From 7efa84b5cdd6d473c7e80912638fca9d7167f202 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Fri, 4 Apr 2025 15:10:02 -0700 Subject: compiler-gcc.h: Introduce __diag_GCC_all It is not possible disabling a diagnostic for all versions of GCC without hard coding the minimum supported version at the site, as the GCC specific macros require a minimum version to disable the warning for: __diag_ignore(GCC, 5, ...); __diag_ignore_all() does not solve this issue because it disables a diagnostic for all versions of both GCC and clang, not just one or the other. Introduce __diag_GCC_all so that developers can write __diag_ignore(GCC, all, ...); to disable a particular diagnostic for all versions of GCC, while not affecting clang. Closes: https://lore.kernel.org/r/CAHk-=wgfX9nBGE0Ap9GjhOy7Mn=RSy=rx0MvqfYFFDx31KJXqQ@mail.gmail.com Signed-off-by: Nathan Chancellor Tested-by: Andy Shevchenko Reviewed-by: Petr Mladek Link: https://patch.msgid.link/20250404-vsprintf-convert-pragmas-to-__diag-v1-1-5d6c5c55b2bd@kernel.org Signed-off-by: Petr Mladek --- include/linux/compiler-gcc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index c9b58188ec61..c75a222880f9 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -127,6 +127,8 @@ #define __diag_GCC_8(s) #endif +#define __diag_GCC_all(s) __diag(s) + #define __diag_ignore_all(option, comment) \ __diag(__diag_GCC_ignore option) -- cgit v1.2.3 From de1c831a7898f164c1c2703c6b2b9e4fb4bebefc Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 15 Apr 2025 10:02:33 -0700 Subject: slab: Decouple slab_debug and no_hash_pointers Some system owners use slab_debug=FPZ (or similar) as a hardening option, but do not want to be forced into having kernel addresses exposed due to the implicit "no_hash_pointers" boot param setting.[1] Introduce the "hash_pointers" boot param, which defaults to "auto" (the current behavior), but also includes "always" (forcing on hashing even when "slab_debug=..." is defined), and "never". The existing "no_hash_pointers" boot param becomes an alias for "hash_pointers=never". This makes it possible to boot with "slab_debug=FPZ hash_pointers=always". Link: https://github.com/KSPP/linux/issues/368 [1] Fixes: 792702911f58 ("slub: force on no_hash_pointers when slub_debug is enabled") Co-developed-by: Sergio Perez Gonzalez Signed-off-by: Sergio Perez Gonzalez Acked-by: Vlastimil Babka Acked-by: David Rientjes Reviewed-by: Bagas Sanjaya Signed-off-by: Kees Cook Reviewed-by: Harry Yoo Acked-by: Rafael Aquini Tested-by: Petr Mladek Reviewed-by: Petr Mladek Link: https://patch.msgid.link/20250415170232.it.467-kees@kernel.org [kees@kernel.org: Add note about hash_pointers into slab_debug kernel parameter documentation.] Signed-off-by: Petr Mladek --- include/linux/sprintf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sprintf.h b/include/linux/sprintf.h index 51cab2def9ec..521bb2cd2648 100644 --- a/include/linux/sprintf.h +++ b/include/linux/sprintf.h @@ -22,7 +22,7 @@ __scanf(2, 0) int vsscanf(const char *, const char *, va_list); /* These are for specific cases, do not use without real need */ extern bool no_hash_pointers; -int no_hash_pointers_enable(char *str); +void hash_pointers_finalize(bool slub_debug); /* Used for Rust formatting ('%pA') */ char *rust_fmt_argument(char *buf, char *end, const void *ptr); -- cgit v1.2.3 From 7934a8dd8692b56714ce9b36421e316445d94a77 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 6 Jun 2025 13:10:23 +0900 Subject: module: remove meaningless 'name' parameter from __MODULE_INFO() The symbol names in the .modinfo section are never used and already randomized by the __UNIQUE_ID() macro. Therefore, the second parameter of __MODULE_INFO() is meaningless and can be removed to simplify the code. With this change, the symbol names in the .modinfo section will be prefixed with __UNIQUE_ID_modinfo, making it clearer that they originate from MODULE_INFO(). [Before] $ objcopy -j .modinfo vmlinux.o modinfo.o $ nm -n modinfo.o | head -n10 0000000000000000 r __UNIQUE_ID_license560 0000000000000011 r __UNIQUE_ID_file559 0000000000000030 r __UNIQUE_ID_description558 0000000000000074 r __UNIQUE_ID_license580 000000000000008e r __UNIQUE_ID_file579 00000000000000bd r __UNIQUE_ID_description578 00000000000000e6 r __UNIQUE_ID_license581 00000000000000ff r __UNIQUE_ID_file580 0000000000000134 r __UNIQUE_ID_description579 0000000000000179 r __UNIQUE_ID_uncore_no_discover578 [After] $ objcopy -j .modinfo vmlinux.o modinfo.o $ nm -n modinfo.o | head -n10 0000000000000000 r __UNIQUE_ID_modinfo560 0000000000000011 r __UNIQUE_ID_modinfo559 0000000000000030 r __UNIQUE_ID_modinfo558 0000000000000074 r __UNIQUE_ID_modinfo580 000000000000008e r __UNIQUE_ID_modinfo579 00000000000000bd r __UNIQUE_ID_modinfo578 00000000000000e6 r __UNIQUE_ID_modinfo581 00000000000000ff r __UNIQUE_ID_modinfo580 0000000000000134 r __UNIQUE_ID_modinfo579 0000000000000179 r __UNIQUE_ID_modinfo578 Signed-off-by: Masahiro Yamada Reviewed-by: Petr Pavlu --- include/crypto/algapi.h | 4 ++-- include/linux/module.h | 3 --- include/linux/moduleparam.h | 9 +++++---- include/net/tcp.h | 4 ++-- 4 files changed, 9 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h index 188eface0a11..fc4574940636 100644 --- a/include/crypto/algapi.h +++ b/include/crypto/algapi.h @@ -43,8 +43,8 @@ * alias. */ #define MODULE_ALIAS_CRYPTO(name) \ - __MODULE_INFO(alias, alias_userspace, name); \ - __MODULE_INFO(alias, alias_crypto, "crypto-" name) + MODULE_INFO(alias, name); \ + MODULE_INFO(alias, "crypto-" name) struct crypto_aead; struct crypto_instance; diff --git a/include/linux/module.h b/include/linux/module.h index 92e1420fccdf..81b41cc6a19e 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -164,9 +164,6 @@ extern void cleanup_module(void); struct module_kobject *lookup_or_create_module_kobject(const char *name); -/* Generic info of form tag = "info" */ -#define MODULE_INFO(tag, info) __MODULE_INFO(tag, tag, info) - /* For userspace: you can also call me... */ #define MODULE_ALIAS(_alias) MODULE_INFO(alias, _alias) diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index bfb85fd13e1f..00166f747e27 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -20,18 +20,19 @@ /* Chosen so that structs with an unsigned long line up. */ #define MAX_PARAM_PREFIX_LEN (64 - sizeof(unsigned long)) -#define __MODULE_INFO(tag, name, info) \ - static const char __UNIQUE_ID(name)[] \ +/* Generic info of form tag = "info" */ +#define MODULE_INFO(tag, info) \ + static const char __UNIQUE_ID(modinfo)[] \ __used __section(".modinfo") __aligned(1) \ = __MODULE_INFO_PREFIX __stringify(tag) "=" info #define __MODULE_PARM_TYPE(name, _type) \ - __MODULE_INFO(parmtype, name##type, #name ":" _type) + MODULE_INFO(parmtype, #name ":" _type) /* One for each parameter, describing how to use it. Some files do multiple of these per line, so can't just use MODULE_INFO. */ #define MODULE_PARM_DESC(_parm, desc) \ - __MODULE_INFO(parm, _parm, #_parm ":" desc) + MODULE_INFO(parm, #_parm ":" desc) struct kernel_param; diff --git a/include/net/tcp.h b/include/net/tcp.h index 5078ad868fee..9b39ef630c92 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2662,8 +2662,8 @@ void tcp_update_ulp(struct sock *sk, struct proto *p, void (*write_space)(struct sock *sk)); #define MODULE_ALIAS_TCP_ULP(name) \ - __MODULE_INFO(alias, alias_userspace, name); \ - __MODULE_INFO(alias, alias_tcp_ulp, "tcp-ulp-" name) + MODULE_INFO(alias, name); \ + MODULE_INFO(alias, "tcp-ulp-" name) #ifdef CONFIG_NET_SOCK_MSG struct sk_msg; -- cgit v1.2.3 From 50b4233a22b1ee9ccd0e847597de66ce21329ddb Mon Sep 17 00:00:00 2001 From: Julian Vetter Date: Tue, 3 Jun 2025 15:21:21 +0200 Subject: include/linux/jhash.h: replace __get_unaligned_cpu32 in jhash function __get_unaligned_cpu32() is deprecated. So, replace it with the more generic get_unaligned() and just cast the input parameter. Link: https://lkml.kernel.org/r/20250603132121.3674066-1-julian@outer-limits.org Signed-off-by: Julian Vetter Cc: Arnd Bergmann Cc: Wei-Hsin Yeh Signed-off-by: Andrew Morton --- include/linux/jhash.