From 0cce06ba859a515bd06224085d3addb870608b6d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 25 Apr 2023 17:03:13 +0200 Subject: debugobjects,locking: Annotate debug_object_fill_pool() wait type violation There is an explicit wait-type violation in debug_object_fill_pool() for PREEMPT_RT=n kernels which allows them to more easily fill the object pool and reduce the chance of allocation failures. Lockdep's wait-type checks are designed to check the PREEMPT_RT locking rules even for PREEMPT_RT=n kernels and object to this, so create a lockdep annotation to allow this to stand. Specifically, create a 'lock' type that overrides the inner wait-type while it is held -- allowing one to temporarily raise it, such that the violation is hidden. Reported-by: Vlastimil Babka Reported-by: Qi Zheng Signed-off-by: Peter Zijlstra (Intel) Tested-by: Qi Zheng Link: https://lkml.kernel.org/r/20230429100614.GA1489784@hirez.programming.kicks-ass.net --- include/linux/lockdep.h | 14 ++++++++++++++ include/linux/lockdep_types.h | 1 + 2 files changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 1023f349af71..a3329fb49b33 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -339,6 +339,16 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); #define lockdep_repin_lock(l,c) lock_repin_lock(&(l)->dep_map, (c)) #define lockdep_unpin_lock(l,c) lock_unpin_lock(&(l)->dep_map, (c)) +/* + * Must use lock_map_aquire_try() with override maps to avoid + * lockdep thinking they participate in the block chain. + */ +#define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type) \ + struct lockdep_map _name = { \ + .name = #_name "-wait-type-override", \ + .wait_type_inner = _wait_type, \ + .lock_type = LD_LOCK_WAIT_OVERRIDE, } + #else /* !CONFIG_LOCKDEP */ static inline void lockdep_init_task(struct task_struct *task) @@ -427,6 +437,9 @@ extern int lockdep_is_held(const void *); #define lockdep_repin_lock(l, c) do { (void)(l); (void)(c); } while (0) #define lockdep_unpin_lock(l, c) do { (void)(l); (void)(c); } while (0) +#define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type) \ + struct lockdep_map __maybe_unused _name = {} + #endif /* !LOCKDEP */ enum xhlock_context_t { @@ -551,6 +564,7 @@ do { \ #define rwsem_release(l, i) lock_release(l, i) #define lock_map_acquire(l) lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_) +#define lock_map_acquire_try(l) lock_acquire_exclusive(l, 0, 1, NULL, _THIS_IP_) #define lock_map_acquire_read(l) lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_) #define lock_map_acquire_tryread(l) lock_acquire_shared_recursive(l, 0, 1, NULL, _THIS_IP_) #define lock_map_release(l) lock_release(l, _THIS_IP_) diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h index d22430840b53..59f4fb1626ea 100644 --- a/include/linux/lockdep_types.h +++ b/include/linux/lockdep_types.h @@ -33,6 +33,7 @@ enum lockdep_wait_type { enum lockdep_lock_type { LD_LOCK_NORMAL = 0, /* normal, catch all */ LD_LOCK_PERCPU, /* percpu */ + LD_LOCK_WAIT_OVERRIDE, /* annotation */ LD_LOCK_MAX, }; -- cgit v1.2.3 From c00bc80462afc7963f449d7f21d896d2f629cacc Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 20:23:34 +0200 Subject: power: supply: bq27xxx: Fix poll_interval handling and races on remove Before this patch bq27xxx_battery_teardown() was setting poll_interval = 0 to avoid bq27xxx_battery_update() requeuing the delayed_work item. There are 2 problems with this: 1. If the driver is unbound through sysfs, rather then the module being rmmod-ed, this changes poll_interval unexpectedly 2. This is racy, after it being set poll_interval could be changed before bq27xxx_battery_update() checks it through /sys/module/bq27xxx_battery/parameters/poll_interval Fix this by added a removed attribute to struct bq27xxx_device_info and using that instead of setting poll_interval to 0. There also is another poll_interval related race on remove(), writing /sys/module/bq27xxx_battery/parameters/poll_interval will requeue the delayed_work item for all devices on the bq27xxx_battery_devices list and the device being removed was only removed from that list after cancelling the delayed_work item. Fix this by moving the removal from the bq27xxx_battery_devices list to before cancelling the delayed_work item. Fixes: 8cfaaa811894 ("bq27x00_battery: Fix OOPS caused by unregistring bq27x00 driver") Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- drivers/power/supply/bq27xxx_battery.c | 22 +++++++++------------- include/linux/power/bq27xxx_battery.h | 1 + 2 files changed, 10 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 79aedf83cc8d..7411f1cf741b 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1801,7 +1801,7 @@ static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) di->last_update = jiffies; - if (poll_interval > 0) + if (!di->removed && poll_interval > 0) mod_delayed_work(system_wq, &di->work, poll_interval * HZ); } @@ -2132,22 +2132,18 @@ EXPORT_SYMBOL_GPL(bq27xxx_battery_setup); void bq27xxx_battery_teardown(struct bq27xxx_device_info *di) { - /* - * power_supply_unregister call bq27xxx_battery_get_property which - * call bq27xxx_battery_poll. - * Make sure that bq27xxx_battery_poll will not call - * schedule_delayed_work again after unregister (which cause OOPS). - */ - poll_interval = 0; - - cancel_delayed_work_sync(&di->work); - - power_supply_unregister(di->bat); - mutex_lock(&bq27xxx_list_lock); list_del(&di->list); mutex_unlock(&bq27xxx_list_lock); + /* Set removed to avoid bq27xxx_battery_update() re-queuing the work */ + mutex_lock(&di->lock); + di->removed = true; + mutex_unlock(&di->lock); + + cancel_delayed_work_sync(&di->work); + + power_supply_unregister(di->bat); mutex_destroy(&di->lock); } EXPORT_SYMBOL_GPL(bq27xxx_battery_teardown); diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index a1aa68141d0b..e3322dad9c85 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -68,6 +68,7 @@ struct bq27xxx_device_info { struct bq27xxx_access_methods bus; struct bq27xxx_reg_cache cache; int charge_design_full; + bool removed; unsigned long last_update; struct delayed_work work; struct power_supply *bat; -- cgit v1.2.3 From 939a116142012926e25de0ea6b7e2f8d86a5f1b6 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 20:23:37 +0200 Subject: power: supply: bq27xxx: Ensure power_supply_changed() is called on current sign changes On gauges where the current register is signed, there is no charging flag in the flags register. So only checking flags will not result in power_supply_changed() getting called when e.g. a charger is plugged in and the current sign changes from negative (discharging) to positive (charging). This causes userspace's notion of the status to lag until userspace does a poll. And when a power_supply_leds.c LED trigger is used to indicate charging status with a LED, this LED will lag until the capacity percentage changes, which may take many minutes (because the LED trigger only is updated on power_supply_changed() calls). Fix this by calling bq27xxx_battery_current_and_status() on gauges with a signed current register and checking if the status has changed. Fixes: 297a533b3e62 ("bq27x00: Cache battery registers") Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- drivers/power/supply/bq27xxx_battery.c | 13 ++++++++++++- include/linux/power/bq27xxx_battery.h | 3 +++ 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 8f2995e9850a..f98b51ce19b5 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1836,6 +1836,7 @@ static int bq27xxx_battery_current_and_status( static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) { + union power_supply_propval status = di->last_status; struct bq27xxx_reg_cache cache = {0, }; bool has_singe_flag = di->opts & BQ27XXX_O_ZERO; @@ -1860,14 +1861,24 @@ static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) if (di->regs[BQ27XXX_REG_CYCT] != INVALID_REG_ADDR) cache.cycle_count = bq27xxx_battery_read_cyct(di); + /* + * On gauges with signed current reporting the current must be + * checked to detect charging <-> discharging status changes. + */ + if (!(di->opts & BQ27XXX_O_ZERO)) + bq27xxx_battery_current_and_status(di, NULL, &status, &cache); + /* We only have to read charge design full once */ if (di->charge_design_full <= 0) di->charge_design_full = bq27xxx_battery_read_dcap(di); } if ((di->cache.capacity != cache.capacity) || - (di->cache.flags != cache.flags)) + (di->cache.flags != cache.flags) || + (di->last_status.intval != status.intval)) { + di->last_status.intval = status.intval; power_supply_changed(di->bat); + } if (memcmp(&di->cache, &cache, sizeof(cache)) != 0) di->cache = cache; diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index e3322dad9c85..7c8d65414a70 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -2,6 +2,8 @@ #ifndef __LINUX_BQ27X00_BATTERY_H__ #define __LINUX_BQ27X00_BATTERY_H__ +#include + enum bq27xxx_chip { BQ27000 = 1, /* bq27000, bq27200 */ BQ27010, /* bq27010, bq27210 */ @@ -70,6 +72,7 @@ struct bq27xxx_device_info { int charge_design_full; bool removed; unsigned long last_update; + union power_supply_propval last_status; struct delayed_work work; struct power_supply *bat; struct list_head list; -- cgit v1.2.3 From 19b8766459c41c6f318f8a548cc1c66dffd18363 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Thu, 20 Apr 2023 16:06:03 +0100 Subject: firmware: arm_ffa: Fix FFA device names for logical partitions Each physical partition can provide multiple services each with UUID. Each such service can be presented as logical partition with a unique combination of VM ID and UUID. The number of distinct UUID in a system will be less than or equal to the number of logical partitions. However, currently it fails to register more than one logical partition or service within a physical partition as the device name contains only VM ID while both VM ID and UUID are maintained in the partition information. The kernel complains with the below message: | sysfs: cannot create duplicate filename '/devices/arm-ffa-8001' | CPU: 1 PID: 1 Comm: swapper/0 Not tainted 6.3.0-rc7 #8 | Hardware name: FVP Base RevC (DT) | Call trace: | dump_backtrace+0xf8/0x118 | show_stack+0x18/0x24 | dump_stack_lvl+0x50/0x68 | dump_stack+0x18/0x24 | sysfs_create_dir_ns+0xe0/0x13c | kobject_add_internal+0x220/0x3d4 | kobject_add+0x94/0x100 | device_add+0x144/0x5d8 | device_register+0x20/0x30 | ffa_device_register+0x88/0xd8 | ffa_setup_partitions+0x108/0x1b8 | ffa_init+0x2ec/0x3a4 | do_one_initcall+0xcc/0x240 | do_initcall_level+0x8c/0xac | do_initcalls+0x54/0x94 | do_basic_setup+0x1c/0x28 | kernel_init_freeable+0x100/0x16c | kernel_init+0x20/0x1a0 | ret_from_fork+0x10/0x20 | kobject_add_internal failed for arm-ffa-8001 with -EEXIST, don't try to | register things with the same name in the same directory. | arm_ffa arm-ffa: unable to register device arm-ffa-8001 err=-17 | ARM FF-A: ffa_setup_partitions: failed to register partition ID 0x8001 By virtue of being random enough to avoid collisions when generated in a distributed system, there is no way to compress UUID keys to the number of bits required to identify each. We can eliminate '-' in the name but it is not worth eliminating 4 bytes and add unnecessary logic for doing that. Also v1.0 doesn't provide the UUID of the partitions which makes it hard to use the same for the device name. So to keep it simple, let us alloc an ID using ida_alloc() and append the same to "arm-ffa" to make up a unique device name. Also stash the id value in ffa_dev to help freeing the ID later when the device is destroyed. Fixes: e781858488b9 ("firmware: arm_ffa: Add initial FFA bus support for device enumeration") Reported-by: Lucian Paul-Trifu Link: https://lore.kernel.org/r/20230419-ffa_fixes_6-4-v2-3-d9108e43a176@arm.com Signed-off-by: Sudeep Holla --- drivers/firmware/arm_ffa/bus.c | 16 +++++++++++++--- include/linux/arm_ffa.h | 1 + 2 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c index 36bd5423c2f0..2b8bfcd010f5 100644 --- a/drivers/firmware/arm_ffa/bus.c +++ b/drivers/firmware/arm_ffa/bus.c @@ -15,6 +15,8 @@ #include "common.h" +static DEFINE_IDA(ffa_bus_id); + static int ffa_device_match(struct device *dev, struct device_driver *drv) { const struct ffa_device_id *id_table; @@ -131,6 +133,7 @@ static void ffa_release_device(struct device *dev) { struct ffa_device *ffa_dev = to_ffa_dev(dev); + ida_free(&ffa_bus_id, ffa_dev->id); kfree(ffa_dev); } @@ -171,18 +174,24 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev) struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, const struct ffa_ops *ops) { - int ret; + int id, ret; struct device *dev; struct ffa_device *ffa_dev; + id = ida_alloc_min(&ffa_bus_id, 1, GFP_KERNEL); + if (id < 0) + return NULL; + ffa_dev = kzalloc(sizeof(*ffa_dev), GFP_KERNEL); - if (!ffa_dev) + if (!ffa_dev) { + ida_free(&ffa_bus_id, id); return NULL; + } dev = &ffa_dev->dev; dev->bus = &ffa_bus_type; dev->release = ffa_release_device; - dev_set_name(&ffa_dev->dev, "arm-ffa-%04x", vm_id); + dev_set_name(&ffa_dev->dev, "arm-ffa-%d", id); ffa_dev->vm_id = vm_id; ffa_dev->ops = ops; @@ -218,4 +227,5 @@ void arm_ffa_bus_exit(void) { ffa_devices_unregister(); bus_unregister(&ffa_bus_type); + ida_destroy(&ffa_bus_id); } diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index c87aeecaa9b2..583fe3b49a49 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -96,6 +96,7 @@ /* FFA Bus/Device/Driver related */ struct ffa_device { + u32 id; int vm_id; bool mode_32bit; uuid_t uuid; -- cgit v1.2.3 From ef1148d4487438a3408d6face2a8360d91b4af70 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 10 May 2023 15:46:46 +0000 Subject: ipv6: remove nexthop_fib6_nh_bh() After blamed commit, nexthop_fib6_nh_bh() and nexthop_fib6_nh() are the same. Delete nexthop_fib6_nh_bh(), and convert /proc/net/ipv6_route to standard rcu to avoid this splat: [ 5723.180080] WARNING: suspicious RCU usage [ 5723.180083] ----------------------------- [ 5723.180084] include/net/nexthop.h:516 suspicious rcu_dereference_check() usage! [ 5723.180086] other info that might help us debug this: [ 5723.180087] rcu_scheduler_active = 2, debug_locks = 1 [ 5723.180089] 2 locks held by cat/55856: [ 5723.180091] #0: ffff9440a582afa8 (&p->lock){+.+.}-{3:3}, at: seq_read_iter (fs/seq_file.c:188) [ 5723.180100] #1: ffffffffaac07040 (rcu_read_lock_bh){....}-{1:2}, at: rcu_lock_acquire (include/linux/rcupdate.h:326) [ 5723.180109] stack backtrace: [ 5723.180111] CPU: 14 PID: 55856 Comm: cat Tainted: G S I 6.3.0-dbx-DEV #528 [ 5723.180115] Call Trace: [ 5723.180117] [ 5723.180119] dump_stack_lvl (lib/dump_stack.c:107) [ 5723.180124] dump_stack (lib/dump_stack.c:114) [ 5723.180126] lockdep_rcu_suspicious (include/linux/context_tracking.h:122) [ 5723.180132] ipv6_route_seq_show (include/net/nexthop.h:?) [ 5723.180135] ? ipv6_route_seq_next (net/ipv6/ip6_fib.c:2605) [ 5723.180140] seq_read_iter (fs/seq_file.c:272) [ 5723.180145] seq_read (fs/seq_file.c:163) [ 5723.180151] proc_reg_read (fs/proc/inode.c:316 fs/proc/inode.c:328) [ 5723.180155] vfs_read (fs/read_write.c:468) [ 5723.180160] ? up_read (kernel/locking/rwsem.c:1617) [ 5723.180164] ksys_read (fs/read_write.c:613) [ 5723.180168] __x64_sys_read (fs/read_write.c:621) [ 5723.180170] do_syscall_64 (arch/x86/entry/common.c:?) [ 5723.180174] entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) [ 5723.180177] RIP: 0033:0x7fa455677d2a Fixes: 09eed1192cec ("neighbour: switch to standard rcu, instead of rcu_bh") Reported-by: syzbot Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230510154646.370659-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/net/nexthop.h | 23 ----------------------- net/ipv6/ip6_fib.c | 16 ++++++++-------- 2 files changed, 8 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 9fa291a04621..2b12725de9c0 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -497,29 +497,6 @@ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) return NULL; } -/* Variant of nexthop_fib6_nh(). - * Caller should either hold rcu_read_lock(), or RTNL. - */ -static inline struct fib6_nh *nexthop_fib6_nh_bh(struct nexthop *nh) -{ - struct nh_info *nhi; - - if (nh->is_group) { - struct nh_group *nh_grp; - - nh_grp = rcu_dereference_rtnl(nh->nh_grp); - nh = nexthop_mpath_select(nh_grp, 0); - if (!nh) - return NULL; - } - - nhi = rcu_dereference_rtnl(nh->nh_info); - if (nhi->family == AF_INET6) - return &nhi->fib6_nh; - - return NULL; -} - static inline struct net_device *fib6_info_nh_dev(struct fib6_info *f6i) { struct fib6_nh *fib6_nh; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 2438da5ff6da..bac768d36cc1 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -2491,7 +2491,7 @@ static int ipv6_route_native_seq_show(struct seq_file *seq, void *v) const struct net_device *dev; if (rt->nh) - fib6_nh = nexthop_fib6_nh_bh(rt->nh); + fib6_nh = nexthop_fib6_nh(rt->nh); seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen); @@ -2556,14 +2556,14 @@ static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl, if (tbl) { h = (tbl->tb6_id & (FIB6_TABLE_HASHSZ - 1)) + 1; - node = rcu_dereference_bh(hlist_next_rcu(&tbl->tb6_hlist)); + node = rcu_dereference(hlist_next_rcu(&tbl->tb6_hlist)); } else { h = 0; node = NULL; } while (!node && h < FIB6_TABLE_HASHSZ) { - node = rcu_dereference_bh( + node = rcu_dereference( hlist_first_rcu(&net->ipv6.fib_table_hash[h++])); } return hlist_entry_safe(node, struct fib6_table, tb6_hlist); @@ -2593,7 +2593,7 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (!v) goto iter_table; - n = rcu_dereference_bh(((struct fib6_info *)v)->fib6_next); + n = rcu_dereference(((struct fib6_info *)v)->fib6_next); if (n) return n; @@ -2619,12 +2619,12 @@ iter_table: } static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU_BH) + __acquires(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; - rcu_read_lock_bh(); + rcu_read_lock(); iter->tbl = ipv6_route_seq_next_table(NULL, net); iter->skip = *pos; @@ -2645,7 +2645,7 @@ static bool ipv6_route_iter_active(struct ipv6_route_iter *iter) } static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v) - __releases(RCU_BH) + __releases(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; @@ -2653,7 +2653,7 @@ static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v) if (ipv6_route_iter_active(iter)) fib6_walker_unlink(net, &iter->w); - rcu_read_unlock_bh(); + rcu_read_unlock(); } #if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL) -- cgit v1.2.3 From 8432a15cd810c99db464b7e7858d559f3e1920e3 Mon Sep 17 00:00:00 2001 From: Jó Ágila Bitsch Date: Sat, 22 Apr 2023 18:05:32 +0200 Subject: usb: gadget: drop superfluous ':' in doc string There was one superfluous ':' that kernel-doc complained about. Reported-by: Randy Dunlap Closes: https://lore.kernel.org/all/c718a490-028d-2682-9ad7-8256d16504bf@infradead.org/ Fixes: fb6211f1584a ("usb: gadget: add doc to struct usb_composite_dev") Signed-off-by: Jó Ágila Bitsch Reviewed-by: Randy Dunlap Link: https://lore.kernel.org/r/ZEQFzMntIrwvZl4+@jo-einhundert Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/composite.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index a2448e98854f..07531c4f4350 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -443,7 +443,7 @@ static inline struct usb_composite_driver *to_cdriver( * @bcd_webusb_version: 0x0100 by default, WebUSB specification version * @b_webusb_vendor_code: 0x0 by default, vendor code for WebUSB * @landing_page: empty by default, landing page to announce in WebUSB - * @use_webusb:: false by default, interested gadgets set it + * @use_webusb: false by default, interested gadgets set it * @os_desc_config: the configuration to be used with OS descriptors * @setup_pending: true when setup request is queued but not completed * @os_desc_pending: true when os_desc request is queued but not completed -- cgit v1.2.3 From 672cde9ef80ffde9e76d38f7aa2b287c4a18de9a Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 21 Apr 2023 08:46:11 +0300 Subject: iio: fix doc for iio_gts_find_sel_by_int_time The kerneldoc for iio_gts_find_sel_by_int_time() has an error. Documentation states that function is searching a selector for a HW-gain while it is searching a selector for an integration time. Fix the documentation by saying the function is looking for a selector for an integration time. Fixes: 38416c28e168 ("iio: light: Add gain-time-scale helpers") Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/ZEIjI4YUzqPZk/9X@fedora Signed-off-by: Jonathan Cameron --- include/linux/iio/iio-gts-helper.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/iio/iio-gts-helper.h b/include/linux/iio/iio-gts-helper.h index dd64e544a3da..9cb6c80dea71 100644 --- a/include/linux/iio/iio-gts-helper.h +++ b/include/linux/iio/iio-gts-helper.h @@ -135,7 +135,7 @@ static inline int iio_gts_find_int_time_by_sel(struct iio_gts *gts, int sel) /** * iio_gts_find_sel_by_int_time - find selector matching integration time * @gts: Gain time scale descriptor - * @gain: HW-gain for which matching selector is searched for + * @time: Integration time for which matching selector is searched for * * Return: a selector matching given integration time or -EINVAL if * selector was not found. -- cgit v1.2.3 From 6769a0b7ee0c3b31e1b22c3fadff2bfb642de23f Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Thu, 17 Nov 2022 04:59:22 +0000 Subject: media: dvb-core: Fix use-after-free on race condition at dvb_frontend If the device node of dvb_frontend is open() and the device is disconnected, many kinds of UAFs may occur when calling close() on the device node. The root cause of this is that wake_up() for dvbdev->wait_queue is implemented in the dvb_frontend_release() function, but wait_event() is not implemented in the dvb_frontend_stop() function. So, implement wait_event() function in dvb_frontend_stop() and add 'remove_mutex' which prevents race condition for 'fe->exit'. [mchehab: fix a couple of checkpatch warnings and some mistakes at the error handling logic] Link: https://lore.kernel.org/linux-media/20221117045925.14297-2-imv4bel@gmail.com Signed-off-by: Hyunwoo Kim Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dvb_frontend.c | 53 +++++++++++++++++++++++++++++------ include/media/dvb_frontend.h | 6 +++- 2 files changed, 49 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c index cc0a789f09ae..947b61959b2b 100644 --- a/drivers/media/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb-core/dvb_frontend.c @@ -809,15 +809,26 @@ static void dvb_frontend_stop(struct dvb_frontend *fe) dev_dbg(fe->dvb->device, "%s:\n", __func__); + mutex_lock(&fe->remove_mutex); + if (fe->exit != DVB_FE_DEVICE_REMOVED) fe->exit = DVB_FE_NORMAL_EXIT; mb(); - if (!fepriv->thread) + if (!fepriv->thread) { + mutex_unlock(&fe->remove_mutex); return; + } kthread_stop(fepriv->thread); + mutex_unlock(&fe->remove_mutex); + + if (fepriv->dvbdev->users < -1) { + wait_event(fepriv->dvbdev->wait_queue, + fepriv->dvbdev->users == -1); + } + sema_init(&fepriv->sem, 1); fepriv->state = FESTATE_IDLE; @@ -2761,9 +2772,13 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) struct dvb_adapter *adapter = fe->dvb; int ret; + mutex_lock(&fe->remove_mutex); + dev_dbg(fe->dvb->device, "%s:\n", __func__); - if (fe->exit == DVB_FE_DEVICE_REMOVED) - return -ENODEV; + if (fe->exit == DVB_FE_DEVICE_REMOVED) { + ret = -ENODEV; + goto err_remove_mutex; + } if (adapter->mfe_shared == 2) { mutex_lock(&adapter->mfe_lock); @@ -2771,7 +2786,8 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (adapter->mfe_dvbdev && !adapter->mfe_dvbdev->writers) { mutex_unlock(&adapter->mfe_lock); - return -EBUSY; + ret = -EBUSY; + goto err_remove_mutex; } adapter->mfe_dvbdev = dvbdev; } @@ -2794,8 +2810,10 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) while (mferetry-- && (mfedev->users != -1 || mfepriv->thread)) { if (msleep_interruptible(500)) { - if (signal_pending(current)) - return -EINTR; + if (signal_pending(current)) { + ret = -EINTR; + goto err_remove_mutex; + } } } @@ -2807,7 +2825,8 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (mfedev->users != -1 || mfepriv->thread) { mutex_unlock(&adapter->mfe_lock); - return -EBUSY; + ret = -EBUSY; + goto err_remove_mutex; } adapter->mfe_dvbdev = dvbdev; } @@ -2866,6 +2885,8 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (adapter->mfe_shared) mutex_unlock(&adapter->mfe_lock); + + mutex_unlock(&fe->remove_mutex); return ret; err3: @@ -2887,6 +2908,9 @@ err1: err0: if (adapter->mfe_shared) mutex_unlock(&adapter->mfe_lock); + +err_remove_mutex: + mutex_unlock(&fe->remove_mutex); return ret; } @@ -2897,6 +2921,8 @@ static int dvb_frontend_release(struct inode *inode, struct file *file) struct dvb_frontend_private *fepriv = fe->frontend_priv; int ret; + mutex_lock(&fe->remove_mutex); + dev_dbg(fe->dvb->device, "%s:\n", __func__); if ((file->f_flags & O_ACCMODE) != O_RDONLY) { @@ -2918,10 +2944,18 @@ static int dvb_frontend_release(struct inode *inode, struct file *file) } mutex_unlock(&fe->dvb->mdev_lock); #endif - if (fe->exit != DVB_FE_NO_EXIT) - wake_up(&dvbdev->wait_queue); if (fe->ops.ts_bus_ctrl) fe->ops.ts_bus_ctrl(fe, 0); + + if (fe->exit != DVB_FE_NO_EXIT) { + mutex_unlock(&fe->remove_mutex); + wake_up(&dvbdev->wait_queue); + } else { + mutex_unlock(&fe->remove_mutex); + } + + } else { + mutex_unlock(&fe->remove_mutex); } dvb_frontend_put(fe); @@ -3022,6 +3056,7 @@ int dvb_register_frontend(struct dvb_adapter *dvb, fepriv = fe->frontend_priv; kref_init(&fe->refcount); + mutex_init(&fe->remove_mutex); /* * After initialization, there need to be two references: one diff --git a/include/media/dvb_frontend.h b/include/media/dvb_frontend.h index e7c44870f20d..367d5381217b 100644 --- a/include/media/dvb_frontend.h +++ b/include/media/dvb_frontend.h @@ -686,7 +686,10 @@ struct dtv_frontend_properties { * @id: Frontend ID * @exit: Used to inform the DVB core that the frontend * thread should exit (usually, means that the hardware - * got disconnected. + * got disconnected). + * @remove_mutex: mutex that avoids a race condition between a callback + * called when the hardware is disconnected and the + * file_operations of dvb_frontend. */ struct dvb_frontend { @@ -704,6 +707,7 @@ struct dvb_frontend { int (*callback)(void *adapter_priv, int component, int cmd, int arg); int id; unsigned int exit; + struct mutex remove_mutex; }; /** -- cgit v1.2.3 From 4172385b0c9ac366dcab78eda48c26814b87ed1a Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Thu, 17 Nov 2022 04:59:23 +0000 Subject: media: dvb-core: Fix use-after-free due on race condition at dvb_net A race condition may occur between the .disconnect function, which is called when the device is disconnected, and the dvb_device_open() function, which is called when the device node is open()ed. This results in several types of UAFs. The root cause of this is that you use the dvb_device_open() function, which does not implement a conditional statement that checks 'dvbnet->exit'. So, add 'remove_mutex` to protect 'dvbnet->exit' and use locked_dvb_net_open() function to check 'dvbnet->exit'. [mchehab: fix a checkpatch warning] Link: https://lore.kernel.org/linux-media/20221117045925.14297-3-imv4bel@gmail.com Signed-off-by: Hyunwoo Kim Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dvb_net.c | 38 +++++++++++++++++++++++++++++++++++--- include/media/dvb_net.h | 4 ++++ 2 files changed, 39 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/media/dvb-core/dvb_net.c b/drivers/media/dvb-core/dvb_net.c index 8a2febf33ce2..8bb8dd34c223 100644 --- a/drivers/media/dvb-core/dvb_net.c +++ b/drivers/media/dvb-core/dvb_net.c @@ -1564,15 +1564,43 @@ static long dvb_net_ioctl(struct file *file, return dvb_usercopy(file, cmd, arg, dvb_net_do_ioctl); } +static int locked_dvb_net_open(struct inode *inode, struct file *file) +{ + struct dvb_device *dvbdev = file->private_data; + struct dvb_net *dvbnet = dvbdev->priv; + int ret; + + if (mutex_lock_interruptible(&dvbnet->remove_mutex)) + return -ERESTARTSYS; + + if (dvbnet->exit) { + mutex_unlock(&dvbnet->remove_mutex); + return -ENODEV; + } + + ret = dvb_generic_open(inode, file); + + mutex_unlock(&dvbnet->remove_mutex); + + return ret; +} + static int dvb_net_close(struct inode *inode, struct file *file) { struct dvb_device *dvbdev = file->private_data; struct dvb_net *dvbnet = dvbdev->priv; + mutex_lock(&dvbnet->remove_mutex); + dvb_generic_release(inode, file); - if(dvbdev->users == 1 && dvbnet->exit == 1) + if (dvbdev->users == 1 && dvbnet->exit == 1) { + mutex_unlock(&dvbnet->remove_mutex); wake_up(&dvbdev->wait_queue); + } else { + mutex_unlock(&dvbnet->remove_mutex); + } + return 0; } @@ -1580,7 +1608,7 @@ static int dvb_net_close(struct inode *inode, struct file *file) static const struct file_operations dvb_net_fops = { .owner = THIS_MODULE, .unlocked_ioctl = dvb_net_ioctl, - .open = dvb_generic_open, + .open = locked_dvb_net_open, .release = dvb_net_close, .llseek = noop_llseek, }; @@ -1599,10 +1627,13 @@ void dvb_net_release (struct dvb_net *dvbnet) { int i; + mutex_lock(&dvbnet->remove_mutex); dvbnet->exit = 1; + mutex_unlock(&dvbnet->remove_mutex); + if (dvbnet->dvbdev->users < 1) wait_event(dvbnet->dvbdev->wait_queue, - dvbnet->dvbdev->users==1); + dvbnet->dvbdev->users == 1); dvb_unregister_device(dvbnet->dvbdev); @@ -1621,6 +1652,7 @@ int dvb_net_init (struct dvb_adapter *adap, struct dvb_net *dvbnet, int i; mutex_init(&dvbnet->ioctl_mutex); + mutex_init(&dvbnet->remove_mutex); dvbnet->demux = dmx; for (i=0; iowner. And these fops are registered in 'file->f_ops' using replace_fops() in the dvb_device_open() process, and kfree()d in dvb_free_device(). However, it is not common to use dynamically allocated fops instead of 'static const' fops as an argument of replace_fops(), and UAF may occur. These UAFs can occur on any dvb type using dvb_register_device(), such as dvb_dvr, dvb_demux, dvb_frontend, dvb_net, etc. So, instead of kfree() the fops dynamically allocated in dvb_register_device() in dvb_free_device() called during the .disconnect() process, kfree() it collectively in exit_dvbdev() called when the dvbdev.c module is removed. Link: https://lore.kernel.org/linux-media/20221117045925.14297-4-imv4bel@gmail.com Signed-off-by: Hyunwoo Kim Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dvbdev.c | 84 ++++++++++++++++++++++++++++++----------- include/media/dvbdev.h | 15 ++++++++ 2 files changed, 78 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c index e9b3ce09e534..a4b05e366ccc 100644 --- a/drivers/media/dvb-core/dvbdev.c +++ b/drivers/media/dvb-core/dvbdev.c @@ -27,6 +27,7 @@ #include static DEFINE_MUTEX(dvbdev_mutex); +static LIST_HEAD(dvbdevfops_list); static int dvbdev_debug; module_param(dvbdev_debug, int, 0644); @@ -453,14 +454,15 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, enum dvb_device_type type, int demux_sink_pads) { struct dvb_device *dvbdev; - struct file_operations *dvbdevfops; + struct file_operations *dvbdevfops = NULL; + struct dvbdevfops_node *node = NULL, *new_node = NULL; struct device *clsdev; int minor; int id, ret; mutex_lock(&dvbdev_register_lock); - if ((id = dvbdev_get_free_id (adap, type)) < 0){ + if ((id = dvbdev_get_free_id (adap, type)) < 0) { mutex_unlock(&dvbdev_register_lock); *pdvbdev = NULL; pr_err("%s: couldn't find free device id\n", __func__); @@ -468,18 +470,45 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, } *pdvbdev = dvbdev = kzalloc(sizeof(*dvbdev), GFP_KERNEL); - if (!dvbdev){ mutex_unlock(&dvbdev_register_lock); return -ENOMEM; } - dvbdevfops = kmemdup(template->fops, sizeof(*dvbdevfops), GFP_KERNEL); + /* + * When a device of the same type is probe()d more than once, + * the first allocated fops are used. This prevents memory leaks + * that can occur when the same device is probe()d repeatedly. + */ + list_for_each_entry(node, &dvbdevfops_list, list_head) { + if (node->fops->owner == adap->module && + node->type == type && + node->template == template) { + dvbdevfops = node->fops; + break; + } + } - if (!dvbdevfops){ - kfree (dvbdev); - mutex_unlock(&dvbdev_register_lock); - return -ENOMEM; + if (dvbdevfops == NULL) { + dvbdevfops = kmemdup(template->fops, sizeof(*dvbdevfops), GFP_KERNEL); + if (!dvbdevfops) { + kfree(dvbdev); + mutex_unlock(&dvbdev_register_lock); + return -ENOMEM; + } + + new_node = kzalloc(sizeof(struct dvbdevfops_node), GFP_KERNEL); + if (!new_node) { + kfree(dvbdevfops); + kfree(dvbdev); + mutex_unlock(&dvbdev_register_lock); + return -ENOMEM; + } + + new_node->fops = dvbdevfops; + new_node->type = type; + new_node->template = template; + list_add_tail (&new_node->list_head, &dvbdevfops_list); } memcpy(dvbdev, template, sizeof(struct dvb_device)); @@ -490,20 +519,20 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, dvbdev->priv = priv; dvbdev->fops = dvbdevfops; init_waitqueue_head (&dvbdev->wait_queue); - dvbdevfops->owner = adap->module; - list_add_tail (&dvbdev->list_head, &adap->device_list); - down_write(&minor_rwsem); #ifdef CONFIG_DVB_DYNAMIC_MINORS for (minor = 0; minor < MAX_DVB_MINORS; minor++) if (dvb_minors[minor] == NULL) break; - if (minor == MAX_DVB_MINORS) { + if (new_node) { + list_del (&new_node->list_head); + kfree(dvbdevfops); + kfree(new_node); + } list_del (&dvbdev->list_head); - kfree(dvbdevfops); kfree(dvbdev); up_write(&minor_rwsem); mutex_unlock(&dvbdev_register_lock); @@ -512,41 +541,47 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, #else minor = nums2minor(adap->num, type, id); #endif - dvbdev->minor = minor; dvb_minors[minor] = dvb_device_get(dvbdev); up_write(&minor_rwsem); - ret = dvb_register_media_device(dvbdev, type, minor, demux_sink_pads); if (ret) { pr_err("%s: dvb_register_media_device failed to create the mediagraph\n", __func__); - + if (new_node) { + list_del (&new_node->list_head); + kfree(dvbdevfops); + kfree(new_node); + } dvb_media_device_free(dvbdev); list_del (&dvbdev->list_head); - kfree(dvbdevfops); kfree(dvbdev); mutex_unlock(&dvbdev_register_lock); return ret; } - mutex_unlock(&dvbdev_register_lock); - clsdev = device_create(dvb_class, adap->device, MKDEV(DVB_MAJOR, minor), dvbdev, "dvb%d.%s%d", adap->num, dnames[type], id); if (IS_ERR(clsdev)) { pr_err("%s: failed to create device dvb%d.%s%d (%ld)\n", __func__, adap->num, dnames[type], id, PTR_ERR(clsdev)); + if (new_node) { + list_del (&new_node->list_head); + kfree(dvbdevfops); + kfree(new_node); + } dvb_media_device_free(dvbdev); list_del (&dvbdev->list_head); - kfree(dvbdevfops); kfree(dvbdev); + mutex_unlock(&dvbdev_register_lock); return PTR_ERR(clsdev); } + dprintk("DVB: register adapter%d/%s%d @ minor: %i (0x%02x)\n", adap->num, dnames[type], id, minor, minor); + mutex_unlock(&dvbdev_register_lock); return 0; } EXPORT_SYMBOL(dvb_register_device); @@ -575,7 +610,6 @@ static void dvb_free_device(struct kref *ref) { struct dvb_device *dvbdev = container_of(ref, struct dvb_device, ref); - kfree (dvbdev->fops); kfree (dvbdev); } @@ -1081,9 +1115,17 @@ error: static void __exit exit_dvbdev(void) { + struct dvbdevfops_node *node, *next; + class_destroy(dvb_class); cdev_del(&dvb_device_cdev); unregister_chrdev_region(MKDEV(DVB_MAJOR, 0), MAX_DVB_MINORS); + + list_for_each_entry_safe(node, next, &dvbdevfops_list, list_head) { + list_del (&node->list_head); + kfree(node->fops); + kfree(node); + } } subsys_initcall(init_dvbdev); diff --git a/include/media/dvbdev.h b/include/media/dvbdev.h index 29d25c8a6f13..8958e5e2fc5b 100644 --- a/include/media/dvbdev.h +++ b/include/media/dvbdev.h @@ -193,6 +193,21 @@ struct dvb_device { void *priv; }; +/** + * struct dvbdevfops_node - fops nodes registered in dvbdevfops_list + * + * @fops: Dynamically allocated fops for ->owner registration + * @type: type of dvb_device + * @template: dvb_device used for registration + * @list_head: list_head for dvbdevfops_list + */ +struct dvbdevfops_node { + struct file_operations *fops; + enum dvb_device_type type; + const struct dvb_device *template; + struct list_head list_head; +}; + /** * dvb_device_get - Increase dvb_device reference * -- cgit v1.2.3 From 948f072ada23e0a504c5e4d7d71d4c83bd0785ec Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 9 May 2023 09:42:47 +1000 Subject: SUNRPC: always free ctxt when freeing deferred request Since the ->xprt_ctxt pointer was added to svc_deferred_req, it has not been sufficient to use kfree() to free a deferred request. We may need to free the ctxt as well. As freeing the ctxt is all that ->xpo_release_rqst() does, we repurpose it to explicit do that even when the ctxt is not stored in an rqst. So we now have ->xpo_release_ctxt() which is given an xprt and a ctxt, which may have been taken either from an rqst or from a dreq. The caller is now responsible for clearing that pointer after the call to ->xpo_release_ctxt. We also clear dr->xprt_ctxt when the ctxt is moved into a new rqst when revisiting a deferred request. This ensures there is only one pointer to the ctxt, so the risk of double freeing in future is reduced. The new code in svc_xprt_release which releases both the ctxt and any rq_deferred depends on this. Fixes: 773f91b2cf3f ("SUNRPC: Fix NFSD's request deferral on RDMA transports") Signed-off-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_rdma.h | 2 +- include/linux/sunrpc/svc_xprt.h | 2 +- net/sunrpc/svc_xprt.c | 23 +++++++++++++++++------ net/sunrpc/svcsock.c | 30 ++++++++++++++++-------------- net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 11 +++++------ net/sunrpc/xprtrdma/svc_rdma_transport.c | 2 +- 6 files changed, 41 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 24aa159d29a7..fbc4bd423b35 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -176,7 +176,7 @@ extern struct svc_rdma_recv_ctxt * extern void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma, struct svc_rdma_recv_ctxt *ctxt); extern void svc_rdma_flush_recv_queues(struct svcxprt_rdma *rdma); -extern void svc_rdma_release_rqst(struct svc_rqst *rqstp); +extern void svc_rdma_release_ctxt(struct svc_xprt *xprt, void *ctxt); extern int svc_rdma_recvfrom(struct svc_rqst *); /* svc_rdma_rw.c */ diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 867479204840..a6b12631db21 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -23,7 +23,7 @@ struct svc_xprt_ops { int (*xpo_sendto)(struct svc_rqst *); int (*xpo_result_payload)(struct svc_rqst *, unsigned int, unsigned int); - void (*xpo_release_rqst)(struct svc_rqst *); + void (*xpo_release_ctxt)(struct svc_xprt *xprt, void *ctxt); void (*xpo_detach)(struct svc_xprt *); void (*xpo_free)(struct svc_xprt *); void (*xpo_kill_temp_xprt)(struct svc_xprt *); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 5fd94f6bdc75..13a14897bc17 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -532,13 +532,23 @@ void svc_reserve(struct svc_rqst *rqstp, int space) } EXPORT_SYMBOL_GPL(svc_reserve); +static void free_deferred(struct svc_xprt *xprt, struct svc_deferred_req *dr) +{ + if (!dr) + return; + + xprt->xpt_ops->xpo_release_ctxt(xprt, dr->xprt_ctxt); + kfree(dr); +} + static void svc_xprt_release(struct svc_rqst *rqstp) { struct svc_xprt *xprt = rqstp->rq_xprt; - xprt->xpt_ops->xpo_release_rqst(rqstp); + xprt->xpt_ops->xpo_release_ctxt(xprt, rqstp->rq_xprt_ctxt); + rqstp->rq_xprt_ctxt = NULL; - kfree(rqstp->rq_deferred); + free_deferred(xprt, rqstp->rq_deferred); rqstp->rq_deferred = NULL; svc_rqst_release_pages(rqstp); @@ -1054,7 +1064,7 @@ static void svc_delete_xprt(struct svc_xprt *xprt) spin_unlock_bh(&serv->sv_lock); while ((dr = svc_deferred_dequeue(xprt)) != NULL) - kfree(dr); + free_deferred(xprt, dr); call_xpt_users(xprt); svc_xprt_put(xprt); @@ -1176,8 +1186,8 @@ static void svc_revisit(struct cache_deferred_req *dreq, int too_many) if (too_many || test_bit(XPT_DEAD, &xprt->xpt_flags)) { spin_unlock(&xprt->xpt_lock); trace_svc_defer_drop(dr); + free_deferred(xprt, dr); svc_xprt_put(xprt); - kfree(dr); return; } dr->xprt = NULL; @@ -1222,14 +1232,13 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) dr->addrlen = rqstp->rq_addrlen; dr->daddr = rqstp->rq_daddr; dr->argslen = rqstp->rq_arg.len >> 2; - dr->xprt_ctxt = rqstp->rq_xprt_ctxt; /* back up head to the start of the buffer and copy */ skip = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len; memcpy(dr->args, rqstp->rq_arg.head[0].iov_base - skip, dr->argslen << 2); } - WARN_ON_ONCE(rqstp->rq_xprt_ctxt != dr->xprt_ctxt); + dr->xprt_ctxt = rqstp->rq_xprt_ctxt; rqstp->rq_xprt_ctxt = NULL; trace_svc_defer(rqstp); svc_xprt_get(rqstp->rq_xprt); @@ -1263,6 +1272,8 @@ static noinline int svc_deferred_recv(struct svc_rqst *rqstp) rqstp->rq_daddr = dr->daddr; rqstp->rq_respages = rqstp->rq_pages; rqstp->rq_xprt_ctxt = dr->xprt_ctxt; + + dr->xprt_ctxt = NULL; svc_xprt_received(rqstp->rq_xprt); return dr->argslen << 2; } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 9989194446a5..63fe7a338992 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -121,27 +121,27 @@ static void svc_reclassify_socket(struct socket *sock) #endif /** - * svc_tcp_release_rqst - Release transport-related resources - * @rqstp: request structure with resources to be released + * svc_tcp_release_ctxt - Release transport-related resources + * @xprt: the transport which owned the context + * @ctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt * */ -static void svc_tcp_release_rqst(struct svc_rqst *rqstp) +static void svc_tcp_release_ctxt(struct svc_xprt *xprt, void *ctxt) { } /** - * svc_udp_release_rqst - Release transport-related resources - * @rqstp: request structure with resources to be released + * svc_udp_release_ctxt - Release transport-related resources + * @xprt: the transport which owned the context + * @ctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt * */ -static void svc_udp_release_rqst(struct svc_rqst *rqstp) +static void svc_udp_release_ctxt(struct svc_xprt *xprt, void *ctxt) { - struct sk_buff *skb = rqstp->rq_xprt_ctxt; + struct sk_buff *skb = ctxt; - if (skb) { - rqstp->rq_xprt_ctxt = NULL; + if (skb) consume_skb(skb); - } } union svc_pktinfo_u { @@ -696,7 +696,8 @@ static int svc_udp_sendto(struct svc_rqst *rqstp) unsigned int sent; int err; - svc_udp_release_rqst(rqstp); + svc_udp_release_ctxt(xprt, rqstp->rq_xprt_ctxt); + rqstp->rq_xprt_ctxt = NULL; svc_set_cmsg_data(rqstp, cmh); @@ -768,7 +769,7 @@ static const struct svc_xprt_ops svc_udp_ops = { .xpo_recvfrom = svc_udp_recvfrom, .xpo_sendto = svc_udp_sendto, .xpo_result_payload = svc_sock_result_payload, - .xpo_release_rqst = svc_udp_release_rqst, + .xpo_release_ctxt = svc_udp_release_ctxt, .xpo_detach = svc_sock_detach, .xpo_free = svc_sock_free, .xpo_has_wspace = svc_udp_has_wspace, @@ -1301,7 +1302,8 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp) unsigned int sent; int err; - svc_tcp_release_rqst(rqstp); + svc_tcp_release_ctxt(xprt, rqstp->rq_xprt_ctxt); + rqstp->rq_xprt_ctxt = NULL; atomic_inc(&svsk->sk_sendqlen); mutex_lock(&xprt->xpt_mutex); @@ -1346,7 +1348,7 @@ static const struct svc_xprt_ops svc_tcp_ops = { .xpo_recvfrom = svc_tcp_recvfrom, .xpo_sendto = svc_tcp_sendto, .xpo_result_payload = svc_sock_result_payload, - .xpo_release_rqst = svc_tcp_release_rqst, + .xpo_release_ctxt = svc_tcp_release_ctxt, .xpo_detach = svc_tcp_sock_detach, .xpo_free = svc_sock_free, .xpo_has_wspace = svc_tcp_has_wspace, diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 1c658fa43063..a22fe7587fa6 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -239,21 +239,20 @@ void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma, } /** - * svc_rdma_release_rqst - Release transport-specific per-rqst resources - * @rqstp: svc_rqst being released + * svc_rdma_release_ctxt - Release transport-specific per-rqst resources + * @xprt: the transport which owned the context + * @vctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt * * Ensure that the recv_ctxt is released whether or not a Reply * was sent. For example, the client could close the connection, * or svc_process could drop an RPC, before the Reply is sent. */ -void