From 9edebe46010c2b50b0d54ac859f666a43ea6e274 Mon Sep 17 00:00:00 2001 From: Pan Bian Date: Thu, 21 Jan 2021 04:33:43 -0800 Subject: [PATCH 01/33] net: dsa: bcm_sf2: put device node before return commit cf3c46631e1637582f517a574c77cd6c05793817 upstream. Put the device node dn before return error code on failure path. Fixes: 461cd1b03e32 ("net: dsa: bcm_sf2: Register our slave MDIO bus") Signed-off-by: Pan Bian Link: https://lore.kernel.org/r/20210121123343.26330-1-bianpan2016@163.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/dsa/bcm_sf2.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index b16aea0e3999..6dd29bad1609 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -421,15 +421,19 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds) /* Find our integrated MDIO bus node */ dn = of_find_compatible_node(NULL, NULL, "brcm,unimac-mdio"); priv->master_mii_bus = of_mdio_find_bus(dn); - if (!priv->master_mii_bus) + if (!priv->master_mii_bus) { + of_node_put(dn); return -EPROBE_DEFER; + } get_device(&priv->master_mii_bus->dev); priv->master_mii_dn = dn; priv->slave_mii_bus = devm_mdiobus_alloc(ds->dev); - if (!priv->slave_mii_bus) + if (!priv->slave_mii_bus) { + of_node_put(dn); return -ENOMEM; + } priv->slave_mii_bus->priv = priv; priv->slave_mii_bus->name = "sf2 slave mii"; From bc4e7277cc93b12b6c51b803c32b89700437d607 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Mon, 25 Jan 2021 13:41:16 +0100 Subject: [PATCH 02/33] net: switchdev: don't set port_obj_info->handled true when -EOPNOTSUPP commit 20776b465c0c249f5e5b5b4fe077cd24ef1cda86 upstream. It's not true that switchdev_port_obj_notify() only inspects the ->handled field of "struct switchdev_notifier_port_obj_info" if call_switchdev_blocking_notifiers() returns 0 - there's a WARN_ON() triggering for a non-zero return combined with ->handled not being true. But the real problem here is that -EOPNOTSUPP is not being properly handled. The wrapper functions switchdev_handle_port_obj_add() et al change a return value of -EOPNOTSUPP to 0, and the treatment of ->handled in switchdev_port_obj_notify() seems to be designed to change that back to -EOPNOTSUPP in case nobody actually acted on the notifier (i.e., everybody returned -EOPNOTSUPP). Currently, as soon as some device down the stack passes the check_cb() check, ->handled gets set to true, which means that switchdev_port_obj_notify() cannot actually ever return -EOPNOTSUPP. This, for example, means that the detection of hardware offload support in the MRP code is broken: switchdev_port_obj_add() used by br_mrp_switchdev_send_ring_test() always returns 0, so since the MRP code thinks the generation of MRP test frames has been offloaded, no such frames are actually put on the wire. Similarly, br_mrp_switchdev_set_ring_role() also always returns 0, causing mrp->ring_role_offloaded to be set to 1. To fix this, continue to set ->handled true if any callback returns success or any error distinct from -EOPNOTSUPP. But if all the callbacks return -EOPNOTSUPP, make sure that ->handled stays false, so the logic in switchdev_port_obj_notify() can propagate that information. Fixes: 9a9f26e8f7ea ("bridge: mrp: Connect MRP API with the switchdev API") Fixes: f30f0601eb93 ("switchdev: Add helpers to aid traversal through lower devices") Reviewed-by: Petr Machata Signed-off-by: Rasmus Villemoes Link: https://lore.kernel.org/r/20210125124116.102928-1-rasmus.villemoes@prevas.dk Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- net/switchdev/switchdev.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 3a1d428c1336..ea9ddea35a88 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -461,10 +461,11 @@ static int __switchdev_handle_port_obj_add(struct net_device *dev, extack = switchdev_notifier_info_to_extack(&port_obj_info->info); if (check_cb(dev)) { - /* This flag is only checked if the return value is success. */ - port_obj_info->handled = true; - return add_cb(dev, port_obj_info->obj, port_obj_info->trans, - extack); + err = add_cb(dev, port_obj_info->obj, port_obj_info->trans, + extack); + if (err != -EOPNOTSUPP) + port_obj_info->handled = true; + return err; } /* Switch ports might be stacked under e.g. a LAG. Ignore the @@ -513,9 +514,10 @@ static int __switchdev_handle_port_obj_del(struct net_device *dev, int err = -EOPNOTSUPP; if (check_cb(dev)) { - /* This flag is only checked if the return value is success. */ - port_obj_info->handled = true; - return del_cb(dev, port_obj_info->obj); + err = del_cb(dev, port_obj_info->obj); + if (err != -EOPNOTSUPP) + port_obj_info->handled = true; + return err; } /* Switch ports might be stacked under e.g. a LAG. Ignore the @@ -563,9 +565,10 @@ static int __switchdev_handle_port_attr_set(struct net_device *dev, int err = -EOPNOTSUPP; if (check_cb(dev)) { - port_attr_info->handled = true; - return set_cb(dev, port_attr_info->attr, - port_attr_info->trans); + err = set_cb(dev, port_attr_info->attr, port_attr_info->trans); + if (err != -EOPNOTSUPP) + port_attr_info->handled = true; + return err; } /* Switch ports might be stacked under e.g. a LAG. Ignore the From 5e8776df14fa8b88b00ba833f6947c88fec95570 Mon Sep 17 00:00:00 2001 From: Lijun Pan Date: Wed, 27 Jan 2021 19:34:42 -0600 Subject: [PATCH 03/33] ibmvnic: Ensure that CRQ entry read are correctly ordered commit e41aec79e62fa50f940cf222d1e9577f14e149dc upstream. Ensure that received Command-Response Queue (CRQ) entries are properly read in order by the driver. dma_rmb barrier has been added before accessing the CRQ descriptor to ensure the entire descriptor is read before processing. Fixes: 032c5e82847a ("Driver for IBM System i/p VNIC protocol") Signed-off-by: Lijun Pan Link: https://lore.kernel.org/r/20210128013442.88319-1-ljp@linux.ibm.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/ibm/ibmvnic.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 9040340fad19..c3079f436f6d 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -4752,6 +4752,12 @@ static void ibmvnic_tasklet(void *data) while (!done) { /* Pull all the valid messages off the CRQ */ while ((crq = ibmvnic_next_crq(adapter)) != NULL) { + /* This barrier makes sure ibmvnic_next_crq()'s + * crq->generic.first & IBMVNIC_CRQ_CMD_RSP is loaded + * before ibmvnic_handle_crq()'s + * switch(gen_crq->first) and switch(gen_crq->cmd). + */ + dma_rmb(); ibmvnic_handle_crq(crq, adapter); crq->generic.first = 0; } From 1410d2b68207cbb3bc16a4db7d655f5e06a39929 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 4 Feb 2021 16:02:10 +0100 Subject: [PATCH 04/33] Revert "Revert "block: end bio with BLK_STS_AGAIN in case of non-mq devs and REQ_NOWAIT"" This reverts commit bba91cdba612fbce4f8575c5d94d2b146fb83ea3 which is commit b0beb28097fa04177b3769f4bb7a0d0d9c4ae76e upstream. It breaks things in 5.4.y, so let's drop it. Reported-by: Andres Freund Cc: Bijan Mottahedeh CC: Jens Axboe Cc: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- block/blk-core.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index d2213220099d..5808baa950c3 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -886,11 +886,14 @@ generic_make_request_checks(struct bio *bio) } /* - * For a REQ_NOWAIT based request, return -EOPNOTSUPP - * if queue is not a request based queue. + * Non-mq queues do not honor REQ_NOWAIT, so complete a bio + * with BLK_STS_AGAIN status in order to catch -EAGAIN and + * to give a chance to the caller to repeat request gracefully. */ - if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q)) - goto not_supported; + if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q)) { + status = BLK_STS_AGAIN; + goto end_io; + } if (should_fail_bio(bio)) goto end_io; From 11084836e5fbbfd644935e9b78cbd43cb7b4023c Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 14 Jan 2021 19:34:22 +0100 Subject: [PATCH 05/33] ACPI: thermal: Do not call acpi_thermal_check() directly commit 81b704d3e4674e09781d331df73d76675d5ad8cb upstream. Calling acpi_thermal_check() from acpi_thermal_notify() directly is problematic if _TMP triggers Notify () on the thermal zone for which it has been evaluated (which happens on some systems), because it causes a new acpi_thermal_notify() invocation to be queued up every time and if that takes place too often, an indefinite number of pending work items may accumulate in kacpi_notify_wq over time. Besides, it is not really useful to queue up a new invocation of acpi_thermal_check() if one of them is pending already. For these reasons, rework acpi_thermal_notify() to queue up a thermal check instead of calling acpi_thermal_check() directly and only allow one thermal check to be pending at a time. Moreover, only allow one acpi_thermal_check_fn() instance at a time to run thermal_zone_device_update() for one thermal zone and make it return early if it sees other instances running for the same thermal zone. While at it, fold acpi_thermal_check() into acpi_thermal_check_fn(), as it is only called from there after the other changes made here. [This issue appears to have been exposed by commit 6d25be5782e4 ("sched/core, workqueues: Distangle worker accounting from rq lock"), but it is unclear why it was not visible earlier.] BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=208877 Reported-by: Stephen Berman Diagnosed-by: Sebastian Andrzej Siewior Signed-off-by: Rafael J. Wysocki Reviewed-by: Sebastian Andrzej Siewior Tested-by: Stephen Berman Cc: All applicable [bigeasy: Backported to v5.4.y] Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Greg Kroah-Hartman --- drivers/acpi/thermal.c | 55 +++++++++++++++++++++++++++++------------- 1 file changed, 38 insertions(+), 17 deletions(-) diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c index d831a61e0010..383c7029d3ce 100644 --- a/drivers/acpi/thermal.c +++ b/drivers/acpi/thermal.c @@ -174,6 +174,8 @@ struct acpi_thermal { int tz_enabled; int