From 8e98b87f515d8c4bae521048a037b2cc431c3fd5 Mon Sep 17 00:00:00 2001 From: Nuno Sa Date: Wed, 17 Jan 2024 14:10:49 +0100 Subject: iio: imu: adis: ensure proper DMA alignment Aligning the buffer to the L1 cache is not sufficient in some platforms as they might have larger cacheline sizes for caches after L1 and thus, we can't guarantee DMA safety. That was the whole reason to introduce IIO_DMA_MINALIGN in [1]. Do the same for the sigma_delta ADCs. [1]: https://lore.kernel.org/linux-iio/20220508175712.647246-2-jic23@kernel.org/ Fixes: ccd2b52f4ac6 ("staging:iio: Add common ADIS library") Signed-off-by: Nuno Sa Link: https://lore.kernel.org/r/20240117-adis-improv-v1-1-7f90e9fad200@analog.com Cc: Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index dc9ea299e088..8898966bc0f0 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -11,6 +11,7 @@ #include #include +#include #include #define ADIS_WRITE_REG(reg) ((0x80 | (reg))) @@ -131,7 +132,7 @@ struct adis { unsigned long irq_flag; void *buffer; - u8 tx[10] ____cacheline_aligned; + u8 tx[10] __aligned(IIO_DMA_MINALIGN); u8 rx[4]; }; -- cgit v1.2.3 From 59598510be1d49e1cff7fd7593293bb8e1b2398b Mon Sep 17 00:00:00 2001 From: Nuno Sa Date: Wed, 17 Jan 2024 13:41:03 +0100 Subject: iio: adc: ad_sigma_delta: ensure proper DMA alignment Aligning the buffer to the L1 cache is not sufficient in some platforms as they might have larger cacheline sizes for caches after L1 and thus, we can't guarantee DMA safety. That was the whole reason to introduce IIO_DMA_MINALIGN in [1]. Do the same for the sigma_delta ADCs. [1]: https://lore.kernel.org/linux-iio/20220508175712.647246-2-jic23@kernel.org/ Fixes: 0fb6ee8d0b5e ("iio: ad_sigma_delta: Don't put SPI transfer buffer on the stack") Signed-off-by: Nuno Sa Link: https://lore.kernel.org/r/20240117-dev_sigma_delta_no_irq_flags-v1-1-db39261592cf@analog.com Cc: Signed-off-by: Jonathan Cameron --- include/linux/iio/adc/ad_sigma_delta.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index 7852f6c9a714..719cf9cc6e1a 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -8,6 +8,8 @@ #ifndef __AD_SIGMA_DELTA_H__ #define __AD_SIGMA_DELTA_H__ +#include + enum ad_sigma_delta_mode { AD_SD_MODE_CONTINUOUS = 0, AD_SD_MODE_SINGLE = 1, @@ -99,7 +101,7 @@ struct ad_sigma_delta { * 'rx_buf' is up to 32 bits per sample + 64 bit timestamp, * rounded to 16 bytes to take into account padding. */ - uint8_t tx_buf[4] ____cacheline_aligned; + uint8_t tx_buf[4] __aligned(IIO_DMA_MINALIGN); uint8_t rx_buf[16] __aligned(8); }; -- cgit v1.2.3 From 41353fbad4f551e82c2792f7e82ac225c79cc710 Mon Sep 17 00:00:00 2001 From: Guixin Liu Date: Thu, 18 Jan 2024 20:51:45 +0800 Subject: nvmet: unify aer type enum The host and target use two definition of aer type, unify them into a single one. Signed-off-by: Guixin Liu Reviewed-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Signed-off-by: Keith Busch --- include/linux/nvme.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 462c21e0e417..68eff8c86ce3 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -816,12 +816,6 @@ struct nvme_reservation_status_ext { struct nvme_registered_ctrl_ext regctl_eds[]; }; -enum nvme_async_event_type { - NVME_AER_TYPE_ERROR = 0, - NVME_AER_TYPE_SMART = 1, - NVME_AER_TYPE_NOTICE = 2, -}; - /* I/O commands */ enum nvme_opcode { -- cgit v1.2.3 From c4608d1bf7c6536d1a3d233eb21e50678681564e Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Wed, 20 Dec 2023 22:59:43 -0800 Subject: mm: mmap: map MAP_STACK to VM_NOHUGEPAGE commit efa7df3e3bb5 ("mm: align larger anonymous mappings on THP boundaries") incured regression for stress-ng pthread benchmark [1]. It is because THP get allocated to pthread's stack area much more possible than before. Pthread's stack area is allocated by mmap without VM_GROWSDOWN or VM_GROWSUP flag, so kernel can't tell whether it is a stack area or not. The MAP_STACK flag is used to mark the stack area, but it is a no-op on Linux. Mapping MAP_STACK to VM_NOHUGEPAGE to prevent from allocating THP for such stack area. With this change the stack area looks like: fffd18e10000-fffd19610000 rw-p 00000000 00:00 0 Size: 8192 kB KernelPageSize: 4 kB MMUPageSize: 4 kB Rss: 12 kB Pss: 12 kB Pss_Dirty: 12 kB Shared_Clean: 0 kB Shared_Dirty: 0 kB Private_Clean: 0 kB Private_Dirty: 12 kB Referenced: 12 kB Anonymous: 12 kB KSM: 0 kB LazyFree: 0 kB AnonHugePages: 0 kB ShmemPmdMapped: 0 kB FilePmdMapped: 0 kB Shared_Hugetlb: 0 kB Private_Hugetlb: 0 kB Swap: 0 kB SwapPss: 0 kB Locked: 0 kB THPeligible: 0 VmFlags: rd wr mr mw me ac nh The "nh" flag is set. [1] https://lore.kernel.org/linux-mm/202312192310.56367035-oliver.sang@intel.com/ Link: https://lkml.kernel.org/r/20231221065943.2803551-2-shy828301@gmail.com Fixes: efa7df3e3bb5 ("mm: align larger anonymous mappings on THP boundaries") Signed-off-by: Yang Shi Reported-by: kernel test robot Tested-by: Oliver Sang Reviewed-by: Yin Fengwei Cc: Rik van Riel Cc: Matthew Wilcox Cc: Christopher Lameter Cc: Huang, Ying Cc: Signed-off-by: Andrew Morton --- include/linux/mman.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mman.h b/include/linux/mman.h index 40d94411d492..dc7048824be8 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -156,6 +156,7 @@ calc_vm_flag_bits(unsigned long flags) return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | + _calc_vm_trans(flags, MAP_STACK, VM_NOHUGEPAGE) | arch_calc_vm_flag_bits(flags); } -- cgit v1.2.3 From f6564fce256a3944aa1bc76cb3c40e792d97c1eb Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 18 Jan 2024 11:59:14 +0100 Subject: mm, kmsan: fix infinite recursion due to RCU critical section Alexander Potapenko writes in [1]: "For every memory access in the code instrumented by KMSAN we call kmsan_get_metadata() to obtain the metadata for the memory being accessed. For virtual memory the metadata pointers are stored in the corresponding `struct page`, therefore we need to call virt_to_page() to get them. According to the comment in arch/x86/include/asm/page.h, virt_to_page(kaddr) returns a valid pointer iff virt_addr_valid(kaddr) is true, so KMSAN needs to call virt_addr_valid() as well. To avoid recursion, kmsan_get_metadata() must not call instrumented code, therefore ./arch/x86/include/asm/kmsan.h forks parts of arch/x86/mm/physaddr.c to check whether a virtual address is valid or not. But the introduction of rcu_read_lock() to pfn_valid() added instrumented RCU API calls to virt_to_page_or_null(), which is called by kmsan_get_metadata(), so there is an infinite recursion now. I do not think it is correct to stop that recursion by doing kmsan_enter_runtime()/kmsan_exit_runtime() in kmsan_get_metadata(): that would prevent instrumented functions called from within the runtime from tracking the shadow values, which might introduce false positives." Fix the issue by switching pfn_valid() to the _sched() variant of rcu_read_lock/unlock(), which does not require calling into RCU. Given the critical section in pfn_valid() is very