From 4ca57d5139a0be3cf76c1667a4c0afb16d4a3b02 Mon Sep 17 00:00:00 2001 From: Rajaravi Krishna Katta Date: Tue, 14 Sep 2021 18:28:48 +0300 Subject: habanalabs: fix resetting args in wait for CS IOCTL In wait for CS IOCTL code, the driver resets the incoming args structure before returning to the user, regardless of the return value of the IOCTL. In case the IOCTL returns EINTR, resetting the args will result in error in case the userspace will repeat the ioctl call immediately (which is the behavior in the hl-thunk userspace library). The solution is to reset the args only if the driver returns success (0) as a return value for the IOCTL. Signed-off-by: Rajaravi Krishna Katta Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 7cc2a0f3f2f5..d13bb8c1b450 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -917,7 +917,6 @@ struct hl_wait_cs_in { #define HL_WAIT_CS_STATUS_BUSY 1 #define HL_WAIT_CS_STATUS_TIMEDOUT 2 #define HL_WAIT_CS_STATUS_ABORTED 3 -#define HL_WAIT_CS_STATUS_INTERRUPTED 4 #define HL_WAIT_CS_STATUS_FLAG_GONE 0x1 #define HL_WAIT_CS_STATUS_FLAG_TIMESTAMP_VLD 0x2 @@ -1286,7 +1285,8 @@ struct hl_debug_args { * EIO - The CS was aborted (usually because the device was reset) * ENODEV - The device wants to do hard-reset (so user need to close FD) * - * The driver also returns a custom define inside the IOCTL which can be: + * The driver also returns a custom define in case the IOCTL call returned 0. + * The define can be one of the following: * * HL_WAIT_CS_STATUS_COMPLETED - The CS has been completed successfully (0) * HL_WAIT_CS_STATUS_BUSY - The CS is still executing (0) @@ -1294,8 +1294,6 @@ struct hl_debug_args { * (ETIMEDOUT) * HL_WAIT_CS_STATUS_ABORTED - The CS was aborted, usually because the * device was reset (EIO) - * HL_WAIT_CS_STATUS_INTERRUPTED - Waiting for the CS was interrupted (EINTR) - * */ #define HL_IOCTL_WAIT_CS \ -- cgit v1.2.3 From 6098475d4cb48d821bdf453c61118c56e26294f0 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 8 Oct 2021 14:31:57 +0100 Subject: spi: Fix deadlock when adding SPI controllers on SPI buses MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently we have a global spi_add_lock which we take when adding new devices so that we can check that we're not trying to reuse a chip select that's already controlled. This means that if the SPI device is itself a SPI controller and triggers the instantiation of further SPI devices we trigger a deadlock as we try to register and instantiate those devices while in the process of doing so for the parent controller and hence already holding the global spi_add_lock. Since we only care about concurrency within a single SPI bus move the lock to be per controller, avoiding the deadlock. This can be easily triggered in the case of spi-mux. Reported-by: Uwe Kleine-König Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 8371bca13729..6b0b686f6f90 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -531,6 +531,9 @@ struct spi_controller { /* I/O mutex */ struct mutex io_mutex; + /* Used to avoid adding the same CS twice */ + struct mutex add_lock; + /* lock and mutex for SPI bus locking */ spinlock_t bus_lock_spinlock; struct mutex bus_lock_mutex; -- cgit v1.2.3 From 075718fdaf0efe20223571236c1bf14ca35a7aa1 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 14 Oct 2021 00:50:55 -0400 Subject: sctp: fix transport encap_port update in sctp_vtag_verify transport encap_port update should be updated when sctp_vtag_verify() succeeds, namely, returns 1, not returns 0. Correct it in this patch. While at it, also fix the indentation. Fixes: a1dd2cf2f1ae ("sctp: allow changing transport encap_port by peer packets") Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/sm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 2eb6d7c2c931..f37c7a558d6d 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -384,11 +384,11 @@ sctp_vtag_verify(const struct sctp_chunk *chunk, * Verification Tag value does not match the receiver's own * tag value, the receiver shall silently discard the packet... */ - if (ntohl(chunk->sctp_hdr->vtag) == asoc->c.my_vtag) - return 1; + if (ntohl(chunk->sctp_hdr->vtag) != asoc->c.my_vtag) + return 0; chunk->transport->encap_port = SCTP_INPUT_CB(chunk->skb)->encap_port; - return 0; + return 1; } /* Check VTAG of the packet matches the sender's own tag and the T bit is -- cgit v1.2.3 From a76c2315bec7afeb9bafe776fe532106fa0a8b05 Mon Sep 17 00:00:00 2001 From: Leonard Crestez Date: Fri, 15 Oct 2021 10:26:05 +0300 Subject: tcp: md5: Allow MD5SIG_FLAG_IFINDEX with ifindex=0 Multiple VRFs are generally meant to be "separate" but right now md5 keys for the default VRF also affect connections inside VRFs if the IP addresses happen to overlap. So far the combination of TCP_MD5SIG_FLAG_IFINDEX with tcpm_ifindex == 0 was an error, accept this to mean "key only applies to default VRF". This is what applications using VRFs for traffic separation want. Signed-off-by: Leonard Crestez Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/tcp.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 3166dc15d7d6..60c384569e9c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1576,6 +1576,7 @@ struct tcp_md5sig_key { u8 keylen; u8 family; /* AF_INET or AF_INET6 */ u8 prefixlen; + u8 flags; union tcp_md5_addr addr; int l3index; /* set if key added with L3 scope */ u8 key[TCP_MD5SIG_MAXKEYLEN]; @@ -1621,10 +1622,10 @@ struct tcp_md5sig_pool { int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb); int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, - int family, u8 prefixlen, int l3index, + int family, u8 prefixlen, int l3index, u8 flags, const u8 *newkey, u8 newkeylen, gfp_t gfp); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, - int family, u8 prefixlen, int l3index); + int family, u8 prefixlen, int l3index, u8 flags); struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk); -- cgit v1.2.3 From 8e141f9eb803e209714a80aa6ec073893f94c526 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 29 Sep 2021 09:12:40 +0200 Subject: block: drain file system I/O on del_gendisk Instead of delaying draining of file system I/O related items like the blk-qos queues, the integrity read workqueue and timeouts only when the request_queue is removed, do that when del_gendisk is called. This is important for SCSI where the upper level drivers that control the gendisk are separate entities, and the disk can be freed much earlier than the request_queue, or can even be unbound without tearing down the queue. Fixes: edb0872f44ec ("block: move the bdi from the request_queue to the gendisk") Reported-by: Ming Lei Signed-off-by: Christoph Hellwig Tested-by: Darrick J. Wong Link: https://lore.kernel.org/r/20210929071241.934472-5-hch@lst.de Tested-by: Yi Zhang Signed-off-by: Jens Axboe --- include/linux/genhd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index c68d83c87f83..0f5315c2b5a3 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -149,6 +149,7 @@ struct gendisk { unsigned long state; #define GD_NEED_PART_SCAN 0 #define GD_READ_ONLY 1 +#define GD_DEAD 2 struct mutex open_mutex; /* open/close mutex */ unsigned open_partitions; /* number of open partitions */ -- cgit v1.2.3 From c41108049d143304faf06852c7181262b7b0d242 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Oct 2021 11:33:01 +0200 Subject: kyber: avoid q->disk dereferences in trace points q->disk becomes invalid after the gendisk is removed. Work around this by caching the dev_t for the tracepoints. The real fix would be to properly tear down the I/O schedulers with the gendisk, but that is a much more invasive change. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211012093301.GA27795@lst.de Tested-by: Yi Zhang Signed-off-by: Jens Axboe --- include/trace/events/kyber.h | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/trace/events/kyber.h b/include/trace/events/kyber.h index 491098a0d8ed..bf7533f171ff 100644 --- a/include/trace/events/kyber.h +++ b/include/trace/events/kyber.h @@ -13,11 +13,11 @@ TRACE_EVENT(kyber_latency, - TP_PROTO(struct request_queue *q, const char *domain, const char *type, + TP_PROTO(dev_t dev, const char *domain, const char *type, unsigned int percentile, unsigned int numerator, unsigned int denominator, unsigned