kelvin_offset; struct work_struct thermal_check_work; + struct mutex thermal_check_lock; + refcount_t thermal_check_count; }; /* -------------------------------------------------------------------------- @@ -494,17 +496,6 @@ static int acpi_thermal_get_trip_points(struct acpi_thermal *tz) return 0; } -static void acpi_thermal_check(void *data) -{ - struct acpi_thermal *tz = data; - - if (!tz->tz_enabled) - return; - - thermal_zone_device_update(tz->thermal_zone, - THERMAL_EVENT_UNSPECIFIED); -} - /* sys I/F for generic thermal sysfs support */ static int thermal_get_temp(struct thermal_zone_device *thermal, int *temp) @@ -538,6 +529,8 @@ static int thermal_get_mode(struct thermal_zone_device *thermal, return 0; } +static void acpi_thermal_check_fn(struct work_struct *work); + static int thermal_set_mode(struct thermal_zone_device *thermal, enum thermal_device_mode mode) { @@ -563,7 +556,7 @@ static int thermal_set_mode(struct thermal_zone_device *thermal, ACPI_DEBUG_PRINT((ACPI_DB_INFO, "%s kernel ACPI thermal control\n", tz->tz_enabled ? "Enable" : "Disable")); - acpi_thermal_check(tz); + acpi_thermal_check_fn(&tz->thermal_check_work); } return 0; } @@ -932,6 +925,12 @@ static void acpi_thermal_unregister_thermal_zone(struct acpi_thermal *tz) Driver Interface -------------------------------------------------------------------------- */ +static void acpi_queue_thermal_check(struct acpi_thermal *tz) +{ + if (!work_pending(&tz->thermal_check_work)) + queue_work(acpi_thermal_pm_queue, &tz->thermal_check_work); +} + static void acpi_thermal_notify(struct acpi_device *device, u32 event) { struct acpi_thermal *tz = acpi_driver_data(device); @@ -942,17 +941,17 @@ static void acpi_thermal_notify(struct acpi_device *device, u32 event) switch (event) { case ACPI_THERMAL_NOTIFY_TEMPERATURE: - acpi_thermal_check(tz); + acpi_queue_thermal_check(tz); break; case ACPI_THERMAL_NOTIFY_THRESHOLDS: acpi_thermal_trips_update(tz, ACPI_TRIPS_REFRESH_THRESHOLDS); - acpi_thermal_check(tz); + acpi_queue_thermal_check(tz); acpi_bus_generate_netlink_event(device->pnp.device_class, dev_name(&device->dev), event, 0); break; case ACPI_THERMAL_NOTIFY_DEVICES: acpi_thermal_trips_update(tz, ACPI_TRIPS_REFRESH_DEVICES); - acpi_thermal_check(tz); + acpi_queue_thermal_check(tz); acpi_bus_generate_netlink_event(device->pnp.device_class, dev_name(&device->dev), event, 0); break; @@ -1052,7 +1051,27 @@ static void acpi_thermal_check_fn(struct work_struct *work) { struct acpi_thermal *tz = container_of(work, struct acpi_thermal, thermal_check_work); - acpi_thermal_check(tz); + + if (!tz->tz_enabled) + return; + /* + * In general, it is not sufficient to check the pending bit, because + * subsequent instances of this function may be queued after one of them + * has started running (e.g. if _TMP sleeps). Avoid bailing out if just + * one of them is running, though, because it may have done the actual + * check some time ago, so allow at least one of them to block on the + * mutex while another one is running the update. + */ + if (!refcount_dec_not_one(&tz->thermal_check_count)) + return; + + mutex_lock(&tz->thermal_check_lock); + + thermal_zone_device_update(tz->thermal_zone, THERMAL_EVENT_UNSPECIFIED); + + refcount_inc(&tz->thermal_check_count); + + mutex_unlock(&tz->thermal_check_lock); } static int acpi_thermal_add(struct acpi_device *device) @@ -1084,6 +1103,8 @@ static int acpi_thermal_add(struct acpi_device *device) if (result) goto free_memory; + refcount_set(&tz->thermal_check_count, 3); + mutex_init(&tz->thermal_check_lock); INIT_WORK(&tz->thermal_check_work, acpi_thermal_check_fn); pr_info(PREFIX "%s [%s] (%ld C)\n", acpi_device_name(device), @@ -1149,7 +1170,7 @@ static int acpi_thermal_resume(struct device *dev) tz->state.active |= tz->trips.active[i].flags.enabled; } - queue_work(acpi_thermal_pm_queue, &tz->thermal_check_work); + acpi_queue_thermal_check(tz); return AE_OK; } From b28387cf8f1c76e48e06f2f4cd6f4ac4fee0562f Mon Sep 17 00:00:00 2001 From: Vincenzo Frascino Date: Tue, 26 Jan 2021 13:40:56 +0000 Subject: [PATCH 06/33] arm64: Fix kernel address detection of __is_lm_address() commit 519ea6f1c82fcdc9842908155ae379de47818778 upstream. Currently, the __is_lm_address() check just masks out the top 12 bits of the address, but if they are 0, it still yields a true result. This has as a side effect that virt_addr_valid() returns true even for invalid virtual addresses (e.g. 0x0). Fix the detection checking that it's actually a kernel address starting at PAGE_OFFSET. Fixes: 68dd8ef32162 ("arm64: memory: Fix virt_addr_valid() using __is_lm_address()") Cc: # 5.4.x Cc: Will Deacon Suggested-by: Catalin Marinas Reviewed-by: Catalin Marinas Acked-by: Mark Rutland Signed-off-by: Vincenzo Frascino Link: https://lore.kernel.org/r/20210126134056.45747-1-vincenzo.frascino@arm.com Signed-off-by: Catalin Marinas Signed-off-by: Greg Kroah-Hartman --- arch/arm64/include/asm/memory.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 51d867cf146c..a77a2ae864e3 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -247,11 +247,11 @@ static inline const void *__tag_set(const void *addr, u8 tag) /* - * The linear kernel range starts at the bottom of the virtual address - * space. Testing the top bit for the start of the region is a - * sufficient check and avoids having to worry about the tag. + * Check whether an arbitrary address is within the linear map, which + * lives in the [PAGE_OFFSET, PAGE_END) interval at the bottom of the + * kernel's TTBR1 address range. */ -#define __is_lm_address(addr) (!(((u64)addr) & BIT(vabits_actual - 1))) +#define __is_lm_address(addr) (((u64)(addr) ^ PAGE_OFFSET) < (PAGE_END - PAGE_OFFSET)) #define __lm_to_phys(addr) (((addr) & ~PAGE_OFFSET) + PHYS_OFFSET) #define __kimg_to_phys(addr) ((addr) - kimage_voffset) From 55cb8e232f9ac72f432b081877faa18848058bd3 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Mon, 1 Feb 2021 19:06:33 +0000 Subject: [PATCH 07/33] arm64: Do not pass tagged addresses to __is_lm_address() commit 91cb2c8b072e00632adf463b78b44f123d46a0fa upstream. Commit 519ea6f1c82f ("arm64: Fix kernel address detection of __is_lm_address()") fixed the incorrect validation of addresses below PAGE_OFFSET. However, it no longer allowed tagged addresses to be passed to virt_addr_valid(). Fix this by explicitly resetting the pointer tag prior to invoking __is_lm_address(). This is consistent with the __lm_to_phys() macro. Fixes: 519ea6f1c82f ("arm64: Fix kernel address detection of __is_lm_address()") Signed-off-by: Catalin Marinas Acked-by: Ard Biesheuvel Cc: # 5.4.x Cc: Will Deacon Cc: Vincenzo Frascino Cc: Mark Rutland Link: https://lore.kernel.org/r/20210201190634.22942-2-catalin.marinas@arm.com Signed-off-by: Greg Kroah-Hartman --- arch/arm64/include/asm/memory.h | 2 +- arch/arm64/mm/physaddr.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index a77a2ae864e3..6c295a231882 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -332,7 +332,7 @@ static inline void *phys_to_virt(phys_addr_t x) #endif /* !CONFIG_SPARSEMEM_VMEMMAP || CONFIG_DEBUG_VIRTUAL */ #define virt_addr_valid(addr) ({ \ - __typeof__(addr) __addr = addr; \ + __typeof__(addr) __addr = __tag_reset(addr); \ __is_lm_address(__addr) && pfn_valid(virt_to_pfn(__addr)); \ }) diff --git a/arch/arm64/mm/physaddr.c b/arch/arm64/mm/physaddr.c index 67a9ba9eaa96..cde44c13dda1 100644 --- a/arch/arm64/mm/physaddr.c +++ b/arch/arm64/mm/physaddr.c @@ -9,7 +9,7 @@ phys_addr_t __virt_to_phys(unsigned long x) { - WARN(!__is_lm_address(x), + WARN(!__is_lm_address(__tag_reset(x)), "virt_to_phys used for non-linear address: %pK (%pS)\n", (void *)x, (void *)x); From 1960c3d40b6999dba2c7ca2ad333e394bfcc358d Mon Sep 17 00:00:00 2001 From: Enke Chen Date: Fri, 22 Jan 2021 11:13:06 -0800 Subject: [PATCH 08/33] tcp: make TCP_USER_TIMEOUT accurate for zero window probes commit 344db93ae3ee69fc137bd6ed89a8ff1bf5b0db08 upstream. The TCP_USER_TIMEOUT is checked by the 0-window probe timer. As the timer has backoff with a max interval of about two minutes, the actual timeout for TCP_USER_TIMEOUT can be off by up to two minutes. In this patch the TCP_USER_TIMEOUT is made more accurate by taking it into account when computing the timer value for the 0-window probes. This patch is similar to and builds on top of the one that made TCP_USER_TIMEOUT accurate for RTOs in commit b701a99e431d ("tcp: Add tcp_clamp_rto_to_user_timeout() helper to improve accuracy"). Fixes: 9721e709fa68 ("tcp: simplify window probe aborting on USER_TIMEOUT") Signed-off-by: Enke Chen Reviewed-by: Neal Cardwell Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20210122191306.GA99540@localhost.localdomain Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- include/net/tcp.h | 1 + net/ipv4/tcp_input.c | 1 + net/ipv4/tcp_output.c | 2 ++ net/ipv4/tcp_timer.c | 18 ++++++++++++++++++ 4 files changed, 22 insertions(+) diff --git a/include/net/tcp.h b/include/net/tcp.h index 4b38ba101b9b..37b51456784f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -619,6 +619,7 @@ static inline void tcp_clear_xmit_timers(struct sock *sk) unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu); unsigned int tcp_current_mss(struct sock *sk); +u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when); /* Bound MSS / TSO packet size with the half of the window */ static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 26305aa88651..a1768ded2d54 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3295,6 +3295,7 @@ static void tcp_ack_probe(struct sock *sk) } else { unsigned long when = tcp_probe0_when(sk, TCP_RTO_MAX); + when = tcp_clamp_probe0_to_user_timeout(sk, when); tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, when, TCP_RTO_MAX, NULL); } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5da6ffce390c..d0774b4e934d 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3850,6 +3850,8 @@ void tcp_send_probe0(struct sock *sk) */ timeout = TCP_RESOURCE_PROBE_INTERVAL; } + + timeout = tcp_clamp_probe0_to_user_timeout(sk, timeout); tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout, TCP_RTO_MAX, NULL); } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 7fcd116fbd37..fa2ae96ecdc4 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -40,6 +40,24 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(remaining)); } +u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + u32 remaining; + s32 elapsed; + + if (!icsk->icsk_user_timeout || !icsk->icsk_probes_tstamp) + return when; + + elapsed = tcp_jiffies32 - icsk->icsk_probes_tstamp; + if (unlikely(elapsed < 0)) + elapsed = 0; + remaining = msecs_to_jiffies(icsk->icsk_user_timeout) - elapsed; + remaining = max_t(u32, remaining, TCP_TIMEOUT_MIN); + + return min_t(u32, remaining, when); +} + /** * tcp_write_err() - close socket and save error info * @sk: The socket the error has appeared on. From 21a0c97fb27c16475d4bae3930654e1d1cf2c329 Mon Sep 17 00:00:00 2001 From: ethanwu Date: Fri, 7 Feb 2020 17:38:15 +0800 Subject: [PATCH 09/33] btrfs: backref, only collect file extent items matching backref offset commit 7ac8b88ee668a5b4743ebf3e9888fabac85c334a upstream. When resolving one backref of type EXTENT_DATA_REF, we collect all references that simply reference the EXTENT_ITEM even though their (file_pos - file_extent_item::offset) are not the same as the btrfs_extent_data_ref::offset we are searching for. This patch adds additional check so that we only collect references whose (file_pos - file_extent_item::offset) == btrfs_extent_data_ref::offset. Reviewed-by: Josef Bacik Reviewed-by: Johannes Thumshirn Signed-off-by: ethanwu Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/backref.c | 63 ++++++++++++++++++++++++---------------------- 1 file changed, 33 insertions(+), 30 deletions(-) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 86e280edf804..5517b9fd37cd 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -347,33 +347,10 @@ static int add_prelim_ref(const struct btrfs_fs_info *fs_info, return -ENOMEM; ref->root_id = root_id; - if (key) { + if (key) ref->key_for_search = *key; - /* - * We can often find data backrefs with an offset that is too - * large (>= LLONG_MAX, maximum allowed file offset) due to - * underflows when subtracting a file's offset with the data - * offset of its corresponding extent data item. This can - * happen for example in the clone ioctl. - * So if we detect such case we set the search key's offset to - * zero to make sure we will find the matching file extent item - * at add_all_parents(), otherwise we will miss it because the - * offset taken form the backref is much larger then the offset - * of the file extent item. This can make us scan a very large - * number of file extent items, but at least it will not make - * us miss any. - * This is an ugly workaround for a behaviour that should have - * never existed, but it does and a fix for the clone ioctl - * would touch a lot of places, cause backwards incompatibility - * and would not fix the problem for extents cloned with older - * kernels. - */ - if (ref->key_for_search.type == BTRFS_EXTENT_DATA_KEY && - ref->key_for_search.offset >= LLONG_MAX) - ref->key_for_search.offset = 0; - } else { + else memset(&ref->key_for_search, 0, sizeof(ref->key_for_search)); - } ref->inode_list = NULL; ref->level = level; @@ -424,6 +401,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, u64 disk_byte; u64 wanted_disk_byte = ref->wanted_disk_byte; u64 count = 0; + u64 data_offset; if (level != 0) { eb = path->nodes[level]; @@ -457,11 +435,15 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item); disk_byte = btrfs_file_extent_disk_bytenr(eb, fi); + data_offset = btrfs_file_extent_offset(eb, fi); if (disk_byte == wanted_disk_byte) { eie = NULL; old = NULL; - count++; + if (ref->key_for_search.offset == key.offset - data_offset) + count++; + else + goto next; if (extent_item_pos) { ret = check_extent_in_eb(&key, eb, fi, *extent_item_pos, @@ -513,6 +495,7 @@ static int resolve_indirect_ref(struct btrfs_fs_info *fs_info, int root_level; int level = ref->level; int index; + struct btrfs_key search_key = ref->key_for_search; root_key.objectid = ref->root_id; root_key.type = BTRFS_ROOT_ITEM_KEY; @@ -545,13 +528,33 @@ static int resolve_indirect_ref(struct btrfs_fs_info *fs_info, goto out; } + /* + * We can often find data backrefs with an offset that is too large + * (>= LLONG_MAX, maximum allowed file offset) due to underflows when + * subtracting a file's offset with the data offset of its + * corresponding extent data item. This can happen for example in the + * clone ioctl. + * + * So if we detect such case we set the search key's offset to zero to + * make sure we will find the matching file extent item at + * add_all_parents(), otherwise we will miss it because the offset + * taken form the backref is much larger then the offset of the file + * extent item. This can make us scan a very large number of file + * extent items, but at least it will not make us miss any. + * + * This is an ugly workaround for a behaviour that should have never + * existed, but it does and a fix for the clone ioctl would touch a lot + * of places, cause backwards incompatibility and would not fix the + * problem for extents cloned with older kernels. + */ + if (search_key.type == BTRFS_EXTENT_DATA_KEY && + search_key.offset >= LLONG_MAX) + search_key.offset = 0; path->lowest_level = level; if (time_seq == SEQ_LAST) - ret = btrfs_search_slot(NULL, root, &ref->key_for_search, path, - 0, 0); + ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); else - ret = btrfs_search_old_slot(root, &ref->key_for_search, path, - time_seq); + ret = btrfs_search_old_slot(root, &search_key, path, time_seq); /* root node has been locked, we can release @subvol_srcu safely here */ srcu_read_unlock(&fs_info->subvol_srcu, index); From c3089b06d6fe02145db27bc1dd9ad6458e8659ae Mon Sep 17 00:00:00 2001 From: ethanwu Date: Fri, 7 Feb 2020 17:38:16 +0800 Subject: [PATCH 10/33] btrfs: backref, don't add refs from shared block when resolving normal backref commit ed58f2e66e849c34826083e5a6c1b506ee8a4d8e upstream. All references from the block of SHARED_DATA_REF belong to that shared block backref. For example: item 11 key (40831553536 EXTENT_ITEM 4194304) itemoff 15460 itemsize 95 extent refs 24 gen 7302 flags DATA extent data backref root 257 objectid 260 offset 65536 count 5 extent data backref root 258 objectid 265 offset 0 count 9 shared data backref parent 394985472 count 10 Block 394985472 might be leaf from root 257, and the item obejctid and (file_pos - file_extent_item::offset) in that leaf just happens to be 260 and 65536 which is equal to the first extent data backref entry. Before this patch, when we resolve backref: root 257 objectid 260 offset 65536 we will add those refs in block 394985472 and wrongly treat those as the refs we want. Fix this by checking if the leaf we are processing is shared data backref, if so, just skip this leaf. Shared data refs added into preftrees.direct have all entry value = 0 (root_id = 0, key = NULL, level = 0) except parent entry. Other refs from indirect tree will have key value and root id != 0, and these values won't be changed when their parent is resolved and added to preftrees.direct. Therefore, we could reuse the preftrees.direct and search ref with all values = 0 except parent is set to avoid getting those resolved refs block. Reviewed-by: Josef Bacik Reviewed-by: Johannes Thumshirn Signed-off-by: ethanwu Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/backref.c | 61 +++++++++++++++++++++++++++++++++++++++------- 1 file changed, 52 insertions(+), 9 deletions(-) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 5517b9fd37cd..f9039ac7d86c 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -386,8 +386,34 @@ static int add_indirect_ref(const struct btrfs_fs_info *fs_info, wanted_disk_byte, count, sc, gfp_mask); } +static int is_shared_data_backref(struct preftrees *preftrees, u64 bytenr) +{ + struct rb_node **p = &preftrees->direct.root.rb_root.rb_node; + struct rb_node *parent = NULL; + struct prelim_ref *ref = NULL; + struct prelim_ref target = {0}; + int result; + + target.parent = bytenr; + + while (*p) { + parent = *p; + ref = rb_entry(parent, struct prelim_ref, rbnode); + result = prelim_ref_compare(ref, &target); + + if (result < 0) + p = &(*p)->rb_left; + else if (result > 0) + p = &(*p)->rb_right; + else + return 1; + } + return 0; +} + static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, - struct ulist *parents, struct prelim_ref *ref, + struct ulist *parents, + struct preftrees *preftrees, struct prelim_ref *ref, int level, u64 time_seq, const u64 *extent_item_pos, u64 total_refs, bool ignore_offset) { @@ -412,11 +438,16 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, } /* - * We normally enter this function with the path already pointing to - * the first item to check. But sometimes, we may enter it with - * slot==nritems. In that case, go to the next leaf before we continue. + * 1. We normally enter this function with the path already pointing to + * the first item to check. But sometimes, we may enter it with + * slot == nritems. + * 2. We are searching for normal backref but bytenr of this leaf + * matches shared data backref + * For these cases, go to the next leaf before we continue. */ - if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { + eb = path->nodes[0]; + if (path->slots[0] >= btrfs_header_nritems(eb) || + is_shared_data_backref(preftrees, eb->start)) { if (time_seq == SEQ_LAST) ret = btrfs_next_leaf(root, path); else @@ -433,6 +464,17 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, key.type != BTRFS_EXTENT_DATA_KEY) break; + /* + * We