ldisc+0xbc/0x110
   process_one_work+0x1d4/0x4b0
   worker_thread+0x180/0x430
   kthread+0x11c/0x120

In the testcase pty04, The first process call the write syscall to send data to the pty master. At the same time, the workqueue will do the flush_to_ldisc to pop data in a loop until there is no more data left. When the sender and workqueue running in different core, the sender sends data fastly in full time which will result in workqueue doing work in loop for a long time and occuring softlockup in flush_to_ldisc with kernel configured without preempt. So I add need_resched check and cond_resched in the flush_to_ldisc loop to avoid it.

---
 drivers/tty/tty_buffer.c | 3 +++
 1 file changed, 3 insertions(+)

index cf11882d26025..a5b32dd056bef 100644
@@ -528,6 +528,9 @@ static void flush_to_ldisc(struct work_struct *work)
 		if (!count)
 			break;
 		head->read += count;
+
+		if (need_resched())
+			cond_resched();
 	}
 
 	mutex_unlock(&buf->lock);

2.33.0

From: Bart Van Assche <[email protected]>

[ Upstream commit c91cf42f61dc77b289784ea7b15a8531defa41c0 ]

This patch fixes the following gcc 10 build error:

arch/mips/sni/time.c: In function ‘a20r_set_periodic’:
arch/mips/sni/time.c:15:26: error: unsigned conversion from ‘int’ to ‘u8’ {aka ‘volatile unsigned char’} changes value from ‘576’ to ‘64’ [-Werror=overflow]
15 | #define SNI_COUNTER0_DIV ((SNI_CLOCK_TICK_RATE / SNI_COUNTER2_DIV) / HZ)
| ^
arch/mips/sni/time.c:21:45: note: in expansion of macro ‘SNI_COUNTER0_DIV’

   21 |  *(volatile u8 *)(A20R_PT_CLOCK_BASE + 0) = SNI_COUNTER0_DIV;
      |                                             ^~~~~~~~~~~~~~~~

---
 arch/mips/sni/time.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index 0eb7d1e8821be..d741e24a21879 100644
@@ -18,14 +18,14 @@ static int a20r_set_periodic(struct clock_event_device *evt)
 {
 	*(volatile u8 *)(A20R_PT_CLOCK_BASE + 12) = 0x34;
 	wmb();
-	*(volatile u8 *)(A20R_PT_CLOCK_BASE + 0) = SNI_COUNTER0_DIV;
+	*(volatile u8 *)(A20R_PT_CLOCK_BASE + 0) = SNI_COUNTER0_DIV & 0xff;
 	wmb();
 	*(volatile u8 *)(A20R_PT_CLOCK_BASE + 0) = SNI_COUNTER0_DIV >> 8;
 	wmb();
 
 	*(volatile u8 *)(A20R_PT_CLOCK_BASE + 12) = 0xb4;
 	wmb();
-	*(volatile u8 *)(A20R_PT_CLOCK_BASE + 8) = SNI_COUNTER2_DIV;
+	*(volatile u8 *)(A20R_PT_CLOCK_BASE + 8) = SNI_COUNTER2_DIV & 0xff;
 	wmb();
 	*(volatile u8 *)(A20R_PT_CLOCK_BASE + 8) = SNI_COUNTER2_DIV >> 8;
 	wmb();

2.33.0

From: Mike Christie <[email protected]>

[ Upstream commit ed1227e080990ffec5bf39006ec8a57358e6689a ]

This patch fixes the following bugs:

1. If there are multiple ordered cmds queued and multiple simple cmds completing, target_restart_delayed_cmds() could be called on different CPUs and each instance could start a ordered cmd. They could then run in different orders than they were queued.

2. target_restart_delayed_cmds() and target_handle_task_attr() can race where:

1. target_handle_task_attr() has passed the simple_cmds == 0 check.

2. transport_complete_task_attr() then decrements simple_cmds to 0.

3. transport_complete_task_attr() runs target_restart_delayed_cmds() and it does not see any cmds on the delayed_cmd_list.

4. target_handle_task_attr() adds the cmd to the delayed_cmd_list.

The cmd will then end up timing out.

3. If we are sent > 1 ordered cmds and simple_cmds == 0, we can execute them out of order, because target_handle_task_attr() will hit that simple_cmds check first and return false for all ordered cmds sent.

4. We run target_restart_delayed_cmds() after every cmd completion, so if there is more than 1 simple cmd running, we start executing ordered cmds after that first cmd instead of waiting for all of them to complete.

5. Ordered cmds are not supposed to start until HEAD OF QUEUE and all older cmds have completed, and not just simple.

6. It's not a bug but it doesn't make sense to take the delayed_cmd_lock for every cmd completion when ordered cmds are almost never used. Just replacing that lock with an atomic increases IOPs by up to 10% when completions are spread over multiple CPUs and there are multiple sessions/ mqs/thread accessing the same device.

This patch moves the queued delayed handling to a per device work to serialze the cmd executions for each device and adds a new counter to track HEAD_OF_QUEUE and SIMPLE cmds. We can then check the new counter to determine when to run the work on the completion path.