int samples), - TP_ARGS(q, domain, type, percentile, numerator, denominator, samples), + TP_ARGS(dev, domain, type, percentile, numerator, denominator, samples), TP_STRUCT__entry( __field( dev_t, dev ) @@ -30,7 +30,7 @@ TRACE_EVENT(kyber_latency, ), TP_fast_assign( - __entry->dev = disk_devt(q->disk); + __entry->dev = dev; strlcpy(__entry->domain, domain, sizeof(__entry->domain)); strlcpy(__entry->type, type, sizeof(__entry->type)); __entry->percentile = percentile; @@ -47,10 +47,9 @@ TRACE_EVENT(kyber_latency, TRACE_EVENT(kyber_adjust, - TP_PROTO(struct request_queue *q, const char *domain, - unsigned int depth), + TP_PROTO(dev_t dev, const char *domain, unsigned int depth), - TP_ARGS(q, domain, depth), + TP_ARGS(dev, domain, depth), TP_STRUCT__entry( __field( dev_t, dev ) @@ -59,7 +58,7 @@ TRACE_EVENT(kyber_adjust, ), TP_fast_assign( - __entry->dev = disk_devt(q->disk); + __entry->dev = dev; strlcpy(__entry->domain, domain, sizeof(__entry->domain)); __entry->depth = depth; ), @@ -71,9 +70,9 @@ TRACE_EVENT(kyber_adjust, TRACE_EVENT(kyber_throttled, - TP_PROTO(struct request_queue *q, const char *domain), + TP_PROTO(dev_t dev, const char *domain), - TP_ARGS(q, domain), + TP_ARGS(dev, domain), TP_STRUCT__entry( __field( dev_t, dev ) @@ -81,7 +80,7 @@ TRACE_EVENT(kyber_throttled, ), TP_fast_assign( - __entry->dev = disk_devt(q->disk); + __entry->dev = dev; strlcpy(__entry->domain, domain, sizeof(__entry->domain)); ), -- cgit v1.2.3 From b416beb25d9317499c823aea1522eefd8d72ea36 Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Mon, 18 Oct 2021 11:29:34 +0800 Subject: mctp: unify sockaddr_mctp types Use the more precise __kernel_sa_family_t for smctp_family, to match struct sockaddr. Also, use an unsigned int for the network member; negative networks don't make much sense. We're already using unsigned for mctp_dev and mctp_skb_cb, but need to change mctp_sock to suit. Fixes: 60fc63981693 ("mctp: Add sockaddr_mctp to uapi") Signed-off-by: Jeremy Kerr Acked-by: Eugene Syromiatnikov Signed-off-by: David S. Miller --- include/net/mctp.h | 2 +- include/uapi/linux/mctp.h | 5 +++-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/mctp.h b/include/net/mctp.h index a824d47c3c6d..ffd2c23bd76d 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -54,7 +54,7 @@ struct mctp_sock { struct sock sk; /* bind() params */ - int bind_net; + unsigned int bind_net; mctp_eid_t bind_addr; __u8 bind_type; diff --git a/include/uapi/linux/mctp.h b/include/uapi/linux/mctp.h index 52b54d13f385..f384962d8ff2 100644 --- a/include/uapi/linux/mctp.h +++ b/include/uapi/linux/mctp.h @@ -10,6 +10,7 @@ #define __UAPI_MCTP_H #include +#include typedef __u8 mctp_eid_t; @@ -18,8 +19,8 @@ struct mctp_addr { }; struct sockaddr_mctp { - unsigned short int smctp_family; - int smctp_network; + __kernel_sa_family_t smctp_family; + unsigned int smctp_network; struct mctp_addr smctp_addr; __u8 smctp_type; __u8 smctp_tag; -- cgit v1.2.3 From 5a20dd46b8b8459382685969cf0f196ae9fb9766 Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Mon, 18 Oct 2021 11:29:35 +0800 Subject: mctp: Be explicit about struct sockaddr_mctp padding We currently have some implicit padding in struct sockaddr_mctp. This patch makes this padding explicit, and ensures we have consistent layout on platforms with <32bit alignmnent. Fixes: 60fc63981693 ("mctp: Add sockaddr_mctp to uapi") Signed-off-by: Jeremy Kerr Signed-off-by: David S. Miller --- include/uapi/linux/mctp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/mctp.h b/include/uapi/linux/mctp.h index f384962d8ff2..6acd4ccafbf7 100644 --- a/include/uapi/linux/mctp.h +++ b/include/uapi/linux/mctp.h @@ -20,10 +20,12 @@ struct mctp_addr { struct sockaddr_mctp { __kernel_sa_family_t smctp_family; + __u16 __smctp_pad0; unsigned int smctp_network; struct mctp_addr smctp_addr; __u8 smctp_type; __u8 smctp_tag; + __u8 __smctp_pad1; }; #define MCTP_NET_ANY 0x0 -- cgit v1.2.3 From 15bc01effefe97757ef02ca09e9d1b927ab22725 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 16 Oct 2021 15:59:49 -0500 Subject: ucounts: Fix signal ucount refcounting In commit