From 5c563ee90a22d3295bcd6217e3ecd7bf9f4d9d48 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Fri, 24 May 2024 11:58:28 -0700 Subject: cpumask: introduce assign_cpu() macro Now that assign_bit() is a thin macro wrapper around set_bit() and clear_bit(), we can use it in cpumask API and drop duplicating implementations of set_cpu_xxx() helpers with no additional overhead. Bloat-o-meter reports almost 2k less of generated code for allyesconfig, mostly in kernel/cpu.c: add/remove: 2/4 grow/shrink: 3/4 up/down: 498/-2228 (-1730) Reviewed-by: Alexander Lobakin Signed-off-by: Yury Norov --- include/linux/cpumask.h | 40 ++++++---------------------------------- 1 file changed, 6 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 23686bed441d..18410acdbc9e 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -1083,44 +1083,16 @@ void init_cpu_present(const struct cpumask *src); void init_cpu_possible(const struct cpumask *src); void init_cpu_online(const struct cpumask *src); -static inline void -set_cpu_possible(unsigned int cpu, bool possible) -{ - if (possible) - cpumask_set_cpu(cpu, &__cpu_possible_mask); - else - cpumask_clear_cpu(cpu, &__cpu_possible_mask); -} +#define assign_cpu(cpu, mask, val) \ + assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val)) -static inline void -set_cpu_present(unsigned int cpu, bool present) -{ - if (present) - cpumask_set_cpu(cpu, &__cpu_present_mask); - else - cpumask_clear_cpu(cpu, &__cpu_present_mask); -} +#define set_cpu_possible(cpu, possible) assign_cpu((cpu), &__cpu_possible_mask, (possible)) +#define set_cpu_present(cpu, present) assign_cpu((cpu), &__cpu_present_mask, (present)) +#define set_cpu_active(cpu, active) assign_cpu((cpu), &__cpu_active_mask, (active)) +#define set_cpu_dying(cpu, dying) assign_cpu((cpu), &__cpu_dying_mask, (dying)) void set_cpu_online(unsigned int cpu, bool online); -static inline void -set_cpu_active(unsigned int cpu, bool active) -{ - if (active) - cpumask_set_cpu(cpu, &__cpu_active_mask); - else - cpumask_clear_cpu(cpu, &__cpu_active_mask); -} - -static inline void -set_cpu_dying(unsigned int cpu, bool dying) -{ - if (dying) - cpumask_set_cpu(cpu, &__cpu_dying_mask); - else - cpumask_clear_cpu(cpu, &__cpu_dying_mask); -} - /** * to_cpumask - convert a NR_CPUS bitmap to a struct cpumask * * @bitmap: the bitmap -- cgit v1.2.3 From e0eeb938adb0367de4b0946125a06142d8de7d37 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 11 Jun 2024 15:38:12 +0300 Subject: bitops: Add a comment explaining the double underscore macros Linus Walleij pointed out that a new comer might be confused about the difference between set_bit() and __set_bit(). Add a comment explaining the difference. Link: https://lore.kernel.org/all/CACRpkdZFPG_YLici-BmYfk9HZ36f4WavCN3JNotkk8cPgCODCg@mail.gmail.com/ Signed-off-by: Dan Carpenter Reviewed-by: Linus Walleij Signed-off-by: Yury Norov --- include/linux/bitops.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 46d4bdc634c0..ba35bbf07798 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -47,12 +47,17 @@ extern unsigned long __sw_hweight64(__u64 w); __builtin_constant_p(*(const unsigned long *)(addr))) ? \ const##op(nr, addr) : op(nr, addr)) +/* + * The following macros are non-atomic versions of their non-underscored + * counterparts. + */ #define __set_bit(nr, addr) bitop(___set_bit, nr, addr) #define __clear_bit(nr, addr) bitop(___clear_bit, nr, addr) #define __change_bit(nr, addr) bitop(___change_bit, nr, addr) #define __test_and_set_bit(nr, addr) bitop(___test_and_set_bit, nr, addr) #define __test_and_clear_bit(nr, addr) bitop(___test_and_clear_bit, nr, addr) #define __test_and_change_bit(nr, addr) bitop(___test_and_change_bit, nr, addr) + #define test_bit(nr, addr) bitop(_test_bit, nr, addr) #define test_bit_acquire(nr, addr) bitop(_test_bit_acquire, nr, addr) -- cgit v1.2.3 From 675e979db473d08be346a3190c5f0db095a57153 Mon Sep 17 00:00:00 2001 From: "Fabio M. De Francesco" Date: Fri, 7 Jun 2024 16:43:58 +0200 Subject: cxl/events: Use a common struct for DRAM and General Media events cxl_event_common was an unfortunate naming choice and caused confusion with the existing Common Event Record. Furthermore, its fields didn't map all the common information between DRAM and General Media Events. Remove cxl_event_common and introduce cxl_event_media_hdr to record common information between DRAM and General Media events. cxl_event_media_hdr, which is embedded in both cxl_event_gen_media and cxl_event_dram, leverages the commonalities between the two events to simplify their respective handling. Suggested-by: Dan Williams Reviewed-by: Alison Schofield Reviewed-by: Dan Williams Reviewed-by: Ira Weiny Signed-off-by: Fabio M. De Francesco Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/20240607144423.48681-1-fabio.m.de.francesco@linux.intel.com Signed-off-by: Dave Jiang --- include/linux/cxl-event.h | 45 +++++++++++++++++++-------------------------- 1 file changed, 19 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h index 60b25020281f..0bea1afbd747 100644 --- a/include/linux/cxl-event.h +++ b/include/linux/cxl-event.h @@ -21,6 +21,21 @@ struct cxl_event_record_hdr { u8 reserved[15]; } __packed; +struct cxl_event_media_hdr { + struct cxl_event_record_hdr hdr; + __le64 phys_addr; + u8 descriptor; + u8 type; + u8 transaction_type; + /* + * The meaning of Validity Flags from bit 2 is + * different across DRAM and General Media records + */ + u8 validity_flags[2]; + u8 channel; + u8 rank; +} __packed; + #define CXL_EVENT_RECORD_DATA_LENGTH 0x50 struct cxl_event_generic { struct cxl_event_record_hdr hdr; @@ -33,14 +48,7 @@ struct cxl_event_generic { */ #define CXL_EVENT_GEN_MED_COMP_ID_SIZE 0x10 struct cxl_event_gen_media { - struct cxl_event_record_hdr hdr; - __le64 phys_addr; - u8 descriptor; - u8 type; - u8 transaction_type; - u8 validity_flags[2]; - u8 channel; - u8 rank; + struct cxl_event_media_hdr media_hdr; u8 device[3]; u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE]; u8 reserved[46]; @@ -52,14 +60,7 @@ struct cxl_event_gen_media { */ #define CXL_EVENT_DER_CORRECTION_MASK_SIZE 0x20 struct cxl_event_dram { - struct cxl_event_record_hdr hdr; - __le64 phys_addr; - u8 descriptor; - u8 type; - u8 transaction_type; - u8 validity_flags[2]; - u8 channel; - u8 rank; + struct cxl_event_media_hdr media_hdr; u8 nibble_mask[3]; u8 bank_group; u8 bank; @@ -95,21 +96,13 @@ struct cxl_event_mem_module { u8 reserved[0x3d]; } __packed; -/* - * General Media or DRAM Event Common Fields - * - provides common access to phys_addr - */ -struct cxl_event_common { - struct cxl_event_record_hdr hdr; - __le64 phys_addr; -} __packed; - union cxl_event { struct cxl_event_generic generic; struct cxl_event_gen_media gen_media; struct cxl_event_dram dram; struct cxl_event_mem_module mem_module; - struct cxl_event_common common; + /* dram & gen_media event header */ + struct cxl_event_media_hdr media_hdr; } __packed; /* -- cgit v1.2.3 From 1f9a8286bc0c3df7d789ea625d9d9db3d7779f2d Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 28 May 2024 14:58:03 +0000 Subject: uaccess: always export _copy_[from|to]_user with CONFIG_RUST Rust code needs to be able to access _copy_from_user and _copy_to_user so that it can skip the check_copy_size check in cases where the length is known at compile-time, mirroring the logic for when C code will skip check_copy_size. To