---
 drivers/target/target_core_device.c    |  2 +
 drivers/target/target_core_internal.h  |  1 +
 drivers/target/target_core_transport.c | 76 ++++++++++++++++++--------
 include/target/target_core_base.h      |  6 +-
 4 files changed, 61 insertions(+), 24 deletions(-)

index cebef8e5a43d1..68b2fa562201c 100644
@@ -791,6 +791,8 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name)
 	INIT_LIST_HEAD(&dev->t10_alua.lba_map_list);
 	spin_lock_init(&dev->t10_alua.lba_map_lock);
 
+	INIT_WORK(&dev->delayed_cmd_work, target_do_delayed_work);
+
 	dev->t10_wwn.t10_dev = dev;
 	dev->t10_alua.t10_dev = dev;
 

index 18e3eb16e7567..7060be69dc6a3 100644
@@ -149,6 +149,7 @@ void	transport_clear_lun_ref(struct se_lun *);
 void	transport_send_task_abort(struct se_cmd *);
 sense_reason_t	target_cmd_size_check(struct se_cmd *cmd, unsigned int size);
 void	target_qf_do_work(struct work_struct *work);
+void	target_do_delayed_work(struct work_struct *work);
 bool	target_check_wce(struct se_device *dev);
 bool	target_check_fua(struct se_device *dev);
 void	__target_execute_cmd(struct se_cmd *, bool);

index 0d924e968c94b..336c9f71b750a 100644
@@ -771,8 +771,9 @@ struct se_device {
 	atomic_long_t		read_bytes;
 	atomic_long_t		write_bytes;
 	/* Active commands on this virtual SE device */
-	atomic_t		simple_cmds;
-	atomic_t		dev_ordered_sync;
+	atomic_t		non_ordered;
+	bool			ordered_sync_in_progress;
+	atomic_t		delayed_cmd_count;
 	atomic_t		dev_qf_count;
 	u32			export_count;
 	spinlock_t		delayed_cmd_lock;

@@ -795,6 +796,7 @@ struct se_device {
 	struct list_head	dev_tmr_list;
 	struct workqueue_struct *tmr_wq;
 	struct work_struct	qf_work_queue;
+	struct work_struct	delayed_cmd_work;
 	struct list_head	delayed_cmd_list;
 	struct list_head	state_list;
 	struct list_head	qf_cmd_list;

2.33.0

From: Mike Christie <[email protected]>

[ Upstream commit 1283c0d1a32bb924324481586b5d6e8e76f676ba ]

We can't free the tg_pt_gp in core_alua_set_tg_pt_gp_id() because it's still accessed via configfs. Its release must go through the normal configfs/refcount process.

The max alua_tg_pt_gps_count check should probably have been done in core_alua_allocate_tg_pt_gp(), but with the current code userspace could have created 0x0000ffff + 1 groups, but only set the id for 0x0000ffff. Then it could have deleted a group with an ID set, and then set the ID for that extra group and it would work ok.

It's unlikely, but just in case this patch continues to allow that type of behavior, and just fixes the kfree() while in use bug.

---
 drivers/target/target_core_alua.c | 1 -
 1 file changed, 1 deletion(-)

index 928127642574b..18e67230fc6a3 100644
@@ -1711,7 +1711,6 @@ int core_alua_set_tg_pt_gp_id(
 		pr_err("Maximum ALUA alua_tg_pt_gps_count:"
 			" 0x0000ffff reached\n");
 		spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
-		kmem_cache_free(t10_alua_tg_pt_gp_cache, tg_pt_gp);
 		return -ENOSPC;
 	}
 again:

2.33.0

From: Anatolij Gustschin <[email protected]>

[ Upstream commit aed2886a5e9ffc8269a4220bff1e9e030d3d2eb1 ]

Fixes build warnings:
Warning (unit_address_vs_reg): /memory: node has a reg or ranges property, but no unit name

---
 arch/powerpc/boot/dts/charon.dts    | 2 +-
 arch/powerpc/boot/dts/digsy_mtc.dts | 2 +-
 arch/powerpc/boot/dts/lite5200.dts  | 2 +-
 arch/powerpc/boot/dts/lite5200b.dts | 2 +-
 arch/powerpc/boot/dts/media5200.dts | 2 +-
 arch/powerpc/boot/dts/mpc5200b.dtsi | 2 +-
 arch/powerpc/boot/dts/o2d.dts       | 2 +-
 arch/powerpc/boot/dts/o2d.dtsi      | 2 +-
 arch/powerpc/boot/dts/o2dnt2.dts    | 2 +-
 arch/powerpc/boot/dts/o3dnt.dts     | 2 +-
 arch/powerpc/boot/dts/pcm032.dts    | 2 +-
 arch/powerpc/boot/dts/tqm5200.dts   | 2 +-
 12 files changed, 12 insertions(+), 12 deletions(-)

index 0e00e508eaa6a..1c8fe20752e6a 100644
@@ -39,7 +39,7 @@
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x08000000>;	// 128MB
 	};

index c280e75c86bfd..d4a0a367ed66b 100644
@@ -20,7 +20,7 @@
 	model = "intercontrol,digsy-mtc";
 	compatible = "intercontrol,digsy-mtc";
 
-	memory {
+	memory@0 {
 		reg = <0x00000000 0x02000000>;	// 32MB
 	};
 

index 179a1785d6454..18d137a3393f0 100644
@@ -36,7 +36,7 @@
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x04000000>;	// 64MB
 	};

index 5abb46c5cc951..29419cf81e044 100644
@@ -35,7 +35,7 @@
 		led4 { gpios = <&gpio_simple 2 1>; };
 	};
 
-	memory {
+	memory@0 {
 		reg = <0x00000000 0x10000000>;	// 256MB
 	};
 

index b5413cb85f134..3d57463bc49da 100644
@@ -36,7 +36,7 @@
 		};
 	};
 
-	memory {
+	memory@0 {
 		reg = <0x00000000 0x08000000>;	// 128MB RAM
 	};
 

index 969b2200b2f97..ecfba675b5611 100644
@@ -37,7 +37,7 @@
 		};
 	};
 
-	memory: memory {
+	memory: memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x04000000>;	// 64MB
 	};

index 9f6dd4d889b32..5a676e8141caf 100644
@@ -16,7 +16,7 @@
 	model = "ifm,o2d";
 	compatible = "ifm,o2d";
 