fda31c50292a ("signal: avoid double atomic counter increments for user accounting") Linus made a clever optimization to how rlimits and the struct user_struct. Unfortunately that optimization does not work in the obvious way when moved to nested rlimits. The problem is that the last decrement of the per user namespace per user sigpending counter might also be the last decrement of the sigpending counter in the parent user namespace as well. Which means that simply freeing the leaf ucount in __free_sigqueue is not enough. Maintain the optimization and handle the tricky cases by introducing inc_rlimit_get_ucounts and dec_rlimit_put_ucounts. By moving the entire optimization into functions that perform all of the work it becomes possible to ensure that every level is handled properly. The new function inc_rlimit_get_ucounts returns 0 on failure to increment the ucount. This is different than inc_rlimit_ucounts which increments the ucounts and returns LONG_MAX if the ucount counter has exceeded it's maximum or it wrapped (to indicate the counter needs to decremented). I wish we had a single user to account all pending signals to across all of the threads of a process so this complexity was not necessary Cc: stable@vger.kernel.org Fixes: d64696905554 ("Reimplement RLIMIT_SIGPENDING on top of ucounts") v1: https://lkml.kernel.org/r/87mtnavszx.fsf_-_@disp2133 Link: https://lkml.kernel.org/r/87fssytizw.fsf_-_@disp2133 Reviewed-by: Alexey Gladkov Tested-by: Rune Kleveland Tested-by: Yu Zhao Tested-by: Jordan Glover Signed-off-by: "Eric W. Biederman" --- include/linux/user_namespace.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index eb70cabe6e7f..33a4240e6a6f 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -127,6 +127,8 @@ static inline long get_ucounts_value(struct ucounts *ucounts, enum ucount_type t long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v); bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v); +long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type); +void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum ucount_type type); bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max); static inline void set_rlimit_ucount_max(struct user_namespace *ns, -- cgit v1.2.3 From ed65df63a39a3f6ed04f7258de8b6789e5021c18 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 18 Oct 2021 15:44:12 -0400 Subject: tracing: Have all levels of checks prevent recursion While writing an email explaining the "bit = 0" logic for a discussion on making ftrace_test_recursion_trylock() disable preemption, I discovered a path that makes the "not do the logic if bit is zero" unsafe. The recursion logic is done in hot paths like the function tracer. Thus, any code executed causes noticeable overhead. Thus, tricks are done to try to limit the amount of code executed. This included the recursion testing logic. Having recursion testing is important, as there are many paths that can end up in an infinite recursion cycle when tracing every function in the kernel. Thus protection is needed to prevent that from happening. Because it is OK to recurse due to different running context levels (e.g. an interrupt preempts a trace, and then a trace occurs in the interrupt handler), a set of bits are used to know which context one is in (normal, softirq, irq and NMI). If a recursion occurs in the same level, it is prevented*. Then there are infrastructure levels of recursion as well. When more than one callback is attached to the same function to trace, it calls a loop function to iterate over all the callbacks. Both the callbacks and the loop function have recursion protection. The callbacks use the "ftrace_test_recursion_trylock()" which has a "function" set of context bits to test, and the loop function calls the internal trace_test_and_set_recursion() directly, with an "internal" set of bits. If an architecture does not implement all the features supported by ftrace then the callbacks are never called directly, and the loop function is called instead, which will implement the features of ftrace. Since both the loop function and the callbacks do recursion