small, this is a reasonable trade-off (with preemptible RCU). KMSAN further needs to be careful to suppress calls into the scheduler, which would be another source of recursion. This can be done by wrapping the call to pfn_valid() into preempt_disable/enable_no_resched(). The downside is that this sacrifices breaking scheduling guarantees; however, a kernel compiled with KMSAN has already given up any performance guarantees due to being heavily instrumented. Note, KMSAN code already disables tracing via Makefile, and since mmzone.h is included, it is not necessary to use the notrace variant, which is generally preferred in all other cases. Link: https://lkml.kernel.org/r/20240115184430.2710652-1-glider@google.com [1] Link: https://lkml.kernel.org/r/20240118110022.2538350-1-elver@google.com Fixes: 5ec8e8ea8b77 ("mm/sparsemem: fix race in accessing memory_section->usage") Signed-off-by: Marco Elver Reported-by: Alexander Potapenko Reported-by: syzbot+93a9e8a3dea8d6085e12@syzkaller.appspotmail.com Reviewed-by: Alexander Potapenko Tested-by: Alexander Potapenko Cc: Charan Teja Kalla Cc: Borislav Petkov (AMD) Cc: Dave Hansen Cc: Dmitry Vyukov Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 4ed33b127821..a497f189d988 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -2013,9 +2013,9 @@ static inline int pfn_valid(unsigned long pfn) if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; ms = __pfn_to_section(pfn); - rcu_read_lock(); + rcu_read_lock_sched(); if (!valid_section(ms)) { - rcu_read_unlock(); + rcu_read_unlock_sched(); return 0; } /* @@ -2023,7 +2023,7 @@ static inline int pfn_valid(unsigned long pfn) * the entire section-sized span. */ ret = early_section(ms) || pfn_section_valid(ms, pfn); - rcu_read_unlock(); + rcu_read_unlock_sched(); return ret; } -- cgit v1.2.3 From a22fe1d6dec7e98535b97249fdc95c2be79120bb Mon Sep 17 00:00:00 2001 From: Frank Li Date: Tue, 23 Jan 2024 12:28:41 -0500 Subject: dmaengine: fix is_slave_direction() return false when DMA_DEV_TO_DEV is_slave_direction() should return true when direction is DMA_DEV_TO_DEV. Fixes: 49920bc66984 ("dmaengine: add new enum dma_transfer_direction") Signed-off-by: Frank Li Link: https://lore.kernel.org/r/20240123172842.3764529-1-Frank.Li@nxp.com Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 3df70d6131c8..752dbde4cec1 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -953,7 +953,8 @@ static inline int dmaengine_slave_config(struct dma_chan *chan, static inline bool is_slave_direction(enum dma_transfer_direction direction) { - return (direction == DMA_MEM_TO_DEV) || (direction == DMA_DEV_TO_MEM); + return (direction == DMA_MEM_TO_DEV) || (direction == DMA_DEV_TO_MEM) || + (direction == DMA_DEV_TO_DEV); } static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_single( -- cgit v1.2.3 From 5a287d3d2b9de2b3e747132c615599907ba5c3c1 Mon Sep 17 00:00:00 2001 From: Ondrej Mosnacek Date: Fri, 26 Jan 2024 19:45:31 +0100 Subject: lsm: fix default return value of the socket_getpeersec_*() hooks For these hooks the true "neutral" value is -EOPNOTSUPP, which is currently what is returned when no LSM provides this hook and what LSMs return when there is no security context set on the socket. Correct the value in and adjust the dispatch functions in security/security.c to avoid issues when the BPF LSM is enabled. Cc: stable@vger.kernel.org Fixes: 98e828a0650f ("security: Refactor declaration of LSM hooks") Signed-off-by: Ondrej Mosnacek [PM: subject line tweak] Signed-off-by: Paul Moore --- include/linux/lsm_hook_defs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 185924c56378..76458b6d53da 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -315,9 +315,9 @@ LSM_HOOK(int, 0, socket_getsockopt, struct socket *sock, int level, int optname) LSM_HOOK(int, 0, socket_setsockopt, struct socket *sock, int level, int optname) LSM_HOOK(int, 0, socket_shutdown, struct socket *sock, int how) LSM_HOOK(int, 0, socket_sock_rcv_skb, struct sock *sk, struct sk_buff *skb) -LSM_HOOK(int, 0, socket_getpeersec_stream, struct socket *sock, +LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_stream, struct socket *sock, sockptr_t optval, sockptr_t optlen, unsigned int len) -LSM_HOOK(int, 0, socket_getpeersec_dgram, struct socket *sock, +LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_dgram, struct socket *sock, struct sk_buff *skb, u32 *secid) LSM_HOOK(int, 0, sk_alloc_security, struct sock *sk, int family, gfp_t priority) LSM_HOOK(void, LSM_RET_VOID, sk_free_security, struct sock *sk) -- cgit v1.2.3 From 764ad6b02777d77dca3659ca490f0898aa593670 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Wed, 24 Jan 2024 12:26:59 +0100 Subject: HID: bpf: use __bpf_kfunc instead of noinline Follow the docs at Documentation/bpf/kfuncs.rst: - declare the function with `__bpf_kfunc` - disables missing prototype warnings, which allows to remove them from include/linux/hid-bpf.h Removing the prototypes is not an issue because we currently have to redeclare them when writing the BPF program. They will eventually be generated by bpftool directly AFAIU. Link: https://lore.kernel.org/r/20240124-b4-hid-bpf-fixes-v2-3-052520b1e5e6@kernel.org Signed-off-by: Benjamin Tissoires --- include/linux/hid_bpf.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid_bpf.h b/include/linux/hid_bpf.h index 840cd254172d..7118ac28d468 100644 --- a/include/linux/hid_bpf.h +++ b/include/linux/hid_bpf.h @@ -77,17 +77,6 @@ enum hid_bpf_attach_flags { int hid_bpf_device_event(struct hid_bpf_ctx *ctx); int hid_bpf_rdesc_fixup(struct hid_bpf_ctx *ctx); -/* Following functions are kfunc that we export to BPF programs */ -/* available everywhere in HID-BPF */ -__u8 *hid_bpf_get_data(struct hid_bpf_ctx *ctx, unsigned int offset, const size_t __sz); - -/* only available in syscall */ -int hid_bpf_attach_prog(unsigned int hid_id, int prog_fd, __u32 flags); -int hid_bpf_hw_request(struct hid_bpf_ctx *ctx, __u8 *buf, size_t buf__sz, - enum hid_report_type rtype, enum hid_class_request reqtype); -struct hid_bpf_ctx *hid_bpf_allocate_context(unsigned int hid_id); -void hid_bpf_release_context(struct hid_bpf_ctx *ctx); - /* * Below is HID internal */ -- cgit v1.2.3 From 1e560864159d002b453da42bd2c13a1805515a20 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 30 Jan 2024 11:02:43 +0100 Subject: PCI/ASPM: Fix deadlock when enabling ASPM A last minute revert in 6.7-final introduced a potential deadlock when enabling ASPM during probe of Qualcomm PCIe controllers as reported by lockdep: ============================================ WARNING: possible recursive locking detected 6.7.0 #40 Not tainted -------------------------------------------- kworker/u16:5/90 is trying to acquire lock: ffffacfa78ced000 (pci_bus_sem){++++}-{3:3}, at: pcie_aspm_pm_state_change+0x58/0xdc but task is already holding lock: ffffacfa78ced000 (pci_bus_sem){++++}-{3:3}, at: pci_walk_bus+0x34/0xbc other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(pci_bus_sem); lock(pci_bus_sem); *** DEADLOCK *** Call trace: print_deadlock_bug+0x25c/0x348 __lock_acquire+0x10a4/0x2064 lock_acquire+0x1e8/0x318 down_read+0x60/0x184 pcie_aspm_pm_state_change+0x58/0xdc pci_set_full_power_state+0xa8/0x114 pci_set_power_state+0xc4/0x120 qcom_pcie_enable_aspm+0x1c/0x3c [pcie_qcom] pci_walk_bus+0x64/0xbc qcom_pcie_host_post_init_2_7_0+0x28/0x34 [pcie_qcom] The deadlock can easily be reproduced on machines like the Lenovo ThinkPad X13s by adding a delay to increase the race window during asynchronous probe where another thread can take a write lock. Add a new pci_set_power_state_locked() and associated helper functions that can be called with the PCI bus semaphore held to avoid taking the read lock twice. Link: https://lore.kernel.org/r/ZZu0qx2cmn7IwTyQ@hovoldconsulting.com Link: https://lore.kernel.org/r/20240130100243.11011-1-johan+linaro@kernel.org Fixes: f93e71aea6c6 ("Revert "PCI/ASPM: Remove pcie_aspm_pm_state_change()"") Signed-off-by: Johan Hovold Signed-off-by: Bjorn Helgaas Cc: # 6.7 --- include/linux/pci.