-	memory {
+	memory@0 {
 		reg = <0x00000000 0x08000000>;  // 128MB
 	};
 

index cf073e693f24d..1b4df5f64b580 100644
@@ -23,7 +23,7 @@
 	model = "ifm,o2d";
 	compatible = "ifm,o2d";
 
-	memory {
+	memory@0 {
 		reg = <0x00000000 0x04000000>;	// 64MB
 	};
 

index a0f5b97a4f06e..5184c461a205f 100644
@@ -16,7 +16,7 @@
 	model = "ifm,o2dnt2";
 	compatible = "ifm,o2d";
 
-	memory {
+	memory@0 {
 		reg = <0x00000000 0x08000000>;  // 128MB
 	};
 

index acce49326491b..045b901719245 100644
@@ -16,7 +16,7 @@
 	model = "ifm,o3dnt";
 	compatible = "ifm,o2d";
 
-	memory {
+	memory@0 {
 		reg = <0x00000000 0x04000000>;  // 64MB
 	};
 

index 576249bf2fb91..637e14286dde5 100644
@@ -26,7 +26,7 @@
 	model = "phytec,pcm032";
 	compatible = "phytec,pcm032";
 
-	memory {
+	memory@0 {
 		reg = <0x00000000 0x08000000>;	// 128MB
 	};
 

index 1db07f6cf133c..68b9e8240fb5b 100644
@@ -36,7 +36,7 @@
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x04000000>;	// 64MB
 	};

2.33.0

From: Chengfeng Ye <[email protected]>

[ Upstream commit a0d21bb3279476c777434c40d969ea88ca64f9aa ]

The pointer block return from snd_gf1_dma_next_block could be null, so there is a potential null pointer dereference issue. Fix this by adding a null check before dereference.

---
 sound/isa/gus/gus_dma.c | 2 ++
 1 file changed, 2 insertions(+)

index 36c27c8323601..2e27cd3427c87 100644
@@ -141,6 +141,8 @@ static void snd_gf1_dma_interrupt(struct snd_gus_card * gus)
 	}
 	block = snd_gf1_dma_next_block(gus);
 	spin_unlock(&gus->dma_lock);
+	if (!block)
+		return;
 	snd_gf1_dma_program(gus, block->addr, block->buf_addr, block->count, (unsigned short) block->cmd);
 	kfree(block);
 #if 0

2.33.0

From: Michael Ellerman <[email protected]>

[ Upstream commit fef071be57dc43679a32d5b0e6ee176d6f12e9f2 ]

In dcr-low.S we use cmpli with three arguments, instead of four arguments as defined in the ISA:

	cmpli	cr0,r3,1024

This appears to be a PPC440-ism, looking at the "PPC440x5 CPU Core User’s Manual" it shows cmpli having no L field, but implied to be 0 due to the core being 32-bit. It mentions that the ISA defines four arguments and recommends using cmplwi.

It also corresponds to the old POWER instruction set, which had no L field there, a reserved bit instead.

dcr-low.S is only built 32-bit, because it is only built when DCR_NATIVE=y, which is only selected by 40x and 44x. Looking at the generated code (with gcc/gas) we see cmplwi as expected.

Although gas is happy with the 3-argument version when building for 32-bit, the LLVM assembler is not and errors out with:

arch/powerpc/sysdev/dcr-low.S:27:10: error: invalid operand for instruction
cmpli 0,%r3,1024; ...

           ^

Switch to the cmplwi extended opcode, which avoids any confusion when reading the ISA, fixes the issue with the LLVM assembler, and also means the code could be built 64-bit in future (though that's very unlikely).

---
 arch/powerpc/sysdev/dcr-low.S | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index e687bb2003ff0..5589fbe48bbdc 100644
@@ -15,7 +15,7 @@
 #include <asm/export.h>
 
 #define DCR_ACCESS_PROLOG(table) \
-	cmpli	cr0,r3,1024;	 \
+	cmplwi	cr0,r3,1024;	 \
 	rlwinm  r3,r3,4,18,27;   \
 	lis     r5,table@h;      \
 	ori     r5,r5,table@l;   \

2.33.0

From: Nick Desaulniers <[email protected]>

[ Upstream commit 0e38225c92c7964482a8bb6b3e37fde4319e965c ]

request_irq is marked __must_check, but the call in shx3_prepare_cpus has a void return type, so it can't propagate failure to the caller. Follow cues from hexagon and just print an error.

---
 arch/sh/kernel/cpu/sh4a/smp-shx3.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

index 0d3637c494bfe..c1f66c35e0c12 100644
@@ -76,8 +76,9 @@ static void shx3_prepare_cpus(unsigned int max_cpus)
 	BUILD_BUG_ON(SMP_MSG_NR >= 8);
 
 	for (i = 0; i < SMP_MSG_NR; i++)
-		request_irq(104 + i, ipi_interrupt_handler,
-			    IRQF_PERCPU, "IPI", (void *)(long)i);
+		if (request_irq(104 + i, ipi_interrupt_handler,
+			    IRQF_PERCPU, "IPI", (void *)(long)i))
+			pr_err("Failed to request irq %d\n", i);
 
 	for (i = 0; i < max_cpus; i++)
 		set_cpu_present(i, true);

2.33.0

From: Lu Wei <[email protected]>

[ Upstream commit bde82ee391fa6d3ad054313c4aa7b726d32515ce ]

If KMEM_CACHE or maple_alloc_dev failed, the maple_bus_init() will return 0 rather than error, because the retval is not changed after KMEM_CACHE or maple_alloc_dev failed.