protection, it was seemed unnecessary to do it in both locations. Thus, a trick was made to have the internal set of recursion bits at a more significant bit location than the function bits. Then, if any of the higher bits were set, the logic of the function bits could be skipped, as any new recursion would first have to go through the loop function. This is true for architectures that do not support all the ftrace features, because all functions being traced must first go through the loop function before going to the callbacks. But this is not true for architectures that support all the ftrace features. That's because the loop function could be called due to two callbacks attached to the same function, but then a recursion function inside the callback could be called that does not share any other callback, and it will be called directly. i.e. traced_function_1: [ more than one callback tracing it ] call loop_func loop_func: trace_recursion set internal bit call callback callback: trace_recursion [ skipped because internal bit is set, return 0 ] call traced_function_2 traced_function_2: [ only traced by above callback ] call callback callback: trace_recursion [ skipped because internal bit is set, return 0 ] call traced_function_2 [ wash, rinse, repeat, BOOM! out of shampoo! ] Thus, the "bit == 0 skip" trick is not safe, unless the loop function is call for all functions. Since we want to encourage architectures to implement all ftrace features, having them slow down due to this extra logic may encourage the maintainers to update to the latest ftrace features. And because this logic is only safe for them, remove it completely. [*] There is on layer of recursion that is allowed, and that is to allow for the transition between interrupt context (normal -> softirq -> irq -> NMI), because a trace may occur before the context update is visible to the trace recursion logic. Link: https://lore.kernel.org/all/609b565a-ed6e-a1da-f025-166691b5d994@linux.alibaba.com/ Link: https://lkml.kernel.org/r/20211018154412.09fcad3c@gandalf.local.home Cc: Linus Torvalds Cc: Petr Mladek Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Thomas Gleixner Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Josh Poimboeuf Cc: Jiri Kosina Cc: Miroslav Benes Cc: Joe Lawrence Cc: Colin Ian King Cc: Masami Hiramatsu Cc: "Peter Zijlstra (Intel)" Cc: Nicholas Piggin Cc: Jisheng Zhang Cc: =?utf-8?b?546L6LSH?= Cc: Guo Ren Cc: stable@vger.kernel.org Fixes: edc15cafcbfa3 ("tracing: Avoid unnecessary multiple recursion checks") Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_recursion.h | 49 ++++++++--------------------------------- 1 file changed, 9 insertions(+), 40 deletions(-) (limited to 'include') diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h index a9f9c5714e65..fe95f0922526 100644 --- a/include/linux/trace_recursion.h +++ b/include/linux/trace_recursion.h @@ -16,23 +16,8 @@ * When function tracing occurs, the following steps are made: * If arch does not support a ftrace feature: * call internal function (uses INTERNAL bits) which calls... - * If callback is registered to the "global" list, the list - * function is called and recursion checks the GLOBAL bits. - * then this function calls... * The function callback, which can use the FTRACE bits to * check for recursion. - * - * Now if the arch does not support a feature, and it calls - * the global list function which calls the ftrace callback - * all three of these steps will do a recursion protection. - * There's no reason to do one if the previous caller already - * did. The recursion that we are protecting against will - * go through the same steps again. - * - * To prevent the multiple recursion checks, if a recursion - * bit is set that is higher than the MAX bit of the current - * check, then we know that the check was made by the previous - * caller, and we can skip the current check. */ enum { /* Function recursion bits */ @@ -40,12 +25,14 @@ enum { TRACE_FTRACE_NMI_BIT, TRACE_FTRACE_IRQ_BIT, TRACE_FTRACE_SIRQ_BIT, + TRACE_FTRACE_TRANSITION_BIT, - /* INTERNAL_BITs must be greater than FTRACE_BITs */ + /* Internal use recursion bits */ TRACE_INTERNAL_BIT, TRACE_INTERNAL_NMI_BIT, TRACE_INTERNAL_IRQ_BIT, TRACE_INTERNAL_SIRQ_BIT, + TRACE_INTERNAL_TRANSITION_BIT, TRACE_BRANCH_BIT, /* @@ -86,12 +73,6 @@ enum { */ TRACE_GRAPH_NOTRACE_BIT, - /* - * When transitioning between context, the preempt_count() may - * not be correct. Allow for a single recursion to cover this case. - */ - TRACE_TRANSITION_BIT, - /* Used to prevent recursion recording from recursing. */ TRACE_RECORD_RECURSION_BIT, }; @@ -113,12 +94,10 @@ enum { #define TRACE_CONTEXT_BITS 4 #define TRACE_FTRACE_START TRACE_FTRACE_BIT -#define TRACE_FTRACE_MAX ((1 << (TRACE_FTRACE_START + TRACE_CONTEXT_BITS)) - 1) #define TRACE_LIST_START TRACE_INTERNAL_BIT -#define TRACE_LIST_MAX ((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1) -#define TRACE_CONTEXT_MASK TRACE_LIST_MAX +#define TRACE_CONTEXT_MASK ((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1) /* * Used for setting context @@ -132,6 +111,7 @@ enum { TRACE_CTX_IRQ, TRACE_CTX_SOFTIRQ, TRACE_CTX_NORMAL, + TRACE_CTX_TRANSITION, }; static __always_inline int trace_get_context_bit(void) @@ -160,45 +140,34 @@ extern void ftrace_record_recursion(unsigned long ip, unsigned long parent_ip); #endif static __always_inline int trace_test_and_set_recursion(unsigned long ip, unsigned long pip, - int start, int max) + int start) { unsigned int val = READ_ONCE(current->trace_recursion); int bit; - /* A previous recursion check was made */ - if ((val & TRACE_CONTEXT_MASK) > max) - return 0; - bit = trace_get_context_bit() + start; if (unlikely(val & (1 << bit))) { /* * It could be that preempt_count has not been updated during * a switch between contexts. Allow for a single recursion. */ - bit = TRACE_TRANSITION_BIT; + bit = TRACE_CTX_TRANSITION + start; if (val & (1 << bit)) { do_ftrace_record_recursion(ip, pip); return -1; } - } else { - /* Normal check passed, clear the transition to allow it again */ - val &= ~(1 << TRACE_TRANSITION_BIT); } val |= 1 << bit; current->trace_recursion = val; barrier(); - return bit + 1; + return bit; } static __always_inline void trace_clear_recursion(int bit) { - if (!bit) - return; - barrier(); - bit--; trace_recursion_clear(bit); } @@ -214,7 +183,7 @@ static __always_inline void trace_clear_recursion(int bit) static __always_inline int ftrace_test_recursion_trylock(unsigned long ip, unsigned long parent_ip) { - return trace_test_and_set_recursion(ip, parent_ip, TRACE_FTRACE_START, TRACE_FTRACE_MAX); + return trace_test_and_set_recursion(ip, parent_ip, TRACE_FTRACE_START); } /** -- cgit v1.2.3 From 76af6a054da4055305ddb28c5eb151b9ee4f74f9 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Mon, 18 Oct 2021 15:15:32 -0700 Subject: mm/migrate: add CPU hotplug to demotion #ifdef Once upon a time, the node demotion updates were driven solely by memory hotplug events. But now, there are handlers for both CPU and memory hotplug. However, the #ifdef around the code checks only memory hotplug. A system that has HOTPLUG_CPU=y but MEMORY_HOTPLUG=n would miss CPU hotplug events. Update the #ifdef around the common code. Add memory and CPU-specific #ifdefs for their handlers. These memory/CPU #ifdefs avoid unused function warnings when their Kconfig option is off. [arnd@arndb.de: rework hotplug_memory_notifier() stub] Link: https://lkml.kernel.org/r/20211013144029.2154629-1-arnd@kernel.org Link: https://lkml.kernel.org/r/20210924161255.E5FE8F7E@davehans-spike.ostc.intel.com Fixes: 884a6e5d1f93 ("mm/migrate: update node demotion order on hotplug events") Signed-off-by: Dave Hansen Signed-off-by: Arnd Bergmann Cc: "Huang, Ying" Cc: Michal Hocko Cc: Wei Xu Cc: Oscar Salvador Cc: David Rientjes Cc: Dan Williams Cc: David Hildenbrand Cc: Greg Thelen Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/memory.h b/include/linux/memory.h index 7efc0a7c14c9..182c606adb06 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -160,7 +160,10 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, #define register_hotmemory_notifier(nb) register_memory_notifier(nb) #define unregister_hotmemory_notifier(nb) unregister_memory_notifier(nb) #else -#define hotplug_memory_notifier(fn, pri) ({ 0; }) +static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri) +{ + return 0; +} /* These aren't inline functions due to a GCC bug. */ #define register_hotmemory_notifier(nb) ({ (void)(nb); 0; }) #define unregister_hotmemory_notifier(nb) ({ (void)(nb); }) -- cgit v1.2.3 From a6a0251c6fce496744121b4e08c899f45270dbcc Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Mon, 18 Oct 2021 15:15:35 -0700 Subject: mm/migrate: fix CPUHP state to update node demotion order The node demotion order needs to be updated during CPU hotplug. Because whether a NUMA node has CPU may influence the demotion order. The update function should be called during CPU online/offline after the node_states[N_CPU] has been updated. That is done in CPUHP_AP_ONLINE_DYN during CPU online and in CPUHP_MM_VMSTAT_DEAD during CPU offline. But in commit 884a6e5d1f93 ("mm/migrate: update node demotion order on hotplug events"), the function to update node demotion order is called in CPUHP_AP_ONLINE_DYN during CPU online/offline. This doesn't satisfy the order requirement. For example, there are 4 CPUs (P0, P1, P2, P3) in 2 sockets (P0, P1 in S0 and P2, P3 in S1), the demotion order is - S0 -> NUMA_NO_NODE - S1 -> NUMA_NO_NODE After P2 and P3 is offlined, because S1 has no CPU now, the demotion order should have been changed to - S0 -> S1 - S1 -> NO_NODE but it isn't changed, because the order updating callback for CPU hotplug doesn't see the new nodemask. After that, if P1 is offlined, the demotion order is changed to the expected order as above. So in this patch, we added CPUHP_AP_MM_DEMOTION_ONLINE and CPUHP_MM_DEMOTION_DEAD to be called after CPUHP_AP_ONLINE_DYN and CPUHP_MM_VMSTAT_DEAD during CPU online and offline, and register the update function on them. Link: https://lkml.kernel.org/r/20210929060351.7293-1-ying.huang@intel.com Fixes: 884a6e5d1f93 ("mm/migrate: update node demotion order on hotplug events") Signed-off-by: "Huang, Ying" Cc: Thomas Gleixner Cc: Dave Hansen Cc: Yang Shi Cc: Zi Yan Cc: Michal Hocko Cc: Wei Xu Cc: Oscar Salvador Cc: David Rientjes Cc: Dan Williams Cc: David Hildenbrand Cc: Greg Thelen Cc: Keith Busch Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuhotplug.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 832d8a74fa59..991911048857 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -72,6 +72,8 @@ enum cpuhp_state { CPUHP_SLUB_DEAD, CPUHP_DEBUG_OBJ_DEAD, CPUHP_MM_WRITEBACK_DEAD, + /* Must be after CPUHP_MM_VMSTAT_DEAD */ + CPUHP_MM_DEMOTION_DEAD, CPUHP_MM_VMSTAT_DEAD, CPUHP_SOFTIRQ_DEAD, CPUHP_NET_MVNETA_DEAD, @@ -240,6 +242,8 @@ enum cpuhp_state { CPUHP_AP_BASE_CACHEINFO_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, + /* Must be after CPUHP_AP_ONLINE_DYN for node_states[N_CPU] update */ + CPUHP_AP_MM_DEMOTION_ONLINE, CPUHP_AP_X86_HPET_ONLINE, CPUHP_AP_X86_KVM_CLK_ONLINE, CPUHP_AP_DTPM_CPU_ONLINE, -- cgit v1.2.3 From b0e901280d9860a0a35055f220e8e457f300f40a Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Mon, 18 Oct 2021 15:16:09 -0700 Subject: elfcore: correct reference to CONFIG_UML Commit 6e7b64b9dd6d ("elfcore: fix building with clang") introduces special handling for two architectures, ia64 and User Mode Linux. However, the wrong name, i.e., CONFIG_UM, for the intended Kconfig symbol for User-Mode Linux was used. Although the directory for User Mode Linux is ./arch/um; the Kconfig symbol for this architecture is called CONFIG_UML. Luckily, ./scripts/checkkconfigsymbols.py warns on non-existing configs: UM Referencing files: include/linux/elfcore.h Similar symbols: UML, NUMA Correct the name of the config to the intended one. [akpm@linux-foundation.org: fix um/x86_64, per Catalin] Link: https://lkml.kernel.org/r/20211006181119.2851441-1-catalin.marinas@arm.com Link: https://lkml.kernel.org/r/YV6pejGzLy5ppEpt@arm.com Link: https://lkml.kernel.org/r/20211006082209.417-1-lukas.bulwahn@gmail.com Fixes: 6e7b64b9dd6d ("elfcore: fix building with clang") Signed-off-by: Lukas Bulwahn Cc: Arnd Bergmann Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Catalin Marinas Cc: Barret Rhoden Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/elfcore.