do this, we ensure that exported versions of these methods are available when CONFIG_RUST is enabled. Alice has verified that this patch passes the CONFIG_TEST_USER_COPY test on x86 using the Android cuttlefish emulator. Signed-off-by: Arnd Bergmann Tested-by: Alice Ryhl Reviewed-by: Boqun Feng Reviewed-by: Kees Cook Signed-off-by: Alice Ryhl Acked-by: Andrew Morton Link: https://lore.kernel.org/r/20240528-alice-mm-v7-2-78222c31b8f4@google.com Signed-off-by: Miguel Ojeda --- include/linux/uaccess.h | 46 ++++++++++++++++++++++++++++++++-------------- 1 file changed, 32 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 3064314f4832..d8e4105a2f21 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -5,6 +5,7 @@ #include #include #include +#include #include #include @@ -138,13 +139,26 @@ __copy_to_user(void __user *to, const void *from, unsigned long n) return raw_copy_to_user(to, from, n); } -#ifdef INLINE_COPY_FROM_USER +/* + * Architectures that #define INLINE_COPY_TO_USER use this function + * directly in the normal copy_to/from_user(), the other ones go + * through an extern _copy_to/from_user(), which expands the same code + * here. + * + * Rust code always uses the extern definition. + */ static inline __must_check unsigned long -_copy_from_user(void *to, const void __user *from, unsigned long n) +_inline_copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); if (!should_fail_usercopy() && likely(access_ok(from, n))) { + /* + * Ensure that bad access_ok() speculation will not + * lead to nasty side effects *after* the copy is + * finished: + */ + barrier_nospec(); instrument_copy_from_user_before(to, from, n); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); @@ -153,14 +167,11 @@ _copy_from_user(void *to, const void __user *from, unsigned long n) memset(to + (n - res), 0, res); return res; } -#else extern __must_check unsigned long _copy_from_user(void *, const void __user *, unsigned long); -#endif -#ifdef INLINE_COPY_TO_USER static inline __must_check unsigned long -_copy_to_user(void __user *to, const void *from, unsigned long n) +_inline_copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) @@ -171,25 +182,32 @@ _copy_to_user(void __user *to, const void *from, unsigned long n) } return n; } -#else extern __must_check unsigned long _copy_to_user(void __user *, const void *, unsigned long); -#endif static __always_inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { - if (check_copy_size(to, n, false)) - n = _copy_from_user(to, from, n); - return n; + if (!check_copy_size(to, n, false)) + return n; +#ifdef INLINE_COPY_FROM_USER + return _inline_copy_from_user(to, from, n); +#else + return _copy_from_user(to, from, n); +#endif } static __always_inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { - if (check_copy_size(from, n, true)) - n = _copy_to_user(to, from, n); - return n; + if (!check_copy_size(from, n, true)) + return n; + +#ifdef INLINE_COPY_TO_USER + return _inline_copy_to_user(to, from, n); +#else + return _copy_to_user(to, from, n); +#endif } #ifndef copy_mc_to_kernel -- cgit v1.2.3 From 415fb383ec2bbe4d4bb1a1b5593cd67eb058f1de Mon Sep 17 00:00:00 2001 From: Francis Pravin Date: Mon, 15 Jul 2024 06:31:57 +0530 Subject: nvme-core: choose PIF from QPIF if QPIFS supports and PIF is QTYPE As per TP4141a: "If the Qualified Protection Information Format Support(QPIFS) bit is set to 1 and the Protection Information Format(PIF) field is set to 11b (i.e., Qualified Type), then the pif is as defined in the Qualified Protection Information Format (QPIF) field." So, choose PIF from QPIF if QPIFS supports and PIF is QTYPE. Signed-off-by: Francis Pravin Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch --- include/linux/nvme.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 57e27e48c913..5c2290f0d5af 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -483,6 +483,9 @@ enum { NVME_ID_NS_NVM_STS_MASK = 0x7f, NVME_ID_NS_NVM_GUARD_SHIFT = 7, NVME_ID_NS_NVM_GUARD_MASK = 0x3, + NVME_ID_NS_NVM_QPIF_SHIFT = 9, + NVME_ID_NS_NVM_QPIF_MASK = 0xf, + NVME_ID_NS_NVM_QPIFS = 1 << 3, }; static inline __u8 nvme_elbaf_sts(__u32 elbaf) @@ -495,6 +498,11 @@ static inline __u8 nvme_elbaf_guard_type(__u32 elbaf) return (elbaf >> NVME_ID_NS_NVM_GUARD_SHIFT) & NVME_ID_NS_NVM_GUARD_MASK; } +static inline __u8 nvme_elbaf_qualified_guard_type(__u32 elbaf) +{ + return (elbaf >> NVME_ID_NS_NVM_QPIF_SHIFT) & NVME_ID_NS_NVM_QPIF_MASK; +} + struct nvme_id_ctrl_nvm { __u8 vsl; __u8 wzsl; @@ -574,6 +582,7 @@ enum { NVME_NVM_NS_16B_GUARD = 0, NVME_NVM_NS_32B_GUARD = 1, NVME_NVM_NS_64B_GUARD = 2, + NVME_NVM_NS_QTYPE_GUARD = 3, }; static inline __u8 nvme_lbaf_index(__u8 flbas) -- cgit v1.2.3 From a2d6d8aee4a4f694920bfaf6f6be3690e0f8d302 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 19 Jul 2024 11:56:34 +0200 Subject: ALSA: hda: tas2781: mark const variables as __maybe_unused An earlier patch changed the DECLARE_TLV_DB_SCALE declaration, but now there are additional static const variables that cause the same build warnings: In file included from sound/pci/hda/tas2781_hda_i2c.c:23: include/sound/tas2781-tlv.h:23:28: error: 'tas2563_dvc_table' defined but not used [-Werror=unused-const-variable=] 23 | static const unsigned char tas2563_dvc_table[][4] = { | ^~~~~~~~~~~~~~~~~ In file included from include/sound/tlv.h:10, from sound/pci/hda/tas2781_hda_i2c.c:22: include/sound/tas2781-tlv.h:20:35: error: 'tas2563_dvc_tlv' defined but not used [-Werror=unused-const-variable=] 20 | static const DECLARE_TLV_DB_SCALE(tas2563_dvc_tlv, -12150, 50, 1); | ^~~~~~~~~~~~~~~ Mark them all as unused as well. Signed-off-by: Arnd Bergmann Link: https://patch.msgid.link/20240719095640.3741247-1-arnd@kernel.org Signed-off-by: Takashi Iwai --- include/sound/tas2781-tlv.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/sound/tas2781-tlv.h b/include/sound/tas2781-tlv.h index 99c41bfc7827..00fd4d449ff3 100644 --- a/include/sound/tas2781-tlv.h +++ b/include/sound/tas2781-tlv.h @@ -16,11 +16,11 @@ #define __TAS2781_TLV_H__ static const __maybe_unused DECLARE_TLV_DB_SCALE(dvc_tlv, -10000, 100, 0); -static const DECLARE_TLV_DB_SCALE(amp_vol_tlv, 1100, 50, 0); -static const DECLARE_TLV_DB_SCALE(tas2563_dvc_tlv, -12150, 50, 1); +static const __maybe_unused DECLARE_TLV_DB_SCALE(amp_vol_tlv, 1100, 50, 0); +static const __maybe_unused DECLARE_TLV_DB_SCALE(tas2563_dvc_tlv, -12150, 50, 1); /* pow(10, db/20) * pow(2,30) */ -static const unsigned char tas2563_dvc_table[][4] = { +static const __maybe_unused unsigned char tas2563_dvc_table[][4] = { { 0X00, 0X00, 0X00, 0X00 }, /* -121.5db */ { 0X00, 0X00, 0X03, 0XBC }, /* -121.0db */ { 0X00, 0X00, 0X03, 0XF5 }, /* -120.5db */ -- cgit v1.2.3 From eabd9db64ea8ba64d2a0b1d70da38e1a95dcd08b Mon Sep 17 00:00:00 2001 From: Haibo Xu Date: Thu, 13 Jun 2024 16:54:33 +0800 Subject: ACPI: RISCV: Add NUMA support based on SRAT and SLIT Add acpi_numa.c file to enable parse NUMA information from ACPI SRAT and SLIT tables. SRAT table provide CPUs(Hart) and memory nodes to proximity domain mapping, while SLIT table provide the distance metrics between proximity domains. Signed-off-by: Haibo Xu Reviewed-by: Sunil V L Reviewed-by: Hanjun Guo Link: https://lore.kernel.org/r/65dbad1fda08a32922c44886e4581e49b4a2fecc.1718268003.git.haibo1.xu@intel.com Signed-off-by: Palmer Dabbelt --- include/linux/acpi.