---
 drivers/sh/maple/maple.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

index bec81c2404f78..1682fa3671bc3 100644
@@ -835,8 +835,10 @@ static int __init maple_bus_init(void)
 
 	maple_queue_cache = KMEM_CACHE(maple_buffer, SLAB_HWCACHE_ALIGN);
 
-	if (!maple_queue_cache)
+	if (!maple_queue_cache) {
+		retval = -ENOMEM;
 		goto cleanup_bothirqs;
+	}
 
 	INIT_LIST_HEAD(&maple_waitq);
 	INIT_LIST_HEAD(&maple_sentq);

@@ -849,6 +851,7 @@ static int __init maple_bus_init(void)
 		if (!mdev[i]) {
 			while (i-- > 0)
 				maple_free_dev(mdev[i]);
+			retval = -ENOMEM;
 			goto cleanup_cache;
 		}
 		baseunits[i] = mdev[i];

2.33.0

From: Randy Dunlap <[email protected]>

[ Upstream commit fda1bc533094a7db68b11e7503d2c6c73993d12a ]

FRAME_POINTER depends on DEBUG_KERNEL so DWARF_UNWINDER should depend on DEBUG_KERNEL before selecting FRAME_POINTER.

WARNING: unmet direct dependencies detected for FRAME_POINTER
Depends on [n]: DEBUG_KERNEL [=n] && (M68K || UML || SUPERH [=y]) || ARCH_WANT_FRAME_POINTERS [=n] Selected by [y]:
- DWARF_UNWINDER [=y]

---
 arch/sh/Kconfig.debug | 1 +
 1 file changed, 1 insertion(+)

index d0767672640d8..4209405179262 100644
@@ -61,6 +61,7 @@ config DUMP_CODE
 
 config DWARF_UNWINDER
 	bool "Enable the DWARF unwinder for stacktraces"
+	depends on DEBUG_KERNEL
 	select FRAME_POINTER
 	depends on SUPERH32
 	default n

2.33.0

From: Randy Dunlap <[email protected]>

[ Upstream commit b929926f01f2d14635345d22eafcf60feed1085e ]

Fix this by defining both ENDIAN macros in <asm/sfp-machine.h> so that they can be utilized in <math-emu/soft-fp.h> according to the latter's comment:
/* Allow sfp-machine to have its own byte order definitions. */

(This is what is done in arch/nds32/include/asm/sfp-machine.h.)

This placates these build warnings:

In file included from ../arch/sh/math-emu/math.c:23:
.../include/math-emu/single.h:50:21: warning: "__BIG_ENDIAN" is not defined, evaluates to 0 [-Wundef]
50 | #if __BYTE_ORDER == __BIG_ENDIAN
In file included from ../arch/sh/math-emu/math.c:24:
.../include/math-emu/double.h:59:21: warning: "__BIG_ENDIAN" is not defined, evaluates to 0 [-Wundef]
59 | #if __BYTE_ORDER == __BIG_ENDIAN

---
 arch/sh/include/asm/sfp-machine.h | 8 ++++++++
 1 file changed, 8 insertions(+)

index d3c548443f2a6..dd195c6f3b9d8 100644
@@ -25,6 +25,14 @@
 #ifndef _SFP_MACHINE_H
 #define _SFP_MACHINE_H
 
+#ifdef __BIG_ENDIAN__
+#define __BYTE_ORDER __BIG_ENDIAN
+#define __LITTLE_ENDIAN 0
+#else
+#define __BYTE_ORDER __LITTLE_ENDIAN
+#define __BIG_ENDIAN 0
+#endif
+
 #define _FP_W_TYPE_SIZE		32
 #define _FP_W_TYPE		unsigned long
 #define _FP_WS_TYPE		signed long

2.33.0

From: Randy Dunlap <[email protected]>

[ Upstream commit 5eeaafc8d69373c095e461bdb39e5c9b62228ac5 ]

Several header files need info on CONFIG_32BIT or CONFIG_64BIT, but kconfig symbol BCM63XX does not provide that info. This leads to many build errors, e.g.:

   arch/mips/include/asm/page.h:196:13: error: use of undeclared identifier 'CAC_BASE'
           return x - PAGE_OFFSET + PHYS_OFFSET;
   arch/mips/include/asm/mach-generic/spaces.h:91:23: note: expanded from macro 'PAGE_OFFSET'
   #define PAGE_OFFSET             (CAC_BASE + PHYS_OFFSET)
   arch/mips/include/asm/io.h:134:28: error: use of undeclared identifier 'CAC_BASE'
           return (void *)(address + PAGE_OFFSET - PHYS_OFFSET);
   arch/mips/include/asm/mach-generic/spaces.h:91:23: note: expanded from macro 'PAGE_OFFSET'
   #define PAGE_OFFSET             (CAC_BASE + PHYS_OFFSET)

arch/mips/include/asm/uaccess.h:82:10: error: use of undeclared identifier '__UA_LIMIT'

           return (__UA_LIMIT & (addr | (addr + size) | __ua_size(size))) == 0;

Selecting the SYS_HAS_CPU_BMIPS* symbols causes SYS_HAS_CPU_BMIPS to be set, which then selects CPU_SUPPORT_32BIT_KERNEL, which causes CONFIG_32BIT to be set. (a bit more indirect than v1 [RFC].)