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/jhash.h b/include/linux/jhash.h index fa26a2dd3b52..7c1c1821c694 100644 --- a/include/linux/jhash.h +++ b/include/linux/jhash.h @@ -24,7 +24,7 @@ * Jozsef */ #include -#include +#include /* Best hash sizes are of power of two */ #define jhash_size(n) ((u32)1<<(n)) @@ -77,9 +77,9 @@ static inline u32 jhash(const void *key, u32 length, u32 initval) /* All but the last block: affect some 32 bits of (a,b,c) */ while (length > 12) { - a += __get_unaligned_cpu32(k); - b += __get_unaligned_cpu32(k + 4); - c += __get_unaligned_cpu32(k + 8); + a += get_unaligned((u32 *)k); + b += get_unaligned((u32 *)(k + 4)); + c += get_unaligned((u32 *)(k + 8)); __jhash_mix(a, b, c); length -= 12; k += 12; -- cgit v1.2.3 From 2489e958129ff7cbf26a34ee33cdc9ccbd68fe3c Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Thu, 12 Jun 2025 14:11:57 +0800 Subject: relayfs: abolish prev_padding Patch series "relayfs: misc changes", v5. The series mostly focuses on the error counters which helps every user debug their own kernel module. This patch (of 5): prev_padding represents the unused space of certain subbuffer. If the content of a call of relay_write() exceeds the limit of the remainder of this subbuffer, it will skip storing in the rest space and record the start point as buf->prev_padding in relay_switch_subbuf(). Since the buf is a per-cpu big buffer, the point of prev_padding as a global value for the whole buffer instead of a single subbuffer (whose padding info is stored in buf->padding[]) seems meaningless from the real use cases, so we don't bother to record it any more. Link: https://lkml.kernel.org/r/20250612061201.34272-1-kerneljasonxing@gmail.com Link: https://lkml.kernel.org/r/20250612061201.34272-2-kerneljasonxing@gmail.com Signed-off-by: Jason Xing Reviewed-by: Yushan Zhou Reviewed-by: Masami Hiramatsu (Google) Cc: Jens Axboe Cc: Mathieu Desnoyers Cc: Steven Rostedt Signed-off-by: Andrew Morton --- include/linux/relay.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/relay.h b/include/linux/relay.h index b3224111d074..e10a0fdf4325 100644 --- a/include/linux/relay.h +++ b/include/linux/relay.h @@ -47,7 +47,6 @@ struct rchan_buf unsigned int page_count; /* number of current buffer pages */ unsigned int finalized; /* buffer has been finalized */ size_t *padding; /* padding counts per sub-buffer */ - size_t prev_padding; /* temporary variable */ size_t bytes_consumed; /* bytes consumed in cur read subbuf */ size_t early_bytes; /* bytes consumed before VFS inited */ unsigned int cpu; /* this buf's cpu */ @@ -84,7 +83,6 @@ struct rchan_callbacks * @buf: the channel buffer containing the new sub-buffer * @subbuf: the start of the new sub-buffer * @prev_subbuf: the start of the previous sub-buffer - * @prev_padding: unused space at the end of previous sub-buffer * * The client should return 1 to continue logging, 0 to stop * logging. @@ -100,8 +98,7 @@ struct rchan_callbacks */ int (*subbuf_start) (struct rchan_buf *buf, void *subbuf, - void *prev_subbuf, - size_t prev_padding); + void *prev_subbuf); /* * create_buf_file - create file to represent a relay channel buffer -- cgit v1.2.3 From ca01a90ae7bf9bb22137e719366bdc0f387675c2 Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Thu, 12 Jun 2025 14:11:58 +0800 Subject: relayfs: support a counter tracking if per-cpu buffers is full When using relay mechanism, we often encounter the case where new data are lost or old unconsumed data are overwritten because of slow reader. Add 'full' field in per-cpu buffer structure to detect if the above case is happening. Relay has two modes: 1) non-overwrite mode, 2) overwrite mode. So buffer being full here respectively means: 1) relayfs doesn't intend to accept new data and then simply drop them, or 2) relayfs is going to start over again and overwrite old unread data with new data. Note: this counter doesn't need any explicit lock to protect from being modified by different threads for the better performance consideration. Writers calling __relay_write/relay_write should consider how to use the lock and ensure it performs under the lock protection, thus it's not necessary to add a new small lock here. Link: https://lkml.kernel.org/r/20250612061201.34272-3-kerneljasonxing@gmail.com Signed-off-by: Jason Xing Reviewed-by: Yushan Zhou Reviewed-by: Jens Axboe Reviewed-by: Masami Hiramatsu (Google) Cc: Mathieu Desnoyers Cc: Steven Rostedt Signed-off-by: Andrew Morton --- include/linux/relay.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/relay.h b/include/linux/relay.h index e10a0fdf4325..cd77eb285a48 100644 --- a/include/linux/relay.h +++ b/include/linux/relay.h @@ -28,6 +28,14 @@ */ #define RELAYFS_CHANNEL_VERSION 7 +/* + * Relay buffer statistics + */ +struct rchan_buf_stats +{ + unsigned int full_count; /* counter for buffer full */ +}; + /* * Per-cpu relay channel buffer */ @@ -43,6 +51,7 @@ struct rchan_buf struct irq_work wakeup_work; /* reader wakeup */ struct dentry *dentry; /* channel file dentry */ struct kref kref; /* channel buffer refcount */ + struct rchan_buf_stats stats; /* buffer stats */ struct page **page_array; /* array of current buffer pages */ unsigned int page_count; /* number of current buffer pages */ unsigned int finalized; /* buffer has been finalized */ -- cgit v1.2.3 From a53202ce7fbafd24f854865b02eff891e246c550 Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Thu, 12 Jun 2025 14:11:59 +0800 Subject: relayfs: introduce getting relayfs statistics function In this version, only support getting the counter for buffer full and implement the framework of how it works. Users can pass certain flag to fetch what field/statistics they expect to know. Each time it only returns one result. So do not pass multiple flags. Link: https://lkml.kernel.org/r/20250612061201.34272-4-kerneljasonxing@gmail.com Signed-off-by: Jason Xing Reviewed-by: Yushan Zhou Reviewed-by: Masami Hiramatsu (Google) Cc: Jens Axboe Cc: Mathieu Desnoyers Cc: Steven Rostedt Signed-off-by: Andrew Morton --- include/linux/relay.