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index add9368e6314..7ab0d13672da 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1422,6 +1422,7 @@ int pci_load_and_free_saved_state(struct pci_dev *dev, struct pci_saved_state **state); int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state); int pci_set_power_state(struct pci_dev *dev, pci_power_t state); +int pci_set_power_state_locked(struct pci_dev *dev, pci_power_t state); pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state); bool pci_pme_capable(struct pci_dev *dev, pci_power_t state); void pci_pme_active(struct pci_dev *dev, bool enable); @@ -1625,6 +1626,8 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata); +void pci_walk_bus_locked(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), + void *userdata); int pci_cfg_space_size(struct pci_dev *dev); unsigned char pci_bus_max_busnr(struct pci_bus *bus); void pci_setup_bridge(struct pci_bus *bus); @@ -2025,6 +2028,8 @@ static inline int pci_save_state(struct pci_dev *dev) { return 0; } static inline void pci_restore_state(struct pci_dev *dev) { } static inline int pci_set_power_state(struct pci_dev *dev, pci_power_t state) { return 0; } +static inline int pci_set_power_state_locked(struct pci_dev *dev, pci_power_t state) +{ return 0; } static inline int pci_wake_from_d3(struct pci_dev *dev, bool enable) { return 0; } static inline pci_power_t pci_choose_state(struct pci_dev *dev, -- cgit v1.2.3 From 97f7cf1cd80eeed3b7c808b7c12463295c751001 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 29 Jan 2024 10:57:01 +0100 Subject: netfilter: ipset: fix performance regression in swap operation The patch "netfilter: ipset: fix race condition between swap/destroy and kernel side add/del/test", commit 28628fa9 fixes a race condition. But the synchronize_rcu() added to the swap function unnecessarily slows it down: it can safely be moved to destroy and use call_rcu() instead. Eric Dumazet pointed out that simply calling the destroy functions as rcu callback does not work: sets with timeout use garbage collectors which need cancelling at destroy which can wait. Therefore the destroy functions are split into two: cancelling garbage collectors safely at executing the command received by netlink and moving the remaining part only into the rcu callback. Link: https://lore.kernel.org/lkml/C0829B10-EAA6-4809-874E-E1E9C05A8D84@automattic.com/ Fixes: 28628fa952fe ("netfilter: ipset: fix race condition between swap/destroy and kernel side add/del/test") Reported-by: Ale Crismani Reported-by: David Wang <00107082@163.com> Tested-by: David Wang <00107082@163.com> Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index e8c350a3ade1..e9f4f845d760 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -186,6 +186,8 @@ struct ip_set_type_variant { /* Return true if "b" set is the same as "a" * according to the create set parameters */ bool (*same_set)(const struct ip_set *a, const struct ip_set *b); + /* Cancel ongoing garbage collectors before destroying the set*/ + void (*cancel_gc)(struct ip_set *set); /* Region-locking is used */ bool region_lock; }; @@ -242,6 +244,8 @@ extern void ip_set_type_unregister(struct ip_set_type *set_type); /* A generic IP set */ struct ip_set { + /* For call_cru in destroy */ + struct rcu_head rcu; /* The name of the set */ char name[IPSET_MAXNAMELEN]; /* Lock protecting the set data */ -- cgit v1.2.3 From f9e9115d0c014dec3278d68823eaff159f98f4d6 Mon Sep 17 00:00:00 2001 From: Caleb Sander Date: Wed, 31 Jan 2024 09:43:13 -0700 Subject: nvme: take const cmd pointer in read-only helpers nvme_is_fabrics() and nvme_is_write() only read struct nvme_command, so take it by const pointer. This allows callers to pass a const pointer and communicates that these functions don't modify the command. Signed-off-by: Caleb Sander Reviewed-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Signed-off-by: Keith Busch --- include/linux/nvme.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 68eff8c86ce3..bc605ec4a3fd 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1812,7 +1812,7 @@ struct nvme_command { }; }; -static inline bool nvme_is_fabrics(struct nvme_command *cmd) +static inline bool nvme_is_fabrics(const struct nvme_command *cmd) { return cmd->common.opcode == nvme_fabrics_command; } @@ -1831,7 +1831,7 @@ struct nvme_error_slot { __u8 resv2[24]; }; -static inline bool nvme_is_write(struct nvme_command *cmd) +static inline bool nvme_is_write(const struct nvme_command *cmd) { /* * What a mess... -- cgit v1.2.3 From 54ce1927eb787f7bbb7ee664841c8f5932703f39 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Wed, 31 Jan 2024 15:55:38 -0800 Subject: cxl/cper: Fix errant CPER prints for CXL events Jonathan reports that CXL CPER events dump an extra generic error message. {1}[Hardware Error]: Hardware error from APEI Generic Hardware Error Source: 1 {1}[Hardware Error]: event severity: recoverable {1}[Hardware Error]: Error 0, type: recoverable {1}[Hardware Error]: section type: unknown, fbcd0a77-c260-417f-85a9-088b1621eba6 {1}[Hardware Error]: section length: 0x90 {1}[Hardware Error]: 00000000: 00000090 00000007 00000000 0d938086 ................ {1}[Hardware Error]: 00000010: 00100000 00000000 00040000 00000000 ................ ... CXL events were rerouted though the CXL subsystem for additional processing. However, when that work was done it was missed that cper_estatus_print_section() continued with a generic error message which is confusing. Teach CPER print code to ignore printing details of some section types. Assign the CXL event GUIDs to this set to prevent confusing unknown prints. Reported-by: Jonathan Cameron Suggested-by: Jonathan Cameron Signed-off-by: Ira Weiny Reviewed-by: Dave Jiang Reviewed-by: Jonathan Cameron Reviewed-by: Alison Schofield Signed-off-by: Ard Biesheuvel --- include/linux/cper.