are searching for normal backref but bytenr of this leaf + * matches shared data backref. + */ + if (slot == 0 && is_shared_data_backref(preftrees, eb->start)) { + if (time_seq == SEQ_LAST) + ret = btrfs_next_leaf(root, path); + else + ret = btrfs_next_old_leaf(root, path, time_seq); + continue; + } fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item); disk_byte = btrfs_file_extent_disk_bytenr(eb, fi); data_offset = btrfs_file_extent_offset(eb, fi); @@ -484,6 +526,7 @@ next: */ static int resolve_indirect_ref(struct btrfs_fs_info *fs_info, struct btrfs_path *path, u64 time_seq, + struct preftrees *preftrees, struct prelim_ref *ref, struct ulist *parents, const u64 *extent_item_pos, u64 total_refs, bool ignore_offset) @@ -577,8 +620,8 @@ static int resolve_indirect_ref(struct btrfs_fs_info *fs_info, eb = path->nodes[level]; } - ret = add_all_parents(root, path, parents, ref, level, time_seq, - extent_item_pos, total_refs, ignore_offset); + ret = add_all_parents(root, path, parents, preftrees, ref, level, + time_seq, extent_item_pos, total_refs, ignore_offset); out: path->lowest_level = 0; btrfs_release_path(path); @@ -656,8 +699,8 @@ static int resolve_indirect_refs(struct btrfs_fs_info *fs_info, ret = BACKREF_FOUND_SHARED; goto out; } - err = resolve_indirect_ref(fs_info, path, time_seq, ref, - parents, extent_item_pos, + err = resolve_indirect_ref(fs_info, path, time_seq, preftrees, + ref, parents, extent_item_pos, total_refs, ignore_offset); /* * we can only tolerate ENOENT,otherwise,we should catch error From 66bcf5f6f989c470509100224921dfdb2fe4edae Mon Sep 17 00:00:00 2001 From: ethanwu Date: Fri, 7 Feb 2020 17:38:17 +0800 Subject: [PATCH 11/33] btrfs: backref, only search backref entries from leaves of the same root commit cfc0eed0ec89db7c4a8d461174cabfaa4a0912c7 upstream. We could have some nodes/leaves in subvolume whose owner are not the that subvolume. In this way, when we resolve normal backrefs of that subvolume, we should avoid collecting those references from these blocks. Reviewed-by: Josef Bacik Reviewed-by: Johannes Thumshirn Signed-off-by: ethanwu Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/backref.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index f9039ac7d86c..bc0d954a1334 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -443,11 +443,14 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, * slot == nritems. * 2. We are searching for normal backref but bytenr of this leaf * matches shared data backref + * 3. The leaf owner is not equal to the root we are searching + * * For these cases, go to the next leaf before we continue. */ eb = path->nodes[0]; if (path->slots[0] >= btrfs_header_nritems(eb) || - is_shared_data_backref(preftrees, eb->start)) { + is_shared_data_backref(preftrees, eb->start) || + ref->root_id != btrfs_header_owner(eb)) { if (time_seq == SEQ_LAST) ret = btrfs_next_leaf(root, path); else @@ -466,9 +469,12 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, /* * We are searching for normal backref but bytenr of this leaf - * matches shared data backref. + * matches shared data backref, OR + * the leaf owner is not equal to the root we are searching for */ - if (slot == 0 && is_shared_data_backref(preftrees, eb->start)) { + if (slot == 0 && + (is_shared_data_backref(preftrees, eb->start) || + ref->root_id != btrfs_header_owner(eb))) { if (time_seq == SEQ_LAST) ret = btrfs_next_leaf(root, path); else From 27afc71283452fcb55f7ed191d10538ce2f239fa Mon Sep 17 00:00:00 2001 From: ethanwu Date: Fri, 7 Feb 2020 17:38:18 +0800 Subject: [PATCH 12/33] btrfs: backref, use correct count to resolve normal data refs commit b25b0b871f206936d5bca02b80d38c05623e27da upstream. With the following patches: - btrfs: backref, only collect file extent items matching backref offset - btrfs: backref, not adding refs from shared block when resolving normal backref - btrfs: backref, only search backref entries from leaves of the same root we only collect the normal data refs we want, so the imprecise upper bound total_refs of that EXTENT_ITEM could now be changed to the count of the normal backref entry we want to search. Background and how the patches fit together: Btrfs has two types of data backref. For BTRFS_EXTENT_DATA_REF_KEY type of backref, we don't have the exact block number. Therefore, we need to call resolve_indirect_refs. It uses btrfs_search_slot to locate the leaf block. Then we need to walk through the leaves to search for the EXTENT_DATA items that have disk bytenr matching the extent item (add_all_parents). When resolving indirect refs, we could take entries that don't belong to the backref entry we are searching for right now. For that reason when searching backref entry, we always use total refs of that EXTENT_ITEM rather than individual count. For example: item 11 key (40831553536 EXTENT_ITEM 4194304) itemoff 15460 itemsize extent refs 24 gen 7302 flags DATA shared data backref parent 394985472 count 10 #1 extent data backref root 257 objectid 260 offset 1048576 count 3 #2 extent data backref root 256 objectid 260 offset 65536 count 6 #3 extent data backref root 257 objectid 260 offset 65536 count 5 #4 For example, when searching backref entry #4, we'll use total_refs 24, a very loose loop ending condition, instead of total_refs = 5. But using total_refs = 24 is not accurate. Sometimes, we'll never find all the refs from specific root. As a result, the loop keeps on going until we reach the end of that inode. The first 3 patches, handle 3 different types refs we might encounter. These refs do not belong to the normal backref we are searching, and hence need to be skipped. This patch changes the total_refs to correct number so that we could end loop as soon as we find all the refs we want. btrfs send uses backref to find possible clone sources, the following is a simple test to compare the results with and without this patch: $ btrfs subvolume create /sub1 $ for i in `seq 1 163840`; do dd if=/dev/zero of=/sub1/file bs=64K count=1 seek=$((i-1)) conv=notrunc oflag=direct done $ btrfs subvolume snapshot /sub1 /sub2 $ for i in `seq 1 163840`; do dd if=/dev/zero of=/sub1/file bs=4K count=1 seek=$(((i-1)*16+10)) conv=notrunc oflag=direct done $ btrfs subvolume snapshot -r /sub1 /snap1 $ time btrfs send /snap1 | btrfs receive /volume2 Without this patch: real 69m48.124s user 0m50.199s sys 70m15.600s With this patch: real 1m59.683s user 0m35.421s sys 2m42.684s Reviewed-by: Josef Bacik Reviewed-by: Johannes Thumshirn Signed-off-by: ethanwu [ add patchset cover letter with background and numbers ] Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/backref.c | 29 +++++++++++------------------ 1 file changed, 11 insertions(+), 18 deletions(-) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index bc0d954a1334..7f644a58db51 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -415,7 +415,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, struct ulist *parents, struct preftrees *preftrees, struct prelim_ref *ref, int level, u64 time_seq, const u64 *extent_item_pos, - u64 total_refs, bool ignore_offset) + bool ignore_offset) { int ret = 0; int slot; @@ -457,7 +457,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, ret = btrfs_next_old_leaf(root, path, time_seq); } - while (!ret && count < total_refs) { + while (!ret && count < ref->count) { eb = path->nodes[0]; slot = path->slots[0]; @@ -534,8 +534,7 @@ static int resolve_indirect_ref(struct btrfs_fs_info *fs_info, struct btrfs_path *path, u64 time_seq, struct preftrees *preftrees, struct prelim_ref *ref, struct ulist *parents, - const u64 *extent_item_pos, u64 total_refs, - bool ignore_offset) + const u64 *extent_item_pos, bool ignore_offset) { struct btrfs_root *root; struct btrfs_key root_key; @@ -627,7 +626,7 @@ static int resolve_indirect_ref(struct btrfs_fs_info *fs_info, } ret = add_all_parents(root, path, parents, preftrees, ref, level, - time_seq, extent_item_pos, total_refs, ignore_offset); + time_seq, extent_item_pos, ignore_offset); out: path->lowest_level = 0; btrfs_release_path(path); @@ -661,7 +660,7 @@ unode_aux_to_inode_list(struct ulist_node *node) static int resolve_indirect_refs(struct btrfs_fs_info *fs_info, struct btrfs_path *path, u64 time_seq, struct preftrees *preftrees, - const u64 *extent_item_pos, u64 total_refs, + const u64 *extent_item_pos, struct share_check *sc, bool ignore_offset) { int err; @@ -707,7 +706,7 @@ static int resolve_indirect_refs(struct btrfs_fs_info *fs_info, } err = resolve_indirect_ref(fs_info, path, time_seq, preftrees, ref, parents, extent_item_pos, - total_refs, ignore_offset); + ignore_offset); /* * we can only tolerate ENOENT,otherwise,we should catch error * and return directly. @@ -810,8 +809,7 @@ static int add_missing_keys(struct btrfs_fs_info *fs_info, */ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_head *head, u64 seq, - struct preftrees *preftrees, u64 *total_refs, - struct share_check *sc) + struct preftrees *preftrees, struct share_check *sc) { struct btrfs_delayed_ref_node *node; struct btrfs_delayed_extent_op *extent_op = head->extent_op; @@ -845,7 +843,6 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, default: BUG(); } - *total_refs += count; switch (node->type) { case BTRFS_TREE_BLOCK_REF_KEY: { /* NORMAL INDIRECT METADATA backref */ @@ -928,7 +925,7 @@ out: static int add_inline_refs(const struct btrfs_fs_info *fs_info, struct btrfs_path *path, u64 bytenr, int *info_level, struct preftrees *preftrees, - u64 *total_refs, struct share_check *sc) + struct share_check *sc) { int ret = 0; int slot; @@ -952,7 +949,6 @@ static int add_inline_refs(const struct btrfs_fs_info *fs_info, ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item); flags = btrfs_extent_flags(leaf, ei); - *total_refs += btrfs_extent_refs(leaf, ei); btrfs_item_key_to_cpu(leaf, &found_key, slot); ptr = (unsigned long)(ei + 1); @@ -1177,8 +1173,6 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans, struct prelim_ref *ref; struct rb_node *node; struct extent_inode_elem *eie = NULL; - /* total of both direct AND indirect refs! */ - u64 total_refs = 0; struct preftrees preftrees = { .direct = PREFTREE_INIT, .indirect = PREFTREE_INIT, @@ -1247,7 +1241,7 @@ again: } spin_unlock(&delayed_refs->lock); ret = add_delayed_refs(fs_info, head, time_seq, - &preftrees, &total_refs, sc); + &preftrees, sc); mutex_unlock(&head->mutex); if (ret) goto out; @@ -1268,8 +1262,7 @@ again: (key.type == BTRFS_EXTENT_ITEM_KEY || key.type == BTRFS_METADATA_ITEM_KEY)) { ret = add_inline_refs(fs_info, path, bytenr, - &info_level, &preftrees, - &total_refs, sc); + &info_level, &preftrees, sc); if (ret) goto out; ret = add_keyed_refs(fs_info, path, bytenr, info_level, @@ -1288,7 +1281,7 @@ again: WARN_ON(!RB_EMPTY_ROOT(&preftrees.indirect_missing_keys.root.rb_root)); ret = resolve_indirect_refs(fs_info, path, time_seq, &preftrees, - extent_item_pos, total_refs, sc, ignore_offset); + extent_item_pos, sc, ignore_offset); if (ret) goto out; From fd4c12f3120988789f124c0162e495299b56d1de Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 14 Jan 2021 10:19:29 -0800 Subject: [PATCH 13/33] net_sched: gen_estimator: support large ewma log commit dd5e073381f2ada3630f36be42833c6e9c78b75e upstream syzbot report reminded us that very big ewma_log were supported in the past, even if they made litle sense. tc qdisc replace dev xxx root est 1sec 131072sec ... While fixing the bug, also add boundary checks for ewma_log, in line with range supported by iproute2. UBSAN: shift-out-of-bounds in net/core/gen_estimator.c:83:38 shift exponent -1 is negative CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.10.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x107/0x163 lib/dump_stack.c:120 ubsan_epilogue+0xb/0x5a lib/ubsan.c:148 __ubsan_handle_shift_out_of_bounds.cold+0xb1/0x181 lib/ubsan.c:395 est_timer.cold+0xbb/0x12d net/core/gen_estimator.c:83 call_timer_fn+0x1a5/0x710 kernel/time/timer.c:1417 expire_timers kernel/time/timer.c:1462 [inline] __run_timers.part.0+0x692/0xa80 kernel/time/timer.c:1731 __run_timers kernel/time/timer.c:1712 [inline] run_timer_softirq+0xb3/0x1d0 kernel/time/timer.c:1744 __do_softirq+0x2bc/0xa77 kernel/softirq.c:343 asm_call_irq_on_stack+0xf/0x20 __run_on_irqstack arch/x86/include/asm/irq_stack.h:26 [inline] run_on_irqstack_cond arch/x86/include/asm/irq_stack.h:77 [inline] do_softirq_own_stack+0xaa/0xd0 arch/x86/kernel/irq_64.c:77 invoke_softirq kernel/softirq.c:226 [inline] __irq_exit_rcu+0x17f/0x200 kernel/softirq.c:420 irq_exit_rcu+0x5/0x20 kernel/softirq.c:432 sysvec_apic_timer_interrupt+0x4d/0x100 arch/x86/kernel/apic/apic.c:1096 asm_sysvec_apic_timer_interrupt+0x12/0x20 arch/x86/include/asm/idtentry.h:628 RIP: 0010:native_save_fl arch/x86/include/asm/irqflags.h:29 [inline] RIP: 0010:arch_local_save_flags arch/x86/include/asm/irqflags.h:79 [inline] RIP: 0010:arch_irqs_disabled arch/x86/include/asm/irqflags.h:169 [inline] RIP: 0010:acpi_safe_halt drivers/acpi/processor_idle.c:111 [inline] RIP: 0010:acpi_idle_do_entry+0x1c9/0x250 drivers/acpi/processor_idle.c:516 Fixes: 1c0d32fde5bd ("net_sched: gen_estimator: complete rewrite of rate estimators") Signed-off-by: Eric Dumazet Reported-by: syzbot Link: https://lore.kernel.org/r/20210114181929.1717985-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski [sudip: adjust context] Signed-off-by: Sudip Mukherjee Signed-off-by: Greg Kroah-Hartman --- net/core/gen_estimator.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index bfe7bdd4c340..98c396769be9 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -80,11 +80,11 @@ static void est_timer(struct timer_list *t) u64 rate, brate; est_fetch_counters(est, &b); - brate = (b.bytes - est->last_bytes) << (10 - est->ewma_log - est->intvl_log); - brate -= (est->avbps >> est->ewma_log); + brate = (b.bytes - est->last_bytes) << (10 - est->intvl_log); + brate = (brate >> est->ewma_log) - (est->avbps >> est->ewma_log); - rate = (u64)(b.packets - est->last_packets) << (10 - est->ewma_log - est->intvl_log); - rate -= (est->avpps >> est->ewma_log); + rate = (u64)(b.packets - est->last_packets) << (10 - est->intvl_log); + rate = (rate >> est->ewma_log) - (est->avpps >> est->ewma_log); write_seqcount_begin(&est->seq); est->avbps += brate; @@ -143,6 +143,9 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, if (parm->interval < -2 || parm->interval > 3) return -EINVAL; + if (parm->ewma_log == 0 || parm->ewma_log >= 31) + return -EINVAL; + est = kzalloc(sizeof(*est), GFP_KERNEL); if (!est) return -ENOBUFS; From 6f705e80fb871fad72ec2e95c5b75afe864b15e7 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Wed, 30 Dec 2020 12:21:05 +0200 Subject: [PATCH 14/33] phy: cpcap-usb: Fix warning for missing regulator_disable [ Upstream commit 764257d9069a9c19758b626cc1ba4ae079335d9e ] On deferred probe, we will get the following splat: cpcap-usb-phy cpcap-usb-phy.0: could not initialize VBUS or ID IIO: -517 WARNING: CPU: 0 PID: 21 at drivers/regulator/core.c:2123 regulator_put+0x68/0x78 ... (regulator_put) from [] (release_nodes+0x1b4/0x1fc) (release_nodes) from [] (really_probe+0x104/0x4a0) (really_probe) from [] (driver_probe_device+0x58/0xb4) Signed-off-by: Tony Lindgren Link: https://lore.kernel.org/r/20201230102105.11826-1-tony@atomide.com Signed-off-by: Vinod Koul Signed-off-by: Sasha Levin --- drivers/phy/motorola/phy-cpcap-usb.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/drivers/phy/motorola/phy-cpcap-usb.c b/drivers/phy/motorola/phy-cpcap-usb.c index 5baf64dfb24d..1bebad36bf2e 100644 --- a/drivers/phy/motorola/phy-cpcap-usb.c +++ b/drivers/phy/motorola/phy-cpcap-usb.c @@ -625,35 +625,42 @@ static int cpcap_usb_phy_probe(struct platform_device *pdev) generic_phy = devm_phy_create(ddata->dev, NULL, &ops); if (IS_ERR(generic_phy)) { error = PTR_ERR(generic_phy); - return PTR_ERR(generic_phy); + goto out_reg_disable; } phy_set_drvdata(generic_phy, ddata); phy_provider = devm_of_phy_provider_register(ddata->dev, of_phy_simple_xlate); - if (IS_ERR(phy_provider)) - return PTR_ERR(phy_provider); + if (IS_ERR(phy_provider)) { + error = PTR_ERR(phy_provider); + goto out_reg_disable; + } error = cpcap_usb_init_optional_pins(ddata); if (error) - return error; + goto out_reg_disable; cpcap_usb_init_optional_gpios(ddata); error = cpcap_usb_init_iio(ddata); if (error) - return error; + goto out_reg_disable; error = cpcap_usb_init_interrupts(pdev, ddata); if (error) - return error; + goto out_reg_disable; usb_add_phy_dev(&ddata->phy); atomic_set(&ddata->active, 1); schedule_delayed_work(&ddata->detect_work, msecs_to_jiffies(1)); return 0; + +out_reg_disable: + regulator_disable(ddata->vusb); + + return error; } static int cpcap_usb_phy_remove(struct platform_device *pdev) From c99ac721363822f0df58f7abb37f28b5610a3c57 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 24 Dec 2020 14:51:58 +0100 Subject: [PATCH 15/33] platform/x86: touchscreen_dmi: Add swap-x-y quirk for Goodix touchscreen on Estar Beauty HD tablet [ Upstream commit 46c54cf2706122c37497896d56d67b0c0aca2ede ] The Estar Beauty HD (MID 7316R) tablet uses a Goodix touchscreen, with the X and Y coordinates swapped compared to the LCD panel. Add a touchscreen_dmi entry for this adding a "touchscreen-swapped-x-y" device-property to the i2c-client instantiated for this device before the driver binds. This is the first entry of a Goodix touchscreen to touchscreen_dmi.c, so far DMI quirks for Goodix touchscreen's have been added directly to drivers/input/touchscreen/goodix.c. Currently there are 3 DMI tables in goodix.c: 1. rotated_screen[] for devices where the touchscreen is rotated 180 degrees vs the LCD panel 2. inverted_x_screen[] for devices where the X axis is inverted 3. nine_bytes_report[] for devices which use a non standard touch report size Arguably only 3. really needs to be inside the driver and the other 2 cases are better handled through the generic touchscreen DMI quirk mechanism from touchscreen_dmi.c, which allows adding device-props to any i2c-client. Esp. now that goodix.c is using the generic touchscreen_properties code. Alternative to the approach from this patch we could add a 4th dmi_system_id table for devices with swapped-x-y axis to goodix.c, but that seems undesirable. Cc: Bastien Nocera Cc: Dmitry Torokhov Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20201224135158.10976-1-hdegoede@redhat.com Signed-off-by: Sasha Levin --- drivers/platform/x86/touchscreen_dmi.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 1e072dbba30d..7ed1189a7200 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -231,6 +231,16 @@ static const struct ts_dmi_data digma_citi_e200_data = { .properties = digma_citi_e200_props, }; +static const struct property_entry estar_beauty_hd_props[] = { + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + { } +}; + +static const struct ts_dmi_data estar_beauty_hd_data = { + .acpi_name = "GDIX1001:00", + .properties = estar_beauty_hd_props, +}; + static const struct property_entry gp_electronic_t701_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 960), PROPERTY_ENTRY_U32("touchscreen-size-y", 640), @@ -747,6 +757,14 @@ static const struct dmi_system_id touchscreen_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "Cherry Trail CR"), }, }, + { + /* Estar Beauty HD (MID 7316R) */ + .driver_data = (void *)&estar_beauty_hd_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Estar"), + DMI_MATCH(DMI_PRODUCT_NAME, "eSTAR BEAUTY HD Intel Quad core"), + }, + }, { /* GP-electronic T701 */ .driver_data = (void *)&gp_electronic_t701_data, From d1aed452c05fc48e4aa32a6ae8264b6e64f34778 Mon Sep 17 00:00:00 2001 From: Arnold Gozum Date: Sat, 26 Dec 2020 15:53:06 -0500 Subject: [PATCH 16/33] platform/x86: intel-vbtn: Support for tablet mode on Dell Inspiron 7352 [ Upstream commit fcd38f178b785623c0325958225744f0d8a075c0 ] The Dell Inspiron 7352 is a 2-in-1 model that has chassis-type "Notebook". Add this model to the dmi_switches_allow_list. Signed-off-by: Arnold Gozum Link: https://lore.kernel.org/r/20201226205307.249659-1-arngozum@gmail.com Signed-off-by: Hans de Goede Signed-off-by: Sasha Levin --- drivers/platform/x86/intel-vbtn.