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 28c3fb2bef0d..5a2b620ccd58 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -264,6 +264,12 @@ static inline void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { } #endif +#ifdef CONFIG_RISCV +void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa); +#else +static inline void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa) { } +#endif + #ifndef PHYS_CPUID_INVALID typedef u32 phys_cpuid_t; #define PHYS_CPUID_INVALID (phys_cpuid_t)(-1) -- cgit v1.2.3 From 10a0e6f3d3db7dcfe36e578923e5f038f1d2b72a Mon Sep 17 00:00:00 2001 From: Anna-Maria Behnsen Date: Wed, 17 Jul 2024 11:49:40 +0200 Subject: timers/migration: Move hierarchy setup into cpuhotplug prepare callback When a CPU comes online the first time, it is possible that a new top level group will be created. In general all propagation is done from the bottom to top. This minimizes complexity and prevents possible races. But when a new top level group is created, the formely top level group needs to be connected to the new level. This is the only time, when the direction to propagate changes is changed: the changes are propagated from top (new top level group) to bottom (formerly top level group). This introduces two races (see (A) and (B)) as reported by Frederic: (A) This race happens, when marking the formely top level group as active, but the last active CPU of the formerly top level group goes idle. Then it's likely that formerly group is no longer active, but marked nevertheless as active in new top level group: [GRP0:0] migrator = 0 active = 0 nextevt = KTIME_MAX / \ 0 1 .. 7 active idle 0) Hierarchy has for now only 8 CPUs and CPU 0 is the only active CPU. [GRP1:0] migrator = TMIGR_NONE active = NONE nextevt = KTIME_MAX \ [GRP0:0] [GRP0:1] migrator = 0 migrator = TMIGR_NONE active = 0 active = NONE nextevt = KTIME_MAX nextevt = KTIME_MAX / \ 0 1 .. 7 8 active idle !online 1) CPU 8 is booting and creates a new group in first level GRP0:1 and therefore also a new top group GRP1:0. For now the setup code proceeded only until the connected between GRP0:1 to the new top group. The connection between CPU8 and GRP0:1 is not yet established and CPU 8 is still !online. [GRP1:0] migrator = TMIGR_NONE active = NONE nextevt = KTIME_MAX / \ [GRP0:0] [GRP0:1] migrator = 0 migrator = TMIGR_NONE active = 0 active = NONE nextevt = KTIME_MAX nextevt = KTIME_MAX / \ 0 1 .. 7 8 active idle !online 2) Setup code now connects GRP0:0 to GRP1:0 and observes while in tmigr_connect_child_parent() that GRP0:0 is not TMIGR_NONE. So it prepares to call tmigr_active_up() on it. It hasn't done it yet. [GRP1:0] migrator = TMIGR_NONE active = NONE nextevt = KTIME_MAX / \ [GRP0:0] [GRP0:1] migrator = TMIGR_NONE migrator = TMIGR_NONE active = NONE active = NONE nextevt = KTIME_MAX nextevt = KTIME_MAX / \ 0 1 .. 7 8 idle idle !online 3) CPU 0 goes idle. Since GRP0:0->parent has been updated by CPU 8 with GRP0:0->lock held, CPU 0 observes GRP1:0 after calling tmigr_update_events() and it propagates the change to the top (no change there and no wakeup programmed since there is no timer). [GRP1:0] migrator = GRP0:0 active = GRP0:0 nextevt = KTIME_MAX / \ [GRP0:0] [GRP0:1] migrator = TMIGR_NONE migrator = TMIGR_NONE active = NONE active = NONE nextevt = KTIME_MAX nextevt = KTIME_MAX / \ 0 1 .. 7 8 idle idle !online 4) Now the setup code finally calls tmigr_active_up() to and sets GRP0:0 active in GRP1:0 [GRP1:0] migrator = GRP0:0 active = GRP0:0, GRP0:1 nextevt = KTIME_MAX / \ [GRP0:0] [GRP0:1] migrator = TMIGR_NONE migrator = 8 active = NONE active = 8 nextevt = KTIME_MAX nextevt = KTIME_MAX / \ | 0 1 .. 7 8 idle idle active 5) Now CPU 8 is connected with GRP0:1 and CPU 8 calls tmigr_active_up() out of tmigr_cpu_online(). [GRP1:0] migrator = GRP0:0 active = GRP0:0 nextevt = T8 / \ [GRP0:0] [GRP0:1] migrator = TMIGR_NONE migrator = TMIGR_NONE active = NONE active = NONE nextevt = KTIME_MAX nextevt = T8 / \ | 0 1 .. 7 8 idle idle idle 5) CPU 8 goes idle with a timer T8 and relies on GRP0:0 as the migrator. But it's not really active, so T8 gets ignored. --> The update which is done in third step is not noticed by setup code. So a wrong migrator is set to top level group and a timer could get ignored. (B) Reading group->parent and group->childmask when an hierarchy update is ongoing and reaches the formerly top level group is racy as those values could be inconsistent. (The notation of migrator and active now slightly changes in contrast to the above example, as now the childmasks are used.) [GRP1:0] migrator = TMIGR_NONE active = 0x00 nextevt = KTIME_MAX \ [GRP0:0] [GRP0:1] migrator = TMIGR_NONE migrator = TMIGR_NONE active = 0x00 active = 0x00 nextevt = KTIME_MAX nextevt = KTIME_MAX childmask= 0 childmask= 1 parent = NULL parent = GRP1:0 / \ 0 1 .. 7 8 idle idle !online childmask=1 1) Hierarchy has 8 CPUs. CPU 8 is at the moment in the process of onlining but did not yet connect GRP0:0 to GRP1:0. [GRP1:0] migrator = TMIGR_NONE active = 0x00 nextevt = KTIME_MAX / \ [GRP0:0] [GRP0:1] migrator = TMIGR_NONE migrator = TMIGR_NONE active = 0x00 active = 0x00 nextevt = KTIME_MAX nextevt = KTIME_MAX childmask= 0 childmask= 1 parent = GRP1:0 parent = GRP1:0 / \ 0 1 .. 7 8 idle idle !online childmask=1 2) Setup code (running on CPU 8) now connects GRP0:0 to GRP1:0, updates parent pointer of GRP0:0 and ... [GRP1:0] migrator = TMIGR_NONE active = 0x00 nextevt = KTIME_MAX / \ [GRP0:0] [GRP0:1] migrator = 0x01 migrator = TMIGR_NONE active = 0x01 active = 0x00 nextevt = KTIME_MAX nextevt = KTIME_MAX childmask= 0 childmask= 1 parent = GRP1:0 parent = GRP1:0 / \ 0 1 .. 7 8 active idle !online childmask=1 tmigr_walk.childmask = 0 3) ... CPU 0 comes active in the same time. As migrator in GRP0:0 was TMIGR_NONE, childmask of GRP0:0 is stored in update propagation data structure tmigr_walk (as update of childmask is not yet visible/updated). And now ... [GRP1:0] migrator = TMIGR_NONE active = 0x00 nextevt = KTIME_MAX / \ [GRP0:0] [GRP0:1] migrator = 0x01 migrator = TMIGR_NONE active = 0x01 active = 0x00 nextevt = KTIME_MAX nextevt = KTIME_MAX childmask= 2 childmask= 1 parent = GRP1:0 parent = GRP1:0 / \ 0 1 .. 7 8 active idle !online childmask=1 tmigr_walk.childmask = 0 4) ... childmask of GRP0:0 is updated by CPU 8 (still part of setup code). [GRP1:0] migrator = 0x00 active = 0x00 nextevt = KTIME_MAX / \ [GRP0:0] [GRP0:1] migrator = 0x01 migrator = TMIGR_NONE active = 0x01 active = 0x00 nextevt = KTIME_MAX nextevt = KTIME_MAX childmask= 2 childmask= 1 parent = GRP1:0 parent = GRP1:0 / \ 0 1 .. 