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cper.h b/include/linux/cper.h index c1a7dc325121..265b0f8fc0b3 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -90,6 +90,29 @@ enum { GUID_INIT(0x667DD791, 0xC6B3, 0x4c27, 0x8A, 0x6B, 0x0F, 0x8E, \ 0x72, 0x2D, 0xEB, 0x41) +/* CXL Event record UUIDs are formatted as GUIDs and reported in section type */ +/* + * General Media Event Record + * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43 + */ +#define CPER_SEC_CXL_GEN_MEDIA_GUID \ + GUID_INIT(0xfbcd0a77, 0xc260, 0x417f, \ + 0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6) +/* + * DRAM Event Record + * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44 + */ +#define CPER_SEC_CXL_DRAM_GUID \ + GUID_INIT(0x601dcbb3, 0x9c06, 0x4eab, \ + 0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24) +/* + * Memory Module Event Record + * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45 + */ +#define CPER_SEC_CXL_MEM_MODULE_GUID \ + GUID_INIT(0xfe927475, 0xdd59, 0x4339, \ + 0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74) + /* * Flags bits definitions for flags in struct cper_record_header * If set, the error has been recovered -- cgit v1.2.3 From 862cf85fef85becc55a173387527adb4f076fab0 Mon Sep 17 00:00:00 2001 From: Nuno Sa Date: Wed, 31 Jan 2024 10:16:47 +0100 Subject: iio: commom: st_sensors: ensure proper DMA alignment Aligning the buffer to the L1 cache is not sufficient in some platforms as they might have larger cacheline sizes for caches after L1 and thus, we can't guarantee DMA safety. That was the whole reason to introduce IIO_DMA_MINALIGN in [1]. Do the same for st_sensors common buffer. While at it, moved the odr_lock before buffer_data as we definitely don't want any other data to share a cacheline with the buffer. [1]: https://lore.kernel.org/linux-iio/20220508175712.647246-2-jic23@kernel.org/ Fixes: e031d5f558f1 ("iio:st_sensors: remove buffer allocation at each buffer enable") Signed-off-by: Nuno Sa Cc: Link: https://lore.kernel.org/r/20240131-dev_dma_safety_stm-v2-1-580c07fae51b@analog.com Signed-off-by: Jonathan Cameron --- include/linux/iio/common/st_sensors.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 607c3a89a647..f9ae5cdd884f 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -258,9 +258,9 @@ struct st_sensor_data { bool hw_irq_trigger; s64 hw_timestamp; - char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] ____cacheline_aligned; - struct mutex odr_lock; + + char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] __aligned(IIO_DMA_MINALIGN); }; #ifdef CONFIG_IIO_BUFFER -- cgit v1.2.3 From dad6a09f3148257ac1773cd90934d721d68ab595 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 29 Jan 2024 15:56:36 -0800 Subject: hrtimer: Report offline hrtimer enqueue The hrtimers migration on CPU-down hotplug process has been moved earlier, before the CPU actually goes to die. This leaves a small window of opportunity to queue an hrtimer in a blind spot, leaving it ignored. For example a practical case has been reported with RCU waking up a SCHED_FIFO task right before the CPUHP_AP_IDLE_DEAD stage, queuing that way a sched/rt timer to the local offline CPU. Make sure such situations never go unnoticed and warn when that happens. Fixes: 5c0930ccaad5 ("hrtimers: Push pending hrtimers away from outgoing CPU earlier") Reported-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240129235646.3171983-4-boqun.feng@gmail.com --- include/linux/hrtimer.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 87e3bedf8eb0..641c4567cfa7 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -157,6 +157,7 @@ enum hrtimer_base_type { * @max_hang_time: Maximum time spent in hrtimer_interrupt * @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are * expired + * @online: CPU is online from an hrtimers point of view * @timer_waiters: A hrtimer_cancel() invocation waits for the timer * callback to finish. * @expires_next: absolute time of the next event, is required for remote @@ -179,7 +180,8 @@ struct hrtimer_cpu_base { unsigned int hres_active : 1, in_hrtirq : 1, hang_detected : 1, - softirq_activated : 1; + softirq_activated : 1, + online : 1; #ifdef CONFIG_HIGH_RES_TIMERS unsigned int nr_events; unsigned short nr_retries; -- cgit v1.2.3 From 3ee07964d407411fd578a3bc998de44fd64d266a Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Thu, 1 Feb 2024 11:55:56 +0100 Subject: serial: core: introduce uart_port_tx_flags() And an enum with a flag: UART_TX_NOSTOP. To NOT call __port->ops->stop_tx() when the circular buffer is empty. mxs-uart needs this (see the next patch). Signed-off-by: "Jiri Slaby (SUSE)" Cc: stable Tested-by: Emil Kronborg Link: https://lore.kernel.org/r/20240201105557.28043-1-jirislaby@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 32 +++++++++++++++++++++++++++----- 1 file changed, 27 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 536b2581d3e2..55b1f3ba48ac 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -748,8 +748,17 @@ struct uart_driver { void uart_write_wakeup(struct uart_port *port); -#define __uart_port_tx(uport, ch, tx_ready, put_char, tx_done, for_test, \ - for_post) \ +/** + * enum UART_TX_FLAGS -- flags for uart_port_tx_flags() + * + * @UART_TX_NOSTOP: don't call port->ops->stop_tx() on empty buffer + */ +enum UART_TX_FLAGS { + UART_TX_NOSTOP = BIT(0), +}; + +#define __uart_port_tx(uport, ch, flags, tx_ready, put_char, tx_done, \ + for_test, for_post) \ ({ \ struct uart_port *__port = (uport); \ struct circ_buf *xmit = &__port->state->xmit; \ @@ -777,7 +786,7 @@ void uart_write_wakeup(struct uart_port *port); if (pending < WAKEUP_CHARS) { \ uart_write_wakeup(__port); \ \ - if (pending == 0) \ + if (!((flags) & UART_TX_NOSTOP) && pending == 0) \ __port->ops->stop_tx(__port); \ } \ \ @@ -812,7 +821,7 @@ void uart_write_wakeup(struct uart_port *port); */ #define uart_port_tx_limited(port, ch, count, tx_ready, put_char, tx_done) ({ \ unsigned int __count = (count); \ - __uart_port_tx(port, ch, tx_ready, put_char, tx_done, __count, \ + __uart_port_tx(port, ch, 0, tx_ready, put_char, tx_done, __count, \ __count--); \ }) @@ -826,8 +835,21 @@ void uart_write_wakeup(struct uart_port *port); * See uart_port_tx_limited() for more details. */ #define uart_port_tx(port, ch, tx_ready, put_char) \ - __uart_port_tx(port, ch, tx_ready, put_char, ({}), true, ({})) + __uart_port_tx(port, ch, 0, tx_ready, put_char, ({}), true, ({})) + +/** + * uart_port_tx_flags -- transmit helper for uart_port with flags + * @port: uart port + * @ch: variable to store a character to be written to the HW + * @flags: %UART_TX_NOSTOP or similar + * @tx_ready: can HW accept more data function + * @put_char: function to write a character + * + * See uart_port_tx_limited() for more details. + */ +#define uart_port_tx_flags(port, ch, flags, tx_ready, put_char) \ + __uart_port_tx(port, ch, flags, tx_ready, put_char, ({}), true, ({})) /* * Baud rate helpers. */ -- cgit v1.2.3 From 853b8d7597eea4ccaaefbcf0942cd42fc86d542a Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 2 Feb 2024 12:22:58 +0200 