svc_rdma_release_rqst(struct svc_rqst *rqstp) +void svc_rdma_release_ctxt(struct svc_xprt *xprt, void *vctxt) { - struct svc_rdma_recv_ctxt *ctxt = rqstp->rq_xprt_ctxt; - struct svc_xprt *xprt = rqstp->rq_xprt; + struct svc_rdma_recv_ctxt *ctxt = vctxt; struct svcxprt_rdma *rdma = container_of(xprt, struct svcxprt_rdma, sc_xprt); - rqstp->rq_xprt_ctxt = NULL; if (ctxt) svc_rdma_recv_ctxt_put(rdma, ctxt); } diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 416b298f74dd..ca04f7a6a085 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -80,7 +80,7 @@ static const struct svc_xprt_ops svc_rdma_ops = { .xpo_recvfrom = svc_rdma_recvfrom, .xpo_sendto = svc_rdma_sendto, .xpo_result_payload = svc_rdma_result_payload, - .xpo_release_rqst = svc_rdma_release_rqst, + .xpo_release_ctxt = svc_rdma_release_ctxt, .xpo_detach = svc_rdma_detach, .xpo_free = svc_rdma_free, .xpo_has_wspace = svc_rdma_has_wspace, -- cgit v1.2.3 From dcb88fc47d0e79fd54a19a63a4c8a7594ba0838e Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 12 May 2023 12:46:07 -0500 Subject: ASoC: SOF: Intel: hda-mlink: add helper to get SoundWire hlink Same functionality as for DMIC/SSP with different ID. Signed-off-by: Pierre-Louis Bossart hext_link; +} +EXPORT_SYMBOL_NS(hdac_bus_eml_sdw_get_hlink, SND_SOC_SOF_HDA_MLINK); + int hdac_bus_eml_enable_offload(struct hdac_bus *bus, bool alt, int elid, bool enable) { struct hdac_ext2_link *h2link; -- cgit v1.2.3 From ccc2f0c1b6b613cd0014c3dcd465a4b57856b0fe Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 12 May 2023 12:46:11 -0500 Subject: ASoC: SOF: Intel: hda-mlink: add helper to program SoundWire PCMSyCM registers These registers enable the HDaudio DMA hardware to split/merge data from different PDIs, possibly on different links. This capability exists for all types of HDaudio extended links, but for now is only required for SoundWire. In the SSP/DMIC case, the IP is programmed by the DSP firmware. Signed-off-by: Pierre-Louis Bossart base_ptr + h2link->shim_offset + + h2link->instance_offset * sublink + + AZX_REG_SDW_SHIM_PCMSyCM(y); + + mutex_lock(&h2link->eml_lock); + + hdaml_shim_map_stream_ch(pcmsycm, 0, hweight32(channel_mask), + stream_id, dir); + + mutex_unlock(&h2link->eml_lock); + + val = readw(pcmsycm); + + dev_dbg(bus->dev, "channel_mask %#x stream_id %d dir %d pcmscm %#x\n", + channel_mask, stream_id, dir, val); + + return 0; +} EXPORT_SYMBOL_NS(hdac_bus_eml_sdw_map_stream_ch, SND_SOC_SOF_HDA_MLINK); + void hda_bus_ml_put_all(struct hdac_bus *bus) { struct hdac_ext_link *hlink; -- cgit v1.2.3 From be3c215342956313845308e0e631341e62370a2b Mon Sep 17 00:00:00 2001 From: Ranjani Sridharan Date: Mon, 15 May 2023 13:44:03 +0300 Subject: ASoC: SOF: Separate the tokens for input and output pin index Using the same token ID for both input and output format pin index results in collisions and incorrect pin index getting parsed from topology. Signed-off-by: Ranjani Sridharan Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm-chip.c | 4 ++++ drivers/char/tpm/tpm-interface.c | 10 ++++++++++ include/linux/tpm.h | 1 + 3 files changed, 15 insertions(+) (limited to 'include') diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index c10a4aa97373..cd48033b804a 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -571,6 +571,10 @@ static int tpm_hwrng_read(struct hwrng *rng, void *data, size_t max, bool wait) { struct tpm_chip *chip = container_of(rng, struct tpm_chip, hwrng); + /* Give back zero bytes, as TPM chip has not yet fully resumed: */ + if (chip->flags & TPM_CHIP_FLAG_SUSPENDED) + return 0; + return tpm_get_random(chip, data, max); } diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index 4463d0018290..586ca10b0d72 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -412,6 +412,8 @@ int tpm_pm_suspend(struct device *dev) } suspended: + chip->flags |= TPM_CHIP_FLAG_SUSPENDED; + if (rc) dev_err(dev, "Ignoring error %d while suspending\n", rc); return 0; @@ -429,6 +431,14 @@ int tpm_pm_resume(struct device *dev) if (chip == NULL) return -ENODEV; + chip->flags &= ~TPM_CHIP_FLAG_SUSPENDED; + + /* + * Guarantee that SUSPENDED is written last, so that hwrng does not + * activate before the chip has been fully resumed. + */ + wmb(); + return 0; } EXPORT_SYMBOL_GPL(tpm_pm_resume); diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 77693389c3f9..6a1e8f157255 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -282,6 +282,7 @@ enum tpm_chip_flags { TPM_CHIP_FLAG_ALWAYS_POWERED = BIT(5), TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED = BIT(6), TPM_CHIP_FLAG_FIRMWARE_UPGRADE = BIT(7), + TPM_CHIP_FLAG_SUSPENDED = BIT(8), }; #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) -- cgit v1.2.3 From f7ba52f302fdc392e0047f38e50841483d997144 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 18 Apr 2023 14:49:25 -0700 Subject: vmlinux.lds.h: Discard .note.gnu.property section When tooling reads ELF notes, it assumes each note entry is aligned to the value listed in the .note section header's sh_addralign field. The kernel-created ELF notes in the .note.Linux and .note.Xen sections are aligned to 4 bytes. This causes the toolchain to set those sections' sh_addralign values to 4. On the other hand, the GCC-created .note.gnu.property section has an sh_addralign value of 8 for some reason, despite being based on struct Elf32_Nhdr which only needs 4-byte alignment. When the mismatched input sections get linked together into the vmlinux .notes output section, the higher alignment "wins", resulting in an sh_addralign of 8, which confuses tooling. For example: $ readelf -n .tmp_vmlinux.btf ... readelf: .tmp_vmlinux.btf: Warning: note with invalid namesz and/or descsz found at offset 0x170 readelf: .tmp_vmlinux.btf: Warning: type: 0x4, namesize: 0x006e6558, descsize: 0x00008801, alignment: 8 In this case readelf thinks there's alignment padding where there is none, so it starts reading an ELF note in the middle. With newer toolchains (e.g., latest Fedora Rawhide), a similar mismatch triggers a build failure when combined with CONFIG_X86_KERNEL_IBT: btf_encoder__encode: btf__dedup failed! Failed to encode BTF libbpf: failed to find '.BTF' ELF section in vmlinux FAILED: load BTF from vmlinux: No data available make[1]: *** [scripts/Makefile.vmlinux:35: vmlinux] Error 255 This latter error was caused by pahole crashing when it encountered the corrupt .notes section. This crash has been fixed in dwarves version 1.25. As Tianyi Liu describes: "Pahole reads .notes to look for LINUX_ELFNOTE_BUILD_LTO. When LTO is enabled, pahole needs to call cus__merge_and_process_cu to merge compile units, at which point there should only be one unspecified type (used to represent some compilation information) in the global context. However, when the kernel is compiled without LTO, if pahole calls cus__merge_and_process_cu due to alignment issues with notes, multiple unspecified types may appear after merging the cus, and older versions of pahole only support up to one. This is why pahole 1.24 crashes, while newer versions support multiple. However, the latest version of pahole still does not solve the problem of incorrect LTO recognition, so compiling the kernel may be slower than normal." Even with the newer pahole, the note section misaligment issue still exists and pahole is misinterpreting the LTO note. Fix it by discarding the .note.gnu.property section. While GNU properties are important for user space (and VDSO), they don't seem to have any use for vmlinux. (In fact, they're already getting (inadvertently) stripped from vmlinux when CONFIG_DEBUG_INFO_BTF is enabled. The BTF data is extracted from vmlinux.o with "objcopy --only-section=.BTF" into .btf.vmlinux.bin.o. That file doesn't have .note.gnu.property, so when it gets modified and linked back into the main object, the linker automatically strips it (see "How GNU properties are merged" in the ld man page).) Reported-by: Daniel Xu Link: https://lkml.kernel.org/bpf/57830c30-cd77-40cf-9cd1-3bb608aa602e@app.fastmail.com Debugged-by: Tianyi Liu Suggested-by: Joan Bruguera Micó Link: https://lore.kernel.org/r/20230418214925.ay3jpf2zhw75kgmd@treble Signed-off-by: Josh Poimboeuf --- include/asm-generic/vmlinux.lds.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index d1f57e4868ed..cebdf1ca415d 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -891,9 +891,16 @@ /* * Discard .note.GNU-stack, which is emitted as PROGBITS by the compiler. * Otherwise, the type of .notes section would become PROGBITS instead of NOTES. + * + * Also, discard .note.gnu.property, otherwise it forces the notes section to + * be 8-byte aligned which causes alignment mismatches with the kernel's custom + * 4-byte aligned notes. */ #define NOTES \ - /DISCARD/ : { *(.note.GNU-stack) } \ + /DISCARD/ : { \ + *(.note.GNU-stack) \ + *(.note.gnu.property) \ + } \ .notes : AT(ADDR(.notes) - LOAD_OFFSET) { \ BOUNDED_SECTION_BY(.note.*, _notes) \ } NOTES_HEADERS \ -- cgit v1.2.3 From 06caeb536b2b21668efd2d6fa97c09461957b3a7 Mon Sep 17 00:00:00 2001 From: Po-Wen Kao Date: Thu, 4 May 2023 23:44:50 +0800 Subject: scsi: ufs: core: Rename symbol sizeof_utp_transfer_cmd_desc() Naming the functions after standard operators like sizeof() may cause confusion. Rename it to ufshcd_get_ucd_size(). Signed-off-by: Po-Wen Kao Link: https://lore.kernel.org/r/20230504154454.26654-3-powen.kao@mediatek.com Suggested-by: Manivannan Sadhasivam Reviewed-by: Stanley Chu Reviewed-by: Ziqi Chen Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufs-mcq.c | 2 +- drivers/ufs/core/ufshcd.c | 10 +++++----- include/ufs/ufshcd.h | 2 +- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index b7c5f39b50e6..937933d3f77c 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -265,7 +265,7 @@ static int ufshcd_mcq_get_tag(struct ufs_hba *hba, addr = (le64_to_cpu(cqe->command_desc_base_addr) & CQE_UCD_BA) - hba->ucdl_dma_addr; - return div_u64(addr, sizeof_utp_transfer_cmd_desc(hba)); + return div_u64(addr, ufshcd_get_ucd_size(hba)); } static void ufshcd_mcq_process_cqe(struct ufs_hba *hba, diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 984abbe1fb93..e7e79f515e14 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -2849,10 +2849,10 @@ static void ufshcd_map_queues(struct Scsi_Host *shost) static void ufshcd_init_lrb(struct ufs_hba *hba, struct ufshcd_lrb *lrb, int i) { struct utp_transfer_cmd_desc *cmd_descp = (void *)hba->ucdl_base_addr + - i * sizeof_utp_transfer_cmd_desc(hba); + i * ufshcd_get_ucd_size(hba); struct utp_transfer_req_desc *utrdlp = hba->utrdl_base_addr; dma_addr_t cmd_desc_element_addr = hba->ucdl_dma_addr + - i * sizeof_utp_transfer_cmd_desc(hba); + i * ufshcd_get_ucd_size(hba); u16 response_offset = offsetof(struct utp_transfer_cmd_desc, response_upiu); u16 prdt_offset = offsetof(struct utp_transfer_cmd_desc, prd_table); @@ -3761,7 +3761,7 @@ static int ufshcd_memory_alloc(struct ufs_hba *hba) size_t utmrdl_size, utrdl_size, ucdl_size; /* Allocate memory for UTP command descriptors */ - ucdl_size = sizeof_utp_transfer_cmd_desc(hba) * hba->nutrs; + ucdl_size = ufshcd_get_ucd_size(hba) * hba->nutrs; hba->ucdl_base_addr = dmam_alloc_coherent(hba->dev, ucdl_size, &hba->ucdl_dma_addr, @@ -3861,7 +3861,7 @@ static void ufshcd_host_memory_configure(struct ufs_hba *hba) prdt_offset = offsetof(struct utp_transfer_cmd_desc, prd_table); - cmd_desc_size = sizeof_utp_transfer_cmd_desc(hba); + cmd_desc_size = ufshcd_get_ucd_size(hba); cmd_desc_dma_addr = hba->ucdl_dma_addr; for (i = 0; i < hba->nutrs; i++) { @@ -8452,7 +8452,7 @@ static void ufshcd_release_sdb_queue(struct ufs_hba *hba, int nutrs) { size_t ucdl_size, utrdl_size; - ucdl_size = sizeof_utp_transfer_cmd_desc(hba) * nutrs; + ucdl_size = ufshcd_get_ucd_size(hba) * nutrs; dmam_free_coherent(hba->dev, ucdl_size, hba->ucdl_base_addr, hba->ucdl_dma_addr); diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index f7553293ba98..df1d04f7a542 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -1133,7 +1133,7 @@ static inline size_t ufshcd_sg_entry_size(const struct ufs_hba *hba) ({ (void)(hba); BUILD_BUG_ON(sg_entry_size != sizeof(struct ufshcd_sg_entry)); }) #endif -static inline size_t sizeof_utp_transfer_cmd_desc(const struct ufs_hba *hba) +static inline size_t ufshcd_get_ucd_size(const struct ufs_hba *hba) { return sizeof(struct utp_transfer_cmd_desc) + SG_ALL * ufshcd_sg_entry_size(hba); } -- cgit v1.2.3 From f15afbd34d8fadbd375f1212e97837e32bc170cc Mon Sep 17 00:00:00 2001 From: Hao Ge Date: Mon, 24 Apr 2023 13:18:35 +0800 Subject: fs: fix undefined behavior in bit shift for SB_NOUSER Shifting signed 32-bit value by 31 bits is undefined, so changing significant bit to unsigned. It was spotted by UBSAN. So let's just fix this by using the BIT() helper for all SB_* flags. Fixes: e462ec50cb5f ("VFS: Differentiate mount flags (MS_*) from internal superblock flags") Signed-off-by: Hao Ge Message-Id: <20230424051835.374204-1-gehao@kylinos.cn> [brauner@kernel.org: use BIT() for all SB_* flags] Signed-off-by: Christian Brauner --- include/linux/fs.h | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 21a981680856..133f0640fb24 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1076,29 +1076,29 @@ extern int send_sigurg(struct fown_struct *fown); * sb->s_flags. Note that these mirror the equivalent MS_* flags where * represented in both. */ -#define SB_RDONLY 1 /* Mount read-only */ -#define SB_NOSUID 2 /* Ignore suid and sgid bits */ -#define SB_NODEV 4 /* Disallow access to device special files */ -#define SB_NOEXEC 8 /* Disallow program execution */ -#define SB_SYNCHRONOUS 16 /* Writes are synced at once */ -#define SB_MANDLOCK 64 /* Allow mandatory locks on an FS */ -#define SB_DIRSYNC 128 /* Directory modifications are synchronous */ -#define SB_NOATIME 1024 /* Do not update access times. */ -#define SB_NODIRATIME 2048 /* Do not update directory access times */ -#define SB_SILENT 32768 -#define SB_POSIXACL (1<<16) /* VFS does not apply the umask */ -#define SB_INLINECRYPT (1<<17) /* Use blk-crypto for encrypted files */ -#define SB_KERNMOUNT (1<<22) /* this is a kern_mount call */ -#define SB_I_VERSION (1<<23) /* Update inode I_version field */ -#define SB_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ +#define SB_RDONLY BIT(0) /* Mount read-only */ +#define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */ +#define SB_NODEV BIT(2) /* Disallow access to device special files */ +#define SB_NOEXEC BIT(3) /* Disallow program execution */ +#define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */ +#define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */ +#define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */ +#define SB_NOATIME BIT(10) /* Do not update access times. */ +#define SB_NODIRATIME BIT(11) /* Do not update directory access times */ +#define SB_SILENT BIT(15) +#define SB_POSIXACL BIT(16) /* VFS does not apply the umask */ +#define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ +#define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ +#define SB_I_VERSION BIT(23) /* Update inode I_version field */ +#define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */ /* These sb flags are internal to the kernel */ -#define SB_SUBMOUNT (1<<26) -#define SB_FORCE (1<<27) -#define SB_NOSEC (1<<28) -#define SB_BORN (1<<29) -#define SB_ACTIVE (1<<30) -#define SB_NOUSER (1<<31) +#define SB_SUBMOUNT BIT(26) +#define SB_FORCE BIT(27) +#define SB_NOSEC BIT(28) +#define SB_BORN BIT(29) +#define SB_ACTIVE BIT(30) +#define SB_NOUSER BIT(31) /* These flags relate to encoding and casefolding */ #define SB_ENC_STRICT_MODE_FL (1 << 0) -- cgit v1.2.3 From a18ef64fe1e4558b14a6e0ca9fbe8264475b7013 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 17 May 2023 14:47:12 +0200 Subject: tracing: make ftrace_likely_update() declaration visible This function is only used when CONFIG_TRACE_BRANCH_PROFILING is set and DISABLE_BRANCH_PROFILING is not set, and the declaration is hidden behind this combination of tests. But that causes a warning when building with CONFIG_TRACING_BRANCHES, since that sets DISABLE_BRANCH_PROFILING for the tracing code, and the declaration is thus hidden: kernel/trace/trace_branch.c:205:6: error: no previous prototype for 'ftrace_likely_update' [-Werror=missing-prototypes] Move the declaration out of the #ifdef to avoid the warning. Signed-off-by: Arnd Bergmann Signed-off-by: Linus Torvalds --- include/linux/compiler.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 947a60b801db..d7779a18b24f 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -12,11 +12,10 @@ * Note: DISABLE_BRANCH_PROFILING can be used by special lowlevel code * to disable branch tracing on a per file basis. */ -#if defined(CONFIG_TRACE_BRANCH_PROFILING) \ - && !defined(DISABLE_BRANCH_PROFILING) && !defined(__CHECKER__) void ftrace_likely_update(struct ftrace_likely_data *f, int val, int expect, int is_constant); - +#if defined(CONFIG_TRACE_BRANCH_PROFILING) \ + && !defined(DISABLE_BRANCH_PROFILING) && !defined(__CHECKER__) #define likely_notrace(x) __builtin_expect(!!(x), 1) #define unlikely_notrace(x) __builtin_expect(!!(x), 0) -- cgit v1.2.3 From 26e239b37ebdfd189a2e6f94d3407e70313348bc Mon Sep 17 00:00:00 2001 From: Joan Bruguera Micó Date: Wed, 3 May 2023 01:32:32 +0000 Subject: mm: shrinkers: fix race condition on debugfs cleanup When something registers and unregisters many shrinkers, such as: for x in $(seq 10000); do unshare -Ui true; done Sometimes the following error is printed to the kernel log: debugfs: Directory '...' with parent 'shrinker' already present! This occurs since commit badc28d4924b ("mm: shrinkers: fix deadlock in shrinker debugfs") / v6.2: Since the call to `debugfs_remove_recursive` was moved outside the `shrinker_rwsem`/`shrinker_mutex` lock, but the call to `ida_free` stayed inside, a newly registered shrinker can be re-assigned that ID and attempt to create the debugfs directory before the directory from the previous shrinker has been removed. The locking changes in commit f95bdb700bc6 ("mm: vmscan: make global slab shrink lockless") made the race condition more likely, though it existed before then. Commit badc28d4924b ("mm: shrinkers: fix deadlock in shrinker debugfs") could be reverted since the issue is addressed should no longer occur since the count and scan operations are lockless since commit 20cd1892fcc3 ("mm: shrinkers: make count and scan in shrinker debugfs lockless"). However, since this is a contended lock, prefer instead moving `ida_free` outside the lock to avoid the race. Link: https://lkml.kernel.org/r/20230503013232.299211-1-joanbrugueram@gmail.com Fixes: badc28d4924b ("mm: shrinkers: fix deadlock in shrinker debugfs") Signed-off-by: Joan Bruguera Micó Cc: Qi Zheng Cc: Roman Gushchin Signed-off-by: Andrew Morton --- include/linux/shrinker.h | 13 +++++++++++-- mm/shrinker_debug.c | 15 ++++++++++----- mm/vmscan.c | 5 +++-- 3 files changed, 24 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 7bde8e1c228a..224293b2dd06 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -107,7 +107,10 @@ extern void synchronize_shrinkers(void); #ifdef CONFIG_SHRINKER_DEBUG extern int shrinker_debugfs_add(struct shrinker *shrinker); -extern struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker); +extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id); +extern void shrinker_debugfs_remove(struct dentry *debugfs_entry, + int debugfs_id); extern int __printf(2, 3) shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...); #else /* CONFIG_SHRINKER_DEBUG */ @@ -115,10 +118,16 @@ static inline int shrinker_debugfs_add(struct shrinker *shrinker) { return 0; } -static inline struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) +static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id) { + *debugfs_id = -1; return NULL; } +static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, + int debugfs_id) +{ +} static inline __printf(2, 3) int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) { diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c index 3f83b10c5031..fe10436d9911 100644 --- a/mm/shrinker_debug.c +++ b/mm/shrinker_debug.c @@ -237,7 +237,8 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) } EXPORT_SYMBOL(shrinker_debugfs_rename); -struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) +struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id) { struct dentry *entry = shrinker->debugfs_entry; @@ -246,14 +247,18 @@ struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) kfree_const(shrinker->name); shrinker->name = NULL; - if (entry) { - ida_free(&shrinker_debugfs_ida, shrinker->debugfs_id); - shrinker->debugfs_entry = NULL; - } + *debugfs_id = entry ? shrinker->debugfs_id : -1; + shrinker->debugfs_entry = NULL; return entry; } +void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id) +{ + debugfs_remove_recursive(debugfs_entry); + ida_free(&shrinker_debugfs_ida, debugfs_id); +} + static int __init shrinker_debugfs_init(void) { struct shrinker *shrinker; diff --git a/mm/vmscan.c b/mm/vmscan.c index d257916f39e5..6d0cd2840cf0 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -805,6 +805,7 @@ EXPORT_SYMBOL(register_shrinker); void unregister_shrinker(struct shrinker *shrinker) { struct dentry *debugfs_entry; + int debugfs_id; if (!(shrinker->flags & SHRINKER_REGISTERED)) return; @@ -814,13 +815,13 @@ void unregister_shrinker(struct shrinker *shrinker) shrinker->flags &= ~SHRINKER_REGISTERED; if (shrinker->flags & SHRINKER_MEMCG_AWARE) unregister_memcg_shrinker(shrinker); - debugfs_entry = shrinker_debugfs_remove(shrinker); + debugfs_entry = shrinker_debugfs_detach(shrinker, &debugfs_id); mutex_unlock(&shrinker_mutex); atomic_inc(&shrinker_srcu_generation); synchronize_srcu(&shrinker_srcu); - debugfs_remove_recursive(debugfs_entry); + shrinker_debugfs_remove(debugfs_entry, debugfs_id); kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; -- cgit v1.2.3 From 2e9f8ab68f42b059e80db71266c1675c07c664bd Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 21:45:36 +0200 Subject: mdio_bus: unhide mdio_bus_init prototype mdio_bus_init() is either used as a local module_init() entry, or it gets called in phy_device.c. In the former case, there is no declaration, which causes a warning: drivers/net/phy/mdio_bus.c:1371:12: error: no previous prototype for 'mdio_bus_init' [-Werror=missing-prototypes] Remove the #ifdef around the declaration to avoid the warning.. Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230516194625.549249-4-arnd@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/phy.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index c5a0dc829714..6478838405a0 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1900,10 +1900,8 @@ void phy_package_leave(struct phy_device *phydev); int devm_phy_package_join(struct device *dev, struct phy_device *phydev, int addr, size_t priv_size); -#if IS_ENABLED(CONFIG_PHYLIB) int __init mdio_bus_init(void); void mdio_bus_exit(void); -#endif int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data); int phy_ethtool_get_sset_count(struct phy_device *phydev); -- cgit v1.2.3 From e123036be377ddf628226a7c6d4f9af5efd113d3 Mon Sep 17 00:00:00 2001 From: Ranjani Sridharan Date: Wed, 17 May 2023 13:57:31 -0500 Subject: ASoC: soc-pcm: test if a BE can be prepared In the BE hw_params configuration, the existing code checks if any of the existing FEs are prepared, running, paused or suspended - and skips the configuration in those cases. This allows multiple calls of hw_params which the ALSA state machine supports. This check is not handled for the prepare stage, which can lead to the same BE being prepared multiple times. This patch adds a check similar to that of the hw_params, with the main difference being that the suspended state is allowed: the ALSA state machine allows a transition from suspended to prepared with hw_params skipped. This problem was detected on Intel IPC4/SoundWire devices, where the BE dailink .prepare stage is used to configure the SoundWire stream with a bank switch. Multiple .prepare calls lead to conflicts with the .trigger operation with IPC4 configurations. This problem was not detected earlier on Intel devices, HDaudio BE dailinks detect that the link is already prepared and skip the configuration, and for IPC3 devices there is no BE trigger. Link: https://github.com/thesofproject/sof/issues/7596 Signed-off-by: Ranjani Sridharan dpcm[stream].state != SND_SOC_DPCM_STATE_HW_PARAMS) && (be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP) && (be->dpcm[stream].state != SND_SOC_DPCM_STATE_SUSPEND) && @@ -3042,3 +3045,20 @@ int snd_soc_dpcm_can_be_params(struct snd_soc_pcm_runtime *fe, return snd_soc_dpcm_check_state(fe, be, stream, state, ARRAY_SIZE(state)); } EXPORT_SYMBOL_GPL(snd_soc_dpcm_can_be_params); + +/* + * We can only prepare a BE DAI if any of it's FE are not prepared, + * running or paused for the specified stream direction. + */ +int snd_soc_dpcm_can_be_prepared(struct snd_soc_pcm_runtime *fe, + struct snd_soc_pcm_runtime *be, int stream) +{ + const enum snd_soc_dpcm_state state[] = { + SND_SOC_DPCM_STATE_START, + SND_SOC_DPCM_STATE_PAUSED, + SND_SOC_DPCM_STATE_PREPARE, + }; + + return snd_soc_dpcm_check_state(fe, be, stream, state, ARRAY_SIZE(state)); +} +EXPORT_SYMBOL_GPL(snd_soc_dpcm_can_be_prepared); -- cgit v1.2.3 From 14c4be92ebb3e36e392aa9dd8f314038a9f96f3c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 16 May 2023 18:50:38 -0700 Subject: tls: rx: strp: force mixed decrypted records into copy mode If a record is partially decrypted we'll have to CoW it, anyway, so go into copy mode and allocate a writable skb right away. This will make subsequent fix simpler because we won't have to teach tls_strp_msg_make_copy() how to copy skbs while preserving decrypt status. Tested-by: Shai Amiram Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/skbuff.h | 10 ++++++++++ net/tls/tls_strp.c | 16 +++++++++++----- 2 files changed, 21 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 738776ab8838..0b40417457cd 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1587,6 +1587,16 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) to->l4_hash = from->l4_hash; }; +static inline int skb_cmp_decrypted(const struct sk_buff *skb1, + const struct sk_buff *skb2) +{ +#ifdef CONFIG_TLS_DEVICE + return skb2->decrypted - skb1->decrypted; +#else + return 0; +#endif +} + static inline void skb_copy_decrypted(struct sk_buff *to, const struct sk_buff *from) { diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 24016c865e00..2b6fa9855999 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -317,15 +317,19 @@ static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort) return 0; } -static bool tls_strp_check_no_dup(struct tls_strparser *strp) +static bool tls_strp_check_queue_ok(struct tls_strparser *strp) { unsigned int len = strp->stm.offset + strp->stm.full_len; - struct sk_buff *skb; + struct sk_buff *first, *skb; u32 seq; - skb = skb_shinfo(strp->anchor)->frag_list; - seq = TCP_SKB_CB(skb)->seq; + first = skb_shinfo(strp->anchor)->frag_list; + skb = first; + seq = TCP_SKB_CB(first)->seq; + /* Make sure there's no duplicate data in the queue, + * and the decrypted status matches. + */ while (skb->len < len) { seq += skb->len; len -= skb->len; @@ -333,6 +337,8 @@ static bool tls_strp_check_no_dup(struct tls_strparser *strp) if (TCP_SKB_CB(skb)->seq != seq) return false; + if (skb_cmp_decrypted(first, skb)) + return false; } return true; @@ -413,7 +419,7 @@ static int tls_strp_read_sock(struct tls_strparser *strp) return tls_strp_read_copy(strp, true); } - if (!tls_strp_check_no_dup(strp)) + if (!tls_strp_check_queue_ok(strp)) return tls_strp_read_copy(strp, false); strp->msg_ready = 1; -- cgit v1.2.3 From eca9bfafee3a0487e59c59201ae14c7594ba940a Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 16 May 2023 18:50:41 -0700 Subject: tls: rx: strp: preserve decryption status of skbs when needed When receive buffer is small we try to copy out the data from TCP into a skb maintained by TLS to prevent connection from stalling. Unfortunately if a single record is made up of a mix of decrypted and non-decrypted skbs combining them into a single skb leads to loss of decryption status, resulting in decryption errors or data corruption. Similarly when trying to use TCP receive queue directly we need to make sure that all the skbs within the record have the same status. If we don't the mixed status will be detected correctly but we'll CoW the anchor, again collapsing it into a single paged skb without decrypted status preserved. So the "fixup" code will not know which parts of skb to re-encrypt. Fixes: 84c61fe1a75b ("tls: rx: do not use the standard strparser") Tested-by: Shai Amiram Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/net/tls.h | 1 + net/tls/tls.h | 5 +++ net/tls/tls_device.c | 22 ++++------ net/tls/tls_strp.c | 117 +++++++++++++++++++++++++++++++++++++++++++-------- 4 files changed, 114 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 6056ce5a2aa5..596595c4b1af 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -126,6 +126,7 @@ struct tls_strparser { u32 mark : 8; u32 stopped : 1; u32 copy_mode : 1; + u32 mixed_decrypted : 1; u32 msg_ready : 1; struct strp_msg stm; diff --git a/net/tls/tls.h b/net/tls/tls.h index 804c3880d028..0672acab2773 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -167,6 +167,11 @@ static inline bool tls_strp_msg_ready(struct tls_sw_context_rx *ctx) return ctx->strp.msg_ready; } +static inline bool tls_strp_msg_mixed_decrypted(struct tls_sw_context_rx *ctx) +{ + return ctx->strp.mixed_decrypted; +} + #ifdef CONFIG_TLS_DEVICE int tls_device_init(void); void tls_device_cleanup(void); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 3b87c7b04ac8..bf69c9d6d06c 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -1007,20 +1007,14 @@ int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx) struct tls_sw_context_rx *sw_ctx = tls_sw_ctx_rx(tls_ctx); struct sk_buff *skb = tls_strp_msg(sw_ctx); struct strp_msg *rxm = strp_msg(skb); - int is_decrypted = skb->decrypted; - int is_encrypted = !is_decrypted; - struct sk_buff *skb_iter; - int left; - - left = rxm->full_len + rxm->offset - skb_pagelen(skb); - /* Check if all the data is decrypted already */ - skb_iter = skb_shinfo(skb)->frag_list; - while (skb_iter && left > 0) { - is_decrypted &= skb_iter->decrypted; - is_encrypted &= !skb_iter->decrypted; - - left -= skb_iter->len; - skb_iter = skb_iter->next; + int is_decrypted, is_encrypted; + + if (!tls_strp_msg_mixed_decrypted(sw_ctx)) { + is_decrypted = skb->decrypted; + is_encrypted = !is_decrypted; + } else { + is_decrypted = 0; + is_encrypted = 0; } trace_tls_device_decrypted(sk, tcp_sk(sk)->copied_seq - rxm->full_len, diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 61fbf84baf9e..da95abbb7ea3 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -29,7 +29,8 @@ static void tls_strp_anchor_free(struct tls_strparser *strp) struct skb_shared_info *shinfo = skb_shinfo(strp->anchor); DEBUG_NET_WARN_ON_ONCE(atomic_read(&shinfo->dataref) != 1); - shinfo->frag_list = NULL; + if (!strp->copy_mode) + shinfo->frag_list = NULL; consume_skb(strp->anchor); strp->anchor = NULL; } @@ -195,22 +196,22 @@ static void tls_strp_flush_anchor_copy(struct tls_strparser *strp) for (i = 0; i < shinfo->nr_frags; i++) __skb_frag_unref(&shinfo->frags[i], false); shinfo->nr_frags = 0; + if (strp->copy_mode) { + kfree_skb_list(shinfo->frag_list); + shinfo->frag_list = NULL; + } strp->copy_mode = 0; + strp->mixed_decrypted = 0; } -static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, - unsigned int offset, size_t in_len) +static int tls_strp_copyin_frag(struct tls_strparser *strp, struct sk_buff *skb, + struct sk_buff *in_skb, unsigned int offset, + size_t in_len) { - struct tls_strparser *strp = (struct tls_strparser *)desc->arg.data; - struct sk_buff *skb; - skb_frag_t *frag; size_t len, chunk; + skb_frag_t *frag; int sz; - if (strp->msg_ready) - return 0; - - skb = strp->anchor; frag = &skb_shinfo(skb)->frags[skb->len / PAGE_SIZE]; len = in_len; @@ -228,10 +229,8 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, skb_frag_size_add(frag, chunk); sz = tls_rx_msg_size(strp, skb); - if (sz < 0) { - desc->error = sz; - return 0; - } + if (sz < 0) + return sz; /* We may have over-read, sz == 0 is guaranteed under-read */ if (unlikely(sz && sz < skb->len)) { @@ -271,15 +270,99 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, offset += chunk; } - if (strp->stm.full_len == skb->len) { +read_done: + return in_len - len; +} + +static int tls_strp_copyin_skb(struct tls_strparser *strp, struct sk_buff *skb, + struct sk_buff *in_skb, unsigned int offset, + size_t in_len) +{ + struct sk_buff *nskb, *first, *last; + struct skb_shared_info *shinfo; + size_t chunk; + int sz; + + if (strp->stm.full_len) + chunk = strp->stm.full_len - skb->len; + else + chunk = TLS_MAX_PAYLOAD_SIZE + PAGE_SIZE; + chunk = min(chunk, in_len); + + nskb = tls_strp_skb_copy(strp, in_skb, offset, chunk); + if (!nskb) + return -ENOMEM; + + shinfo = skb_shinfo(skb); + if (!shinfo->frag_list) { + shinfo->frag_list = nskb; + nskb->prev = nskb; + } else { + first = shinfo->frag_list; + last = first->prev; + last->next = nskb; + first->prev = nskb; + } + + skb->len += chunk; + skb->data_len += chunk; + + if (!strp->stm.full_len) { + sz = tls_rx_msg_size(strp, skb); + if (sz < 0) + return sz; + + /* We may have over-read, sz == 0 is guaranteed under-read */ + if (unlikely(sz && sz < skb->len)) { + int over = skb->len - sz; + + WARN_ON_ONCE(over > chunk); + skb->len -= over; + skb->data_len -= over; + __pskb_trim(nskb, nskb->len - over); + + chunk -= over; + } + + strp->stm.full_len = sz; + } + + return chunk; +} + +static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, + unsigned int offset, size_t in_len) +{ + struct tls_strparser *strp = (struct tls_strparser *)desc->arg.data; + struct sk_buff *skb; + int ret; + + if (strp->msg_ready) + return 0; + + skb = strp->anchor; + if (!skb->len) + skb_copy_decrypted(skb, in_skb); + else + strp->mixed_decrypted |= !!skb_cmp_decrypted(skb, in_skb); + + if (IS_ENABLED(CONFIG_TLS_DEVICE) && strp->mixed_decrypted) + ret = tls_strp_copyin_skb(strp, skb, in_skb, offset, in_len); + else + ret = tls_strp_copyin_frag(strp, skb, in_skb, offset, in_len); + if (ret < 0) { + desc->error = ret; + ret = 0; + } + + if (strp->stm.full_len && strp->stm.full_len == skb->len) { desc->count = 0; strp->msg_ready = 1; tls_rx_msg_ready(strp); } -read_done: - return in_len - len; + return ret; } static int tls_strp_read_copyin(struct tls_strparser *strp) -- cgit v1.2.3 From ddaf098ea779b3c1302c7843f6ff01e89b1fd380 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 16 May 2023 21:20:14 +0200 Subject: driver core: class: properly reference count class_dev_iter() When class_dev_iter is initialized, the reference count for the subsys private structure is incremented, but never decremented, causing a memory leak over time. To resolve this, save off a pointer to the internal structure into the class_dev_iter structure and then when the iterator is finished, drop the reference count. Reported-and-tested-by: syzbot+e7afd76ad060fa0d2605@syzkaller.appspotmail.com Fixes: 7b884b7f24b4 ("driver core: class.c: convert to only use class_to_subsys") Reported-by: Mirsad Goran Todorovac Cc: Alan Stern Acked-by: Rafael J. Wysocki Tested-by: Mirsad Goran Todorovac Link: https://lore.kernel.org/r/2023051610-stove-condense-9a77@gregkh Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 2 ++ include/linux/device/class.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/drivers/base/class.c b/drivers/base/class.c index ac1808d1a2e8..05d9df90f621 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -320,6 +320,7 @@ void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class, start_knode = &start->p->knode_class; klist_iter_init_node(&sp->klist_devices, &iter->ki, start_knode); iter->type = type; + iter->sp = sp; } EXPORT_SYMBOL_GPL(class_dev_iter_init); @@ -361,6 +362,7 @@ EXPORT_SYMBOL_GPL(class_dev_iter_next); void class_dev_iter_exit(struct class_dev_iter *iter) { klist_iter_exit(&iter->ki); + subsys_put(iter->sp); } EXPORT_SYMBOL_GPL(class_dev_iter_exit); diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 9deeaeb457bb..abf3d3bfb6fe 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -74,6 +74,7 @@ struct class { struct class_dev_iter { struct klist_iter ki; const struct device_type *type; + struct subsys_private *sp; }; int __must_check class_register(const struct class *class); -- cgit v1.2.3 From a2ac591cb4d83e1f2d4b4adb3c14b2c79764650a Mon Sep 17 00:00:00 2001 From: Ruihan Li Date: Wed, 3 May 2023 21:39:36 +0800 Subject: Bluetooth: Fix UAF in hci_conn_hash_flush again Commit 06149746e720 ("Bluetooth: hci_conn: Add support for linking multiple hcon") reintroduced a previously fixed bug [1] ("KASAN: slab-use-after-free Read in hci_conn_hash_flush"). This bug was originally fixed by commit 5dc7d23e167e ("Bluetooth: hci_conn: Fix possible UAF"). The hci_conn_unlink function was added to avoid invalidating the link traversal caused by successive hci_conn_del operations releasing extra connections. However, currently hci_conn_unlink itself also releases extra connections, resulted in the reintroduced bug. This patch follows a more robust solution for cleaning up all connections, by repeatedly removing the first connection until there are none left. This approach does not rely on the inner workings of hci_conn_del and ensures proper cleanup of all connections. Meanwhile, we need to make sure that hci_conn_del never fails. Indeed it doesn't, as it now always returns zero. To make this a bit clearer, this patch also changes its return type to void. Reported-by: syzbot+8bb72f86fc823817bc5d@syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-bluetooth/000000000000aa920505f60d25ad@google.com/ Fixes: 06149746e720 ("Bluetooth: hci_conn: Add support for linking multiple hcon") Signed-off-by: Ruihan Li Co-developed-by: Luiz Augusto von Dentz Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 2 +- net/bluetooth/hci_conn.c | 33 ++++++++++++++++++++++----------- 2 files changed, 23 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index a6c8aee2f256..8baf34639939 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1327,7 +1327,7 @@ int hci_le_create_cis(struct hci_conn *conn); struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 role); -int hci_conn_del(struct hci_conn *conn); +void hci_conn_del(struct hci_conn *conn); void hci_conn_hash_flush(struct hci_dev *hdev); void hci_conn_check_pending(struct hci_dev *hdev); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 44d0643fc681..ce588359b290 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1088,6 +1088,14 @@ static void hci_conn_unlink(struct hci_conn *conn) hci_conn_unlink(child); + /* If hdev is down it means + * hci_dev_close_sync/hci_conn_hash_flush is in progress + * and links don't need to be cleanup as all connections + * would be cleanup. + */ + if (!test_bit(HCI_UP, &hdev->flags)) + continue; + /* Due to race, SCO connection might be not established * yet at this point. Delete it now, otherwise it is * possible for it to be stuck and can't be deleted. @@ -1112,7 +1120,7 @@ static void hci_conn_unlink(struct hci_conn *conn) conn->link = NULL; } -int hci_conn_del(struct hci_conn *conn) +void hci_conn_del(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; @@ -1163,8 +1171,6 @@ int hci_conn_del(struct hci_conn *conn) * rest of hci_conn_del. */ hci_conn_cleanup(conn); - - return 0; } struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, uint8_t src_type) @@ -2465,22 +2471,27 @@ timer: /* Drop all connection on the device */ void hci_conn_hash_flush(struct hci_dev *hdev) { - struct hci_conn_hash *h = &hdev->conn_hash; - struct hci_conn *c, *n; + struct list_head *head = &hdev->conn_hash.list; + struct hci_conn *conn; BT_DBG("hdev %s", hdev->name); - list_for_each_entry_safe(c, n, &h->list, list) { - c->state = BT_CLOSED; - - hci_disconn_cfm(c, HCI_ERROR_LOCAL_HOST_TERM); + /* We should not traverse the list here, because hci_conn_del + * can remove extra links, which may cause the list traversal + * to hit items that have already been released. + */ + while ((conn = list_first_entry_or_null(head, + struct hci_conn, + list)) != NULL) { + conn->state = BT_CLOSED; + hci_disconn_cfm(conn, HCI_ERROR_LOCAL_HOST_TERM); /* Unlink before deleting otherwise it is possible that * hci_conn_del removes the link which may cause the list to * contain items already freed. */ - hci_conn_unlink(c); - hci_conn_del(c); + hci_conn_unlink(conn); + hci_conn_del(conn); } } -- cgit v1.2.3 From ae9b15fbe63447bc1d3bba3769f409d17ca6fdf6 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Wed, 17 May 2023 14:30:10 +0000 Subject: net: fix stack overflow when LRO is disabled for virtual interfaces When the virtual interface's feature is updated, it synchronizes the updated feature for its own lower interface. This propagation logic should be worked as the iteration, not recursively. But it works recursively due to the netdev notification unexpectedly. This problem occurs when it disables LRO only for the team and bonding interface type. team0 | +------+------+-----+-----+ | | | | | team1 team2 team3 ... team200 If team0's LRO feature is updated, it generates the NETDEV_FEAT_CHANGE event to its own lower interfaces(team1 ~ team200). It is worked by netdev_sync_lower_features(). So, the NETDEV_FEAT_CHANGE notification logic of each lower interface work iteratively. But generated NETDEV_FEAT_CHANGE event is also sent to the upper interface too. upper interface(team0) generates the NETDEV_FEAT_CHANGE event for its own lower interfaces again. lower and upper interfaces receive this event and generate this event again and again. So, the stack overflow occurs. But it is not the infinite loop issue. Because the netdev_sync_lower_features() updates features before generating the NETDEV_FEAT_CHANGE event. Already synchronized lower interfaces skip notification logic. So, it is just the problem that iteration logic is changed to the recursive unexpectedly due to the notification mechanism. Reproducer: ip link add team0 type team ethtool -K team0 lro on for i in {1..200} do ip link add team$i master team0 type team ethtool -K team$i lro on done ethtool -K team0 lro off In order to fix it, the notifier_ctx member of bonding/team is introduced. Reported-by: syzbot+60748c96cf5c6df8e581@syzkaller.appspotmail.com Fixes: fd867d51f889 ("net/core: generic support for disabling netdev features down stack") Signed-off-by: Taehee Yoo Reviewed-by: Eric Dumazet Reviewed-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230517143010.3596250-1-ap420073@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/bonding/bond_main.c | 8 +++++++- drivers/net/team/team.c | 7 ++++++- include/linux/if_team.h | 1 + include/net/bonding.h | 1 + 4 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 3fed888629f7..edbaa1444f8e 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3947,7 +3947,11 @@ static int bond_slave_netdev_event(unsigned long event, unblock_netpoll_tx(); break; case NETDEV_FEAT_CHANGE: - bond_compute_features(bond); + if (!bond->notifier_ctx) { + bond->notifier_ctx = true; + bond_compute_features(bond); + bond->notifier_ctx = false; + } break; case NETDEV_RESEND_IGMP: /* Propagate to master device */ @@ -6342,6 +6346,8 @@ static int bond_init(struct net_device *bond_dev) if (!bond->wq) return -ENOMEM; + bond->notifier_ctx = false; + spin_lock_init(&bond->stats_lock); netdev_lockdep_set_classes(bond_dev); diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index d10606f257c4..555b0b1e9a78 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1629,6 +1629,7 @@ static int team_init(struct net_device *dev) team->dev = dev; team_set_no_mode(team); + team->notifier_ctx = false; team->pcpu_stats = netdev_alloc_pcpu_stats(struct team_pcpu_stats); if (!team->pcpu_stats) @@ -3022,7 +3023,11 @@ static int team_device_event(struct notifier_block *unused, team_del_slave(port->team->dev, dev); break; case NETDEV_FEAT_CHANGE: - team_compute_features(port->team); + if (!port->team->notifier_ctx) { + port->team->notifier_ctx = true; + team_compute_features(port->team); + port->team->notifier_ctx = false; + } break; case NETDEV_PRECHANGEMTU: /* Forbid to change mtu of underlaying device */ diff --git a/include/linux/if_team.h b/include/linux/if_team.h index fc985e5c739d..8de6b6e67829 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -208,6 +208,7 @@ struct team { bool queue_override_enabled; struct list_head *qom_lists; /* array of queue override mapping lists */ bool port_mtu_change_allowed; + bool notifier_ctx; struct { unsigned int count; unsigned int interval; /* in ms */ diff --git a/include/net/bonding.h b/include/net/bonding.h index 0efef2a952b7..59955ac33157 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -221,6 +221,7 @@ struct bonding { struct bond_up_slave __rcu *usable_slaves; struct bond_up_slave __rcu *all_slaves; bool force_primary; + bool notifier_ctx; s32 slave_cnt; /* never change this value outside the attach/detach wrappers */ int (*recv_probe)(const struct sk_buff *, struct bonding *, struct slave *); -- cgit v1.2.3 From e3afec91aad23c52dfe426c7d7128e4839c3eed8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 May 2023 11:00:10 +0200 Subject: block: remove NFL4_UFLG_MASK The NFL4_UFLG_MASK define slipped in in commit 9208d4149758 ("block: add a ->get_unique_id method") and should never have been added, as NFSD as the only user of it already has it's copy. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230520090010.527046-1-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b441e633f4dd..c0ffe203a602 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1376,8 +1376,6 @@ enum blk_unique_id { BLK_UID_NAA = 3, }; -#define NFL4_UFLG_MASK 0x0000003F - struct block_device_operations { void (*submit_bio)(struct bio *bio); int (*poll_bio)(struct bio *bio, struct io_comp_batch *iob, -- cgit v1.2.3 From 95109657471311601b98e71f03d0244f48dc61bb Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Fri, 19 May 2023 22:17:07 +0200 Subject: ASoC: Intel: Skylake: Fix declaration of enum skl_ch_cfg Constant 'C4_CHANNEL' does not exist on the firmware side. Value 0xC is reserved for 'C7_1' instead. Fixes: 04afbbbb1cba ("ASoC: Intel: Skylake: Update the topology interface structure") Signed-off-by: Cezary Rojewski Signed-off-by: Amadeusz Sławiński Link: https://lore.kernel.org/r/20230519201711.4073845-4-amadeuszx.slawinski@linux.intel.com Signed-off-by: Mark Brown --- include/uapi/sound/skl-tplg-interface.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/sound/skl-tplg-interface.h b/include/uapi/sound/skl-tplg-interface.h index f29899b179a6..4bf9c4f9add8 100644 --- a/include/uapi/sound/skl-tplg-interface.h +++ b/include/uapi/sound/skl-tplg-interface.h @@ -66,7 +66,8 @@ enum skl_ch_cfg { SKL_CH_CFG_DUAL_MONO = 9, SKL_CH_CFG_I2S_DUAL_STEREO_0 = 10, SKL_CH_CFG_I2S_DUAL_STEREO_1 = 11, - SKL_CH_CFG_4_CHANNEL = 12, + SKL_CH_CFG_7_1 = 12, + SKL_CH_CFG_4_CHANNEL = SKL_CH_CFG_7_1, SKL_CH_CFG_INVALID }; -- cgit v1.2.3 From 836855100b87b4dd7a82546131779dc255c18b67 Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Fri, 19 May 2023 22:17:09 +0200 Subject: ASoC: Intel: avs: Account for UID of ACPI device Configurations with multiple codecs attached to the platform are supported but only if each from the set is different. Add new field representing the 'Unique ID' so that codecs that share Vendor and Part IDs can be differentiated and thus enabling support for such configurations. Signed-off-by: Cezary Rojewski Signed-off-by: Amadeusz Sławiński Link: https://lore.kernel.org/r/20230519201711.4073845-6-amadeuszx.slawinski@linux.intel.com Signed-off-by: Mark Brown --- include/sound/soc-acpi.h | 1 + sound/soc/intel/avs/board_selection.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h index b38fd25c5729..528279056b3a 100644 --- a/include/sound/soc-acpi.h +++ b/include/sound/soc-acpi.h @@ -170,6 +170,7 @@ struct snd_soc_acpi_link_adr { /* Descriptor for SST ASoC machine driver */ struct snd_soc_acpi_mach { u8 id[ACPI_ID_LEN]; + const char *uid; const struct snd_soc_acpi_codecs *comp_ids; const u32 link_mask; const struct snd_soc_acpi_link_adr *links; diff --git a/sound/soc/intel/avs/board_selection.c b/sound/soc/intel/avs/board_selection.c index b2823c2107f7..60f8fb0bff95 100644 --- a/sound/soc/intel/avs/board_selection.c +++ b/sound/soc/intel/avs/board_selection.c @@ -443,7 +443,7 @@ static int avs_register_i2s_boards(struct avs_dev *adev) } for (mach = boards->machs; mach->id[0]; mach++) { - if (!acpi_dev_present(mach->id, NULL, -1)) + if (!acpi_dev_present(mach->id, mach->uid, -1)) continue; if (mach->machine_quirk) -- cgit v1.2.3 From c21f11d182c2180d8b90eaff84f574cfa845b250 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Fri, 19 May 2023 10:07:33 +0100 Subject: drm: fix drmm_mutex_init() In mutex_init() lockdep identifies a lock by defining a special static key for each lock class. However if we wrap the macro in a function, like in drmm_mutex_init(), we end up generating: int drmm_mutex_init(struct drm_device *dev, struct mutex *lock) { static struct lock_class_key __key; __mutex_init((lock), "lock", &__key); .... } The static __key here is what lockdep uses to identify the lock class, however since this is just a normal function the key here will be created once, where all callers then use the same key. In effect the mutex->depmap.key will be the same pointer for different drmm_mutex_init() callers. This then results in impossible lockdep splats since lockdep thinks completely unrelated locks are the same lock class. To fix this turn drmm_mutex_init() into a macro such that it generates a different "static struct lock_class_key __key" for each invocation, which looks to be inline with what mutex_init() wants. v2: - Revamp the commit message with clearer explanation of the issue. - Rather export __drmm_mutex_release() than static inline. Reported-by: Thomas Hellström Reported-by: Sarah Walker Fixes: e13f13e039dc ("drm: Add DRM-managed mutex_init()") Cc: Stanislaw Gruszka Cc: Boris Brezillon Cc: Thomas Zimmermann Cc: Jocelyn Falempe Cc: Daniel Vetter Cc: dri-devel@lists.freedesktop.org Signed-off-by: Matthew Auld Reviewed-by: Boris Brezillon Reviewed-by: Stanislaw Gruszka Reviewed-by: Lucas De Marchi Acked-by: Thomas Zimmermann Signed-off-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20230519090733.489019-1-matthew.auld@intel.com --- drivers/gpu/drm/drm_managed.c | 22 ++-------------------- include/drm/drm_managed.h | 18 +++++++++++++++++- 2 files changed, 19 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_managed.c b/drivers/gpu/drm/drm_managed.c index 4cf214de50c4..c21c3f623033 100644 --- a/drivers/gpu/drm/drm_managed.c +++ b/drivers/gpu/drm/drm_managed.c @@ -264,28 +264,10 @@ void drmm_kfree(struct drm_device *dev, void *data) } EXPORT_SYMBOL(drmm_kfree); -static void drmm_mutex_release(struct drm_device *dev, void *res) +void __drmm_mutex_release(struct drm_device *dev, void *res) { struct mutex *lock = res; mutex_destroy(lock); } - -/** - * drmm_mutex_init - &drm_device-managed mutex_init() - * @dev: DRM device - * @lock: lock to be initialized - * - * Returns: - * 0 on success, or a negative errno code otherwise. - * - * This is a &drm_device-managed version of mutex_init(). The initialized - * lock is automatically destroyed on the final drm_dev_put(). - */ -int drmm_mutex_init(struct drm_device *dev, struct mutex *lock) -{ - mutex_init(lock); - - return drmm_add_action_or_reset(dev, drmm_mutex_release, lock); -} -EXPORT_SYMBOL(drmm_mutex_init); +EXPORT_SYMBOL(__drmm_mutex_release); diff --git a/include/drm/drm_managed.h b/include/drm/drm_managed.h index 359883942612..ad08f834af40 100644 --- a/include/drm/drm_managed.h +++ b/include/drm/drm_managed.h @@ -105,6 +105,22 @@ char *drmm_kstrdup(struct drm_device *dev, const char *s, gfp_t gfp); void drmm_kfree(struct drm_device *dev, void *data); -int drmm_mutex_init(struct drm_device *dev, struct mutex *lock); +void __drmm_mutex_release(struct drm_device *dev, void *res); + +/** + * drmm_mutex_init - &drm_device-managed mutex_init() + * @dev: DRM device + * @lock: lock to be initialized + * + * Returns: + * 0 on success, or a negative errno code otherwise. + * + * This is a &drm_device-managed version of mutex_init(). The initialized + * lock is automatically destroyed on the final drm_dev_put(). + */ +#define drmm_mutex_init(dev, lock) ({ \ + mutex_init(lock); \ + drmm_add_action_or_reset(dev, __drmm_mutex_release, lock); \ +}) \ #endif -- cgit v1.2.3 From 13247018d68f21e7132924b9853f7e2c423588b6 Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Mon, 8 May 2023 18:22:17 +0200 Subject: scsi: target: iscsi: Fix hang in the iSCSI login code If the initiator suddenly stops sending data during a login while keeping the TCP connection open, the login_work won't be scheduled and will never release the login semaphore; concurrent login operations will therefore get stuck and fail. The bug is due to the inability of the login timeout code to properly handle this particular case. Fix the problem by replacing the old per-NP login timer with a new per-connection timer. The timer is started when an initiator connects to the target; if it expires, it sends a SIGINT signal to the thread pointed at by the conn->login_kworker pointer. conn->login_kworker is set by calling the iscsit_set_login_timer_kworker() helper, initially it will point to the np thread; When the login operation's control is in the process of being passed from the NP-thread to login_work, the conn->login_worker pointer is set to NULL. Finally, login_kworker will be changed to point to the worker thread executing the login_work job. If conn->login_kworker is NULL when the timer expires, it means that the login operation hasn't been completed yet but login_work isn't running, in this case the timer will mark the login process as failed and will schedule login_work so the latter will be forced to free the resources it holds. Signed-off-by: Maurizio Lombardi Link: https://lore.kernel.org/r/20230508162219.1731964-2-mlombard@redhat.com Reviewed-by: Mike Christie Signed-off-by: Martin K. Petersen --- drivers/target/iscsi/iscsi_target.c | 2 - drivers/target/iscsi/iscsi_target_login.c | 63 +++------------------------- drivers/target/iscsi/iscsi_target_nego.c | 70 +++++++++++++++++-------------- drivers/target/iscsi/iscsi_target_util.c | 51 ++++++++++++++++++++++ drivers/target/iscsi/iscsi_target_util.h | 4 ++ include/target/iscsi/iscsi_target_core.h | 6 ++- 6 files changed, 103 insertions(+), 93 deletions(-) (limited to 'include') diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 834cce50f9b0..b516c2893420 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -364,8 +364,6 @@ struct iscsi_np *iscsit_add_np( init_completion(&np->np_restart_comp); INIT_LIST_HEAD(&np->np_list); - timer_setup(&np->np_login_timer, iscsi_handle_login_thread_timeout, 0); - ret = iscsi_target_setup_login_socket(np, sockaddr); if (ret != 0) { kfree(np); diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 274bdd7845ca..90b870f234f0 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -811,59 +811,6 @@ void iscsi_post_login_handler( iscsit_dec_conn_usage_count(conn); } -void iscsi_handle_login_thread_timeout(struct timer_list *t) -{ - struct iscsi_np *np = from_timer(np, t, np_login_timer); - - spin_lock_bh(&np->np_thread_lock); - pr_err("iSCSI Login timeout on Network Portal %pISpc\n", - &np->np_sockaddr); - - if (np->np_login_timer_flags & ISCSI_TF_STOP) { - spin_unlock_bh(&np->np_thread_lock); - return; - } - - if (np->np_thread) - send_sig(SIGINT, np->np_thread, 1); - - np->np_login_timer_flags &= ~ISCSI_TF_RUNNING; - spin_unlock_bh(&np->np_thread_lock); -} - -static void iscsi_start_login_thread_timer(struct iscsi_np *np) -{ - /* - * This used the TA_LOGIN_TIMEOUT constant because at this - * point we do not have access to ISCSI_TPG_ATTRIB(tpg)->login_timeout - */ - spin_lock_bh(&np->np_thread_lock); - np->np_login_timer_flags &= ~ISCSI_TF_STOP; - np->np_login_timer_flags |= ISCSI_TF_RUNNING; - mod_timer(&np->np_login_timer, jiffies + TA_LOGIN_TIMEOUT * HZ); - - pr_debug("Added timeout timer to iSCSI login request for" - " %u seconds.\n", TA_LOGIN_TIMEOUT); - spin_unlock_bh(&np->np_thread_lock); -} - -static void iscsi_stop_login_thread_timer(struct iscsi_np *np) -{ - spin_lock_bh(&np->np_thread_lock); - if (!(np->np_login_timer_flags & ISCSI_TF_RUNNING)) { - spin_unlock_bh(&np->np_thread_lock); - return; - } - np->np_login_timer_flags |= ISCSI_TF_STOP; - spin_unlock_bh(&np->np_thread_lock); - - del_timer_sync(&np->np_login_timer); - - spin_lock_bh(&np->np_thread_lock); - np->np_login_timer_flags &= ~ISCSI_TF_RUNNING; - spin_unlock_bh(&np->np_thread_lock); -} - int iscsit_setup_np( struct iscsi_np *np, struct sockaddr_storage *sockaddr) @@ -1123,10 +1070,13 @@ static struct iscsit_conn *iscsit_alloc_conn(struct iscsi_np *np) spin_lock_init(&conn->nopin_timer_lock); spin_lock_init(&conn->response_queue_lock); spin_lock_init(&conn->state_lock); + spin_lock_init(&conn->login_worker_lock); + spin_lock_init(&conn->login_timer_lock); timer_setup(&conn->nopin_response_timer, iscsit_handle_nopin_response_timeout, 0); timer_setup(&conn->nopin_timer, iscsit_handle_nopin_timeout, 0); + timer_setup(&conn->login_timer, iscsit_login_timeout, 0); if (iscsit_conn_set_transport(conn, np->np_transport) < 0) goto free_conn; @@ -1304,7 +1254,7 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) goto new_sess_out; } - iscsi_start_login_thread_timer(np); + iscsit_start_login_timer(conn, current); pr_debug("Moving to TARG_CONN_STATE_XPT_UP.\n"); conn->conn_state = TARG_CONN_STATE_XPT_UP; @@ -1417,8 +1367,6 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) if (ret < 0) goto new_sess_out; - iscsi_stop_login_thread_timer(np); - if (ret == 1) { tpg_np = conn->tpg_np; @@ -1434,7 +1382,7 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) new_sess_out: new_sess = true; old_sess_out: - iscsi_stop_login_thread_timer(np); + iscsit_stop_login_timer(conn); tpg_np = conn->tpg_np; iscsi_target_login_sess_out(conn, zero_tsih, new_sess); new_sess = false; @@ -1448,7 +1396,6 @@ old_sess_out: return 1; exit: - iscsi_stop_login_thread_timer(np); spin_lock_bh(&np->np_thread_lock); np->np_thread_state = ISCSI_NP_THREAD_EXIT; spin_unlock_bh(&np->np_thread_lock); diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c index 24040c118e49..e3a5644a70b3 100644 --- a/drivers/target/iscsi/iscsi_target_nego.c +++ b/drivers/target/iscsi/iscsi_target_nego.c @@ -535,25 +535,6 @@ static void iscsi_target_login_drop(struct iscsit_conn *conn, struct iscsi_login iscsi_target_login_sess_out(conn, zero_tsih, true); } -struct conn_timeout { - struct timer_list timer; - struct iscsit_conn *conn; -}; - -static void iscsi_target_login_timeout(struct timer_list *t) -{ - struct conn_timeout *timeout = from_timer(timeout, t, timer); - struct iscsit_conn *conn = timeout->conn; - - pr_debug("Entering iscsi_target_login_timeout >>>>>>>>>>>>>>>>>>>\n"); - - if (conn->login_kworker) { - pr_debug("Sending SIGINT to conn->login_kworker %s/%d\n", - conn->login_kworker->comm, conn->login_kworker->pid); - send_sig(SIGINT, conn->login_kworker, 1); - } -} - static void iscsi_target_do_login_rx(struct work_struct *work) { struct iscsit_conn *conn = container_of(work, @@ -562,12 +543,15 @@ static void iscsi_target_do_login_rx(struct work_struct *work) struct iscsi_np *np = login->np; struct iscsi_portal_group *tpg = conn->tpg; struct iscsi_tpg_np *tpg_np = conn->tpg_np; - struct conn_timeout timeout; int rc, zero_tsih = login->zero_tsih; bool state; pr_debug("entering iscsi_target_do_login_rx, conn: %p, %s:%d\n", conn, current->comm, current->pid); + + spin_lock(&conn->login_worker_lock); + set_bit(LOGIN_FLAGS_WORKER_RUNNING, &conn->login_flags); + spin_unlock(&conn->login_worker_lock); /* * If iscsi_target_do_login_rx() has been invoked by ->sk_data_ready() * before initial PDU processing in iscsi_target_start_negotiation() @@ -597,19 +581,16 @@ static void iscsi_target_do_login_rx(struct work_struct *work) goto err; } - conn->login_kworker = current; allow_signal(SIGINT); - - timeout.conn = conn; - timer_setup_on_stack(&timeout.timer, iscsi_target_login_timeout, 0); - mod_timer(&timeout.timer, jiffies + TA_LOGIN_TIMEOUT * HZ); - pr_debug("Starting login timer for %s/%d\n", current->comm, current->pid); + rc = iscsit_set_login_timer_kworker(conn, current); + if (rc < 0) { + /* The login timer has already expired */ + pr_debug("iscsi_target_do_login_rx, login failed\n"); + goto err; + } rc = conn->conn_transport->iscsit_get_login_rx(conn, login); - del_timer_sync(&timeout.timer); - destroy_timer_on_stack(&timeout.timer); flush_signals(current); - conn->login_kworker = NULL; if (rc < 0) goto err; @@ -646,7 +627,17 @@ static void iscsi_target_do_login_rx(struct work_struct *work) if (iscsi_target_sk_check_and_clear(conn, LOGIN_FLAGS_WRITE_ACTIVE)) goto err; + + /* + * Set the login timer thread pointer to NULL to prevent the + * login process from getting stuck if the initiator + * stops sending data. + */ + rc = iscsit_set_login_timer_kworker(conn, NULL); + if (rc < 0) + goto err; } else if (rc == 1) { + iscsit_stop_login_timer(conn); cancel_delayed_work(&conn->login_work); iscsi_target_nego_release(conn); iscsi_post_login_handler(np, conn, zero_tsih); @@ -656,6 +647,7 @@ static void iscsi_target_do_login_rx(struct work_struct *work) err: iscsi_target_restore_sock_callbacks(conn); + iscsit_stop_login_timer(conn); cancel_delayed_work(&conn->login_work); iscsi_target_login_drop(conn, login); iscsit_deaccess_np(np, tpg, tpg_np); @@ -1368,14 +1360,30 @@ int iscsi_target_start_negotiation( * and perform connection cleanup now. */ ret = iscsi_target_do_login(conn, login); - if (!ret && iscsi_target_sk_check_and_clear(conn, LOGIN_FLAGS_INITIAL_PDU)) - ret = -1; + if (!ret) { + spin_lock(&conn->login_worker_lock); + + if (iscsi_target_sk_check_and_clear(conn, LOGIN_FLAGS_INITIAL_PDU)) + ret = -1; + else if (!test_bit(LOGIN_FLAGS_WORKER_RUNNING, &conn->login_flags)) { + if (iscsit_set_login_timer_kworker(conn, NULL) < 0) { + /* + * The timeout has expired already. + * Schedule login_work to perform the cleanup. + */ + schedule_delayed_work(&conn->login_work, 0); + } + } + + spin_unlock(&conn->login_worker_lock); + } if (ret < 0) { iscsi_target_restore_sock_callbacks(conn); iscsi_remove_failed_auth_entry(conn); } if (ret != 0) { + iscsit_stop_login_timer(conn); cancel_delayed_work_sync(&conn->login_work); iscsi_target_nego_release(conn); } diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index 26dc8ed3045b..b14835fcb033 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -1040,6 +1040,57 @@ void iscsit_stop_nopin_timer(struct iscsit_conn *conn) spin_unlock_bh(&conn->nopin_timer_lock); } +void iscsit_login_timeout(struct timer_list *t) +{ + struct iscsit_conn *conn = from_timer(conn, t, login_timer); + struct iscsi_login *login = conn->login; + + pr_debug("Entering iscsi_target_login_timeout >>>>>>>>>>>>>>>>>>>\n"); + + spin_lock_bh(&conn->login_timer_lock); + login->login_failed = 1; + + if (conn->login_kworker) { + pr_debug("Sending SIGINT to conn->login_kworker %s/%d\n", + conn->login_kworker->comm, conn->login_kworker->pid); + send_sig(SIGINT, conn->login_kworker, 1); + } else { + schedule_delayed_work(&conn->login_work, 0); + } + spin_unlock_bh(&conn->login_timer_lock); +} + +void iscsit_start_login_timer(struct iscsit_conn *conn, struct task_struct *kthr) +{ + pr_debug("Login timer started\n"); + + conn->login_kworker = kthr; + mod_timer(&conn->login_timer, jiffies + TA_LOGIN_TIMEOUT * HZ); +} + +int iscsit_set_login_timer_kworker(struct iscsit_conn *conn, struct task_struct *kthr) +{ + struct iscsi_login *login = conn->login; + int ret = 0; + + spin_lock_bh(&conn->login_timer_lock); + if (login->login_failed) { + /* The timer has already expired */ + ret = -1; + } else { + conn->login_kworker = kthr; + } + spin_unlock_bh(&conn->login_timer_lock); + + return ret; +} + +void iscsit_stop_login_timer(struct iscsit_conn *conn) +{ + pr_debug("Login timer stopped\n"); + timer_delete_sync(&conn->login_timer); +} + int iscsit_send_tx_data( struct iscsit_cmd *cmd, struct iscsit_conn *conn, diff --git a/drivers/target/iscsi/iscsi_target_util.h b/drivers/target/iscsi/iscsi_target_util.h index 33ea799a0850..24b8e577575a 100644 --- a/drivers/target/iscsi/iscsi_target_util.h +++ b/drivers/target/iscsi/iscsi_target_util.h @@ -56,6 +56,10 @@ extern void iscsit_handle_nopin_timeout(struct timer_list *t); extern void __iscsit_start_nopin_timer(struct iscsit_conn *); extern void iscsit_start_nopin_timer(struct iscsit_conn *); extern void iscsit_stop_nopin_timer(struct iscsit_conn *); +extern void iscsit_login_timeout(struct timer_list *t); +extern void iscsit_start_login_timer(struct iscsit_conn *, struct task_struct *kthr); +extern void iscsit_stop_login_timer(struct iscsit_conn *); +extern int iscsit_set_login_timer_kworker(struct iscsit_conn *, struct task_struct *kthr); extern int iscsit_send_tx_data(struct iscsit_cmd *, struct iscsit_conn *, int); extern int iscsit_fe_sendpage_sg(struct iscsit_cmd *, struct iscsit_conn *); extern int iscsit_tx_login_rsp(struct iscsit_conn *, u8, u8); diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index 229118156a1f..42f4a4c0c100 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -562,12 +562,14 @@ struct iscsit_conn { #define LOGIN_FLAGS_READ_ACTIVE 2 #define LOGIN_FLAGS_WRITE_ACTIVE 3 #define LOGIN_FLAGS_CLOSED 4 +#define LOGIN_FLAGS_WORKER_RUNNING 5 unsigned long login_flags; struct delayed_work login_work; struct iscsi_login *login; struct timer_list nopin_timer; struct timer_list nopin_response_timer; struct timer_list transport_timer; + struct timer_list login_timer; struct task_struct *login_kworker; /* Spinlock used for add/deleting cmd's from conn_cmd_list */ spinlock_t cmd_lock; @@ -576,6 +578,8 @@ struct iscsit_conn { spinlock_t nopin_timer_lock; spinlock_t response_queue_lock; spinlock_t state_lock; + spinlock_t login_timer_lock; + spinlock_t login_worker_lock; /* libcrypto RX and TX contexts for crc32c */ struct ahash_request *conn_rx_hash; struct ahash_request *conn_tx_hash; @@ -792,7 +796,6 @@ struct iscsi_np { enum np_thread_state_table np_thread_state; bool enabled; atomic_t np_reset_count; - enum iscsi_timer_flags_table np_login_timer_flags; u32 np_exports; enum np_flags_table np_flags; spinlock_t np_thread_lock; @@ -800,7 +803,6 @@ struct iscsi_np { struct socket *np_socket; struct sockaddr_storage np_sockaddr; struct task_struct *np_thread; - struct timer_list np_login_timer; void *np_context; struct iscsit_transport *np_transport; struct list_head np_list; -- cgit v1.2.3 From 98a8c2bf938a5973716f280da618077a3d255976 Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Mon, 8 May 2023 18:22:18 +0200 Subject: scsi: target: iscsi: Remove unused transport_timer Signed-off-by: Maurizio Lombardi Link: https://lore.kernel.org/r/20230508162219.1731964-3-mlombard@redhat.com Reviewed-by: Mike Christie Signed-off-by: Martin K. Petersen --- include/target/iscsi/iscsi_target_core.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index 42f4a4c0c100..4c15420e8965 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -568,7 +568,6 @@ struct iscsit_conn { struct iscsi_login *login; struct timer_list nopin_timer; struct timer_list nopin_response_timer; - struct timer_list transport_timer; struct timer_list login_timer; struct task_struct *login_kworker; /* Spinlock used for add/deleting cmd's from conn_cmd_list */ -- cgit v1.2.3 From c7dd225bc224726c22db08e680bf787f60ebdee3 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Sun, 2 Apr 2023 17:14:10 +0300 Subject: net/mlx5: DR, Check force-loopback RC QP capability independently from RoCE SW Steering uses RC QP for writing STEs to ICM. This writingis done in LB (loopback), and FL (force-loopback) QP is preferred for performance. FL is available when RoCE is enabled or disabled based on RoCE caps. This patch adds reading of FL capability from HCA caps in addition to the existing reading from RoCE caps, thus fixing the case where we didn't have loopback enabled when RoCE was disabled. Fixes: 7304d603a57a ("net/mlx5: DR, Add support for force-loopback QP") Signed-off-by: Itamar Gozlan Signed-off-by: Yevgeny Kliteynik Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c | 4 +++- include/linux/mlx5/mlx5_ifc.h | 4 +++- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c index 3835ba3f4dda..1aa525e509f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -117,6 +117,8 @@ int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev, caps->gvmi = MLX5_CAP_GEN(mdev, vhca_id); caps->flex_protocols = MLX5_CAP_GEN(mdev, flex_parser_protocols); caps->sw_format_ver = MLX5_CAP_GEN(mdev, steering_format_version); + caps->roce_caps.fl_rc_qp_when_roce_disabled = + MLX5_CAP_GEN(mdev, fl_rc_qp_when_roce_disabled); if (MLX5_CAP_GEN(mdev, roce)) { err = dr_cmd_query_nic_vport_roce_en(mdev, 0, &roce_en); @@ -124,7 +126,7 @@ int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev, return err; caps->roce_caps.roce_en = roce_en; - caps->roce_caps.fl_rc_qp_when_roce_disabled = + caps->roce_caps.fl_rc_qp_when_roce_disabled |= MLX5_CAP_ROCE(mdev, fl_rc_qp_when_roce_disabled); caps->roce_caps.fl_rc_qp_when_roce_enabled = MLX5_CAP_ROCE(mdev, fl_rc_qp_when_roce_enabled); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index dc5e2cb302a5..b89778d0d326 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1705,7 +1705,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 rc[0x1]; u8 uar_4k[0x1]; - u8 reserved_at_241[0x9]; + u8 reserved_at_241[0x7]; + u8 fl_rc_qp_when_roce_disabled[0x1]; + u8 regexp_params[0x1]; u8 uar_sz[0x6]; u8 port_selection_cap[0x1]; u8 reserved_at_248[0x1]; -- cgit v1.2.3 From 3632679d9e4f879f49949bb5b050e0de553e4739 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Mon, 22 May 2023 14:08:20 +0200 Subject: ipv{4,6}/raw: fix output xfrm lookup wrt protocol With a raw socket bound to IPPROTO_RAW (ie with hdrincl enabled), the protocol field of the flow structure, build by raw_sendmsg() / rawv6_sendmsg()), is set to IPPROTO_RAW. This breaks the ipsec policy lookup when some policies are defined with a protocol in the selector. For ipv6, the sin6_port field from 'struct sockaddr_in6' could be used to specify the protocol. Just accept all values for IPPROTO_RAW socket. For ipv4, the sin_port field of 'struct sockaddr_in' could not be used without breaking backward compatibility (the value of this field was never checked). Let's add a new kind of control message, so that the userland could specify which protocol is used. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") CC: stable@vger.kernel.org Signed-off-by: Nicolas Dichtel Link: https://lore.kernel.org/r/20230522120820.1319391-1-nicolas.dichtel@6wind.com Signed-off-by: Paolo Abeni --- include/net/ip.h | 2 ++ include/uapi/linux/in.h | 1 + net/ipv4/ip_sockglue.c | 12 +++++++++++- net/ipv4/raw.c | 5 ++++- net/ipv6/raw.c | 3 ++- 5 files changed, 20 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index c3fffaa92d6e..acec504c469a 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -76,6 +76,7 @@ struct ipcm_cookie { __be32 addr; int oif; struct ip_options_rcu *opt; + __u8 protocol; __u8 ttl; __s16 tos; char priority; @@ -96,6 +97,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, ipcm->sockc.tsflags = inet->sk.sk_tsflags; ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; + ipcm->protocol = inet->inet_num; } #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb)) diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 4b7f2df66b99..e682ab628dfa 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -163,6 +163,7 @@ struct in_addr { #define IP_MULTICAST_ALL 49 #define IP_UNICAST_IF 50 #define IP_LOCAL_PORT_RANGE 51 +#define IP_PROTOCOL 52 #define MCAST_EXCLUDE 0 #define MCAST_INCLUDE 1 diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index b511ff0adc0a..8e97d8d4cc9d 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -317,7 +317,14 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, ipc->tos = val; ipc->priority = rt_tos2priority(ipc->tos); break; - + case IP_PROTOCOL: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) + return -EINVAL; + val = *(int *)CMSG_DATA(cmsg); + if (val < 1 || val > 255) + return -EINVAL; + ipc->protocol = val; + break; default: return -EINVAL; } @@ -1761,6 +1768,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_LOCAL_PORT_RANGE: val = inet->local_port_range.hi << 16 | inet->local_port_range.lo; break; + case IP_PROTOCOL: + val = inet_sk(sk)->inet_num; + break; default: sockopt_release_sock(sk); return -ENOPROTOOPT; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index ff712bf2a98d..eadf1c9ef7e4 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -532,6 +532,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } ipcm_init_sk(&ipc, inet); + /* Keep backward compat */ + if (hdrincl) + ipc.protocol = IPPROTO_RAW; if (msg->msg_controllen) { err = ip_cmsg_send(sk, msg, &ipc, false); @@ -599,7 +602,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, RT_SCOPE_UNIVERSE, - hdrincl ? IPPROTO_RAW : sk->sk_protocol, + hdrincl ? ipc.protocol : sk->sk_protocol, inet_sk_flowi_flags(sk) | (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0, sk->sk_uid); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 7d0adb612bdd..44ee7a2e72ac 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -793,7 +793,8 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (!proto) proto = inet->inet_num; - else if (proto != inet->inet_num) + else if (proto != inet->inet_num && + inet->inet_num != IPPROTO_RAW) return -EINVAL; if (proto > 255) -- cgit v1.2.3 From 29173d07f79883ac94f5570294f98af3d4287382 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 22 May 2023 19:56:06 -0700 Subject: bpf, sockmap: Convert schedule_work into delayed_work Sk_buffs are fed into sockmap verdict programs either from a strparser (when the user might want to decide how framing of skb is done by attaching another parser program) or directly through tcp_read_sock. The tcp_read_sock is the preferred method for performance when the BPF logic is a stream parser. The flow for Cilium's common use case with a stream parser is, tcp_read_sock() sk_psock_verdict_recv ret = bpf_prog_run_pin_on_cpu() sk_psock_verdict_apply(sock, skb, ret) // if system is under memory pressure or app is slow we may // need to queue skb. Do this queuing through ingress_skb and // then kick timer to wake up handler skb_queue_tail(ingress_skb, skb) schedule_work(work); The work queue is wired up to sk_psock_backlog(). This will then walk the ingress_skb skb list that holds our sk_buffs that could not be handled, but should be OK to run at some later point. However, its possible that the workqueue doing this work still hits an error when sending the skb. When this happens the skbuff is requeued on a temporary 'state' struct kept with the workqueue. This is necessary because its possible to partially send an skbuff before hitting an error and we need to know how and where to restart when the workqueue runs next. Now for the trouble, we don't rekick the workqueue. This can cause a stall where the skbuff we just cached on the state variable might never be sent. This happens when its the last packet in a flow and no further packets come along that would cause the system to kick the workqueue from that side. To fix we could do simple schedule_work(), but while under memory pressure it makes sense to back off some instead of continue to retry repeatedly. So instead to fix convert schedule_work to schedule_delayed_work and add backoff logic to reschedule from backlog queue on errors. Its not obvious though what a good backoff is so use '1'. To test we observed some flakes whil running NGINX compliance test with sockmap we attributed these failed test to this bug and subsequent issue. >From on list discussion. This commit bec217197b41("skmsg: Schedule psock work if the cached skb exists on the psock") was intended to address similar race, but had a couple cases it missed. Most obvious it only accounted for receiving traffic on the local socket so if redirecting into another socket we could still get an sk_buff stuck here. Next it missed the case where copied=0 in the recv() handler and then we wouldn't kick the scheduler. Also its sub-optimal to require userspace to kick the internal mechanisms of sockmap to wake it up and copy data to user. It results in an extra syscall and requires the app to actual handle the EAGAIN correctly. Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Tested-by: William Findlay Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20230523025618.113937-3-john.fastabend@gmail.com --- include/linux/skmsg.h | 2 +- net/core/skmsg.c | 21 ++++++++++++++------- net/core/sock_map.c | 3 ++- 3 files changed, 17 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 84f787416a54..904ff9a32ad6 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -105,7 +105,7 @@ struct sk_psock { struct proto *sk_proto; struct mutex work_mutex; struct sk_psock_work_state work_state; - struct work_struct work; + struct delayed_work work; struct rcu_work rwork; }; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 4a3dc8d27295..0a9ee2acac0b 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -482,7 +482,7 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, } out: if (psock->work_state.skb && copied > 0) - schedule_work(&psock->work); + schedule_delayed_work(&psock->work, 0); return copied; } EXPORT_SYMBOL_GPL(sk_msg_recvmsg); @@ -640,7 +640,8 @@ static void sk_psock_skb_state(struct sk_psock *psock, static void sk_psock_backlog(struct work_struct *work) { - struct sk_psock *psock = container_of(work, struct sk_psock, work); + struct delayed_work *dwork = to_delayed_work(work); + struct sk_psock *psock = container_of(dwork, struct sk_psock, work); struct sk_psock_work_state *state = &psock->work_state; struct sk_buff *skb = NULL; bool ingress; @@ -680,6 +681,12 @@ start: if (ret == -EAGAIN) { sk_psock_skb_state(psock, state, skb, len, off); + + /* Delay slightly to prioritize any + * other work that might be here. + */ + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + schedule_delayed_work(&psock->work, 1); goto end; } /* Hard errors break pipe and stop xmit. */ @@ -734,7 +741,7 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node) INIT_LIST_HEAD(&psock->link); spin_lock_init(&psock->link_lock); - INIT_WORK(&psock->work, sk_psock_backlog); + INIT_DELAYED_WORK(&psock->work, sk_psock_backlog); mutex_init(&psock->work_mutex); INIT_LIST_HEAD(&psock->ingress_msg); spin_lock_init(&psock->ingress_lock); @@ -823,7 +830,7 @@ static void sk_psock_destroy(struct work_struct *work) sk_psock_done_strp(psock); - cancel_work_sync(&psock->work); + cancel_delayed_work_sync(&psock->work); mutex_destroy(&psock->work_mutex); psock_progs_drop(&psock->progs); @@ -938,7 +945,7 @@ static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *skb) } skb_queue_tail(&psock_other->ingress_skb, skb); - schedule_work(&psock_other->work); + schedule_delayed_work(&psock_other->work, 0); spin_unlock_bh(&psock_other->ingress_lock); return 0; } @@ -1018,7 +1025,7 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, spin_lock_bh(&psock->ingress_lock); if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { skb_queue_tail(&psock->ingress_skb, skb); - schedule_work(&psock->work); + schedule_delayed_work(&psock->work, 0); err = 0; } spin_unlock_bh(&psock->ingress_lock); @@ -1049,7 +1056,7 @@ static void sk_psock_write_space(struct sock *sk) psock = sk_psock(sk); if (likely(psock)) { if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) - schedule_work(&psock->work); + schedule_delayed_work(&psock->work, 0); write_space = psock->saved_write_space; } rcu_read_unlock(); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 7c189c2e2fbf..00afb66cd095 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -1644,9 +1644,10 @@ void sock_map_close(struct sock *sk, long timeout) rcu_read_unlock(); sk_psock_stop(psock); release_sock(sk); - cancel_work_sync(&psock->work); + cancel_delayed_work_sync(&psock->work); sk_psock_put(sk, psock); } + /* Make sure we do not recurse. This is a bug. * Leak the socket instead of crashing on a stack overflow. */ -- cgit v1.2.3 From 405df89dd52cbcd69a3cd7d9a10d64de38f854b2 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 22 May 2023 19:56:08 -0700 Subject: bpf, sockmap: Improved check for empty queue We noticed some rare sk_buffs were stepping past the queue when system was under memory pressure. The general theory is to skip enqueueing sk_buffs when its not necessary which is the normal case with a system that is properly provisioned for the task, no memory pressure and enough cpu assigned. But, if we can't allocate memory due to an ENOMEM error when enqueueing the sk_buff into the sockmap receive queue we push it onto a delayed workqueue to retry later. When a new sk_buff is received we then check if that queue is empty. However, there is a problem with simply checking the queue length. When a sk_buff is being processed from the ingress queue but not yet on the sockmap msg receive queue its possible to also recv a sk_buff through normal path. It will check the ingress queue which is zero and then skip ahead of the pkt being processed. Previously we used sock lock from both contexts which made the problem harder to hit, but not impossible. To fix instead of popping the skb from the queue entirely we peek the skb from the queue and do the copy there. This ensures checks to the queue length are non-zero while skb is being processed. Then finally when the entire skb has been copied to user space queue or another socket we pop it off the queue. This way the queue length check allows bypassing the queue only after the list has been completely processed. To reproduce issue we run NGINX compliance test with sockmap running and observe some flakes in our testing that we attributed to this issue. Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Suggested-by: Jakub Sitnicki Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Tested-by: William Findlay Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20230523025618.113937-5-john.fastabend@gmail.com --- include/linux/skmsg.h | 1 - net/core/skmsg.c | 32 ++++++++------------------------ 2 files changed, 8 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 904ff9a32ad6..054d7911bfc9 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -71,7 +71,6 @@ struct sk_psock_link { }; struct sk_psock_work_state { - struct sk_buff *skb; u32 len; u32 off; }; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 76ff15f8bb06..bcd45a99a3db 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -622,16 +622,12 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, static void sk_psock_skb_state(struct sk_psock *psock, struct sk_psock_work_state *state, - struct sk_buff *skb, int len, int off) { spin_lock_bh(&psock->ingress_lock); if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { - state->skb = skb; state->len = len; state->off = off; - } else { - sock_drop(psock->sk, skb); } spin_unlock_bh(&psock->ingress_lock); } @@ -642,23 +638,17 @@ static void sk_psock_backlog(struct work_struct *work) struct sk_psock *psock = container_of(dwork, struct sk_psock, work); struct sk_psock_work_state *state = &psock->work_state; struct sk_buff *skb = NULL; + u32 len = 0, off = 0; bool ingress; - u32 len, off; int ret; mutex_lock(&psock->work_mutex); - if (unlikely(state->skb)) { - spin_lock_bh(&psock->ingress_lock); - skb = state->skb; + if (unlikely(state->len)) { len = state->len; off = state->off; - state->skb = NULL; - spin_unlock_bh(&psock->ingress_lock); } - if (skb) - goto start; - while ((skb = skb_dequeue(&psock->ingress_skb))) { + while ((skb = skb_peek(&psock->ingress_skb))) { len = skb->len; off = 0; if (skb_bpf_strparser(skb)) { @@ -667,7 +657,6 @@ static void sk_psock_backlog(struct work_struct *work) off = stm->offset; len = stm->full_len; } -start: ingress = skb_bpf_ingress(skb); skb_bpf_redirect_clear(skb); do { @@ -677,8 +666,7 @@ start: len, ingress); if (ret <= 0) { if (ret == -EAGAIN) { - sk_psock_skb_state(psock, state, skb, - len, off); + sk_psock_skb_state(psock, state, len, off); /* Delay slightly to prioritize any * other work that might be here. @@ -690,15 +678,16 @@ start: /* Hard errors break pipe and stop xmit. */ sk_psock_report_error(psock, ret ? -ret : EPIPE); sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); - sock_drop(psock->sk, skb); goto end; } off += ret; len -= ret; } while (len); - if (!ingress) + skb = skb_dequeue(&psock->ingress_skb); + if (!ingress) { kfree_skb(skb); + } } end: mutex_unlock(&psock->work_mutex); @@ -791,11 +780,6 @@ static void __sk_psock_zap_ingress(struct sk_psock *psock) skb_bpf_redirect_clear(skb); sock_drop(psock->sk, skb); } - kfree_skb(psock->work_state.skb); - /* We null the skb here to ensure that calls to sk_psock_backlog - * do not pick up the free'd skb. - */ - psock->work_state.skb = NULL; __sk_psock_purge_ingress_msg(psock); } @@ -814,7 +798,6 @@ void sk_psock_stop(struct sk_psock *psock) spin_lock_bh(&psock->ingress_lock); sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); sk_psock_cork_free(psock); - __sk_psock_zap_ingress(psock); spin_unlock_bh(&psock->ingress_lock); } @@ -829,6 +812,7 @@ static void sk_psock_destroy(struct work_struct *work) sk_psock_done_strp(psock); cancel_delayed_work_sync(&psock->work); + __sk_psock_zap_ingress(psock); mutex_destroy(&psock->work_mutex); psock_progs_drop(&psock->progs); -- cgit v1.2.3 From e5c6de5fa025882babf89cecbed80acf49b987fa Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 22 May 2023 19:56:12 -0700 Subject: bpf, sockmap: Incorrectly handling copied_seq The read_skb() logic is incrementing the tcp->copied_seq which is used for among other things calculating how many outstanding bytes can be read by the application. This results in application errors, if the application does an ioctl(FIONREAD) we return zero because this is calculated from the copied_seq value. To fix this we move tcp->copied_seq accounting into the recv handler so that we update these when the recvmsg() hook is called and data is in fact copied into user buffers. This gives an accurate FIONREAD value as expected and improves ACK handling. Before we were calling the tcp_rcv_space_adjust() which would update 'number of bytes copied to user in last RTT' which is wrong for programs returning SK_PASS. The bytes are only copied to the user when recvmsg is handled. Doing the fix for recvmsg is straightforward, but fixing redirect and SK_DROP pkts is a bit tricker. Build a tcp_psock_eat() helper and then call this from skmsg handlers. This fixes another issue where a broken socket with a BPF program doing a resubmit could hang the receiver. This happened because although read_skb() consumed the skb through sock_drop() it did not update the copied_seq. Now if a single reccv socket is redirecting to many sockets (for example for lb) the receiver sk will be hung even though we might expect it to continue. The hang comes from not updating the copied_seq numbers and memory pressure resulting from that. We have a slight layer problem of calling tcp_eat_skb even if its not a TCP socket. To fix we could refactor and create per type receiver handlers. I decided this is more work than we want in the fix and we already have some small tweaks depending on caller that use the helper skb_bpf_strparser(). So we extend that a bit and always set the strparser bit when it is in use and then we can gate the seq_copied updates on this. Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20230523025618.113937-9-john.fastabend@gmail.com --- include/net/tcp.h | 10 ++++++++++ net/core/skmsg.c | 15 +++++++-------- net/ipv4/tcp.c | 10 +--------- net/ipv4/tcp_bpf.c | 28 +++++++++++++++++++++++++++- 4 files changed, 45 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 04a31643cda3..18a038d16434 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1470,6 +1470,8 @@ static inline void tcp_adjust_rcv_ssthresh(struct sock *sk) } void tcp_cleanup_rbuf(struct sock *sk, int copied); +void __tcp_cleanup_rbuf(struct sock *sk, int copied); + /* We provision sk_rcvbuf around 200% of sk_rcvlowat. * If 87.5 % (7/8) of the space has been consumed, we want to override @@ -2326,6 +2328,14 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); #endif /* CONFIG_BPF_SYSCALL */ +#ifdef CONFIG_INET +void tcp_eat_skb(struct sock *sk, struct sk_buff *skb); +#else +static inline void tcp_eat_skb(struct sock *sk, struct sk_buff *skb) +{ +} +#endif + int tcp_bpf_sendmsg_redir(struct sock *sk, bool ingress, struct sk_msg *msg, u32 bytes, int flags); #endif /* CONFIG_NET_SOCK_MSG */ diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 08be5f409fb8..a9060e1f0e43 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -979,10 +979,8 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, err = -EIO; sk_other = psock->sk; if (sock_flag(sk_other, SOCK_DEAD) || - !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { - skb_bpf_redirect_clear(skb); + !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) goto out_free; - } skb_bpf_set_ingress(skb); @@ -1011,18 +1009,19 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, err = 0; } spin_unlock_bh(&psock->ingress_lock); - if (err < 0) { - skb_bpf_redirect_clear(skb); + if (err < 0) goto out_free; - } } break; case __SK_REDIRECT: + tcp_eat_skb(psock->sk, skb); err = sk_psock_skb_redirect(psock, skb); break; case __SK_DROP: default: out_free: + skb_bpf_redirect_clear(skb); + tcp_eat_skb(psock->sk, skb); sock_drop(psock->sk, skb); } @@ -1067,8 +1066,7 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) skb_dst_drop(skb); skb_bpf_redirect_clear(skb); ret = bpf_prog_run_pin_on_cpu(prog, skb); - if (ret == SK_PASS) - skb_bpf_set_strparser(skb); + skb_bpf_set_strparser(skb); ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); skb->sk = NULL; } @@ -1176,6 +1174,7 @@ static int sk_psock_verdict_recv(struct sock *sk, struct sk_buff *skb) psock = sk_psock(sk); if (unlikely(!psock)) { len = 0; + tcp_eat_skb(sk, skb); sock_drop(sk, skb); goto out; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e914e3446377..a60f6f4e7cd9 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1571,7 +1571,7 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) * calculation of whether or not we must ACK for the sake of * a window update. */ -static void __tcp_cleanup_rbuf(struct sock *sk, int copied) +void __tcp_cleanup_rbuf(struct sock *sk, int copied) { struct tcp_sock *tp = tcp_sk(sk); bool time_to_ack = false; @@ -1786,14 +1786,6 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) break; } } - WRITE_ONCE(tp->copied_seq, seq); - - tcp_rcv_space_adjust(sk); - - /* Clean up data we have read: This will do ACK frames. */ - if (copied > 0) - __tcp_cleanup_rbuf(sk, copied); - return copied; } EXPORT_SYMBOL(tcp_read_skb); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 01dd76be1a58..5f93918c063c 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -11,6 +11,24 @@ #include #include +void tcp_eat_skb(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_sock *tcp; + int copied; + + if (!skb || !skb->len || !sk_is_tcp(sk)) + return; + + if (skb_bpf_strparser(skb)) + return; + + tcp = tcp_sk(sk); + copied = tcp->copied_seq + skb->len; + WRITE_ONCE(tcp->copied_seq, copied); + tcp_rcv_space_adjust(sk); + __tcp_cleanup_rbuf(sk, skb->len); +} + static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg, u32 apply_bytes, int flags) { @@ -198,8 +216,10 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, int flags, int *addr_len) { + struct tcp_sock *tcp = tcp_sk(sk); + u32 seq = tcp->copied_seq; struct sk_psock *psock; - int copied; + int copied = 0; if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); @@ -244,9 +264,11 @@ msg_bytes_ready: if (is_fin) { copied = 0; + seq++; goto out; } } + seq += copied; if (!copied) { long timeo; int data; @@ -284,6 +306,10 @@ msg_bytes_ready: copied = -EAGAIN; } out: + WRITE_ONCE(tcp->copied_seq, seq); + tcp_rcv_space_adjust(sk); + if (copied > 0) + __tcp_cleanup_rbuf(sk, copied); release_sock(sk); sk_psock_put(sk, psock); return copied; -- cgit v1.2.3 From dcbd1ac2668b5fa02069ea96d581ca3f70a7543c Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Fri, 19 May 2023 16:07:40 -0700 Subject: tracing/user_events: Rename link fields for clarity Currently most list_head fields of various structs within user_events are simply named link. This causes folks to keep additional context in their head when working with the code, which can be confusing. Instead of using link, describe what the actual link is, for example: list_del_rcu(&mm->link); Changes into: list_del_rcu(&mm->mms_link); The reader now is given a hint the link is to the mms global list instead of having to remember or spot check within the code. Link: https://lkml.kernel.org/r/20230519230741.669-4-beaub@linux.microsoft.com Link: https://lore.kernel.org/linux-trace-kernel/CAHk-=wicngggxVpbnrYHjRTwGE0WYscPRM+L2HO2BF8ia1EXgQ@mail.gmail.com/ Suggested-by: Linus Torvalds Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- include/linux/user_events.h | 2 +- kernel/trace/trace_events_user.c | 40 ++++++++++++++++++++++------------------ 2 files changed, 23 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 2847f5a18a86..17d452b389de 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -17,7 +17,7 @@ #ifdef CONFIG_USER_EVENTS struct user_event_mm { - struct list_head link; + struct list_head mms_link; struct list_head enablers; struct mm_struct *mm; struct user_event_mm *next; diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index d34a59630e70..238c7a0615fa 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -96,7 +96,7 @@ struct user_event { * these to track enablement sites that are tied to an event. */ struct user_event_enabler { - struct list_head link; + struct list_head mm_enablers_link; struct user_event *event; unsigned long addr; @@ -155,7 +155,7 @@ struct user_event_file_info { #define VALIDATOR_REL (1 << 1) struct user_event_validator { - struct list_head link; + struct list_head user_event_link; int offset; int flags; }; @@ -261,7 +261,7 @@ error: static void user_event_enabler_destroy(struct user_event_enabler *enabler) { - list_del_rcu(&enabler->link); + list_del_rcu(&enabler->mm_enablers_link); /* No longer tracking the event via the enabler */ refcount_dec(&enabler->event->refcnt); @@ -440,7 +440,7 @@ static bool user_event_enabler_exists(struct user_event_mm *mm, { struct user_event_enabler *enabler; - list_for_each_entry(enabler, &mm->enablers, link) { + list_for_each_entry(enabler, &mm->enablers, mm_enablers_link) { if (enabler->addr == uaddr && ENABLE_BIT(enabler) == bit) return true; } @@ -461,7 +461,7 @@ static void user_event_enabler_update(struct user_event *user) next = mm->next; mmap_read_lock(mm->mm); - list_for_each_entry(enabler, &mm->enablers, link) { + list_for_each_entry(enabler, &mm->enablers, mm_enablers_link) { if (enabler->event == user) { attempt = 0; user_event_enabler_write(mm, enabler, true, &attempt); @@ -497,7 +497,7 @@ static bool user_event_enabler_dup(struct user_event_enabler *orig, refcount_inc(&enabler->event->refcnt); /* Enablers not exposed yet, RCU not required */ - list_add(&enabler->link, &mm->enablers); + list_add(&enabler->mm_enablers_link, &mm->enablers); return true; } @@ -527,13 +527,15 @@ static struct user_event_mm *user_event_mm_get_all(struct user_event *user) */ rcu_read_lock(); - list_for_each_entry_rcu(mm, &user_event_mms, link) - list_for_each_entry_rcu(enabler, &mm->enablers, link) + list_for_each_entry_rcu(mm, &user_event_mms, mms_link) { + list_for_each_entry_rcu(enabler, &mm->enablers, mm_enablers_link) { if (enabler->event == user) { mm->next = found; found = user_event_mm_get(mm); break; } + } + } rcu_read_unlock(); @@ -572,7 +574,7 @@ static void user_event_mm_attach(struct user_event_mm *user_mm, struct task_stru unsigned long flags; spin_lock_irqsave(&user_event_mms_lock, flags); - list_add_rcu(&user_mm->link, &user_event_mms); + list_add_rcu(&user_mm->mms_link, &user_event_mms); spin_unlock_irqrestore(&user_event_mms_lock, flags); t->user_event_mm = user_mm; @@ -601,7 +603,7 @@ static void user_event_mm_destroy(struct user_event_mm *mm) { struct user_event_enabler *enabler, *next; - list_for_each_entry_safe(enabler, next, &mm->enablers, link) + list_for_each_entry_safe(enabler, next, &mm->enablers, mm_enablers_link) user_event_enabler_destroy(enabler); mmdrop(mm->mm); @@ -638,7 +640,7 @@ void user_event_mm_remove(struct task_struct *t) /* Remove the mm from the list, so it can no longer be enabled */ spin_lock_irqsave(&user_event_mms_lock, flags); - list_del_rcu(&mm->link); + list_del_rcu(&mm->mms_link); spin_unlock_irqrestore(&user_event_mms_lock, flags); /* @@ -686,9 +688,10 @@ void user_event_mm_dup(struct task_struct *t, struct user_event_mm *old_mm) rcu_read_lock(); - list_for_each_entry_rcu(enabler, &old_mm->enablers, link) + list_for_each_entry_rcu(enabler, &old_mm->enablers, mm_enablers_link) { if (!user_event_enabler_dup(enabler, mm)) goto error; + } rcu_read_unlock(); @@ -757,7 +760,7 @@ retry: */ if (!*write_result) { refcount_inc(&enabler->event->refcnt); - list_add_rcu(&enabler->link, &user_mm->enablers); + list_add_rcu(&enabler->mm_enablers_link, &user_mm->enablers); } mutex_unlock(&event_mutex); @@ -913,8 +916,8 @@ static void user_event_destroy_validators(struct user_event *user) struct user_event_validator *validator, *next; struct list_head *head = &user->validators; - list_for_each_entry_safe(validator, next, head, link) { - list_del(&validator->link); + list_for_each_entry_safe(validator, next, head, user_event_link) { + list_del(&validator->user_event_link); kfree(validator); } } @@ -968,7 +971,7 @@ add_validator: validator->offset = offset; /* Want sequential access when validating */ - list_add_tail(&validator->link, &user->validators); + list_add_tail(&validator->user_event_link, &user->validators); add_field: field->type = type; @@ -1358,7 +1361,7 @@ static int user_event_validate(struct user_event *user, void *data, int len) void *pos, *end = data + len; u32 loc, offset, size; - list_for_each_entry(validator, head, link) { + list_for_each_entry(validator, head, user_event_link) { pos = data + validator->offset; /* Already done min_size check, no bounds check here */ @@ -2279,7 +2282,7 @@ static long user_events_ioctl_unreg(unsigned long uarg) */ mutex_lock(&event_mutex); - list_for_each_entry_safe(enabler, next, &mm->enablers, link) + list_for_each_entry_safe(enabler, next, &mm->enablers, mm_enablers_link) { if (enabler->addr == reg.disable_addr && ENABLE_BIT(enabler) == reg.disable_bit) { set_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler)); @@ -2290,6 +2293,7 @@ static long user_events_ioctl_unreg(unsigned long uarg) /* Removed at least one */ ret = 0; } + } mutex_unlock(&event_mutex); -- cgit v1.2.3 From ff9e1632d69e596d8ca256deb07433a8f3565038 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Fri, 19 May 2023 16:07:41 -0700 Subject: tracing/user_events: Document user_event_mm one-shot list usage During 6.4 development it became clear that the one-shot list used by the user_event_mm's next field was confusing to others. It is not clear how this list is protected or what the next field usage is for unless you are familiar with the code. Add comments into the user_event_mm struct indicating lock requirement and usage. Also document how and why this approach was used via comments in both user_event_enabler_update() and user_event_mm_get_all() and the rules to properly use it. Link: https://lkml.kernel.org/r/20230519230741.669-5-beaub@linux.microsoft.com Link: https://lore.kernel.org/linux-trace-kernel/CAHk-=wicngggxVpbnrYHjRTwGE0WYscPRM+L2HO2BF8ia1EXgQ@mail.gmail.com/ Suggested-by: Linus Torvalds Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- include/linux/user_events.h | 1 + kernel/trace/trace_events_user.c | 23 ++++++++++++++++++++++- 2 files changed, 23 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 17d452b389de..8afa8c3a0973 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -20,6 +20,7 @@ struct user_event_mm { struct list_head mms_link; struct list_head enablers; struct mm_struct *mm; + /* Used for one-shot lists, protected by event_mutex */ struct user_event_mm *next; refcount_t refcnt; refcount_t tasks; diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 238c7a0615fa..dbb14705d0d3 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -451,12 +451,25 @@ static bool user_event_enabler_exists(struct user_event_mm *mm, static void user_event_enabler_update(struct user_event *user) { struct user_event_enabler *enabler; - struct user_event_mm *mm = user_event_mm_get_all(user); struct user_event_mm *next; + struct user_event_mm *mm; int attempt; lockdep_assert_held(&event_mutex); + /* + * We need to build a one-shot list of all the mms that have an + * enabler for the user_event passed in. This list is only valid + * while holding the event_mutex. The only reason for this is due + * to the global mm list being RCU protected and we use methods + * which can wait (mmap_read_lock and pin_user_pages_remote). + * + * NOTE: user_event_mm_get_all() increments the ref count of each + * mm that is added to the list to prevent removal timing windows. + * We must always put each mm after they are used, which may wait. + */ + mm = user_event_mm_get_all(user); + while (mm) { next = mm->next; mmap_read_lock(mm->mm); @@ -515,6 +528,14 @@ static struct user_event_mm *user_event_mm_get_all(struct user_event *user) struct user_event_enabler *enabler; struct user_event_mm *mm; + /* + * We use the mm->next field to build a one-shot list from the global + * RCU protected list. To build this list the event_mutex must be held. + * This lets us build a list without requiring allocs that could fail + * when user based events are most wanted for diagnostics. + */ + lockdep_assert_held(&event_mutex); + /* * We do not want to block fork/exec while enablements are being * updated, so we use RCU to walk the current tasks that have used -- cgit v1.2.3 From 368d3cb406cdd074d1df2ad9ec06d1bfcb664882 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Mon, 22 May 2023 11:17:14 +0800 Subject: page_pool: fix inconsistency for page_pool_ring_[un]lock() page_pool_ring_[un]lock() use in_softirq() to decide which spin lock variant to use, and when they are called in the context with in_softirq() being false, spin_lock_bh() is called in page_pool_ring_lock() while spin_unlock() is called in page_pool_ring_unlock(), because spin_lock_bh() has disabled the softirq in page_pool_ring_lock(), which causes inconsistency for spin lock pair calling. This patch fixes it by returning in_softirq state from page_pool_producer_lock(), and use it to decide which spin lock variant to use in page_pool_producer_unlock(). As pool->ring has both producer and consumer lock, so rename it to page_pool_producer_[un]lock() to reflect the actual usage. Also move them to page_pool.c as they are only used there, and remove the 'inline' as the compiler may have better idea to do inlining or not. Fixes: 7886244736a4 ("net: page_pool: Add bulk support for ptr_ring") Signed-off-by: Yunsheng Lin Acked-by: Jesper Dangaard Brouer Acked-by: Ilias Apalodimas Link: https://lore.kernel.org/r/20230522031714.5089-1-linyunsheng@huawei.com Signed-off-by: Jakub Kicinski --- include/net/page_pool.h | 18 ------------------ net/core/page_pool.c | 28 ++++++++++++++++++++++++++-- 2 files changed, 26 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/net/page_pool.h b/include/net/page_pool.h index c8ec2f34722b..126f9e294389 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -399,22 +399,4 @@ static inline void page_pool_nid_changed(struct page_pool *pool, int new_nid) page_pool_update_nid(pool, new_nid); } -static inline void page_pool_ring_lock(struct page_pool *pool) - __acquires(&pool->ring.producer_lock) -{ - if (in_softirq()) - spin_lock(&pool->ring.producer_lock); - else - spin_lock_bh(&pool->ring.producer_lock); -} - -static inline void page_pool_ring_unlock(struct page_pool *pool) - __releases(&pool->ring.producer_lock) -{ - if (in_softirq()) - spin_unlock(&pool->ring.producer_lock); - else - spin_unlock_bh(&pool->ring.producer_lock); -} - #endif /* _NET_PAGE_POOL_H */ diff --git a/net/core/page_pool.c b/net/core/page_pool.c index e212e9d7edcb..a3e12a61d456 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -134,6 +134,29 @@ EXPORT_SYMBOL(page_pool_ethtool_stats_get); #define recycle_stat_add(pool, __stat, val) #endif +static bool page_pool_producer_lock(struct page_pool *pool) + __acquires(&pool->ring.producer_lock) +{ + bool in_softirq = in_softirq(); + + if (in_softirq) + spin_lock(&pool->ring.producer_lock); + else + spin_lock_bh(&pool->ring.producer_lock); + + return in_softirq; +} + +static void page_pool_producer_unlock(struct page_pool *pool, + bool in_softirq) + __releases(&pool->ring.producer_lock) +{ + if (in_softirq) + spin_unlock(&pool->ring.producer_lock); + else + spin_unlock_bh(&pool->ring.producer_lock); +} + static int page_pool_init(struct page_pool *pool, const struct page_pool_params *params) { @@ -617,6 +640,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, int count) { int i, bulk_len = 0; + bool in_softirq; for (i = 0; i < count; i++) { struct page *page = virt_to_head_page(data[i]); @@ -635,7 +659,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, return; /* Bulk producer into ptr_ring page_pool cache */ - page_pool_ring_lock(pool); + in_softirq = page_pool_producer_lock(pool); for (i = 0; i < bulk_len; i++) { if (__ptr_ring_produce(&pool->ring, data[i])) { /* ring full */ @@ -644,7 +668,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, } } recycle_stat_add(pool, ring, i); - page_pool_ring_unlock(pool); + page_pool_producer_unlock(pool, in_softirq); /* Hopefully all pages was return into ptr_ring */ if (likely(i == bulk_len)) -- cgit v1.2.3 From 4b512860bdbdddcf41467ebd394f27cb8dfb528c Mon Sep 17 00:00:00 2001 From: Steven Rostedt (Google) Date: Tue, 23 May 2023 23:09:13 -0400 Subject: tracing: Rename stacktrace field to common_stacktrace The histogram and synthetic events can use a pseudo event called "stacktrace" that will create a stacktrace at the time of the event and use it just like it was a normal field. We have other pseudo events such as "common_cpu" and "common_timestamp". To stay consistent with that, convert "stacktrace" to "common_stacktrace". As this was used in older kernels, to keep backward compatibility, this will act just like "common_cpu" did with "cpu". That is, "cpu" will be the same as "common_cpu" unless the event has a "cpu" field. In which case, the event's field is used. The same is true with "stacktrace". Also update the documentation to reflect this change. Link: https://lore.kernel.org/linux-trace-kernel/20230523230913.6860e28d@rorschach.local.home Cc: Masami Hiramatsu Cc: Tom Zanussi Cc: Mark Rutland Signed-off-by: Steven Rostedt (Google) --- Documentation/trace/histogram.rst | 64 +++++++++++++++++++-------------------- include/linux/trace_events.h | 1 + kernel/trace/trace.c | 2 +- kernel/trace/trace_events.c | 2 ++ kernel/trace/trace_events_hist.c | 16 ++++++---- 5 files changed, 46 insertions(+), 39 deletions(-) (limited to 'include') diff --git a/Documentation/trace/histogram.rst b/Documentation/trace/histogram.rst index 479c9eac6335..3c9b263de9c2 100644 --- a/Documentation/trace/histogram.rst +++ b/Documentation/trace/histogram.rst @@ -35,7 +35,7 @@ Documentation written by Tom Zanussi in place of an explicit value field - this is simply a count of event hits. If 'values' isn't specified, an implicit 'hitcount' value will be automatically created and used as the only value. - Keys can be any field, or the special string 'stacktrace', which + Keys can be any field, or the special string 'common_stacktrace', which will use the event's kernel stacktrace as the key. The keywords 'keys' or 'key' can be used to specify keys, and the keywords 'values', 'vals', or 'val' can be used to specify values. Compound @@ -54,7 +54,7 @@ Documentation written by Tom Zanussi 'compatible' if the fields named in the trigger share the same number and type of fields and those fields also have the same names. Note that any two events always share the compatible 'hitcount' and - 'stacktrace' fields and can therefore be combined using those + 'common_stacktrace' fields and can therefore be combined using those fields, however pointless that may be. 'hist' triggers add a 'hist' file to each event's subdirectory. @@ -547,9 +547,9 @@ Extended error information the hist trigger display symbolic call_sites, we can have the hist trigger additionally display the complete set of kernel stack traces that led to each call_site. To do that, we simply use the special - value 'stacktrace' for the key parameter:: + value 'common_stacktrace' for the key parameter:: - # echo 'hist:keys=stacktrace:values=bytes_req,bytes_alloc:sort=bytes_alloc' > \ + # echo 'hist:keys=common_stacktrace:values=bytes_req,bytes_alloc:sort=bytes_alloc' > \ /sys/kernel/tracing/events/kmem/kmalloc/trigger The above trigger will use the kernel stack trace in effect when an @@ -561,9 +561,9 @@ Extended error information every callpath to a kmalloc for a kernel compile):: # cat /sys/kernel/tracing/events/kmem/kmalloc/hist - # trigger info: hist:keys=stacktrace:vals=bytes_req,bytes_alloc:sort=bytes_alloc:size=2048 [active] + # trigger info: hist:keys=common_stacktrace:vals=bytes_req,bytes_alloc:sort=bytes_alloc:size=2048 [active] - { stacktrace: + { common_stacktrace: __kmalloc_track_caller+0x10b/0x1a0 kmemdup+0x20/0x50 hidraw_report_event+0x8a/0x120 [hid] @@ -581,7 +581,7 @@ Extended error information cpu_startup_entry+0x315/0x3e0 rest_init+0x7c/0x80 } hitcount: 3 bytes_req: 21 bytes_alloc: 24 - { stacktrace: + { common_stacktrace: __kmalloc_track_caller+0x10b/0x1a0 kmemdup+0x20/0x50 hidraw_report_event+0x8a/0x120 [hid] @@ -596,7 +596,7 @@ Extended error information do_IRQ+0x5a/0xf0 ret_from_intr+0x0/0x30 } hitcount: 3 bytes_req: 21 bytes_alloc: 24 - { stacktrace: + { common_stacktrace: kmem_cache_alloc_trace+0xeb/0x150 aa_alloc_task_context+0x27/0x40 apparmor_cred_prepare+0x1f/0x50 @@ -608,7 +608,7 @@ Extended error information . . . - { stacktrace: + { common_stacktrace: __kmalloc+0x11b/0x1b0 i915_gem_execbuffer2+0x6c/0x2c0 [i915] drm_ioctl+0x349/0x670 [drm] @@ -616,7 +616,7 @@ Extended error information SyS_ioctl+0x81/0xa0 system_call_fastpath+0x12/0x6a } hitcount: 17726 bytes_req: 13944120 bytes_alloc: 19593808 - { stacktrace: + { common_stacktrace: __kmalloc+0x11b/0x1b0 load_elf_phdrs+0x76/0xa0 load_elf_binary+0x102/0x1650 @@ -625,7 +625,7 @@ Extended error information SyS_execve+0x3a/0x50 return_from_execve+0x0/0x23 } hitcount: 33348 bytes_req: 17152128 bytes_alloc: 20226048 - { stacktrace: + { common_stacktrace: kmem_cache_alloc_trace+0xeb/0x150 apparmor_file_alloc_security+0x27/0x40 security_file_alloc+0x16/0x20 @@ -636,7 +636,7 @@ Extended error information SyS_open+0x1e/0x20 system_call_fastpath+0x12/0x6a } hitcount: 4766422 bytes_req: 9532844 bytes_alloc: 38131376 - { stacktrace: + { common_stacktrace: __kmalloc+0x11b/0x1b0 seq_buf_alloc+0x1b/0x50 seq_read+0x2cc/0x370 @@ -1026,7 +1026,7 @@ Extended error information First we set up an initially paused stacktrace trigger on the netif_receive_skb event:: - # echo 'hist:key=stacktrace:vals=len:pause' > \ + # echo 'hist:key=common_stacktrace:vals=len:pause' > \ /sys/kernel/tracing/events/net/netif_receive_skb/trigger Next, we set up an 'enable_hist' trigger on the sched_process_exec @@ -1060,9 +1060,9 @@ Extended error information $ wget https://www.kernel.org/pub/linux/kernel/v3.x/patch-3.19.xz # cat /sys/kernel/tracing/events/net/netif_receive_skb/hist - # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused] + # trigger info: hist:keys=common_stacktrace:vals=len:sort=hitcount:size=2048 [paused] - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 netif_receive_skb_internal+0x23/0x90 @@ -1079,7 +1079,7 @@ Extended error information kthread+0xd2/0xf0 ret_from_fork+0x42/0x70 } hitcount: 85 len: 28884 - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 netif_receive_skb_internal+0x23/0x90 @@ -1097,7 +1097,7 @@ Extended error information irq_thread+0x11f/0x150 kthread+0xd2/0xf0 } hitcount: 98 len: 664329 - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 process_backlog+0xa8/0x150 @@ -1115,7 +1115,7 @@ Extended error information inet_sendmsg+0x64/0xa0 sock_sendmsg+0x3d/0x50 } hitcount: 115 len: 13030 - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 netif_receive_skb_internal+0x23/0x90 @@ -1142,14 +1142,14 @@ Extended error information into the histogram. In order to avoid having to set everything up again, we can just clear the histogram first:: - # echo 'hist:key=stacktrace:vals=len:clear' >> \ + # echo 'hist:key=common_stacktrace:vals=len:clear' >> \ /sys/kernel/tracing/events/net/netif_receive_skb/trigger Just to verify that it is in fact cleared, here's what we now see in the hist file:: # cat /sys/kernel/tracing/events/net/netif_receive_skb/hist - # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused] + # trigger info: hist:keys=common_stacktrace:vals=len:sort=hitcount:size=2048 [paused] Totals: Hits: 0 @@ -1485,12 +1485,12 @@ Extended error information And here's an example that shows how to combine histogram data from any two events even if they don't share any 'compatible' fields - other than 'hitcount' and 'stacktrace'. These commands create a + other than 'hitcount' and 'common_stacktrace'. These commands create a couple of triggers named 'bar' using those fields:: - # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \ + # echo 'hist:name=bar:key=common_stacktrace:val=hitcount' > \ /sys/kernel/tracing/events/sched/sched_process_fork/trigger - # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \ + # echo 'hist:name=bar:key=common_stacktrace:val=hitcount' > \ /sys/kernel/tracing/events/net/netif_rx/trigger And displaying the output of either shows some interesting if @@ -1501,16 +1501,16 @@ Extended error information # event histogram # - # trigger info: hist:name=bar:keys=stacktrace:vals=hitcount:sort=hitcount:size=2048 [active] + # trigger info: hist:name=bar:keys=common_stacktrace:vals=hitcount:sort=hitcount:size=2048 [active] # - { stacktrace: + { common_stacktrace: kernel_clone+0x18e/0x330 kernel_thread+0x29/0x30 kthreadd+0x154/0x1b0 ret_from_fork+0x3f/0x70 } hitcount: 1 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx_ni+0x20/0x70 dev_loopback_xmit+0xaa/0xd0 @@ -1528,7 +1528,7 @@ Extended error information call_cpuidle+0x3b/0x60 cpu_startup_entry+0x22d/0x310 } hitcount: 1 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx_ni+0x20/0x70 dev_loopback_xmit+0xaa/0xd0 @@ -1543,7 +1543,7 @@ Extended error information SyS_sendto+0xe/0x10 entry_SYSCALL_64_fastpath+0x12/0x6a } hitcount: 2 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx+0x1c/0x60 loopback_xmit+0x6c/0xb0 @@ -1561,7 +1561,7 @@ Extended error information sock_sendmsg+0x38/0x50 ___sys_sendmsg+0x14e/0x270 } hitcount: 76 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx+0x1c/0x60 loopback_xmit+0x6c/0xb0 @@ -1579,7 +1579,7 @@ Extended error information sock_sendmsg+0x38/0x50 ___sys_sendmsg+0x269/0x270 } hitcount: 77 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx+0x1c/0x60 loopback_xmit+0x6c/0xb0 @@ -1597,7 +1597,7 @@ Extended error information sock_sendmsg+0x38/0x50 SYSC_sendto+0xef/0x170 } hitcount: 88 - { stacktrace: + { common_stacktrace: kernel_clone+0x18e/0x330 SyS_clone+0x19/0x20 entry_SYSCALL_64_fastpath+0x12/0x6a @@ -1949,7 +1949,7 @@ uninterruptible state:: # cd /sys/kernel/tracing # echo 's:block_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events - # echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 2' >> events/sched/sched_switch/trigger + # echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=common_stacktrace if prev_state == 2' >> events/sched/sched_switch/trigger # echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(block_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger # echo 1 > events/synthetic/block_lat/enable # cat trace diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 0e373222a6df..7c4a0b72334e 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -806,6 +806,7 @@ enum { FILTER_TRACE_FN, FILTER_COMM, FILTER_CPU, + FILTER_STACKTRACE, }; extern int trace_event_raw_init(struct trace_event_call *call); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index ebc59781456a..81801dc31784 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5752,7 +5752,7 @@ static const char readme_msg[] = "\t table using the key(s) and value(s) named, and the value of a\n" "\t sum called 'hitcount' is incremented. Keys and values\n" "\t correspond to fields in the event's format description. Keys\n" - "\t can be any field, or the special string 'stacktrace'.\n" + "\t can be any field, or the special string 'common_stacktrace'.\n" "\t Compound keys consisting of up to two fields can be specified\n" "\t by the 'keys' keyword. Values must correspond to numeric\n" "\t fields. Sort keys consisting of up to two fields can be\n" diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 654ffa40457a..57e539d47989 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -194,6 +194,8 @@ static int trace_define_generic_fields(void) __generic_field(int, common_cpu, FILTER_CPU); __generic_field(char *, COMM, FILTER_COMM); __generic_field(char *, comm, FILTER_COMM); + __generic_field(char *, stacktrace, FILTER_STACKTRACE); + __generic_field(char *, STACKTRACE, FILTER_STACKTRACE); return ret; } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 543cb7dc84ad..b97d3ad832f1 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1364,7 +1364,7 @@ static const char *hist_field_name(struct hist_field *field, if (field->field) field_name = field->field->name; else - field_name = "stacktrace"; + field_name = "common_stacktrace"; } else if (field->flags & HIST_FIELD_FL_HITCOUNT) field_name = "hitcount"; @@ -2367,7 +2367,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, hist_data->enable_timestamps = true; if (*flags & HIST_FIELD_FL_TIMESTAMP_USECS) hist_data->attrs->ts_in_usecs = true; - } else if (strcmp(field_name, "stacktrace") == 0) { + } else if (strcmp(field_name, "common_stacktrace") == 0) { *flags |= HIST_FIELD_FL_STACKTRACE; } else if (strcmp(field_name, "common_cpu") == 0) *flags |= HIST_FIELD_FL_CPU; @@ -2378,11 +2378,15 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, if (!field || !field->size) { /* * For backward compatibility, if field_name - * was "cpu", then we treat this the same as - * common_cpu. This also works for "CPU". + * was "cpu" or "stacktrace", then we treat this + * the same as common_cpu and common_stacktrace + * respectively. This also works for "CPU", and + * "STACKTRACE". */ if (field && field->filter_type == FILTER_CPU) { *flags |= HIST_FIELD_FL_CPU; + } else if (field && field->filter_type == FILTER_STACKTRACE) { + *flags |= HIST_FIELD_FL_STACKTRACE; } else { hist_err(tr, HIST_ERR_FIELD_NOT_FOUND, errpos(field_name)); @@ -5394,7 +5398,7 @@ static void hist_trigger_print_key(struct seq_file *m, if (key_field->field) seq_printf(m, "%s.stacktrace", key_field->field->name); else - seq_puts(m, "stacktrace:\n"); + seq_puts(m, "common_stacktrace:\n"); hist_trigger_stacktrace_print(m, key + key_field->offset, HIST_STACKTRACE_DEPTH); @@ -5977,7 +5981,7 @@ static int event_hist_trigger_print(struct seq_file *m, if (field->field) seq_printf(m, "%s.stacktrace", field->field->name); else - seq_puts(m, "stacktrace"); + seq_puts(m, "common_stacktrace"); } else hist_field_print(m, field); } -- cgit v1.2.3 From 335b4223466dd75f9f3ea4918187afbadd22e5c8 Mon Sep 17 00:00:00 2001 From: Maximilian Heyne Date: Wed, 3 May 2023 13:16:53 +0000 Subject: x86/pci/xen: populate MSI sysfs entries Commit bf5e758f02fc ("genirq/msi: Simplify sysfs handling") reworked the creation of sysfs entries for MSI IRQs. The creation used to be in msi_domain_alloc_irqs_descs_locked after calling ops->domain_alloc_irqs. Then it moved into __msi_domain_alloc_irqs which is an implementation of domain_alloc_irqs. However, Xen comes with the only other implementation of domain_alloc_irqs and hence doesn't run the sysfs population code anymore. Commit 6c796996ee70 ("x86/pci/xen: Fixup fallout from the PCI/MSI overhaul") set the flag MSI_FLAG_DEV_SYSFS for the xen msi_domain_info but that doesn't actually have an effect because Xen uses it's own domain_alloc_irqs implementation. Fix this by making use of the fallback functions for sysfs population. Fixes: bf5e758f02fc ("genirq/msi: Simplify sysfs handling") Signed-off-by: Maximilian Heyne Reviewed-by: Juergen Gross Link: https://lore.kernel.org/r/20230503131656.15928-1-mheyne@amazon.de Signed-off-by: Juergen Gross --- arch/x86/pci/xen.c | 8 +++++--- include/linux/msi.h | 9 ++++++++- kernel/irq/msi.c | 4 ++-- 3 files changed, 15 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 8babce71915f..014c508e914d 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -198,7 +198,7 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) i++; } kfree(v); - return 0; + return msi_device_populate_sysfs(&dev->dev); error: if (ret == -ENOSYS) @@ -254,7 +254,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) dev_dbg(&dev->dev, "xen: msi --> pirq=%d --> irq=%d\n", pirq, irq); } - return 0; + return msi_device_populate_sysfs(&dev->dev); error: dev_err(&dev->dev, "Failed to create MSI%s! ret=%d!\n", @@ -346,7 +346,7 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) if (ret < 0) goto out; } - ret = 0; + ret = msi_device_populate_sysfs(&dev->dev); out: return ret; } @@ -394,6 +394,8 @@ static void xen_teardown_msi_irqs(struct pci_dev *dev) xen_destroy_irq(msidesc->irq + i); msidesc->irq = 0; } + + msi_device_destroy_sysfs(&dev->dev); } static void xen_pv_teardown_msi_irqs(struct pci_dev *dev) diff --git a/include/linux/msi.h b/include/linux/msi.h index cdb14a1ef268..a50ea79522f8 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -383,6 +383,13 @@ int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc); void arch_teardown_msi_irq(unsigned int irq); int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); void arch_teardown_msi_irqs(struct pci_dev *dev); +#endif /* CONFIG_PCI_MSI_ARCH_FALLBACKS */ + +/* + * Xen uses non-default msi_domain_ops and hence needs a way to populate sysfs + * entries of MSI IRQs. + */ +#if defined(CONFIG_PCI_XEN) || defined(CONFIG_PCI_MSI_ARCH_FALLBACKS) #ifdef CONFIG_SYSFS int msi_device_populate_sysfs(struct device *dev); void msi_device_destroy_sysfs(struct device *dev); @@ -390,7 +397,7 @@ void msi_device_destroy_sysfs(struct device *dev); static inline int msi_device_populate_sysfs(struct device *dev) { return 0; } static inline void msi_device_destroy_sysfs(struct device *dev) { } #endif /* !CONFIG_SYSFS */ -#endif /* CONFIG_PCI_MSI_ARCH_FALLBACKS */ +#endif /* CONFIG_PCI_XEN || CONFIG_PCI_MSI_ARCH_FALLBACKS */ /* * The restore hook is still available even for fully irq domain based diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 7a97bcb086bf..b4c31a5c1147 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -542,7 +542,7 @@ fail: return ret; } -#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS +#if defined(CONFIG_PCI_MSI_ARCH_FALLBACKS) || defined(CONFIG_PCI_XEN) /** * msi_device_populate_sysfs - Populate msi_irqs sysfs entries for a device * @dev: The device (PCI, platform etc) which will get sysfs entries @@ -574,7 +574,7 @@ void msi_device_destroy_sysfs(struct device *dev) msi_for_each_desc(desc, dev, MSI_DESC_ALL) msi_sysfs_remove_desc(dev, desc); } -#endif /* CONFIG_PCI_MSI_ARCH_FALLBACK */ +#endif /* CONFIG_PCI_MSI_ARCH_FALLBACK || CONFIG_PCI_XEN */ #else /* CONFIG_SYSFS */ static inline int msi_sysfs_create_group(struct device *dev) { return 0; } static inline int msi_sysfs_populate_desc(struct device *dev, struct msi_desc *desc) { return 0; } -- cgit v1.2.3 From 672b584c68de309017cd2ce8938856c9b7c1b70e Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 11 Apr 2023 15:47:15 +0200 Subject: dt-bindings: power: qcom,rpmpd: Add SA8155P Add a compatible for SA8155P platforms and relevant defines to the include file. Signed-off-by: Konrad Dybcio Acked-by: Krzysztof Kozlowski Tested-by: Bartosz Golaszewski Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230411-topic-hanaau-v2-1-fd3d70844b31@linaro.org --- Documentation/devicetree/bindings/power/qcom,rpmpd.yaml | 1 + include/dt-bindings/power/qcom-rpmpd.h | 9 +++++++++ 2 files changed, 10 insertions(+) (limited to 'include') diff --git a/Documentation/devicetree/bindings/power/qcom,rpmpd.yaml b/Documentation/devicetree/bindings/power/qcom,rpmpd.yaml index afad3135ed67..f9c211a9a938 100644 --- a/Documentation/devicetree/bindings/power/qcom,rpmpd.yaml +++ b/Documentation/devicetree/bindings/power/qcom,rpmpd.yaml @@ -29,6 +29,7 @@ properties: - qcom,qcm2290-rpmpd - qcom,qcs404-rpmpd - qcom,qdu1000-rpmhpd + - qcom,sa8155p-rpmhpd - qcom,sa8540p-rpmhpd - qcom,sa8775p-rpmhpd - qcom,sdm660-rpmpd diff --git a/include/dt-bindings/power/qcom-rpmpd.h b/include/dt-bindings/power/qcom-rpmpd.h index 1bf8e87ecd7e..867b18e041ea 100644 --- a/include/dt-bindings/power/qcom-rpmpd.h +++ b/include/dt-bindings/power/qcom-rpmpd.h @@ -90,6 +90,15 @@ #define SM8150_MMCX 9 #define SM8150_MMCX_AO 10 +/* SA8155P is a special case, kept for backwards compatibility */ +#define SA8155P_CX SM8150_CX +#define SA8155P_CX_AO SM8150_CX_AO +#define SA8155P_EBI SM8150_EBI +#define SA8155P_GFX SM8150_GFX +#define SA8155P_MSS SM8150_MSS +#define SA8155P_MX SM8150_MX +#define SA8155P_MX_AO SM8150_MX_AO + /* SM8250 Power Domain Indexes */ #define SM8250_CX 0 #define SM8250_CX_AO 1 -- cgit v1.2.3 From 1db1f21caebbb1b6e9b1e7657df613616be3fb49 Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Thu, 13 Apr 2023 15:48:30 +0300 Subject: net/mlx5e: Use query_special_contexts cmd only once per mdev Don't query the firmware so many times (num rqs * num wqes * wqe frags) because it slows down linearly the interface creation time when the product is larger. Do it only once per mdev and store the result in mlx5e_param. Due to helper function being called from different files, move it to an appropriate location. Rename the function with a proper prefix and add a small cleanup. This fix applies only for legacy rq. Fixes: 1b1e4868836a ("net/mlx5e: Use query_special_contexts for mkeys") Signed-off-by: Dragos Tatulea Reviewed-by: Or Har-Toov Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 1 + drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 24 +++-------------------- drivers/net/ethernet/mellanox/mlx5/core/mr.c | 21 ++++++++++++++++++++ include/linux/mlx5/driver.h | 1 + 4 files changed, 26 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index b8987a404d75..8e999f238194 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -327,6 +327,7 @@ struct mlx5e_params { unsigned int sw_mtu; int hard_mtu; bool ptp_rx; + __be32 terminate_lkey_be; }; static inline u8 mlx5e_get_dcb_num_tc(struct mlx5e_params *params) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 2944691f06ad..0235adcbc609 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -727,26 +727,6 @@ static void mlx5e_rq_free_shampo(struct mlx5e_rq *rq) mlx5e_rq_shampo_hd_free(rq); } -static __be32 mlx5e_get_terminate_scatter_list_mkey(struct mlx5_core_dev *dev) -{ - u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {}; - u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)] = {}; - int res; - - if (!MLX5_CAP_GEN(dev, terminate_scatter_list_mkey)) - return MLX5_TERMINATE_SCATTER_LIST_LKEY; - - MLX5_SET(query_special_contexts_in, in, opcode, - MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS); - res = mlx5_cmd_exec_inout(dev, query_special_contexts, in, out); - if (res) - return MLX5_TERMINATE_SCATTER_LIST_LKEY; - - res = MLX5_GET(query_special_contexts_out, out, - terminate_scatter_list_mkey); - return cpu_to_be32(res); -} - static int mlx5e_alloc_rq(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, struct mlx5e_rq_param *rqp, @@ -908,7 +888,7 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, /* check if num_frags is not a pow of two */ if (rq->wqe.info.num_frags < (1 << rq->wqe.info.log_num_frags)) { wqe->data[f].byte_count = 0; - wqe->data[f].lkey = mlx5e_get_terminate_scatter_list_mkey(mdev); + wqe->data[f].lkey = params->terminate_lkey_be; wqe->data[f].addr = 0; } } @@ -5007,6 +4987,8 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 /* RQ */ mlx5e_build_rq_params(mdev, params); + params->terminate_lkey_be = mlx5_core_get_terminate_scatter_list_mkey(mdev); + params->packet_merge.timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT); /* CQ moderation params */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index 9d735c343a3b..678f0be81375 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -32,6 +32,7 @@ #include #include +#include #include "mlx5_core.h" int mlx5_core_create_mkey(struct mlx5_core_dev *dev, u32 *mkey, u32 *in, @@ -122,3 +123,23 @@ int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num) return mlx5_cmd_exec_in(dev, destroy_psv, in); } EXPORT_SYMBOL(mlx5_core_destroy_psv); + +__be32 mlx5_core_get_terminate_scatter_list_mkey(struct mlx5_core_dev *dev) +{ + u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {}; + u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)] = {}; + u32 mkey; + + if (!MLX5_CAP_GEN(dev, terminate_scatter_list_mkey)) + return MLX5_TERMINATE_SCATTER_LIST_LKEY; + + MLX5_SET(query_special_contexts_in, in, opcode, + MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS); + if (mlx5_cmd_exec_inout(dev, query_special_contexts, in, out)) + return MLX5_TERMINATE_SCATTER_LIST_LKEY; + + mkey = MLX5_GET(query_special_contexts_out, out, + terminate_scatter_list_mkey); + return cpu_to_be32(mkey); +} +EXPORT_SYMBOL(mlx5_core_get_terminate_scatter_list_mkey); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a4c4f737f9c1..94d2be5848ae 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1093,6 +1093,7 @@ void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn, int npsvs, u32 *sig_index); int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num); +__be32 mlx5_core_get_terminate_scatter_list_mkey(struct mlx5_core_dev *dev); void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common); int mlx5_query_odp_caps(struct mlx5_core_dev *dev, struct mlx5_odp_caps *odp_caps); -- cgit v1.2.3 From 26fb5480a27d34975cc2b680b77af189620dd740 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 11 May 2023 11:49:50 -0400 Subject: net/handshake: Enable the SNI extension to work properly Enable the upper layer protocol to specify the SNI peername. This avoids the need for tlshd to use a DNS lookup, which can return a hostname that doesn't match the incoming certificate's SubjectName. Fixes: 2fd5532044a8 ("net/handshake: Add a kernel API for requesting a TLSv1.3 handshake") Reviewed-by: Simon Horman Signed-off-by: Chuck Lever Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/handshake.yaml | 4 ++++ Documentation/networking/tls-handshake.rst | 5 +++++ include/net/handshake.h | 1 + include/uapi/linux/handshake.h | 1 + net/handshake/tlshd.c | 8 ++++++++ 5 files changed, 19 insertions(+) (limited to 'include') diff --git a/Documentation/netlink/specs/handshake.yaml b/Documentation/netlink/specs/handshake.yaml index 614f1a585511..6d89e30f5fd5 100644 --- a/Documentation/netlink/specs/handshake.yaml +++ b/Documentation/netlink/specs/handshake.yaml @@ -68,6 +68,9 @@ attribute-sets: type: nest nested-attributes: x509 multi-attr: true + - + name: peername + type: string - name: done attributes: @@ -105,6 +108,7 @@ operations: - auth-mode - peer-identity - certificate + - peername - name: done doc: Handler reports handshake completion diff --git a/Documentation/networking/tls-handshake.rst b/Documentation/networking/tls-handshake.rst index a2817a88e905..6f5ea1646a47 100644 --- a/Documentation/networking/tls-handshake.rst +++ b/Documentation/networking/tls-handshake.rst @@ -53,6 +53,7 @@ fills in a structure that contains the parameters of the request: struct socket *ta_sock; tls_done_func_t ta_done; void *ta_data; + const char *ta_peername; unsigned int ta_timeout_ms; key_serial_t ta_keyring; key_serial_t ta_my_cert; @@ -71,6 +72,10 @@ instantiated a struct file in sock->file. has completed. Further explanation of this function is in the "Handshake Completion" sesction below. +The consumer can provide a NUL-terminated hostname in the @ta_peername +field that is sent as part of ClientHello. If no peername is provided, +the DNS hostname associated with the server's IP address is used instead. + The consumer can fill in the @ta_timeout_ms field to force the servicing handshake agent to exit after a number of milliseconds. This enables the socket to be fully closed once both the kernel and the handshake agent diff --git a/include/net/handshake.h b/include/net/handshake.h index 3352b1ab43b3..2e26e436e85f 100644 --- a/include/net/handshake.h +++ b/include/net/handshake.h @@ -24,6 +24,7 @@ struct tls_handshake_args { struct socket *ta_sock; tls_done_func_t ta_done; void *ta_data; + const char *ta_peername; unsigned int ta_timeout_ms; key_serial_t ta_keyring; key_serial_t ta_my_cert; diff --git a/include/uapi/linux/handshake.h b/include/uapi/linux/handshake.h index 1de4d0b95325..3d7ea58778c9 100644 --- a/include/uapi/linux/handshake.h +++ b/include/uapi/linux/handshake.h @@ -44,6 +44,7 @@ enum { HANDSHAKE_A_ACCEPT_AUTH_MODE, HANDSHAKE_A_ACCEPT_PEER_IDENTITY, HANDSHAKE_A_ACCEPT_CERTIFICATE, + HANDSHAKE_A_ACCEPT_PEERNAME, __HANDSHAKE_A_ACCEPT_MAX, HANDSHAKE_A_ACCEPT_MAX = (__HANDSHAKE_A_ACCEPT_MAX - 1) diff --git a/net/handshake/tlshd.c b/net/handshake/tlshd.c index fcbeb63b4eb1..b735f5cced2f 100644 --- a/net/handshake/tlshd.c +++ b/net/handshake/tlshd.c @@ -31,6 +31,7 @@ struct tls_handshake_req { int th_type; unsigned int th_timeout_ms; int th_auth_mode; + const char *th_peername; key_serial_t th_keyring; key_serial_t th_certificate; key_serial_t th_privkey; @@ -48,6 +49,7 @@ tls_handshake_req_init(struct handshake_req *req, treq->th_timeout_ms = args->ta_timeout_ms; treq->th_consumer_done = args->ta_done; treq->th_consumer_data = args->ta_data; + treq->th_peername = args->ta_peername; treq->th_keyring = args->ta_keyring; treq->th_num_peerids = 0; treq->th_certificate = TLS_NO_CERT; @@ -214,6 +216,12 @@ static int tls_handshake_accept(struct handshake_req *req, ret = nla_put_u32(msg, HANDSHAKE_A_ACCEPT_MESSAGE_TYPE, treq->th_type); if (ret < 0) goto out_cancel; + if (treq->th_peername) { + ret = nla_put_string(msg, HANDSHAKE_A_ACCEPT_PEERNAME, + treq->th_peername); + if (ret < 0) + goto out_cancel; + } if (treq->th_timeout_ms) { ret = nla_put_u32(msg, HANDSHAKE_A_ACCEPT_TIMEOUT, treq->th_timeout_ms); if (ret < 0) -- cgit v1.2.3 From fd936fd8ac105ba3eb764185e8ba483c789c893e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 23 May 2023 21:01:30 +0200 Subject: efi: fix missing prototype warnings The cper.c file needs to include an extra header, and efi_zboot_entry needs an extern declaration to avoid these 'make W=1' warnings: drivers/firmware/efi/libstub/zboot.c:65:1: error: no previous prototype for 'efi_zboot_entry' [-Werror=missing-prototypes] drivers/firmware/efi/efi.c:176:16: error: no previous prototype for 'efi_attr_is_visible' [-Werror=missing-prototypes] drivers/firmware/efi/cper.c:626:6: error: no previous prototype for 'cper_estatus_print' [-Werror=missing-prototypes] drivers/firmware/efi/cper.c:649:5: error: no previous prototype for 'cper_estatus_check_header' [-Werror=missing-prototypes] drivers/firmware/efi/cper.c:662:5: error: no previous prototype for 'cper_estatus_check' [-Werror=missing-prototypes] To make this easier, move the cper specific declarations to include/linux/cper.h. Signed-off-by: Arnd Bergmann Acked-by: Rafael J. Wysocki Signed-off-by: Ard Biesheuvel --- drivers/acpi/apei/apei-internal.h | 6 ------ drivers/acpi/apei/bert.c | 1 + drivers/firmware/efi/libstub/efistub.h | 3 +++ include/linux/cper.h | 6 ++++++ include/linux/efi.h | 2 ++ 5 files changed, 12 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/acpi/apei/apei-internal.h b/drivers/acpi/apei/apei-internal.h index 1d6ef9654725..67c2c3b959e1 100644 --- a/drivers/acpi/apei/apei-internal.h +++ b/drivers/acpi/apei/apei-internal.h @@ -7,7 +7,6 @@ #ifndef APEI_INTERNAL_H #define APEI_INTERNAL_H -#include #include struct apei_exec_context; @@ -130,10 +129,5 @@ static inline u32 cper_estatus_len(struct acpi_hest_generic_status *estatus) return sizeof(*estatus) + estatus->data_length; } -void cper_estatus_print(const char *pfx, - const struct acpi_hest_generic_status *estatus); -int cper_estatus_check_header(const struct acpi_hest_generic_status *estatus); -int cper_estatus_check(const struct acpi_hest_generic_status *estatus); - int apei_osc_setup(void); #endif diff --git a/drivers/acpi/apei/bert.c b/drivers/acpi/apei/bert.c index c23eb75866d0..7514e38d5640 100644 --- a/drivers/acpi/apei/bert.c +++ b/drivers/acpi/apei/bert.