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/relay.h b/include/linux/relay.h index cd77eb285a48..5310967f9d74 100644 --- a/include/linux/relay.h +++ b/include/linux/relay.h @@ -31,6 +31,12 @@ /* * Relay buffer statistics */ +enum { + RELAY_STATS_BUF_FULL = (1 << 0), + + RELAY_STATS_LAST = RELAY_STATS_BUF_FULL, +}; + struct rchan_buf_stats { unsigned int full_count; /* counter for buffer full */ @@ -167,6 +173,7 @@ struct rchan *relay_open(const char *base_filename, void *private_data); extern void relay_close(struct rchan *chan); extern void relay_flush(struct rchan *chan); +size_t relay_stats(struct rchan *chan, int flags); extern void relay_subbufs_consumed(struct rchan *chan, unsigned int cpu, size_t consumed); -- cgit v1.2.3 From 19f3cb64a25b80db667a00182785577fae465b3e Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Thu, 12 Jun 2025 14:12:01 +0800 Subject: relayfs: support a counter tracking if data is too big to write It really doesn't matter if the user/admin knows what the last too big value is. Record how many times this case is triggered would be helpful. Solve the existing issue where relay_reset() doesn't restore the value. Store the counter in the per-cpu buffer structure instead of the global buffer structure. It also solves the racy condition which is likely to happen when a few of per-cpu buffers encounter the too big data case and then access the global field last_toobig without lock protection. Remove the printk in relay_close() since kernel module can directly call relay_stats() as they want. Link: https://lkml.kernel.org/r/20250612061201.34272-6-kerneljasonxing@gmail.com Signed-off-by: Jason Xing Reviewed-by: Yushan Zhou Reviewed-by: Masami Hiramatsu (Google) Cc: Jens Axboe Cc: Mathieu Desnoyers Cc: Steven Rostedt Signed-off-by: Andrew Morton --- include/linux/relay.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/relay.h b/include/linux/relay.h index 5310967f9d74..6772a7075840 100644 --- a/include/linux/relay.h +++ b/include/linux/relay.h @@ -33,13 +33,15 @@ */ enum { RELAY_STATS_BUF_FULL = (1 << 0), + RELAY_STATS_WRT_BIG = (1 << 1), - RELAY_STATS_LAST = RELAY_STATS_BUF_FULL, + RELAY_STATS_LAST = RELAY_STATS_WRT_BIG, }; struct rchan_buf_stats { unsigned int full_count; /* counter for buffer full */ + unsigned int big_count; /* counter for too big to write */ }; /* @@ -79,7 +81,6 @@ struct rchan const struct rchan_callbacks *cb; /* client callbacks */ struct kref kref; /* channel refcount */ void *private_data; /* for user-defined data */ - size_t last_toobig; /* tried to log event > subbuf size */ struct rchan_buf * __percpu *buf; /* per-cpu channel buffers */ int is_global; /* One global buffer ? */ struct list_head list; /* for channel list */ -- cgit v1.2.3 From 1857fcc847443b0238cb64584b43d8c3a9049a0a Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 17 Mar 2025 17:02:28 +0800 Subject: lib/raid6: replace custom zero page with ZERO_PAGE Use the system-wide zero page instead of a custom zero page. [herbert@gondor.apana.org.au: update lib/raid6/recov_rvv.c, per Klara] Link: https://lkml.kernel.org/r/aFkUnXWtxcgOTVkw@gondor.apana.org.au Link: https://lkml.kernel.org/r/Z9flJNkWQICx0PXk@gondor.apana.org.au Signed-off-by: Herbert Xu Cc: Song Liu Cc: Yu Kuai Cc: Klara Modin Signed-off-by: Andrew Morton --- include/linux/raid/pq.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h index 72ff44cca864..2467b3be15c9 100644 --- a/include/linux/raid/pq.h +++ b/include/linux/raid/pq.h @@ -11,8 +11,13 @@ #ifdef __KERNEL__ #include +#include -extern const char raid6_empty_zero_page[PAGE_SIZE]; +/* This should be const but the raid6 code is too convoluted for that. */ +static inline void *raid6_get_zero_page(void) +{ + return page_address(ZERO_PAGE(0)); +} #else /* ! __KERNEL__ */ /* Used for testing in user space */ @@ -191,6 +196,11 @@ static inline uint32_t raid6_jiffies(void) return tv.tv_sec*1000 + tv.tv_usec/1000; } +static inline void *raid6_get_zero_page(void) +{ + return raid6_empty_zero_page; +} + #endif /* ! __KERNEL__ */ #endif /* LINUX_RAID_RAID6_H */ -- cgit v1.2.3 From 35c18f2933c596b4fd6a98baee36f3137d133a5f Mon Sep 17 00:00:00 2001 From: Jiri Bohac Date: Thu, 12 Jun 2025 12:13:21 +0200 Subject: Add a new optional ",cma" suffix to the crashkernel= command line option Patch series "kdump: crashkernel reservation from CMA", v5. This series implements a way to reserve additional crash kernel memory using CMA. Currently, all the memory for the crash kernel is not usable by the 1st (production) kernel. It is also unmapped so that it can't be corrupted by the fault that will eventually trigger the crash. This makes sense for the memory actually used by the kexec-loaded crash kernel image and initrd and the data prepared during the load (vmcoreinfo, ...). However, the reserved space needs to be much larger than that to provide enough run-time memory for the crash kernel and the kdump userspace. Estimating the amount of memory to reserve is difficult. Being too careful makes kdump likely to end in OOM, being too generous takes even more memory from the production system. Also, the reservation only allows reserving a single contiguous block (or two with the "low" suffix). I've seen systems where this fails because the physical memory is fragmented. By reserving additional crashkernel memory from CMA, the main crashkernel reservation can be just large enough to fit the kernel and initrd image, minimizing the memory taken away from the production system. Most of the run-time memory for the crash kernel will be memory previously available to userspace in the production system. As this memory is no longer wasted, the reservation can be done with a generous margin, making kdump more reliable. Kernel memory that we need to preserve for dumping is normally not allocated from CMA, unless it is explicitly allocated as movable. Currently this is only the case for memory ballooning and zswap. Such movable memory will be missing from the vmcore. User data is typically not dumped by makedumpfile. When dumping of user data is intended this new CMA reservation cannot be used. There are five patches in this series: The first adds a new ",cma" suffix to the recenly introduced generic crashkernel parsing code. parse_crashkernel() takes one more argument to store the cma reservation size. The second patch implements reserve_crashkernel_cma() which performs the reservation. If the requested size is not available in a single range, multiple smaller ranges will be reserved. The third patch updates Documentation/, explicitly mentioning the potential DMA corruption of the CMA-reserved memory. The fourth patch adds a short delay before booting the kdump kernel, allowing pending DMA transfers to finish. The fifth patch enables the functionality for x86 as a proof of concept. There are just three things every arch needs to do: - call reserve_crashkernel_cma() - include the CMA-reserved ranges in the physical memory map - exclude the CMA-reserved ranges from the memory available through /proc/vmcore by excluding them from the vmcoreinfo PT_LOAD ranges. Adding other architectures is easy and I can do that as soon as this series is merged. With this series applied, specifying crashkernel=100M craskhernel=1G,cma on the command line will make a standard crashkernel reservation of 100M, where kexec will load the kernel and initrd. An additional 1G will be reserved from CMA, still usable by the production system. The crash kernel will have 1.1G memory available. The 100M can be reliably predicted based on the size of the kernel and initrd. The new cma suffix is completely optional. When no crashkernel=size,cma is specified, everything works as before. This patch (of 5): Add a new cma_size parameter to parse_crashkernel(). When not NULL, call __parse_crashkernel to parse the CMA reservation size from "crashkernel=size,cma" and store it in cma_size. Set cma_size to NULL in all calls to parse_crashkernel(). Link: https://lkml.kernel.org/r/aEqnxxfLZMllMC8I@dwarf.suse.cz Link: https://lkml.kernel.org/r/aEqoQckgoTQNULnh@dwarf.suse.cz Signed-off-by: Jiri Bohac Cc: Baoquan He Cc: Dave Young Cc: Donald Dutile Cc: Michal Hocko Cc: Philipp Rudo Cc: Pingfan Liu Cc: Tao Liu Cc: Vivek Goyal Cc: David Hildenbrand Signed-off-by: Andrew Morton --- include/linux/crash_reserve.