---
 arch/mips/Kconfig | 3 +++
 1 file changed, 3 insertions(+)

index 8e77149d658fc..85afd6b4297b2 100644
@@ -273,6 +273,9 @@ config BCM63XX
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_HAS_EARLY_PRINTK
+	select SYS_HAS_CPU_BMIPS32_3300
+	select SYS_HAS_CPU_BMIPS4350
+	select SYS_HAS_CPU_BMIPS4380
 	select SWAP_IO_SPACE
 	select GPIOLIB
 	select HAVE_CLK

2.33.0

From: Vincent Donnefort <[email protected]>

[ Upstream commit 42dc938a590c96eeb429e1830123fef2366d9c80 ]

Nothing protects the access to the per_cpu variable sd_llc_id. When testing the same CPU (i.e. this_cpu == that_cpu), a race condition exists with update_top_cache_domain(). One scenario being:

CPU1 CPU2
==================================================================

per_cpu(sd_llc_id, CPUX) => 0
partition_sched_domains_locked()
detach_destroy_domains()
cpus_share_cache(CPUX, CPUX) update_top_cache_domain(CPUX)
per_cpu(sd_llc_id, CPUX) => 0
per_cpu(sd_llc_id, CPUX) = CPUX
per_cpu(sd_llc_id, CPUX) => CPUX
return false

ttwu_queue_cond() wouldn't catch smp_processor_id() == cpu and the result is a warning triggered from ttwu_queue_wakelist().

Avoid a such race in cpus_share_cache() by always returning true when this_cpu == that_cpu.

---
 kernel/sched/core.c | 3 +++
 1 file changed, 3 insertions(+)

index 7cedada731c1b..544a1cb66d90d 100644
@@ -1852,6 +1852,9 @@ out:
 
 bool cpus_share_cache(int this_cpu, int that_cpu)
 {
+	if (this_cpu == that_cpu)
+		return true;
+
 	return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
 }
 #endif /* CONFIG_SMP */

2.33.0

From: Pavel Skripkin <[email protected]>

[ Upstream commit f8885ac89ce310570e5391fe0bf0ec9c7c9b4fdc ]

Smatch says:

	bnx2x_init_ops.h:640 bnx2x_ilt_client_mem_op()
	warn: variable dereferenced before check 'ilt' (see line 638)

Move ilt_cli variable initialization _after_ ilt validation, because it's unsafe to deref the pointer before validation check.

---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index 1835d2e451c01..fc7fce642666c 100644
@@ -635,11 +635,13 @@ static int bnx2x_ilt_client_mem_op(struct bnx2x *bp, int cli_num,
 {
 	int i, rc;
 	struct bnx2x_ilt *ilt = BP_ILT(bp);
-	struct ilt_client_info *ilt_cli = &ilt->clients[cli_num];
+	struct ilt_client_info *ilt_cli;
 
 	if (!ilt || !ilt->lines)
 		return -1;
 
+	ilt_cli = &ilt->clients[cli_num];
+
 	if (ilt_cli->flags & (ILT_CLIENT_SKIP_INIT | ILT_CLIENT_SKIP_MEM))
 		return 0;
 

2.33.0

From: Surabhi Boob <[email protected]>

[ Upstream commit 321421b57a12e933f92b228e0e6d0b2c6541f41d ]

While issuing VF Reset from the guest OS, the VF driver prints logs about critical / Overflow error detection. This is not an actual error since the VF_MBX_ARQLEN register is set to all FF's for a short period of time and the VF would catch the bits set if it was reading the register during that spike of time. This patch introduces an additional check to ignore this condition since the VF is in reset.

---
 drivers/net/ethernet/intel/i40evf/i40evf_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index ad2dd5b747b23..6bc772401cff2 100644
@@ -2027,7 +2027,7 @@ static void i40evf_adminq_task(struct work_struct *work)
 
 	/* check for error indications */
 	val = rd32(hw, hw->aq.arq.len);
-	if (val == 0xdeadbeef) /* indicates device in reset */
+	if (val == 0xdeadbeef || val == 0xffffffff) /* device in reset */
 		goto freedom;
 	oldval = val;
 	if (val & I40E_VF_ARQLEN1_ARQVFE_MASK) {

2.33.0

From: Colin Ian King <[email protected]>

[ Upstream commit 255e51da15baed47531beefd02f222e4dc01f1c1 ]

In the case where fw_getenv returns an error when fetching values for ememsizea and memsize then variable phys_memsize is not assigned a variable and will be uninitialized on a zero check of phys_memsize. Fix this by initializing phys_memsize to zero.

Cleans up cppcheck error:
arch/mips/generic/yamon-dt.c:100:7: error: Uninitialized variable: phys_memsize [uninitvar]

---
 arch/mips/generic/yamon-dt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index b408dac722ac7..e5fcaafea3a42 100644
@@ -81,7 +81,7 @@ static unsigned int __init gen_fdt_mem_array(
 __init int yamon_dt_append_memory(void *fdt,
 				  const struct yamon_mem_region *regions)
 {
-	unsigned long phys_memsize, memsize;
+	unsigned long phys_memsize = 0, memsize;
 	__be32 mem_array[2 * MAX_MEM_ARRAY_ENTRIES];
 	unsigned int mem_entries;
 	int i, err, mem_off;

2.33.0

From: Randy Dunlap <[email protected]>

[ Upstream commit e8f67482e5a4bc8d0b65d606d08cb60ee123b468 ]

BCM63XX selects HAVE_LEGACY_CLK but does not provide/support clk_get_parent(), so add a simple implementation of that function so that callers of it will build without errors.