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index 2aaa15779d50..957ebec35aad 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -109,7 +109,7 @@ static inline int elf_core_copy_task_fpregs(struct task_struct *t, struct pt_reg #endif } -#if defined(CONFIG_UM) || defined(CONFIG_IA64) +#if (defined(CONFIG_UML) && defined(CONFIG_X86_32)) || defined(CONFIG_IA64) /* * These functions parameterize elf_core_dump in fs/binfmt_elf.c to write out * extra segments containing the gate DSO contents. Dumping its -- cgit v1.2.3 From 79f9bc5843142b649575f887dccdf1c07ad75c20 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 18 Oct 2021 15:16:16 -0700 Subject: mm/secretmem: fix NULL page->mapping dereference in page_is_secretmem() Check for a NULL page->mapping before dereferencing the mapping in page_is_secretmem(), as the page's mapping can be nullified while gup() is running, e.g. by reclaim or truncation. BUG: kernel NULL pointer dereference, address: 0000000000000068 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP NOPTI CPU: 6 PID: 4173897 Comm: CPU 3/KVM Tainted: G W RIP: 0010:internal_get_user_pages_fast+0x621/0x9d0 Code: <48> 81 7a 68 80 08 04 bc 0f 85 21 ff ff 8 89 c7 be RSP: 0018:ffffaa90087679b0 EFLAGS: 00010046 RAX: ffffe3f37905b900 RBX: 00007f2dd561e000 RCX: ffffe3f37905b934 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffe3f37905b900 ... CR2: 0000000000000068 CR3: 00000004c5898003 CR4: 00000000001726e0 Call Trace: get_user_pages_fast_only+0x13/0x20 hva_to_pfn+0xa9/0x3e0 try_async_pf+0xa1/0x270 direct_page_fault+0x113/0xad0 kvm_mmu_page_fault+0x69/0x680 vmx_handle_exit+0xe1/0x5d0 kvm_arch_vcpu_ioctl_run+0xd81/0x1c70 kvm_vcpu_ioctl+0x267/0x670 __x64_sys_ioctl+0x83/0xa0 do_syscall_64+0x56/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae Link: https://lkml.kernel.org/r/20211007231502.3552715-1-seanjc@google.com Fixes: 1507f51255c9 ("mm: introduce memfd_secret system call to create "secret" memory areas") Signed-off-by: Sean Christopherson Reported-by: Darrick J. Wong Reported-by: Stephen Tested-by: Darrick J. Wong Reviewed-by: David Hildenbrand Reviewed-by: Mike Rapoport Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/secretmem.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h index 21c3771e6a56..988528b5da43 100644 --- a/include/linux/secretmem.h +++ b/include/linux/secretmem.h @@ -23,7 +23,7 @@ static inline bool page_is_secretmem(struct page *page) mapping = (struct address_space *) ((unsigned long)page->mapping & ~PAGE_MAPPING_FLAGS); - if (mapping != page->mapping) + if (!mapping || mapping != page->mapping) return false; return mapping->a_ops == &secretmem_aops; -- cgit v1.2.3 From 14fe2471c62816ba82546fb68369d957c3a58b59 Mon Sep 17 00:00:00 2001 From: Maor Dickman Date: Thu, 7 Oct 2021 16:05:38 +0300 Subject: net/mlx5: Lag, change multipath and bonding to be mutually exclusive Both multipath and bonding events are changing the HW LAG state independently. Handling one of the features events while the other is already enabled can cause unwanted behavior, for example handling bonding event while multipath enabled will disable the lag and cause multipath to stop working. Fix it by ignoring bonding event while in multipath and ignoring FIB events while in bonding mode. Fixes: 544fe7c2e654 ("net/mlx5e: Activate HW multipath and handle port affinity based on FIB events") Signed-off-by: Maor Dickman Reviewed-by: Roi Dayan Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index e23417424373..f17d2101af7a 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1138,7 +1138,6 @@ int mlx5_cmd_create_vport_lag(struct mlx5_core_dev *dev); int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev); bool mlx5_lag_is_roce(struct mlx5_core_dev *dev); bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev); -bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev); bool mlx5_lag_is_active(struct mlx5_core_dev *dev); bool mlx5_lag_is_master(struct mlx5_core_dev *dev); bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev); -- cgit v1.2.3