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include "apei-internal.h" diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index 67d5a20802e0..54a2822cae77 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -1133,4 +1133,7 @@ const u8 *__efi_get_smbios_string(const struct efi_smbios_record *record, void efi_remap_image(unsigned long image_base, unsigned alloc_size, unsigned long code_size); +asmlinkage efi_status_t __efiapi +efi_zboot_entry(efi_handle_t handle, efi_system_table_t *systab); + #endif diff --git a/include/linux/cper.h b/include/linux/cper.h index eacb7dd7b3af..c1a7dc325121 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -572,4 +572,10 @@ void cper_print_proc_ia(const char *pfx, int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg); int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg); +struct acpi_hest_generic_status; +void cper_estatus_print(const char *pfx, + const struct acpi_hest_generic_status *estatus); +int cper_estatus_check_header(const struct acpi_hest_generic_status *estatus); +int cper_estatus_check(const struct acpi_hest_generic_status *estatus); + #endif diff --git a/include/linux/efi.h b/include/linux/efi.h index 7aa62c92185f..571d1a6e1b74 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1338,4 +1338,6 @@ bool efi_config_table_is_usable(const efi_guid_t *guid, unsigned long table) return xen_efi_config_table_is_usable(guid, table); } +umode_t efi_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n); + #endif /* _LINUX_EFI_H */ -- cgit v1.2.3 From 9828ed3f695a138f7add89fa2a186ababceb8006 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 25 May 2023 09:32:25 -0700 Subject: module: error out early on concurrent load of the same module file It turns out that udev under certain circumstances will concurrently try to load the same modules over-and-over excessively. This isn't a kernel bug, but it ends up affecting the kernel, to the point that under certain circumstances we can fail to boot, because the kernel uses a lot of memory to read all the module data all at once. Note that it isn't a memory leak, it's just basically a thundering herd problem happening at bootup with a lot of CPUs, with the worst cases then being pretty bad. Admittedly the worst situations are somewhat contrived: lots and lots of CPUs, not a lot of memory, and KASAN enabled to make it all slower and as such (unintentionally) exacerbate the problem. Luis explains: [1] "My best assessment of the situation is that each CPU in udev ends up triggering a load of duplicate set of modules, not just one, but *a lot*. Not sure what heuristics udev uses to load a set of modules per CPU." Petr Pavlu chimes in: [2] "My understanding is that udev workers are forked. An initial kmod context is created by the main udevd process but no sharing happens after the fork. It means that the mentioned memory pool logic doesn't really kick in. Multiple parallel load requests come from multiple udev workers, for instance, each handling an udev event for one CPU device and making the exactly same requests as all others are doing at the same time. The optimization idea would be to recognize these duplicate requests at the udevd/kmod level and converge them" Note that module loading has tried to mitigate this issue before, see for example commit 064f4536d139 ("module: avoid allocation if module is already present and ready"), which has a few ASCII graphs on memory use due to this same issue. However, while that noticed that the module was already loaded, and exited with an error early before spending any more time on setting up the module, it didn't handle the case of multiple concurrent module loads all being active - but not complete - at the same time. Yes, one of them will eventually win the race and finalize its copy, and the others will then notice that the module already exists and error out, but while this all happens, we have tons of unnecessary concurrent work being done. Again, the real fix is for udev to not do that (maybe it should use threads instead of fork, and have actual shared data structures and not cause duplicate work). That real fix is apparently not trivial. But it turns out that the kernel already has a pretty good model for dealing with concurrent access to the same file: the i_writecount of the inode. In fact, the module loading already indirectly uses 'i_writecount' , because 'kernel_file_read()' will in fact do ret = deny_write_access(file); if (ret) return ret; ... allow_write_access(file); around the read of the file data. We do not allow concurrent writes to the file, and return -ETXTBUSY if the file was open for writing at the same time as the module data is loaded from it. And the solution to the reader concurrency problem is to simply extend this "no concurrent writers" logic to simply be "exclusive access". Note that "exclusive" in this context isn't really some absolute thing: it's only exclusion from writers and from other "special readers" that do this writer denial. So we simply introduce a variation of that "deny_write_access()" logic that not only denies write access, but also requires that this is the _only_ such access that denies write access. Which means that you can't start loading a module that is already being loaded as a module by somebody else, or you will get the same -ETXTBSY error that you would get if there were writers around. [ It also means that you can't try to load a currently executing executable as a module, for the same reason: executables do that same "deny_write_access()" thing, and that's obviously where the whole ETXTBSY logic traditionally came from. This is not a problem for kernel modules, since the set of normal executable files and kernel module files is entirely disjoint. ] This new function is called "exclusive_deny_write_access()", and the implementation is trivial, in that it's just an atomic decrement of i_writecount if it was 0 before. To use that new exclusivity check, all we then do is wrap the module loading with that exclusive_deny_write_access()() / allow_write_access() pair. The actual patch is a bit bigger than that, because we want to surround not just the "load file data" part, but the whole module setup, to get maximum exclusion. So this ends up splitting up "finit_module()" into a few helper functions to make it all very clear and legible. In Luis' test-case (bringing up 255 vcpu's in a virtual machine [3]), the "wasted vmalloc" space (ie module data read into a vmalloc'ed area in order to be loaded as a module, but then discarded because somebody else loaded the same module instead) dropped from 1.8GiB to 474kB. Yes, that's gigabytes to kilobytes. It doesn't drop completely to zero, because even with this change, you can still end up having completely serial pointless module loads, where one udev process has loaded a module fully (and thus the kernel has released that exclusive lock on the module file), and then another udev process tries to load the same module again. So while we cannot fully get rid of the fundamental bug in user space, we _can_ get rid of the excessive concurrent thundering herd effect. A couple of final side notes on this all: - This tweak only affects the "finit_module()" system call, which gives the kernel a file descriptor with the module data. You can also just feed the module data as raw data from user space with "init_module()" (note the lack of 'f' at the beginning), and obviously for that case we do _not_ have any "exclusive read" logic. So if you absolutely want to do things wrong in user space, and try to load the same module multiple times, and error out only later when the kernel ends up saying "you can't load the same module name twice", you can still do that. And in fact, some distros will do exactly that, because they will uncompress the kernel module data in user space before feeding it to the kernel (mainly because they haven't started using the new kernel side decompression yet). So this is not some absolute "you can't do concurrent loads of the same module". It's literally just a very simple heuristic that will catch it early in case you try to load the exact same module file at the same time, and in that case avoid a potentially nasty situation. - There is another user of "deny_write_access()": the verity code that enables fs-verity on a file (the FS_IOC_ENABLE_VERITY ioctl). If you use fs-verity and you care about verifying the kernel modules (which does make sense), you should do it *before* loading said kernel module. That may sound obvious, but now the implementation basically requires it. Because if you try to do it concurrently, the kernel may refuse to load the module file that is being set up by the fs-verity code. - This all will obviously mean that if you insist on loading the same module in parallel, only one module load will succeed, and the others will return with an error. That was true before too, but what is different is that the -ETXTBSY error can be returned *before* the success case of another process fully loading and instantiating the module. Again, that might sound obvious, and it is indeed the whole point of the whole change: we are much quicker to notice the whole "you're already in the process of loading this module". So it's very much intentional, but it does mean that if you just spray the kernel with "finit_module()", and expect that the module is immediately loaded afterwards without checking the return value, you are doing something horribly horribly wrong. I'd like to say that that would never happen, but the whole _reason_ for this commit is that udev is currently doing something horribly horribly wrong, so ... Link: https://lore.kernel.org/all/ZEGopJ8VAYnE7LQ2@bombadil.infradead.org/ [1] Link: https://lore.kernel.org/all/23bd0ce6-ef78-1cd8-1f21-0e706a00424a@suse.com/ [2] Link: https://lore.kernel.org/lkml/ZG%2Fa+nrt4%2FAAUi5z@bombadil.infradead.org/ [3] Cc: Greg Kroah-Hartman Cc: Lucas De Marchi Cc: Petr Pavlu Tested-by: Luis Chamberlain Signed-off-by: Linus Torvalds --- include/linux/fs.h | 6 ++++++ kernel/module/main.c | 58 ++++++++++++++++++++++++++++++++++++++-------------- 2 files changed, 49 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 133f0640fb24..86b50271b4f7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2566,6 +2566,12 @@ static inline int deny_write_access(struct file *file) struct inode *inode = file_inode(file); return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY; } +static inline int exclusive_deny_write_access(struct file *file) +{ + int old = 0; + struct inode *inode = file_inode(file); + return atomic_try_cmpxchg(&inode->i_writecount, &old, -1) ? 0 : -ETXTBSY; +} static inline void put_write_access(struct inode * inode) { atomic_dec(&inode->i_writecount); diff --git a/kernel/module/main.c b/kernel/module/main.c index 044aa2c9e3cb..b4c7e925fdb0 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -3057,25 +3057,13 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, return load_module(&info, uargs, 0); } -SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) +static int file_init_module(struct file *file, const char __user * uargs, int flags) { struct load_info info = { }; void *buf = NULL; int len; - int err; - - err = may_init_module(); - if (err) - return err; - - pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags); - if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS - |MODULE_INIT_IGNORE_VERMAGIC - |MODULE_INIT_COMPRESSED_FILE)) - return -EINVAL; - - len = kernel_read_file_from_fd(fd, 0, &buf, INT_MAX, NULL, + len = kernel_read_file(file, 0, &buf, INT_MAX, NULL, READING_MODULE); if (len < 0) { mod_stat_inc(&failed_kreads); @@ -3084,7 +3072,7 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) } if (flags & MODULE_INIT_COMPRESSED_FILE) { - err = module_decompress(&info, buf, len); + int err = module_decompress(&info, buf, len); vfree(buf); /* compressed data is no longer needed */ if (err) { mod_stat_inc(&failed_decompress); @@ -3099,6 +3087,46 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) return load_module(&info, uargs, flags); } +/* + * kernel_read_file() will already deny write access, but module + * loading wants _exclusive_ access to the file, so we do that + * here, along with basic sanity checks. + */ +static int prepare_file_for_module_load(struct file *file) +{ + if (!file || !(file->f_mode & FMODE_READ)) + return -EBADF; + if (!S_ISREG(file_inode(file)->i_mode)) + return -EINVAL; + return exclusive_deny_write_access(file); +} + +SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) +{ + struct fd f; + int err; + + err = may_init_module(); + if (err) + return err; + + pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags); + + if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS + |MODULE_INIT_IGNORE_VERMAGIC + |MODULE_INIT_COMPRESSED_FILE)) + return -EINVAL; + + f = fdget(fd); + err = prepare_file_for_module_load(f.file); + if (!err) { + err = file_init_module(f.file, uargs, flags); + allow_write_access(f.file); + } + fdput(f); + return err; +} + /* Keep in sync with MODULE_FLAGS_BUF_SIZE !!! */ char *module_flags(struct module *mod, char *buf, bool show_state) { -- cgit v1.2.3 From cbd77119b6355872cd308a60e99f9ca678435d15 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Wed, 17 May 2023 17:16:35 +0530 Subject: EDAC/qcom: Get rid of hardcoded register offsets The LLCC EDAC register offsets varies between each SoC. Hardcoding the register offsets won't work and will often result in crash due to accessing the wrong locations. Hence, get the register offsets from the LLCC driver matching the individual SoCs. Cc: # 6.0: 5365cea199c7 ("soc: qcom: llcc: Rename reg_offset structs to reflect LLCC version") Cc: # 6.0: c13d7d261e36 ("soc: qcom: llcc: Pass LLCC version based register offsets to EDAC driver") Cc: # 6.0 Fixes: a6e9d7ef252c ("soc: qcom: llcc: Add configuration data for SM8450 SoC") Acked-by: Borislav Petkov (AMD) Signed-off-by: Manivannan Sadhasivam Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230517114635.76358-3-manivannan.sadhasivam@linaro.org --- drivers/edac/qcom_edac.c | 116 ++++++++++++++++++------------------- include/linux/soc/qcom/llcc-qcom.h | 6 -- 2 files changed, 58 insertions(+), 64 deletions(-) (limited to 'include') diff --git a/drivers/edac/qcom_edac.c b/drivers/edac/qcom_edac.c index 6140001f21c4..b2db545c6810 100644 --- a/drivers/edac/qcom_edac.c +++ b/drivers/edac/qcom_edac.c @@ -21,30 +21,9 @@ #define TRP_SYN_REG_CNT 6 #define DRP_SYN_REG_CNT 8 -#define LLCC_COMMON_STATUS0 0x0003000c #define LLCC_LB_CNT_MASK GENMASK(31, 28) #define LLCC_LB_CNT_SHIFT 28 -/* Single & double bit syndrome register offsets */ -#define TRP_ECC_SB_ERR_SYN0 0x0002304c -#define TRP_ECC_DB_ERR_SYN0 0x00020370 -#define DRP_ECC_SB_ERR_SYN0 0x0004204c -#define DRP_ECC_DB_ERR_SYN0 0x00042070 - -/* Error register offsets */ -#define TRP_ECC_ERROR_STATUS1 0x00020348 -#define TRP_ECC_ERROR_STATUS0 0x00020344 -#define DRP_ECC_ERROR_STATUS1 0x00042048 -#define DRP_ECC_ERROR_STATUS0 0x00042044 - -/* TRP, DRP interrupt register offsets */ -#define DRP_INTERRUPT_STATUS 0x00041000 -#define TRP_INTERRUPT_0_STATUS 0x00020480 -#define DRP_INTERRUPT_CLEAR 0x00041008 -#define DRP_ECC_ERROR_CNTR_CLEAR 0x00040004 -#define TRP_INTERRUPT_0_CLEAR 0x00020484 -#define TRP_ECC_ERROR_CNTR_CLEAR 0x00020440 - /* Mask and shift macros */ #define ECC_DB_ERR_COUNT_MASK GENMASK(4, 0) #define ECC_DB_ERR_WAYS_MASK GENMASK(31, 16) @@ -60,15 +39,6 @@ #define DRP_TRP_INT_CLEAR GENMASK(1, 0) #define DRP_TRP_CNT_CLEAR GENMASK(1, 0) -/* Config registers offsets*/ -#define DRP_ECC_ERROR_CFG 0x00040000 - -/* Tag RAM, Data RAM interrupt register offsets */ -#define CMN_INTERRUPT_0_ENABLE 0x0003001c -#define CMN_INTERRUPT_2_ENABLE 0x0003003c -#define TRP_INTERRUPT_0_ENABLE 0x00020488 -#define DRP_INTERRUPT_ENABLE 0x0004100c - #define SB_ERROR_THRESHOLD 0x1 #define SB_ERROR_THRESHOLD_SHIFT 24 #define SB_DB_TRP_INTERRUPT_ENABLE 0x3 @@ -88,9 +58,6 @@ enum { static const struct llcc_edac_reg_data edac_reg_data[] = { [LLCC_DRAM_CE] = { .name = "DRAM Single-bit", - .synd_reg = DRP_ECC_SB_ERR_SYN0, - .count_status_reg = DRP_ECC_ERROR_STATUS1, - .ways_status_reg = DRP_ECC_ERROR_STATUS0, .reg_cnt = DRP_SYN_REG_CNT, .count_mask = ECC_SB_ERR_COUNT_MASK, .ways_mask = ECC_SB_ERR_WAYS_MASK, @@ -98,9 +65,6 @@ static const struct llcc_edac_reg_data edac_reg_data[] = { }, [LLCC_DRAM_UE] = { .name = "DRAM Double-bit", - .synd_reg = DRP_ECC_DB_ERR_SYN0, - .count_status_reg = DRP_ECC_ERROR_STATUS1, - .ways_status_reg = DRP_ECC_ERROR_STATUS0, .reg_cnt = DRP_SYN_REG_CNT, .count_mask = ECC_DB_ERR_COUNT_MASK, .ways_mask = ECC_DB_ERR_WAYS_MASK, @@ -108,9 +72,6 @@ static const struct llcc_edac_reg_data edac_reg_data[] = { }, [LLCC_TRAM_CE] = { .name = "TRAM Single-bit", - .synd_reg = TRP_ECC_SB_ERR_SYN0, - .count_status_reg = TRP_ECC_ERROR_STATUS1, - .ways_status_reg = TRP_ECC_ERROR_STATUS0, .reg_cnt = TRP_SYN_REG_CNT, .count_mask = ECC_SB_ERR_COUNT_MASK, .ways_mask = ECC_SB_ERR_WAYS_MASK, @@ -118,9 +79,6 @@ static const struct llcc_edac_reg_data edac_reg_data[] = { }, [LLCC_TRAM_UE] = { .name = "TRAM Double-bit", - .synd_reg = TRP_ECC_DB_ERR_SYN0, - .count_status_reg = TRP_ECC_ERROR_STATUS1, - .ways_status_reg = TRP_ECC_ERROR_STATUS0, .reg_cnt = TRP_SYN_REG_CNT, .count_mask = ECC_DB_ERR_COUNT_MASK, .ways_mask = ECC_DB_ERR_WAYS_MASK, @@ -128,7 +86,7 @@ static const struct llcc_edac_reg_data edac_reg_data[] = { }, }; -static int qcom_llcc_core_setup(struct regmap *llcc_bcast_regmap) +static int qcom_llcc_core_setup(struct llcc_drv_data *drv, struct regmap *llcc_bcast_regmap) { u32 sb_err_threshold; int ret; @@ -137,31 +95,31 @@ static int qcom_llcc_core_setup(struct regmap *llcc_bcast_regmap) * Configure interrupt enable registers such that Tag, Data RAM related * interrupts are propagated to interrupt controller for servicing */ - ret = regmap_update_bits(llcc_bcast_regmap, CMN_INTERRUPT_2_ENABLE, + ret = regmap_update_bits(llcc_bcast_regmap, drv->edac_reg_offset->cmn_interrupt_2_enable, TRP0_INTERRUPT_ENABLE, TRP0_INTERRUPT_ENABLE); if (ret) return ret; - ret = regmap_update_bits(llcc_bcast_regmap, TRP_INTERRUPT_0_ENABLE, + ret = regmap_update_bits(llcc_bcast_regmap, drv->edac_reg_offset->trp_interrupt_0_enable, SB_DB_TRP_INTERRUPT_ENABLE, SB_DB_TRP_INTERRUPT_ENABLE); if (ret) return ret; sb_err_threshold = (SB_ERROR_THRESHOLD << SB_ERROR_THRESHOLD_SHIFT); - ret = regmap_write(llcc_bcast_regmap, DRP_ECC_ERROR_CFG, + ret = regmap_write(llcc_bcast_regmap, drv->edac_reg_offset->drp_ecc_error_cfg, sb_err_threshold); if (ret) return ret; - ret = regmap_update_bits(llcc_bcast_regmap, CMN_INTERRUPT_2_ENABLE, + ret = regmap_update_bits(llcc_bcast_regmap, drv->edac_reg_offset->cmn_interrupt_2_enable, DRP0_INTERRUPT_ENABLE, DRP0_INTERRUPT_ENABLE); if (ret) return ret; - ret = regmap_write(llcc_bcast_regmap, DRP_INTERRUPT_ENABLE, + ret = regmap_write(llcc_bcast_regmap, drv->edac_reg_offset->drp_interrupt_enable, SB_DB_DRP_INTERRUPT_ENABLE); return ret; } @@ -175,24 +133,28 @@ qcom_llcc_clear_error_status(int err_type, struct llcc_drv_data *drv) switch (err_type) { case LLCC_DRAM_CE: case LLCC_DRAM_UE: - ret = regmap_write(drv->bcast_regmap, DRP_INTERRUPT_CLEAR, + ret = regmap_write(drv->bcast_regmap, + drv->edac_reg_offset->drp_interrupt_clear, DRP_TRP_INT_CLEAR); if (ret) return ret; - ret = regmap_write(drv->bcast_regmap, DRP_ECC_ERROR_CNTR_CLEAR, + ret = regmap_write(drv->bcast_regmap, + drv->edac_reg_offset->drp_ecc_error_cntr_clear, DRP_TRP_CNT_CLEAR); if (ret) return ret; break; case LLCC_TRAM_CE: case LLCC_TRAM_UE: - ret = regmap_write(drv->bcast_regmap, TRP_INTERRUPT_0_CLEAR, + ret = regmap_write(drv->bcast_regmap, + drv->edac_reg_offset->trp_interrupt_0_clear, DRP_TRP_INT_CLEAR); if (ret) return ret; - ret = regmap_write(drv->bcast_regmap, TRP_ECC_ERROR_CNTR_CLEAR, + ret = regmap_write(drv->bcast_regmap, + drv->edac_reg_offset->trp_ecc_error_cntr_clear, DRP_TRP_CNT_CLEAR); if (ret) return ret; @@ -205,16 +167,54 @@ qcom_llcc_clear_error_status(int err_type, struct llcc_drv_data *drv) return ret; } +struct qcom_llcc_syn_regs { + u32 synd_reg; + u32 count_status_reg; + u32 ways_status_reg; +}; + +static void get_reg_offsets(struct llcc_drv_data *drv, int err_type, + struct qcom_llcc_syn_regs *syn_regs) +{ + const struct llcc_edac_reg_offset *edac_reg_offset = drv->edac_reg_offset; + + switch (err_type) { + case LLCC_DRAM_CE: + syn_regs->synd_reg = edac_reg_offset->drp_ecc_sb_err_syn0; + syn_regs->count_status_reg = edac_reg_offset->drp_ecc_error_status1; + syn_regs->ways_status_reg = edac_reg_offset->drp_ecc_error_status0; + break; + case LLCC_DRAM_UE: + syn_regs->synd_reg = edac_reg_offset->drp_ecc_db_err_syn0; + syn_regs->count_status_reg = edac_reg_offset->drp_ecc_error_status1; + syn_regs->ways_status_reg = edac_reg_offset->drp_ecc_error_status0; + break; + case LLCC_TRAM_CE: + syn_regs->synd_reg = edac_reg_offset->trp_ecc_sb_err_syn0; + syn_regs->count_status_reg = edac_reg_offset->trp_ecc_error_status1; + syn_regs->ways_status_reg = edac_reg_offset->trp_ecc_error_status0; + break; + case LLCC_TRAM_UE: + syn_regs->synd_reg = edac_reg_offset->trp_ecc_db_err_syn0; + syn_regs->count_status_reg = edac_reg_offset->trp_ecc_error_status1; + syn_regs->ways_status_reg = edac_reg_offset->trp_ecc_error_status0; + break; + } +} + /* Dump Syndrome registers data for Tag RAM, Data RAM bit errors*/ static int dump_syn_reg_values(struct llcc_drv_data *drv, u32 bank, int err_type) { struct llcc_edac_reg_data reg_data = edac_reg_data[err_type]; + struct qcom_llcc_syn_regs regs = { }; int err_cnt, err_ways, ret, i; u32 synd_reg, synd_val; + get_reg_offsets(drv, err_type, ®s); + for (i = 0; i < reg_data.reg_cnt; i++) { - synd_reg = reg_data.synd_reg + (i * 4); + synd_reg = regs.synd_reg + (i * 4); ret = regmap_read(drv->regmaps[bank], synd_reg, &synd_val); if (ret) @@ -224,7 +224,7 @@ dump_syn_reg_values(struct llcc_drv_data *drv, u32 bank, int err_type) reg_data.name, i, synd_val); } - ret = regmap_read(drv->regmaps[bank], reg_data.count_status_reg, + ret = regmap_read(drv->regmaps[bank], regs.count_status_reg, &err_cnt); if (ret) goto clear; @@ -234,7 +234,7 @@ dump_syn_reg_values(struct llcc_drv_data *drv, u32 bank, int err_type) edac_printk(KERN_CRIT, EDAC_LLCC, "%s: Error count: 0x%4x\n", reg_data.name, err_cnt); - ret = regmap_read(drv->regmaps[bank], reg_data.ways_status_reg, + ret = regmap_read(drv->regmaps[bank], regs.ways_status_reg, &err_ways); if (ret) goto clear; @@ -295,7 +295,7 @@ static irqreturn_t llcc_ecc_irq_handler(int irq, void *edev_ctl) /* Iterate over the banks and look for Tag RAM or Data RAM errors */ for (i = 0; i < drv->num_banks; i++) { - ret = regmap_read(drv->regmaps[i], DRP_INTERRUPT_STATUS, + ret = regmap_read(drv->regmaps[i], drv->edac_reg_offset->drp_interrupt_status, &drp_error); if (!ret && (drp_error & SB_ECC_ERROR)) { @@ -310,7 +310,7 @@ static irqreturn_t llcc_ecc_irq_handler(int irq, void *edev_ctl) if (!ret) irq_rc = IRQ_HANDLED; - ret = regmap_read(drv->regmaps[i], TRP_INTERRUPT_0_STATUS, + ret = regmap_read(drv->regmaps[i], drv->edac_reg_offset->trp_interrupt_0_status, &trp_error); if (!ret && (trp_error & SB_ECC_ERROR)) { @@ -342,7 +342,7 @@ static int qcom_llcc_edac_probe(struct platform_device *pdev) int ecc_irq; int rc; - rc = qcom_llcc_core_setup(llcc_driv_data->bcast_regmap); + rc = qcom_llcc_core_setup(llcc_driv_data, llcc_driv_data->bcast_regmap); if (rc) return rc; diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index 423220e66026..93417ba1ead4 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -69,9 +69,6 @@ struct llcc_slice_desc { /** * struct llcc_edac_reg_data - llcc edac registers data for each error type * @name: Name of the error - * @synd_reg: Syndrome register address - * @count_status_reg: Status register address to read the error count - * @ways_status_reg: Status register address to read the error ways * @reg_cnt: Number of registers * @count_mask: Mask value to get the error count * @ways_mask: Mask value to get the error ways @@ -80,9 +77,6 @@ struct llcc_slice_desc { */ struct llcc_edac_reg_data { char *name; - u64 synd_reg; - u64 count_status_reg; - u64 ways_status_reg; u32 reg_cnt; u32 count_mask; u32 ways_mask; -- cgit v1.2.3 From 36e4fc57fc1619f462e669e939209c45763bc8f5 Mon Sep 17 00:00:00 2001 From: Akihiro Suda Date: Sun, 28 May 2023 19:36:02 +0200 Subject: efi: Bump stub image version for macOS HVF compatibility The macOS hypervisor framework includes a host-side VMM called VZLinuxBootLoader [1] which implements native support for booting the Linux kernel inside a guest directly (instead of, e.g., via GRUB installed inside the guest). On x86, it incorporates a BIOS style loader that does not implement or expose EFI to the loaded kernel. However, this loader appears to fail when the 'image minor version' field in the kernel image's PE/COFF header (which is generally only used by EFI based bootloaders) is set to any value other than 0x0. [2] Commit e346bebbd36b1576 ("efi: libstub: Always enable initrd command line loader and bump version") incremented the EFI stub image minor version to convey that all EFI stub kernels now implement support for the initrd= command line option, and do so in a way where it can load initrd images from any filesystem known to the EFI firmware (as opposed to prior implementations that could only load initrds from the same volume that the kernel image was loaded from). Unfortunately, bumping the version to v1.1 triggers this issue in VZLinuxBootLoader, breaking the boot on x86. So let's keep the image minor version at 0x0, and bump the image major version instead. While at it, convert this field to a bit field, so that individual features are discoverable from it, as suggested by Linus. So let's bump the major version to v3, and document the initrd= command line loading feature as being represented by bit 1 in the mask. Note that, due to the prior interpretation as a monotonically increasing version field, loaders are still permitted to assume that the LoadFile2 initrd loading feature is supported for any major version value >= 1, even if bit 0 is not set. [1] https://developer.apple.com/documentation/virtualization/vzlinuxbootloader [2] https://lore.kernel.org/linux-efi/CAG8fp8Teu4G9JuenQrqGndFt2Gy+V4YgJ=hN1xX7AD940YKf3A@mail.gmail.com/ Fixes: e346bebbd36b1576 ("efi: libstub: Always enable initrd command ...") Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217485 Signed-off-by: Akihiro Suda [ardb: rewrite comment and commit log] Signed-off-by: Ard Biesheuvel --- include/linux/pe.h | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/pe.h b/include/linux/pe.h index 5e1e11540870..fdf9c95709ba 100644 --- a/include/linux/pe.h +++ b/include/linux/pe.h @@ -11,25 +11,26 @@ #include /* - * Linux EFI stub v1.0 adds the following functionality: - * - Loading initrd from the LINUX_EFI_INITRD_MEDIA_GUID device path, - * - Loading/starting the kernel from firmware that targets a different - * machine type, via the entrypoint exposed in the .compat PE/COFF section. + * Starting from version v3.0, the major version field should be interpreted as + * a bit mask of features supported by the kernel's EFI stub: + * - 0x1: initrd loading from the LINUX_EFI_INITRD_MEDIA_GUID device path, + * - 0x2: initrd loading using the initrd= command line option, where the file + * may be specified using device path notation, and is not required to + * reside on the same volume as the loaded kernel image. * * The recommended way of loading and starting v1.0 or later kernels is to use * the LoadImage() and StartImage() EFI boot services, and expose the initrd * via the LINUX_EFI_INITRD_MEDIA_GUID device path. * - * Versions older than v1.0 support initrd loading via the image load options - * (using initrd=, limited to the volume from which the kernel itself was - * loaded), or via arch specific means (bootparams, DT, etc). + * Versions older than v1.0 may support initrd loading via the image load + * options (using initrd=, limited to the volume from which the kernel itself + * was loaded), or only via arch specific means (bootparams, DT, etc). * - * On x86, LoadImage() and StartImage() can be omitted if the EFI handover - * protocol is implemented, which can be inferred from the version, - * handover_offset and xloadflags fields in the bootparams structure. + * The minor version field must remain 0x0. + * (https://lore.kernel.org/all/efd6f2d4-547c-1378-1faa-53c044dbd297@gmail.com/) */ -#define LINUX_EFISTUB_MAJOR_VERSION 0x1 -#define LINUX_EFISTUB_MINOR_VERSION 0x1 +#define LINUX_EFISTUB_MAJOR_VERSION 0x3 +#define LINUX_EFISTUB_MINOR_VERSION 0x0 /* * LINUX_PE_MAGIC appears at offset 0x38 into the MS-DOS header of EFI bootable -- cgit v1.2.3 From ac2263b588dffd3a1efd7ed0b156ea6c5aea200d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 29 May 2023 06:40:33 -0400 Subject: Revert "module: error out early on concurrent load of the same module file" This reverts commit 9828ed3f695a138f7add89fa2a186ababceb8006. Sadly, it does seem to cause failures to load modules. Johan Hovold reports: "This change breaks module loading during boot on the Lenovo Thinkpad X13s (aarch64). Specifically it results in indefinite probe deferral of the display and USB (ethernet) which makes it a pain to debug. Typing in the dark to acquire some logs reveals that other modules are missing as well" Since this was applied late as a "let's try this", I'm reverting it asap, and we can try to figure out what goes wrong later. The excessive parallel module loading problem is annoying, but not noticeable in normal situations, and this was only meant as an optimistic workaround for a user-space bug. One possible solution may be to do the optimistic exclusive open first, and then use a lock to serialize loading if that fails. Reported-by: Johan Hovold Link: https://lore.kernel.org/lkml/ZHRpH-JXAxA6DnzR@hovoldconsulting.com/ Signed-off-by: Linus Torvalds --- include/linux/fs.h | 6 ------ kernel/module/main.c | 58 ++++++++++++++-------------------------------------- 2 files changed, 15 insertions(+), 49 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 86b50271b4f7..133f0640fb24 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2566,12 +2566,6 @@ static inline int deny_write_access(struct file *file) struct inode *inode = file_inode(file); return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY; } -static inline int exclusive_deny_write_access(struct file *file) -{ - int old = 0; - struct inode *inode = file_inode(file); - return atomic_try_cmpxchg(&inode->i_writecount, &old, -1) ? 0 : -ETXTBSY; -} static inline void put_write_access(struct inode * inode) { atomic_dec(&inode->i_writecount); diff --git a/kernel/module/main.c b/kernel/module/main.c index b4c7e925fdb0..044aa2c9e3cb 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -3057,13 +3057,25 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, return load_module(&info, uargs, 0); } -static int file_init_module(struct file *file, const char __user * uargs, int flags) +SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) { struct load_info info = { }; void *buf = NULL; int len; + int err; + + err = may_init_module(); + if (err) + return err; + + pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags); - len = kernel_read_file(file, 0, &buf, INT_MAX, NULL, + if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS + |MODULE_INIT_IGNORE_VERMAGIC + |MODULE_INIT_COMPRESSED_FILE)) + return -EINVAL; + + len = kernel_read_file_from_fd(fd, 0, &buf, INT_MAX, NULL, READING_MODULE); if (len < 0) { mod_stat_inc(&failed_kreads); @@ -3072,7 +3084,7 @@ static int file_init_module(struct file *file, const char __user * uargs, int fl } if (flags & MODULE_INIT_COMPRESSED_FILE) { - int err = module_decompress(&info, buf, len); + err = module_decompress(&info, buf, len); vfree(buf); /* compressed data is no longer needed */ if (err) { mod_stat_inc(&failed_decompress); @@ -3087,46 +3099,6 @@ static int file_init_module(struct file *file, const char __user * uargs, int fl return load_module(&info, uargs, flags); } -/* - * kernel_read_file() will already deny write access, but module - * loading wants _exclusive_ access to the file, so we do that - * here, along with basic sanity checks. - */ -static int prepare_file_for_module_load(struct file *file) -{ - if (!file || !