From 7efa84b5cdd6d473c7e80912638fca9d7167f202 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Fri, 4 Apr 2025 15:10:02 -0700 Subject: compiler-gcc.h: Introduce __diag_GCC_all It is not possible disabling a diagnostic for all versions of GCC without hard coding the minimum supported version at the site, as the GCC specific macros require a minimum version to disable the warning for: __diag_ignore(GCC, 5, ...); __diag_ignore_all() does not solve this issue because it disables a diagnostic for all versions of both GCC and clang, not just one or the other. Introduce __diag_GCC_all so that developers can write __diag_ignore(GCC, all, ...); to disable a particular diagnostic for all versions of GCC, while not affecting clang. Closes: https://lore.kernel.org/r/CAHk-=wgfX9nBGE0Ap9GjhOy7Mn=RSy=rx0MvqfYFFDx31KJXqQ@mail.gmail.com Signed-off-by: Nathan Chancellor Tested-by: Andy Shevchenko Reviewed-by: Petr Mladek Link: https://patch.msgid.link/20250404-vsprintf-convert-pragmas-to-__diag-v1-1-5d6c5c55b2bd@kernel.org Signed-off-by: Petr Mladek --- include/linux/compiler-gcc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index c9b58188ec61..c75a222880f9 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -127,6 +127,8 @@ #define __diag_GCC_8(s) #endif +#define __diag_GCC_all(s) __diag(s) + #define __diag_ignore_all(option, comment) \ __diag(__diag_GCC_ignore option) -- cgit v1.2.3 From de1c831a7898f164c1c2703c6b2b9e4fb4bebefc Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 15 Apr 2025 10:02:33 -0700 Subject: slab: Decouple slab_debug and no_hash_pointers Some system owners use slab_debug=FPZ (or similar) as a hardening option, but do not want to be forced into having kernel addresses exposed due to the implicit "no_hash_pointers" boot param setting.[1] Introduce the "hash_pointers" boot param, which defaults to "auto" (the current behavior), but also includes "always" (forcing on hashing even when "slab_debug=..." is defined), and "never". The existing "no_hash_pointers" boot param becomes an alias for "hash_pointers=never". This makes it possible to boot with "slab_debug=FPZ hash_pointers=always". Link: https://github.com/KSPP/linux/issues/368 [1] Fixes: 792702911f58 ("slub: force on no_hash_pointers when slub_debug is enabled") Co-developed-by: Sergio Perez Gonzalez Signed-off-by: Sergio Perez Gonzalez Acked-by: Vlastimil Babka Acked-by: David Rientjes Reviewed-by: Bagas Sanjaya Signed-off-by: Kees Cook Reviewed-by: Harry Yoo Acked-by: Rafael Aquini Tested-by: Petr Mladek Reviewed-by: Petr Mladek Link: https://patch.msgid.link/20250415170232.it.467-kees@kernel.org [kees@kernel.org: Add note about hash_pointers into slab_debug kernel parameter documentation.] Signed-off-by: Petr Mladek --- Documentation/admin-guide/kernel-parameters.txt | 38 ++++++++++----- include/linux/sprintf.h | 2 +- lib/vsprintf.c | 61 +++++++++++++++++++++++-- mm/slub.c | 5 +- 4 files changed, 86 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 3f35d5b8c296..0dd5cd17e87e 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1798,6 +1798,27 @@ backtraces on all cpus. Format: 0 | 1 + hash_pointers= + [KNL,EARLY] + By default, when pointers are printed to the console + or buffers via the %p format string, that pointer is + "hashed", i.e. obscured by hashing the pointer value. + This is a security feature that hides actual kernel + addresses from unprivileged users, but it also makes + debugging the kernel more difficult since unequal + pointers can no longer be compared. The choices are: + Format: { auto | always | never } + Default: auto + + auto - Hash pointers unless slab_debug is enabled. + always - Always hash pointers (even if slab_debug is + enabled). + never - Never hash pointers. This option should only + be specified when debugging the kernel. Do + not use on production kernels. The boot + param "no_hash_pointers" is an alias for + this mode. + hashdist= [KNL,NUMA] Large hashes allocated during boot are distributed across NUMA nodes. Defaults on for 64-bit NUMA, off otherwise. @@ -4120,18 +4141,7 @@ no_hash_pointers [KNL,EARLY] - Force pointers printed to the console or buffers to be - unhashed. By default, when a pointer is printed via %p - format string, that pointer is "hashed", i.e. obscured - by hashing the pointer value. This is a security feature - that hides actual kernel addresses from unprivileged - users, but it also makes debugging the kernel more - difficult since unequal pointers can no longer be - compared. However, if this command-line option is - specified, then all normal pointers will have their true - value printed. This option should only be specified when - debugging the kernel. Please do not use on production - kernels. + Alias for "hash_pointers=never". nohibernate [HIBERNATION] Disable hibernation and resume. @@ -6481,6 +6491,10 @@ Documentation/mm/slub.rst. (slub_debug legacy name also accepted for now) + Using this option implies the "no_hash_pointers" + option which can be undone by adding the + "hash_pointers=always" option. + slab_max_order= [MM] Determines the maximum allowed order for slabs. A high setting may cause OOMs due to memory diff --git a/include/linux/sprintf.h b/include/linux/sprintf.h index 51cab2def9ec..521bb2cd2648 100644 --- a/include/linux/sprintf.h +++ b/include/linux/sprintf.h @@ -22,7 +22,7 @@ __scanf(2, 0) int vsscanf(const char *, const char *, va_list); /* These are for specific cases, do not use without real need */ extern bool no_hash_pointers; -int no_hash_pointers_enable(char *str); +void hash_pointers_finalize(bool slub_debug); /* Used for Rust formatting ('%pA') */ char *rust_fmt_argument(char *buf, char *end, const void *ptr); diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 01699852f30c..22cbd75266ef 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -60,6 +60,20 @@ bool no_hash_pointers __ro_after_init; EXPORT_SYMBOL_GPL(no_hash_pointers); +/* + * Hashed pointers policy selected by "hash_pointers=..." boot param + * + * `auto` - Hashed pointers enabled unless disabled by slub_debug_enabled=true + * `always` - Hashed pointers enabled unconditionally + * `never` - Hashed pointers disabled unconditionally + */ +enum hash_pointers_policy { + HASH_PTR_AUTO = 0, + HASH_PTR_ALWAYS, + HASH_PTR_NEVER +}; +static enum hash_pointers_policy hash_pointers_mode __initdata; + noinline static unsigned long long simple_strntoull(const char *startp, char **endp, unsigned int base, size_t max_chars) { @@ -2271,12 +2285,23 @@ char *resource_or_range(const char *fmt, char *buf, char *end, void *ptr, return resource_string(buf, end, ptr, spec, fmt); } -int __init no_hash_pointers_enable(char *str) +void __init hash_pointers_finalize(bool slub_debug) { - if (no_hash_pointers) - return 0; + switch (hash_pointers_mode) { + case HASH_PTR_ALWAYS: + no_hash_pointers = false; + break; + case HASH_PTR_NEVER: + no_hash_pointers = true; + break; + case HASH_PTR_AUTO: + default: + no_hash_pointers = slub_debug; + break; + } - no_hash_pointers = true; + if (!no_hash_pointers) + return; pr_warn("**********************************************************\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); @@ -2289,11 +2314,39 @@ int __init no_hash_pointers_enable(char *str) pr_warn("** the kernel, report this immediately to your system **\n"); pr_warn("** administrator! **\n"); pr_warn("** **\n"); + pr_warn("** Use hash_pointers=always to force this mode off **\n"); + pr_warn("** **\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warn("**********************************************************\n"); +} + +static int __init hash_pointers_mode_parse(char *str) +{ + if (!str) { + pr_warn("Hash pointers mode empty; falling back to auto.\n"); + hash_pointers_mode = HASH_PTR_AUTO; + } else if (strncmp(str, "auto", 4) == 0) { + pr_info("Hash pointers mode set to auto.\n"); + hash_pointers_mode = HASH_PTR_AUTO; + } else if (strncmp(str, "never", 5) == 0) { + pr_info("Hash pointers mode set to never.\n"); + hash_pointers_mode = HASH_PTR_NEVER; + } else if (strncmp(str, "always", 6) == 0) { + pr_info("Hash pointers mode set to always.\n"); + hash_pointers_mode = HASH_PTR_ALWAYS; + } else { + pr_warn("Unknown hash_pointers mode '%s' specified; assuming auto.\n", str); + hash_pointers_mode = HASH_PTR_AUTO; + } return 0; } +early_param("hash_pointers", hash_pointers_mode_parse); + +static int __init no_hash_pointers_enable(char *str) +{ + return hash_pointers_mode_parse("never"); +} early_param("no_hash_pointers", no_hash_pointers_enable); /* diff --git a/mm/slub.c b/mm/slub.c index b46f87662e71..f3d61b330a76 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -6314,9 +6314,8 @@ void __init kmem_cache_init(void) if (debug_guardpage_minorder()) slub_max_order = 0; - /* Print slub debugging pointers without hashing */ - if (__slub_debug_enabled()) - no_hash_pointers_enable(NULL); + /* Inform pointer hashing choice about slub debugging state. */ + hash_pointers_finalize(__slub_debug_enabled()); kmem_cache_node = &boot_kmem_cache_node; kmem_cache = &boot_kmem_cache; -- cgit v1.2.3 From 385a766bed48c5bcf620061f24e864dafeca671a Mon Sep 17 00:00:00 2001 From: Igor Belwon Date: Thu, 15 May 2025 16:43:02 +0200 Subject: phy: exynos5-usbdrd: Add support for the Exynos990 usbdrd phy The Exynos990 usbdrd PHY is a combo PHY which supports USB SS, HS and DisplayPort outputs. This commit adds support only for UTMI+ (USB HS). Reviewed-by: Krzysztof Kozlowski Signed-off-by: Igor Belwon Reviewed-by: Neil Armstrong Link: https://lore.kernel.org/r/20250515-usb-resends-may-15-v3-2-ad33a85b6cee@mentallysanemainliners.org Signed-off-by: Vinod Koul --- drivers/phy/samsung/phy-exynos5-usbdrd.c | 32 +++++++++++++++++++++++++++++ include/linux/soc/samsung/exynos-regs-pmu.h | 3 +++ 2 files changed, 35 insertions(+) (limited to 'include/linux') diff --git a/drivers/phy/samsung/phy-exynos5-usbdrd.c b/drivers/phy/samsung/phy-exynos5-usbdrd.c index 917a76d584f0..dd660ebe8045 100644 --- a/drivers/phy/samsung/phy-exynos5-usbdrd.c +++ b/drivers/phy/samsung/phy-exynos5-usbdrd.c @@ -2025,6 +2025,35 @@ static const struct exynos5_usbdrd_phy_drvdata exynos850_usbdrd_phy = { .n_regulators = ARRAY_SIZE(exynos5_regulator_names), }; +static const struct exynos5_usbdrd_phy_tuning