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/crash_reserve.h b/include/linux/crash_reserve.h index 1fe7e7d1b214..e784aaff2f5a 100644 --- a/include/linux/crash_reserve.h +++ b/include/linux/crash_reserve.h @@ -16,7 +16,8 @@ extern struct resource crashk_low_res; int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, unsigned long long *crash_size, unsigned long long *crash_base, - unsigned long long *low_size, bool *high); + unsigned long long *low_size, unsigned long long *cma_size, + bool *high); #ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION #ifndef DEFAULT_CRASH_KERNEL_LOW_SIZE -- cgit v1.2.3 From ab475510e0422bb5672d465f9d0f523d72fdb7f1 Mon Sep 17 00:00:00 2001 From: Jiri Bohac Date: Thu, 12 Jun 2025 12:16:39 +0200 Subject: kdump: implement reserve_crashkernel_cma reserve_crashkernel_cma() reserves CMA ranges for the crash kernel. If allocating the requested size fails, try to reserve in smaller blocks. Store the reserved ranges in the crashk_cma_ranges array and the number of ranges in crashk_cma_cnt. Link: https://lkml.kernel.org/r/aEqpBwOy_ekm0gw9@dwarf.suse.cz Signed-off-by: Jiri Bohac Cc: Baoquan He Cc: Dave Young Cc: David Hildenbrand Cc: Donald Dutile Cc: Michal Hocko Cc: Philipp Rudo Cc: Pingfan Liu Cc: Tao Liu Cc: Vivek Goyal Signed-off-by: Andrew Morton --- include/linux/crash_reserve.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/crash_reserve.h b/include/linux/crash_reserve.h index e784aaff2f5a..7b44b41d0a20 100644 --- a/include/linux/crash_reserve.h +++ b/include/linux/crash_reserve.h @@ -13,12 +13,24 @@ */ extern struct resource crashk_res; extern struct resource crashk_low_res; +extern struct range crashk_cma_ranges[]; +#if defined(CONFIG_CMA) && defined(CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION) +#define CRASHKERNEL_CMA +#define CRASHKERNEL_CMA_RANGES_MAX 4 +extern int crashk_cma_cnt; +#else +#define crashk_cma_cnt 0 +#define CRASHKERNEL_CMA_RANGES_MAX 0 +#endif + int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, unsigned long long *crash_size, unsigned long long *crash_base, unsigned long long *low_size, unsigned long long *cma_size, bool *high); +void __init reserve_crashkernel_cma(unsigned long long cma_size); + #ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION #ifndef DEFAULT_CRASH_KERNEL_LOW_SIZE #define DEFAULT_CRASH_KERNEL_LOW_SIZE (128UL << 20) -- cgit v1.2.3 From b76e89e50fc3693b7b8a443ed906320d8ccb93fd Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Thu, 3 Jul 2025 10:10:01 +0800 Subject: panic: generalize panic_print's function to show sys info 'panic_print' was introduced to help debugging kernel panic by dumping different kinds of system information like tasks' call stack, memory, ftrace buffer, etc. Actually this function could also be used to help debugging other cases like task-hung, soft/hard lockup, etc. where user may need the snapshot of system info at that time. Extract system info dump function related code from panic.c to separate file sys_info.[ch], for wider usage by other kernel parts for debugging. Also modify the macro names about singulars/plurals. Link: https://lkml.kernel.org/r/20250703021004.42328-3-feng.tang@linux.alibaba.com Signed-off-by: Feng Tang Suggested-by: Petr Mladek Cc: John Ogness Cc: Jonathan Corbet Cc: Lance Yang Cc: "Paul E . McKenney" Cc: Steven Rostedt Cc: Nathan Chancellor Signed-off-by: Andrew Morton --- include/linux/sys_info.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100644 include/linux/sys_info.h (limited to 'include') diff --git a/include/linux/sys_info.h b/include/linux/sys_info.h new file mode 100644 index 000000000000..53b7e27dbf2a --- /dev/null +++ b/include/linux/sys_info.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_SYS_INFO_H +#define _LINUX_SYS_INFO_H + +/* + * SYS_INFO_PANIC_CONSOLE_REPLAY is for panic case only, as it needs special + * handling which only fits panic case. + */ +#define SYS_INFO_TASKS 0x00000001 +#define SYS_INFO_MEM 0x00000002 +#define SYS_INFO_TIMERS 0x00000004 +#define SYS_INFO_LOCKS 0x00000008 +#define SYS_INFO_FTRACE 0x00000010 +#define SYS_INFO_PANIC_CONSOLE_REPLAY 0x00000020 +#define SYS_INFO_ALL_CPU_BT 0x00000040 +#define SYS_INFO_BLOCKED_TASKS 0x00000080 + +void sys_info(unsigned long si_mask); + +#endif /* _LINUX_SYS_INFO_H */ -- cgit v1.2.3 From d747755917bf8ae08f490c3fe7d8e321afab8127 Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Thu, 3 Jul 2025 10:10:02 +0800 Subject: panic: add 'panic_sys_info' sysctl to take human readable string parameter Bitmap definition for 'panic_print' is hard to remember and decode. Add 'panic_sys_info='sysctl to take human readable string like "tasks,mem,timers,locks,ftrace,..." and translate it into bitmap. The detailed mapping is: SYS_INFO_TASKS "tasks" SYS_INFO_MEM "mem" SYS_INFO_TIMERS "timers" SYS_INFO_LOCKS "locks" SYS_INFO_FTRACE "ftrace" SYS_INFO_ALL_CPU_BT "all_bt" SYS_INFO_BLOCKED_TASKS "blocked_tasks" [nathan@kernel.org: add __maybe_unused to sys_info_avail] Link: https://lkml.kernel.org/r/20250708-fix-clang-sys_info_avail-warning-v1-1-60d239eacd64@kernel.org Link: https://lkml.kernel.org/r/20250703021004.42328-4-feng.tang@linux.alibaba.com Signed-off-by: Feng Tang Suggested-by: Petr Mladek Cc: John Ogness Cc: Jonathan Corbet Cc: Lance Yang Cc: "Paul E . McKenney" Cc: Steven Rostedt Cc: Nathan Chancellor Cc: Andy Shevchenko Signed-off-by: Andrew Morton --- include/linux/sys_info.