7 8 active idle !online childmask=1 tmigr_walk.childmask = 0 5) CPU 0 sees the connection to GRP1:0 and now propagates active state to GRP1:0 but with childmask = 0 as stored in propagation data structure. --> Now GRP1:0 always has a migrator as 0x00 != TMIGR_NONE and for all CPUs it looks like GRP1:0 is always active. To prevent those races, the setup of the hierarchy is moved into the cpuhotplug prepare callback. The prepare callback is not executed by the CPU which will come online, it is executed by the CPU which prepares onlining of the other CPU. This CPU is active while it is connecting the formerly top level to the new one. This prevents from (A) to happen and it also prevents from any further walk above the formerly top level until that active CPU becomes inactive, releasing the new ->parent and ->childmask updates to be visible by any subsequent walk up above the formerly top level hierarchy. This prevents from (B) to happen. The direction for the updates is now forced to look like "from bottom to top". However if the active CPU prevents from tmigr_cpu_(in)active() to walk up with the update not-or-half visible, nothing prevents walking up to the new top with a 0 childmask in tmigr_handle_remote_up() or tmigr_requires_handle_remote_up() if the active CPU doing the prepare is not the migrator. But then it looks fine because: * tmigr_check_migrator() should just return false * The migrator is active and should eventually observe the new childmask at some point in a future tick. Split setup functionality of online callback into the cpuhotplug prepare callback and setup hotplug state. Change init call into early_initcall() to make sure an already active CPU prepares everything for newly upcoming CPUs. Reorder the code, that all prepare related functions are close to each other and online and offline callbacks are also close together. Fixes: 7ee988770326 ("timers: Implement the hierarchical pull model") Signed-off-by: Anna-Maria Behnsen Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Link: https://lore.kernel.org/r/20240717094940.18687-1-anna-maria@linutronix.de --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 7a5785f405b6..df59666a2a66 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -122,6 +122,7 @@ enum cpuhp_state { CPUHP_KVM_PPC_BOOK3S_PREPARE, CPUHP_ZCOMP_PREPARE, CPUHP_TIMERS_PREPARE, + CPUHP_TMIGR_PREPARE, CPUHP_MIPS_SOC_PREPARE, CPUHP_BP_PREPARE_DYN, CPUHP_BP_PREPARE_DYN_END = CPUHP_BP_PREPARE_DYN + 20, -- cgit v1.2.3 From 835a9a67f54f01033417a254e53a1391f99db708 Mon Sep 17 00:00:00 2001 From: Anna-Maria Behnsen Date: Tue, 16 Jul 2024 16:19:24 +0200 Subject: timers/migration: Rename childmask by groupmask to make naming more obvious childmask in the group reflects the mask that is required to 'reference' this group in the parent. When reading childmask, this might be confusing, as this suggests, that this is the mask of the child of the group. Clarify this by renaming childmask in the tmigr_group and tmc_group by groupmask. Signed-off-by: Anna-Maria Behnsen Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Link: https://lore.kernel.org/r/20240716-tmigr-fixes-v4-6-757baa7803fe@linutronix.de --- include/trace/events/timer_migration.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/trace/events/timer_migration.h b/include/trace/events/timer_migration.h index 79f19e76a80b..47db5eaf2f9a 100644 --- a/include/trace/events/timer_migration.h +++ b/include/trace/events/timer_migration.h @@ -43,7 +43,7 @@ TRACE_EVENT(tmigr_connect_child_parent, __field( unsigned int, lvl ) __field( unsigned int, numa_node ) __field( unsigned int, num_children ) - __field( u32, childmask ) + __field( u32, groupmask ) ), TP_fast_assign( @@ -52,11 +52,11 @@ TRACE_EVENT(tmigr_connect_child_parent, __entry->lvl = child->parent->level; __entry->numa_node = child->parent->numa_node; __entry->num_children = child->parent->num_children; - __entry->childmask = child->childmask; + __entry->groupmask = child->groupmask; ), - TP_printk("group=%p childmask=%0x parent=%p lvl=%d numa=%d num_children=%d", - __entry->child, __entry->childmask, __entry->parent, + TP_printk("group=%p groupmask=%0x parent=%p lvl=%d numa=%d num_children=%d", + __entry->child, __entry->groupmask, __entry->parent, __entry->lvl, __entry->numa_node, __entry->num_children) ); @@ -72,7 +72,7 @@ TRACE_EVENT(tmigr_connect_cpu_parent, __field( unsigned int, lvl ) __field( unsigned int, numa_node ) __field( unsigned int, num_children ) - __field( u32, childmask ) + __field( u32, groupmask ) ), TP_fast_assign( @@ -81,11 +81,11 @@ TRACE_EVENT(tmigr_connect_cpu_parent, __entry->lvl = tmc->tmgroup->level; __entry->numa_node = tmc->tmgroup->numa_node; __entry->num_children = tmc->tmgroup->num_children; - __entry->childmask = tmc->childmask; + __entry->groupmask = tmc->groupmask; ), - TP_printk("cpu=%d childmask=%0x parent=%p lvl=%d numa=%d num_children=%d", - __entry->cpu, __entry->childmask, __entry->parent, + TP_printk("cpu=%d groupmask=%0x parent=%p lvl=%d numa=%d num_children=%d", + __entry->cpu, __entry->groupmask, __entry->parent, __entry->lvl, __entry->numa_node, __entry->num_children) ); -- cgit v1.2.3 From a2b72b81fb3ba18717fc000949ca9d45a3351130 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 24 Jul 2024 12:16:20 +0100 Subject: io_uring: kill REQ_F_CANCEL_SEQ We removed the reliance on the flag by the cancellation path and now it's unused. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/e57afe566bbe4fefeb44daffb08900f2a4756577.1721819383.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 3bb6198d1523..e62aa9f0629f 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -461,7 +461,6 @@ enum { REQ_F_SUPPORT_NOWAIT_BIT, REQ_F_ISREG_BIT, REQ_F_POLL_NO_LAZY_BIT, - REQ_F_CANCEL_SEQ_BIT, REQ_F_CAN_POLL_BIT, REQ_F_BL_EMPTY_BIT, REQ_F_BL_NO_RECYCLE_BIT, @@ -536,8 +535,6 @@ enum { REQ_F_HASH_LOCKED = IO_REQ_FLAG(REQ_F_HASH_LOCKED_BIT), /* don't use lazy poll wake for this request */ REQ_F_POLL_NO_LAZY = IO_REQ_FLAG(REQ_F_POLL_NO_LAZY_BIT), - /* cancel sequence is set and valid */ - REQ_F_CANCEL_SEQ = IO_REQ_FLAG(REQ_F_CANCEL_SEQ_BIT), /* file is pollable */ REQ_F_CAN_POLL = IO_REQ_FLAG(REQ_F_CAN_POLL_BIT), /* buffer list was empty after selection of buffer */ -- cgit v1.2.3 From 9722c3b66e21ff08aec570d02a97d331087fd70f Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Wed, 24 Jul 2024 18:33:06 +0200 Subject: of: remove internal arguments from of_property_for_each_u32() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The of_property_for_each_u32() macro needs five parameters, two of which are primarily meant as internal variables for the macro itself (in the for() clause). Yet these two parameters are used by a few drivers, and this can be considered misuse or at least bad practice. Now that the kernel uses C11 to build, these two parameters can be avoided by declaring them internally, thus changing this pattern: struct property *prop; const __be32 *p; u32 val; of_property_for_each_u32(np, "xyz", prop, p, val) { ... } to this: u32 val; of_property_for_each_u32(np, "xyz", val) { ... } However two variables cannot be declared in the for clause even with C11, so declare one struct that contain the two variables we actually need. As the variables inside this struct are not meant to be used by users of this macro, give the struct instance the noticeable name "_it" so it is visible during code reviews, helping to avoid new code to use it directly. Most usages are trivially converted as they do not use those two parameters, as expected. The non-trivial cases are: - drivers/clk/clk.c, of_clk_get_parent_name(): easily doable anyway - drivers/clk/clk-si5351.c, si5351_dt_parse(): this is more complex as the checks had to be replicated in a different way, making code more verbose and somewhat uglier, but I refrained from a full rework to keep as much of the original code untouched having no hardware to test my changes All the changes have been build tested. The few for which I have the hardware have been runtime-tested too. Reviewed-by: Andre Przywara # drivers/clk/sunxi/clk-simple-gates.c, drivers/clk/sunxi/clk-sun8i-bus-gates.c Acked-by: Bartosz Golaszewski # drivers/gpio/gpio-brcmstb.c Acked-by: Nicolas Ferre # drivers/irqchip/irq-atmel-aic-common.c Acked-by: Jonathan Cameron # drivers/iio/adc/ti_am335x_adc.c Acked-by: Uwe Kleine-König # drivers/pwm/pwm-samsung.c Acked-by: Richard Leitner # drivers/usb/misc/usb251xb.c Acked-by: Mark Brown # sound/soc/codecs/arizona.c Reviewed-by: Richard Fitzgerald # sound/soc/codecs/arizona.c Acked-by: Michael Ellerman # arch/powerpc/sysdev/xive/spapr.c Acked-by: Stephen Boyd # clk Signed-off-by: Luca Ceresoli Acked-by: Lee Jones Link: https://lore.kernel.org/r/20240724-of_property_for_each_u32-v3-1-bea82ce429e2@bootlin.com Signed-off-by: Rob Herring (Arm) --- include/linux/of.