Fixes these build errors:

mips-linux-ld: drivers/iio/adc/ingenic-adc.o: in function `jz4770_adc_init_clk_div':
ingenic-adc.c:(.text+0xe4): undefined reference to `clk_get_parent'
mips-linux-ld: drivers/iio/adc/ingenic-adc.o: in function `jz4725b_adc_init_clk_div':
ingenic-adc.c:(.text+0x1b8): undefined reference to `clk_get_parent'

---
 arch/mips/bcm63xx/clk.c | 6 ++++++
 1 file changed, 6 insertions(+)

index 19577f771c1f0..d2a5054b0492b 100644
@@ -337,6 +337,12 @@ void clk_disable(struct clk *clk)
 
 EXPORT_SYMBOL(clk_disable);
 
+struct clk *clk_get_parent(struct clk *clk)
+{
+	return NULL;
+}
+EXPORT_SYMBOL(clk_get_parent);
+
 unsigned long clk_get_rate(struct clk *clk)
 {
 	if (!clk)

2.33.0

From: Randy Dunlap <[email protected]>

[ Upstream commit fc1aabb088860d6cf9dd03612b7a6f0de91ccac2 ]

Provide a simple implementation of clk_get_parent() in the lantiq subarch so that callers of it will build without errors.

Fixes this build error:
ERROR: modpost: "clk_get_parent" [drivers/iio/adc/ingenic-adc.ko] undefined!

---
 arch/mips/lantiq/clk.c | 6 ++++++
 1 file changed, 6 insertions(+)

index a263d1b751ffe..a8e309dcd38d7 100644
@@ -160,6 +160,12 @@ void clk_deactivate(struct clk *clk)
 }
 EXPORT_SYMBOL(clk_deactivate);
 
+struct clk *clk_get_parent(struct clk *clk)
+{
+	return NULL;
+}
+EXPORT_SYMBOL(clk_get_parent);
+
 static inline u32 get_counter_resolution(void)
 {
 	u32 res;

2.33.0

From: Christophe JAILLET <[email protected]>

[ Upstream commit c961a7d2aa23ae19e0099fbcdf1040fb760eea83 ]

If 'led_classdev_register()' fails, some additional resources should be released.

Add the missing 'i8042_remove_filter()' and 'lis3lv02d_remove_fs()' calls that are already in the remove function but are missing here.

---
 drivers/platform/x86/hp_accel.c | 2 ++
 1 file changed, 2 insertions(+)

index 9c3c83ef445bf..075332c6890d0 100644
@@ -383,9 +383,11 @@ static int lis3lv02d_add(struct acpi_device *device)
 	INIT_WORK(&hpled_led.work, delayed_set_status_worker);
 	ret = led_classdev_register(NULL, &hpled_led.led_classdev);
 	if (ret) {
+		i8042_remove_filter(hp_accel_i8042_filter);
 		lis3lv02d_joystick_disable(&lis3_dev);
 		lis3lv02d_poweroff(&lis3_dev);
 		flush_work(&hpled_led.work);
+		lis3lv02d_remove_fs(&lis3_dev);
 		return ret;
 	}
 

2.33.0

From: Jonathan Davies <[email protected]>

[ Upstream commit cf9acc90c80ecbee00334aa85d92f4e74014bcff ]

virtio_net_hdr_to_skb does not set the skb's gso_size and gso_type correctly for UFO packets received via virtio-net that are a little over the GSO size. This can lead to problems elsewhere in the networking stack, e.g. ovs_vport_send dropping over-sized packets if gso_size is not set.

This is due to the comparison

if (skb->len - p_off > gso_size)

not properly accounting for the transport layer header.

p_off includes the size of the transport layer header (thlen), so skb->len - p_off is the size of the TCP/UDP payload.

gso_size is read from the virtio-net header. For UFO, fragmentation happens at the IP level so does not need to include the UDP header.

Hence the calculation could be comparing a TCP/UDP payload length with an IP payload length, causing legitimate virtio-net packets to have lack gso_type/gso_size information.

Example: a UDP packet with payload size 1473 has IP payload size 1481. If the guest used UFO, it is not fragmented and the virtio-net header's flags indicate that it is a GSO frame (VIRTIO_NET_HDR_GSO_UDP), with gso_size = 1480 for an MTU of 1500. skb->len will be 1515 and p_off will be 42, so skb->len - p_off = 1473. Hence the comparison fails, and shinfo->gso_size and gso_type are not set as they should be.

Instead, add the UDP header length before comparing to gso_size when using UFO. In this way, it is the size of the IP payload that is compared to gso_size.

---
 include/linux/virtio_net.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

index ca68826d84495..162761f72c142 100644
@@ -118,10 +118,15 @@ retry:
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size);
+		unsigned int nh_off = p_off;
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
 
+		/* UFO may not include transport header in gso_size. */
+		if (gso_type & SKB_GSO_UDP)
+			nh_off -= thlen;
+
 		/* Too small packets are not really GSO ones. */
-		if (skb->len - p_off > gso_size) {
+		if (skb->len - nh_off > gso_size) {
 			shinfo->gso_size = gso_size;
 			shinfo->gso_type = gso_type;
 

2.33.0

From: Michal Maloszewski <[email protected]>

[ Upstream commit 37d9e304acd903a445df8208b8a13d707902dea6 ]

Remove the reason of null pointer dereference in sync VSI filters. Added new I40E_VSI_RELEASING flag to signalize deleting and releasing of VSI resources to sync this thread with sync filters subtask. Without this patch it is possible to start update the VSI filter list after VSI is removed, that's causing a kernel oops.