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/sys_info.h b/include/linux/sys_info.h index 53b7e27dbf2a..89d77dc4f2ed 100644 --- a/include/linux/sys_info.h +++ b/include/linux/sys_info.h @@ -2,6 +2,8 @@ #ifndef _LINUX_SYS_INFO_H #define _LINUX_SYS_INFO_H +#include + /* * SYS_INFO_PANIC_CONSOLE_REPLAY is for panic case only, as it needs special * handling which only fits panic case. @@ -16,5 +18,11 @@ #define SYS_INFO_BLOCKED_TASKS 0x00000080 void sys_info(unsigned long si_mask); +unsigned long sys_info_parse_param(char *str); +#ifdef CONFIG_SYSCTL +int sysctl_sys_info_handler(const struct ctl_table *ro_table, int write, + void *buffer, size_t *lenp, + loff_t *ppos); +#endif #endif /* _LINUX_SYS_INFO_H */ -- cgit v1.2.3 From ae2da51def76020fa16f53cd3446c00cafe41008 Mon Sep 17 00:00:00 2001 From: Lance Yang Date: Fri, 27 Jun 2025 15:29:22 +0800 Subject: locking/rwsem: make owner helpers globally available Patch series "extend hung task blocker tracking to rwsems". Inspired by mutex blocker tracking[1], and having already extended it to semaphores, let's now add support for reader-writer semaphores (rwsems). The approach is simple: when a task enters TASK_UNINTERRUPTIBLE while waiting for an rwsem, we just call hung_task_set_blocker(). The hung task detector can then query the rwsem's owner to identify the lock holder. Tracking works reliably for writers, as there can only be a single writer holding the lock, and its task struct is stored in the owner field. The main challenge lies with readers. The owner field points to only one of many concurrent readers, so we might lose track of the blocker if that specific reader unlocks, even while others remain. This is not a significant issue, however. In practice, long-lasting lock contention is almost always caused by a writer. Therefore, reliably tracking the writer is the primary goal of this patch series ;) With this change, the hung task detector can now show blocker task's info like below: [Fri Jun 27 15:21:34 2025] INFO: task cat:28631 blocked for more than 122 seconds. [Fri Jun 27 15:21:34 2025] Tainted: G S 6.16.0-rc3 #8 [Fri Jun 27 15:21:34 2025] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [Fri Jun 27 15:21:34 2025] task:cat state:D stack:0 pid:28631 tgid:28631 ppid:28501 task_flags:0x400000 flags:0x00004000 [Fri Jun 27 15:21:34 2025] Call Trace: [Fri Jun 27 15:21:34 2025] [Fri Jun 27 15:21:34 2025] __schedule+0x7c7/0x1930 [Fri Jun 27 15:21:34 2025] ? __pfx___schedule+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? policy_nodemask+0x215/0x340 [Fri Jun 27 15:21:34 2025] ? _raw_spin_lock_irq+0x8a/0xe0 [Fri Jun 27 15:21:34 2025] ? __pfx__raw_spin_lock_irq+0x10/0x10 [Fri Jun 27 15:21:34 2025] schedule+0x6a/0x180 [Fri Jun 27 15:21:34 2025] schedule_preempt_disabled+0x15/0x30 [Fri Jun 27 15:21:34 2025] rwsem_down_read_slowpath+0x55e/0xe10 [Fri Jun 27 15:21:34 2025] ? __pfx_rwsem_down_read_slowpath+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? __pfx___might_resched+0x10/0x10 [Fri Jun 27 15:21:34 2025] down_read+0xc9/0x230 [Fri Jun 27 15:21:34 2025] ? __pfx_down_read+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? __debugfs_file_get+0x14d/0x700 [Fri Jun 27 15:21:34 2025] ? __pfx___debugfs_file_get+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? handle_pte_fault+0x52a/0x710 [Fri Jun 27 15:21:34 2025] ? selinux_file_permission+0x3a9/0x590 [Fri Jun 27 15:21:34 2025] read_dummy_rwsem_read+0x4a/0x90 [Fri Jun 27 15:21:34 2025] full_proxy_read+0xff/0x1c0 [Fri Jun 27 15:21:34 2025] ? rw_verify_area+0x6d/0x410 [Fri Jun 27 15:21:34 2025] vfs_read+0x177/0xa50 [Fri Jun 27 15:21:34 2025] ? __pfx_vfs_read+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? fdget_pos+0x1cf/0x4c0 [Fri Jun 27 15:21:34 2025] ksys_read+0xfc/0x1d0 [Fri Jun 27 15:21:34 2025] ? __pfx_ksys_read+0x10/0x10 [Fri Jun 27 15:21:34 2025] do_syscall_64+0x66/0x2d0 [Fri Jun 27 15:21:34 2025] entry_SYSCALL_64_after_hwframe+0x76/0x7e [Fri Jun 27 15:21:34 2025] RIP: 0033:0x7f3f8faefb40 [Fri Jun 27 15:21:34 2025] RSP: 002b:00007ffdeda5ab98 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [Fri Jun 27 15:21:34 2025] RAX: ffffffffffffffda RBX: 0000000000010000 RCX: 00007f3f8faefb40 [Fri Jun 27 15:21:34 2025] RDX: 0000000000010000 RSI: 00000000010fa000 RDI: 0000000000000003 [Fri Jun 27 15:21:34 2025] RBP: 00000000010fa000 R08: 0000000000000000 R09: 0000000000010fff [Fri Jun 27 15:21:34 2025] R10: 00007ffdeda59fe0 R11: 0000000000000246 R12: 00000000010fa000 [Fri Jun 27 15:21:34 2025] R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000fff [Fri Jun 27 15:21:34 2025] [Fri Jun 27 15:21:34 2025] INFO: task cat:28631 blocked on an rw-semaphore likely owned by task cat:28630 [Fri Jun 27 15:21:34 2025] task:cat state:S stack:0 pid:28630 tgid:28630 ppid:28501 task_flags:0x400000 flags:0x00004000 [Fri Jun 27 15:21:34 2025] Call Trace: [Fri Jun 27 15:21:34 2025] [Fri Jun 27 15:21:34 2025] __schedule+0x7c7/0x1930 [Fri Jun 27 15:21:34 2025] ? __pfx___schedule+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? __mod_timer+0x304/0xa80 [Fri Jun 27 15:21:34 2025] schedule+0x6a/0x180 [Fri Jun 27 15:21:34 2025] schedule_timeout+0xfb/0x230 [Fri Jun 27 15:21:34 2025] ? __pfx_schedule_timeout+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? __pfx_process_timeout+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? down_write+0xc4/0x140 [Fri Jun 27 15:21:34 2025] msleep_interruptible+0xbe/0x150 [Fri Jun 27 15:21:34 2025] read_dummy_rwsem_write+0x54/0x90 [Fri Jun 27 15:21:34 2025] full_proxy_read+0xff/0x1c0 [Fri Jun 27 15:21:34 2025] ? rw_verify_area+0x6d/0x410 [Fri Jun 27 15:21:34 2025] vfs_read+0x177/0xa50 [Fri Jun 27 15:21:34 2025] ? __pfx_vfs_read+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? fdget_pos+0x1cf/0x4c0 [Fri Jun 27 15:21:34 2025] ksys_read+0xfc/0x1d0 [Fri Jun 27 15:21:34 2025] ? __pfx_ksys_read+0x10/0x10 [Fri Jun 27 15:21:34 2025] do_syscall_64+0x66/0x2d0 [Fri Jun 27 15:21:34 2025] entry_SYSCALL_64_after_hwframe+0x76/0x7e [Fri Jun 27 15:21:34 2025] RIP: 0033:0x7f8f288efb40 [Fri Jun 27 15:21:34 2025] RSP: 002b:00007ffffb631038 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [Fri Jun 27 15:21:34 2025] RAX: ffffffffffffffda RBX: 0000000000010000 RCX: 00007f8f288efb40 [Fri Jun 27 15:21:34 2025] RDX: 0000000000010000 RSI: 000000002a4b5000 RDI: 0000000000000003 [Fri Jun 27 15:21:34 2025] RBP: 000000002a4b5000 R08: 0000000000000000 R09: 0000000000010fff [Fri Jun 27 15:21:34 2025] R10: 00007ffffb630460 R11: 0000000000000246 R12: 000000002a4b5000 [Fri Jun 27 15:21:34 2025] R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000fff [Fri Jun 27 15:21:34 2025] This patch (of 3): In preparation for extending blocker tracking to support rwsems, make the rwsem_owner() and is_rwsem_reader_owned() helpers globally available for determining if the blocker is a writer or one of the readers. Additionally, a stale owner pointer in a reader-owned rwsem can lead to false positives in blocker tracking when CONFIG_DETECT_HUNG_TASK_BLOCKER is enabled. To mitigate this, clear the owner field on the reader unlock path, similar to what CONFIG_DEBUG_RWSEMS does. A NULL owner is better than a stale one for diagnostics. Link: https://lkml.kernel.org/r/20250627072924.36567-1-lance.yang@linux.dev Link: https://lkml.kernel.org/r/20250627072924.36567-2-lance.yang@linux.dev Link: https://lore.kernel.org/all/174046694331.2194069.15472952050240807469.stgit@mhiramat.tok.corp.google.com/ [1] Signed-off-by: Lance Yang Reviewed-by: Masami Hiramatsu (Google) Cc: Anna Schumaker Cc: Boqun Feng Cc: Ingo Molnar Cc: Joel Granados Cc: John Stultz Cc: Kent Overstreet Cc: Mingzhe Yang Cc: Peter Zijlstra Cc: Sergey Senozhatsky Cc: Steven Rostedt Cc: Tomasz Figa Cc: Waiman Long Cc: Will Deacon Cc: Yongliang Gao Cc: Zi Li Signed-off-by: Andrew Morton --- include/linux/rwsem.