Subject: remap_range: merge do_clone_file_range() into vfs_clone_file_range() commit dfad37051ade ("remap_range: move permission hooks out of do_clone_file_range()") moved the permission hooks from do_clone_file_range() out to its caller vfs_clone_file_range(), but left all the fast sanity checks in do_clone_file_range(). This makes the expensive security hooks be called in situations that they would not have been called before (e.g. fs does not support clone). The only reason for the do_clone_file_range() helper was that overlayfs did not use to be able to call vfs_clone_file_range() from copy up context with sb_writers lock held. However, since commit c63e56a4a652 ("ovl: do not open/llseek lower file with upper sb_writers held"), overlayfs just uses an open coded version of vfs_clone_file_range(). Merge_clone_file_range() into vfs_clone_file_range(), restoring the original order of checks as it was before the regressing commit and adapt the overlayfs code to call vfs_clone_file_range() before the permission hooks that were added by commit ca7ab482401c ("ovl: add permission hooks outside of do_splice_direct()"). Note that in the merge of do_clone_file_range(), the file_start_write() context was reduced to cover ->remap_file_range() without holding it over the permission hooks, which was the reason for doing the regressing commit in the first place. Reported-and-tested-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202401312229.eddeb9a6-oliver.sang@intel.com Fixes: dfad37051ade ("remap_range: move permission hooks out of do_clone_file_range()") Signed-off-by: Amir Goldstein Link: https://lore.kernel.org/r/20240202102258.1582671-1-amir73il@gmail.com Reviewed-by: Jan Kara Signed-off-by: Christian Brauner --- include/linux/fs.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index ed5966a70495..023f37c60709 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2101,9 +2101,6 @@ int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *count, unsigned int remap_flags); -extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - loff_t len, unsigned int remap_flags); extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); -- cgit v1.2.3 From f814bdda774c183b0cc15ec8f3b6e7c6f4527ba5 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 23 Jan 2024 18:58:26 +0100 Subject: blk-wbt: Fix detection of dirty-throttled tasks The detection of dirty-throttled tasks in blk-wbt has been subtly broken since its beginning in 2016. Namely if we are doing cgroup writeback and the throttled task is not in the root cgroup, balance_dirty_pages() will set dirty_sleep for the non-root bdi_writeback structure. However blk-wbt checks dirty_sleep only in the root cgroup bdi_writeback structure. Thus detection of recently throttled tasks is not working in this case (we noticed this when we switched to cgroup v2 and suddently writeback was slow). Since blk-wbt has no easy way to get to proper bdi_writeback and furthermore its intention has always been to work on the whole device rather than on individual cgroups, just move the dirty_sleep timestamp from bdi_writeback to backing_dev_info. That fixes the checking for recently throttled task and saves memory for everybody as a bonus. CC: stable@vger.kernel.org Fixes: b57d74aff9ab ("writeback: track if we're sleeping on progress in balance_dirty_pages()") Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20240123175826.21452-1-jack@suse.cz [axboe: fixup indentation errors] Signed-off-by: Jens Axboe --- include/linux/backing-dev-defs.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index ae12696ec492..2ad261082bba 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -141,8 +141,6 @@ struct bdi_writeback { struct delayed_work dwork; /* work item used for writeback */ struct delayed_work bw_dwork; /* work item used for bandwidth estimate */ - unsigned long dirty_sleep; /* last wait */ - struct list_head bdi_node; /* anchored at bdi->wb_list */ #ifdef CONFIG_CGROUP_WRITEBACK @@ -179,6 +177,11 @@ struct backing_dev_info { * any dirty wbs, which is depended upon by bdi_has_dirty(). */ atomic_long_t tot_write_bandwidth; + /* + * Jiffies when last process was dirty throttled on this bdi. Used by + * blk-wbt. + */ + unsigned long last_bdp_sleep; struct bdi_writeback wb; /* the root writeback info for this bdi */ struct list_head wb_list; /* list of all wbs */ -- cgit v1.2.3 From cd7d469c25704d414d71bf3644f163fb74e7996b Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Fri, 13 Oct 2023 13:55:44 +0800 Subject: libceph: fail sparse-read if the data length doesn't match Once this happens that means there have bugs. Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index fa018d5864e7..f66f6aac74f6 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -45,6 +45,7 @@ enum ceph_sparse_read_state { CEPH_SPARSE_READ_HDR = 0, CEPH_SPARSE_READ_EXTENTS, CEPH_SPARSE_READ_DATA_LEN, + CEPH_SPARSE_READ_DATA_PRE, CEPH_SPARSE_READ_DATA, }; @@ -64,7 +65,7 @@ struct ceph_sparse_read { u64 sr_req_len; /* orig request length */ u64 sr_pos; /* current pos in buffer */ int sr_index; /* current extent index */ - __le32 sr_datalen; /* length of actual data */ + u32 sr_datalen; /* length of actual data */ u32 sr_count; /* extent count in reply */ int sr_ext_len; /* length of extent array */ struct ceph_sparse_extent *sr_extent; /* extent array */ -- cgit v1.2.3 From 8e46a2d068c92a905d01cbb018b00d66991585ab Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 14 Dec 2023 16:01:03 +0800 Subject: libceph: just wait for more data to be available on the socket A short read may occur while reading the message footer from the socket. Later, when the socket is ready for another read, the messenger invokes all read_partial_*() handlers, including read_partial_sparse_msg_data(). The expectation is that read_partial_sparse_msg_data() would bail, allowing the messenger to invoke read_partial() for the footer and pick up where it left off. However read_partial_sparse_msg_data() violates that and ends up calling into the state machine in the OSD client. The sparse-read state machine assumes that it's a new op and interprets some piece of the footer as the sparse-read header and returns bogus extents/data length, etc. To determine whether read_partial_sparse_msg_data() should bail, let's reuse cursor->total_resid. Because once it reaches to zero that means all the extents and data have been successfully received in last read, else it could break out when partially reading any of the extents and data. And then osd_sparse_read() could continue where it left off. [ idryomov: changelog ] Link: https://tracker.ceph.com/issues/63586 Fixes: d396f89db39a ("libceph: add sparse read support to msgr1") Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- include/linux/ceph/messenger.