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/of.h b/include/linux/of.h index 13cf7a43b473..85b60ac9eec5 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -430,11 +430,9 @@ extern int of_detach_node(struct device_node *); #define of_match_ptr(_ptr) (_ptr) /* - * struct property *prop; - * const __be32 *p; * u32 u; * - * of_property_for_each_u32(np, "propname", prop, p, u) + * of_property_for_each_u32(np, "propname", u) * printk("U32 value: %x\n", u); */ const __be32 *of_prop_next_u32(struct property *prop, const __be32 *cur, @@ -1431,11 +1429,12 @@ static inline int of_property_read_s32(const struct device_node *np, err == 0; \ err = of_phandle_iterator_next(it)) -#define of_property_for_each_u32(np, propname, prop, p, u) \ - for (prop = of_find_property(np, propname, NULL), \ - p = of_prop_next_u32(prop, NULL, &u); \ - p; \ - p = of_prop_next_u32(prop, p, &u)) +#define of_property_for_each_u32(np, propname, u) \ + for (struct {struct property *prop; const __be32 *item; } _it = \ + {of_find_property(np, propname, NULL), \ + of_prop_next_u32(_it.prop, NULL, &u)}; \ + _it.item; \ + _it.item = of_prop_next_u32(_it.prop, _it.item, &u)) #define of_property_for_each_string(np, propname, prop, s) \ for (prop = of_find_property(np, propname, NULL), \ -- cgit v1.2.3 From 63c33ca0969cf4d4574103b69fb46f58a19a182b Mon Sep 17 00:00:00 2001 From: Bhoomik Gupta Date: Mon, 8 Jul 2024 11:08:35 +0530 Subject: i3c: master: Enhance i3c_bus_type visibility for device searching & event monitoring Improve the visibility of i3c_bus_type to facilitate searching for i3c devices attached to the i3c bus. Enable other drivers to use bus_register_notifier to monitor i3c bus device events. Signed-off-by: Bhoomik Gupta Link: https://lore.kernel.org/r/20240708053835.3003986-1-bhoomik.gupta@nxp.com Signed-off-by: Alexandre Belloni --- include/linux/i3c/master.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h index 0ca27dd86956..074f632868d9 100644 --- a/include/linux/i3c/master.h +++ b/include/linux/i3c/master.h @@ -33,6 +33,7 @@ enum { struct i3c_master_controller; struct i3c_bus; struct i3c_device; +extern const struct bus_type i3c_bus_type; /** * struct i3c_i2c_dev_desc - Common part of the I3C/I2C device descriptor -- cgit v1.2.3 From 24168c5e6dfbdd5b414f048f47f75d64533296ca Mon Sep 17 00:00:00 2001 From: Carlos Song Date: Mon, 15 Jul 2024 18:53:51 -0400 Subject: dt-bindings: i3c: add header for generic I3C flags Add header file for generic I3C flags to avoid hard code in dts file. Signed-off-by: Carlos Song Reviewed-by: Frank Li Acked-by: Jason Liu Signed-off-by: Frank Li Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20240715225351.3237284-1-Frank.Li@nxp.com Signed-off-by: Alexandre Belloni --- include/dt-bindings/i3c/i3c.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 include/dt-bindings/i3c/i3c.h (limited to 'include') diff --git a/include/dt-bindings/i3c/i3c.h b/include/dt-bindings/i3c/i3c.h new file mode 100644 index 000000000000..373439218bba --- /dev/null +++ b/include/dt-bindings/i3c/i3c.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause */ +/* + * Copyright 2024 NXP + */ + +#ifndef _DT_BINDINGS_I3C_I3C_H +#define _DT_BINDINGS_I3C_I3C_H + +#define I2C_FM (1 << 4) +#define I2C_FM_PLUS (0 << 4) + +#define I2C_FILTER (0 << 5) +#define I2C_NO_FILTER_HIGH_FREQUENCY (1 << 5) +#define I2C_NO_FILTER_LOW_FREQUENCY (2 << 5) + +#endif -- cgit v1.2.3 From 342b2e395d5f34c9f111a818556e617939f83a8c Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Fri, 26 Jul 2024 15:24:30 +0100 Subject: io_uring/napi: use ktime in busy polling It's more natural to use ktime/ns instead of keeping around usec, especially since we're comparing it against user provided timers, so convert napi busy poll internal handling to ktime. It's also nicer since the type (ktime_t vs unsigned long) now tells the unit of measure. Keep everything as ktime, which we convert to/from micro seconds for IORING_[UN]REGISTER_NAPI. The net/ busy polling works seems to work with usec, however it's not real usec as shift by 10 is used to get it from nsecs, see busy_loop_current_time(), so it's easy to get truncated nsec back and we get back better precision. Note, we can further improve it later by removing the truncation and maybe convincing net/ to use ktime/ns instead. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/95e7ec8d095069a3ed5d40a4bc6f8b586698bc7e.1722003776.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index e62aa9f0629f..3315005df117 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -404,7 +404,7 @@ struct io_ring_ctx { spinlock_t napi_lock; /* napi_list lock */ /* napi busy poll default timeout */ - unsigned int napi_busy_poll_to; + ktime_t napi_busy_poll_dt; bool napi_prefer_busy_poll; bool napi_enabled; -- cgit v1.2.3 From d659b715e94ac039803d7601505d3473393fc0be Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Mon, 15 Jul 2024 10:04:23 +1000 Subject: mm/huge_memory: avoid PMD-size page cache if needed xarray can't support arbitrary page cache size. the largest and supported page cache size is defined as MAX_PAGECACHE_ORDER by commit 099d90642a71 ("mm/filemap: make MAX_PAGECACHE_ORDER acceptable to xarray"). However, it's possible to have 512MB page cache in the huge memory's collapsing path on ARM64 system whose base page size is 64KB. 512MB page cache is breaking the limitation and a warning is raised when the xarray entry is split as shown in the following example. [root@dhcp-10-26-1-207 ~]# cat /proc/1/smaps | grep KernelPageSize KernelPageSize: 64 kB [root@dhcp-10-26-1-207 ~]# cat /tmp/test.c : int main(int argc, char **argv) { const char *filename = TEST_XFS_FILENAME; int fd = 0; void *buf = (void *)-1, *p; int pgsize = getpagesize(); int ret = 0; if (pgsize != 0x10000) { fprintf(stdout, "System with 64KB base page size is required!