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index c8b543d428b0..544853bed5b9 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -132,6 +132,18 @@ static inline int rwsem_is_contended(struct rw_semaphore *sem) return !list_empty(&sem->wait_list); } +#if defined(CONFIG_DEBUG_RWSEMS) || defined(CONFIG_DETECT_HUNG_TASK_BLOCKER) +/* + * Return just the real task structure pointer of the owner + */ +extern struct task_struct *rwsem_owner(struct rw_semaphore *sem); + +/* + * Return true if the rwsem is owned by a reader. + */ +extern bool is_rwsem_reader_owned(struct rw_semaphore *sem); +#endif + #else /* !CONFIG_PREEMPT_RT */ #include -- cgit v1.2.3 From 77da18de55ac6417e48905bec8b3c66f023b15a9 Mon Sep 17 00:00:00 2001 From: Lance Yang Date: Fri, 27 Jun 2025 15:29:23 +0800 Subject: hung_task: extend hung task blocker tracking to rwsems Inspired by mutex blocker tracking[1], and having already extended it to semaphores, let's now add support for reader-writer semaphores (rwsems). The approach is simple: when a task enters TASK_UNINTERRUPTIBLE while waiting for an rwsem, we just call hung_task_set_blocker(). The hung task detector can then query the rwsem's owner to identify the lock holder. Tracking works reliably for writers, as there can only be a single writer holding the lock, and its task struct is stored in the owner field. The main challenge lies with readers. The owner field points to only one of many concurrent readers, so we might lose track of the blocker if that specific reader unlocks, even while others remain. This is not a significant issue, however. In practice, long-lasting lock contention is almost always caused by a writer. Therefore, reliably tracking the writer is the primary goal of this patch series ;) With this change, the hung task detector can now show blocker task's info like below: [Fri Jun 27 15:21:34 2025] INFO: task cat:28631 blocked for more than 122 seconds. [Fri Jun 27 15:21:34 2025] Tainted: G S 6.16.0-rc3 #8 [Fri Jun 27 15:21:34 2025] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [Fri Jun 27 15:21:34 2025] task:cat state:D stack:0 pid:28631 tgid:28631 ppid:28501 task_flags:0x400000 flags:0x00004000 [Fri Jun 27 15:21:34 2025] Call Trace: [Fri Jun 27 15:21:34 2025] [Fri Jun 27 15:21:34 2025] __schedule+0x7c7/0x1930 [Fri Jun 27 15:21:34 2025] ? __pfx___schedule+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? policy_nodemask+0x215/0x340 [Fri Jun 27 15:21:34 2025] ? _raw_spin_lock_irq+0x8a/0xe0 [Fri Jun 27 15:21:34 2025] ? __pfx__raw_spin_lock_irq+0x10/0x10 [Fri Jun 27 15:21:34 2025] schedule+0x6a/0x180 [Fri Jun 27 15:21:34 2025] schedule_preempt_disabled+0x15/0x30 [Fri Jun 27 15:21:34 2025] rwsem_down_read_slowpath+0x55e/0xe10 [Fri Jun 27 15:21:34 2025] ? __pfx_rwsem_down_read_slowpath+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? __pfx___might_resched+0x10/0x10 [Fri Jun 27 15:21:34 2025] down_read+0xc9/0x230 [Fri Jun 27 15:21:34 2025] ? __pfx_down_read+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? __debugfs_file_get+0x14d/0x700 [Fri Jun 27 15:21:34 2025] ? __pfx___debugfs_file_get+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? handle_pte_fault+0x52a/0x710 [Fri Jun 27 15:21:34 2025] ? selinux_file_permission+0x3a9/0x590 [Fri Jun 27 15:21:34 2025] read_dummy_rwsem_read+0x4a/0x90 [Fri Jun 27 15:21:34 2025] full_proxy_read+0xff/0x1c0 [Fri Jun 27 15:21:34 2025] ? rw_verify_area+0x6d/0x410 [Fri Jun 27 15:21:34 2025] vfs_read+0x177/0xa50 [Fri Jun 27 15:21:34 2025] ? __pfx_vfs_read+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? fdget_pos+0x1cf/0x4c0 [Fri Jun 27 15:21:34 2025] ksys_read+0xfc/0x1d0 [Fri Jun 27 15:21:34 2025] ? __pfx_ksys_read+0x10/0x10 [Fri Jun 27 15:21:34 2025] do_syscall_64+0x66/0x2d0 [Fri Jun 27 15:21:34 2025] entry_SYSCALL_64_after_hwframe+0x76/0x7e [Fri Jun 27 15:21:34 2025] RIP: 0033:0x7f3f8faefb40 [Fri Jun 27 15:21:34 2025] RSP: 002b:00007ffdeda5ab98 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [Fri Jun 27 15:21:34 2025] RAX: ffffffffffffffda RBX: 0000000000010000 RCX: 00007f3f8faefb40 [Fri Jun 27 15:21:34 2025] RDX: 0000000000010000 RSI: 00000000010fa000 RDI: 0000000000000003 [Fri Jun 27 15:21:34 2025] RBP: 00000000010fa000 R08: 0000000000000000 R09: 0000000000010fff [Fri Jun 27 15:21:34 2025] R10: 00007ffdeda59fe0 R11: 0000000000000246 R12: 00000000010fa000 [Fri Jun 27 15:21:34 2025] R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000fff [Fri Jun 27 15:21:34 2025] [Fri Jun 27 15:21:34 2025] INFO: task cat:28631 blocked on an rw-semaphore likely owned by task cat:28630 [Fri Jun 27 15:21:34 2025] task:cat state:S stack:0 pid:28630 tgid:28630 ppid:28501 task_flags:0x400000 flags:0x00004000 [Fri Jun 27 15:21:34 2025] Call Trace: [Fri Jun 27 15:21:34 2025] [Fri Jun 27 15:21:34 2025] __schedule+0x7c7/0x1930 [Fri Jun 27 15:21:34 2025] ? __pfx___schedule+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? __mod_timer+0x304/0xa80 [Fri Jun 27 15:21:34 2025] schedule+0x6a/0x180 [Fri Jun 27 15:21:34 2025] schedule_timeout+0xfb/0x230 [Fri Jun 27 15:21:34 2025] ? __pfx_schedule_timeout+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? __pfx_process_timeout+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? down_write+0xc4/0x140 [Fri Jun 27 15:21:34 2025] msleep_interruptible+0xbe/0x150 [Fri Jun 27 15:21:34 2025] read_dummy_rwsem_write+0x54/0x90 [Fri Jun 27 15:21:34 2025] full_proxy_read+0xff/0x1c0 [Fri Jun 27 15:21:34 2025] ? rw_verify_area+0x6d/0x410 [Fri Jun 27 15:21:34 2025] vfs_read+0x177/0xa50 [Fri Jun 27 15:21:34 2025] ? __pfx_vfs_read+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? fdget_pos+0x1cf/0x4c0 [Fri Jun 27 15:21:34 2025] ksys_read+0xfc/0x1d0 [Fri Jun 27 15:21:34 2025] ? __pfx_ksys_read+0x10/0x10 [Fri Jun 27 15:21:34 2025] do_syscall_64+0x66/0x2d0 [Fri Jun 27 15:21:34 2025] entry_SYSCALL_64_after_hwframe+0x76/0x7e [Fri Jun 27 15:21:34 2025] RIP: 0033:0x7f8f288efb40 [Fri Jun 27 15:21:34 2025] RSP: 002b:00007ffffb631038 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [Fri Jun 27 15:21:34 2025] RAX: ffffffffffffffda RBX: 0000000000010000 RCX: 00007f8f288efb40 [Fri Jun 27 15:21:34 2025] RDX: 0000000000010000 RSI: 000000002a4b5000 RDI: 0000000000000003 [Fri Jun 27 15:21:34 2025] RBP: 000000002a4b5000 R08: 0000000000000000 R09: 0000000000010fff [Fri Jun 27 15:21:34 2025] R10: 00007ffffb630460 R11: 0000000000000246 R12: 000000002a4b5000 [Fri Jun 27 15:21:34 2025] R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000fff [Fri Jun 27 15:21:34 2025] [1] https://lore.kernel.org/all/174046694331.2194069.15472952050240807469.stgit@mhiramat.tok.corp.google.com/ Link: https://lkml.kernel.org/r/20250627072924.36567-3-lance.yang@linux.dev Signed-off-by: Lance Yang Suggested-by: Masami Hiramatsu (Google) Reviewed-by: Masami Hiramatsu (Google) Cc: Anna Schumaker Cc: Boqun Feng Cc: Ingo Molnar Cc: Joel Granados Cc: John Stultz Cc: Kent Overstreet Cc: Mingzhe Yang Cc: Peter Zijlstra Cc: Sergey Senozhatsky Cc: Steven Rostedt Cc: Tomasz Figa Cc: Waiman Long Cc: Will Deacon Cc: Yongliang Gao Cc: Zi Li Signed-off-by: Andrew Morton --- include/linux/hung_task.