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 2eaaabbe98cb..1717cc57cdac 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -283,7 +283,7 @@ struct ceph_msg { struct kref kref; bool more_to_follow; bool needs_out_seq; - bool sparse_read; + u64 sparse_read_total; int front_alloc_len; struct ceph_msgpool *pool; -- cgit v1.2.3 From 7d708c145b2631941b8b0b4a740dc2990818c39c Mon Sep 17 00:00:00 2001 From: Thinh Nguyen Date: Fri, 9 Feb 2024 01:24:54 +0000 Subject: Revert "usb: dwc3: Support EBC feature of DWC_usb31" This reverts commit 398aa9a7e77cf23c2a6f882ddd3dcd96f21771dc. The update to the gadget API to support EBC feature is incomplete. It's missing at least the following: * New usage documentation * Gadget capability check * Condition for the user to check how many and which endpoints can be used as "fifo_mode" * Description of how it can affect completed request (e.g. dwc3 won't update TRB on completion -- ie. how it can affect request's actual length report) Let's revert this until it's ready. Fixes: 398aa9a7e77c ("usb: dwc3: Support EBC feature of DWC_usb31") Signed-off-by: Thinh Nguyen Link: https://lore.kernel.org/r/3042f847ff904b4dd4e4cf66a1b9df470e63439e.1707441690.git.Thinh.Nguyen@synopsys.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gadget.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index a771ccc038ac..6532beb587b1 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -236,7 +236,6 @@ struct usb_ep { unsigned max_streams:16; unsigned mult:2; unsigned maxburst:5; - unsigned fifo_mode:1; u8 address; const struct usb_endpoint_descriptor *desc; const struct usb_ss_ep_comp_descriptor *comp_desc; -- cgit v1.2.3 From 4356e9f841f7fbb945521cef3577ba394c65f3fc Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 9 Feb 2024 12:39:31 -0800 Subject: work around gcc bugs with 'asm goto' with outputs We've had issues with gcc and 'asm goto' before, and we created a 'asm_volatile_goto()' macro for that in the past: see commits 3f0116c3238a ("compiler/gcc4: Add quirk for 'asm goto' miscompilation bug") and a9f180345f53 ("compiler/gcc4: Make quirk for asm_volatile_goto() unconditional"). Then, much later, we ended up removing the workaround in commit 43c249ea0b1e ("compiler-gcc.h: remove ancient workaround for gcc PR 58670") because we no longer supported building the kernel with the affected gcc versions, but we left the macro uses around. Now, Sean Christopherson reports a new version of a very similar problem, which is fixed by re-applying that ancient workaround. But the problem in question is limited to only the 'asm goto with outputs' cases, so instead of re-introducing the old workaround as-is, let's rename and limit the workaround to just that much less common case. It looks like there are at least two separate issues that all hit in this area: (a) some versions of gcc don't mark the asm goto as 'volatile' when it has outputs: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619 https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110420 which is easy to work around by just adding the 'volatile' by hand. (b) Internal compiler errors: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110422 which are worked around by adding the extra empty 'asm' as a barrier, as in the original workaround. but the problem Sean sees may be a third thing since it involves bad code generation (not an ICE) even with the manually added 'volatile'. but the same old workaround works for this case, even if this feels a bit like voodoo programming and may only be hiding the issue. Reported-and-tested-by: Sean Christopherson Link: https://lore.kernel.org/all/20240208220604.140859-1-seanjc@google.com/ Cc: Nick Desaulniers Cc: Uros Bizjak Cc: Jakub Jelinek Cc: Andrew Pinski Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc.h | 19 +++++++++++++++++++ include/linux/compiler_types.h | 4 ++-- 2 files changed, 21 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index aebb65bf95a7..c1a963be7d28 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -64,6 +64,25 @@ __builtin_unreachable(); \ } while (0) +/* + * GCC 'asm goto' with outputs miscompiles certain code sequences: + * + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110420 + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110422 + * + * Work it around via the same compiler barrier quirk that we used + * to use for the old 'asm goto' workaround. + * + * Also, always mark such 'asm goto' statements as volatile: all + * asm goto statements are supposed to be volatile as per the + * documentation, but some versions of gcc didn't actually do + * that for asms with outputs: + * + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619 + */ +#define asm_goto_output(x...) \ + do { asm volatile goto(x); asm (""); } while (0) + #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) #define __HAVE_BUILTIN_BSWAP32__ #define __HAVE_BUILTIN_BSWAP64__ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 6f1ca49306d2..663d8791c871 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -362,8 +362,8 @@ struct ftrace_likely_data { #define __member_size(p) __builtin_object_size(p, 1) #endif -#ifndef asm_volatile_goto -#define asm_volatile_goto(x...) asm goto(x) +#ifndef asm_goto_output +#define asm_goto_output(x...) asm goto(x) #endif #ifdef CONFIG_CC_HAS_ASM_INLINE -- cgit v1.2.3 From 119ff04864a24470b1e531bb53e5c141aa8fefb0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Feb 2024 14:43:21 +0000 Subject: tcp: move tp->scaling_ratio to tcp_sock_read_txrx group tp->scaling_ratio is a read mostly field, used in rx and tx fast paths. Fixes: d5fed5addb2b ("tcp: reorganize tcp_sock fast path variables") Signed-off-by: Eric Dumazet Cc: Coco Li Cc: Wei Wang Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 89b290d8c8dc..168f5dca6609 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -221,6 +221,7 @@ struct tcp_sock { u32 lost_out; /* Lost packets */ u32 sacked_out; /* SACK'd packets */ u16 tcp_header_len; /* Bytes of tcp header to send */ + u8 scaling_ratio; /* see tcp_win_from_space() */ u8 chrono_type : 2, /* current chronograph type */ repair : 1, is_sack_reneg:1, /* in recovery from loss with SACK reneg? */ @@ -352,7 +353,6 @@ struct tcp_sock { u32 compressed_ack_rcv_nxt; struct list_head tsq_node; /* anchor in tsq_tasklet.head list */ - u8 scaling_ratio; /* see tcp_win_from_space() */ /* Information of the most recently (s)acked skb */ struct tcp_rack { u64 mstamp; /* (Re)sent time of the skb */ -- cgit v1.2.3 From 666a877deab2bcf8fd11c962d69e687e18168a6f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Feb 2024 14:43:22 +0000 Subject: tcp: move tp->tcp_usec_ts to tcp_sock_read_txrx group tp->tcp_usec_ts is a read mostly field, used in rx and tx fast paths. Fixes: d5fed5addb2b ("tcp: reorganize tcp_sock fast path variables") Signed-off-by: Eric Dumazet Cc: Coco Li Cc: Wei Wang Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/tcp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 168f5dca6609..a1c47a6d69b0 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -224,6 +224,7 @@ struct tcp_sock { u8 scaling_ratio; /* see tcp_win_from_space() */ u8 chrono_type : 2, /* current chronograph type */ repair : 1, + tcp_usec_ts : 1, /* TSval values in usec */ is_sack_reneg:1, /* in recovery from loss with SACK reneg? */ is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */ __cacheline_group_end(tcp_sock_read_txrx); @@ -368,8 +369,7 @@ struct tcp_sock { u8 compressed_ack; u8 dup_ack_counter:2, tlp_retrans:1, /* TLP is a retransmission */ - tcp_usec_ts:1, /* TSval values in usec */ - unused:4; + unused:5; u8 thin_lto : 1,/* Use linear timeouts for thin streams */ recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */ fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */ -- cgit v1.2.3 From c353c7b7ffb7ae6ed8f3339906fe33c8be6cf344 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Feb 2024 14:43:23 +0000 Subject: net-device: move lstats in net_device_read_txrx dev->lstats is notably used from loopback ndo_start_xmit() and other virtual drivers. Per cpu stats updates are dirtying per-cpu data, but the pointer itself is read-only. Fixes: 43a71cd66b9c ("net-device: reorganize net_device fast path variables") Signed-off-by: Eric Dumazet Cc: Coco Li Cc: Simon Horman Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 118c40258d07..ef7bfbb98497 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2141,6 +2141,11 @@ struct net_device { /* TXRX read-mostly hotpath */ __cacheline_group_begin(net_device_read_txrx); + union { + struct pcpu_lstats __percpu *lstats; + struct pcpu_sw_netstats __percpu *tstats; + struct pcpu_dstats __percpu *dstats; + }; unsigned int flags; unsigned short hard_header_len; netdev_features_t features; @@ -2395,11 +2400,6 @@ struct net_device { enum netdev_ml_priv_type ml_priv_type; enum netdev_stat_type pcpu_stat_type:8; - union { - struct pcpu_lstats __percpu *lstats; - struct pcpu_sw_netstats __percpu *tstats; - struct pcpu_dstats __percpu *dstats; - }; #if IS_ENABLED(CONFIG_GARP) struct garp_port __rcu *garp_port; -- cgit v1.2.3 From 11ba1728be3edb6928791f4c622f154ebe228ae6 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Fri, 2 Feb 2024 12:30:26 +0000 Subject: ptrace: Introduce exception_ip arch hook On architectures with delay slot, architecture level instruction pointer (or program counter) in pt_regs may differ from where exception was triggered. Introduce exception_ip hook to invoke architecture code and determine actual instruction pointer to the exception. Link: https://lore.kernel.org/lkml/00d1b813-c55f-4365-8d81-d70258e10b16@app.fastmail.com/ Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- include/linux/ptrace.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index eaaef3ffec22..90507d4afcd6 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -393,6 +393,10 @@ static inline void user_single_step_report(struct pt_regs *regs) #define current_user_stack_pointer() user_stack_pointer(current_pt_regs()) #endif +#ifndef exception_ip +#define exception_ip(x) instruction_pointer(x) +#endif + extern int task_current_syscall(struct task_struct *target, struct syscall_info *info); extern void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact); -- cgit v1.2.3 From 6ac86372102b477083db99a9af8246fb916271b5 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 25 Jan 2024 09:15:59 +0100 Subject: gpiolib: add gpiod_to_gpio_device() stub for !GPIOLIB Add empty stub of gpiod_to_gpio_device() when GPIOLIB is not enabled. Cc: Fixes: 370232d096e3 ("gpiolib: provide gpiod_to_gpio_device()") Signed-off-by: Krzysztof Kozlowski Signed-off-by: Bartosz Golaszewski --- include/linux/gpio/driver.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 9a5c6c76e653..012797e7106d 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -819,6 +819,12 @@ static inline struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc) return ERR_PTR(-ENODEV); } +static inline struct gpio_device *gpiod_to_gpio_device(struct gpio_desc *desc) +{ + WARN_ON(1); + return ERR_PTR(-ENODEV); +} + static inline int gpiochip_lock_as_irq(struct gpio_chip *gc, unsigned int offset) { -- cgit v1.2.3 From ebe0c15b135b1e4092c25b95d89e9a5899467499 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 25 Jan 2024 09:16:00 +0100 Subject: gpiolib: add gpio_device_get_base() stub for !GPIOLIB Add empty stub of gpio_device_get_base() when GPIOLIB is not enabled. Cc: Fixes: 8c85a102fc4e ("gpiolib: provide gpio_device_get_base()") Signed-off-by: Krzysztof Kozlowski Signed-off-by: Bartosz Golaszewski --- include/linux/gpio/driver.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 012797e7106d..c1df7698edb0 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -825,6 +825,12 @@ static inline struct gpio_device *gpiod_to_gpio_device(struct gpio_desc *desc) return ERR_PTR(-ENODEV); } +static inline int gpio_device_get_base(struct gpio_device *gdev) +{ + WARN_ON(1); + return -ENODEV; +} + static inline int gpiochip_lock_as_irq(struct gpio_chip *gc, unsigned int offset) { -- cgit v1.2.3 From 2df8aa3cad407044f2febdbbdf220c6dae839c79 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 25 Jan 2024 09:16:01 +0100 Subject: gpiolib: add gpio_device_get_label() stub for !GPIOLIB Add empty stub of gpio_device_get_label() when GPIOLIB is not enabled. Cc: Fixes: d1f7728259ef ("gpiolib: provide gpio_device_get_label()") Suggested-by: kernel test robot Signed-off-by: Krzysztof Kozlowski Signed-off-by: Bartosz Golaszewski --- include/linux/gpio/driver.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index c1df7698edb0..7f75c9a51874 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -831,6 +831,12 @@ static inline int gpio_device_get_base(struct gpio_device *gdev) return -ENODEV; } +static inline const char *gpio_device_get_label(struct gpio_device *gdev) +{ + WARN_ON(1); + return NULL; +} + static inline int gpiochip_lock_as_irq(struct gpio_chip *gc, unsigned int offset) { -- cgit v1.2.3 From 29f6975332479f92233594901c649ff4d71f8cb6 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Mon, 5 Feb 2024 11:10:25 -0800 Subject: nvme: implement support for relaxed effects NVM Express TP4167 provides a way for controllers to report a relaxed execution constraint. Specifically, it notifies of exclusivity for IO vs. admin commands instead of grouping these together. If set, then we don't need to freeze IO in order to execute that admin command. The freezing distrupts IO processes, so it's nice to avoid that if the controller tells us it's not necessary. Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch --- include/linux/nvme.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index bc605ec4a3fd..3ef4053ea950 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -646,6 +646,7 @@ enum { NVME_CMD_EFFECTS_NCC = 1 << 2, NVME_CMD_EFFECTS_NIC = 1 << 3, NVME_CMD_EFFECTS_CCC = 1 << 4, + NVME_CMD_EFFECTS_CSER_MASK = GENMASK(15, 14), NVME_CMD_EFFECTS_CSE_MASK = GENMASK(18, 16), NVME_CMD_EFFECTS_UUID_SEL = 1 << 19, NVME_CMD_EFFECTS_SCOPE_MASK = GENMASK(31, 20), -- cgit v1.2.3 From 8a566f94104df87a067458351675129bb4e1ece2 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 15 Feb 2024 16:22:55 +0200 Subject: seq_buf: Don't use "proxy" headers Update header inclusions to follow IWYU (Include What You Use) principle. Link: https://lkml.kernel.org/r/20240215142255.400264-1-andriy.shevchenko@linux.intel.com Cc: "Matthew Wilcox (Oracle)" Cc: Andrew Morton Signed-off-by: Andy Shevchenko Signed-off-by: Steven Rostedt (Google) --- include/linux/seq_buf.