\n"); return -EPERM; } system("echo 0 > /sys/devices/virtual/bdi/253:0/read_ahead_kb"); system("echo 1 > /proc/sys/vm/drop_caches"); /* Open the xfs file */ fd = open(filename, O_RDONLY); assert(fd > 0); /* Create VMA */ buf = mmap(NULL, TEST_MEM_SIZE, PROT_READ, MAP_SHARED, fd, 0); assert(buf != (void *)-1); fprintf(stdout, "mapped buffer at 0x%p\n", buf); /* Populate VMA */ ret = madvise(buf, TEST_MEM_SIZE, MADV_NOHUGEPAGE); assert(ret == 0); ret = madvise(buf, TEST_MEM_SIZE, MADV_POPULATE_READ); assert(ret == 0); /* Collapse VMA */ ret = madvise(buf, TEST_MEM_SIZE, MADV_HUGEPAGE); assert(ret == 0); ret = madvise(buf, TEST_MEM_SIZE, MADV_COLLAPSE); if (ret) { fprintf(stdout, "Error %d to madvise(MADV_COLLAPSE)\n", errno); goto out; } /* Split xarray entry. Write permission is needed */ munmap(buf, TEST_MEM_SIZE); buf = (void *)-1; close(fd); fd = open(filename, O_RDWR); assert(fd > 0); fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, TEST_MEM_SIZE - pgsize, pgsize); out: if (buf != (void *)-1) munmap(buf, TEST_MEM_SIZE); if (fd > 0) close(fd); return ret; } [root@dhcp-10-26-1-207 ~]# gcc /tmp/test.c -o /tmp/test [root@dhcp-10-26-1-207 ~]# /tmp/test ------------[ cut here ]------------ WARNING: CPU: 25 PID: 7560 at lib/xarray.c:1025 xas_split_alloc+0xf8/0x128 Modules linked in: nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib \ nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct \ nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 \ ip_set rfkill nf_tables nfnetlink vfat fat virtio_balloon drm fuse \ xfs libcrc32c crct10dif_ce ghash_ce sha2_ce sha256_arm64 virtio_net \ sha1_ce net_failover virtio_blk virtio_console failover dimlib virtio_mmio CPU: 25 PID: 7560 Comm: test Kdump: loaded Not tainted 6.10.0-rc7-gavin+ #9 Hardware name: QEMU KVM Virtual Machine, BIOS edk2-20240524-1.el9 05/24/2024 pstate: 83400005 (Nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--) pc : xas_split_alloc+0xf8/0x128 lr : split_huge_page_to_list_to_order+0x1c4/0x780 sp : ffff8000ac32f660 x29: ffff8000ac32f660 x28: ffff0000e0969eb0 x27: ffff8000ac32f6c0 x26: 0000000000000c40 x25: ffff0000e0969eb0 x24: 000000000000000d x23: ffff8000ac32f6c0 x22: ffffffdfc0700000 x21: 0000000000000000 x20: 0000000000000000 x19: ffffffdfc0700000 x18: 0000000000000000 x17: 0000000000000000 x16: ffffd5f3708ffc70 x15: 0000000000000000 x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000 x11: ffffffffffffffc0 x10: 0000000000000040 x9 : ffffd5f3708e692c x8 : 0000000000000003 x7 : 0000000000000000 x6 : ffff0000e0969eb8 x5 : ffffd5f37289e378 x4 : 0000000000000000 x3 : 0000000000000c40 x2 : 000000000000000d x1 : 000000000000000c x0 : 0000000000000000 Call trace: xas_split_alloc+0xf8/0x128 split_huge_page_to_list_to_order+0x1c4/0x780 truncate_inode_partial_folio+0xdc/0x160 truncate_inode_pages_range+0x1b4/0x4a8 truncate_pagecache_range+0x84/0xa0 xfs_flush_unmap_range+0x70/0x90 [xfs] xfs_file_fallocate+0xfc/0x4d8 [xfs] vfs_fallocate+0x124/0x2f0 ksys_fallocate+0x4c/0xa0 __arm64_sys_fallocate+0x24/0x38 invoke_syscall.constprop.0+0x7c/0xd8 do_el0_svc+0xb4/0xd0 el0_svc+0x44/0x1d8 el0t_64_sync_handler+0x134/0x150 el0t_64_sync+0x17c/0x180 Fix it by correcting the supported page cache orders, different sets for DAX and other files. With it corrected, 512MB page cache becomes disallowed on all non-DAX files on ARM64 system where the base page size is 64KB. After this patch is applied, the test program fails with error -EINVAL returned from __thp_vma_allowable_orders() and the madvise() system call to collapse the page caches. Link: https://lkml.kernel.org/r/20240715000423.316491-1-gshan@redhat.com Fixes: 6b24ca4a1a8d ("mm: Use multi-index entries in the page cache") Signed-off-by: Gavin Shan Acked-by: David Hildenbrand Reviewed-by: Ryan Roberts Acked-by: Zi Yan Cc: Baolin Wang Cc: Barry Song Cc: Don Dutile Cc: Matthew Wilcox (Oracle) Cc: Peter Xu Cc: Ryan Roberts Cc: William Kucharski Cc: [5.17+] Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index cff002be83eb..e25d9ebfdf89 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -74,14 +74,20 @@ extern struct kobj_attribute thpsize_shmem_enabled_attr; #define THP_ORDERS_ALL_ANON ((BIT(PMD_ORDER + 1) - 1) & ~(BIT(0) | BIT(1))) /* - * Mask of all large folio orders supported for file THP. + * Mask of all large folio orders supported for file THP. Folios in a DAX + * file is never split and the MAX_PAGECACHE_ORDER limit does not apply to + * it. */ -#define THP_ORDERS_ALL_FILE (BIT(PMD_ORDER) | BIT(PUD_ORDER)) +#define THP_ORDERS_ALL_FILE_DAX \ + (BIT(PMD_ORDER) | BIT(PUD_ORDER)) +#define THP_ORDERS_ALL_FILE_DEFAULT \ + ((BIT(MAX_PAGECACHE_ORDER + 1) - 1) & ~BIT(0)) /* * Mask of all large folio orders supported for THP. */ -#define THP_ORDERS_ALL (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE) +#define THP_ORDERS_ALL \ + (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE_DAX | THP_ORDERS_ALL_FILE_DEFAULT) #define TVA_SMAPS (1 << 0) /* Will be used for procfs */ #define TVA_IN_PF (1 << 1) /* Page fault handler */ -- cgit v1.2.3 From b3bebe44306e23827397d0d774d206e3fa374041 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Wed, 17 Jul 2024 14:28:44 -0700 Subject: alloc_tag: outline and export free_reserved_page() Outline and export free_reserved_page() because modules use it and it in turn uses page_ext_{get|put} which should not be exported. The same result could be obtained by outlining {get|put}_page_tag_ref() but that would have higher performance impact as these functions are used in more performance critical paths. Link: https://lkml.kernel.org/r/20240717212844.2749975-1-surenb@google.com Fixes: dcfe378c81f7 ("lib: introduce support for page allocation tagging") Signed-off-by: Suren Baghdasaryan Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202407080044.DWMC9N9I-lkp@intel.com/ Suggested-by: Christoph Hellwig Suggested-by: Vlastimil Babka Acked-by: Vlastimil Babka Cc: Kees Cook Cc: Kent Overstreet Cc: Pasha Tatashin Cc: Sourav Panda Cc: [6.10] Signed-off-by: Andrew Morton --- include/linux/mm.h | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 4563b560ced7..c4b238a20b76 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3137,21 +3137,7 @@ extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end, int nid); /* Free the reserved page into the buddy system, so it gets managed. */ -static inline void free_reserved_page(struct page *page) -{ - if (mem_alloc_profiling_enabled()) { - union codetag_ref *ref = get_page_tag_ref(page); - - if (ref) { - set_codetag_empty(ref); - put_page_tag_ref(ref); - } - } - ClearPageReserved(page); - init_page_count(page); - __free_page(page); - adjust_managed_page_count(page, 1); -} +void free_reserved_page(struct page *page); #define free_highmem_page(page) free_reserved_page(page) static inline void mark_page_reserved(struct page *page) -- cgit v1.2.3 From f59adcf5933271ab7247c4c8938c67be8905b725 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Tue, 23 Jul 2024 17:12:44 +0000 Subject: mm: memcg: add cacheline padding after lruvec in mem_cgroup_per_node Oliver Sand reported a performance regression caused by commit 98c9daf5ae6b ("mm: memcg: guard memcg1-specific members of struct mem_cgroup_per_node"), which puts some fields of the mem_cgroup_per_node structure under the CONFIG_MEMCG_V1 config option. Apparently it causes a false cache sharing between lruvec and lru_zone_size members of the structure. Fix it by adding an explicit padding after the lruvec member. Even though the padding is not required with CONFIG_MEMCG_V1 set, it seems like the introduced memory overhead is not significant enough to warrant another divergence in the mem_cgroup_per_node layout, so the padding is added unconditionally. Link: https://lkml.kernel.org/r/20240723171244.747521-1-roman.gushchin@linux.dev Fixes: 98c9daf5ae6b ("mm: memcg: guard memcg1-specific members of struct mem_cgroup_per_node") Signed-off-by: Roman Gushchin Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202407121335.31a10cb6-oliver.sang@intel.com Tested-by: Oliver Sang Acked-by: Shakeel Butt Cc: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Cc: Roman Gushchin Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 7e2eb091049a..0e5bf25d324f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -109,6 +109,7 @@ struct mem_cgroup_per_node { /* Fields which get updated often at the end. */ struct lruvec lruvec; + CACHELINE_PADDING(_pad2_); unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; struct mem_cgroup_reclaim_iter iter; }; -- cgit v1.2.3 From 3a7e02c040b130b5545e4b115aada7bacd80a2b6 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 26 Jul 2024 15:32:27 -0700 Subject: minmax: avoid overly complicated constant expressions in VM code The minmax infrastructure is overkill for simple constants, and can cause huge expansions because those simple constants are then used by other things. For example, 'pageblock_order' is a core VM constant, but because it was implemented using 'min_t()' and all the type-checking that involves, it actually expanded to something like 2.5kB of preprocessor noise. And when that simple constant was then used inside other expansions: #define pageblock_nr_pages (1UL << pageblock_order) #define pageblock_start_pfn(pfn) ALIGN_DOWN((pfn), pageblock_nr_pages) and we then use that inside a 'max()' macro: case ISOLATE_SUCCESS: update_cached = false; last_migrated_pfn = max(cc->zone->zone_start_pfn, pageblock_start_pfn(cc->migrate_pfn - 1)); the end result was that one statement expanding to 253kB in size. There are probably other cases of this, but this one case certainly stood out. I've added 'MIN_T()' and 'MAX_T()' macros for this kind of "core simple constant with specific type" use. These macros skip the type checking, and as such need to be very sparingly used only for obvious cases that have active issues like this. Reported-by: Lorenzo Stoakes Link: https://lore.kernel.org/all/36aa2cad-1db1-4abf-8dd2-fb20484aabc3@lucifer.local/ Cc: David Laight Signed-off-by: Linus Torvalds --- include/linux/minmax.h | 7 +++++++ include/linux/pageblock-flags.h | 4 ++-- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/minmax.h b/include/linux/minmax.h index 2ec559284a9f..a7ef65f78933 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -270,4 +270,11 @@ static inline bool in_range32(u32 val, u32 start, u32 len) #define swap(a, b) \ do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) +/* + * Use these carefully: no type checking, and uses the arguments + * multiple times. Use for obvious constants only. + */ +#define MIN_T(type,a,b) __cmp(min,(type)(a),(type)(b)) +#define MAX_T(type,a,b) __cmp(max,(type)(a),(type)(b)) + #endif /* _LINUX_MINMAX_H */ diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index 547e82cdc89a..fc6b9c87cb0a 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -41,13 +41,13 @@ extern unsigned int pageblock_order; * Huge pages are a constant size, but don't exceed the maximum allocation * granularity. */ -#define pageblock_order min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_PAGE_ORDER) +#define pageblock_order MIN_T(unsigned int, HUGETLB_PAGE_ORDER, MAX_PAGE_ORDER) #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ #elif defined(CONFIG_TRANSPARENT_HUGEPAGE) -#define pageblock_order min_t(unsigned int, HPAGE_PMD_ORDER, MAX_PAGE_ORDER) +#define pageblock_order MIN_T(unsigned int, HPAGE_PMD_ORDER, MAX_PAGE_ORDER) #else /* CONFIG_TRANSPARENT_HUGEPAGE */ -- cgit v1.2.3 From 00e3913b0416fe69d28745c0a2a340e2f76c219c Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Fri, 26 Jul 2024 01:16:48 +0900 Subject: Revert "firewire: Annotate struct fw_iso_packet with __counted_by()" This reverts commit d3155742db89df3b3c96da383c400e6ff4d23c25. The header_length field is byte unit, thus it can not express the number of elements in header field. It seems that the argument for counted_by attribute can have no arithmetic expression, therefore this commit just reverts the issued commit. Suggested-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20240725161648.130404-1-o-takashi@sakamocchi.jp Signed-off-by: Takashi Sakamoto --- include/linux/firewire.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 00abe0e5d602..1cca14cf5652 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -462,9 +462,8 @@ struct fw_iso_packet { /* rx: Sync bit, wait for matching sy */ u32 tag:2; /* tx: Tag in packet header */ u32 sy:4; /* tx: Sy in packet header */ - u32 header_length:8; /* Length of immediate header */ - /* tx: Top of 1394 isoch. data_block */ - u32 header[] __counted_by(header_length); + u32 header_length:8; /* Size of immediate header */ + u32 header[]; /* tx: Top of 1394 isoch. data_block */ }; #define FW_ISO_CONTEXT_TRANSMIT 0 -- cgit v1.2.3 From 017fa3e89187848fd056af757769c9e66ac3e93d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 28 Jul 2024 13:50:01 -0700 Subject: minmax: simplify and clarify min_t()/max_t() implementation This simplifies the min_t() and max_t() macros by no longer making them work in the context of a C constant expression. That means that you can no longer use them for static initializers or for array sizes in type definitions, but there were only a couple of such uses, and all of them were converted (famous last words) to use MIN_T/MAX_T instead. Cc: David Laight Cc: Lorenzo Stoakes Signed-off-by: Linus Torvalds --- include/linux/minmax.h | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/minmax.h b/include/linux/minmax.h index a7ef65f78933..9c2848abc804 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -45,17 +45,20 @@ #define __cmp(op, x, y) ((x) __cmp_op_##op (y) ? (x) : (y)) -#define __cmp_once(op, x, y, unique_x, unique_y) ({ \ - typeof(x) unique_x = (x); \ - typeof(y) unique_y = (y); \ +#define __cmp_once_unique(op, type, x, y, ux, uy) \ + ({ type ux = (x); type uy = (y); __cmp(op, ux, uy); }) + +#define __cmp_once(op, type, x, y) \ + __cmp_once_unique(op, type, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_)) + +#define __careful_cmp_once(op, x, y) ({ \ static_assert(__types_ok(x, y), \ #op "(" #x ", " #y ") signedness error, fix types or consider u" #op "() before " #op "_t()"); \ - __cmp(op, unique_x, unique_y); }) + __cmp_once(op, __auto_type, x, y); }) #define __careful_cmp(op, x, y) \ __builtin_choose_expr(__is_constexpr((x) - (y)), \ - __cmp(op, x, y), \ - __cmp_once(op, x, y, __UNIQUE_ID(__x), __UNIQUE_ID(__y))) + __cmp(op, x, y), __careful_cmp_once(op, x, y)) #define __clamp(val, lo, hi) \ ((val) >= (hi) ? (hi) : ((val) <= (lo) ? (lo) : (val))) @@ -158,7 +161,7 @@ * @x: first value * @y: second value */ -#define min_t(type, x, y) __careful_cmp(min, (type)(x), (type)(y)) +#define min_t(type, x, y) __cmp_once(min, type, x, y) /** * max_t - return maximum of two values, using the specified type @@ -166,7 +169,7 @@ * @x: first value * @y: second value */ -#define max_t(type, x, y) __careful_cmp(max, (type)(x), (type)(y)) +#define max_t(type, x, y) __cmp_once(max, type, x, y) /* * Do not check the array parameter using __must_be_array(). -- cgit v1.2.3 From 1da91ea87aefe2c25b68c9f96947a9271ba6325d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 31 May 2024 14:12:01 -0400 Subject: introduce fd_file(), convert all accessors to it. For any changes of struct fd representation we need to turn existing accesses to fields into calls of wrappers. Accesses to struct fd::flags are very few (3 in linux/file.h, 1 in net/socket.c, 3 in fs/overlayfs/file.c and 3 more in explicit initializers). Those can be dealt with in the commit converting to new layout; accesses to struct fd::file are too many for that. This commit converts (almost) all of f.file to fd_file(f). It's not entirely mechanical ('file' is used as a member name more than just in struct fd) and it does not even attempt to distinguish the uses in pointer context from those in boolean context; the latter will be eventually turned into a separate helper (fd_empty()). NOTE: mass conversion to fd_empty(), tempting as it might be, is a bad idea; better do that piecewise in commit that convert from fdget...