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/hung_task.h b/include/linux/hung_task.h index 1bc2b3244613..34e615c76ca5 100644 --- a/include/linux/hung_task.h +++ b/include/linux/hung_task.h @@ -21,17 +21,17 @@ * type. * * Type encoding: - * 00 - Blocked on mutex (BLOCKER_TYPE_MUTEX) - * 01 - Blocked on semaphore (BLOCKER_TYPE_SEM) - * 10 - Blocked on rt-mutex (BLOCKER_TYPE_RTMUTEX) - * 11 - Blocked on rw-semaphore (BLOCKER_TYPE_RWSEM) + * 00 - Blocked on mutex (BLOCKER_TYPE_MUTEX) + * 01 - Blocked on semaphore (BLOCKER_TYPE_SEM) + * 10 - Blocked on rw-semaphore as READER (BLOCKER_TYPE_RWSEM_READER) + * 11 - Blocked on rw-semaphore as WRITER (BLOCKER_TYPE_RWSEM_WRITER) */ -#define BLOCKER_TYPE_MUTEX 0x00UL -#define BLOCKER_TYPE_SEM 0x01UL -#define BLOCKER_TYPE_RTMUTEX 0x02UL -#define BLOCKER_TYPE_RWSEM 0x03UL +#define BLOCKER_TYPE_MUTEX 0x00UL +#define BLOCKER_TYPE_SEM 0x01UL +#define BLOCKER_TYPE_RWSEM_READER 0x02UL +#define BLOCKER_TYPE_RWSEM_WRITER 0x03UL -#define BLOCKER_TYPE_MASK 0x03UL +#define BLOCKER_TYPE_MASK 0x03UL #ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER static inline void hung_task_set_blocker(void *lock, unsigned long type) -- cgit v1.2.3 From b3d5fd6f82dde8c906dc2a587003a44252ae5eae Mon Sep 17 00:00:00 2001 From: Kuan-Wei Chiu Date: Fri, 6 Jun 2025 21:47:56 +0800 Subject: lib/math/gcd: use static key to select implementation at runtime Patch series "Optimize GCD performance on RISC-V by selecting implementation at runtime", v3. The current implementation of gcd() selects between the binary GCD and the odd-even GCD algorithm at compile time, depending on whether CONFIG_CPU_NO_EFFICIENT_FFS is set. On platforms like RISC-V, however, this compile-time decision can be misleading: even when the compiler emits ctz instructions based on the assumption that they are efficient (as is the case when CONFIG_RISCV_ISA_ZBB is enabled), the actual hardware may lack support for the Zbb extension. In such cases, ffs() falls back to a software implementation at runtime, making the binary GCD algorithm significantly slower than the odd-even variant. To address this, we introduce a static key to allow runtime selection between the binary and odd-even GCD implementations. On RISC-V, the kernel now checks for Zbb support during boot. If Zbb is unavailable, the static key is disabled so that gcd() consistently uses the more efficient odd-even algorithm in that scenario. Additionally, to further reduce code size, we select CONFIG_CPU_NO_EFFICIENT_FFS automatically when CONFIG_RISCV_ISA_ZBB is not enabled, avoiding compilation of the unused binary GCD implementation entirely on systems where it would never be executed. This series ensures that the most efficient GCD algorithm is used in practice and avoids compiling unnecessary code based on hardware capabilities and kernel configuration. This patch (of 3): On platforms like RISC-V, the compiler may generate hardware FFS instructions even if the underlying CPU does not actually support them. Currently, the GCD implementation is chosen at compile time based on CONFIG_CPU_NO_EFFICIENT_FFS, which can result in suboptimal behavior on such systems. Introduce a static key, efficient_ffs_key, to enable runtime selection between the binary GCD (using ffs) and the odd-even GCD implementation. This allows the kernel to default to the faster binary GCD when FFS is efficient, while retaining the ability to fall back when needed. Link: https://lkml.kernel.org/r/20250606134758.1308400-1-visitorckw@gmail.com Link: https://lkml.kernel.org/r/20250606134758.1308400-2-visitorckw@gmail.com Co-developed-by: Yu-Chun Lin Signed-off-by: Yu-Chun Lin Signed-off-by: Kuan-Wei Chiu Cc: Albert Ou Cc: Ching-Chun (Jim) Huang Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Alexandre Ghiti Signed-off-by: Andrew Morton --- include/linux/gcd.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/gcd.h b/include/linux/gcd.h index cb572677fd7f..616e81a7f7e3 100644 --- a/include/linux/gcd.h +++ b/include/linux/gcd.h @@ -3,6 +3,9 @@ #define _GCD_H #include +#include + +DECLARE_STATIC_KEY_TRUE(efficient_ffs_key); unsigned long gcd(unsigned long a, unsigned long b) __attribute_const__; -- cgit v1.2.3 From ad38574a8e8223361e265973fbd87013ea058c5d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 8 Jul 2025 18:03:33 +0100 Subject: f2fs: Pass a folio to ADDRS_PER_PAGE() All callers now have a folio so pass it in. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 5206d63b3386..25857877eaec 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -268,7 +268,7 @@ struct node_footer { /* Node IDs in an Indirect Block */ #define NIDS_PER_BLOCK ((F2FS_BLKSIZE - sizeof(struct node_footer)) / sizeof(__le32)) -#define ADDRS_PER_PAGE(page, inode) (addrs_per_page(inode, IS_INODE(page))) +#define ADDRS_PER_PAGE(folio, inode) (addrs_per_page(inode, IS_INODE(&folio->page))) #define NODE_DIR1_BLOCK (DEF_ADDRS_PER_INODE + 1) #define NODE_DIR2_BLOCK (DEF_ADDRS_PER_INODE + 2) -- cgit v1.2.3 From a5f3be6e652a7beaaf6c482bc013b64129a5d239 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 8 Jul 2025 18:03:34 +0100 Subject: f2fs: Pass a folio to IS_INODE() All callers now have a folio so pass it in. Also make it const to help the compiler. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 25857877eaec..2f8b8bfc0e73 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -268,7 +268,7 @@ struct node_footer { /* Node IDs in an Indirect Block */ #define NIDS_PER_BLOCK ((F2FS_BLKSIZE - sizeof(struct node_footer)) / sizeof(__le32)) -#define ADDRS_PER_PAGE(folio, inode) (addrs_per_page(inode, IS_INODE(&folio->page))) +#define ADDRS_PER_PAGE(folio, inode) (addrs_per_page(inode, IS_INODE(folio))) #define NODE_DIR1_BLOCK (DEF_ADDRS_PER_INODE + 1) #define NODE_DIR2_BLOCK (DEF_ADDRS_PER_INODE + 2) -- cgit v1.2.3 From a824388d911927b2a82bf7dcfd7cef6ee45c8b43 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 8 Jul 2025 18:03:36 +0100 Subject: f2fs: Use a folio in f2fs_is_cp_guaranteed() Convert the passed page to a folio and use it throughout. Removes a use of fscrypt_is_bounce_page(), which we're trying to remove. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/fscrypt.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 56fad33043d5..8d9127a0fdb3 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -332,12 +332,13 @@ static inline struct page *fscrypt_pagecache_page(struct page *bounce_page) return (struct page *)page_private(bounce_page); } -static inline bool fscrypt_is_bounce_folio(struct folio *folio) +static inline bool fscrypt_is_bounce_folio(const struct folio *folio) { return folio->mapping == NULL; } -static inline struct folio *fscrypt_pagecache_folio(struct folio *bounce_folio) +static inline +struct folio *fscrypt_pagecache_folio(const struct folio *bounce_folio) { return bounce_folio->private; } @@ -518,12 +519,13 @@ static inline struct page *fscrypt_pagecache_page(struct page *bounce_page) return ERR_PTR(-EINVAL); } -static inline bool fscrypt_is_bounce_folio(struct folio *folio) +static inline bool fscrypt_is_bounce_folio(const struct folio *folio) { return false; } -static inline struct folio *fscrypt_pagecache_folio(struct folio *bounce_folio) +static inline +struct folio *fscrypt_pagecache_folio(const struct folio *bounce_folio) { WARN_ON_ONCE(1); return ERR_PTR(-EINVAL); -- cgit v1.2.3 From 54091eee08acebfb5e971611c3f189e7577a1058 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 25 Jul 2025 10:58:14 +0900 Subject: scsi: libsas: Refactor dev_is_sata() Use a switch statement in dev_is_sata() to make the code more readable (and probably slightly