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h index c44f4b47b945..07b26e751060 100644 --- a/include/linux/seq_buf.h +++ b/include/linux/seq_buf.h @@ -2,7 +2,10 @@ #ifndef _LINUX_SEQ_BUF_H #define _LINUX_SEQ_BUF_H -#include +#include +#include +#include +#include /* * Trace sequences are used to allow a function to call several other functions -- cgit v1.2.3 From 6efe4d18796934b8ada66c1c446510e7f2d9b972 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 15 Feb 2024 17:25:06 +0200 Subject: seq_buf: Fix kernel documentation There are plenty of issues with the kernel documentation here: - misspelled word "sequence" - different style of returned value descriptions - missed Return sections - unaligned style of ASCII / NUL-terminated / etc - wrong function references Fix all these. Link: https://lkml.kernel.org/r/20240215152506.598340-1-andriy.shevchenko@linux.intel.com Cc: Andrew Morton Signed-off-by: Andy Shevchenko Reviewed-by: Randy Dunlap Signed-off-by: Steven Rostedt (Google) --- include/linux/seq_buf.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h index 07b26e751060..fe41da005970 100644 --- a/include/linux/seq_buf.h +++ b/include/linux/seq_buf.h @@ -13,7 +13,7 @@ */ /** - * seq_buf - seq buffer structure + * struct seq_buf - seq buffer structure * @buffer: pointer to the buffer * @size: size of the buffer * @len: the amount of data inside the buffer @@ -80,10 +80,10 @@ static inline unsigned int seq_buf_used(struct seq_buf *s) } /** - * seq_buf_str - get %NUL-terminated C string from seq_buf + * seq_buf_str - get NUL-terminated C string from seq_buf * @s: the seq_buf handle * - * This makes sure that the buffer in @s is nul terminated and + * This makes sure that the buffer in @s is NUL-terminated and * safe to read as a string. * * Note, if this is called when the buffer has overflowed, then @@ -93,7 +93,7 @@ static inline unsigned int seq_buf_used(struct seq_buf *s) * After this function is called, s->buffer is safe to use * in string operations. * - * Returns @s->buf after making sure it is terminated. + * Returns: @s->buf after making sure it is terminated. */ static inline const char *seq_buf_str(struct seq_buf *s) { @@ -113,7 +113,7 @@ static inline const char *seq_buf_str(struct seq_buf *s) * @s: the seq_buf handle * @bufp: the beginning of the buffer is stored here * - * Return the number of bytes available in the buffer, or zero if + * Returns: the number of bytes available in the buffer, or zero if * there's no space. */ static inline size_t seq_buf_get_buf(struct seq_buf *s, char **bufp) @@ -135,7 +135,7 @@ static inline size_t seq_buf_get_buf(struct seq_buf *s, char **bufp) * @num: the number of bytes to commit * * Commit @num bytes of data written to a buffer previously acquired - * by seq_buf_get. To signal an error condition, or that the data + * by seq_buf_get_buf(). To signal an error condition, or that the data * didn't fit in the available space, pass a negative @num value. */ static inline void seq_buf_commit(struct seq_buf *s, int num) -- cgit v1.2.3 From 68fb3ca0e408e00db1c3f8fccdfa19e274c033be Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 15 Feb 2024 11:14:33 -0800 Subject: update workarounds for gcc "asm goto" issue In commit 4356e9f841f7 ("work around gcc bugs with 'asm goto' with outputs") I did the gcc workaround unconditionally, because the cause of the bad code generation wasn't entirely clear. In the meantime, Jakub Jelinek debugged the issue, and has come up with a fix in gcc [2], which also got backported to the still maintained branches of gcc-11, gcc-12 and gcc-13. Note that while the fix technically wasn't in the original gcc-14 branch, Jakub says: "while it is true that no GCC 14 snapshots until today (or whenever the fix will be committed) have the fix, for GCC trunk it is up to the distros to use the latest snapshot if they use it at all and would allow better testing of the kernel code without the workaround, so that if there are other issues they won't be discovered years later. Most userland code doesn't actually use asm goto with outputs..." so we will consider gcc-14 to be fixed - if somebody is using gcc snapshots of the gcc-14 before the fix, they should upgrade. Note that while the bug goes back to gcc-11, in practice other gcc changes seem to have effectively hidden it since gcc-12.1 as per a bisect by Jakub. So even a gcc-14 snapshot without the fix likely doesn't show actual problems. Also, make the default 'asm_goto_output()' macro mark the asm as volatile by hand, because of an unrelated gcc issue [1] where it doesn't match the documented behavior ("asm goto is always volatile"). Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103979 [1] Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921 [2] Link: https://lore.kernel.org/all/20240208220604.140859-1-seanjc@google.com/ Requested-by: Jakub Jelinek Cc: Uros Bizjak Cc: Nick Desaulniers Cc: Sean Christopherson Cc: Andrew Pinski Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc.h | 7 ++++--- include/linux/compiler_types.h | 9 ++++++++- 2 files changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index c1a963be7d28..75bd1692d2e3 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -67,10 +67,9 @@ /* * GCC 'asm goto' with outputs miscompiles certain code sequences: * - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110420 - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110422 + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921 * - * Work it around via the same compiler barrier quirk that we used + * Work around it via the same compiler barrier quirk that we used * to use for the old 'asm goto' workaround. * * Also, always mark such 'asm goto' statements as volatile: all @@ -80,8 +79,10 @@ * * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619 */ +#ifdef CONFIG_GCC_ASM_GOTO_OUTPUT_WORKAROUND #define asm_goto_output(x...) \ do { asm volatile goto(x); asm (""); } while (0) +#endif #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) #define __HAVE_BUILTIN_BSWAP32__ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 663d8791c871..0caf354cb94b 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -362,8 +362,15 @@ struct ftrace_likely_data { #define __member_size(p) __builtin_object_size(p, 1) #endif +/* + * Some versions of gcc do not mark 'asm goto' volatile: + * + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103979 + * + * We do it here by hand, because it doesn't hurt. + */ #ifndef asm_goto_output -#define asm_goto_output(x...) asm goto(x) +#define asm_goto_output(x...) asm volatile goto(x) #endif #ifdef CONFIG_CC_HAS_ASM_INLINE -- cgit v1.2.3