exynos990_tunes_utmi_postinit[] = { + PHY_TUNING_ENTRY_PHY(EXYNOS850_DRD_HSPPARACON, + (HSPPARACON_TXVREF | + HSPPARACON_TXPREEMPAMP | HSPPARACON_SQRX | + HSPPARACON_COMPDIS), + (FIELD_PREP_CONST(HSPPARACON_TXVREF, 7) | + FIELD_PREP_CONST(HSPPARACON_TXPREEMPAMP, 3) | + FIELD_PREP_CONST(HSPPARACON_SQRX, 5) | + FIELD_PREP_CONST(HSPPARACON_COMPDIS, 7))), + PHY_TUNING_ENTRY_LAST +}; + +static const struct exynos5_usbdrd_phy_tuning *exynos990_tunes[PTS_MAX] = { + [PTS_UTMI_POSTINIT] = exynos990_tunes_utmi_postinit, +}; + +static const struct exynos5_usbdrd_phy_drvdata exynos990_usbdrd_phy = { + .phy_cfg = phy_cfg_exynos850, + .phy_ops = &exynos850_usbdrd_phy_ops, + .phy_tunes = exynos990_tunes, + .pmu_offset_usbdrd0_phy = EXYNOS990_PHY_CTRL_USB20, + .clk_names = exynos5_clk_names, + .n_clks = ARRAY_SIZE(exynos5_clk_names), + .core_clk_names = exynos5_core_clk_names, + .n_core_clks = ARRAY_SIZE(exynos5_core_clk_names), + .regulator_names = exynos5_regulator_names, + .n_regulators = ARRAY_SIZE(exynos5_regulator_names), +}; + static const struct exynos5_usbdrd_phy_config phy_cfg_gs101[] = { { .id = EXYNOS5_DRDPHY_UTMI, @@ -2228,6 +2257,9 @@ static const struct of_device_id exynos5_usbdrd_phy_of_match[] = { }, { .compatible = "samsung,exynos850-usbdrd-phy", .data = &exynos850_usbdrd_phy + }, { + .compatible = "samsung,exynos990-usbdrd-phy", + .data = &exynos990_usbdrd_phy }, { }, }; diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h index 1a2c0e0838f9..7754697e5810 100644 --- a/include/linux/soc/samsung/exynos-regs-pmu.h +++ b/include/linux/soc/samsung/exynos-regs-pmu.h @@ -662,6 +662,9 @@ #define EXYNOS5433_PAD_RETENTION_UFS_OPTION (0x3268) #define EXYNOS5433_PAD_RETENTION_FSYSGENIO_OPTION (0x32A8) +/* For Exynos990 */ +#define EXYNOS990_PHY_CTRL_USB20 (0x72C) + /* For Tensor GS101 */ /* PMU ALIVE */ #define GS101_SYSIP_DAT0 (0x810) -- cgit v1.2.3 From 72bf1441231ab421a380771e37a5c595493db178 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Sun, 15 Jun 2025 22:32:51 +0900 Subject: firewire: core: allocate workqueue for AR/AT request/response contexts Some tasklets (softIRQs) are still used as bottom-halves to handle events for 1394 OHCI AR/AT contexts. However, using softIRQs for IRQ bottom halves is generally discouraged today. This commit adds a per-fw_card workqueue to accommodate the behaviour specified by the 1394 OHCI specification. According to the 1394 OHCI specification, system memory pages are reserved for each asynchronous DMA context. This allows concurrent operation across contexts. In the 1394 OHCI PCI driver implementation, the hardware generates IRQs either upon receiving asynchronous packets from other nodes (incoming) or after completing transmission to them (outgoing). These independent events can occur in the same transmission cycle, therefore the max_active parameter for the workqueue is set to the total number of AR/AT contexts (=4). The WQ_UNBOUND flag is used to allow the work to be scheduled on any available core, since there is little CPU cache affinity benefit for the data. Each DMA context uses a circular descriptor list in system memory, allowing deferred data processing in software as long as buffer overrun are avoided. Since the overall operation is sleepable except for small atomic regions, WQ_BH is not used. As the descriptors contain timestamps, WQ_HIGHPRI is specified to support semi-real-time processing. The asynchronous context is also used by the SCSI over IEEE 1394 protocol implementation (sbp2), which can be part of memory reclaim paths. Therefore, WQ_MEM_RECLAIM is required. To allow uses to adjust CPU affinity according to workload, WQ_SYSFS is specified so that workqueue attributes are exposed to user space. Link: https://lore.kernel.org/r/20250615133253.433057-2-o-takashi@sakamocchi.jp Signed-off-by: Takashi Sakamoto --- drivers/firewire/core-card.c | 48 +++++++++++++++++++++++++++++++------------- include/linux/firewire.h | 1 + 2 files changed, 35 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c index 2b6ad47b6d57..b3e48ca516fe 100644 --- a/drivers/firewire/core-card.c +++ b/drivers/firewire/core-card.c @@ -574,7 +574,6 @@ EXPORT_SYMBOL(fw_card_initialize); int fw_card_add(struct fw_card *card, u32 max_receive, u32 link_speed, u64 guid, unsigned int supported_isoc_contexts) { - struct workqueue_struct *isoc_wq; int ret; // This workqueue should be: @@ -589,29 +588,48 @@ int fw_card_add(struct fw_card *card, u32 max_receive, u32 link_speed, u64 guid, // * == WQ_SYSFS Parameters are available via sysfs. // * max_active == n_it + n_ir A hardIRQ could notify events for multiple isochronous // contexts if they are scheduled to the same cycle. - isoc_wq = alloc_workqueue("firewire-isoc-card%u", - WQ_UNBOUND | WQ_FREEZABLE | WQ_HIGHPRI | WQ_SYSFS, - supported_isoc_contexts, card->index); - if (!isoc_wq) + card->isoc_wq = alloc_workqueue("firewire-isoc-card%u", + WQ_UNBOUND | WQ_FREEZABLE | WQ_HIGHPRI | WQ_SYSFS, + supported_isoc_contexts, card->index); + if (!card->isoc_wq) return -ENOMEM; + // This workqueue should be: + // * != WQ_BH Sleepable. + // * == WQ_UNBOUND Any core can process data for asynchronous context. + // * == WQ_MEM_RECLAIM Used for any backend of block device. + // * == WQ_FREEZABLE The target device would not be available when being freezed. + // * == WQ_HIGHPRI High priority to process semi-realtime timestamped data. + // * == WQ_SYSFS Parameters are available via sysfs. + // * max_active == 4 A hardIRQ could notify events for a pair of requests and + // response AR/AT contexts. + card->async_wq = alloc_workqueue("firewire-async-card%u", + WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_HIGHPRI | WQ_SYSFS, + 4, card->index); + if (!card->async_wq) { + ret = -ENOMEM; + goto err_isoc; + } + card->max_receive = max_receive; card->link_speed = link_speed; card->guid = guid; - guard(mutex)(&card_mutex); + scoped_guard(mutex, &card_mutex) { + generate_config_rom(card, tmp_config_rom); + ret = card->driver->enable(card, tmp_config_rom, config_rom_length); + if (ret < 0) + goto err_async; - generate_config_rom(card, tmp_config_rom); - ret = card->driver->enable(card, tmp_config_rom, config_rom_length); - if (ret < 0) { - destroy_workqueue(isoc_wq); - return ret; + list_add_tail(&card->link, &card_list); } - card->isoc_wq = isoc_wq; - list_add_tail(&card->link, &card_list); - return 0; +err_async: + destroy_workqueue(card->async_wq); +err_isoc: + destroy_workqueue(card->isoc_wq); + return ret; } EXPORT_SYMBOL(fw_card_add); @@ -744,6 +762,7 @@ void fw_core_remove_card(struct fw_card *card) dummy_driver.stop_iso = card->driver->stop_iso; card->driver = &dummy_driver; drain_workqueue(card->isoc_wq); + drain_workqueue(card->async_wq); scoped_guard(spinlock_irqsave, &card->lock) fw_destroy_nodes(card); @@ -753,6 +772,7 @@ void fw_core_remove_card(struct fw_card *card) wait_for_completion(&card->done); destroy_workqueue(card->isoc_wq); + destroy_workqueue(card->async_wq); WARN_ON(!list_empty(&card->transaction_list)); } diff --git a/include/linux/firewire.h b/include/linux/firewire.h index b632eec3ab52..c55b8e30e700 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -136,6 +136,7 @@ struct fw_card { __be32 maint_utility_register; struct workqueue_struct *isoc_wq; + struct workqueue_struct *async_wq; }; static inline struct fw_card *fw_card_get(struct fw_card *card) -- cgit v1.2.3 From aef6bcc0f278eba408751f8b3e0beae992e9faec Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Sun, 15 Jun 2025 22:32:53 +0900 Subject: firewire: ohci: use workqueue to handle events of AT request/response contexts This commit adds a work item to handle events of 1394 OHCI AT request/response contexts, and queues the item to the specific workqueue. The call of struct fw_packet.callbaqck() is done in the workqueue when receiving acknowledgement to the asynchronous packet transferred to remote node. Link: https://lore.kernel.org/r/20250615133253.433057-4-o-takashi@sakamocchi.jp Signed-off-by: Takashi Sakamoto --- drivers/firewire/net.c | 4 ++-- drivers/firewire/ohci.c | 40 ++++++++++++++++++++++++---------------- include/linux/firewire.h | 11 +++++++++-- 3 files changed, 35 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/firewire/net.c b/drivers/firewire/net.c index 1bf0e15c1540..6d6446713539 100644 --- a/drivers/firewire/net.c +++ b/drivers/firewire/net.c @@ -1007,7 +1007,7 @@ static int fwnet_send_packet(struct fwnet_packet_task *ptask) spin_lock_irqsave(&dev->lock, flags); - /* If the AT tasklet already ran, we may be last user. */ + /* If the AT work item already ran, we may be last user. */ free = (ptask->outstanding_pkts == 0 && !ptask->enqueued); if (!free) ptask->enqueued = true; @@ -1026,7 +1026,7 @@ static int fwnet_send_packet(struct fwnet_packet_task *ptask) spin_lock_irqsave(&dev->lock, flags); - /* If the AT tasklet already ran, we may be last user. */ + /* If the AT work item already ran, we may be last user. */ free = (ptask->outstanding_pkts == 0 && !ptask->enqueued); if (!free) ptask->enqueued = true; diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 68317b5a64a7..709a714fd5c8 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -158,7 +158,7 @@ struct context { descriptor_callback_t callback; - struct tasklet_struct tasklet; + struct work_struct work; }; struct iso_context { @@ -1176,9 +1176,9 @@ static void context_retire_descriptors(struct context *ctx) } } -static void context_tasklet(unsigned long data) +static void ohci_at_context_work(struct work_struct *work) { - struct context *ctx = (struct context *) data; + struct context *ctx = from_work(ctx, work, work); context_retire_descriptors(ctx); } @@ -1243,7 +1243,6 @@ static int context_init(struct context *ctx, struct fw_ohci *ohci, ctx->buffer_tail = list_entry(ctx->buffer_list.next, struct descriptor_buffer, list); - tasklet_init(&ctx->tasklet, context_tasklet, (unsigned long)ctx); ctx->callback = callback; /* @@ -1524,13 +1523,17 @@ static int at_context_queue_packet(struct context *ctx, static void at_context_flush(struct context *ctx) { - tasklet_disable(&ctx->tasklet); + // Avoid dead lock due to programming mistake. + if (WARN_ON_ONCE(current_work() == &ctx->work)) + return; - ctx->flushing = true; - context_tasklet((unsigned