better than a series of or conditions). Also have this inline function return a boolean instead of an integer. No functional changes. Signed-off-by: Damien Le Moal Link: https://lore.kernel.org/r/20250725015818.171252-2-dlemoal@kernel.org Reviewed-by: John Garry Reviewed-by: Jason Yan Signed-off-by: Martin K. Petersen --- include/scsi/sas_ata.h | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/scsi/sas_ata.h b/include/scsi/sas_ata.h index 92e27e7bf088..8dddd0036f99 100644 --- a/include/scsi/sas_ata.h +++ b/include/scsi/sas_ata.h @@ -15,10 +15,17 @@ #ifdef CONFIG_SCSI_SAS_ATA -static inline int dev_is_sata(struct domain_device *dev) +static inline bool dev_is_sata(struct domain_device *dev) { - return dev->dev_type == SAS_SATA_DEV || dev->dev_type == SAS_SATA_PM || - dev->dev_type == SAS_SATA_PM_PORT || dev->dev_type == SAS_SATA_PENDING; + switch (dev->dev_type) { + case SAS_SATA_DEV: + case SAS_SATA_PENDING: + case SAS_SATA_PM: + case SAS_SATA_PM_PORT: + return true; + default: + return false; + } } int sas_get_ata_info(struct domain_device *dev, struct ex_phy *phy); @@ -49,9 +56,9 @@ static inline void sas_ata_disabled_notice(void) pr_notice_once("ATA device seen but CONFIG_SCSI_SAS_ATA=N\n"); } -static inline int dev_is_sata(struct domain_device *dev) +static inline bool dev_is_sata(struct domain_device *dev) { - return 0; + return false; } static inline int sas_ata_init(struct domain_device *dev) { -- cgit v1.2.3 From bd31394aabf36ee18781c6371e02d789484ffda3 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 25 Jul 2025 10:58:16 +0900 Subject: scsi: libsas: Make sas_get_ata_info() static The function sas_get_ata_info() is used only in drivers/scsi/libsas/sas_ata.c. Remove its definition from include/scsi/sas_ata.h and make this function static. No functional changes. Signed-off-by: Damien Le Moal Link: https://lore.kernel.org/r/20250725015818.171252-4-dlemoal@kernel.org Reviewed-by: Johannes Thumshirn Reviewed-by: John Garry Reviewed-by: Jason Yan Signed-off-by: Martin K. Petersen --- include/scsi/sas_ata.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/scsi/sas_ata.h b/include/scsi/sas_ata.h index 8dddd0036f99..5e3475975aee 100644 --- a/include/scsi/sas_ata.h +++ b/include/scsi/sas_ata.h @@ -28,7 +28,6 @@ static inline bool dev_is_sata(struct domain_device *dev) } } -int sas_get_ata_info(struct domain_device *dev, struct ex_phy *phy); int sas_ata_init(struct domain_device *dev); void sas_ata_task_abort(struct sas_task *task); void sas_ata_strategy_handler(struct Scsi_Host *shost); @@ -96,11 +95,6 @@ static inline void sas_resume_sata(struct asd_sas_port *port) { } -static inline int sas_get_ata_info(struct domain_device *dev, struct ex_phy *phy) -{ - return 0; -} - static inline void sas_ata_end_eh(struct ata_port *ap) { } -- cgit v1.2.3 From 704ed03abf6b1c2752a8b16446a5ebf18694fefe Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 25 Jul 2025 10:58:17 +0900 Subject: scsi: libsas: Move declarations of internal functions to sas_internal.h Move the declaration of all functions used only within libsas from include/scsi/sas_ata.h to drivers/scsi/libsas/sas_internal.h. No functional changes. Signed-off-by: Damien Le Moal Link: https://lore.kernel.org/r/20250725015818.171252-5-dlemoal@kernel.org Reviewed-by: Johannes Thumshirn Reviewed-by: John Garry Reviewed-by: Jason Yan Signed-off-by: Martin K. Petersen --- include/scsi/sas_ata.h | 68 +------------------------------------------------- 1 file changed, 1 insertion(+), 67 deletions(-) (limited to 'include') diff --git a/include/scsi/sas_ata.h b/include/scsi/sas_ata.h index 5e3475975aee..a161c0222931 100644 --- a/include/scsi/sas_ata.h +++ b/include/scsi/sas_ata.h @@ -28,77 +28,24 @@ static inline bool dev_is_sata(struct domain_device *dev) } } -int sas_ata_init(struct domain_device *dev); -void sas_ata_task_abort(struct sas_task *task); -void sas_ata_strategy_handler(struct Scsi_Host *shost); -void sas_ata_eh(struct Scsi_Host *shost, struct list_head *work_q); void sas_ata_schedule_reset(struct domain_device *dev); -void sas_ata_wait_eh(struct domain_device *dev); -void sas_probe_sata(struct asd_sas_port *port); -void sas_suspend_sata(struct asd_sas_port *port); -void sas_resume_sata(struct asd_sas_port *port); -void sas_ata_end_eh(struct ata_port *ap); void sas_ata_device_link_abort(struct domain_device *dev, bool force_reset); -int sas_execute_ata_cmd(struct domain_device *device, u8 *fis, - int force_phy_id); +int sas_execute_ata_cmd(struct domain_device *device, u8 *fis, int force_phy_id); int smp_ata_check_ready_type(struct ata_link *link); -int sas_discover_sata(struct domain_device *dev); -int sas_ata_add_dev(struct domain_device *parent, struct ex_phy *phy, - struct domain_device *child, int phy_id); extern const struct attribute_group sas_ata_sdev_attr_group; #else -static inline void sas_ata_disabled_notice(void) -{ - pr_notice_once("ATA device seen but CONFIG_SCSI_SAS_ATA=N\n"); -} - static inline bool dev_is_sata(struct domain_device *dev) { return false; } -static inline int sas_ata_init(struct domain_device *dev) -{ - return 0; -} -static inline void sas_ata_task_abort(struct sas_task *task) -{ -} - -static inline void sas_ata_strategy_handler(struct Scsi_Host *shost) -{ -} - -static inline void sas_ata_eh(struct Scsi_Host *shost, struct list_head *work_q) -{ -} static inline void sas_ata_schedule_reset(struct domain_device *dev) { } -static inline void sas_ata_wait_eh(struct domain_device *dev) -{ -} - -static inline void sas_probe_sata(struct asd_sas_port *port) -{ -} - -static inline void sas_suspend_sata(struct asd_sas_port *port) -{ -} - -static inline void sas_resume_sata(struct asd_sas_port *port) -{ -} - -static inline void sas_ata_end_eh(struct ata_port *ap) -{ -} - static inline void sas_ata_device_link_abort(struct domain_device *dev, bool force_reset) { @@ -115,19 +62,6 @@ static inline int smp_ata_check_ready_type(struct ata_link *link) return 0; } -static inline int sas_discover_sata(struct domain_device *dev) -{ - sas_ata_disabled_notice(); - return -ENXIO; -} - -static inline int sas_ata_add_dev(struct domain_device *parent, struct ex_phy *phy, - struct domain_device *child, int phy_id) -{ - sas_ata_disabled_notice(); - return -ENODEV; -} - #define sas_ata_sdev_attr_group ((struct attribute_group) {}) #endif -- cgit v1.2.3 From 97c01e65ef4c1878532be245b2899fc4363cc453 Mon Sep 17 00:00:00 2001 From: Vicki Pfau Date: Sun, 27 Jul 2025 01:15:17 -0700 Subject: Input: Add and document BTN_GRIP* Many controllers these days have started including grip buttons. As there has been no particular assigned BTN_* constants for these, they've been haphazardly assigned to BTN_TRIGGER_HAPPY*. Unfortunately, the assignment of these has varied significantly between drivers. Add and document new constants for these grip buttons. Signed-off-by: Vicki Pfau Link: https://lore.kernel.org/r/20250702040102.125432-2-vi@endrift.com Signed-off-by: Dmitry Torokhov --- include/uapi/linux/input-event-codes.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 5a199f3d4a26..5426297d93fd 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -601,6 +601,11 @@ #define BTN_DPAD_LEFT 0x222 #define BTN_DPAD_RIGHT 0x223