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c index 37035dca469c..d4fc2cbf7870 100644 --- a/drivers/platform/x86/intel-vbtn.c +++ b/drivers/platform/x86/intel-vbtn.c @@ -203,6 +203,12 @@ static const struct dmi_system_id dmi_switches_allow_list[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Switch SA5-271"), }, }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7352"), + }, + }, {} /* Array terminator */ }; From b1f680ffc25b1453b36514b9d84b6b02cb556a6b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Jan 2021 11:14:25 +0100 Subject: [PATCH 17/33] x86: __always_inline __{rd,wr}msr() [ Upstream commit 66a425011c61e71560c234492d204e83cfb73d1d ] When the compiler choses to not inline the trivial MSR helpers: vmlinux.o: warning: objtool: __sev_es_nmi_complete()+0xce: call to __wrmsr.constprop.14() leaves .noinstr.text section Reported-by: Randy Dunlap Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Acked-by: Randy Dunlap # build-tested Link: https://lore.kernel.org/r/X/bf3gV+BW7kGEsB@hirez.programming.kicks-ass.net Signed-off-by: Sasha Levin --- arch/x86/include/asm/msr.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 86f20d520a07..b40d0295d812 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -88,7 +88,7 @@ static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {} * think of extending them - you will be slapped with a stinking trout or a frozen * shark will reach you, wherever you are! You've been warned. */ -static inline unsigned long long notrace __rdmsr(unsigned int msr) +static __always_inline unsigned long long __rdmsr(unsigned int msr) { DECLARE_ARGS(val, low, high); @@ -100,7 +100,7 @@ static inline unsigned long long notrace __rdmsr(unsigned int msr) return EAX_EDX_VAL(val, low, high); } -static inline void notrace __wrmsr(unsigned int msr, u32 low, u32 high) +static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high) { asm volatile("1: wrmsr\n" "2:\n" From 335bbffdd90c57f3c50dd439839a55274fb502ad Mon Sep 17 00:00:00 2001 From: Martin Wilck Date: Mon, 11 Jan 2021 15:25:41 +0100 Subject: [PATCH 18/33] scsi: scsi_transport_srp: Don't block target in failfast state [ Upstream commit 72eeb7c7151302ef007f1acd018cbf6f30e50321 ] If the port is in SRP_RPORT_FAIL_FAST state when srp_reconnect_rport() is entered, a transition to SDEV_BLOCK would be illegal, and a kernel WARNING would be triggered. Skip scsi_target_block() in this case. Link: https://lore.kernel.org/r/20210111142541.21534-1-mwilck@suse.com Reviewed-by: Bart Van Assche Signed-off-by: Martin Wilck Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/scsi_transport_srp.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c index d4d1104fac99..8cd0a87764df 100644 --- a/drivers/scsi/scsi_transport_srp.c +++ b/drivers/scsi/scsi_transport_srp.c @@ -541,7 +541,14 @@ int srp_reconnect_rport(struct srp_rport *rport) res = mutex_lock_interruptible(&rport->mutex); if (res) goto out; - scsi_target_block(&shost->shost_gendev); + if (rport->state != SRP_RPORT_FAIL_FAST) + /* + * sdev state must be SDEV_TRANSPORT_OFFLINE, transition + * to SDEV_BLOCK is illegal. Calling scsi_target_unblock() + * later is ok though, scsi_internal_device_unblock_nowait() + * treats SDEV_TRANSPORT_OFFLINE like SDEV_BLOCK. + */ + scsi_target_block(&shost->shost_gendev); res = rport->state != SRP_RPORT_LOST ? i->f->reconnect(rport) : -ENODEV; pr_debug("%s (state %d): transport.reconnect() returned %d\n", dev_name(&shost->shost_gendev), rport->state, res); From 935fa0d5a5c55d105973770355394389d010dbfc Mon Sep 17 00:00:00 2001 From: Javed Hasan Date: Tue, 15 Dec 2020 11:47:31 -0800 Subject: [PATCH 19/33] scsi: libfc: Avoid invoking response handler twice if ep is already completed MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit b2b0f16fa65e910a3ec8771206bb49ee87a54ac5 ] A race condition exists between the response handler getting called because of exchange_mgr_reset() (which clears out all the active XIDs) and the response we get via an interrupt. Sequence of events: rport ba0200: Port timeout, state PLOGI rport ba0200: Port entered PLOGI state from PLOGI state xid 1052: Exchange timer armed : 20000 msecs  xid timer armed here rport ba0200: Received LOGO request while in state PLOGI rport ba0200: Delete port rport ba0200: work event 3 rport ba0200: lld callback ev 3 bnx2fc: rport_event_hdlr: event = 3, port_id = 0xba0200 bnx2fc: ba0200 - rport not created Yet!! /* Here we reset any outstanding exchanges before freeing rport using the exch_mgr_reset() */ xid 1052: Exchange timer canceled /* Here we got two responses for one xid */ xid 1052: invoking resp(), esb 20000000 state 3 xid 1052: invoking resp(), esb 20000000 state 3 xid 1052: fc_rport_plogi_resp() : ep->resp_active 2 xid 1052: fc_rport_plogi_resp() : ep->resp_active 2 Skip the response if the exchange is already completed. Link: https://lore.kernel.org/r/20201215194731.2326-1-jhasan@marvell.com Signed-off-by: Javed Hasan Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/libfc/fc_exch.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c index 52e866659853..e5b18e5d46da 100644 --- a/drivers/scsi/libfc/fc_exch.c +++ b/drivers/scsi/libfc/fc_exch.c @@ -1619,8 +1619,13 @@ static void fc_exch_recv_seq_resp(struct fc_exch_mgr *mp, struct fc_frame *fp) rc = fc_exch_done_locked(ep); WARN_ON(fc_seq_exch(sp) != ep); spin_unlock_bh(&ep->ex_lock); - if (!rc) + if (!rc) { fc_exch_delete(ep); + } else { + FC_EXCH_DBG(ep, "ep is completed already," + "hence skip calling the resp\n"); + goto skip_resp; + } } /* @@ -1639,6 +1644,7 @@ static void fc_exch_recv_seq_resp(struct fc_exch_mgr *mp, struct fc_frame *fp) if (!fc_invoke_resp(ep, sp, fp)) fc_frame_free(fp); +skip_resp: fc_exch_release(ep); return; rel: @@ -1895,10 +1901,16 @@ static void fc_exch_reset(struct fc_exch *ep) fc_exch_hold(ep); - if (!rc) + if (!rc) { fc_exch_delete(ep); + } else { + FC_EXCH_DBG(ep, "ep is completed already," + "hence skip calling the resp\n"); + goto skip_resp; + } fc_invoke_resp(ep, sp, ERR_PTR(-FC_EX_CLOSED)); +skip_resp: fc_seq_set_resp(sp, NULL, ep->arg); fc_exch_release(ep); } From e0f1ba38f7885fde728b164a24f40d6d67f5a282 Mon Sep 17 00:00:00 2001 From: Dinghao Liu Date: Fri, 25 Dec 2020 16:35:20 +0800 Subject: [PATCH 20/33] scsi: fnic: Fix memleak in vnic_dev_init_devcmd2 [ Upstream commit d6e3ae76728ccde49271d9f5acfebbea0c5625a3 ] When ioread32() returns 0xFFFFFFFF, we should execute cleanup functions like other error handling paths before returning. Link: https://lore.kernel.org/r/20201225083520.22015-1-dinghao.liu@zju.edu.cn Acked-by: Karan Tilak Kumar Signed-off-by: Dinghao Liu Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/fnic/vnic_dev.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/fnic/vnic_dev.c b/drivers/scsi/fnic/vnic_dev.c index 522636e94628..c8bf8c7ada6a 100644 --- a/drivers/scsi/fnic/vnic_dev.c +++ b/drivers/scsi/fnic/vnic_dev.c @@ -444,7 +444,8 @@ int vnic_dev_init_devcmd2(struct vnic_dev *vdev) fetch_index = ioread32(&vdev->devcmd2->wq.ctrl->fetch_index); if (fetch_index == 0xFFFFFFFF) { /* check for hardware gone */ pr_err("error in devcmd2 init"); - return -ENODEV; + err = -ENODEV; + goto err_free_wq; } /* @@ -460,7 +461,7 @@ int vnic_dev_init_devcmd2(struct vnic_dev *vdev) err = vnic_dev_alloc_desc_ring(vdev, &vdev->devcmd2->results_ring, DEVCMD2_RING_SIZE, DEVCMD2_DESC_SIZE); if (err) - goto err_free_wq; + goto err_disable_wq; vdev->devcmd2->result = (struct devcmd2_result *) vdev->devcmd2->results_ring.descs; @@ -481,8 +482,9 @@ int vnic_dev_init_devcmd2(struct vnic_dev *vdev) err_free_desc_ring: vnic_dev_free_desc_ring(vdev, &vdev->devcmd2->results_ring); -err_free_wq: +err_disable_wq: vnic_wq_disable(&vdev->devcmd2->wq); +err_free_wq: vnic_wq_free(&vdev->devcmd2->wq); err_free_devcmd2: kfree(vdev->devcmd2); From efd061fc77f3b73b926a805f0c489cd697ea657c Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Wed, 13 Jan 2021 02:11:23 +0800 Subject: [PATCH 21/33] ASoC: SOF: Intel: hda: Resume codec to do jack detection [ Upstream commit bcd7059abc19e6ec5b2260dff6a008fb99c4eef9 ] Instead of queueing jackpoll_work, runtime resume the codec to let it use different jack detection methods based on jackpoll_interval. This partially matches SOF driver's behavior with commit a6e7d0a4bdb0 ("ALSA: hda: fix jack detection with Realtek codecs when in D3"), the difference is SOF unconditionally resumes the codec. Signed-off-by: Kai-Heng Feng Link: https://lore.kernel.org/r/20210112181128.1229827-1-kai.heng.feng@canonical.com Signed-off-by: Mark Brown Signed-off-by: Sasha Levin --- sound/soc/sof/intel/hda-codec.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/sound/soc/sof/intel/hda-codec.c b/sound/soc/sof/intel/hda-codec.c index 9e8233c10d86..df38616c431a 100644 --- a/sound/soc/sof/intel/hda-codec.c +++ b/sound/soc/sof/intel/hda-codec.c @@ -68,8 +68,7 @@ void hda_codec_jack_check(struct snd_sof_dev *sdev) * has been recorded in STATESTS */ if (codec->jacktbl.used) - schedule_delayed_work(&codec->jackpoll_work, - codec->jackpoll_interval); + pm_request_resume(&codec->core.dev); } #else void hda_codec_jack_wake_enable(struct snd_sof_dev *sdev) {} From 02cc1ee3e8d1b39f20d494d08dd60cb91246c96a Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Fri, 18 Dec 2020 19:47:17 +0100 Subject: [PATCH 22/33] mac80211: fix fast-rx encryption check [ Upstream commit 622d3b4e39381262da7b18ca1ed1311df227de86 ] When using WEP, the default unicast key needs to be selected, instead of the STA PTK. Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20201218184718.93650-5-nbd@nbd.name Signed-off-by: Johannes Berg Signed-off-by: Sasha Levin --- net/mac80211/rx.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 3ab85e1e38d8..1a15e7bae106 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -4080,6 +4080,8 @@ void ieee80211_check_fast_rx(struct sta_info *sta) rcu_read_lock(); key = rcu_dereference(sta->ptk[sta->ptk_idx]); + if (!key) + key = rcu_dereference(sdata->default_unicast_key); if (key) { switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_TKIP: From c03ecc192c8e59e00b45891de5611d907c9746c2 Mon Sep 17 00:00:00 2001 From: Brian King Date: Tue, 12 Jan 2021 09:06:38 -0600 Subject: [PATCH 23/33] scsi: ibmvfc: Set default timeout to avoid crash during migration [ Upstream commit 764907293edc1af7ac857389af9dc858944f53dc ] While testing live partition mobility, we have observed occasional crashes of the Linux partition. What we've seen is that during the live migration, for specific configurations with large amounts of memory, slow network links, and workloads that are changing memory a lot, the partition can end up being suspended for 30 seconds or longer. This resulted in the following scenario: CPU 0 CPU 1 ------------------------------- ---------------------------------- scsi_queue_rq migration_store -> blk_mq_start_request -> rtas_ibm_suspend_me -> blk_add_timer -> on_each_cpu(rtas_percpu_suspend_me _______________________________________V | V -> IPI from CPU 1 -> rtas_percpu_suspend_me -> __rtas_suspend_last_cpu -- Linux partition suspended for > 30 seconds -- -> for_each_online_cpu(cpu) plpar_hcall_norets(H_PROD -> scsi_dispatch_cmd -> scsi_times_out -> scsi_abort_command -> queue_delayed_work -> ibmvfc_queuecommand_lck -> ibmvfc_send_event -> ibmvfc_send_crq - returns H_CLOSED <- returns SCSI_MLQUEUE_HOST_BUSY -> __blk_mq_requeue_request -> scmd_eh_abort_handler -> scsi_try_to_abort_cmd - returns SUCCESS -> scsi_queue_insert Normally, the SCMD_STATE_COMPLETE bit would protect against the command completion and the timeout, but that doesn't work here, since we don't check that at all in the SCSI_MLQUEUE_HOST_BUSY path. In this case we end up calling scsi_queue_insert on a request that has already been queued, or possibly even freed, and we crash. The patch below simply increases the default I/O timeout to avoid this race condition. This is also the timeout value that nearly all IBM SAN storage recommends setting as the default value. Link: https://lore.kernel.org/r/1610463998-19791-1-git-send-email-brking@linux.vnet.ibm.com Signed-off-by: Brian King Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/scsi/ibmvscsi/ibmvfc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index 8a76284b59b0..523809a8a232 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -2881,8 +2881,10 @@ static int ibmvfc_slave_configure(struct scsi_device *sdev) unsigned long flags = 0; spin_lock_irqsave(shost->host_lock, flags); - if (sdev->type == TYPE_DISK) + if (sdev->type == TYPE_DISK) { sdev->allow_restart = 1; + blk_queue_rq_timeout(sdev->request_queue, 120 * HZ); + } spin_unlock_irqrestore(shost->host_lock, flags); return 0; } From 2d1593543418b21130491946d3103ae48f2dc8f3 Mon Sep 17 00:00:00 2001 From: Kai-Chuan Hsieh Date: Fri, 15 Jan 2021 11:15:15 +0800 Subject: [PATCH 24/33] ALSA: hda: Add Cometlake-R PCI ID [ Upstream commit f84d3a1ec375e46a55cc3ba85c04272b24bd3921 ] Add HD Audio Device PCI ID for the Intel Cometlake-R platform Reviewed-by: Kai Vehmanen Signed-off-by: Kai-Chuan Hsieh Link: https://lore.kernel.org/r/20210115031515.13100-1-kaichuan.hsieh@canonical.com Signed-off-by: Takashi Iwai Signed-off-by: Sasha Levin --- sound/pci/hda/hda_intel.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 5f515a29668c..b3667a5efdc1 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2450,6 +2450,9 @@ static const struct pci_device_id azx_ids[] = { /* CometLake-S */ { PCI_DEVICE(0x8086, 0xa3f0), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, + /* CometLake-R */ + { PCI_DEVICE(0x8086, 0xf0c8), + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, /* Icelake */ { PCI_DEVICE(0x8086, 0x34c8), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, From 8e59209d53c92c8504fc20e7cae4cd91b75d12ad Mon Sep 17 00:00:00 2001 From: lianzhi chang Date: Thu, 14 Jan 2021 15:57:41 +0800 Subject: [PATCH 25/33] udf: fix the problem that the disc content is not displayed [ Upstream commit 5cdc4a6950a883594e9640b1decb3fcf6222a594 ] When the capacity of the disc is too large (assuming the 4.7G specification), the disc (UDF file system) will be burned multiple times in the windows (Multisession Usage). When the remaining capacity of the CD is less than 300M (estimated value, for reference only), open the CD in the Linux system, the content of the CD is displayed as blank (the kernel will say "No VRS found"). Windows can display the contents of the CD normally. Through analysis, in the "fs/udf/super.c": udf_check_vsd function, the actual value of VSD_MAX_SECTOR_OFFSET may be much larger than 0x800000. According to the current code logic, it is found that the type of sbi->s_session is "__s32", when the remaining capacity of the disc is less than 300M (take a set of test values: sector=3154903040, sbi->s_session=1540464, sb->s_blocksize_bits=11 ), the calculation result of "sbi->s_session << sb->s_blocksize_bits" will overflow. Therefore, it is necessary to convert the type of s_session to "loff_t" (when udf_check_vsd starts, assign a value to _sector, which is also converted in this way), so that the result will not overflow, and then the content of the disc can be displayed normally. Link: https://lore.kernel.org/r/20210114075741.30448-1-changlianzhi@uniontech.com Signed-off-by: lianzhi chang Signed-off-by: Jan Kara Signed-off-by: Sasha Levin --- fs/udf/super.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/udf/super.c b/fs/udf/super.c index 4aba4878ed96..8bb001c7927f 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -705,6 +705,7 @@ static int udf_check_vsd(struct super_block *sb) struct buffer_head *bh = NULL; int nsr = 0; struct udf_sb_info *sbi; + loff_t session_offset; sbi = UDF_SB(sb); if (sb->s_blocksize < sizeof(struct volStructDesc)) @@ -712,7 +713,8 @@ static int udf_check_vsd(struct super_block *sb) else sectorsize = sb->s_blocksize; - sector += (((loff_t)sbi->s_session) << sb->s_blocksize_bits); + session_offset = (loff_t)sbi->s_session << sb->s_blocksize_bits; + sector += session_offset; udf_debug("Starting at sector %u (%lu byte sectors)\n", (unsigned int)(sector >> sb->s_blocksize_bits), @@ -757,8 +759,7 @@ static int udf_check_vsd(struct super_block *sb) if (nsr > 0) return 1; - else if (!bh && sector - (sbi->s_session << sb->s_blocksize_bits) == - VSD_FIRST_SECTOR_OFFSET) + else if (!bh && sector - session_offset == VSD_FIRST_SECTOR_OFFSET) return -1; else return 0; From 805e9cdb57938c9db35d223f7fa78acf868995df Mon Sep 17 00:00:00 2001 From: Revanth Rajashekar Date: Thu, 14 Jan 2021 18:55:07 -0700 Subject: [PATCH 26/33] nvme: check the PRINFO bit before deciding the host buffer length [ Upstream commit 4d6b1c95b974761c01cbad92321b82232b66d2a2 ] According to NVMe spec v1.4, section 8.3.1, the PRINFO bit and the metadata size play a vital role in deteriming the host buffer size. If PRIFNO bit is set and MS==8, the host doesn't add the metadata buffer, instead the controller adds it. Signed-off-by: Revanth Rajashekar Signed-off-by: Christoph Hellwig Signed-off-by: Sasha Levin --- drivers/nvme/host/core.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 7a964271959d..c2cabd77884b 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1295,8 +1295,21 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) } length = (io.nblocks + 1) << ns->lba_shift; - meta_len = (io.nblocks + 1) * ns->ms; - metadata = nvme_to_user_ptr(io.metadata); + + if ((io.control & NVME_RW_PRINFO_PRACT) && + ns->ms == sizeof(struct t10_pi_tuple)) { + /* + * Protection information is stripped/inserted by the + * controller. + */ + if (nvme_to_user_ptr(io.metadata)) + return -EINVAL; + meta_len = 0; + metadata = NULL; + } else { + meta_len = (io.nblocks + 1) * ns->ms; + metadata = nvme_to_user_ptr(io.metadata); + } if (ns->ext) { length += meta_len; From c6eb3dfdac44bea0cc3ac8bc5a28962d1174bbb7 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 19 Jan 2021 15:18:00 +1100 Subject: [PATCH 27/33] selftests/powerpc: Only test lwm/stmw on big endian [ Upstream commit dd3a44c06f7b4f14e90065bf05d62c255b20005f ] Newer binutils (>= 2.36) refuse to assemble lmw/stmw when building in little endian mode. That breaks compilation of our alignment handler test: /tmp/cco4l14N.s: Assembler messages: /tmp/cco4l14N.s:1440: Error: `lmw' invalid when little-endian /tmp/cco4l14N.s:1814: Error: `stmw' invalid when little-endian make[2]: *** [../../lib.mk:139: /output/kselftest/powerpc/alignment/alignment_handler] Error 1 These tests do pass on little endian machines, as the kernel will still emulate those instructions even when running little endian (which is arguably a kernel bug). But we don't really need to test that case, so ifdef those instructions out to get the alignment test building again. Reported-by: Libor Pechacek Signed-off-by: Michael Ellerman Tested-by: Libor Pechacek Link: https://lore.kernel.org/r/20210119041800.3093047-1-mpe@ellerman.id.au Signed-off-by: Sasha Levin --- .../testing/selftests/powerpc/alignment/alignment_handler.