long)ctx); - ctx->flushing = false; + disable_work_sync(&ctx->work); - tasklet_enable(&ctx->tasklet); + WRITE_ONCE(ctx->flushing, true); + ohci_at_context_work(&ctx->work); + WRITE_ONCE(ctx->flushing, false); + + enable_work(&ctx->work); } static int handle_at_packet(struct context *context, @@ -1542,7 +1545,7 @@ static int handle_at_packet(struct context *context, struct fw_ohci *ohci = context->ohci; int evt; - if (last->transfer_status == 0 && !context->flushing) + if (last->transfer_status == 0 && !READ_ONCE(context->flushing)) /* This descriptor isn't done yet, stop iteration. */ return 0; @@ -1576,7 +1579,7 @@ static int handle_at_packet(struct context *context, break; case OHCI1394_evt_missing_ack: - if (context->flushing) + if (READ_ONCE(context->flushing)) packet->ack = RCODE_GENERATION; else { /* @@ -1598,7 +1601,7 @@ static int handle_at_packet(struct context *context, break; case OHCI1394_evt_no_status: - if (context->flushing) { + if (READ_ONCE(context->flushing)) { packet->ack = RCODE_GENERATION; break; } @@ -2239,10 +2242,10 @@ static irqreturn_t irq_handler(int irq, void *data) queue_work(ohci->card.async_wq, &ohci->ar_response_ctx.work); if (event & OHCI1394_reqTxComplete) - tasklet_schedule(&ohci->at_request_ctx.tasklet); + queue_work(ohci->card.async_wq, &ohci->at_request_ctx.work); if (event & OHCI1394_respTxComplete) - tasklet_schedule(&ohci->at_response_ctx.tasklet); + queue_work(ohci->card.async_wq, &ohci->at_response_ctx.work); if (event & OHCI1394_isochRx) { iso_event = reg_read(ohci, OHCI1394_IsoRecvIntEventClear); @@ -2684,7 +2687,10 @@ static int ohci_cancel_packet(struct fw_card *card, struct fw_packet *packet) struct driver_data *driver_data = packet->driver_data; int ret = -ENOENT; - tasklet_disable_in_atomic(&ctx->tasklet); + // Avoid dead lock due to programming mistake. + if (WARN_ON_ONCE(current_work() == &ctx->work)) + return 0; + disable_work_sync(&ctx->work); if (packet->ack != 0) goto out; @@ -2703,7 +2709,7 @@ static int ohci_cancel_packet(struct fw_card *card, struct fw_packet *packet) packet->callback(packet, &ohci->card, packet->ack); ret = 0; out: - tasklet_enable(&ctx->tasklet); + enable_work(&ctx->work); return ret; } @@ -3765,11 +3771,13 @@ static int pci_probe(struct pci_dev *dev, OHCI1394_AsReqTrContextControlSet, handle_at_packet); if (err < 0) return err; + INIT_WORK(&ohci->at_request_ctx.work, ohci_at_context_work); err = context_init(&ohci->at_response_ctx, ohci, OHCI1394_AsRspTrContextControlSet, handle_at_packet); if (err < 0) return err; + INIT_WORK(&ohci->at_response_ctx.work, ohci_at_context_work); reg_write(ohci, OHCI1394_IsoRecvIntMaskSet, ~0); ohci->ir_context_channels = ~0ULL; diff --git a/include/linux/firewire.h b/include/linux/firewire.h index c55b8e30e700..cceb70415ed2 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -308,8 +308,7 @@ struct fw_packet { * For successful transmission, the status code is the ack received * from the destination. Otherwise it is one of the juju-specific * rcodes: RCODE_SEND_ERROR, _CANCELLED, _BUSY, _GENERATION, _NO_ACK. - * The callback can be called from tasklet context and thus - * must never block. + * The callback can be called from workqueue and thus must never block. */ fw_packet_callback_t callback; int ack; @@ -382,6 +381,10 @@ void __fw_send_request(struct fw_card *card, struct fw_transaction *t, int tcode * * A variation of __fw_send_request() to generate callback for response subaction without time * stamp. + * + * The callback is invoked in the workqueue context in most cases. However, if an error is detected + * before queueing or the destination address refers to the local node, it is invoked in the + * current context instead. */ static inline void fw_send_request(struct fw_card *card, struct fw_transaction *t, int tcode, int destination_id, int generation, int speed, @@ -411,6 +414,10 @@ static inline void fw_send_request(struct fw_card *card, struct fw_transaction * * @callback_data: data to be passed to the transaction completion callback * * A variation of __fw_send_request() to generate callback for response subaction with time stamp. + * + * The callback is invoked in the workqueue context in most cases. However, if an error is detected + * before queueing or the destination address refers to the local node, it is invoked in the current + * context instead. */ static inline void fw_send_request_with_tstamp(struct fw_card *card, struct fw_transaction *t, int tcode, int destination_id, int generation, int speed, unsigned long long offset, -- cgit v1.2.3 From 543f5e314282c4c2e5114f88ddecc9aeaf0985e2 Mon Sep 17 00:00:00 2001 From: Kaustabh Chakraborty Date: Thu, 12 Jun 2025 20:39:30 +0530 Subject: phy: exynos-mipi-video: introduce support for exynos7870 Add support for Exynos7870 in the existing MIPI CSIS/DSIM driver. The SoC has one DSIM phy and three CSIS phys. Signed-off-by: Kaustabh Chakraborty Reviewed-by: Neil Armstrong Link: https://lore.kernel.org/r/20250612-exynos7870-mipi-phy-v1-2-3fff0b62d9d3@disroot.org Signed-off-by: Vinod Koul --- drivers/phy/samsung/phy-exynos-mipi-video.c | 52 +++++++++++++++++++++++++++++ include/linux/soc/samsung/exynos-regs-pmu.h | 5 +++ 2 files changed, 57 insertions(+) (limited to 'include/linux') diff --git a/drivers/phy/samsung/phy-exynos-mipi-video.c b/drivers/phy/samsung/phy-exynos-mipi-video.c index f6756a609a9a..b184923b9b40 100644 --- a/drivers/phy/samsung/phy-exynos-mipi-video.c +++ b/drivers/phy/samsung/phy-exynos-mipi-video.c @@ -213,6 +213,55 @@ static const struct mipi_phy_device_desc exynos5433_mipi_phy = { }, }; +static const struct mipi_phy_device_desc exynos7870_mipi_phy = { + .num_regmaps = 3, + .regmap_names = { + "samsung,pmu-syscon", + "samsung,disp-sysreg", + "samsung,cam-sysreg" + }, + .num_phys = 4, + .phys = { + { + /* EXYNOS_MIPI_PHY_ID_CSIS0 */ + .coupled_phy_id = EXYNOS_MIPI_PHY_ID_DSIM0, + .enable_val = EXYNOS4_PHY_ENABLE, + .enable_reg = EXYNOS7870_MIPI_PHY_CONTROL0, + .enable_map = EXYNOS_MIPI_REGMAP_PMU, + .resetn_val = BIT(0), + .resetn_reg = 0, + .resetn_map = EXYNOS_MIPI_REGMAP_CAM0, + }, { + /* EXYNOS_MIPI_PHY_ID_DSIM0 */ + .coupled_phy_id = EXYNOS_MIPI_PHY_ID_CSIS0, + .enable_val = EXYNOS4_PHY_ENABLE, + .enable_reg = EXYNOS7870_MIPI_PHY_CONTROL0, + .enable_map = EXYNOS_MIPI_REGMAP_PMU, + .resetn_val = BIT(0), + .resetn_reg = 0, + .resetn_map = EXYNOS_MIPI_REGMAP_DISP, + }, { + /* EXYNOS_MIPI_PHY_ID_CSIS1 */ + .coupled_phy_id = EXYNOS_MIPI_PHY_ID_NONE, + .enable_val = EXYNOS4_PHY_ENABLE, + .enable_reg = EXYNOS7870_MIPI_PHY_CONTROL1, + .enable_map = EXYNOS_MIPI_REGMAP_PMU, + .resetn_val = BIT(1), + .resetn_reg = 0, + .resetn_map = EXYNOS_MIPI_REGMAP_CAM0, + }, { + /* EXYNOS_MIPI_PHY_ID_CSIS2 */ + .coupled_phy_id = EXYNOS_MIPI_PHY_ID_NONE, + .enable_val = EXYNOS4_PHY_ENABLE, + .enable_reg = EXYNOS7870_MIPI_PHY_CONTROL2, + .enable_map = EXYNOS_MIPI_REGMAP_PMU, + .resetn_val = BIT(2), + .resetn_reg = 0, + .resetn_map = EXYNOS_MIPI_REGMAP_CAM0, + }, + }, +}; + struct exynos_mipi_video_phy { struct regmap *regmaps[EXYNOS_MIPI_REGMAPS_NUM]; int num_phys; @@ -351,6 +400,9 @@ static const struct of_device_id exynos_mipi_video_phy_of_match[] = { }, { .compatible = "samsung,exynos5433-mipi-video-phy", .data = &exynos5433_mipi_phy, + }, { + .compatible = "samsung,exynos7870-mipi-video-phy", + .data = &exynos7870_mipi_phy, }, { /* sentinel */ }, }; diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h index 7754697e5810..fa28a8784d65 100644 --- a/include/linux/soc/samsung/exynos-regs-pmu.h +++ b/include/linux/soc/samsung/exynos-regs-pmu.h @@ -665,6 +665,11 @@ /* For Exynos990 */ #define EXYNOS990_PHY_CTRL_USB20 (0x72C) +/* For Exynos7870 */ +#define EXYNOS7870_MIPI_PHY_CONTROL0 (0x070c) +#define EXYNOS7870_MIPI_PHY_CONTROL1 (0x0714) +#define EXYNOS7870_MIPI_PHY_CONTROL2 (0x0734) + /* For Tensor GS101 */ /* PMU ALIVE */ #define GS101_SYSIP_DAT0 (0x810) -- cgit v1.2.3 From 9724e6f1953644cc9a5d102605d624bc79609038 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 11 Jun 2025 08:13:36 +0200 Subject: pinctrl: Constify pointers to 'pinctrl_desc' Pin controller core code only stores the pointer to 'struct pinctrl_desc' and does not modify it anywhere. The pointer can be changed to pointer to const which makes the code safer, explicit and later allows constifying 'pinctrl_desc' allocations in individual drivers. Reviewed-by: Geert Uytterhoeven Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/20250611-pinctrl-const-desc-v2-4-b11c1d650384@linaro.org Signed-off-by: Linus Walleij --- drivers/pinctrl/core.c | 13 +++++++------ drivers/pinctrl/core.h | 2 +- include/linux/pinctrl/pinctrl.h | 8 ++++---- 3 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c index 9046292d1360..73b78d6eac67 100644 --- a/drivers/pinctrl/core.c +++ b/drivers/pinctrl/core.c @@ -2062,7 +2062,7 @@ static int pinctrl_check_ops(struct pinctrl_dev *pctldev) * @driver_data: private pin controller data for this pin controller */ static struct pinctrl_dev * -pinctrl_init_controller(struct pinctrl_desc *pctldesc, struct device *dev, +pinctrl_init_controller(const struct pinctrl_desc *pctldesc, struct device *dev, void *driver_data) { struct pinctrl_dev *pctldev; @@ -2132,7 +2132,8 @@ out_err: return ERR_PTR(ret); } -static void pinctrl_uninit_controller(struct pinctrl_dev *pctldev, struct pinctrl_desc *pctldesc) +static void pinctrl_uninit_controller(struct pinctrl_dev *pctldev, + const struct pinctrl_desc *pctldesc) { pinctrl_free_pindescs(pctldev, pctldesc->pins, pctldesc->npins); @@ -2209,7 +2210,7 @@ EXPORT_SYMBOL_GPL(pinctrl_enable); * struct pinctrl_dev handle. To avoid issues later on, please use the * new pinctrl_register_and_init() below instead. */ -struct pinctrl_dev *pinctrl_register(struct pinctrl_desc *pctldesc, +struct pinctrl_dev *pinctrl_register(const struct pinctrl_desc *pctldesc, struct device *dev, void *driver_data) { struct pinctrl_dev *pctldev; @@ -2239,7 +2240,7 @@ EXPORT_SYMBOL_GPL(pinctrl_register); * Note that pinctrl_enable() still needs to be manually called after * this once the driver is ready. */ -int pinctrl_register_and_init(struct pinctrl_desc *pctldesc, +int pinctrl_register_and_init(const struct pinctrl_desc *pctldesc, struct device *dev, void *driver_data, struct pinctrl_dev **pctldev) { @@ -2330,7 +2331,7 @@ static int devm_pinctrl_dev_match(struct device *dev, void *res, void *data) * The pinctrl device will be automatically released when the device is unbound. */ struct pinctrl_dev *devm_pinctrl_register(struct device *dev, - struct pinctrl_desc *pctldesc, + const struct pinctrl_desc *pctldesc, void *driver_data) { struct pinctrl_dev **ptr, *pctldev; @@ -2364,7 +2365,7 @@ EXPORT_SYMBOL_GPL(devm_pinctrl_register); * The pinctrl device will be automatically released when the device is unbound. */ int devm_pinctrl_register_and_init(struct device *dev, - struct pinctrl_desc *pctldesc, + const struct pinctrl_desc *pctldesc, void *driver_data, struct pinctrl_dev **pctldev) { diff --git a/drivers/pinctrl/core.h b/drivers/pinctrl/core.h index d6c24978e708..fc513a9cdd4f 100644 --- a/drivers/pinctrl/core.h +++ b/drivers/pinctrl/core.h @@ -51,7 +51,7 @@ struct pinctrl_state; */ struct pinctrl_dev { struct list_head node; - struct pinctrl_desc *desc; + const struct pinctrl_desc *desc; struct radix_tree_root pin_desc_tree; #ifdef CONFIG_GENERIC_PINCTRL_GROUPS struct radix_tree_root pin_group_tree; diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h index 9a8189ffd0f2..d138e1815645 100644 --- a/include/linux/pinctrl/pinctrl.h +++ b/include/linux/pinctrl/pinctrl.h @@ -165,25 +165,25 @@ struct pinctrl_desc { /* External interface to pin controller */ -extern int pinctrl_register_and_init(struct pinctrl_desc *pctldesc, +extern int pinctrl_register_and_init(const struct pinctrl_desc *pctldesc, struct device *dev, void *driver_data, struct pinctrl_dev **pctldev); extern int pinctrl_enable(struct pinctrl_dev *pctldev); /* Please use pinctrl_register_and_init() and pinctrl_enable() instead */ -extern struct pinctrl_dev *pinctrl_register(struct pinctrl_desc *pctldesc, +extern struct pinctrl_dev *pinctrl_register(const struct pinctrl_desc *pctldesc, struct device *dev, void *driver_data); extern void pinctrl_unregister(struct pinctrl_dev *pctldev); extern int devm_pinctrl_register_and_init(struct device *dev, - struct pinctrl_desc *pctldesc, + const struct pinctrl_desc *pctldesc, void *driver_data, struct pinctrl_dev **pctldev); /* Please use devm_pinctrl_register_and_init() instead */ extern struct pinctrl_dev *devm_pinctrl_register(struct device *dev, - struct pinctrl_desc *pctldesc, + const struct pinctrl_desc *pctldesc, void *driver_data); extern void devm_pinctrl_unregister(struct device *dev, -- cgit v1.2.3 From 520c790c83e9e4c915a8e3fc9f2152ece39b6511 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Sun, 8 Jun 2025 22:40:02 +0200 Subject: power: supply: core: remove of_node from power_supply_config All drivers have been migrated from .of_node to .fwnode, so let's kill the former. Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Sebastian Reichel Link: https://lore.kernel.org/r/20250430-psy-core-convert-to-fwnode-v2-2-f9643b958677@collabora.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- drivers/power/supply/power_supply_core.c | 3 +-- include/linux/power_supply.h | 1 - 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index 33a5bfce4604..89947f1fe610 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -1529,10 +1529,9 @@ __power_supply_register(struct device *parent, dev_set_drvdata(dev, psy); psy->desc = desc; if (cfg) { + device_set_node(dev, cfg->fwnode); dev->groups = cfg->attr_grp; psy->drv_data = cfg->drv_data; - dev->of_node = - cfg->fwnode ? to_of_node(cfg->fwnode) : cfg->of_node; psy->supplied_to = cfg->supplied_to; psy->num_supplicants = cfg->num_supplicants; } diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 7803edaa8ff8..72012141656e 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -232,7 +232,6 @@ struct power_supply; /* Run-time specific power supply configuration */ struct power_supply_config { - struct device_node *of_node; struct fwnode_handle *fwnode; /* Driver private data */ -- cgit v1.2.3 From f368f87b22dab8e97c5f447b00a0cae79fefbdcb Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Sun, 8 Jun 2025 22:40:06 +0200 Subject: power: supply: core: convert to fwnnode Replace any DT specific code with fwnode in the power-supply core. Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20250430-psy-core-convert-to-fwnode-v2-4-f9643b958677@collabora.com Signed-off-by: Sebastian Reichel --- drivers/power/supply/bq2415x_charger.c | 2 +- drivers/power/supply/power_supply_core.c | 65 ++++++++++++++++---------------- include/linux/power_supply.h | 2 +- 3 files changed, 34 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/drivers/power/supply/bq2415x_charger.c b/drivers/power/supply/bq2415x_charger.c index 9e3b9181ee76..1ecbca510bba 100644 --- a/drivers/power/supply/bq2415x_charger.c +++ b/drivers/power/supply/bq2415x_charger.c @@ -1674,7 +1674,7 @@ static int bq2415x_probe(struct i2c_client *client) /* Query for initial reported_mode and set it */ if (bq->nb.notifier_call) { if (np) { - notify_psy = power_supply_get_by_phandle(np, + notify_psy = power_supply_get_by_phandle(of_fwnode_handle(np), "ti,usb-charger-detection"); if (IS_ERR(notify_psy)) notify_psy = NULL; diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index f2c79f15838d..2d83bb125a48 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include @@ -196,24 +195,24 @@ static int __power_supply_populate_supplied_from(struct power_supply *epsy, void *data) { struct power_supply *psy = data; - struct device_node *np; + struct fwnode_handle *np; int i = 0; do { - np = of_parse_phandle(psy->dev.of_node, "power-supplies", i++); - if (!np) + np = fwnode_find_reference(psy->dev.fwnode, "power-supplies", i++); + if (IS_ERR(np)) break; - if (np == epsy->dev.of_node) { + if (np == epsy->dev.fwnode) { dev_dbg(&psy->dev, "%s: Found supply : %s\n", psy->desc->name, epsy->desc->name); psy->supplied_from[i-1] = (char *)epsy->desc->name; psy->num_supplies++; - of_node_put(np); + fwnode_handle_put(np); break; } - of_node_put(np); - } while (np); + fwnode_handle_put(np); + } while (!IS_ERR(np)); return 0; } @@ -232,16 +231,16 @@ static int power_supply_populate_supplied_from(struct power_supply *psy) static int __power_supply_find_supply_from_node(struct power_supply *epsy, void *data) { - struct device_node *np = data; + struct fwnode_handle *fwnode = data; /* returning non-zero breaks out of power_supply_for_each_psy loop */ - if (epsy->dev.of_node == np) + if (epsy->dev.fwnode == fwnode) return 1; return 0; } -static int power_supply_find_supply_from_node(struct device_node *supply_node) +static int power_supply_find_supply_from_fwnode(struct fwnode_handle *supply_node) { int error; @@ -249,7 +248,7 @@ static int power_supply_find_supply_from_node(struct device_node *supply_node) * power_supply_for_each_psy() either returns its own errors or values * returned by __power_supply_find_supply_from_node(). * - * __power_supply_find_supply_from_node() will return 0 (no match) + * __power_supply_find_supply_from_fwnode() will return 0 (no match) * or 1 (match). * * We return 0 if power_supply_for_each_psy() returned 1, -EPROBE_DEFER if @@ -262,7 +261,7 @@ static int power_supply_find_supply_from_node(struct device_node *supply_node) static int power_supply_check_supplies(struct power_supply *psy) { - struct device_node *np; + struct fwnode_handle *np; int cnt = 0; /* If there is already a list honor it */ @@ -270,24 +269,24 @@ static int power_supply_check_supplies(struct power_supply *psy) return 0; /* No device node found, nothing to do */ - if (!psy->dev.of_node) + if (!psy->dev.fwnode) return 0; do { int ret; - np = of_parse_phandle(psy->dev.of_node, "power-supplies", cnt++); - if (!np) + np = fwnode_find_reference(psy->dev.fwnode, "power-supplies", cnt++); + if (IS_ERR(np)) break; - ret = power_supply_find_supply_from_node(np); - of_node_put(np); + ret = power_supply_find_supply_from_fwnode(np); + fwnode_handle_put(np); if (ret) { dev_dbg(&psy->dev, "Failed to find supply!\n"); return ret; } - } while (np); + } while (!IS_ERR(np)); /* Missing valid "power-supplies" entries */ if (cnt == 1) @@ -498,14 +497,14 @@ void power_supply_put(struct power_supply *psy) EXPORT_SYMBOL_GPL(power_supply_put); #ifdef CONFIG_OF -static int power_supply_match_device_node(struct device *dev, const void *data) +static int power_supply_match_device_fwnode(struct device *dev, const void *data) { - return dev->parent && dev->parent->of_node == data; + return dev->parent && dev_fwnode(dev->parent) == data; } /** * power_supply_get_by_phandle() - Search for a power supply and returns its ref - * @np: Pointer to device node holding phandle property + * @fwnode: Pointer to fwnode holding phandle property * @property: Name of property holding a power supply name * * If power supply was found, it increases reference count for the @@ -515,21 +514,21 @@ static int power_supply_match_device_node(struct device *dev, const void *data) * Return: On success returns a reference to a power supply with * matching name equals to value under @property, NULL or ERR_PTR otherwise. */ -struct power_supply *power_supply_get_by_phandle(struct device_node *np, - const char *property) +struct power_supply *power_supply_get_by_phandle(struct fwnode_handle *fwnode, + const char *property) { - struct device_node *power_supply_np; + struct fwnode_handle *power_supply_fwnode; struct power_supply *psy = NULL; struct device *dev; - power_supply_np = of_parse_phandle(np, property, 0); - if (!power_supply_np) - return ERR_PTR(-ENODEV); + power_supply_fwnode = fwnode_find_reference(fwnode, property, 0); + if (IS_ERR(power_supply_fwnode)) + return ERR_CAST(power_supply_fwnode); - dev = class_find_device(&power_supply_class, NULL, power_supply_np, - power_supply_match_device_node); + dev = class_find_device(&power_supply_class, NULL, power_supply_fwnode, + power_supply_match_device_fwnode); - of_node_put(power_supply_np); + fwnode_handle_put(power_supply_fwnode); if (dev) { psy = dev_to_psy(dev); @@ -561,14 +560,14 @@ struct power_supply *devm_power_supply_get_by_phandle(struct device *dev, { struct power_supply **ptr, *psy; - if (!dev->of_node) + if (!dev_fwnode(dev)) return ERR_PTR(-ENODEV); ptr = devres_alloc(devm_power_supply_put, sizeof(*ptr), GFP_KERNEL); if (!ptr) return ERR_PTR(-ENOMEM); - psy = power_supply_get_by_phandle(dev->of_node, property); + psy = power_supply_get_by_phandle(dev_fwnode(dev), property); if (IS_ERR_OR_NULL(psy)) { devres_free(ptr); } else { diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 72012141656e..d90ac7b73755 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -808,7 +808,7 @@ static inline struct power_supply *power_supply_get_by_name(const char *name) { return NULL; } #endif #ifdef CONFIG_OF -extern struct power_supply *power_supply_get_by_phandle(struct device_node *np, +extern struct power_supply *power_supply_get_by_phandle(struct fwnode_handle *fwnode, const char *property); extern struct power_supply *devm_power_supply_get_by_phandle( struct device *dev, const char *property); -- cgit v1.2.3 From 370643f45aad93476b6489238ccb45a77b94da3f Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Sun, 8 Jun 2025 22:40:07 +0200 Subject: power: supply: core: rename power_supply_get_by_phandle to power_supply_get_by_reference (devm_)power_supply_get_by_phandle now internally uses fwnode and are no longer DT specific. Thus drop the ifdef check for CONFIG_OF and rename to (devm_)power_supply_get_by_reference to avoid the DT terminology. Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20250430-psy-core-convert-to-fwnode-v2-5-f9643b958677@collabora.com Signed-off-by: Sebastian Reichel --- drivers/phy/allwinner/phy-sun4i-usb.c | 2 +- drivers/power/supply/bq2415x_charger.c | 2 +- drivers/power/supply/power_supply_core.c | 22 ++++++++++------------ include/linux/power_supply.h | 15 +++------------ 4 files changed, 15 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/drivers/phy/allwinner/phy-sun4i-usb.c b/drivers/phy/allwinner/phy-sun4i-usb.c index 29b8fd4b9351..8873aed3a52a 100644 --- a/drivers/phy/allwinner/phy-sun4i-usb.c +++ b/drivers/phy/allwinner/phy-sun4i-usb.c @@ -754,7 +754,7 @@ static int sun4i_usb_phy_probe(struct platform_device *pdev) } if (of_property_present(np, "usb0_vbus_power-supply")) { - data->vbus_power_supply = devm_power_supply_get_by_phandle(dev, + data->vbus_power_supply = devm_power_supply_get_by_reference(dev, "usb0_vbus_power-supply"); if (IS_ERR(data->vbus_power_supply)) { dev_err(dev, "Couldn't get the VBUS power supply\n"); diff --git a/drivers/power/supply/bq2415x_charger.c b/drivers/power/supply/bq2415x_charger.c index 1ecbca510bba..917c26ee56bc 100644 --- a/drivers/power/supply/bq2415x_charger.c +++ b/drivers/power/supply/bq2415x_charger.c @@ -1674,7 +1674,7 @@ static int bq2415x_probe(struct i2c_client *client) /* Query for initial reported_mode and set it */ if (bq->nb.notifier_call) { if (np) { - notify_psy = power_supply_get_by_phandle(of_fwnode_handle(np), + notify_psy = power_supply_get_by_reference(of_fwnode_handle(np), "ti,usb-charger-detection"); if (IS_ERR(notify_psy)) notify_psy = NULL; diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index 2d83bb125a48..aedb20c1d276 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -496,14 +496,13 @@ void power_supply_put(struct power_supply *psy) } EXPORT_SYMBOL_GPL(power_supply_put); -#ifdef CONFIG_OF static int power_supply_match_device_fwnode(struct device *dev, const void *data) { return dev->parent && dev_fwnode(dev->parent) == data; } /** - * power_supply_get_by_phandle() - Search for a power supply and returns its ref + * power_supply_get_by_reference() - Search for a power supply and returns its ref * @fwnode: Pointer to fwnode holding phandle property * @property: Name of property holding a power supply name * @@ -514,8 +513,8 @@ static int power_supply_match_device_fwnode(struct device *dev, const void *data * Return: On success returns a reference to a power supply with * matching name equals to value under @property, NULL or ERR_PTR otherwise. */ -struct power_supply *power_supply_get_by_phandle(struct fwnode_handle *fwnode, - const char *property) +struct power_supply *power_supply_get_by_reference(struct fwnode_handle *fwnode, + const char *property) { struct fwnode_handle *power_supply_fwnode; struct power_supply *psy = NULL; @@ -537,7 +536,7 @@ struct power_supply *power_supply_get_by_phandle(struct fwnode_handle *fwnode, return psy; } -EXPORT_SYMBOL_GPL(power_supply_get_by_phandle); +EXPORT_SYMBOL_GPL(power_supply_get_by_reference); static void devm_power_supply_put(struct device *dev, void *res) { @@ -547,16 +546,16 @@ static void devm_power_supply_put(struct device *dev, void *res) } /** - * devm_power_supply_get_by_phandle() - Resource managed version of - * power_supply_get_by_phandle() + * devm_power_supply_get_by_reference() - Resource managed version of + * power_supply_get_by_reference() * @dev: Pointer to device holding phandle property * @property: Name of property holding a power supply phandle * * Return: On success returns a reference to a power supply with * matching name equals to value under @property, NULL or ERR_PTR otherwise. */ -struct power_supply *devm_power_supply_get_by_phandle(struct device *dev, - const char *property) +struct power_supply *devm_power_supply_get_by_reference(struct device *dev, + const char *property) { struct power_supply **ptr, *psy; @@ -567,7 +566,7 @@ struct power_supply *devm_power_supply_get_by_phandle(struct device *dev, if (!ptr) return ERR_PTR(-ENOMEM); - psy = power_supply_get_by_phandle(dev_fwnode(dev), property); + psy = power_supply_get_by_reference(dev_fwnode(dev), property); if (IS_ERR_OR_NULL(psy)) { devres_free(ptr); } else { @@ -576,8 +575,7 @@ struct power_supply *devm_power_supply_get_by_phandle(struct device *dev, } return psy; } -EXPORT_SYMBOL_GPL(devm_power_supply_get_by_phandle); -#endif /* CONFIG_OF */ +EXPORT_SYMBOL_GPL(devm_power_supply_get_by_reference); int power_supply_get_battery_info(struct power_supply *psy, struct power_supply_battery_info **info_out) diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index d90ac7b73755..45468959dd98 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -807,19 +807,10 @@ static inline void power_supply_put(struct power_supply *psy) {} static inline struct power_supply *power_supply_get_by_name(const char *name) { return NULL; } #endif -#ifdef CONFIG_OF -extern struct power_supply *power_supply_get_by_phandle(struct fwnode_handle *fwnode, - const char *property); -extern struct power_supply *devm_power_supply_get_by_phandle( +extern struct power_supply *power_supply_get_by_reference(struct fwnode_handle *fwnode, + const char *property); +extern struct power_supply *devm_power_supply_get_by_reference( struct device *dev, const char *property); -#else /* !CONFIG_OF */ -static inline struct power_supply * -power_supply_get_by_phandle(struct device_node *np, const char *property) -{ return NULL; } -static inline struct power_supply * -devm_power_supply_get_by_phandle(struct device *dev, const char *property) -{ return NULL; } -#endif /* CONFIG_OF */ extern const enum power_supply_property power_supply_battery_info_properties[]; extern const size_t power_supply_battery_info_properties_size; -- cgit v1.2.3 From 3aa54d162490f14d1f1fdf3b3d1170b2ea50276b Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 18 Jun 2025 11:11:29 +0200 Subject: PCI/pwrctrl: Fix the kerneldoc tag for private fields The correct tag for marking private fields in kerneldoc is "private:", not capitalized "Private:". Fix the pwrctl struct to silence the following warnings: Warning: include/linux/pci-pwrctrl.h:45 struct member 'nb' not described in 'pci_pwrctrl' Warning: include/linux/pci-pwrctrl.h:45 struct member 'link' not described in 'pci_pwrctrl' Warning: include/linux/pci-pwrctrl.h:45 struct member 'work' not described in 'pci_pwrctrl' Fixes: 4565d2652a37 ("PCI/pwrctl: Add PCI power control core code") Reported-by: Bjorn Helgaas Closes: https://lore.kernel.org/all/20250617233539.GA1177120@bhelgaas/ Signed-off-by: Bartosz Golaszewski Signed-off-by: Bjorn Helgaas Link: https://patch.msgid.link/20250618091129.44810-1-brgl@bgdev.pl --- include/linux/pci-pwrctrl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci-pwrctrl.h b/include/linux/pci-pwrctrl.h index 7d439b0675e9..4aefc7901cd1 100644 --- a/include/linux/pci-pwrctrl.h +++ b/include/linux/pci-pwrctrl.h @@ -39,7 +39,7 @@ struct device_link; struct pci_pwrctrl { struct device *dev; - /* Private: don't use. */ + /* private: internal use only */ struct notifier_block nb; struct device_link *link; struct work_struct work; -- cgit v1.2.3 From 7934a8dd8692b56714ce9b36421e316445d94a77 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 6 Jun 2025 13:10:23 +0900 Subject: module: remove meaningless 'name' parameter from __MODULE_INFO() The symbol names in the .modinfo section are never used and already randomized by the __UNIQUE_ID() macro. Therefore, the second parameter of __MODULE_INFO() is meaningless and can be removed to simplify the code. With this change, the symbol names in the .modinfo section will be prefixed with __UNIQUE_ID_modinfo, making it clearer that they originate from MODULE_INFO(). [Before] $ objcopy -j .modinfo vmlinux.o modinfo.o $ nm -n modinfo.o | head -n10 0000000000000000 r __UNIQUE_ID_license560 0000000000000011 r __UNIQUE_ID_file559 0000000000000030 r __UNIQUE_ID_description558 0000000000000074 r __UNIQUE_ID_license580 000000000000008e r __UNIQUE_ID_file579 00000000000000bd r __UNIQUE_ID_description578 00000000000000e6 r __UNIQUE_ID_license581 00000000000000ff r __UNIQUE_ID_file580 0000000000000134 r __UNIQUE_ID_description579 0000000000000179 r __UNIQUE_ID_uncore_no_discover578 [After] $ objcopy -j .modinfo vmlinux.o modinfo.o $ nm -n modinfo.o | head -n10 0000000000000000 r __UNIQUE_ID_modinfo560 0000000000000011 r __UNIQUE_ID_modinfo559 0000000000000030 r __UNIQUE_ID_modinfo558 0000000000000074 r __UNIQUE_ID_modinfo580 000000000000008e r __UNIQUE_ID_modinfo579 00000000000000bd r __UNIQUE_ID_modinfo578 00000000000000e6 r __UNIQUE_ID_modinfo581 00000000000000ff r __UNIQUE_ID_modinfo580 0000000000000134 r __UNIQUE_ID_modinfo579 0000000000000179 r __UNIQUE_ID_modinfo578 Signed-off-by: Masahiro Yamada Reviewed-by: Petr Pavlu --- include/crypto/algapi.h | 4 ++-- include/linux/module.h | 3 --- include/linux/moduleparam.h | 9 +++++---- include/net/tcp.h | 4 ++-- 4 files changed, 9 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h index 188eface0a11..fc4574940636 100644 --- a/include/crypto/algapi.h +++ b/include/crypto/algapi.h @@ -43,8 +43,8 @@ * alias. */ #define MODULE_ALIAS_CRYPTO(name) \ - __MODULE_INFO(alias, alias_userspace, name); \ - __MODULE_INFO(alias, alias_crypto, "crypto-" name) + MODULE_INFO(alias, name); \ + MODULE_INFO(alias, "crypto-" name) struct crypto_aead; struct crypto_instance; diff --git a/include/linux/module.h b/include/linux/module.h index 92e1420fccdf..81b41cc6a19e 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -164,9 +164,6 @@ extern void cleanup_module(void); struct module_kobject *lookup_or_create_module_kobject(const char *name); -/* Generic info of form tag = "info" */ -#define MODULE_INFO(tag, info) __MODULE_INFO(tag, tag, info) - /* For userspace: you can also call me... */ #define MODULE_ALIAS(_alias) MODULE_INFO(alias, _alias) diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index bfb85fd13e1f..00166f747e27 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -20,18 +20,19 @@ /* Chosen so that structs with an unsigned long line up. */ #define MAX_PARAM_PREFIX_LEN (64 - sizeof(unsigned long)) -#define __MODULE_INFO(tag, name, info) \ - static const char __UNIQUE_ID(name)[] \ +/* Generic info of form tag = "info" */ +#define MODULE_INFO(tag, info) \ + static const char __UNIQUE_ID(modinfo)[] \ __used __section(".modinfo") __aligned(1) \ = __MODULE_INFO_PREFIX __stringify(tag) "=" info #define __MODULE_PARM_TYPE(name, _type) \ - __MODULE_INFO(parmtype, name##type, #name ":" _type) + MODULE_INFO(parmtype, #name ":" _type) /* One for each parameter, describing how to use it. Some files do multiple of these per line, so can't just use MODULE_INFO. */ #define MODULE_PARM_DESC(_parm, desc) \ - __MODULE_INFO(parm, _parm, #_parm ":" desc) + MODULE_INFO(parm, #_parm ":" desc) struct kernel_param; diff --git a/include/net/tcp.h b/include/net/tcp.h index 5078ad868fee..9b39ef630c92 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2662,8 +2662,8 @@ void tcp_update_ulp(struct sock *sk, struct proto *p, void (*write_space)(struct sock *sk)); #define MODULE_ALIAS_TCP_ULP(name) \ - __MODULE_INFO(alias, alias_userspace, name); \ - __MODULE_INFO(alias, alias_tcp_ulp, "tcp-ulp-" name) + MODULE_INFO(alias, name); \ + MODULE_INFO(alias, "tcp-ulp-" name) #ifdef CONFIG_NET_SOCK_MSG struct sk_msg; -- cgit v1.2.3 From a02fd05661d73a8507dd70dd820e9b984490c545 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Tue, 24 Jun 2025 14:29:27 +0800 Subject: PCI: Extend isolated function probing to LoongArch Like s390 and the jailhouse hypervisor, LoongArch's PCI architecture allows passing isolated PCI functions to a guest OS instance. So it is possible that there is a multi-function device without function 0 for the host or guest. Allow probing such functions by adding a IS_ENABLED(CONFIG_LOONGARCH) case in the hypervisor_isolated_pci_functions() helper. This is similar to commit 189c6c33ff42 ("PCI: Extend isolated function probing to s390"). Signed-off-by: Huacai Chen Signed-off-by: Bjorn Helgaas Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20250624062927.4037734-1-chenhuacai@loongson.cn --- include/linux/hypervisor.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hypervisor.h b/include/linux/hypervisor.h index 9efbc54e35e5..be5417303ecf 100644 --- a/include/linux/hypervisor.h +++ b/include/linux/hypervisor.h @@ -37,6 +37,9 @@ static inline bool hypervisor_isolated_pci_functions(void) if (IS_ENABLED(CONFIG_S390)) return true; + if (IS_ENABLED(CONFIG_LOONGARCH)) + return true; + return jailhouse_paravirt(); } -- cgit v1.2.3 From 2642f55d44ce563f227dd9c620eda0dec8d882be Mon Sep 17 00:00:00 2001 From: Peter Griffin Date: Thu, 19 Jun 2025 12:18:16 +0100 Subject: pinctrl: samsung: add support for gs101 wakeup mask programming gs101 differs to other currently supported SoCs in that it has 3 wakeup mask registers for the 67 external wakeup interrupt pins in alive and far_alive. EINT_WAKEUP_MASK 0x3A80 EINT[31:0] EINT_WAKEUP_MASK2 0x3A84 EINT[63:32] EINT_WAKEUP_MASK3 0x3A88 EINT[66:64] Add gs101 specific callbacks and a dedicated gs101_wkup_irq_chip struct to handle these differences. The current wakeup mask with upstream is programmed as WAKEUP_MASK0[0x3A80] value[0xFFFFFFFF] WAKEUP_MASK1[0x3A84] value[0xF2FFEFFF] WAKEUP_MASK2[0x3A88] value[0xFFFFFFFF] Which corresponds to the following wakeup sources: gpa7-3 vol down gpa8-1 vol up gpa10-1 power gpa8-2 typec-int Signed-off-by: Peter Griffin Link: https://lore.kernel.org/r/20250619-gs101-eint-mask-v1-2-89438cfd7499@linaro.org Signed-off-by: Krzysztof Kozlowski --- drivers/pinctrl/samsung/pinctrl-exynos.c | 100 ++++++++++++++++++++++++---- drivers/pinctrl/samsung/pinctrl-samsung.h | 4 ++ include/linux/soc/samsung/exynos-regs-pmu.h | 1 + 3 files changed, 91 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c index f3e1c11abe55..5554768d465f 100644 --- a/drivers/pinctrl/samsung/pinctrl-exynos.c +++ b/drivers/pinctrl/samsung/pinctrl-exynos.c @@ -32,18 +32,24 @@ #include "pinctrl-samsung.h" #include "pinctrl-exynos.h" +#define MAX_WAKEUP_REG 3 + struct exynos_irq_chip { struct irq_chip chip; u32 eint_con; u32 eint_mask; u32 eint_pend; - u32 *eint_wake_mask_value; + u32 eint_num_wakeup_reg; u32 eint_wake_mask_reg; void (*set_eint_wakeup_mask)(struct samsung_pinctrl_drv_data *drvdata, struct exynos_irq_chip *irq_chip); }; +static u32 eint_wake_mask_values[MAX_WAKEUP_REG] = { EXYNOS_EINT_WAKEUP_MASK_DISABLED, + EXYNOS_EINT_WAKEUP_MASK_DISABLED, + EXYNOS_EINT_WAKEUP_MASK_DISABLED}; + static inline struct exynos_irq_chip *to_exynos_irq_chip(struct irq_chip *chip) { return container_of(chip, struct exynos_irq_chip, chip); @@ -307,7 +313,7 @@ static const struct exynos_irq_chip exynos_gpio_irq_chip __initconst = { .eint_con = EXYNOS_GPIO_ECON_OFFSET, .eint_mask = EXYNOS_GPIO_EMASK_OFFSET, .eint_pend = EXYNOS_GPIO_EPEND_OFFSET, - /* eint_wake_mask_value not used */ + /* eint_wake_mask_values not used */ }; static int exynos_eint_irq_map(struct irq_domain *h, unsigned int virq, @@ -467,10 +473,55 @@ err_domains: return ret; } +#define BITS_PER_U32 32 +static int gs101_wkup_irq_set_wake(struct irq_data *irqd, unsigned int on) +{ + struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd); + struct samsung_pinctrl_drv_data *d = bank->drvdata; + u32 bit, wakeup_reg, shift; + + bit = bank->eint_num + irqd->hwirq; + wakeup_reg = bit / BITS_PER_U32; + shift = bit - (wakeup_reg * BITS_PER_U32); + + if (!on) + eint_wake_mask_values[wakeup_reg] |= BIT_U32(shift); + else + eint_wake_mask_values[wakeup_reg] &= ~BIT_U32(shift); + + dev_info(d->dev, "wake %s for irq %d\n", str_enabled_disabled(on), + irqd->irq); + + return 0; +} + +static void +gs101_pinctrl_set_eint_wakeup_mask(struct samsung_pinctrl_drv_data *drvdata, + struct exynos_irq_chip *irq_chip) +{ + struct regmap *pmu_regs; + + if (!drvdata->retention_ctrl || !drvdata->retention_ctrl->priv) { + dev_warn(drvdata->dev, + "No PMU syscon available. Wake-up mask will not be set.\n"); + return; + } + + pmu_regs = drvdata->retention_ctrl->priv; + + dev_dbg(drvdata->dev, "Setting external wakeup interrupt mask:\n"); + + for (int i = 0; i < irq_chip->eint_num_wakeup_reg; i++) { + dev_dbg(drvdata->dev, "\tWAKEUP_MASK%d[0x%X] value[0x%X]\n", + i, irq_chip->eint_wake_mask_reg + i * 4, + eint_wake_mask_values[i]); + regmap_write(pmu_regs, irq_chip->eint_wake_mask_reg + i * 4, + eint_wake_mask_values[i]); + } +} + static int exynos_wkup_irq_set_wake(struct irq_data *irqd, unsigned int on) { - struct irq_chip *chip = irq_data_get_irq_chip(irqd); - struct exynos_irq_chip *our_chip = to_exynos_irq_chip(chip); struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd); unsigned long bit = 1UL << (2 * bank->eint_offset + irqd->hwirq); @@ -478,9 +529,9 @@ static int exynos_wkup_irq_set_wake(struct irq_data *irqd, unsigned int on) irqd->irq, bank->name, irqd->hwirq); if (!on) - *our_chip->eint_wake_mask_value |= bit; + eint_wake_mask_values[0] |= bit; else - *our_chip->eint_wake_mask_value &= ~bit; + eint_wake_mask_values[0] &= ~bit; return 0; } @@ -500,10 +551,10 @@ exynos_pinctrl_set_eint_wakeup_mask(struct samsung_pinctrl_drv_data *drvdata, pmu_regs = drvdata->retention_ctrl->priv; dev_info(drvdata->dev, "Setting external wakeup interrupt mask: 0x%x\n", - *irq_chip->eint_wake_mask_value); + eint_wake_mask_values[0]); regmap_write(pmu_regs, irq_chip->eint_wake_mask_reg, - *irq_chip->eint_wake_mask_value); + eint_wake_mask_values[0]); } static void @@ -522,11 +573,10 @@ s5pv210_pinctrl_set_eint_wakeup_mask(struct samsung_pinctrl_drv_data *drvdata, clk_base = (void __iomem *) drvdata->retention_ctrl->priv; - __raw_writel(*irq_chip->eint_wake_mask_value, + __raw_writel(eint_wake_mask_values[0], clk_base + irq_chip->eint_wake_mask_reg); } -static u32 eint_wake_mask_value = EXYNOS_EINT_WAKEUP_MASK_DISABLED; /* * irq_chip for wakeup interrupts */ @@ -544,7 +594,7 @@ static const struct exynos_irq_chip s5pv210_wkup_irq_chip __initconst = { .eint_con = EXYNOS_WKUP_ECON_OFFSET, .eint_mask = EXYNOS_WKUP_EMASK_OFFSET, .eint_pend = EXYNOS_WKUP_EPEND_OFFSET, - .eint_wake_mask_value = &eint_wake_mask_value, + .eint_num_wakeup_reg = 1, /* Only differences with exynos4210_wkup_irq_chip: */ .eint_wake_mask_reg = S5PV210_EINT_WAKEUP_MASK, .set_eint_wakeup_mask = s5pv210_pinctrl_set_eint_wakeup_mask, @@ -564,7 +614,7 @@ static const struct exynos_irq_chip exynos4210_wkup_irq_chip __initconst = { .eint_con = EXYNOS_WKUP_ECON_OFFSET, .eint_mask = EXYNOS_WKUP_EMASK_OFFSET, .eint_pend = EXYNOS_WKUP_EPEND_OFFSET, - .eint_wake_mask_value = &eint_wake_mask_value, + .eint_num_wakeup_reg = 1, .eint_wake_mask_reg = EXYNOS_EINT_WAKEUP_MASK, .set_eint_wakeup_mask = exynos_pinctrl_set_eint_wakeup_mask, }; @@ -583,7 +633,7 @@ static const struct exynos_irq_chip exynos7_wkup_irq_chip __initconst = { .eint_con = EXYNOS7_WKUP_ECON_OFFSET, .eint_mask = EXYNOS7_WKUP_EMASK_OFFSET, .eint_pend = EXYNOS7_WKUP_EPEND_OFFSET, - .eint_wake_mask_value = &eint_wake_mask_value, + .eint_num_wakeup_reg = 1, .eint_wake_mask_reg = EXYNOS5433_EINT_WAKEUP_MASK, .set_eint_wakeup_mask = exynos_pinctrl_set_eint_wakeup_mask, }; @@ -599,13 +649,31 @@ static const struct exynos_irq_chip exynosautov920_wkup_irq_chip __initconst = { .irq_request_resources = exynos_irq_request_resources, .irq_release_resources = exynos_irq_release_resources, }, - .eint_wake_mask_value = &eint_wake_mask_value, + .eint_num_wakeup_reg = 1, .eint_wake_mask_reg = EXYNOS5433_EINT_WAKEUP_MASK, .set_eint_wakeup_mask = exynos_pinctrl_set_eint_wakeup_mask, }; +static const struct exynos_irq_chip gs101_wkup_irq_chip __initconst = { + .chip = { + .name = "gs101_wkup_irq_chip", + .irq_unmask = exynos_irq_unmask, + .irq_mask = exynos_irq_mask, + .irq_ack = exynos_irq_ack, + .irq_set_type = exynos_irq_set_type, + .irq_set_wake = gs101_wkup_irq_set_wake, + .irq_request_resources = exynos_irq_request_resources, + .irq_release_resources = exynos_irq_release_resources, + }, + .eint_num_wakeup_reg = 3, + .eint_wake_mask_reg = GS101_EINT_WAKEUP_MASK, + .set_eint_wakeup_mask = gs101_pinctrl_set_eint_wakeup_mask, +}; + /* list of external wakeup controllers supported */ static const struct of_device_id exynos_wkup_irq_ids[] = { + { .compatible = "google,gs101-wakeup-eint", + .data = &gs101_wkup_irq_chip }, { .compatible = "samsung,s5pv210-wakeup-eint", .data = &s5pv210_wkup_irq_chip }, { .compatible = "samsung,exynos4210-wakeup-eint", @@ -688,6 +756,7 @@ out: chained_irq_exit(chip, desc); } +static int eint_num; /* * exynos_eint_wkup_init() - setup handling of external wakeup interrupts. * @d: driver data of samsung pinctrl driver. @@ -736,6 +805,9 @@ __init int exynos_eint_wkup_init(struct samsung_pinctrl_drv_data *d) return -ENXIO; } + bank->eint_num = eint_num; + eint_num = eint_num + bank->nr_pins; + if (!fwnode_property_present(bank->fwnode, "interrupts")) { bank->eint_type = EINT_TYPE_WKUP_MUX; ++muxed_banks; diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.h b/drivers/pinctrl/samsung/pinctrl-samsung.h index fcc57c244d16..1cabcbe1401a 100644 --- a/drivers/pinctrl/samsung/pinctrl-samsung.h +++ b/drivers/pinctrl/samsung/pinctrl-samsung.h @@ -141,6 +141,7 @@ struct samsung_pin_bank_type { * @eint_type: type of the external interrupt supported by the bank. * @eint_mask: bit mask of pins which support EINT function. * @eint_offset: SoC-specific EINT register or interrupt offset of bank. + * @eint_num: total number of eint pins. * @eint_con_offset: ExynosAuto SoC-specific EINT control register offset of bank. * @eint_mask_offset: ExynosAuto SoC-specific EINT mask register offset of bank. * @eint_pend_offset: ExynosAuto SoC-specific EINT pend register offset of bank. @@ -156,6 +157,7 @@ struct samsung_pin_bank_data { enum eint_type eint_type; u32 eint_mask; u32 eint_offset; + u32 eint_num; u32 eint_con_offset; u32 eint_mask_offset; u32 eint_pend_offset; @@ -174,6 +176,7 @@ struct samsung_pin_bank_data { * @eint_type: type of the external interrupt supported by the bank. * @eint_mask: bit mask of pins which support EINT function. * @eint_offset: SoC-specific EINT register or interrupt offset of bank. + * @eint_num: total number of eint pins. * @eint_con_offset: ExynosAuto SoC-specific EINT register or interrupt offset of bank. * @eint_mask_offset: ExynosAuto SoC-specific EINT mask register offset of bank. * @eint_pend_offset: ExynosAuto SoC-specific EINT pend register offset of bank. @@ -201,6 +204,7 @@ struct samsung_pin_bank { enum eint_type eint_type; u32 eint_mask; u32 eint_offset; + u32 eint_num; u32 eint_con_offset; u32 eint_mask_offset; u32 eint_pend_offset; diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h index 1a2c0e0838f9..938c6db235fb 100644 --- a/include/linux/soc/samsung/exynos-regs-pmu.h +++ b/include/linux/soc/samsung/exynos-regs-pmu.h @@ -669,6 +669,7 @@ #define GS101_CPU_INFORM(cpu) \ (GS101_CPU0_INFORM + (cpu*4)) #define GS101_SYSTEM_CONFIGURATION (0x3A00) +#define GS101_EINT_WAKEUP_MASK (0x3A80) #define GS101_PHY_CTRL_USB20 (0x3EB0) #define GS101_PHY_CTRL_USBDP (0x3EB4) -- cgit v1.2.3 From f393a761763c542761abcf978252d431269366d6 Mon Sep 17 00:00:00 2001 From: Gerd Hoffmann Date: Tue, 8 Jul 2025 14:56:23 +0200 Subject: efi: add ovmf debug log driver Recent OVMF versions (edk2-stable202508 + newer) can write their debug log to a memory buffer. This driver exposes the log content via sysfs (/sys/firmware/efi/ovmf_debug_log). Signed-off-by: Gerd Hoffmann Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/Kconfig | 8 +++ drivers/firmware/efi/Makefile | 1 + drivers/firmware/efi/efi.c | 8 +++ drivers/firmware/efi/ovmf-debug-log.c | 111 ++++++++++++++++++++++++++++++++++ include/linux/efi.h | 4 ++ 5 files changed, 132 insertions(+) create mode 100644 drivers/firmware/efi/ovmf-debug-log.c (limited to 'include/linux') diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig index db8c5c03d3a2..eb1bff6968a5 100644 --- a/drivers/firmware/efi/Kconfig +++ b/drivers/firmware/efi/Kconfig @@ -263,6 +263,14 @@ config EFI_COCO_SECRET virt/coco/efi_secret module to access the secrets, which in turn allows userspace programs to access the injected secrets. +config OVMF_DEBUG_LOG + bool "Expose OVMF firmware debug log via sysfs" + depends on EFI + help + Recent OVMF versions (edk2-stable202508 + newer) can write + their debug log to a memory buffer. This driver exposes the + log content via sysfs (/sys/firmware/efi/ovmf_debug_log). + config UNACCEPTED_MEMORY bool depends on EFI_STUB diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile index a2d0009560d0..8efbcf699e4f 100644 --- a/drivers/firmware/efi/Makefile +++ b/drivers/firmware/efi/Makefile @@ -29,6 +29,7 @@ obj-$(CONFIG_APPLE_PROPERTIES) += apple-properties.o obj-$(CONFIG_EFI_RCI2_TABLE) += rci2-table.o obj-$(CONFIG_EFI_EMBEDDED_FIRMWARE) += embedded-firmware.o obj-$(CONFIG_LOAD_UEFI_KEYS) += mokvar-table.o +obj-$(CONFIG_OVMF_DEBUG_LOG) += ovmf-debug-log.o obj-$(CONFIG_SYSFB) += sysfb_efi.o diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index e57bff702b5f..1ce428e2ac8a 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -45,6 +45,7 @@ struct efi __read_mostly efi = { .esrt = EFI_INVALID_TABLE_ADDR, .tpm_log = EFI_INVALID_TABLE_ADDR, .tpm_final_log = EFI_INVALID_TABLE_ADDR, + .ovmf_debug_log = EFI_INVALID_TABLE_ADDR, #ifdef CONFIG_LOAD_UEFI_KEYS .mokvar_table = EFI_INVALID_TABLE_ADDR, #endif @@ -473,6 +474,10 @@ static int __init efisubsys_init(void) platform_device_register_simple("efi_secret", 0, NULL, 0); #endif + if (IS_ENABLED(CONFIG_OVMF_DEBUG_LOG) && + efi.ovmf_debug_log != EFI_INVALID_TABLE_ADDR) + ovmf_log_probe(efi.ovmf_debug_log); + return 0; err_remove_group: @@ -617,6 +622,9 @@ static const efi_config_table_type_t common_tables[] __initconst = { {LINUX_EFI_MEMRESERVE_TABLE_GUID, &mem_reserve, "MEMRESERVE" }, {LINUX_EFI_INITRD_MEDIA_GUID, &initrd, "INITRD" }, {EFI_RT_PROPERTIES_TABLE_GUID, &rt_prop, "RTPROP" }, +#ifdef CONFIG_OVMF_DEBUG_LOG + {OVMF_MEMORY_LOG_TABLE_GUID, &efi.ovmf_debug_log, "OvmfDebugLog" }, +#endif #ifdef CONFIG_EFI_RCI2_TABLE {DELLEMC_EFI_RCI2_TABLE_GUID, &rci2_table_phys }, #endif diff --git a/drivers/firmware/efi/ovmf-debug-log.c b/drivers/firmware/efi/ovmf-debug-log.c new file mode 100644 index 000000000000..5b2471ffaeed --- /dev/null +++ b/drivers/firmware/efi/ovmf-debug-log.c @@ -0,0 +1,111 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include +#include +#include +#include +#include + +#define OVMF_DEBUG_LOG_MAGIC1 0x3167646d666d766f // "ovmfmdg1" +#define OVMF_DEBUG_LOG_MAGIC2 0x3267646d666d766f // "ovmfmdg2" + +struct ovmf_debug_log_header { + u64 magic1; + u64 magic2; + u64 hdr_size; + u64 log_size; + u64 lock; // edk2 spinlock + u64 head_off; + u64 tail_off; + u64 truncated; + u8 fw_version[128]; +}; + +static struct ovmf_debug_log_header *hdr; +static u8 *logbuf; +static u64 logbufsize; + +static ssize_t ovmf_log_read(struct file *filp, struct kobject *kobj, + const struct bin_attribute *attr, char *buf, + loff_t offset, size_t count) +{ + u64 start, end; + + start = hdr->head_off + offset; + if (hdr->head_off > hdr->tail_off && start >= hdr->log_size) + start -= hdr->log_size; + + end = start + count; + if (start > hdr->tail_off) { + if (end > hdr->log_size) + end = hdr->log_size; + } else { + if (end > hdr->tail_off) + end = hdr->tail_off; + } + + if (start > logbufsize || end > logbufsize) + return 0; + if (start >= end) + return 0; + + memcpy(buf, logbuf + start, end - start); + return end - start; +} + +static struct bin_attribute ovmf_log_bin_attr = { + .attr = { + .name = "ovmf_debug_log", + .mode = 0444, + }, + .read = ovmf_log_read, +}; + +int __init ovmf_log_probe(unsigned long ovmf_debug_log_table) +{ + int ret = -EINVAL; + u64 size; + + /* map + verify header */ + hdr = memremap(ovmf_debug_log_table, sizeof(*hdr), MEMREMAP_WB); + if (!hdr) { + pr_err("OVMF debug log: header map failed\n"); + return -EINVAL; + } + + if (hdr->magic1 != OVMF_DEBUG_LOG_MAGIC1 || + hdr->magic2 != OVMF_DEBUG_LOG_MAGIC2) { + printk(KERN_ERR "OVMF debug log: magic mismatch\n"); + goto err_unmap; + } + + size = hdr->hdr_size + hdr->log_size; + pr_info("OVMF debug log: firmware version: \"%s\"\n", hdr->fw_version); + pr_info("OVMF debug log: buffer size: %lluk\n", size / 1024); + + /* map complete log buffer */ + memunmap(hdr); + hdr = memremap(ovmf_debug_log_table, size, MEMREMAP_WB); + if (!hdr) { + pr_err("OVMF debug log: buffer map failed\n"); + return -EINVAL; + } + logbuf = (void *)hdr + hdr->hdr_size; + logbufsize = hdr->log_size; + + ovmf_log_bin_attr.size = size; + ret = sysfs_create_bin_file(efi_kobj, &ovmf_log_bin_attr); + if (ret != 0) { + pr_err("OVMF debug log: sysfs register failed\n"); + goto err_unmap; + } + + return 0; + +err_unmap: + memunmap(hdr); + return ret; +} diff --git a/include/linux/efi.h b/include/linux/efi.h index 7d63d1d75f22..50db7df0efab 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -439,6 +439,7 @@ void efi_native_runtime_setup(void); /* OVMF protocol GUIDs */ #define OVMF_SEV_MEMORY_ACCEPTANCE_PROTOCOL_GUID EFI_GUID(0xc5a010fe, 0x38a7, 0x4531, 0x8a, 0x4a, 0x05, 0x00, 0xd2, 0xfd, 0x16, 0x49) +#define OVMF_MEMORY_LOG_TABLE_GUID EFI_GUID(0x95305139, 0xb20f, 0x4723, 0x84, 0x25, 0x62, 0x7c, 0x88, 0x8f, 0xf1, 0x21) typedef struct { efi_guid_t guid; @@ -642,6 +643,7 @@ extern struct efi { unsigned long esrt; /* ESRT table */ unsigned long tpm_log; /* TPM2 Event Log table */ unsigned long tpm_final_log; /* TPM2 Final Events Log table */ + unsigned long ovmf_debug_log; unsigned long mokvar_table; /* MOK variable config table */ unsigned long coco_secret; /* Confidential computing secret table */ unsigned long unaccepted; /* Unaccepted memory table */ @@ -1344,6 +1346,8 @@ bool efi_config_table_is_usable(const efi_guid_t *guid, unsigned long table) umode_t efi_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n); +int ovmf_log_probe(unsigned long ovmf_debug_log_table); + /* * efivar ops event type */ -- cgit v1.2.3 From 50b4233a22b1ee9ccd0e847597de66ce21329ddb Mon Sep 17 00:00:00 2001 From: Julian Vetter Date: Tue, 3 Jun 2025 15:21:21 +0200 Subject: include/linux/jhash.h: replace __get_unaligned_cpu32 in jhash function __get_unaligned_cpu32() is deprecated. So, replace it with the more generic get_unaligned() and just cast the input parameter. Link: https://lkml.kernel.org/r/20250603132121.3674066-1-julian@outer-limits.org Signed-off-by: Julian Vetter Cc: Arnd Bergmann Cc: Wei-Hsin Yeh Signed-off-by: Andrew Morton --- include/linux/jhash.