() to CLASS(...). [conflicts in fs/fhandle.c, kernel/bpf/syscall.c, mm/memcontrol.c caught by git; fs/stat.c one got caught by git grep] [fs/xattr.c conflict] Reviewed-by: Christian Brauner Signed-off-by: Al Viro --- include/linux/cleanup.h | 2 +- include/linux/file.h | 6 ++++-- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index d9e613803df1..a3d3e888cf1f 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -98,7 +98,7 @@ const volatile void * __must_check_fn(const volatile void *val) * DEFINE_CLASS(fdget, struct fd, fdput(_T), fdget(fd), int fd) * * CLASS(fdget, f)(fd); - * if (!f.file) + * if (!fd_file(f)) * return -EBADF; * * // use 'f' without concern diff --git a/include/linux/file.h b/include/linux/file.h index 237931f20739..0f3f369f2450 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -42,10 +42,12 @@ struct fd { #define FDPUT_FPUT 1 #define FDPUT_POS_UNLOCK 2 +#define fd_file(f) ((f).file) + static inline void fdput(struct fd fd) { if (fd.flags & FDPUT_FPUT) - fput(fd.file); + fput(fd_file(fd)); } extern struct file *fget(unsigned int fd); @@ -79,7 +81,7 @@ static inline struct fd fdget_pos(int fd) static inline void fdput_pos(struct fd f) { if (f.flags & FDPUT_POS_UNLOCK) - __f_unlock_pos(f.file); + __f_unlock_pos(fd_file(f)); fdput(f); } -- cgit v1.2.3 From 88a2f6468d013ca1163490dbddfc95135d1c27a1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 31 May 2024 15:45:12 -0400 Subject: struct fd: representation change We want the compiler to see that fdput() on empty instance is a no-op. The emptiness check is that file reference is NULL, while fdput() is "fput() if FDPUT_FPUT is present in flags". The reason why fdput() on empty instance is a no-op is something compiler can't see - it's that we never generate instances with NULL file reference combined with non-zero flags. It's not that hard to deal with - the real primitives behind fdget() et.al. are returning an unsigned long value, unpacked by (inlined) __to_fd() into the current struct file * + int. The lower bits are used to store flags, while the rest encodes the pointer. Linus suggested that keeping this unsigned long around with the extractions done by inlined accessors should generate a sane code and that turns out to be the case. Namely, turning struct fd into a struct-wrapped unsinged long, with fd_empty(f) => unlikely(f.word == 0) fd_file(f) => (struct file *)(f.word & ~3) fdput(f) => if (f.word & 1) fput(fd_file(f)) ends up with compiler doing the right thing. The cost is the patch footprint, of course - we need to switch f.file to fd_file(f) all over the tree, and it's not doable with simple search and replace; there are false positives, etc. Note that the sole member of that structure is an opaque unsigned long - all accesses should be done via wrappers and I don't want to use a name that would invite manual casts to file pointers, etc. The value of that member is equal either to (unsigned long)p | flags, p being an address of some struct file instance, or to 0 for an empty fd. For now the new predicate (fd_empty(f)) has no users; all the existing checks have form (!fd_file(f)). We will convert to fd_empty() use later; here we only define it (and tell the compiler that it's unlikely to return true). This commit only deals with representation change; there will be followups. Reviewed-by: Christian Brauner Signed-off-by: Al Viro --- include/linux/file.h | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/file.h b/include/linux/file.h index 0f3f369f2450..eb28469b1c16 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -35,18 +35,28 @@ static inline void fput_light(struct file *file, int fput_needed) fput(file); } +/* either a reference to struct file + flags + * (cloned vs. borrowed, pos locked), with + * flags stored in lower bits of value, + * or empty (represented by 0). + */ struct fd { - struct file *file; - unsigned int flags; + unsigned long word; }; #define FDPUT_FPUT 1 #define FDPUT_POS_UNLOCK 2 -#define fd_file(f) ((f).file) +#define fd_file(f) ((struct file *)((f).word & ~(FDPUT_FPUT|FDPUT_POS_UNLOCK))) +static inline bool fd_empty(struct fd f) +{ + return unlikely(!f.word); +} + +#define EMPTY_FD (struct fd){0} static inline void fdput(struct fd fd) { - if (fd.flags & FDPUT_FPUT) + if (fd.word & FDPUT_FPUT) fput(fd_file(fd)); } @@ -60,7 +70,7 @@ extern void __f_unlock_pos(struct file *); static inline struct fd __to_fd(unsigned long v) { - return (struct fd){(struct file *)(v & ~3),v & 3}; + return (struct fd){v}; } static inline struct fd fdget(unsigned int fd) @@ -80,7 +90,7 @@ static inline struct fd fdget_pos(int fd) static inline void fdput_pos(struct fd f) { - if (f.flags & FDPUT_POS_UNLOCK) + if (f.word & FDPUT_POS_UNLOCK) __f_unlock_pos(fd_file(f)); fdput(f); } -- cgit v1.2.3 From de12c3391bce10504c0e7bd767516c74110cfce1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 31 May 2024 16:34:25 -0400 Subject: add struct fd constructors, get rid of __to_fd() Make __fdget() et.al. return struct fd directly. New helpers: BORROWED_FD(file) and CLONED_FD(file), for borrowed and cloned file references resp. NOTE: this might need tuning; in particular, inline on __fget_light() is there to keep the code generation same as before - we probably want to keep it inlined in fdget() et.al. (especially so in fdget_pos()), but that needs profiling. Reviewed-by: Christian Brauner Signed-off-by: Al Viro --- include/linux/file.h | 33 +++++++++++---------------------- 1 file changed, 11 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/linux/file.h b/include/linux/file.h index eb28469b1c16..aab1caff6713 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -53,6 +53,14 @@ static inline bool fd_empty(struct fd f) } #define EMPTY_FD (struct fd){0} +static inline struct fd BORROWED_FD(struct file *f) +{ + return (struct fd){(unsigned long)f}; +} +static inline struct fd CLONED_FD(struct file *f) +{ + return (struct fd){(unsigned long)f | FDPUT_FPUT}; +} static inline void fdput(struct fd fd) { @@ -63,30 +71,11 @@ static inline void fdput(struct fd fd) extern struct file *fget(unsigned int fd); extern struct file *fget_raw(unsigned int fd); extern struct file *fget_task(struct task_struct *task, unsigned int fd); -extern unsigned long __fdget(unsigned int fd); -extern unsigned long __fdget_raw(unsigned int fd); -extern unsigned long __fdget_pos(unsigned int fd); extern void __f_unlock_pos(struct file *); -static inline struct fd __to_fd(unsigned long v) -{ - return (struct fd){v}; -} - -static inline struct fd fdget(unsigned int fd) -{ - return __to_fd(__fdget(fd)); -} - -static inline struct fd fdget_raw(unsigned int fd) -{ - return __to_fd(__fdget_raw(fd)); -} - -static inline struct fd fdget_pos(int fd) -{ - return __to_fd(__fdget_pos(fd)); -} +struct fd fdget(unsigned int fd); +struct fd fdget_raw(unsigned int fd); +struct fd fdget_pos(unsigned int fd); static inline void fdput_pos(struct fd f) { -- cgit v1.2.3