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/powerpc/alignment/alignment_handler.c b/tools/testing/selftests/powerpc/alignment/alignment_handler.c index 0453c50c949c..0725239bbd85 100644 --- a/tools/testing/selftests/powerpc/alignment/alignment_handler.c +++ b/tools/testing/selftests/powerpc/alignment/alignment_handler.c @@ -380,7 +380,6 @@ int test_alignment_handler_integer(void) LOAD_DFORM_TEST(ldu); LOAD_XFORM_TEST(ldx); LOAD_XFORM_TEST(ldux); - LOAD_DFORM_TEST(lmw); STORE_DFORM_TEST(stb); STORE_XFORM_TEST(stbx); STORE_DFORM_TEST(stbu); @@ -399,7 +398,11 @@ int test_alignment_handler_integer(void) STORE_XFORM_TEST(stdx); STORE_DFORM_TEST(stdu); STORE_XFORM_TEST(stdux); + +#ifdef __BIG_ENDIAN__ + LOAD_DFORM_TEST(lmw); STORE_DFORM_TEST(stmw); +#endif return rc; } From 53c10bbf9186086485990aed054d852940992d20 Mon Sep 17 00:00:00 2001 From: Jake Wang Date: Fri, 8 Jan 2021 12:27:51 -0500 Subject: [PATCH 28/33] drm/amd/display: Update dram_clock_change_latency for DCN2.1 [ Upstream commit 901c1ec05ef277ce9d43cb806a225b28b3efe89a ] [WHY] dram clock change latencies get updated using ddr4 latency table, but does that update does not happen before validation. This value should not be the default and should be number received from df for better mode support. This may cause a PState hang on high refresh panels with short vblanks such as on 1080p 360hz or 300hz panels. [HOW] Update latency from 23.84 to 11.72. Signed-off-by: Sung Lee Reviewed-by: Tony Cheng Acked-by: Aurabindo Pillai Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index bb7add5ea227..a6d5beada663 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -257,7 +257,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = { .num_banks = 8, .num_chans = 4, .vmm_page_size_bytes = 4096, - .dram_clock_change_latency_us = 23.84, + .dram_clock_change_latency_us = 11.72, .return_bus_width_bytes = 64, .dispclk_dppclk_vco_speed_mhz = 3600, .xfc_bus_transport_time_us = 4, From 88240f7ac22147e7d831bf052085bb4bbf4d06e6 Mon Sep 17 00:00:00 2001 From: Bing Guo Date: Mon, 4 Jan 2021 14:09:41 -0500 Subject: [PATCH 29/33] drm/amd/display: Change function decide_dp_link_settings to avoid infinite looping [ Upstream commit 4716a7c50c5c66d6ddc42401e1e0ba13b492e105 ] Why: Function decide_dp_link_settings() loops infinitely when required bandwidth can't be supported. How: Check the required bandwidth against verified_link_cap before trying to find a link setting for it. Tested-by: Daniel Wheeler Signed-off-by: Bing Guo Reviewed-by: Jun Lei Acked-by: Anson Jacob Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin --- drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 959eb075d11e..c18f39271b03 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -1914,6 +1914,9 @@ static bool decide_dp_link_settings(struct dc_link *link, struct dc_link_setting initial_link_setting; uint32_t link_bw; + if (req_bw > dc_link_bandwidth_kbps(link, &link->verified_link_cap)) + return false; + /* search for the minimum link setting that: * 1. is supported according to the link training result * 2. could support the b/w requested by the timing From 2d7ca4a84b589210b633b3c2f2c0b8fc627c97c7 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Thu, 14 Jan 2021 16:14:01 -0600 Subject: [PATCH 30/33] objtool: Don't fail on missing symbol table [ Upstream commit 1d489151e9f9d1647110277ff77282fe4d96d09b ] Thanks to a recent binutils change which doesn't generate unused symbols, it's now possible for thunk_64.o be completely empty without CONFIG_PREEMPTION: no text, no data, no symbols. We could edit the Makefile to only build that file when CONFIG_PREEMPTION is enabled, but that will likely create confusion if/when the thunks end up getting used by some other code again. Just ignore it and move on. Reported-by: Nathan Chancellor Reviewed-by: Nathan Chancellor Reviewed-by: Miroslav Benes Tested-by: Nathan Chancellor Link: https://github.com/ClangBuiltLinux/linux/issues/1254 Signed-off-by: Josh Poimboeuf Signed-off-by: Sasha Levin --- tools/objtool/elf.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index edba4745f25a..693d740107a8 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -214,8 +214,11 @@ static int read_symbols(struct elf *elf) symtab = find_section_by_name(elf, ".symtab"); if (!symtab) { - WARN("missing symbol table"); - return -1; + /* + * A missing symbol table is actually possible if it's an empty + * .o file. This can happen for thunk_64.o. + */ + return 0; } symbols_nr = symtab->sh.sh_size / symtab->sh.sh_entsize; From 5b1e4fc2984eab30c5fffbf2bd1f016577cadab6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 12 Jan 2021 11:24:04 +0100 Subject: [PATCH 31/33] kthread: Extract KTHREAD_IS_PER_CPU [ Upstream commit ac687e6e8c26181a33270efd1a2e2241377924b0 ] There is a need to distinguish geniune per-cpu kthreads from kthreads that happen to have a single CPU affinity. Geniune per-cpu kthreads are kthreads that are CPU affine for correctness, these will obviously have PF_KTHREAD set, but must also have PF_NO_SETAFFINITY set, lest userspace modify their affinity and ruins things. However, these two things are not sufficient, PF_NO_SETAFFINITY is also set on other tasks that have their affinities controlled through other means, like for instance workqueues. Therefore another bit is needed; it turns out kthread_create_per_cpu() already has such a bit: KTHREAD_IS_PER_CPU, which is used to make kthread_park()/kthread_unpark() work correctly. Expose this flag and remove the implicit setting of it from kthread_create_on_cpu(); the io_uring usage of it seems dubious at best. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Tested-by: Valentin Schneider Link: https://lkml.kernel.org/r/20210121103506.557620262@infradead.org Signed-off-by: Sasha Levin --- include/linux/kthread.h | 3 +++ kernel/kthread.c | 27 ++++++++++++++++++++++++++- kernel/smpboot.c | 1 + 3 files changed, 30 insertions(+), 1 deletion(-) diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 0f9da966934e..c7108ce5a051 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -31,6 +31,9 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), unsigned int cpu, const char *namefmt); +void kthread_set_per_cpu(struct task_struct *k, int cpu); +bool kthread_is_per_cpu(struct task_struct *k); + /** * kthread_run - create and wake a thread. * @threadfn: the function to run until signal_pending(current). diff --git a/kernel/kthread.c b/kernel/kthread.c index e51f0006057d..1d4c98a19043 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -469,11 +469,36 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), return p; kthread_bind(p, cpu); /* CPU hotplug need to bind once again when unparking the thread. */ - set_bit(KTHREAD_IS_PER_CPU, &to_kthread(p)->flags); to_kthread(p)->cpu = cpu; return p; } +void kthread_set_per_cpu(struct task_struct *k, int cpu) +{ + struct kthread *kthread = to_kthread(k); + if (!kthread) + return; + + WARN_ON_ONCE(!(k->flags & PF_NO_SETAFFINITY)); + + if (cpu < 0) { + clear_bit(KTHREAD_IS_PER_CPU, &kthread->flags); + return; + } + + kthread->cpu = cpu; + set_bit(KTHREAD_IS_PER_CPU, &kthread->flags); +} + +bool kthread_is_per_cpu(struct task_struct *k) +{ + struct kthread *kthread = to_kthread(k); + if (!kthread) + return false; + + return test_bit(KTHREAD_IS_PER_CPU, &kthread->flags); +} + /** * kthread_unpark - unpark a thread created by kthread_create(). * @k: thread created by kthread_create(). diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 2efe1e206167..f25208e8df83 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -188,6 +188,7 @@ __smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu) kfree(td); return PTR_ERR(tsk); } + kthread_set_per_cpu(tsk, cpu); /* * Park the thread so that it could start right on the CPU * when it is available. From b1a1c262e4b0e713e52c63bd3233f1b9d6f2f056 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 15 Jan 2021 19:08:36 +0100 Subject: [PATCH 32/33] workqueue: Restrict affinity change to rescuer [ Upstream commit 640f17c82460e9724fd256f0a1f5d99e7ff0bda4 ] create_worker() will already set the right affinity using kthread_bind_mask(), this means only the rescuer will need to change it's affinity. Howveer, while in cpu-hot-unplug a regular task is not allowed to run on online&&!active as it would be pushed away quite agressively. We need KTHREAD_IS_PER_CPU to survive in that environment. Therefore set the affinity after getting that magic flag. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Tested-by: Valentin Schneider Link: https://lkml.kernel.org/r/20210121103506.826629830@infradead.org Signed-off-by: Sasha Levin --- kernel/workqueue.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 28e52657e093..29c36c029062 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1847,12 +1847,6 @@ static void worker_attach_to_pool(struct worker *worker, { mutex_lock(&wq_pool_attach_mutex); - /* - * set_cpus_allowed_ptr() will fail if the cpumask doesn't have any - * online CPUs. It'll be re-applied when any of the CPUs come up. - */ - set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask); - /* * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains * stable across this function. See the comments above the flag @@ -1861,6 +1855,9 @@ static void worker_attach_to_pool(struct worker *worker, if (pool->flags & POOL_DISASSOCIATED) worker->flags |= WORKER_UNBOUND; + if (worker->rescue_wq) + set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask); + list_add_tail(&worker->node, &pool->workers); worker->pool = pool; From d4716ee8751bf8dabf5872ba008124a0979a5f94 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 7 Feb 2021 15:35:50 +0100 Subject: [PATCH 33/33] Linux 5.4.96 Tested-by: Igor Matheus Andrade Torrente Tested-by: Florian Fainelli Tested-by: Linux Kernel Functional Testing Tested-by: Guenter Roeck Link: https://lore.kernel.org/r/20210205140652.348864025@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index aa3c2e834442..7a47a2594f95 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 4 -SUBLEVEL = 95 +SUBLEVEL = 96 EXTRAVERSION = NAME = Kleptomaniac Octopus