---
 drivers/net/ethernet/intel/i40e/i40e.h      | 1 +
 drivers/net/ethernet/intel/i40e/i40e_main.c | 5 +++--
 2 files changed, 4 insertions(+), 2 deletions(-)

index d0c1bf5441d84..438e2675bc132 100644
@@ -163,6 +163,7 @@ enum i40e_vsi_state_t {
 	__I40E_VSI_OVERFLOW_PROMISC,
 	__I40E_VSI_REINIT_REQUESTED,
 	__I40E_VSI_DOWN_REQUESTED,
+	__I40E_VSI_RELEASING,
 	/* This must be last as it determines the size of the BITMAP */
 	__I40E_VSI_STATE_SIZE__,
 };

index 1555d32ddb962..44a9c8aa3067a 100644
@@ -2415,7 +2415,8 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf)
 
 	for (v = 0; v < pf->num_alloc_vsi; v++) {
 		if (pf->vsi[v] &&
-		    (pf->vsi[v]->flags & I40E_VSI_FLAG_FILTER_CHANGED)) {
+		    (pf->vsi[v]->flags & I40E_VSI_FLAG_FILTER_CHANGED) &&
+		    !test_bit(__I40E_VSI_RELEASING, pf->vsi[v]->state)) {
 			int ret = i40e_sync_vsi_filters(pf->vsi[v]);
 
 			if (ret) {

@@ -10098,7 +10099,7 @@ int i40e_vsi_release(struct i40e_vsi *vsi)
 		dev_info(&pf->pdev->dev, "Can't remove PF VSI\n");
 		return -ENODEV;
 	}
-
+	set_bit(__I40E_VSI_RELEASING, vsi->state);
 	uplink_seid = vsi->uplink_seid;
 	if (vsi->type != I40E_VSI_SRIOV) {
 		if (vsi->netdev_registered) {

2.33.0

From: Lin Ma <[email protected]>

[ Upstream commit 86cdf8e38792545161dbe3350a7eced558ba4d15 ]

There is a possible data race as shown below:

thread-A in nci_request()       | thread-B in nci_close_device()
                                | mutex_lock(&ndev->req_lock);
test_bit(NCI_UP, &ndev->flags); |
...                             | test_and_clear_bit(NCI_UP, &ndev->flags)
mutex_lock(&ndev->req_lock);    |
                                |

This race will allow __nci_request() to be awaked while the device is getting removed.

Similar to commit e2cb6b891ad2 ("bluetooth: eliminate the potential race condition when removing the HCI controller"). this patch alters the function sequence in nci_request() to prevent the data races between the nci_close_device().

---
 net/nfc/nci/core.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

index d3b7419f8b8f0..c73651faa5494 100644
@@ -156,12 +156,15 @@ inline int nci_request(struct nci_dev *ndev,
 {
 	int rc;
 
-	if (!test_bit(NCI_UP, &ndev->flags))
-		return -ENETDOWN;
-
 	/* Serialize all requests */
 	mutex_lock(&ndev->req_lock);
-	rc = __nci_request(ndev, req, opt, timeout);
+	/* check the state after obtaing the lock against any races
+	 * from nci_close_device when the device gets removed.
+	 */
+	if (test_bit(NCI_UP, &ndev->flags))
+		rc = __nci_request(ndev, req, opt, timeout);
+	else
+		rc = -ENETDOWN;
 	mutex_unlock(&ndev->req_lock);
 
 	return rc;

2.33.0

From: Lin Ma <[email protected]>

[ Upstream commit 3e3b5dfcd16a3e254aab61bd1e8c417dd4503102 ]

There is a potential UAF between the unregistration routine and the NFC netlink operations.

The race that cause that UAF can be shown as below:

 (FREE)                      |  (USE)
nfcmrvl_nci_unregister_dev   |  nfc_genl_dev_up
  nci_close_device           |
  nci_unregister_device      |    nfc_get_device
    nfc_unregister_device    |    nfc_dev_up
      rfkill_destory         |
      device_del             |      rfkill_blocked
  ...                        |    ...

The root cause for this race is concluded below:
1. The rfkill_blocked (USE) in nfc_dev_up is supposed to be placed after the device_is_registered check.
2. Since the netlink operations are possible just after the device_add in nfc_register_device, the nfc_dev_up() can happen anywhere during the rfkill creation process, which leads to data race.

This patch reorder these actions to permit
1. Once device_del is finished, the nfc_dev_up cannot dereference the rfkill object.
2. The rfkill_register need to be placed after the device_add of nfc_dev because the parent device need to be created first. So this patch keeps the order but inject device_lock to prevent the data race.

---
 net/nfc/core.c | 32 ++++++++++++++++++--------------
 1 file changed, 18 insertions(+), 14 deletions(-)

index c699d64a0753a..32a2dfc08f480 100644
@@ -106,13 +106,13 @@ int nfc_dev_up(struct nfc_dev *dev)
 
 	device_lock(&dev->dev);
 
-	if (dev->rfkill && rfkill_blocked(dev->rfkill)) {
-		rc = -ERFKILL;
+	if (!device_is_registered(&dev->dev)) {
+		rc = -ENODEV;
 		goto error;
 	}
 
-	if (!device_is_registered(&dev->dev)) {
-		rc = -ENODEV;
+	if (dev->rfkill && rfkill_blocked(dev->rfkill)) {
+		rc = -ERFKILL;
 		goto error;
 	}
 

@@ -1133,11 +1133,7 @@ int nfc_register_device(struct nfc_dev *dev)
 	if (rc)
 		pr_err("Could not register llcp device\n");
 
-	rc = nfc_genl_device_added(dev);
-	if (rc)
-		pr_debug("The userspace won't be notified that the device %s was added\n",
-			 dev_name(&dev->dev));
-
+	device_lock(&dev->dev);
 	dev->rfkill = rfkill_alloc(dev_name(&dev->dev), &dev->dev,
 				   RFKILL_TYPE_NFC, &nfc_rfkill_ops, dev);
 	if (dev->rfkill) {

@@ -1146,6 +1142,12 @@ int nfc_register_device(struct nfc_dev *dev)
 			dev->rfkill = NULL;
 		}
 	}
+	device_unlock(&dev->dev);
+
+	rc = nfc_genl_device_added(dev);
+	if (rc)
+		pr_debug("The userspace won't be notified that the device %s was added\n",
+			 dev_name(&dev->dev));
 
 	return 0;
 }

@@ -1162,10 +1164,17 @@ void nfc_unregister_device(struct nfc_dev *dev)
 
 	pr_debug("dev_name=%s\n", dev_name(&dev->dev));
 