(file->f_mode & FMODE_READ)) - return -EBADF; - if (!S_ISREG(file_inode(file)->i_mode)) - return -EINVAL; - return exclusive_deny_write_access(file); -} - -SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) -{ - struct fd f; - int err; - - err = may_init_module(); - if (err) - return err; - - pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags); - - if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS - |MODULE_INIT_IGNORE_VERMAGIC - |MODULE_INIT_COMPRESSED_FILE)) - return -EINVAL; - - f = fdget(fd); - err = prepare_file_for_module_load(f.file); - if (!err) { - err = file_init_module(f.file, uargs, flags); - allow_write_access(f.file); - } - fdput(f); - return err; -} - /* Keep in sync with MODULE_FLAGS_BUF_SIZE !!! */ char *module_flags(struct module *mod, char *buf, bool show_state) { -- cgit v1.2.3 From 0143d148d1e882fb1538dc9974c94d63961719b9 Mon Sep 17 00:00:00 2001 From: Ruihan Li Date: Mon, 15 May 2023 21:09:55 +0800 Subject: usb: usbfs: Enforce page requirements for mmap The current implementation of usbdev_mmap uses usb_alloc_coherent to allocate memory pages that will later be mapped into the user space. Meanwhile, usb_alloc_coherent employs three different methods to allocate memory, as outlined below: * If hcd->localmem_pool is non-null, it uses gen_pool_dma_alloc to allocate memory; * If DMA is not available, it uses kmalloc to allocate memory; * Otherwise, it uses dma_alloc_coherent. However, it should be noted that gen_pool_dma_alloc does not guarantee that the resulting memory will be page-aligned. Furthermore, trying to map slab pages (i.e., memory allocated by kmalloc) into the user space is not resonable and can lead to problems, such as a type confusion bug when PAGE_TABLE_CHECK=y [1]. To address these issues, this patch introduces hcd_alloc_coherent_pages, which addresses the above two problems. Specifically, hcd_alloc_coherent_pages uses gen_pool_dma_alloc_align instead of gen_pool_dma_alloc to ensure that the memory is page-aligned. To replace kmalloc, hcd_alloc_coherent_pages directly allocates pages by calling __get_free_pages. Reported-by: syzbot+fcf1a817ceb50935ce99@syzkaller.appspotmail.comm Closes: https://lore.kernel.org/lkml/000000000000258e5e05fae79fc1@google.com/ [1] Fixes: f7d34b445abc ("USB: Add support for usbfs zerocopy.") Fixes: ff2437befd8f ("usb: host: Fix excessive alignment restriction for local memory allocations") Cc: stable@vger.kernel.org Signed-off-by: Ruihan Li Acked-by: Alan Stern Link: https://lore.kernel.org/r/20230515130958.32471-2-lrh2000@pku.edu.cn Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/buffer.c | 41 +++++++++++++++++++++++++++++++++++++++++ drivers/usb/core/devio.c | 9 +++++---- include/linux/usb/hcd.h | 5 +++++ 3 files changed, 51 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/usb/core/buffer.c b/drivers/usb/core/buffer.c index fbb087b728dc..268ccbec88f9 100644 --- a/drivers/usb/core/buffer.c +++ b/drivers/usb/core/buffer.c @@ -172,3 +172,44 @@ void hcd_buffer_free( } dma_free_coherent(hcd->self.sysdev, size, addr, dma); } + +void *hcd_buffer_alloc_pages(struct usb_hcd *hcd, + size_t size, gfp_t mem_flags, dma_addr_t *dma) +{ + if (size == 0) + return NULL; + + if (hcd->localmem_pool) + return gen_pool_dma_alloc_align(hcd->localmem_pool, + size, dma, PAGE_SIZE); + + /* some USB hosts just use PIO */ + if (!hcd_uses_dma(hcd)) { + *dma = DMA_MAPPING_ERROR; + return (void *)__get_free_pages(mem_flags, + get_order(size)); + } + + return dma_alloc_coherent(hcd->self.sysdev, + size, dma, mem_flags); +} + +void hcd_buffer_free_pages(struct usb_hcd *hcd, + size_t size, void *addr, dma_addr_t dma) +{ + if (!addr) + return; + + if (hcd->localmem_pool) { + gen_pool_free(hcd->localmem_pool, + (unsigned long)addr, size); + return; + } + + if (!hcd_uses_dma(hcd)) { + free_pages((unsigned long)addr, get_order(size)); + return; + } + + dma_free_coherent(hcd->self.sysdev, size, addr, dma); +} diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index e501a03d6c70..3936ca7f7d2f 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -186,6 +186,7 @@ static int connected(struct usb_dev_state *ps) static void dec_usb_memory_use_count(struct usb_memory *usbm, int *count) { struct usb_dev_state *ps = usbm->ps; + struct usb_hcd *hcd = bus_to_hcd(ps->dev->bus); unsigned long flags; spin_lock_irqsave(&ps->lock, flags); @@ -194,8 +195,8 @@ static void dec_usb_memory_use_count(struct usb_memory *usbm, int *count) list_del(&usbm->memlist); spin_unlock_irqrestore(&ps->lock, flags); - usb_free_coherent(ps->dev, usbm->size, usbm->mem, - usbm->dma_handle); + hcd_buffer_free_pages(hcd, usbm->size, + usbm->mem, usbm->dma_handle); usbfs_decrease_memory_usage( usbm->size + sizeof(struct usb_memory)); kfree(usbm); @@ -247,8 +248,8 @@ static int usbdev_mmap(struct file *file, struct vm_area_struct *vma) goto error_decrease_mem; } - mem = usb_alloc_coherent(ps->dev, size, GFP_USER | __GFP_NOWARN, - &dma_handle); + mem = hcd_buffer_alloc_pages(hcd, + size, GFP_USER | __GFP_NOWARN, &dma_handle); if (!mem) { ret = -ENOMEM; goto error_free_usbm; diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 094c77eaf455..0c7eff91adf4 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -501,6 +501,11 @@ void *hcd_buffer_alloc(struct usb_bus *bus, size_t size, void hcd_buffer_free(struct usb_bus *bus, size_t size, void *addr, dma_addr_t dma); +void *hcd_buffer_alloc_pages(struct usb_hcd *hcd, + size_t size, gfp_t mem_flags, dma_addr_t *dma); +void hcd_buffer_free_pages(struct usb_hcd *hcd, + size_t size, void *addr, dma_addr_t dma); + /* generic bus glue, needed for host controllers that don't use PCI */ extern irqreturn_t usb_hcd_irq(int irq, void *__hcd); -- cgit v1.2.3 From 44d0fb387b53e56c8a050bac5c7d460e21eb226f Mon Sep 17 00:00:00 2001 From: Ruihan Li Date: Mon, 15 May 2023 21:09:58 +0800 Subject: mm: page_table_check: Ensure user pages are not slab pages The current uses of PageAnon in page table check functions can lead to type confusion bugs between struct page and slab [1], if slab pages are accidentally mapped into the user space. This is because slab reuses the bits in struct page to store its internal states, which renders PageAnon ineffective on slab pages. Since slab pages are not expected to be mapped into the user space, this patch adds BUG_ON(PageSlab(page)) checks to make sure that slab pages are not inadvertently mapped. Otherwise, there must be some bugs in the kernel. Reported-by: syzbot+fcf1a817ceb50935ce99@syzkaller.appspotmail.com Closes: https://lore.kernel.org/lkml/000000000000258e5e05fae79fc1@google.com/ [1] Fixes: df4e817b7108 ("mm: page table check") Cc: # 5.17 Signed-off-by: Ruihan Li Acked-by: Pasha Tatashin Link: https://lore.kernel.org/r/20230515130958.32471-5-lrh2000@pku.edu.cn Signed-off-by: Greg Kroah-Hartman --- include/linux/page-flags.h | 6 ++++++ mm/page_table_check.c | 6 ++++++ 2 files changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 1c68d67b832f..92a2063a0a23 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -617,6 +617,12 @@ PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted) * Please note that, confusingly, "page_mapping" refers to the inode * address_space which maps the page from disk; whereas "page_mapped" * refers to user virtual address space into which the page is mapped. + * + * For slab pages, since slab reuses the bits in struct page to store its + * internal states, the page->mapping does not exist as such, nor do these + * flags below. So in order to avoid testing non-existent bits, please + * make sure that PageSlab(page) actually evaluates to false before calling + * the following functions (e.g., PageAnon). See mm/slab.h. */ #define PAGE_MAPPING_ANON 0x1 #define PAGE_MAPPING_MOVABLE 0x2 diff --git a/mm/page_table_check.c b/mm/page_table_check.c index 25d8610c0042..f2baf97d5f38 100644 --- a/mm/page_table_check.c +++ b/mm/page_table_check.c @@ -71,6 +71,8 @@ static void page_table_check_clear(struct mm_struct *mm, unsigned long addr, page = pfn_to_page(pfn); page_ext = page_ext_get(page); + + BUG_ON(PageSlab(page)); anon = PageAnon(page); for (i = 0; i < pgcnt; i++) { @@ -107,6 +109,8 @@ static void page_table_check_set(struct mm_struct *mm, unsigned long addr, page = pfn_to_page(pfn); page_ext = page_ext_get(page); + + BUG_ON(PageSlab(page)); anon = PageAnon(page); for (i = 0; i < pgcnt; i++) { @@ -133,6 +137,8 @@ void __page_table_check_zero(struct page *page, unsigned int order) struct page_ext *page_ext; unsigned long i; + BUG_ON(PageSlab(page)); + page_ext = page_ext_get(page); BUG_ON(!page_ext); for (i = 0; i < (1ul << order); i++) { -- cgit v1.2.3 From 4faeee0cf8a5d88d63cdbc3bab124fb0e6aed08c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 26 May 2023 16:34:58 +0000 Subject: tcp: deny tcp_disconnect() when threads are waiting Historically connect(AF_UNSPEC) has been abused by syzkaller and other fuzzers to trigger various bugs. A recent one triggers a divide-by-zero [1], and Paolo Abeni was able to diagnose the issue. tcp_recvmsg_locked() has tests about sk_state being not TCP_LISTEN and TCP REPAIR mode being not used. Then later if socket lock is released in sk_wait_data(), another thread can call connect(AF_UNSPEC), then make this socket a TCP listener. When recvmsg() is resumed, it can eventually call tcp_cleanup_rbuf() and attempt a divide by 0 in tcp_rcv_space_adjust() [1] This patch adds a new socket field, counting number of threads blocked in sk_wait_event() and inet_wait_for_connect(). If this counter is not zero, tcp_disconnect() returns an error. This patch adds code in blocking socket system calls, thus should not hurt performance of non blocking ones. Note that we probably could revert commit 499350a5a6e7 ("tcp: initialize rcv_mss to TCP_MIN_MSS instead of 0") to restore original tcpi_rcv_mss meaning (was 0 if no payload was ever received on a socket) [1] divide error: 0000 [#1] PREEMPT SMP KASAN CPU: 0 PID: 13832 Comm: syz-executor.5 Not tainted 6.3.0-rc4-syzkaller-00224-g00c7b5f4ddc5 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/02/2023 RIP: 0010:tcp_rcv_space_adjust+0x36e/0x9d0 net/ipv4/tcp_input.c:740 Code: 00 00 00 00 fc ff df 4c 89 64 24 48 8b 44 24 04 44 89 f9 41 81 c7 80 03 00 00 c1 e1 04 44 29 f0 48 63 c9 48 01 e9 48 0f af c1 <49> f7 f6 48 8d 04 41 48 89 44 24 40 48 8b 44 24 30 48 c1 e8 03 48 RSP: 0018:ffffc900033af660 EFLAGS: 00010206 RAX: 4a66b76cbade2c48 RBX: ffff888076640cc0 RCX: 00000000c334e4ac RDX: 0000000000000000 RSI: dffffc0000000000 RDI: 0000000000000001 RBP: 00000000c324e86c R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8880766417f8 R13: ffff888028fbb980 R14: 0000000000000000 R15: 0000000000010344 FS: 00007f5bffbfe700(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b32f25000 CR3: 000000007ced0000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: tcp_recvmsg_locked+0x100e/0x22e0 net/ipv4/tcp.c:2616 tcp_recvmsg+0x117/0x620 net/ipv4/tcp.c:2681 inet6_recvmsg+0x114/0x640 net/ipv6/af_inet6.c:670 sock_recvmsg_nosec net/socket.c:1017 [inline] sock_recvmsg+0xe2/0x160 net/socket.c:1038 ____sys_recvmsg+0x210/0x5a0 net/socket.c:2720 ___sys_recvmsg+0xf2/0x180 net/socket.c:2762 do_recvmmsg+0x25e/0x6e0 net/socket.c:2856 __sys_recvmmsg net/socket.c:2935 [inline] __do_sys_recvmmsg net/socket.c:2958 [inline] __se_sys_recvmmsg net/socket.c:2951 [inline] __x64_sys_recvmmsg+0x20f/0x260 net/socket.c:2951 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f5c0108c0f9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 f1 19 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f5bffbfe168 EFLAGS: 00000246 ORIG_RAX: 000000000000012b RAX: ffffffffffffffda RBX: 00007f5c011ac050 RCX: 00007f5c0108c0f9 RDX: 0000000000000001 RSI: 0000000020000bc0 RDI: 0000000000000003 RBP: 00007f5c010e7b39 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000122 R11: 0000000000000246 R12: 0000000000000000 R13: 00007f5c012cfb1f R14: 00007f5bffbfe300 R15: 0000000000022000 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot Reported-by: Paolo Abeni Diagnosed-by: Paolo Abeni Signed-off-by: Eric Dumazet Tested-by: Paolo Abeni Link: https://lore.kernel.org/r/20230526163458.2880232-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/net/sock.h | 4 ++++ net/ipv4/af_inet.c | 2 ++ net/ipv4/inet_connection_sock.c | 1 + net/ipv4/tcp.c | 6 ++++++ 4 files changed, 13 insertions(+) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 656ea89f60ff..b418425d7230 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -336,6 +336,7 @@ struct sk_filter; * @sk_cgrp_data: cgroup data for this cgroup * @sk_memcg: this socket's memory cgroup association * @sk_write_pending: a write to stream socket waits to start + * @sk_wait_pending: number of threads blocked on this socket * @sk_state_change: callback to indicate change in the state of the sock * @sk_data_ready: callback to indicate there is data to be processed * @sk_write_space: callback to indicate there is bf sending space available @@ -428,6 +429,7 @@ struct sock { unsigned int sk_napi_id; #endif int sk_rcvbuf; + int sk_wait_pending; struct sk_filter __rcu *sk_filter; union { @@ -1174,6 +1176,7 @@ static inline void sock_rps_reset_rxhash(struct sock *sk) #define sk_wait_event(__sk, __timeo, __condition, __wait) \ ({ int __rc; \ + __sk->sk_wait_pending++; \ release_sock(__sk); \ __rc = __condition; \ if (!__rc) { \ @@ -1183,6 +1186,7 @@ static inline void sock_rps_reset_rxhash(struct sock *sk) } \ sched_annotate_sleep(); \ lock_sock(__sk); \ + __sk->sk_wait_pending--; \ __rc = __condition; \ __rc; \ }) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index c4aab3aacbd8..4a76ebf793b8 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -586,6 +586,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending += writebias; + sk->sk_wait_pending++; /* Basic assumption: if someone sets sk->sk_err, he _must_ * change state of the socket from TCP_SYN_*. @@ -601,6 +602,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) } remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending -= writebias; + sk->sk_wait_pending--; return timeo; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 65ad4251f6fd..1386787eaf1a 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1142,6 +1142,7 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, if (newsk) { struct inet_connection_sock *newicsk = inet_csk(newsk); + newsk->sk_wait_pending = 0; inet_sk_set_state(newsk, TCP_SYN_RECV); newicsk->icsk_bind_hash = NULL; newicsk->icsk_bind2_hash = NULL; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index a60f6f4e7cd9..635607ac37e4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3081,6 +3081,12 @@ int tcp_disconnect(struct sock *sk, int flags) int old_state = sk->sk_state; u32 seq; + /* Deny disconnect if other threads are blocked in sk_wait_event() + * or inet_wait_for_connect(). + */ + if (sk->sk_wait_pending) + return -EBUSY; + if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); -- cgit v1.2.3 From ed08d937eaa4f18aa26e47fe6b937205a4745045 Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Thu, 25 May 2023 22:50:41 +0200 Subject: platform/surface: aggregator: Make to_ssam_device_driver() respect constness Make to_ssam_device_driver() a bit safer by replacing container_of() with container_of_const() to respect the constness of the passed in pointer, instead of silently discarding any const specifications. This change also makes it more similar to to_ssam_device(), which already uses container_of_const(). Signed-off-by: Maximilian Luz Link: https://lore.kernel.org/r/20230525205041.2774947-1-luzmaximilian@gmail.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- include/linux/surface_aggregator/device.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/surface_aggregator/device.h b/include/linux/surface_aggregator/device.h index df81043b9e71..42b249b4c24b 100644 --- a/include/linux/surface_aggregator/device.h +++ b/include/linux/surface_aggregator/device.h @@ -243,11 +243,7 @@ static inline bool is_ssam_device(struct device *d) * Return: Returns the pointer to the &struct ssam_device_driver wrapping the * given device driver @d. */ -static inline -struct ssam_device_driver *to_ssam_device_driver(struct device_driver *d) -{ - return container_of(d, struct ssam_device_driver, driver); -} +#define to_ssam_device_driver(d) container_of_const(d, struct ssam_device_driver, driver) const struct ssam_device_id *ssam_device_id_match(const struct ssam_device_id *table, const struct ssam_device_uid uid); -- cgit v1.2.3 From 1919b39fc6eabb9a6f9a51706ff6d03865f5df29 Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Fri, 26 May 2023 08:38:57 -0700 Subject: net: mana: Fix perf regression: remove rx_cqes, tx_cqes counters The apc->eth_stats.rx_cqes is one per NIC (vport), and it's on the frequent and parallel code path of all queues. So, r/w into this single shared variable by many threads on different CPUs creates a lot caching and memory overhead, hence perf regression. And, it's not accurate due to the high volume concurrent r/w. For example, a workload is iperf with 128 threads, and with RPS enabled. We saw perf regression of 25% with the previous patch adding the counters. And this patch eliminates the regression. Since the error path of mana_poll_rx_cq() already has warnings, so keeping the counter and convert it to a per-queue variable is not necessary. So, just remove this counter from this high frequency code path. Also, remove the tx_cqes counter for the same reason. We have warnings & other counters for errors on that path, and don't need to count every normal cqe processing. Cc: stable@vger.kernel.org Fixes: bd7fc6e1957c ("net: mana: Add new MANA VF performance counters for easier troubleshooting") Signed-off-by: Haiyang Zhang Reviewed-by: Horatiu Vultur Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/1685115537-31675-1-git-send-email-haiyangz@microsoft.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/microsoft/mana/mana_en.c | 10 ---------- drivers/net/ethernet/microsoft/mana/mana_ethtool.c | 2 -- include/net/mana/mana.h | 2 -- 3 files changed, 14 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 06d6292e09b3..d907727c7b7a 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -1279,8 +1279,6 @@ static void mana_poll_tx_cq(struct mana_cq *cq) if (comp_read < 1) return; - apc->eth_stats.tx_cqes = comp_read; - for (i = 0; i < comp_read; i++) { struct mana_tx_comp_oob *cqe_oob; @@ -1363,8 +1361,6 @@ static void mana_poll_tx_cq(struct mana_cq *cq) WARN_ON_ONCE(1); cq->work_done = pkt_transmitted; - - apc->eth_stats.tx_cqes -= pkt_transmitted; } static void mana_post_pkt_rxq(struct mana_rxq *rxq) @@ -1626,15 +1622,11 @@ static void mana_poll_rx_cq(struct mana_cq *cq) { struct gdma_comp *comp = cq->gdma_comp_buf; struct mana_rxq *rxq = cq->rxq; - struct mana_port_context *apc; int comp_read, i; - apc = netdev_priv(rxq->ndev); - comp_read = mana_gd_poll_cq(cq->gdma_cq, comp, CQE_POLLING_BUFFER); WARN_ON_ONCE(comp_read > CQE_POLLING_BUFFER); - apc->eth_stats.rx_cqes = comp_read; rxq->xdp_flush = false; for (i = 0; i < comp_read; i++) { @@ -1646,8 +1638,6 @@ static void mana_poll_rx_cq(struct mana_cq *cq) return; mana_process_rx_cqe(rxq, cq, &comp[i]); - - apc->eth_stats.rx_cqes--; } if (rxq->xdp_flush) diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index a64c81410dc1..0dc78679f620 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -13,11 +13,9 @@ static const struct { } mana_eth_stats[] = { {"stop_queue", offsetof(struct mana_ethtool_stats, stop_queue)}, {"wake_queue", offsetof(struct mana_ethtool_stats, wake_queue)}, - {"tx_cqes", offsetof(struct mana_ethtool_stats, tx_cqes)}, {"tx_cq_err", offsetof(struct mana_ethtool_stats, tx_cqe_err)}, {"tx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, tx_cqe_unknown_type)}, - {"rx_cqes", offsetof(struct mana_ethtool_stats, rx_cqes)}, {"rx_coalesced_err", offsetof(struct mana_ethtool_stats, rx_coalesced_err)}, {"rx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index cd386aa7c7cc..9eef19972845 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -347,10 +347,8 @@ struct mana_tx_qp { struct mana_ethtool_stats { u64 stop_queue; u64 wake_queue; - u64 tx_cqes; u64 tx_cqe_err; u64 tx_cqe_unknown_type; - u64 rx_cqes; u64 rx_coalesced_err; u64 rx_cqe_unknown_type; }; -- cgit v1.2.3 From c034203b6a9dae6751ef4371c18cb77983e30c28 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 29 May 2023 14:35:55 +0300 Subject: nfsd: fix double fget() bug in __write_ports_addfd() The bug here is that you cannot rely on getting the same socket from multiple calls to fget() because userspace can influence that. This is a kind of double fetch bug. The fix is to delete the svc_alien_sock() function and instead do the checking inside the svc_addsock() function. Fixes: 3064639423c4 ("nfsd: check passed socket's net matches NFSd superblock's one") Signed-off-by: Dan Carpenter Reviewed-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/nfsd/nfsctl.c | 7 +------ include/linux/sunrpc/svcsock.h | 7 +++---- net/sunrpc/svcsock.c | 24 ++++++------------------ 3 files changed, 10 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index c159817d1282..b4fd7a7062d5 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -690,16 +690,11 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred if (err != 0 || fd < 0) return -EINVAL; - if (svc_alien_sock(net, fd)) { - printk(KERN_ERR "%s: socket net is different to NFSd's one\n", __func__); - return -EINVAL; - } - err = nfsd_create_serv(net); if (err != 0) return err; - err = svc_addsock(nn->nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); + err = svc_addsock(nn->nfsd_serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); if (err >= 0 && !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index d16ae621782c..a7116048a4d4 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -61,10 +61,9 @@ int svc_recv(struct svc_rqst *, long); void svc_send(struct svc_rqst *rqstp); void svc_drop(struct svc_rqst *); void svc_sock_update_bufs(struct svc_serv *serv); -bool svc_alien_sock(struct net *net, int fd); -int svc_addsock(struct svc_serv *serv, const int fd, - char *name_return, const size_t len, - const struct cred *cred); +int svc_addsock(struct svc_serv *serv, struct net *net, + const int fd, char *name_return, const size_t len, + const struct cred *cred); void svc_init_xprt_sock(void); void svc_cleanup_xprt_sock(void); struct svc_xprt *svc_sock_create(struct svc_serv *serv, int prot); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 63fe7a338992..f77cebe2c071 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1480,25 +1480,10 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, return svsk; } -bool svc_alien_sock(struct net *net, int fd) -{ - int err; - struct socket *sock = sockfd_lookup(fd, &err); - bool ret = false; - - if (!sock) - goto out; - if (sock_net(sock->sk) != net) - ret = true; - sockfd_put(sock); -out: - return ret; -} -EXPORT_SYMBOL_GPL(svc_alien_sock); - /** * svc_addsock - add a listener socket to an RPC service * @serv: pointer to RPC service to which to add a new listener + * @net: caller's network namespace * @fd: file descriptor of the new listener * @name_return: pointer to buffer to fill in with name of listener * @len: size of the buffer @@ -1508,8 +1493,8 @@ EXPORT_SYMBOL_GPL(svc_alien_sock); * Name is terminated with '\n'. On error, returns a negative errno * value. */ -int svc_addsock(struct svc_serv *serv, const int fd, char *name_return, - const size_t len, const struct cred *cred) +int svc_addsock(struct svc_serv *serv, struct net *net, const int fd, + char *name_return, const size_t len, const struct cred *cred) { int err = 0; struct socket *so = sockfd_lookup(fd, &err); @@ -1520,6 +1505,9 @@ int svc_addsock(struct svc_serv *serv, const int fd, char *name_return, if (!so) return err; + err = -EINVAL; + if (sock_net(so->sk) != net) + goto out; err = -EAFNOSUPPORT; if ((so->sk->sk_family != PF_INET) && (so->sk->sk_family != PF_INET6)) goto out; -- cgit v1.2.3 From 30c6f0bf9579debce27e45fac34fdc97e46acacc Mon Sep 17 00:00:00 2001 From: fuyuanli Date: Wed, 31 May 2023 16:01:50 +0800 Subject: tcp: fix mishandling when the sack compression is deferred. In this patch, we mainly try to handle sending a compressed ack correctly if it's deferred. Here are more details in the old logic: When sack compression is triggered in the tcp_compressed_ack_kick(), if the sock is owned by user, it will set TCP_DELACK_TIMER_DEFERRED and then defer to the release cb phrase. Later once user releases the sock, tcp_delack_timer_handler() should send a ack as expected, which, however, cannot happen due to lack of ICSK_ACK_TIMER flag. Therefore, the receiver would not sent an ack until the sender's retransmission timeout. It definitely increases unnecessary latency. Fixes: 5d9f4262b7ea ("tcp: add SACK compression") Suggested-by: Eric Dumazet Signed-off-by: fuyuanli Signed-off-by: Jason Xing Link: https://lore.kernel.org/netdev/20230529113804.GA20300@didi-ThinkCentre-M920t-N000/ Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230531080150.GA20424@didi-ThinkCentre-M920t-N000 Signed-off-by: Paolo Abeni --- include/net/tcp.h | 1 + net/ipv4/tcp_input.c | 2 +- net/ipv4/tcp_timer.c | 16 +++++++++++++--- 3 files changed, 15 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 18a038d16434..5066e4586cf0 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -632,6 +632,7 @@ void tcp_reset(struct sock *sk, struct sk_buff *skb); void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb); void tcp_fin(struct sock *sk); void tcp_check_space(struct sock *sk); +void tcp_sack_compress_send_ack(struct sock *sk); /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 61b6710f337a..bf8b22218dd4 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4530,7 +4530,7 @@ static void tcp_sack_maybe_coalesce(struct tcp_sock *tp) } } -static void tcp_sack_compress_send_ack(struct sock *sk) +void tcp_sack_compress_send_ack(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index b839c2f91292..39eb947fe392 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -290,9 +290,19 @@ static int tcp_write_timeout(struct sock *sk) void tcp_delack_timer_handler(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); - if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || - !(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) + if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) + return; + + /* Handling the sack compression case */ + if (tp->compressed_ack) { + tcp_mstamp_refresh(tp); + tcp_sack_compress_send_ack(sk); + return; + } + + if (!(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) return; if (time_after(icsk->icsk_ack.timeout, jiffies)) { @@ -312,7 +322,7 @@ void tcp_delack_timer_handler(struct sock *sk) inet_csk_exit_pingpong_mode(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; } - tcp_mstamp_refresh(tcp_sk(sk)); + tcp_mstamp_refresh(tp); tcp_send_ack(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS); } -- cgit v1.2.3 From 4420528254153189c70b6267593e445dc8654e37 Mon Sep 17 00:00:00 2001 From: Gustavo A. R. Silva Date: Mon, 29 May 2023 12:52:07 -0600 Subject: firewire: Replace zero-length array with flexible-array member Zero-length and one-element arrays are deprecated, and we are moving towards adopting C99 flexible-array members, instead. Address the following warnings found with GCC-13 and -fstrict-flex-arrays=3 enabled: sound/firewire/amdtp-stream.c: In function ‘build_it_pkt_header’: sound/firewire/amdtp-stream.c:694:17: warning: ‘generate_cip_header’ accessing 8 bytes in a region of size 0 [-Wstringop-overflow=] 694 | generate_cip_header(s, cip_header, data_block_counter, syt); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ sound/firewire/amdtp-stream.c:694:17: note: referencing argument 2 of type ‘__be32[2]’ {aka ‘unsigned int[2]’} sound/firewire/amdtp-stream.c:667:13: note: in a call to function ‘generate_cip_header’ 667 | static void generate_cip_header(struct amdtp_stream *s, __be32 cip_header[2], | ^~~~~~~~~~~~~~~~~~~ This helps with the ongoing efforts to tighten the FORTIFY_SOURCE routines on memcpy() and help us make progress towards globally enabling -fstrict-flex-arrays=3 [1]. Link: https://github.com/KSPP/linux/issues/21 Link: https://github.com/KSPP/linux/issues/303 Link: https://gcc.gnu.org/pipermail/gcc-patches/2022-October/602902.html [1] Signed-off-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/ZHT0V3SpvHyxCv5W@work Signed-off-by: Takashi Sakamoto --- include/linux/firewire.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 1716c01c4e54..efb6e2cf2034 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -391,7 +391,7 @@ struct fw_iso_packet { u32 tag:2; /* tx: Tag in packet header */ u32 sy:4; /* tx: Sy in packet header */ u32 header_length:8; /* Length of immediate header */ - u32 header[0]; /* tx: Top of 1394 isoch. data_block */ + u32 header[]; /* tx: Top of 1394 isoch. data_block */ }; #define FW_ISO_CONTEXT_TRANSMIT 0 -- cgit v1.2.3 From f9010dbdce911ee1f1af1398a24b1f9f992e0080 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Thu, 1 Jun 2023 13:32:32 -0500 Subject: fork, vhost: Use CLONE_THREAD to fix freezer/ps regression When switching from kthreads to vhost_tasks two bugs were added: 1. The vhost worker tasks's now show up as processes so scripts doing ps or ps a would not incorrectly detect the vhost task as another process. 2. kthreads disabled freeze by setting PF_NOFREEZE, but vhost tasks's didn't disable or add support for them. To fix both bugs, this switches the vhost task to be thread in the process that does the VHOST_SET_OWNER ioctl, and has vhost_worker call get_signal to support SIGKILL/SIGSTOP and freeze signals. Note that SIGKILL/STOP support is required because CLONE_THREAD requires CLONE_SIGHAND which requires those 2 signals to be supported. This is a modified version of the patch written by Mike Christie which was a modified version of patch originally written by Linus. Much of what depended upon PF_IO_WORKER now depends on PF_USER_WORKER. Including ignoring signals, setting up the register state, and having get_signal return instead of calling do_group_exit. Tidied up the vhost_task abstraction so that the definition of vhost_task only needs to be visible inside of vhost_task.c. Making it easier to review the code and tell what needs to be done where. As part of this the main loop has been moved from vhost_worker into vhost_task_fn. vhost_worker now returns true if work was done. The main loop has been updated to call get_signal which handles SIGSTOP, freezing, and collects the message that tells the thread to exit as part of process exit. This collection clears __fatal_signal_pending. This collection is not guaranteed to clear signal_pending() so clear that explicitly so the schedule() sleeps. For now the vhost thread continues to exist and run work until the last file descriptor is closed and the release function is called as part of freeing struct file. To avoid hangs in the coredump rendezvous and when killing threads in a multi-threaded exec. The coredump code and de_thread have been modified to ignore vhost threads. Remvoing the special case for exec appears to require teaching vhost_dev_flush how to directly complete transactions in case the vhost thread is no longer running. Removing the special case for coredump rendezvous requires either the above fix needed for exec or moving the coredump rendezvous into get_signal. Fixes: 6e890c5d5021 ("vhost: use vhost_tasks for worker threads") Signed-off-by: Eric W. Biederman Co-developed-by: Mike Christie Signed-off-by: Mike Christie Acked-by: Michael S. Tsirkin Signed-off-by: Linus Torvalds --- arch/x86/include/asm/fpu/sched.h | 2 +- arch/x86/kernel/fpu/context.h | 2 +- arch/x86/kernel/fpu/core.c | 2 +- drivers/vhost/vhost.c | 22 +++------- fs/coredump.c | 4 +- include/linux/sched/task.h | 1 - include/linux/sched/vhost_task.h | 15 ++----- kernel/exit.c | 5 ++- kernel/fork.c | 13 +++--- kernel/signal.c | 8 ++-- kernel/vhost_task.c | 92 ++++++++++++++++++++++++++-------------- 11 files changed, 89 insertions(+), 77 deletions(-) (limited to 'include') diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h index c2d6cd78ed0c..78fcde7b1f07 100644 --- a/arch/x86/include/asm/fpu/sched.h +++ b/arch/x86/include/asm/fpu/sched.h @@ -39,7 +39,7 @@ extern void fpu_flush_thread(void); static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) { if (cpu_feature_enabled(X86_FEATURE_FPU) && - !(current->flags & (PF_KTHREAD | PF_IO_WORKER))) { + !(current->flags & (PF_KTHREAD | PF_USER_WORKER))) { save_fpregs_to_fpstate(old_fpu); /* * The save operation preserved register state, so the diff --git a/arch/x86/kernel/fpu/context.h b/arch/x86/kernel/fpu/context.h index 9fcfa5c4dad7..af5cbdd9bd29 100644 --- a/arch/x86/kernel/fpu/context.h +++ b/arch/x86/kernel/fpu/context.h @@ -57,7 +57,7 @@ static inline void fpregs_restore_userregs(void) struct fpu *fpu = ¤t->thread.fpu; int cpu = smp_processor_id(); - if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_IO_WORKER))) + if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_USER_WORKER))) return; if (!fpregs_state_valid(fpu, cpu)) { diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index caf33486dc5e..1015af1ae562 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -426,7 +426,7 @@ void kernel_fpu_begin_mask(unsigned int kfpu_mask) this_cpu_write(in_kernel_fpu, true); - if (!(current->flags & (PF_KTHREAD | PF_IO_WORKER)) && + if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER)) && !test_thread_flag(TIF_NEED_FPU_LOAD)) { set_thread_flag(TIF_NEED_FPU_LOAD); save_fpregs_to_fpstate(¤t->thread.fpu); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index a92af08e7864..074273020849 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -256,7 +256,7 @@ void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work) * test_and_set_bit() implies a memory barrier. */ llist_add(&work->node, &dev->worker->work_list); - wake_up_process(dev->worker->vtsk->task); + vhost_task_wake(dev->worker->vtsk); } } EXPORT_SYMBOL_GPL(vhost_work_queue); @@ -333,31 +333,19 @@ static void vhost_vq_reset(struct vhost_dev *dev, __vhost_vq_meta_reset(vq); } -static int vhost_worker(void *data) +static bool vhost_worker(void *data) { struct vhost_worker *worker = data; struct vhost_work *work, *work_next; struct llist_node *node; - for (;;) { - /* mb paired w/ kthread_stop */ - set_current_state(TASK_INTERRUPTIBLE); - - if (vhost_task_should_stop(worker->vtsk)) { - __set_current_state(TASK_RUNNING); - break; - } - - node = llist_del_all(&worker->work_list); - if (!node) - schedule(); - + node = llist_del_all(&worker->work_list); + if (node) { node = llist_reverse_order(node); /* make sure flag is seen after deletion */ smp_wmb(); llist_for_each_entry_safe(work, work_next, node, node) { clear_bit(VHOST_WORK_QUEUED, &work->flags); - __set_current_state(TASK_RUNNING); kcov_remote_start_common(worker->kcov_handle); work->fn(work); kcov_remote_stop(); @@ -365,7 +353,7 @@ static int vhost_worker(void *data) } } - return 0; + return !!node; } static void vhost_vq_free_iovecs(struct vhost_virtqueue *vq) diff --git a/fs/coredump.c b/fs/coredump.c index ece7badf701b..88740c51b942 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -371,7 +371,9 @@ static int zap_process(struct task_struct *start, int exit_code) if (t != current && !(t->flags & PF_POSTCOREDUMP)) { sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); - nr++; + /* The vhost_worker does not particpate in coredumps */ + if ((t->flags & (PF_USER_WORKER | PF_IO_WORKER)) != PF_USER_WORKER) + nr++; } } diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 537cbf9a2ade..e0f5ac90a228 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -29,7 +29,6 @@ struct kernel_clone_args { u32 io_thread:1; u32 user_worker:1; u32 no_files:1; - u32 ignore_signals:1; unsigned long stack; unsigned long stack_size; unsigned long tls; diff --git a/include/linux/sched/vhost_task.h b/include/linux/sched/vhost_task.h index 6123c10b99cf..837a23624a66 100644 --- a/include/linux/sched/vhost_task.h +++ b/include/linux/sched/vhost_task.h @@ -2,22 +2,13 @@ #ifndef _LINUX_VHOST_TASK_H #define _LINUX_VHOST_TASK_H -#include -struct task_struct; +struct vhost_task; -struct vhost_task { - int (*fn)(void *data); - void *data; - struct completion exited; - unsigned long flags; - struct task_struct *task; -}; - -struct vhost_task *vhost_task_create(int (*fn)(void *), void *arg, +struct vhost_task *vhost_task_create(bool (*fn)(void *), void *arg, const char *name); void vhost_task_start(struct vhost_task *vtsk); void vhost_task_stop(struct vhost_task *vtsk); -bool vhost_task_should_stop(struct vhost_task *vtsk); +void vhost_task_wake(struct vhost_task *vtsk); #endif diff --git a/kernel/exit.c b/kernel/exit.c index 34b90e2e7cf7..edb50b4c9972 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -411,7 +411,10 @@ static void coredump_task_exit(struct task_struct *tsk) tsk->flags |= PF_POSTCOREDUMP; core_state = tsk->signal->core_state; spin_unlock_irq(&tsk->sighand->siglock); - if (core_state) { + + /* The vhost_worker does not particpate in coredumps */ + if (core_state && + ((tsk->flags & (PF_IO_WORKER | PF_USER_WORKER)) != PF_USER_WORKER)) { struct core_thread self; self.task = current; diff --git a/kernel/fork.c b/kernel/fork.c index ed4e01daccaa..81cba91f30bb 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2336,16 +2336,16 @@ __latent_entropy struct task_struct *copy_process( p->flags &= ~PF_KTHREAD; if (args->kthread) p->flags |= PF_KTHREAD; - if (args->user_worker) - p->flags |= PF_USER_WORKER; - if (args->io_thread) { + if (args->user_worker) { /* - * Mark us an IO worker, and block any signal that isn't + * Mark us a user worker, and block any signal that isn't * fatal or STOP */ - p->flags |= PF_IO_WORKER; + p->flags |= PF_USER_WORKER; siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); } + if (args->io_thread) + p->flags |= PF_IO_WORKER; if (args->name) strscpy_pad(p->comm, args->name, sizeof(p->comm)); @@ -2517,9 +2517,6 @@ __latent_entropy struct task_struct *copy_process( if (retval) goto bad_fork_cleanup_io; - if (args->ignore_signals) - ignore_signals(p); - stackleak_task_init(p); if (pid != &init_struct_pid) { diff --git a/kernel/signal.c b/kernel/signal.c index 8f6330f0e9ca..2547fa73bde5 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1368,7 +1368,9 @@ int zap_other_threads(struct task_struct *p) while_each_thread(p, t) { task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); - count++; + /* Don't require de_thread to wait for the vhost_worker */ + if ((t->flags & (PF_IO_WORKER | PF_USER_WORKER)) != PF_USER_WORKER) + count++; /* Don't bother with already dead threads */ if (t->exit_state) @@ -2861,11 +2863,11 @@ relock: } /* - * PF_IO_WORKER threads will catch and exit on fatal signals + * PF_USER_WORKER threads will catch and exit on fatal signals * themselves. They have cleanup that must be performed, so * we cannot call do_exit() on their behalf. */ - if (current->flags & PF_IO_WORKER) + if (current->flags & PF_USER_WORKER) goto out; /* diff --git a/kernel/vhost_task.c b/kernel/vhost_task.c index b7cbd66f889e..f80d5c51ae67 100644 --- a/kernel/vhost_task.c +++ b/kernel/vhost_task.c @@ -12,58 +12,88 @@ enum vhost_task_flags { VHOST_TASK_FLAGS_STOP, }; +struct vhost_task { + bool (*fn)(void *data); + void *data; + struct completion exited; + unsigned long flags; + struct task_struct *task; +}; + static int vhost_task_fn(void *data) { struct vhost_task *vtsk = data; - int ret; + bool dead = false; + + for (;;) { + bool did_work; + + /* mb paired w/ vhost_task_stop */ + if (test_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags)) + break; + + if (!dead && signal_pending(current)) { + struct ksignal ksig; + /* + * Calling get_signal will block in SIGSTOP, + * or clear fatal_signal_pending, but remember + * what was set. + * + * This thread won't actually exit until all + * of the file descriptors are closed, and + * the release function is called. + */ + dead = get_signal(&ksig); + if (dead) + clear_thread_flag(TIF_SIGPENDING); + } + + did_work = vtsk->fn(vtsk->data); + if (!did_work) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + } + } - ret = vtsk->fn(vtsk->data); complete(&vtsk->exited); - do_exit(ret); + do_exit(0); +} + +/** + * vhost_task_wake - wakeup the vhost_task + * @vtsk: vhost_task to wake + * + * wake up the vhost_task worker thread + */ +void vhost_task_wake(struct vhost_task *vtsk) +{ + wake_up_process(vtsk->task); } +EXPORT_SYMBOL_GPL(vhost_task_wake); /** * vhost_task_stop - stop a vhost_task * @vtsk: vhost_task to stop * - * Callers must call vhost_task_should_stop and return from their worker - * function when it returns true; + * vhost_task_fn ensures the worker thread exits after + * VHOST_TASK_FLAGS_SOP becomes true. */ void vhost_task_stop(struct vhost_task *vtsk) { - pid_t pid = vtsk->task->pid; - set_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags); - wake_up_process(vtsk->task); + vhost_task_wake(vtsk); /* * Make sure vhost_task_fn is no longer accessing the vhost_task before - * freeing it below. If userspace crashed or exited without closing, - * then the vhost_task->task could already be marked dead so - * kernel_wait will return early. + * freeing it below. */ wait_for_completion(&vtsk->exited); - /* - * If we are just closing/removing a device and the parent process is - * not exiting then reap the task. - */ - kernel_wait4(pid, NULL, __WCLONE, NULL); kfree(vtsk); } EXPORT_SYMBOL_GPL(vhost_task_stop); /** - * vhost_task_should_stop - should the vhost task return from the work function - * @vtsk: vhost_task to stop - */ -bool vhost_task_should_stop(struct vhost_task *vtsk) -{ - return test_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags); -} -EXPORT_SYMBOL_GPL(vhost_task_should_stop); - -/** - * vhost_task_create - create a copy of a process to be used by the kernel - * @fn: thread stack + * vhost_task_create - create a copy of a task to be used by the kernel + * @fn: vhost worker function * @arg: data to be passed to fn * @name: the thread's name * @@ -71,17 +101,17 @@ EXPORT_SYMBOL_GPL(vhost_task_should_stop); * failure. The returned task is inactive, and the caller must fire it up * through vhost_task_start(). */ -struct vhost_task *vhost_task_create(int (*fn)(void *), void *arg, +struct vhost_task *vhost_task_create(bool (*fn)(void *), void *arg, const char *name) { struct kernel_clone_args args = { - .flags = CLONE_FS | CLONE_UNTRACED | CLONE_VM, + .flags = CLONE_FS | CLONE_UNTRACED | CLONE_VM | + CLONE_THREAD | CLONE_SIGHAND, .exit_signal = 0, .fn = vhost_task_fn, .name = name, .user_worker = 1, .no_files = 1, - .ignore_signals = 1, }; struct vhost_task *vtsk; struct task_struct *tsk; -- cgit v1.2.3 From ed779fe4c9b5a20b4ab4fd6f3e19807445bb78c7 Mon Sep 17 00:00:00 2001 From: Qingfang DENG Date: Thu, 1 Jun 2023 09:54:32 +0800 Subject: neighbour: fix unaligned access to pneigh_entry After the blamed commit, the member key is longer 4-byte aligned. On platforms that do not support unaligned access, e.g., MIPS32R2 with unaligned_action set to 1, this will trigger a crash when accessing an IPv6 pneigh_entry, as the key is cast to an in6_addr pointer. Change the type of the key to u32 to make it aligned. Fixes: 62dd93181aaa ("[IPV6] NDISC: Set per-entry is_router flag in Proxy NA.") Signed-off-by: Qingfang DENG Link: https://lore.kernel.org/r/20230601015432.159066-1-dqfext@gmail.com Signed-off-by: Jakub Kicinski --- include/net/neighbour.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 3fa5774bddac..f6a8ecc6b1fa 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -180,7 +180,7 @@ struct pneigh_entry { netdevice_tracker dev_tracker; u32 flags; u8 protocol; - u8 key[]; + u32 key[]; }; /* -- cgit v1.2.3 From e209fee4118fe9a449d4d805361eb2de6796be39 Mon Sep 17 00:00:00 2001 From: Akihiro Suda Date: Thu, 1 Jun 2023 12:13:05 +0900 Subject: net/ipv4: ping_group_range: allow GID from 2147483648 to 4294967294 With this commit, all the GIDs ("0 4294967294") can be written to the "net.ipv4.ping_group_range" sysctl. Note that 4294967295 (0xffffffff) is an invalid GID (see gid_valid() in include/linux/uidgid.h), and an attempt to register this number will cause -EINVAL. Prior to this commit, only up to GID 2147483647 could be covered. Documentation/networking/ip-sysctl.rst had "0 4294967295" as an example value, but this example was wrong and causing -EINVAL. Fixes: c319b4d76b9e ("net: ipv4: add IPPROTO_ICMP socket kind") Co-developed-by: Kuniyuki Iwashima Signed-off-by: Kuniyuki Iwashima Signed-off-by: Akihiro Suda Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.rst | 4 ++-- include/net/ping.h | 6 +----- net/ipv4/sysctl_net_ipv4.c | 8 ++++---- 3 files changed, 7 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 6ec06a33688a..80b8f73a0244 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -1352,8 +1352,8 @@ ping_group_range - 2 INTEGERS Restrict ICMP_PROTO datagram sockets to users in the group range. The default is "1 0", meaning, that nobody (not even root) may create ping sockets. Setting it to "100 100" would grant permissions - to the single group. "0 4294967295" would enable it for the world, "100 - 4294967295" would enable it for the users, but not daemons. + to the single group. "0 4294967294" would enable it for the world, "100 + 4294967294" would enable it for the users, but not daemons. tcp_early_demux - BOOLEAN Enable early demux for established TCP sockets. diff --git a/include/net/ping.h b/include/net/ping.h index 9233ad3de0ad..bc7779262e60 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -16,11 +16,7 @@ #define PING_HTABLE_SIZE 64 #define PING_HTABLE_MASK (PING_HTABLE_SIZE-1) -/* - * gid_t is either uint or ushort. We want to pass it to - * proc_dointvec_minmax(), so it must not be larger than MAX_INT - */ -#define GID_T_MAX (((gid_t)~0U) >> 1) +#define GID_T_MAX (((gid_t)~0U) - 1) /* Compatibility glue so we can support IPv6 when it's compiled as a module */ struct pingv6_ops { diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 40fe70fc2015..88dfe51e68f3 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -34,8 +34,8 @@ static int ip_ttl_min = 1; static int ip_ttl_max = 255; static int tcp_syn_retries_min = 1; static int tcp_syn_retries_max = MAX_TCP_SYNCNT; -static int ip_ping_group_range_min[] = { 0, 0 }; -static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; +static unsigned long ip_ping_group_range_min[] = { 0, 0 }; +static unsigned long ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; static u32 u32_max_div_HZ = UINT_MAX / HZ; static int one_day_secs = 24 * 3600; static u32 fib_multipath_hash_fields_all_mask __maybe_unused = @@ -165,7 +165,7 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write, { struct user_namespace *user_ns = current_user_ns(); int ret; - gid_t urange[2]; + unsigned long urange[2]; kgid_t low, high; struct ctl_table tmp = { .data = &urange, @@ -178,7 +178,7 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write, inet_get_ping_group_range_table(table, &low, &high); urange[0] = from_kgid_munged(user_ns, low); urange[1] = from_kgid_munged(user_ns, high); - ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + ret = proc_doulongvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) { low = make_kgid(user_ns, urange[0]); -- cgit v1.2.3 From b37a356df86b9e56d30cef4673cba2621c7b7a1e Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Mon, 22 May 2023 11:52:45 +0100 Subject: media: v4l2-subdev: Fix missing kerneldoc for client_caps Add missing kernel doc for the new 'client_caps' field in struct v4l2_subdev_fh. Signed-off-by: Tomi Valkeinen Reviewed-by: Laurent Pinchart Fixes: f57fa2959244 ("media: v4l2-subdev: Add new ioctl for client capabilities") Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index cfd19e72d0fc..b325df0d54d6 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -1119,6 +1119,7 @@ struct v4l2_subdev { * @vfh: pointer to &struct v4l2_fh * @state: pointer to &struct v4l2_subdev_state * @owner: module pointer to the owner of this file handle + * @client_caps: bitmask of ``V4L2_SUBDEV_CLIENT_CAP_*`` */ struct v4l2_subdev_fh { struct v4l2_fh vfh; -- cgit v1.2.3 From edf2e1d2019b2730d6076dbe4c040d37d7c10bbe Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 1 Jun 2023 16:04:44 +0000 Subject: net/ipv6: fix bool/int mismatch for skip_notify_on_dev_down skip_notify_on_dev_down ctl table expects this field to be an int (4 bytes), not a bool (1 byte). Because proc_dou8vec_minmax() was added in 5.13, this patch converts skip_notify_on_dev_down to an int. Following patch then converts the field to u8 and use proc_dou8vec_minmax(). Fixes: 7c6bb7d2faaf ("net/ipv6: Add knob to skip DELROUTE message on device down") Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Acked-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- include/net/netns/ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 3cceb3e9320b..d44b2ee49698 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -53,7 +53,7 @@ struct netns_sysctl_ipv6 { int seg6_flowlabel; u32 ioam6_id; u64 ioam6_id_wide; - bool skip_notify_on_dev_down; + int skip_notify_on_dev_down; u8 fib_notify_on_flag_change; u8 icmpv6_error_anycast_as_unicast; }; -- cgit v1.2.3 From ef62c0ae6db11c095880e473db9f846132d7eba8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 1 Jun 2023 16:04:45 +0000 Subject: net/ipv6: convert skip_notify_on_dev_down sysctl to u8 Save a bit a space, and could help future sysctls to use the same pattern. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Acked-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- include/net/netns/ipv6.h | 2 +- net/ipv6/route.