+	rc = nfc_genl_device_removed(dev);
+	if (rc)
+		pr_debug("The userspace won't be notified that the device %s "
+			 "was removed\n", dev_name(&dev->dev));
+
+	device_lock(&dev->dev);
 	if (dev->rfkill) {
 		rfkill_unregister(dev->rfkill);
 		rfkill_destroy(dev->rfkill);
 	}
+	device_unlock(&dev->dev);
 
 	if (dev->ops->check_presence) {
 		device_lock(&dev->dev);

@@ -1175,11 +1184,6 @@ void nfc_unregister_device(struct nfc_dev *dev)
 		cancel_work_sync(&dev->check_pres_work);
 	}
 
-	rc = nfc_genl_device_removed(dev);
-	if (rc)
-		pr_debug("The userspace won't be notified that the device %s "
-			 "was removed\n", dev_name(&dev->dev));
-
 	nfc_llcp_unregister_device(dev);
 
 	mutex_lock(&nfc_devlist_mutex);

2.33.0

From: Sohaib Mohamed <[email protected]>

[ Upstream commit 92723ea0f11d92496687db8c9725248e9d1e5e1d ]

ASan reports memory leaks while running:

  $ perf bench sched all

---
 tools/perf/bench/sched-messaging.c | 4 ++++
 1 file changed, 4 insertions(+)

index f9d7641ae8338..b4e13db991e9e 100644
@@ -226,6 +226,8 @@ static unsigned int group(pthread_t *pth,
 		snd_ctx->out_fds[i] = fds[1];
 		if (!thread_mode)
 			close(fds[0]);
+
+		free(ctx);
 	}
 
 	/* Now we have all the fds, fork the senders */

@@ -242,6 +244,8 @@ static unsigned int group(pthread_t *pth,
 		for (i = 0; i < num_fds; i++)
 			close(snd_ctx->out_fds[i]);
 
+	free(snd_ctx);
+
 	/* Return number of children to reap */
 	return num_fds * 2;
 }

2.33.0

From: Alexander Antonov <[email protected]>

[ Upstream commit e324234e0aa881b7841c7c713306403e12b069ff ]

According Uncore Reference Manual: any of the CHA events may be filtered by Thread/Core-ID by using tid modifier in CHA Filter 0 Register. Update skx_cha_hw_config() to follow Uncore Guide.

---
 arch/x86/events/intel/uncore_snbep.c | 3 +++
 1 file changed, 3 insertions(+)

index 6b66285c6cede..9cce6d9fec1f4 100644
@@ -3383,6 +3383,9 @@ static int skx_cha_hw_config(struct intel_uncore_box *box, struct perf_event *ev
 	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
 	struct extra_reg *er;
 	int idx = 0;
+	/* Any of the CHA events may be filtered by Thread/Core-ID.*/
+	if (event->hw.config & SNBEP_CBO_PMON_CTL_TID_EN)
+		idx = SKX_CHA_MSR_PMON_BOX_FILTER_TID;
 
 	for (er = skx_uncore_cha_extra_regs; er->msr; er++) {
 		if (er->event != (event->hw.config & er->config_mask))

2.33.0

From: Alexander Antonov <[email protected]>

[ Upstream commit 3866ae319c846a612109c008f43cba80b8c15e86 ]

According to the latest uncore document, COMP_BUF_OCCUPANCY (0xd5) event can be collected on 2-3 counters. Update uncore IIO event constraints for Skylake Server.

---
 arch/x86/events/intel/uncore_snbep.c | 1 +
 1 file changed, 1 insertion(+)

index 9cce6d9fec1f4..b039d416fef34 100644
@@ -3453,6 +3453,7 @@ static struct event_constraint skx_uncore_iio_constraints[] = {
 	UNCORE_EVENT_CONSTRAINT(0xc0, 0xc),
 	UNCORE_EVENT_CONSTRAINT(0xc5, 0xc),
 	UNCORE_EVENT_CONSTRAINT(0xd4, 0xc),
+	UNCORE_EVENT_CONSTRAINT(0xd5, 0xc),
 	EVENT_CONSTRAINT_END
 };
 

2.33.0

From: Nicolas Dichtel <[email protected]>

commit a31d27fbed5d518734cb60956303eb15089a7634 upstream.

As stated in the bonding doc, trans_start must be set manually for drivers using NETIF_F_LLTX:
Drivers that use NETIF_F_LLTX flag must also update netdev_queue->trans_start. If they do not, then the ARP monitor will immediately fail any slaves using that driver, and those slaves will stay down.

---
 drivers/net/tun.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -858,6 +858,7 @@ static netdev_tx_t tun_net_xmit(struct s
 {
 	struct tun_struct *tun = netdev_priv(dev);
 	int txq = skb->queue_mapping;
+	struct netdev_queue *queue;
 	struct tun_file *tfile;
 	u32 numqueues = 0;
 

@@ -916,6 +917,10 @@ static netdev_tx_t tun_net_xmit(struct s
 	if (skb_array_produce(&tfile->tx_array, skb))
 		goto drop;
 
+	/* NETIF_F_LLTX requires to do our own update of trans_start */
+	queue = netdev_get_tx_queue(dev, txq);
+	queue->trans_start = jiffies;
+
 	/* Notify and wake up reader process */
 	if (tfile->flags & TUN_FASYNC)
 		kill_fasync(&tfile->fasync, SIGIO, POLL_IN);