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index d44b2ee49698..5f2cfd84570a 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -53,7 +53,7 @@ struct netns_sysctl_ipv6 { int seg6_flowlabel; u32 ioam6_id; u64 ioam6_id_wide; - int skip_notify_on_dev_down; + u8 skip_notify_on_dev_down; u8 fib_notify_on_flag_change; u8 icmpv6_error_anycast_as_unicast; }; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e3aec46bd466..392aaa373b66 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -6412,9 +6412,9 @@ static struct ctl_table ipv6_route_table_template[] = { { .procname = "skip_notify_on_dev_down", .data = &init_net.ipv6.sysctl.skip_notify_on_dev_down, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, -- cgit v1.2.3 From 132328e8e85174ea788faf8f627c33258c88fbad Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 5 Jun 2023 15:14:45 +0200 Subject: bpf: netfilter: Add BPF_NETFILTER bpf_attach_type Andrii Nakryiko writes: And we currently don't have an attach type for NETLINK BPF link. Thankfully it's not too late to add it. I see that link_create() in kernel/bpf/syscall.c just bypasses attach_type check. We shouldn't have done that. Instead we need to add BPF_NETLINK attach type to enum bpf_attach_type. And wire all that properly throughout the kernel and libbpf itself. This adds BPF_NETFILTER and uses it. This breaks uabi but this wasn't in any non-rc release yet, so it should be fine. v2: check link_attack prog type in link_create too Fixes: 84601d6ee68a ("bpf: add bpf_link support for BPF_NETFILTER programs") Suggested-by: Andrii Nakryiko Signed-off-by: Florian Westphal Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/CAEf4BzZ69YgrQW7DHCJUT_X+GqMq_ZQQPBwopaJJVGFD5=d5Vg@mail.gmail.com/ Link: https://lore.kernel.org/bpf/20230605131445.32016-1-fw@strlen.de --- include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 9 +++++++++ tools/include/uapi/linux/bpf.h | 1 + tools/lib/bpf/libbpf.c | 3 ++- tools/lib/bpf/libbpf_probes.c | 2 ++ 5 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1bb11a6ee667..c994ff5b157c 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1035,6 +1035,7 @@ enum bpf_attach_type { BPF_TRACE_KPROBE_MULTI, BPF_LSM_CGROUP, BPF_STRUCT_OPS, + BPF_NETFILTER, __MAX_BPF_ATTACH_TYPE }; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 14f39c1e573e..0c21d0d8efe4 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2433,6 +2433,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, default: return -EINVAL; } + case BPF_PROG_TYPE_NETFILTER: + if (expected_attach_type == BPF_NETFILTER) + return 0; + return -EINVAL; case BPF_PROG_TYPE_SYSCALL: case BPF_PROG_TYPE_EXT: if (expected_attach_type) @@ -4590,7 +4594,12 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) switch (prog->type) { case BPF_PROG_TYPE_EXT: + break; case BPF_PROG_TYPE_NETFILTER: + if (attr->link_create.attach_type != BPF_NETFILTER) { + ret = -EINVAL; + goto out; + } break; case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_TRACEPOINT: diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1bb11a6ee667..c994ff5b157c 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1035,6 +1035,7 @@ enum bpf_attach_type { BPF_TRACE_KPROBE_MULTI, BPF_LSM_CGROUP, BPF_STRUCT_OPS, + BPF_NETFILTER, __MAX_BPF_ATTACH_TYPE }; diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index ad1ec893b41b..a27f6e9ccce7 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -117,6 +117,7 @@ static const char * const attach_type_name[] = { [BPF_PERF_EVENT] = "perf_event", [BPF_TRACE_KPROBE_MULTI] = "trace_kprobe_multi", [BPF_STRUCT_OPS] = "struct_ops", + [BPF_NETFILTER] = "netfilter", }; static const char * const link_type_name[] = { @@ -8712,7 +8713,7 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("struct_ops+", STRUCT_OPS, 0, SEC_NONE), SEC_DEF("struct_ops.s+", STRUCT_OPS, 0, SEC_SLEEPABLE), SEC_DEF("sk_lookup", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE), - SEC_DEF("netfilter", NETFILTER, 0, SEC_NONE), + SEC_DEF("netfilter", NETFILTER, BPF_NETFILTER, SEC_NONE), }; static size_t custom_sec_def_cnt; diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 6065f408a59c..b7d443129f1c 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -180,7 +180,9 @@ static int probe_prog_load(enum bpf_prog_type prog_type, case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_SYSCTL: + break; case BPF_PROG_TYPE_NETFILTER: + opts.expected_attach_type = BPF_NETFILTER; break; default: return -EOPNOTSUPP; -- cgit v1.2.3 From 1857c19941c87eb36ad47f22a406be5dfe5eff9f Mon Sep 17 00:00:00 2001 From: Zhengping Jiang Date: Wed, 24 May 2023 17:11:58 -0700 Subject: Bluetooth: hci_sync: add lock to protect HCI_UNREGISTER When the HCI_UNREGISTER flag is set, no jobs should be scheduled. Fix potential race when HCI_UNREGISTER is set after the flag is tested in hci_cmd_sync_queue. Fixes: 0b94f2651f56 ("Bluetooth: hci_sync: Fix queuing commands when HCI_UNREGISTER is set") Signed-off-by: Zhengping Jiang Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 1 + net/bluetooth/hci_core.c | 2 ++ net/bluetooth/hci_sync.c | 20 ++++++++++++++------ 3 files changed, 17 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 8baf34639939..fe3893855cd2 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -515,6 +515,7 @@ struct hci_dev { struct work_struct cmd_sync_work; struct list_head cmd_sync_work_list; struct mutex cmd_sync_work_lock; + struct mutex unregister_lock; struct work_struct cmd_sync_cancel_work; struct work_struct reenable_adv_work; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 0164b56de12d..48917c68358d 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2686,7 +2686,9 @@ void hci_unregister_dev(struct hci_dev *hdev) { BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); + mutex_lock(&hdev->unregister_lock); hci_dev_set_flag(hdev, HCI_UNREGISTER); + mutex_unlock(&hdev->unregister_lock); write_lock(&hci_dev_list_lock); list_del(&hdev->list); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 647a8ce54062..a59695f04c25 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -629,6 +629,7 @@ void hci_cmd_sync_init(struct hci_dev *hdev) INIT_WORK(&hdev->cmd_sync_work, hci_cmd_sync_work); INIT_LIST_HEAD(&hdev->cmd_sync_work_list); mutex_init(&hdev->cmd_sync_work_lock); + mutex_init(&hdev->unregister_lock); INIT_WORK(&hdev->cmd_sync_cancel_work, hci_cmd_sync_cancel_work); INIT_WORK(&hdev->reenable_adv_work, reenable_adv); @@ -692,14 +693,19 @@ int hci_cmd_sync_submit(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy) { struct hci_cmd_sync_work_entry *entry; + int err = 0; - if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) - return -ENODEV; + mutex_lock(&hdev->unregister_lock); + if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) { + err = -ENODEV; + goto unlock; + } entry = kmalloc(sizeof(*entry), GFP_KERNEL); - if (!entry) - return -ENOMEM; - + if (!entry) { + err = -ENOMEM; + goto unlock; + } entry->func = func; entry->data = data; entry->destroy = destroy; @@ -710,7 +716,9 @@ int hci_cmd_sync_submit(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, queue_work(hdev->req_workqueue, &hdev->cmd_sync_work); - return 0; +unlock: + mutex_unlock(&hdev->unregister_lock); + return err; } EXPORT_SYMBOL(hci_cmd_sync_submit); -- cgit v1.2.3 From fe2ccc6c29d53e14d3c8b3ddf8ad965a92e074ee Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 31 May 2023 10:57:58 +0200 Subject: Bluetooth: fix debugfs registration Since commit ec6cef9cd98d ("Bluetooth: Fix SMP channel registration for unconfigured controllers") the debugfs interface for unconfigured controllers will be created when the controller is configured. There is however currently nothing preventing a controller from being configured multiple time (e.g. setting the device address using btmgmt) which results in failed attempts to register the already registered debugfs entries: debugfs: File 'features' in directory 'hci0' already present! debugfs: File 'manufacturer' in directory 'hci0' already present! debugfs: File 'hci_version' in directory 'hci0' already present! ... debugfs: File 'quirk_simultaneous_discovery' in directory 'hci0' already present! Add a controller flag to avoid trying to register the debugfs interface more than once. Fixes: ec6cef9cd98d ("Bluetooth: Fix SMP channel registration for unconfigured controllers") Cc: stable@vger.kernel.org # 4.0 Signed-off-by: Johan Hovold Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci.h | 1 + net/bluetooth/hci_sync.c | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 07df96c47ef4..872dcb91a540 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -350,6 +350,7 @@ enum { enum { HCI_SETUP, HCI_CONFIG, + HCI_DEBUGFS_CREATED, HCI_AUTO_OFF, HCI_RFKILLED, HCI_MGMT, diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index a59695f04c25..804cde43b4e0 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -4551,6 +4551,9 @@ static int hci_init_sync(struct hci_dev *hdev) !hci_dev_test_flag(hdev, HCI_CONFIG)) return 0; + if (hci_dev_test_and_set_flag(hdev, HCI_DEBUGFS_CREATED)) + return 0; + hci_debugfs_create_common(hdev); if (lmp_bredr_capable(hdev)) -- cgit v1.2.3 From 71e9588435c38112d6a8686d3d8e7cc1de8fe22c Mon Sep 17 00:00:00 2001 From: Pauli Virtanen Date: Thu, 1 Jun 2023 09:34:45 +0300 Subject: Bluetooth: ISO: use correct CIS order in Set CIG Parameters event The order of CIS handle array in Set CIG Parameters response shall match the order of the CIS_ID array in the command (Core v5.3 Vol 4 Part E Sec 7.8.97). We send CIS_IDs mainly in the order of increasing CIS_ID (but with "last" CIS first if it has fixed CIG_ID). In handling of the reply, we currently assume this is also the same as the order of hci_conn in hdev->conn_hash, but that is not true. Match the correct hci_conn to the correct handle by matching them based on the CIG+CIS combination. The CIG+CIS combination shall be unique for ISO_LINK hci_conn at state >= BT_BOUND, which we maintain in hci_le_set_cig_params. Fixes: 26afbd826ee3 ("Bluetooth: Add initial implementation of CIS connections") Signed-off-by: Pauli Virtanen Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 3 ++- net/bluetooth/hci_event.c | 44 ++++++++++++++++++++++++---------------- 2 files changed, 28 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index fe3893855cd2..9654567cfae3 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1202,7 +1202,8 @@ static inline struct hci_conn *hci_conn_hash_lookup_cis(struct hci_dev *hdev, if (id != BT_ISO_QOS_CIS_UNSET && id != c->iso_qos.ucast.cis) continue; - if (ba_type == c->dst_type && !bacmp(&c->dst, ba)) { + /* Match destination address if set */ + if (!ba || (ba_type == c->dst_type && !bacmp(&c->dst, ba))) { rcu_read_unlock(); return c; } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index d00ef6e3fc45..09ba6d8987ee 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3804,48 +3804,56 @@ static u8 hci_cc_le_set_cig_params(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_le_set_cig_params *rp = data; + struct hci_cp_le_set_cig_params *cp; struct hci_conn *conn; - int i = 0; + u8 status = rp->status; + int i; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_CIG_PARAMS); + if (!cp || rp->num_handles != cp->num_cis || rp->cig_id != cp->cig_id) { + bt_dev_err(hdev, "unexpected Set CIG Parameters response data"); + status = HCI_ERROR_UNSPECIFIED; + } + hci_dev_lock(hdev); - if (rp->status) { + if (status) { while ((conn = hci_conn_hash_lookup_cig(hdev, rp->cig_id))) { conn->state = BT_CLOSED; - hci_connect_cfm(conn, rp->status); + hci_connect_cfm(conn, status); hci_conn_del(conn); } goto unlock; } - rcu_read_lock(); + /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E page 2553 + * + * If the Status return parameter is zero, then the Controller shall + * set the Connection_Handle arrayed return parameter to the connection + * handle(s) corresponding to the CIS configurations specified in + * the CIS_IDs command parameter, in the same order. + */ + for (i = 0; i < rp->num_handles; ++i) { + conn = hci_conn_hash_lookup_cis(hdev, NULL, 0, rp->cig_id, + cp->cis[i].cis_id); + if (!conn || !bacmp(&conn->dst, BDADDR_ANY)) + continue; - list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) { - if (conn->type != ISO_LINK || - conn->iso_qos.ucast.cig != rp->cig_id || - conn->state == BT_CONNECTED) + if (conn->state != BT_BOUND && conn->state != BT_CONNECT) continue; - conn->handle = __le16_to_cpu(rp->handle[i++]); + conn->handle = __le16_to_cpu(rp->handle[i]); bt_dev_dbg(hdev, "%p handle 0x%4.4x parent %p", conn, conn->handle, conn->parent); /* Create CIS if LE is already connected */ - if (conn->parent && conn->parent->state == BT_CONNECTED) { - rcu_read_unlock(); + if (conn->parent && conn->parent->state == BT_CONNECTED) hci_le_create_cis(conn); - rcu_read_lock(); - } - - if (i == rp->num_handles) - break; } - rcu_read_unlock(); - unlock: hci_dev_unlock(hdev); -- cgit v1.2.3 From a2f4c143d76b1a47c91ef9bc46907116b111da0b Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 5 Jun 2023 11:06:17 -0700 Subject: ipv6: rpl: Fix Route of Death. A remote DoS vulnerability of RPL Source Routing is assigned CVE-2023-2156. The Source Routing Header (SRH) has the following format: 0 1 2 3 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Next Header | Hdr Ext Len | Routing Type | Segments Left | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | CmprI | CmprE | Pad | Reserved | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | . . . Addresses[1..n] . . . | | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ The originator of an SRH places the first hop's IPv6 address in the IPv6 header's IPv6 Destination Address and the second hop's IPv6 address as the first address in Addresses[1..n]. The CmprI and CmprE fields indicate the number of prefix octets that are shared with the IPv6 Destination Address. When CmprI or CmprE is not 0, Addresses[1..n] are compressed as follows: 1..n-1 : (16 - CmprI) bytes n : (16 - CmprE) bytes Segments Left indicates the number of route segments remaining. When the value is not zero, the SRH is forwarded to the next hop. Its address is extracted from Addresses[n - Segment Left + 1] and swapped with IPv6 Destination Address. When Segment Left is greater than or equal to 2, the size of SRH is not changed because Addresses[1..n-1] are decompressed and recompressed with CmprI. OTOH, when Segment Left changes from 1 to 0, the new SRH could have a different size because Addresses[1..n-1] are decompressed with CmprI and recompressed with CmprE. Let's say CmprI is 15 and CmprE is 0. When we receive SRH with Segment Left >= 2, Addresses[1..n-1] have 1 byte for each, and Addresses[n] has 16 bytes. When Segment Left is 1, Addresses[1..n-1] is decompressed to 16 bytes and not recompressed. Finally, the new SRH will need more room in the header, and the size is (16 - 1) * (n - 1) bytes. Here the max value of n is 255 as Segment Left is u8, so in the worst case, we have to allocate 3825 bytes in the skb headroom. However, now we only allocate a small fixed buffer that is IPV6_RPL_SRH_WORST_SWAP_SIZE (16 + 7 bytes). If the decompressed size overflows the room, skb_push() hits BUG() below [0]. Instead of allocating the fixed buffer for every packet, let's allocate enough headroom only when we receive SRH with Segment Left 1. [0]: skbuff: skb_under_panic: text:ffffffff81c9f6e2 len:576 put:576 head:ffff8880070b5180 data:ffff8880070b4fb0 tail:0x70 end:0x140 dev:lo kernel BUG at net/core/skbuff.c:200! invalid opcode: 0000 [#1] PREEMPT SMP PTI CPU: 0 PID: 154 Comm: python3 Not tainted 6.4.0-rc4-00190-gc308e9ec0047 #7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 RIP: 0010:skb_panic (net/core/skbuff.c:200) Code: 4f 70 50 8b 87 bc 00 00 00 50 8b 87 b8 00 00 00 50 ff b7 c8 00 00 00 4c 8b 8f c0 00 00 00 48 c7 c7 80 6e 77 82 e8 ad 8b 60 ff <0f> 0b 66 66 2e 0f 1f 84 00 00 00 00 00 90 90 90 90 90 90 90 90 90 RSP: 0018:ffffc90000003da0 EFLAGS: 00000246 RAX: 0000000000000085 RBX: ffff8880058a6600 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff88807dc1c540 RDI: ffff88807dc1c540 RBP: ffffc90000003e48 R08: ffffffff82b392c8 R09: 00000000ffffdfff R10: ffffffff82a592e0 R11: ffffffff82b092e0 R12: ffff888005b1c800 R13: ffff8880070b51b8 R14: ffff888005b1ca18 R15: ffff8880070b5190 FS: 00007f4539f0b740(0000) GS:ffff88807dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055670baf3000 CR3: 0000000005b0e000 CR4: 00000000007506f0 PKRU: 55555554 Call Trace: skb_push (net/core/skbuff.c:210) ipv6_rthdr_rcv (./include/linux/skbuff.h:2880 net/ipv6/exthdrs.c:634 net/ipv6/exthdrs.c:718) ip6_protocol_deliver_rcu (net/ipv6/ip6_input.c:437 (discriminator 5)) ip6_input_finish (./include/linux/rcupdate.h:805 net/ipv6/ip6_input.c:483) __netif_receive_skb_one_core (net/core/dev.c:5494) process_backlog (./include/linux/rcupdate.h:805 net/core/dev.c:5934) __napi_poll (net/core/dev.c:6496) net_rx_action (net/core/dev.c:6565 net/core/dev.c:6696) __do_softirq (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/irq.h:142 kernel/softirq.c:572) do_softirq (kernel/softirq.c:472 kernel/softirq.c:459) __local_bh_enable_ip (kernel/softirq.c:396) __dev_queue_xmit (net/core/dev.c:4272) ip6_finish_output2 (./include/net/neighbour.h:544 net/ipv6/ip6_output.c:134) rawv6_sendmsg (./include/net/dst.h:458 ./include/linux/netfilter.h:303 net/ipv6/raw.c:656 net/ipv6/raw.c:914) sock_sendmsg (net/socket.c:724 net/socket.c:747) __sys_sendto (net/socket.c:2144) __x64_sys_sendto (net/socket.c:2156 net/socket.c:2152 net/socket.c:2152) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) RIP: 0033:0x7f453a138aea Code: d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 f3 0f 1e fa 41 89 ca 64 8b 04 25 18 00 00 00 85 c0 75 15 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 7e c3 0f 1f 44 00 00 41 54 48 83 ec 30 44 89 RSP: 002b:00007ffcc212a1c8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 00007ffcc212a288 RCX: 00007f453a138aea RDX: 0000000000000060 RSI: 00007f4539084c20 RDI: 0000000000000003 RBP: 00007f4538308e80 R08: 00007ffcc212a300 R09: 000000000000001c R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: ffffffffc4653600 R14: 0000000000000001 R15: 00007f4539712d1b Modules linked in: Fixes: 8610c7c6e3bd ("net: ipv6: add support for rpl sr exthdr") Reported-by: Max VA Closes: https://www.interruptlabs.co.uk/articles/linux-ipv6-route-of-death Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230605180617.67284-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- include/net/rpl.h | 3 --- net/ipv6/exthdrs.c | 29 +++++++++++------------------ 2 files changed, 11 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/net/rpl.h b/include/net/rpl.h index 308ef0a05cae..30fe780d1e7c 100644 --- a/include/net/rpl.h +++ b/include/net/rpl.h @@ -23,9 +23,6 @@ static inline int rpl_init(void) static inline void rpl_exit(void) {} #endif -/* Worst decompression memory usage ipv6 address (16) + pad 7 */ -#define IPV6_RPL_SRH_WORST_SWAP_SIZE (sizeof(struct in6_addr) + 7) - size_t ipv6_rpl_srh_size(unsigned char n, unsigned char cmpri, unsigned char cmpre); diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index a8d961d3a477..5fa0e37305d9 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -569,24 +569,6 @@ looped_back: return -1; } - if (skb_cloned(skb)) { - if (pskb_expand_head(skb, IPV6_RPL_SRH_WORST_SWAP_SIZE, 0, - GFP_ATOMIC)) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_OUTDISCARDS); - kfree_skb(skb); - return -1; - } - } else { - err = skb_cow_head(skb, IPV6_RPL_SRH_WORST_SWAP_SIZE); - if (unlikely(err)) { - kfree_skb(skb); - return -1; - } - } - - hdr = (struct ipv6_rpl_sr_hdr *)skb_transport_header(skb); - if (!pskb_may_pull(skb, ipv6_rpl_srh_size(n, hdr->cmpri, hdr->cmpre))) { kfree_skb(skb); @@ -630,6 +612,17 @@ looped_back: skb_pull(skb, ((hdr->hdrlen + 1) << 3)); skb_postpull_rcsum(skb, oldhdr, sizeof(struct ipv6hdr) + ((hdr->hdrlen + 1) << 3)); + if (unlikely(!hdr->segments_left)) { + if (pskb_expand_head(skb, sizeof(struct ipv6hdr) + ((chdr->hdrlen + 1) << 3), 0, + GFP_ATOMIC)) { + __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); + kfree_skb(skb); + kfree(buf); + return -1; + } + + oldhdr = ipv6_hdr(skb); + } skb_push(skb, ((chdr->hdrlen + 1) << 3) + sizeof(struct ipv6hdr)); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); -- cgit v1.2.3 From 1e5c647c3f6d4f8497dedcd226204e1880e0ffb3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 6 Jun 2023 07:41:14 +0000 Subject: rfs: annotate lockless accesses to sk->sk_rxhash Add READ_ONCE()/WRITE_ONCE() on accesses to sk->sk_rxhash. This also prevents a (smart ?) compiler to remove the condition in: if (sk->sk_rxhash != newval) sk->sk_rxhash = newval; We need the condition to avoid dirtying a shared cache line. Fixes: fec5e652e58f ("rfs: Receive Flow Steering") Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- include/net/sock.h | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index b418425d7230..6f428a7f3567 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1152,8 +1152,12 @@ static inline void sock_rps_record_flow(const struct sock *sk) * OR an additional socket flag * [1] : sk_state and sk_prot are in the same cache line. */ - if (sk->sk_state == TCP_ESTABLISHED) - sock_rps_record_flow_hash(sk->sk_rxhash); + if (sk->sk_state == TCP_ESTABLISHED) { + /* This READ_ONCE() is paired with the WRITE_ONCE() + * from sock_rps_save_rxhash() and sock_rps_reset_rxhash(). + */ + sock_rps_record_flow_hash(READ_ONCE(sk->sk_rxhash)); + } } #endif } @@ -1162,15 +1166,19 @@ static inline void sock_rps_save_rxhash(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_RPS - if (unlikely(sk->sk_rxhash != skb->hash)) - sk->sk_rxhash = skb->hash; + /* The following WRITE_ONCE() is paired with the READ_ONCE() + * here, and another one in sock_rps_record_flow(). + */ + if (unlikely(READ_ONCE(sk->sk_rxhash) != skb->hash)) + WRITE_ONCE(sk->sk_rxhash, skb->hash); #endif } static inline void sock_rps_reset_rxhash(struct sock *sk) { #ifdef CONFIG_RPS - sk->sk_rxhash = 0; + /* Paired with READ_ONCE() in sock_rps_record_flow() */ + WRITE_ONCE(sk->sk_rxhash, 0); #endif } -- cgit v1.2.3 From 5c3b74a92aa285a3df722bf6329ba7ccf70346d6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 6 Jun 2023 07:41:15 +0000 Subject: rfs: annotate lockless accesses to RFS sock flow table Add READ_ONCE()/WRITE_ONCE() on accesses to the sock flow table. This also prevents a (smart ?) compiler to remove the condition in: if (table->ents[index] != newval) table->ents[index] = newval; We need the condition to avoid dirtying a shared cache line. Fixes: fec5e652e58f ("rfs: Receive Flow Steering") Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++++-- net/core/dev.c | 6 ++++-- 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 08fbd4622ccf..e6f22b7403d0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -768,8 +768,11 @@ static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, /* We only give a hint, preemption can change CPU under us */ val |= raw_smp_processor_id(); - if (table->ents[index] != val) - table->ents[index] = val; + /* The following WRITE_ONCE() is paired with the READ_ONCE() + * here, and another one in get_rps_cpu(). + */ + if (READ_ONCE(table->ents[index]) != val) + WRITE_ONCE(table->ents[index], val); } } diff --git a/net/core/dev.c b/net/core/dev.c index b3c13e041935..1495f8aff288 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4471,8 +4471,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, u32 next_cpu; u32 ident; - /* First check into global flow table if there is a match */ - ident = sock_flow_table->ents[hash & sock_flow_table->mask]; + /* First check into global flow table if there is a match. + * This READ_ONCE() pairs with WRITE_ONCE() from rps_record_sock_flow(). + */ + ident = READ_ONCE(sock_flow_table->ents[hash & sock_flow_table->mask]); if ((ident ^ hash) & ~rps_cpu_mask) goto try_rps; -- cgit v1.2.3 From d636fc5dd692c8f4e00ae6e0359c0eceeb5d9bdb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 6 Jun 2023 11:19:29 +0000 Subject: net: sched: add rcu annotations around qdisc->qdisc_sleeping syzbot reported a race around qdisc->qdisc_sleeping [1] It is time we add proper annotations to reads and writes to/from qdisc->qdisc_sleeping. [1] BUG: KCSAN: data-race in dev_graft_qdisc / qdisc_lookup_rcu read to 0xffff8881286fc618 of 8 bytes by task 6928 on cpu 1: qdisc_lookup_rcu+0x192/0x2c0 net/sched/sch_api.c:331 __tcf_qdisc_find+0x74/0x3c0 net/sched/cls_api.c:1174 tc_get_tfilter+0x18f/0x990 net/sched/cls_api.c:2547 rtnetlink_rcv_msg+0x7af/0x8c0 net/core/rtnetlink.c:6386 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd write to 0xffff8881286fc618 of 8 bytes by task 6912 on cpu 0: dev_graft_qdisc+0x4f/0x80 net/sched/sch_generic.c:1115 qdisc_graft+0x7d0/0xb60 net/sched/sch_api.c:1103 tc_modify_qdisc+0x712/0xf10 net/sched/sch_api.c:1693 rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6395 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 6912 Comm: syz-executor.5 Not tainted 6.4.0-rc3-syzkaller-00190-g0d85b27b0cc6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/16/2023 Fixes: 3a7d0d07a386 ("net: sched: extend Qdisc with rcu") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Vlad Buslov Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- include/net/sch_generic.h | 6 ++++-- net/core/dev.c | 2 +- net/sched/sch_api.c | 26 ++++++++++++++++---------- net/sched/sch_fq_pie.c | 2 ++ net/sched/sch_generic.c | 30 +++++++++++++++--------------- net/sched/sch_mq.c | 8 ++++---- net/sched/sch_mqprio.c | 8 ++++---- net/sched/sch_pie.c | 5 ++++- net/sched/sch_red.c | 5 ++++- net/sched/sch_sfq.c | 5 ++++- net/sched/sch_taprio.c | 6 +++--- net/sched/sch_teql.c | 2 +- 13 files changed, 63 insertions(+), 44 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e6f22b7403d0..c2f0c6002a84 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -620,7 +620,7 @@ struct netdev_queue { netdevice_tracker dev_tracker; struct Qdisc __rcu *qdisc; - struct Qdisc *qdisc_sleeping; + struct Qdisc __rcu *qdisc_sleeping; #ifdef CONFIG_SYSFS struct kobject kobj; #endif diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index fab5ba3e61b7..27271f2b37cb 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -545,7 +545,7 @@ static inline struct Qdisc *qdisc_root_bh(const struct Qdisc *qdisc) static inline struct Qdisc *qdisc_root_sleeping(const struct Qdisc *qdisc) { - return qdisc->dev_queue->qdisc_sleeping; + return rcu_dereference_rtnl(qdisc->dev_queue->qdisc_sleeping); } static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc) @@ -754,7 +754,9 @@ static inline bool qdisc_tx_changing(const struct net_device *dev) for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - if (rcu_access_pointer(txq->qdisc) != txq->qdisc_sleeping) + + if (rcu_access_pointer(txq->qdisc) != + rcu_access_pointer(txq->qdisc_sleeping)) return true; } return false; diff --git a/net/core/dev.c b/net/core/dev.c index 1495f8aff288..c29f3e1db3ca 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10543,7 +10543,7 @@ struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) return NULL; netdev_init_one_queue(dev, queue, NULL); RCU_INIT_POINTER(queue->qdisc, &noop_qdisc); - queue->qdisc_sleeping = &noop_qdisc; + RCU_INIT_POINTER(queue->qdisc_sleeping, &noop_qdisc); rcu_assign_pointer(dev->ingress_queue, queue); #endif return queue; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 9ea51812b9cf..e4b6452318c0 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -309,7 +309,7 @@ struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle) if (dev_ingress_queue(dev)) q = qdisc_match_from_root( - dev_ingress_queue(dev)->qdisc_sleeping, + rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping), handle); out: return q; @@ -328,7 +328,8 @@ struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle) nq = dev_ingress_queue_rcu(dev); if (nq) - q = qdisc_match_from_root(nq->qdisc_sleeping, handle); + q = qdisc_match_from_root(rcu_dereference(nq->qdisc_sleeping), + handle); out: return q; } @@ -634,8 +635,13 @@ EXPORT_SYMBOL(qdisc_watchdog_init); void qdisc_watchdog_schedule_range_ns(struct qdisc_watchdog *wd, u64 expires, u64 delta_ns) { - if (test_bit(__QDISC_STATE_DEACTIVATED, - &qdisc_root_sleeping(wd->qdisc)->state)) + bool deactivated; + + rcu_read_lock(); + deactivated = test_bit(__QDISC_STATE_DEACTIVATED, + &qdisc_root_sleeping(wd->qdisc)->state); + rcu_read_unlock(); + if (deactivated) return; if (hrtimer_is_queued(&wd->timer)) { @@ -1478,7 +1484,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, } q = qdisc_leaf(p, clid); } else if (dev_ingress_queue(dev)) { - q = dev_ingress_queue(dev)->qdisc_sleeping; + q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping); } } else { q = rtnl_dereference(dev->qdisc); @@ -1564,7 +1570,7 @@ replay: } q = qdisc_leaf(p, clid); } else if (dev_ingress_queue_create(dev)) { - q = dev_ingress_queue(dev)->qdisc_sleeping; + q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping); } } else { q = rtnl_dereference(dev->qdisc); @@ -1805,8 +1811,8 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) dev_queue = dev_ingress_queue(dev); if (dev_queue && - tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb, - &q_idx, s_q_idx, false, + tc_dump_qdisc_root(rtnl_dereference(dev_queue->qdisc_sleeping), + skb, cb, &q_idx, s_q_idx, false, tca[TCA_DUMP_INVISIBLE]) < 0) goto done; @@ -2249,8 +2255,8 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) dev_queue = dev_ingress_queue(dev); if (dev_queue && - tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb, - &t, s_t, false) < 0) + tc_dump_tclass_root(rtnl_dereference(dev_queue->qdisc_sleeping), + skb, tcm, cb, &t, s_t, false) < 0) goto done; done: diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index c699e5095607..591d87d5e5c0 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -379,6 +379,7 @@ static void fq_pie_timer(struct timer_list *t) spinlock_t *root_lock; /* to lock qdisc for probability calculations */ u32 idx; + rcu_read_lock(); root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); @@ -391,6 +392,7 @@ static void fq_pie_timer(struct timer_list *t) mod_timer(&q->adapt_timer, jiffies + q->p_params.tupdate); spin_unlock(root_lock); + rcu_read_unlock(); } static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt, diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 37e41f972f69..3248259eba32 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -648,7 +648,7 @@ struct Qdisc_ops noop_qdisc_ops __read_mostly = { static struct netdev_queue noop_netdev_queue = { RCU_POINTER_INITIALIZER(qdisc, &noop_qdisc), - .qdisc_sleeping = &noop_qdisc, + RCU_POINTER_INITIALIZER(qdisc_sleeping, &noop_qdisc), }; struct Qdisc noop_qdisc = { @@ -1103,7 +1103,7 @@ EXPORT_SYMBOL(qdisc_put_unlocked); struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, struct Qdisc *qdisc) { - struct Qdisc *oqdisc = dev_queue->qdisc_sleeping; + struct Qdisc *oqdisc = rtnl_dereference(dev_queue->qdisc_sleeping); spinlock_t *root_lock; root_lock = qdisc_lock(oqdisc); @@ -1112,7 +1112,7 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, /* ... and graft new one */ if (qdisc == NULL) qdisc = &noop_qdisc; - dev_queue->qdisc_sleeping = qdisc; + rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc); rcu_assign_pointer(dev_queue->qdisc, &noop_qdisc); spin_unlock_bh(root_lock); @@ -1125,12 +1125,12 @@ static void shutdown_scheduler_queue(struct net_device *dev, struct netdev_queue *dev_queue, void *_qdisc_default) { - struct Qdisc *qdisc = dev_queue->qdisc_sleeping; + struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); struct Qdisc *qdisc_default = _qdisc_default; if (qdisc) { rcu_assign_pointer(dev_queue->qdisc, qdisc_default); - dev_queue->qdisc_sleeping = qdisc_default; + rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc_default); qdisc_put(qdisc); } @@ -1154,7 +1154,7 @@ static void attach_one_default_qdisc(struct net_device *dev, if (!netif_is_multiqueue(dev)) qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; - dev_queue->qdisc_sleeping = qdisc; + rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc); } static void attach_default_qdiscs(struct net_device *dev) @@ -1167,7 +1167,7 @@ static void attach_default_qdiscs(struct net_device *dev) if (!netif_is_multiqueue(dev) || dev->priv_flags & IFF_NO_QUEUE) { netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); - qdisc = txq->qdisc_sleeping; + qdisc = rtnl_dereference(txq->qdisc_sleeping); rcu_assign_pointer(dev->qdisc, qdisc); qdisc_refcount_inc(qdisc); } else { @@ -1186,7 +1186,7 @@ static void attach_default_qdiscs(struct net_device *dev) netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); dev->priv_flags |= IFF_NO_QUEUE; netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); - qdisc = txq->qdisc_sleeping; + qdisc = rtnl_dereference(txq->qdisc_sleeping); rcu_assign_pointer(dev->qdisc, qdisc); qdisc_refcount_inc(qdisc); dev->priv_flags ^= IFF_NO_QUEUE; @@ -1202,7 +1202,7 @@ static void transition_one_qdisc(struct net_device *dev, struct netdev_queue *dev_queue, void *_need_watchdog) { - struct Qdisc *new_qdisc = dev_queue->qdisc_sleeping; + struct Qdisc *new_qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); int *need_watchdog_p = _need_watchdog; if (!(new_qdisc->flags & TCQ_F_BUILTIN)) @@ -1272,7 +1272,7 @@ static void dev_reset_queue(struct net_device *dev, struct Qdisc *qdisc; bool nolock; - qdisc = dev_queue->qdisc_sleeping; + qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); if (!qdisc) return; @@ -1303,7 +1303,7 @@ static bool some_qdisc_is_busy(struct net_device *dev) int val; dev_queue = netdev_get_tx_queue(dev, i); - q = dev_queue->qdisc_sleeping; + q = rtnl_dereference(dev_queue->qdisc_sleeping); root_lock = qdisc_lock(q); spin_lock_bh(root_lock); @@ -1379,7 +1379,7 @@ EXPORT_SYMBOL(dev_deactivate); static int qdisc_change_tx_queue_len(struct net_device *dev, struct netdev_queue *dev_queue) { - struct Qdisc *qdisc = dev_queue->qdisc_sleeping; + struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); const struct Qdisc_ops *ops = qdisc->ops; if (ops->change_tx_queue_len) @@ -1404,7 +1404,7 @@ void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx) unsigned int i; for (i = new_real_tx; i < dev->real_num_tx_queues; i++) { - qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping; + qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc_sleeping); /* Only update the default qdiscs we created, * qdiscs with handles are always hashed. */ @@ -1412,7 +1412,7 @@ void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx) qdisc_hash_del(qdisc); } for (i = dev->real_num_tx_queues; i < new_real_tx; i++) { - qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping; + qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc_sleeping); if (qdisc != &noop_qdisc && !qdisc->handle) qdisc_hash_add(qdisc, false); } @@ -1449,7 +1449,7 @@ static void dev_init_scheduler_queue(struct net_device *dev, struct Qdisc *qdisc = _qdisc; rcu_assign_pointer(dev_queue->qdisc, qdisc); - dev_queue->qdisc_sleeping = qdisc; + rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc); } void dev_init_scheduler(struct net_device *dev) diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index d0bc660d7401..c860119a8f09 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -141,7 +141,7 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) * qdisc totals are added at end. */ for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { - qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping; + qdisc = rtnl_dereference(netdev_get_tx_queue(dev, ntx)->qdisc_sleeping); spin_lock_bh(qdisc_lock(qdisc)); gnet_stats_add_basic(&sch->bstats, qdisc->cpu_bstats, @@ -202,7 +202,7 @@ static struct Qdisc *mq_leaf(struct Qdisc *sch, unsigned long cl) { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); - return dev_queue->qdisc_sleeping; + return rtnl_dereference(dev_queue->qdisc_sleeping); } static unsigned long mq_find(struct Qdisc *sch, u32 classid) @@ -221,7 +221,7 @@ static int mq_dump_class(struct Qdisc *sch, unsigned long cl, tcm->tcm_parent = TC_H_ROOT; tcm->tcm_handle |= TC_H_MIN(cl); - tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + tcm->tcm_info = rtnl_dereference(dev_queue->qdisc_sleeping)->handle; return 0; } @@ -230,7 +230,7 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl, { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); - sch = dev_queue->qdisc_sleeping; + sch = rtnl_dereference(dev_queue->qdisc_sleeping); if (gnet_stats_copy_basic(d, sch->cpu_bstats, &sch->bstats, true) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index dc5a0ff50b14..ab69ff7577fc 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -557,7 +557,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) * qdisc totals are added at end. */ for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { - qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping; + qdisc = rtnl_dereference(netdev_get_tx_queue(dev, ntx)->qdisc_sleeping); spin_lock_bh(qdisc_lock(qdisc)); gnet_stats_add_basic(&sch->bstats, qdisc->cpu_bstats, @@ -604,7 +604,7 @@ static struct Qdisc *mqprio_leaf(struct Qdisc *sch, unsigned long cl) if (!dev_queue) return NULL; - return dev_queue->qdisc_sleeping; + return rtnl_dereference(dev_queue->qdisc_sleeping); } static unsigned long mqprio_find(struct Qdisc *sch, u32 classid) @@ -637,7 +637,7 @@ static int mqprio_dump_class(struct Qdisc *sch, unsigned long cl, tcm->tcm_parent = (tc < 0) ? 0 : TC_H_MAKE(TC_H_MAJ(sch->handle), TC_H_MIN(tc + TC_H_MIN_PRIORITY)); - tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + tcm->tcm_info = rtnl_dereference(dev_queue->qdisc_sleeping)->handle; } else { tcm->tcm_parent = TC_H_ROOT; tcm->tcm_info = 0; @@ -693,7 +693,7 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, } else { struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); - sch = dev_queue->qdisc_sleeping; + sch = rtnl_dereference(dev_queue->qdisc_sleeping); if (gnet_stats_copy_basic(d, sch->cpu_bstats, &sch->bstats, true) < 0 || qdisc_qstats_copy(d, sch) < 0) diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index 2152a56d73f8..2da6250ec346 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -421,8 +421,10 @@ static void pie_timer(struct timer_list *t) { struct pie_sched_data *q = from_timer(q, t, adapt_timer); struct Qdisc *sch = q->sch; - spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + spinlock_t *root_lock; + rcu_read_lock(); + root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); pie_calculate_probability(&q->params, &q->vars, sch->qstats.backlog); @@ -430,6 +432,7 @@ static void pie_timer(struct timer_list *t) if (q->params.tupdate) mod_timer(&q->adapt_timer, jiffies + q->params.tupdate); spin_unlock(root_lock); + rcu_read_unlock(); } static int pie_init(struct Qdisc *sch, struct nlattr *opt, diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 98129324e157..16277b6a0238 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -321,12 +321,15 @@ static inline void red_adaptative_timer(struct timer_list *t) { struct red_sched_data *q = from_timer(q, t, adapt_timer); struct Qdisc *sch = q->sch; - spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + spinlock_t *root_lock; + rcu_read_lock(); + root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); red_adaptative_algo(&q->parms, &q->vars); mod_timer(&q->adapt_timer, jiffies + HZ/2); spin_unlock(root_lock); + rcu_read_unlock(); } static int red_init(struct Qdisc *sch, struct nlattr *opt, diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index abd436307d6a..66dcb18638fe 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -606,10 +606,12 @@ static void sfq_perturbation(struct timer_list *t) { struct sfq_sched_data *q = from_timer(q, t, perturb_timer); struct Qdisc *sch = q->sch; - spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + spinlock_t *root_lock; siphash_key_t nkey; get_random_bytes(&nkey, sizeof(nkey)); + rcu_read_lock(); + root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); q->perturbation = nkey; if (!q->filter_list && q->tail) @@ -618,6 +620,7 @@ static void sfq_perturbation(struct timer_list *t) if (q->perturb_period) mod_timer(&q->perturb_timer, jiffies + q->perturb_period); + rcu_read_unlock(); } static int sfq_change(struct Qdisc *sch, struct nlattr *opt) diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 76db9a10ef50..dd7dea2f6e83 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -2358,7 +2358,7 @@ static struct Qdisc *taprio_leaf(struct Qdisc *sch, unsigned long cl) if (!dev_queue) return NULL; - return dev_queue->qdisc_sleeping; + return rtnl_dereference(dev_queue->qdisc_sleeping); } static unsigned long taprio_find(struct Qdisc *sch, u32 classid) @@ -2377,7 +2377,7 @@ static int taprio_dump_class(struct Qdisc *sch, unsigned long cl, tcm->tcm_parent = TC_H_ROOT; tcm->tcm_handle |= TC_H_MIN(cl); - tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + tcm->tcm_info = rtnl_dereference(dev_queue->qdisc_sleeping)->handle; return 0; } @@ -2389,7 +2389,7 @@ static int taprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, { struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); - sch = dev_queue->qdisc_sleeping; + sch = rtnl_dereference(dev_queue->qdisc_sleeping); if (gnet_stats_copy_basic(d, NULL, &sch->bstats, true) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 16f9238aa51d..7721239c185f 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -297,7 +297,7 @@ restart: struct net_device *slave = qdisc_dev(q); struct netdev_queue *slave_txq = netdev_get_tx_queue(slave, 0); - if (slave_txq->qdisc_sleeping != q) + if (rcu_access_pointer(slave_txq->qdisc_sleeping) != q) continue; if (netif_xmit_stopped(netdev_get_tx_queue(slave, subq)) || !netif_running(slave)) { -- cgit v1.2.3 From 886bc7d6ed3357975c5f1d3c784da96000d4bbb4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 6 Jun 2023 11:42:33 +0000 Subject: net: sched: move rtm_tca_policy declaration to include file rtm_tca_policy is used from net/sched/sch_api.c and net/sched/cls_api.c, thus should be declared in an include file. This fixes the following sparse warning: net/sched/sch_api.c:1434:25: warning: symbol 'rtm_tca_policy' was not declared. Should it be static? Fixes: e331473fee3d ("net/sched: cls_api: add missing validation of netlink attributes") Signed-off-by: Eric Dumazet Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/pkt_sched.h | 2 ++ net/sched/cls_api.c | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index f436688b6efc..5722931d83d4 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -127,6 +127,8 @@ static inline void qdisc_run(struct Qdisc *q) } } +extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; + /* Calculate maximal size of packet seen by hard_start_xmit routine of this device. */ diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 2621550bfddc..b2432ee04f31 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -43,8 +43,6 @@ #include #include -extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; - /* The list of all installed classifier types */ static LIST_HEAD(tcf_proto_base); -- cgit v1.2.3 From de29a96acceae732c68a4094d08dc49079eefa02 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Fri, 26 May 2023 15:35:37 +0800 Subject: notifier: Initialize new struct srcu_usage field In commit 95433f726301 ("srcu: Begin offloading srcu_struct fields to srcu_update"), a new struct srcu_usage field was added, but was not properly initialized. This led to a "spinlock bad magic" BUG when the SRCU notifier was ever used. This was observed in the MediaTek CCI devfreq driver on next-20230525. The trimmed stack trace is as follows: BUG: spinlock bad magic on CPU#4, swapper/0/1 lock: 0xffffff80ff529ac0, .magic: 00000000, .owner: /-1, .owner_cpu: 0 Call trace: spin_bug+0xa4/0xe8 do_raw_spin_lock+0xec/0x120 _raw_spin_lock_irqsave+0x78/0xb8 synchronize_srcu+0x3c/0x168 srcu_notifier_chain_unregister+0x5c/0xa0 cpufreq_unregister_notifier+0x94/0xe0 devfreq_passive_event_handler+0x7c/0x3e0 devfreq_remove_device+0x48/0xe8 Add __SRCU_USAGE_INIT() to SRCU_NOTIFIER_INIT() so that srcu_usage gets initialized properly. Reported-by: Jon Hunter Fixes: 95433f726301 ("srcu: Begin offloading srcu_struct fields to srcu_update") Signed-off-by: Chen-Yu Tsai Tested-by: AngeloGioacchino Del Regno Cc: Matthias Brugger Cc: "Rafael J. Wysocki" Cc: "Michał Mirosław" Cc: Dmitry Osipenko Cc: Sachin Sant Cc: Joel Fernandes (Google) Acked-by: Zqiang Signed-off-by: Paul E. McKenney --- include/linux/notifier.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 2aba75145144..86544707236a 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -106,12 +106,22 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); #define RAW_NOTIFIER_INIT(name) { \ .head = NULL } +#ifdef CONFIG_TREE_SRCU #define SRCU_NOTIFIER_INIT(name, pcpu) \ { \ .mutex = __MUTEX_INITIALIZER(name.mutex), \ .head = NULL, \ + .srcuu = __SRCU_USAGE_INIT(name.srcuu), \ .srcu = __SRCU_STRUCT_INIT(name.srcu, name.srcuu, pcpu), \ } +#else +#define SRCU_NOTIFIER_INIT(name, pcpu) \ + { \ + .mutex = __MUTEX_INITIALIZER(name.mutex), \ + .head = NULL, \ + .srcu = __SRCU_STRUCT_INIT(name.srcu, name.srcuu, pcpu), \ + } +#endif #define ATOMIC_NOTIFIER_HEAD(name) \ struct atomic_notifier_head name = \ -- cgit v1.2.3 From 212ed75dc5fb9d1423b3942c8f872a868cda3466 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 7 Jun 2023 11:55:42 +0200 Subject: netfilter: nf_tables: integrate pipapo into commit protocol The pipapo set backend follows copy-on-update approach, maintaining one clone of the existing datastructure that is being updated. The clone and current datastructures are swapped via rcu from the commit step. The existing integration with the commit protocol is flawed because there is no operation to clean up the clone if the transaction is aborted. Moreover, the datastructure swap happens on set element activation. This patch adds two new operations for sets: commit and abort, these new operations are invoked from the commit and abort steps, after the transactions have been digested, and it updates the pipapo set backend to use it. This patch adds a new ->pending_update field to sets to maintain a list of sets that require this new commit and abort operations. Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 4 ++- net/netfilter/nf_tables_api.c | 56 +++++++++++++++++++++++++++++++++++++++ net/netfilter/nft_set_pipapo.c | 55 +++++++++++++++++++++++++++----------- 3 files changed, 99 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 2e24ea1d744c..83db182decc8 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -462,7 +462,8 @@ struct nft_set_ops { const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags); - + void (*commit)(const struct nft_set *set); + void (*abort)(const struct nft_set *set); u64 (*privsize)(const struct nlattr * const nla[], const struct nft_set_desc *desc); bool (*estimate)(const struct nft_set_desc *desc, @@ -557,6 +558,7 @@ struct nft_set { u16 policy; u16 udlen; unsigned char *udata; + struct list_head pending_update; /* runtime data below here */ const struct nft_set_ops *ops ____cacheline_aligned; u16 flags:14, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 0519d45ede6b..3bb0800b3849 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4919,6 +4919,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, set->num_exprs = num_exprs; set->handle = nf_tables_alloc_handle(table); + INIT_LIST_HEAD(&set->pending_update); err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set); if (err < 0) @@ -9275,10 +9276,25 @@ static void nf_tables_commit_audit_log(struct list_head *adl, u32 generation) } } +static void nft_set_commit_update(struct list_head *set_update_list) +{ + struct nft_set *set, *next; + + list_for_each_entry_safe(set, next, set_update_list, pending_update) { + list_del_init(&set->pending_update); + + if (!set->ops->commit) + continue; + + set->ops->commit(set); + } +} + static int nf_tables_commit(struct net *net, struct sk_buff *skb) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; + LIST_HEAD(set_update_list); struct nft_trans_elem *te; struct nft_chain *chain; struct nft_table *table; @@ -9453,6 +9469,11 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_setelem_notify(&trans->ctx, te->set, &te->elem, NFT_MSG_NEWSETELEM); + if (te->set->ops->commit && + list_empty(&te->set->pending_update)) { + list_add_tail(&te->set->pending_update, + &set_update_list); + } nft_trans_destroy(trans); break; case NFT_MSG_DELSETELEM: @@ -9467,6 +9488,11 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) atomic_dec(&te->set->nelems); te->set->ndeact--; } + if (te->set->ops->commit && + list_empty(&te->set->pending_update)) { + list_add_tail(&te->set->pending_update, + &set_update_list); + } break; case NFT_MSG_NEWOBJ: if (nft_trans_obj_update(trans)) { @@ -9529,6 +9555,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) } } + nft_set_commit_update(&set_update_list); + nft_commit_notify(net, NETLINK_CB(skb).portid); nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); nf_tables_commit_audit_log(&adl, nft_net->base_seq); @@ -9588,10 +9616,25 @@ static void nf_tables_abort_release(struct nft_trans *trans) kfree(trans); } +static void nft_set_abort_update(struct list_head *set_update_list) +{ + struct nft_set *set, *next; + + list_for_each_entry_safe(set, next, set_update_list, pending_update) { + list_del_init(&set->pending_update); + + if (!set->ops->abort) + continue; + + set->ops->abort(set); + } +} + static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; + LIST_HEAD(set_update_list); struct nft_trans_elem *te; if (action == NFNL_ABORT_VALIDATE && @@ -9701,6 +9744,12 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_setelem_remove(net, te->set, &te->elem); if (!nft_setelem_is_catchall(te->set, &te->elem)) atomic_dec(&te->set->nelems); + + if (te->set->ops->abort && + list_empty(&te->set->pending_update)) { + list_add_tail(&te->set->pending_update, + &set_update_list); + } break; case NFT_MSG_DELSETELEM: case NFT_MSG_DESTROYSETELEM: @@ -9711,6 +9760,11 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) if (!nft_setelem_is_catchall(te->set, &te->elem)) te->set->ndeact--; + if (te->set->ops->abort && + list_empty(&te->set->pending_update)) { + list_add_tail(&te->set->pending_update, + &set_update_list); + } nft_trans_destroy(trans); break; case NFT_MSG_NEWOBJ: @@ -9753,6 +9807,8 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) } } + nft_set_abort_update(&set_update_list); + synchronize_rcu(); list_for_each_entry_safe_reverse(trans, next, diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 06d46d182634..15e451dc3fc4 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1600,17 +1600,10 @@ static void pipapo_free_fields(struct nft_pipapo_match *m) } } -/** - * pipapo_reclaim_match - RCU callback to free fields from old matching data - * @rcu: RCU head - */ -static void pipapo_reclaim_match(struct rcu_head *rcu) +static void pipapo_free_match(struct nft_pipapo_match *m) { - struct nft_pipapo_match *m; int i; - m = container_of(rcu, struct nft_pipapo_match, rcu); - for_each_possible_cpu(i) kfree(*per_cpu_ptr(m->scratch, i)); @@ -1625,7 +1618,19 @@ static void pipapo_reclaim_match(struct rcu_head *rcu) } /** - * pipapo_commit() - Replace lookup data with current working copy + * pipapo_reclaim_match - RCU callback to free fields from old matching data + * @rcu: RCU head + */ +static void pipapo_reclaim_match(struct rcu_head *rcu) +{ + struct nft_pipapo_match *m; + + m = container_of(rcu, struct nft_pipapo_match, rcu); + pipapo_free_match(m); +} + +/** + * nft_pipapo_commit() - Replace lookup data with current working copy * @set: nftables API set representation * * While at it, check if we should perform garbage collection on the working @@ -1635,7 +1640,7 @@ static void pipapo_reclaim_match(struct rcu_head *rcu) * We also need to create a new working copy for subsequent insertions and * deletions. */ -static void pipapo_commit(const struct nft_set *set) +static void nft_pipapo_commit(const struct nft_set *set) { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *new_clone, *old; @@ -1660,6 +1665,26 @@ static void pipapo_commit(const struct nft_set *set) priv->clone = new_clone; } +static void nft_pipapo_abort(const struct nft_set *set) +{ + struct nft_pipapo *priv = nft_set_priv(set); + struct nft_pipapo_match *new_clone, *m; + + if (!priv->dirty) + return; + + m = rcu_dereference(priv->match); + + new_clone = pipapo_clone(m); + if (IS_ERR(new_clone)) + return; + + priv->dirty = false; + + pipapo_free_match(priv->clone); + priv->clone = new_clone; +} + /** * nft_pipapo_activate() - Mark element reference as active given key, commit * @net: Network namespace @@ -1667,8 +1692,7 @@ static void pipapo_commit(const struct nft_set *set) * @elem: nftables API element representation containing key data * * On insertion, elements are added to a copy of the matching data currently - * in use for lookups, and not directly inserted into current lookup data, so - * we'll take care of that by calling pipapo_commit() here. Both + * in use for lookups, and not directly inserted into current lookup data. Both * nft_pipapo_insert() and nft_pipapo_activate() are called once for each * element, hence we can't purpose either one as a real commit operation. */ @@ -1684,8 +1708,6 @@ static void nft_pipapo_activate(const struct net *net, nft_set_elem_change_active(net, set, &e->ext); nft_set_elem_clear_busy(&e->ext); - - pipapo_commit(set); } /** @@ -1931,7 +1953,6 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, if (i == m->field_count) { priv->dirty = true; pipapo_drop(m, rulemap); - pipapo_commit(set); return; } @@ -2230,6 +2251,8 @@ const struct nft_set_type nft_set_pipapo_type = { .init = nft_pipapo_init, .destroy = nft_pipapo_destroy, .gc_init = nft_pipapo_gc_init, + .commit = nft_pipapo_commit, + .abort = nft_pipapo_abort, .elemsize = offsetof(struct nft_pipapo_elem, ext), }, }; @@ -2252,6 +2275,8 @@ const struct nft_set_type nft_set_pipapo_avx2_type = { .init = nft_pipapo_init, .destroy = nft_pipapo_destroy, .gc_init = nft_pipapo_gc_init, + .commit = nft_pipapo_commit, + .abort = nft_pipapo_abort, .elemsize = offsetof(struct nft_pipapo_elem, ext), }, }; -- cgit v1.2.3 From 58030c76cce473b6cfd630bbecb97215def0dff8 Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Mon, 5 Jun 2023 13:33:23 +0300 Subject: RDMA/cma: Always set static rate to 0 for RoCE Set static rate to 0 as it should be discovered by path query and has no meaning for RoCE. This also avoid of using the rtnl lock and ethtool API, which is a bottleneck when try to setup many rdma-cm connections at the same time, especially with multiple processes. Fixes: 3c86aa70bf67 ("RDMA/cm: Add RDMA CM support for IBoE devices") Signed-off-by: Mark Zhang Link: https://lore.kernel.org/r/f72a4f8b667b803aee9fa794069f61afb5839ce4.1685960567.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- drivers/infiniband/core/cma.c | 4 ++-- include/rdma/ib_addr.h | 23 ----------------------- 2 files changed, 2 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 93a1c48d0c32..6b3f4384e46a 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -3295,7 +3295,7 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) route->path_rec->traffic_class = tos; route->path_rec->mtu = iboe_get_mtu(ndev->mtu); route->path_rec->rate_selector = IB_SA_EQ; - route->path_rec->rate = iboe_get_rate(ndev); + route->path_rec->rate = IB_RATE_PORT_CURRENT; dev_put(ndev); route->path_rec->packet_life_time_selector = IB_SA_EQ; /* In case ACK timeout is set, use this value to calculate @@ -4964,7 +4964,7 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, if (!ndev) return -ENODEV; - ib.rec.rate = iboe_get_rate(ndev); + ib.rec.rate = IB_RATE_PORT_CURRENT; ib.rec.hop_limit = 1; ib.rec.mtu = iboe_get_mtu(ndev->mtu); diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h index d808dc3d239e..811a0f11d0db 100644 --- a/include/rdma/ib_addr.h +++ b/include/rdma/ib_addr.h @@ -194,29 +194,6 @@ static inline enum ib_mtu iboe_get_mtu(int mtu) return 0; } -static inline int iboe_get_rate(struct net_device *dev) -{ - struct ethtool_link_ksettings cmd; - int err; - - rtnl_lock(); - err = __ethtool_get_link_ksettings(dev, &cmd); - rtnl_unlock(); - if (err) - return IB_RATE_PORT_CURRENT; - - if (cmd.base.speed >= 40000) - return IB_RATE_40_GBPS; - else if (cmd.base.speed >= 30000) - return IB_RATE_30_GBPS; - else if (cmd.base.speed >= 20000) - return IB_RATE_20_GBPS; - else if (cmd.base.speed >= 10000) - return IB_RATE_10_GBPS; - else - return IB_RATE_PORT_CURRENT; -} - static inline int rdma_link_local_addr(struct in6_addr *addr) { if (addr->s6_addr32[0] == htonl(0xfe800000) && -- cgit v1.2.3 From 617f5db1a626f18d5cbb7c7faf7bf8f9ea12be78 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Mon, 5 Jun 2023 13:33:26 +0300 Subject: RDMA/mlx5: Fix affinity assignment The cited commit aimed to ensure that Virtual Functions (VFs) assign a queue affinity to a Queue Pair (QP) to distribute traffic when the LAG master creates a hardware LAG. If the affinity was set while the hardware was not in LAG, the firmware would ignore the affinity value. However, this commit unintentionally assigned an affinity to QPs on the LAG master's VPORT even if the RDMA device was not marked as LAG-enabled. In most cases, this was not an issue because when the hardware entered hardware LAG configuration, the RDMA device of the LAG master would be destroyed and a new one would be created, marked as LAG-enabled. The problem arises when a user configures Equal-Cost Multipath (ECMP). In ECMP mode, traffic can be directed to different physical ports based on the queue affinity, which is intended for use by VPORTS other than the E-Switch manager. ECMP mode is supported only if both E-Switch managers are in switchdev mode and the appropriate route is configured via IP. In this configuration, the RDMA device is not destroyed, and we retain the RDMA device that is not marked as LAG-enabled. To ensure correct behavior, Send Queues (SQs) opened by the E-Switch manager through verbs should be assigned strict affinity. This means they will only be able to communicate through the native physical port associated with the E-Switch manager. This will prevent the firmware from assigning affinity and will not allow the SQs to be remapped in case of failover. Fixes: 802dcc7fc5ec ("RDMA/mlx5: Support TX port affinity for VF drivers in LAG mode") Reviewed-by: Maor Gottlieb Signed-off-by: Mark Bloch Link: https://lore.kernel.org/r/425b05f4da840bc684b0f7e8ebf61aeb5cef09b0.1685960567.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/mlx5_ib.h | 3 +++ drivers/infiniband/hw/mlx5/qp.c | 3 +++ drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h | 12 ------------ include/linux/mlx5/driver.h | 12 ++++++++++++ 4 files changed, 18 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 91fc0cdf377d..2dfa6f49a6f4 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -1598,6 +1598,9 @@ static inline bool mlx5_ib_lag_should_assign_affinity(struct mlx5_ib_dev *dev) MLX5_CAP_PORT_SELECTION(dev->mdev, port_select_flow_table_bypass)) return 0; + if (mlx5_lag_is_lacp_owner(dev->mdev) && !dev->lag_active) + return 0; + return dev->lag_active || (MLX5_CAP_GEN(dev->mdev, num_lag_ports) > 1 && MLX5_CAP_GEN(dev->mdev, lag_tx_port_affinity)); diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 70ca8ffa9256..78b96bfb4e6a 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1237,6 +1237,9 @@ static int create_raw_packet_qp_tis(struct mlx5_ib_dev *dev, MLX5_SET(create_tis_in, in, uid, to_mpd(pd)->uid); MLX5_SET(tisc, tisc, transport_domain, tdn); + if (!mlx5_ib_lag_should_assign_affinity(dev) && + mlx5_lag_is_lacp_owner(dev->mdev)) + MLX5_SET(tisc, tisc, strict_lag_tx_port_affinity, 1); if (qp->flags & IB_QP_CREATE_SOURCE_QPN) MLX5_SET(tisc, tisc, underlay_qpn, qp->underlay_qpn); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 1d879374acaa..229520405d4a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -276,18 +276,6 @@ static inline bool mlx5_sriov_is_enabled(struct mlx5_core_dev *dev) return pci_num_vf(dev->pdev) ? true : false; } -static inline int mlx5_lag_is_lacp_owner(struct mlx5_core_dev *dev) -{ - /* LACP owner conditions: - * 1) Function is physical. - * 2) LAG is supported by FW. - * 3) LAG is managed by driver (currently the only option). - */ - return MLX5_CAP_GEN(dev, vport_group_manager) && - (MLX5_CAP_GEN(dev, num_lag_ports) > 1) && - MLX5_CAP_GEN(dev, lag_master); -} - int mlx5_rescan_drivers_locked(struct mlx5_core_dev *dev); static inline int mlx5_rescan_drivers(struct mlx5_core_dev *dev) { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a4c4f737f9c1..8ad16b779898 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1237,6 +1237,18 @@ static inline u16 mlx5_core_max_vfs(const struct mlx5_core_dev *dev) return dev->priv.sriov.max_vfs; } +static inline int mlx5_lag_is_lacp_owner(struct mlx5_core_dev *dev) +{ + /* LACP owner conditions: + * 1) Function is physical. + * 2) LAG is supported by FW. + * 3) LAG is managed by driver (currently the only option). + */ + return MLX5_CAP_GEN(dev, vport_group_manager) && + (MLX5_CAP_GEN(dev, num_lag_ports) > 1) && + MLX5_CAP_GEN(dev, lag_master); +} + static inline int mlx5_get_gid_table_len(u16 param) { if (param > 4) { -- cgit v1.2.3 From 52f79609c0c5b25fddb88e85f25ce08aa7e3fb42 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 8 Jun 2023 09:23:44 -0700 Subject: net: ethtool: correct MAX attribute value for stats When compiling YNL generated code compiler complains about array-initializer-out-of-bounds. Turns out the MAX value for STATS_GRP uses the value for STATS. This may lead to random corruptions in user space (kernel itself doesn't use this value as it never parses stats). Fixes: f09ea6fb1272 ("ethtool: add a new command for reading standard stats") Signed-off-by: Jakub Kicinski Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/uapi/linux/ethtool_netlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 1ebf8d455f07..73e2c10dc2cc 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -783,7 +783,7 @@ enum { /* add new constants above here */ __ETHTOOL_A_STATS_GRP_CNT, - ETHTOOL_A_STATS_GRP_MAX = (__ETHTOOL_A_STATS_CNT - 1) + ETHTOOL_A_STATS_GRP_MAX = (__ETHTOOL_A_STATS_GRP_CNT - 1) }; enum { -- cgit v1.2.3 From 41f2c7c342d3adb1c4dd5f2e3dd831adff16a669 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Fri, 9 Jun 2023 15:22:59 +0300 Subject: net/sched: act_ct: Fix promotion of offloaded unreplied tuple Currently UNREPLIED and UNASSURED connections are added to the nf flow table. This causes the following connection packets to be processed by the flow table which then skips conntrack_in(), and thus such the connections will remain UNREPLIED and UNASSURED even if reply traffic is then seen. Even still, the unoffloaded reply packets are the ones triggering hardware update from new to established state, and if there aren't any to triger an update and/or previous update was missed, hardware can get out of sync with sw and still mark packets as new. Fix the above by: 1) Not skipping conntrack_in() for UNASSURED packets, but still refresh for hardware, as before the cited patch. 2) Try and force a refresh by reply-direction packets that update the hardware rules from new to established state. 3) Remove any bidirectional flows that didn't failed to update in hardware for re-insertion as bidrectional once any new packet arrives. Fixes: 6a9bad0069cf ("net/sched: act_ct: offload UDP NEW connections") Co-developed-by: Vlad Buslov Signed-off-by: Vlad Buslov Signed-off-by: Paul Blakey Reviewed-by: Florian Westphal Link: https://lore.kernel.org/r/1686313379-117663-1-git-send-email-paulb@nvidia.com Signed-off-by: Paolo Abeni --- include/net/netfilter/nf_flow_table.h | 2 +- net/netfilter/nf_flow_table_core.c | 13 ++++++++++--- net/netfilter/nf_flow_table_ip.c | 4 ++-- net/sched/act_ct.c | 9 ++++++++- 4 files changed, 21 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index ebb28ec5b6fa..f37f9f34430c 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -268,7 +268,7 @@ int flow_offload_route_init(struct flow_offload *flow, int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow); void flow_offload_refresh(struct nf_flowtable *flow_table, - struct flow_offload *flow); + struct flow_offload *flow, bool force); struct flow_offload_tuple_rhash *flow_offload_lookup(struct nf_flowtable *flow_table, struct flow_offload_tuple *tuple); diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 04bd0ed4d2ae..b0ef48b21dcb 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -317,12 +317,12 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) EXPORT_SYMBOL_GPL(flow_offload_add); void flow_offload_refresh(struct nf_flowtable *flow_table, - struct flow_offload *flow) + struct flow_offload *flow, bool force) { u32 timeout; timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); - if (timeout - READ_ONCE(flow->timeout) > HZ) + if (force || timeout - READ_ONCE(flow->timeout) > HZ) WRITE_ONCE(flow->timeout, timeout); else return; @@ -334,6 +334,12 @@ void flow_offload_refresh(struct nf_flowtable *flow_table, } EXPORT_SYMBOL_GPL(flow_offload_refresh); +static bool nf_flow_is_outdated(const struct flow_offload *flow) +{ + return test_bit(IPS_SEEN_REPLY_BIT, &flow->ct->status) && + !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); +} + static inline bool nf_flow_has_expired(const struct flow_offload *flow) { return nf_flow_timeout_delta(flow->timeout) <= 0; @@ -423,7 +429,8 @@ static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table, struct flow_offload *flow, void *data) { if (nf_flow_has_expired(flow) || - nf_ct_is_dying(flow->ct)) + nf_ct_is_dying(flow->ct) || + nf_flow_is_outdated(flow)) flow_offload_teardown(flow); if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 19efba1e51ef..3bbaf9c7ea46 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -384,7 +384,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, if (skb_try_make_writable(skb, thoff + hdrsize)) return NF_DROP; - flow_offload_refresh(flow_table, flow); + flow_offload_refresh(flow_table, flow, false); nf_flow_encap_pop(skb, tuplehash); thoff -= offset; @@ -650,7 +650,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, if (skb_try_make_writable(skb, thoff + hdrsize)) return NF_DROP; - flow_offload_refresh(flow_table, flow); + flow_offload_refresh(flow_table, flow, false); nf_flow_encap_pop(skb, tuplehash); diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 9cc0bc7c71ed..abc71a06d634 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -610,6 +610,7 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p, struct flow_offload_tuple tuple = {}; enum ip_conntrack_info ctinfo; struct tcphdr *tcph = NULL; + bool force_refresh = false; struct flow_offload *flow; struct nf_conn *ct; u8 dir; @@ -647,6 +648,7 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p, * established state, then don't refresh. */ return false; + force_refresh = true; } if (tcph && (unlikely(tcph->fin || tcph->rst))) { @@ -660,7 +662,12 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p, else ctinfo = IP_CT_ESTABLISHED_REPLY; - flow_offload_refresh(nf_ft, flow); + flow_offload_refresh(nf_ft, flow, force_refresh); + if (!test_bit(IPS_ASSURED_BIT, &ct->status)) { + /* Process this flow in SW to allow promoting to ASSURED */ + return false; + } + nf_conntrack_get(&ct->ct_general); nf_ct_set(skb, ct, ctinfo); if (nf_ft->flags & NF_FLOWTABLE_COUNTER) -- cgit v1.2.3 From 84ad0af0bccd3691cb951c2974c5cb2c10594d4a Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Sat, 10 Jun 2023 20:30:25 -0700 Subject: net/sched: qdisc_destroy() old ingress and clsact Qdiscs before grafting mini_Qdisc_pair::p_miniq is a double pointer to mini_Qdisc, initialized in ingress_init() to point to net_device::miniq_ingress. ingress Qdiscs access this per-net_device pointer in mini_qdisc_pair_swap(). Similar for clsact Qdiscs and miniq_egress. Unfortunately, after introducing RTNL-unlocked RTM_{NEW,DEL,GET}TFILTER requests (thanks Hillf Danton for the hint), when replacing ingress or clsact Qdiscs, for example, the old Qdisc ("@old") could access the same miniq_{in,e}gress pointer(s) concurrently with the new Qdisc ("@new"), causing race conditions [1] including a use-after-free bug in mini_qdisc_pair_swap() reported by syzbot: BUG: KASAN: slab-use-after-free in mini_qdisc_pair_swap+0x1c2/0x1f0 net/sched/sch_generic.c:1573 Write of size 8 at addr ffff888045b31308 by task syz-executor690/14901 ... Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd9/0x150 lib/dump_stack.c:106 print_address_description.constprop.0+0x2c/0x3c0 mm/kasan/report.c:319 print_report mm/kasan/report.c:430 [inline] kasan_report+0x11c/0x130 mm/kasan/report.c:536 mini_qdisc_pair_swap+0x1c2/0x1f0 net/sched/sch_generic.c:1573 tcf_chain_head_change_item net/sched/cls_api.c:495 [inline] tcf_chain0_head_change.isra.0+0xb9/0x120 net/sched/cls_api.c:509 tcf_chain_tp_insert net/sched/cls_api.c:1826 [inline] tcf_chain_tp_insert_unique net/sched/cls_api.c:1875 [inline] tc_new_tfilter+0x1de6/0x2290 net/sched/cls_api.c:2266 ... @old and @new should not affect each other. In other words, @old should never modify miniq_{in,e}gress after @new, and @new should not update @old's RCU state. Fixing without changing sch_api.c turned out to be difficult (please refer to Closes: for discussions). Instead, make sure @new's first call always happen after @old's last call (in {ingress,clsact}_destroy()) has finished: In qdisc_graft(), return -EBUSY if @old has any ongoing filter requests, and call qdisc_destroy() for @old before grafting @new. Introduce qdisc_refcount_dec_if_one() as the counterpart of qdisc_refcount_inc_nz() used for filter requests. Introduce a non-static version of qdisc_destroy() that does a TCQ_F_BUILTIN check, just like qdisc_put() etc. Depends on patch "net/sched: Refactor qdisc_graft() for ingress and clsact Qdiscs". [1] To illustrate, the syzkaller reproducer adds ingress Qdiscs under TC_H_ROOT (no longer possible after commit c7cfbd115001 ("net/sched: sch_ingress: Only create under TC_H_INGRESS")) on eth0 that has 8 transmission queues: Thread 1 creates ingress Qdisc A (containing mini Qdisc a1 and a2), then adds a flower filter X to A. Thread 2 creates another ingress Qdisc B (containing mini Qdisc b1 and b2) to replace A, then adds a flower filter Y to B. Thread 1 A's refcnt Thread 2 RTM_NEWQDISC (A, RTNL-locked) qdisc_create(A) 1 qdisc_graft(A) 9 RTM_NEWTFILTER (X, RTNL-unlocked) __tcf_qdisc_find(A) 10 tcf_chain0_head_change(A) mini_qdisc_pair_swap(A) (1st) | | RTM_NEWQDISC (B, RTNL-locked) RCU sync 2 qdisc_graft(B) | 1 notify_and_destroy(A) | tcf_block_release(A) 0 RTM_NEWTFILTER (Y, RTNL-unlocked) qdisc_destroy(A) tcf_chain0_head_change(B) tcf_chain0_head_change_cb_del(A) mini_qdisc_pair_swap(B) (2nd) mini_qdisc_pair_swap(A) (3rd) | ... ... Here, B calls mini_qdisc_pair_swap(), pointing eth0->miniq_ingress to its mini Qdisc, b1. Then, A calls mini_qdisc_pair_swap() again during ingress_destroy(), setting eth0->miniq_ingress to NULL, so ingress packets on eth0 will not find filter Y in sch_handle_ingress(). This is just one of the possible consequences of concurrently accessing miniq_{in,e}gress pointers. Fixes: 7a096d579e8e ("net: sched: ingress: set 'unlocked' flag for Qdisc ops") Fixes: 87f373921c4e ("net: sched: ingress: set 'unlocked' flag for clsact Qdisc ops") Reported-by: syzbot+b53a9c0d1ea4ad62da8b@syzkaller.appspotmail.com Closes: https://lore.kernel.org/r/0000000000006cf87705f79acf1a@google.com/ Cc: Hillf Danton Cc: Vlad Buslov Signed-off-by: Peilin Ye Acked-by: Jamal Hadi Salim Signed-off-by: Paolo Abeni --- include/net/sch_generic.h | 8 ++++++++ net/sched/sch_api.c | 28 +++++++++++++++++++++++----- net/sched/sch_generic.c | 14 +++++++++++--- 3 files changed, 42 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 27271f2b37cb..12eadecf8cd0 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -137,6 +137,13 @@ static inline void qdisc_refcount_inc(struct Qdisc *qdisc) refcount_inc(&qdisc->refcnt); } +static inline bool qdisc_refcount_dec_if_one(struct Qdisc *qdisc) +{ + if (qdisc->flags & TCQ_F_BUILTIN) + return true; + return refcount_dec_if_one(&qdisc->refcnt); +} + /* Intended to be used by unlocked users, when concurrent qdisc release is * possible. */ @@ -652,6 +659,7 @@ void dev_deactivate_many(struct list_head *head); struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, struct Qdisc *qdisc); void qdisc_reset(struct Qdisc *qdisc); +void qdisc_destroy(struct Qdisc *qdisc); void qdisc_put(struct Qdisc *qdisc); void qdisc_put_unlocked(struct Qdisc *qdisc); void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, int n, int len); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 094ca3a5b633..aa6b1fe65151 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1086,10 +1086,22 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, if ((q && q->flags & TCQ_F_INGRESS) || (new && new->flags & TCQ_F_INGRESS)) { ingress = 1; - if (!dev_ingress_queue(dev)) { + dev_queue = dev_ingress_queue(dev); + if (!dev_queue) { NL_SET_ERR_MSG(extack, "Device does not have an ingress queue"); return -ENOENT; } + + q = rtnl_dereference(dev_queue->qdisc_sleeping); + + /* This is the counterpart of that qdisc_refcount_inc_nz() call in + * __tcf_qdisc_find() for filter requests. + */ + if (!qdisc_refcount_dec_if_one(q)) { + NL_SET_ERR_MSG(extack, + "Current ingress or clsact Qdisc has ongoing filter requests"); + return -EBUSY; + } } if (dev->flags & IFF_UP) @@ -1110,8 +1122,16 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, qdisc_put(old); } } else { - dev_queue = dev_ingress_queue(dev); - old = dev_graft_qdisc(dev_queue, new); + old = dev_graft_qdisc(dev_queue, NULL); + + /* {ingress,clsact}_destroy() @old before grafting @new to avoid + * unprotected concurrent accesses to net_device::miniq_{in,e}gress + * pointer(s) in mini_qdisc_pair_swap(). + */ + qdisc_notify(net, skb, n, classid, old, new, extack); + qdisc_destroy(old); + + dev_graft_qdisc(dev_queue, new); } skip: @@ -1125,8 +1145,6 @@ skip: if (new && new->ops->attach) new->ops->attach(new); - } else { - notify_and_destroy(net, skb, n, classid, old, new, extack); } if (dev->flags & IFF_UP) diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 3248259eba32..5d7e23f4cc0e 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -1046,7 +1046,7 @@ static void qdisc_free_cb(struct rcu_head *head) qdisc_free(q); } -static void qdisc_destroy(struct Qdisc *qdisc) +static void __qdisc_destroy(struct Qdisc *qdisc) { const struct Qdisc_ops *ops = qdisc->ops; @@ -1070,6 +1070,14 @@ static void qdisc_destroy(struct Qdisc *qdisc) call_rcu(&qdisc->rcu, qdisc_free_cb); } +void qdisc_destroy(struct Qdisc *qdisc) +{ + if (qdisc->flags & TCQ_F_BUILTIN) + return; + + __qdisc_destroy(qdisc); +} + void qdisc_put(struct Qdisc *qdisc) { if (!qdisc) @@ -1079,7 +1087,7 @@ void qdisc_put(struct Qdisc *qdisc) !refcount_dec_and_test(&qdisc->refcnt)) return; - qdisc_destroy(qdisc); + __qdisc_destroy(qdisc); } EXPORT_SYMBOL(qdisc_put); @@ -1094,7 +1102,7 @@ void qdisc_put_unlocked(struct Qdisc *qdisc) !refcount_dec_and_rtnl_lock(&qdisc->refcnt)) return; - qdisc_destroy(qdisc); + __qdisc_destroy(qdisc); rtnl_unlock(); } EXPORT_SYMBOL(qdisc_put_unlocked); -- cgit v1.2.3 From ec21a38df77a5aefbd2f70c48127003b6f259cf3 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 9 Jun 2023 09:16:21 +0100 Subject: Revert "media: dvb-core: Fix use-after-free on race condition at dvb_frontend" As reported by Thomas Voegtle , sometimes a DVB card does not initialize properly booting Linux 6.4-rc4. This is not always, maybe in 3 out of 4 attempts. After double-checking, the root cause seems to be related to the UAF fix, which is causing a race issue: [ 26.332149] tda10071 7-0005: found a 'NXP TDA10071' in cold state, will try to load a firmware [ 26.340779] tda10071 7-0005: downloading firmware from file 'dvb-fe-tda10071.fw' [ 989.277402] INFO: task vdr:743 blocked for more than 491 seconds. [ 989.283504] Not tainted 6.4.0-rc5-i5 #249 [ 989.288036] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 989.295860] task:vdr state:D stack:0 pid:743 ppid:711 flags:0x00004002 [ 989.295865] Call Trace: [ 989.295867] [ 989.295869] __schedule+0x2ea/0x12d0 [ 989.295877] ? asm_sysvec_apic_timer_interrupt+0x16/0x20 [ 989.295881] schedule+0x57/0xc0 [ 989.295884] schedule_preempt_disabled+0xc/0x20 [ 989.295887] __mutex_lock.isra.16+0x237/0x480 [ 989.295891] ? dvb_get_property.isra.10+0x1bc/0xa50 [ 989.295898] ? dvb_frontend_stop+0x36/0x180 [ 989.338777] dvb_frontend_stop+0x36/0x180 [ 989.338781] dvb_frontend_open+0x2f1/0x470 [ 989.338784] dvb_device_open+0x81/0xf0 [ 989.338804] ? exact_lock+0x20/0x20 [ 989.338808] chrdev_open+0x7f/0x1c0 [ 989.338811] ? generic_permission+0x1a2/0x230 [ 989.338813] ? link_path_walk.part.63+0x340/0x380 [ 989.338815] ? exact_lock+0x20/0x20 [ 989.338817] do_dentry_open+0x18e/0x450 [ 989.374030] path_openat+0xca5/0xe00 [ 989.374031] ? terminate_walk+0xec/0x100 [ 989.374034] ? path_lookupat+0x93/0x140 [ 989.374036] do_filp_open+0xc0/0x140 [ 989.374038] ? __call_rcu_common.constprop.91+0x92/0x240 [ 989.374041] ? __check_object_size+0x147/0x260 [ 989.374043] ? __check_object_size+0x147/0x260 [ 989.374045] ? alloc_fd+0xbb/0x180 [ 989.374048] ? do_sys_openat2+0x243/0x310 [ 989.374050] do_sys_openat2+0x243/0x310 [ 989.374052] do_sys_open+0x52/0x80 [ 989.374055] do_syscall_64+0x5b/0x80 [ 989.421335] ? __task_pid_nr_ns+0x92/0xa0 [ 989.421337] ? syscall_exit_to_user_mode+0x20/0x40 [ 989.421339] ? do_syscall_64+0x67/0x80 [ 989.421341] ? syscall_exit_to_user_mode+0x20/0x40 [ 989.421343] ? do_syscall_64+0x67/0x80 [ 989.421345] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 989.421348] RIP: 0033:0x7fe895d067e3 [ 989.421349] RSP: 002b:00007fff933c2ba0 EFLAGS: 00000293 ORIG_RAX: 0000000000000101 [ 989.421351] RAX: ffffffffffffffda RBX: 00007fff933c2c10 RCX: 00007fe895d067e3 [ 989.421352] RDX: 0000000000000802 RSI: 00005594acdce160 RDI: 00000000ffffff9c [ 989.421353] RBP: 0000000000000802 R08: 0000000000000000 R09: 0000000000000000 [ 989.421353] R10: 0000000000000000 R11: 0000000000000293 R12: 0000000000000001 [ 989.421354] R13: 00007fff933c2ca0 R14: 00000000ffffffff R15: 00007fff933c2c90 [ 989.421355] This reverts commit 6769a0b7ee0c3b31e1b22c3fadff2bfb642de23f. Fixes: 6769a0b7ee0c ("media: dvb-core: Fix use-after-free on race condition at dvb_frontend") Link: https://lore.kernel.org/all/da5382ad-09d6-20ac-0d53-611594b30861@lio96.de/ Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dvb_frontend.c | 53 ++++++----------------------------- include/media/dvb_frontend.h | 6 +--- 2 files changed, 10 insertions(+), 49 deletions(-) (limited to 'include') diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c index bc6950a5740f..9293b058ab99 100644 --- a/drivers/media/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb-core/dvb_frontend.c @@ -817,26 +817,15 @@ static void dvb_frontend_stop(struct dvb_frontend *fe) dev_dbg(fe->dvb->device, "%s:\n", __func__); - mutex_lock(&fe->remove_mutex); - if (fe->exit != DVB_FE_DEVICE_REMOVED) fe->exit = DVB_FE_NORMAL_EXIT; mb(); - if (!fepriv->thread) { - mutex_unlock(&fe->remove_mutex); + if (!fepriv->thread) return; - } kthread_stop(fepriv->thread); - mutex_unlock(&fe->remove_mutex); - - if (fepriv->dvbdev->users < -1) { - wait_event(fepriv->dvbdev->wait_queue, - fepriv->dvbdev->users == -1); - } - sema_init(&fepriv->sem, 1); fepriv->state = FESTATE_IDLE; @@ -2780,13 +2769,9 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) struct dvb_adapter *adapter = fe->dvb; int ret; - mutex_lock(&fe->remove_mutex); - dev_dbg(fe->dvb->device, "%s:\n", __func__); - if (fe->exit == DVB_FE_DEVICE_REMOVED) { - ret = -ENODEV; - goto err_remove_mutex; - } + if (fe->exit == DVB_FE_DEVICE_REMOVED) + return -ENODEV; if (adapter->mfe_shared == 2) { mutex_lock(&adapter->mfe_lock); @@ -2794,8 +2779,7 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (adapter->mfe_dvbdev && !adapter->mfe_dvbdev->writers) { mutex_unlock(&adapter->mfe_lock); - ret = -EBUSY; - goto err_remove_mutex; + return -EBUSY; } adapter->mfe_dvbdev = dvbdev; } @@ -2818,10 +2802,8 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) while (mferetry-- && (mfedev->users != -1 || mfepriv->thread)) { if (msleep_interruptible(500)) { - if (signal_pending(current)) { - ret = -EINTR; - goto err_remove_mutex; - } + if (signal_pending(current)) + return -EINTR; } } @@ -2833,8 +2815,7 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (mfedev->users != -1 || mfepriv->thread) { mutex_unlock(&adapter->mfe_lock); - ret = -EBUSY; - goto err_remove_mutex; + return -EBUSY; } adapter->mfe_dvbdev = dvbdev; } @@ -2893,8 +2874,6 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (adapter->mfe_shared) mutex_unlock(&adapter->mfe_lock); - - mutex_unlock(&fe->remove_mutex); return ret; err3: @@ -2916,9 +2895,6 @@ err1: err0: if (adapter->mfe_shared) mutex_unlock(&adapter->mfe_lock); - -err_remove_mutex: - mutex_unlock(&fe->remove_mutex); return ret; } @@ -2929,8 +2905,6 @@ static int dvb_frontend_release(struct inode *inode, struct file *file) struct dvb_frontend_private *fepriv = fe->frontend_priv; int ret; - mutex_lock(&fe->remove_mutex); - dev_dbg(fe->dvb->device, "%s:\n", __func__); if ((file->f_flags & O_ACCMODE) != O_RDONLY) { @@ -2952,18 +2926,10 @@ static int dvb_frontend_release(struct inode *inode, struct file *file) } mutex_unlock(&fe->dvb->mdev_lock); #endif + if (fe->exit != DVB_FE_NO_EXIT) + wake_up(&dvbdev->wait_queue); if (fe->ops.ts_bus_ctrl) fe->ops.ts_bus_ctrl(fe, 0); - - if (fe->exit != DVB_FE_NO_EXIT) { - mutex_unlock(&fe->remove_mutex); - wake_up(&dvbdev->wait_queue); - } else { - mutex_unlock(&fe->remove_mutex); - } - - } else { - mutex_unlock(&fe->remove_mutex); } dvb_frontend_put(fe); @@ -3064,7 +3030,6 @@ int dvb_register_frontend(struct dvb_adapter *dvb, fepriv = fe->frontend_priv; kref_init(&fe->refcount); - mutex_init(&fe->remove_mutex); /* * After initialization, there need to be two references: one diff --git a/include/media/dvb_frontend.h b/include/media/dvb_frontend.h index 367d5381217b..e7c44870f20d 100644 --- a/include/media/dvb_frontend.h +++ b/include/media/dvb_frontend.h @@ -686,10 +686,7 @@ struct dtv_frontend_properties { * @id: Frontend ID * @exit: Used to inform the DVB core that the frontend * thread should exit (usually, means that the hardware - * got disconnected). - * @remove_mutex: mutex that avoids a race condition between a callback - * called when the hardware is disconnected and the - * file_operations of dvb_frontend. + * got disconnected. */ struct dvb_frontend { @@ -707,7 +704,6 @@ struct dvb_frontend { int (*callback)(void *adapter_priv, int component, int cmd, int arg); int id; unsigned int exit; - struct mutex remove_mutex; }; /** -- cgit v1.2.3 From 6aa0365a3c8512587fffd42fe438768709ddef8e Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 15 Jun 2023 17:18:53 +0900 Subject: ata: libata-scsi: Avoid deadlock on rescan after device resume When an ATA port is resumed from sleep, the port is reset and a power management request issued to libata EH to reset the port and rescanning the device(s) attached to the port. Device rescanning is done by scheduling an ata_scsi_dev_rescan() work, which will execute scsi_rescan_device(). However, scsi_rescan_device() takes the generic device lock, which is also taken by dpm_resume() when the SCSI device is resumed as well. If a device rescan execution starts before the completion of the SCSI device resume, the rcu locking used to refresh the cached VPD pages of the device, combined with the generic device locking from scsi_rescan_device() and from dpm_resume() can cause a deadlock. Avoid this situation by changing struct ata_port scsi_rescan_task to be a delayed work instead of a simple work_struct. ata_scsi_dev_rescan() is modified to check if the SCSI device associated with the ATA device that must be rescanned is not suspended. If the SCSI device is still suspended, ata_scsi_dev_rescan() returns early and reschedule itself for execution after an arbitrary delay of 5ms. Reported-by: Kai-Heng Feng Reported-by: Joe Breuer Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217530 Fixes: a19a93e4c6a9 ("scsi: core: pm: Rely on the device driver core for async power management") Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Tested-by: Kai-Heng Feng Tested-by: Joe Breuer --- drivers/ata/libata-core.c | 3 ++- drivers/ata/libata-eh.c | 2 +- drivers/ata/libata-scsi.c | 22 +++++++++++++++++++++- include/linux/libata.h | 2 +- 4 files changed, 25 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 8bf612bdd61a..b4f246f0cac7 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -5348,7 +5348,7 @@ struct ata_port *ata_port_alloc(struct ata_host *host) mutex_init(&ap->scsi_scan_mutex); INIT_DELAYED_WORK(&ap->hotplug_task, ata_scsi_hotplug); - INIT_WORK(&ap->scsi_rescan_task, ata_scsi_dev_rescan); + INIT_DELAYED_WORK(&ap->scsi_rescan_task, ata_scsi_dev_rescan); INIT_LIST_HEAD(&ap->eh_done_q); init_waitqueue_head(&ap->eh_wait_q); init_completion(&ap->park_req_pending); @@ -5954,6 +5954,7 @@ static void ata_port_detach(struct ata_port *ap) WARN_ON(!(ap->pflags & ATA_PFLAG_UNLOADED)); cancel_delayed_work_sync(&ap->hotplug_task); + cancel_delayed_work_sync(&ap->scsi_rescan_task); skip_eh: /* clean up zpodd on port removal */ diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index a6c901811802..6f8d14191593 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -2984,7 +2984,7 @@ static int ata_eh_revalidate_and_attach(struct ata_link *link, ehc->i.flags |= ATA_EHI_SETMODE; /* schedule the scsi_rescan_device() here */ - schedule_work(&(ap->scsi_rescan_task)); + schedule_delayed_work(&ap->scsi_rescan_task, 0); } else if (dev->class == ATA_DEV_UNKNOWN && ehc->tries[dev->devno] && ata_class_enabled(ehc->classes[dev->devno])) { diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 8ce90284eb34..551077cea4e4 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -4597,10 +4597,11 @@ int ata_scsi_user_scan(struct Scsi_Host *shost, unsigned int channel, void ata_scsi_dev_rescan(struct work_struct *work) { struct ata_port *ap = - container_of(work, struct ata_port, scsi_rescan_task); + container_of(work, struct ata_port, scsi_rescan_task.work); struct ata_link *link; struct ata_device *dev; unsigned long flags; + bool delay_rescan = false; mutex_lock(&ap->scsi_scan_mutex); spin_lock_irqsave(ap->lock, flags); @@ -4614,6 +4615,21 @@ void ata_scsi_dev_rescan(struct work_struct *work) if (scsi_device_get(sdev)) continue; + /* + * If the rescan work was scheduled because of a resume + * event, the port is already fully resumed, but the + * SCSI device may not yet be fully resumed. In such + * case, executing scsi_rescan_device() may cause a + * deadlock with the PM code on device_lock(). Prevent + * this by giving up and retrying rescan after a short + * delay. + */ + delay_rescan = sdev->sdev_gendev.power.is_suspended; + if (delay_rescan) { + scsi_device_put(sdev); + break; + } + spin_unlock_irqrestore(ap->lock, flags); scsi_rescan_device(&(sdev->sdev_gendev)); scsi_device_put(sdev); @@ -4623,4 +4639,8 @@ void ata_scsi_dev_rescan(struct work_struct *work) spin_unlock_irqrestore(ap->lock, flags); mutex_unlock(&ap->scsi_scan_mutex); + + if (delay_rescan) + schedule_delayed_work(&ap->scsi_rescan_task, + msecs_to_jiffies(5)); } diff --git a/include/linux/libata.h b/include/linux/libata.h index 311cd93377c7..dd5797fb6305 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -836,7 +836,7 @@ struct ata_port { struct mutex scsi_scan_mutex; struct delayed_work hotplug_task; - struct work_struct scsi_rescan_task; + struct delayed_work scsi_rescan_task; unsigned int hsm_task_state; -- cgit v1.2.3