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jhash.h b/include/linux/jhash.h index fa26a2dd3b52..7c1c1821c694 100644 --- a/include/linux/jhash.h +++ b/include/linux/jhash.h @@ -24,7 +24,7 @@ * Jozsef */ #include -#include +#include /* Best hash sizes are of power of two */ #define jhash_size(n) ((u32)1<<(n)) @@ -77,9 +77,9 @@ static inline u32 jhash(const void *key, u32 length, u32 initval) /* All but the last block: affect some 32 bits of (a,b,c) */ while (length > 12) { - a += __get_unaligned_cpu32(k); - b += __get_unaligned_cpu32(k + 4); - c += __get_unaligned_cpu32(k + 8); + a += get_unaligned((u32 *)k); + b += get_unaligned((u32 *)(k + 4)); + c += get_unaligned((u32 *)(k + 8)); __jhash_mix(a, b, c); length -= 12; k += 12; -- cgit v1.2.3 From 2489e958129ff7cbf26a34ee33cdc9ccbd68fe3c Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Thu, 12 Jun 2025 14:11:57 +0800 Subject: relayfs: abolish prev_padding Patch series "relayfs: misc changes", v5. The series mostly focuses on the error counters which helps every user debug their own kernel module. This patch (of 5): prev_padding represents the unused space of certain subbuffer. If the content of a call of relay_write() exceeds the limit of the remainder of this subbuffer, it will skip storing in the rest space and record the start point as buf->prev_padding in relay_switch_subbuf(). Since the buf is a per-cpu big buffer, the point of prev_padding as a global value for the whole buffer instead of a single subbuffer (whose padding info is stored in buf->padding[]) seems meaningless from the real use cases, so we don't bother to record it any more. Link: https://lkml.kernel.org/r/20250612061201.34272-1-kerneljasonxing@gmail.com Link: https://lkml.kernel.org/r/20250612061201.34272-2-kerneljasonxing@gmail.com Signed-off-by: Jason Xing Reviewed-by: Yushan Zhou Reviewed-by: Masami Hiramatsu (Google) Cc: Jens Axboe Cc: Mathieu Desnoyers Cc: Steven Rostedt Signed-off-by: Andrew Morton --- drivers/gpu/drm/i915/gt/uc/intel_guc_log.c | 3 +-- drivers/net/wwan/iosm/iosm_ipc_trace.c | 3 +-- drivers/net/wwan/t7xx/t7xx_port_trace.c | 2 +- include/linux/relay.h | 5 +---- kernel/relay.c | 14 ++++++++------ kernel/trace/blktrace.c | 2 +- 6 files changed, 13 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c index e8a04e476c57..09a64f224c49 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c @@ -220,8 +220,7 @@ static int guc_action_control_log(struct intel_guc *guc, bool enable, */ static int subbuf_start_callback(struct rchan_buf *buf, void *subbuf, - void *prev_subbuf, - size_t prev_padding) + void *prev_subbuf) { /* * Use no-overwrite mode by default, where relay will stop accepting diff --git a/drivers/net/wwan/iosm/iosm_ipc_trace.c b/drivers/net/wwan/iosm/iosm_ipc_trace.c index eeecfa3d10c5..9656254c1c6c 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_trace.c +++ b/drivers/net/wwan/iosm/iosm_ipc_trace.c @@ -51,8 +51,7 @@ static int ipc_trace_remove_buf_file_handler(struct dentry *dentry) } static int ipc_trace_subbuf_start_handler(struct rchan_buf *buf, void *subbuf, - void *prev_subbuf, - size_t prev_padding) + void *prev_subbuf) { if (relay_buf_full(buf)) { pr_err_ratelimited("Relay_buf full dropping traces"); diff --git a/drivers/net/wwan/t7xx/t7xx_port_trace.c b/drivers/net/wwan/t7xx/t7xx_port_trace.c index 4ed8b4e29bf1..f16d3b01302c 100644 --- a/drivers/net/wwan/t7xx/t7xx_port_trace.c +++ b/drivers/net/wwan/t7xx/t7xx_port_trace.c @@ -33,7 +33,7 @@ static int t7xx_trace_remove_buf_file_handler(struct dentry *dentry) } static int t7xx_trace_subbuf_start_handler(struct rchan_buf *buf, void *subbuf, - void *prev_subbuf, size_t prev_padding) + void *prev_subbuf) { if (relay_buf_full(buf)) { pr_err_ratelimited("Relay_buf full dropping traces"); diff --git a/include/linux/relay.h b/include/linux/relay.h index b3224111d074..e10a0fdf4325 100644 --- a/include/linux/relay.h +++ b/include/linux/relay.h @@ -47,7 +47,6 @@ struct rchan_buf unsigned int page_count; /* number of current buffer pages */ unsigned int finalized; /* buffer has been finalized */ size_t *padding; /* padding counts per sub-buffer */ - size_t prev_padding; /* temporary variable */ size_t bytes_consumed; /* bytes consumed in cur read subbuf */ size_t early_bytes; /* bytes consumed before VFS inited */ unsigned int cpu; /* this buf's cpu */ @@ -84,7 +83,6 @@ struct rchan_callbacks * @buf: the channel buffer containing the new sub-buffer * @subbuf: the start of the new sub-buffer * @prev_subbuf: the start of the previous sub-buffer - * @prev_padding: unused space at the end of previous sub-buffer * * The client should return 1 to continue logging, 0 to stop * logging. @@ -100,8 +98,7 @@ struct rchan_callbacks */ int (*subbuf_start) (struct rchan_buf *buf, void *subbuf, - void *prev_subbuf, - size_t prev_padding); + void *prev_subbuf); /* * create_buf_file - create file to represent a relay channel buffer diff --git a/kernel/relay.c b/kernel/relay.c index 3ee5b038d0d9..fc6ad76b789d 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -249,13 +249,13 @@ EXPORT_SYMBOL_GPL(relay_buf_full); */ static int relay_subbuf_start(struct rchan_buf *buf, void *subbuf, - void *prev_subbuf, size_t prev_padding) + void *prev_subbuf) { if (!buf->chan->cb->subbuf_start) return !relay_buf_full(buf); return buf->chan->cb->subbuf_start(buf, subbuf, - prev_subbuf, prev_padding); + prev_subbuf); } /** @@ -301,7 +301,7 @@ static void __relay_reset(struct rchan_buf *buf, unsigned int init) for (i = 0; i < buf->chan->n_subbufs; i++) buf->padding[i] = 0; - relay_subbuf_start(buf, buf->data, NULL, 0); + relay_subbuf_start(buf, buf->data, NULL); } /** @@ -554,9 +554,11 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length) goto toobig; if (buf->offset != buf->chan->subbuf_size + 1) { - buf->prev_padding = buf->chan->subbuf_size - buf->offset; + size_t prev_padding; + + prev_padding = buf->chan->subbuf_size - buf->offset; old_subbuf = buf->subbufs_produced % buf->chan->n_subbufs; - buf->padding[old_subbuf] = buf->prev_padding; + buf->padding[old_subbuf] = prev_padding; buf->subbufs_produced++; if (buf->dentry) d_inode(buf->dentry)->i_size += @@ -581,7 +583,7 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length) new_subbuf = buf->subbufs_produced % buf->chan->n_subbufs; new = buf->start + new_subbuf * buf->chan->subbuf_size; buf->offset = 0; - if (!relay_subbuf_start(buf, new, old, buf->prev_padding)) { + if (!relay_subbuf_start(buf, new, old)) { buf->offset = buf->chan->subbuf_size + 1; return 0; } diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 3f6a7bdc6edf..d3083c88474e 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -461,7 +461,7 @@ static const struct file_operations blk_msg_fops = { * the user space app in telling how many lost events there were. */ static int blk_subbuf_start_callback(struct rchan_buf *buf, void *subbuf, - void *prev_subbuf, size_t prev_padding) + void *prev_subbuf) { struct blk_trace *bt; -- cgit v1.2.3 From ca01a90ae7bf9bb22137e719366bdc0f387675c2 Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Thu, 12 Jun 2025 14:11:58 +0800 Subject: relayfs: support a counter tracking if per-cpu buffers is full When using relay mechanism, we often encounter the case where new data are lost or old unconsumed data are overwritten because of slow reader. Add 'full' field in per-cpu buffer structure to detect if the above case is happening. Relay has two modes: 1) non-overwrite mode, 2) overwrite mode. So buffer being full here respectively means: 1) relayfs doesn't intend to accept new data and then simply drop them, or 2) relayfs is going to start over again and overwrite old unread data with new data. Note: this counter doesn't need any explicit lock to protect from being modified by different threads for the better performance consideration. Writers calling __relay_write/relay_write should consider how to use the lock and ensure it performs under the lock protection, thus it's not necessary to add a new small lock here. Link: https://lkml.kernel.org/r/20250612061201.34272-3-kerneljasonxing@gmail.com Signed-off-by: Jason Xing Reviewed-by: Yushan Zhou Reviewed-by: Jens Axboe Reviewed-by: Masami Hiramatsu (Google) Cc: Mathieu Desnoyers Cc: Steven Rostedt Signed-off-by: Andrew Morton --- include/linux/relay.h | 9 +++++++++ kernel/relay.c | 8 +++++++- 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/relay.h b/include/linux/relay.h index e10a0fdf4325..cd77eb285a48 100644 --- a/include/linux/relay.h +++ b/include/linux/relay.h @@ -28,6 +28,14 @@ */ #define RELAYFS_CHANNEL_VERSION 7 +/* + * Relay buffer statistics + */ +struct rchan_buf_stats +{ + unsigned int full_count; /* counter for buffer full */ +}; + /* * Per-cpu relay channel buffer */ @@ -43,6 +51,7 @@ struct rchan_buf struct irq_work wakeup_work; /* reader wakeup */ struct dentry *dentry; /* channel file dentry */ struct kref kref; /* channel buffer refcount */ + struct rchan_buf_stats stats; /* buffer stats */ struct page **page_array; /* array of current buffer pages */ unsigned int page_count; /* number of current buffer pages */ unsigned int finalized; /* buffer has been finalized */ diff --git a/kernel/relay.c b/kernel/relay.c index fc6ad76b789d..4b07efddc2cf 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -251,8 +251,13 @@ EXPORT_SYMBOL_GPL(relay_buf_full); static int relay_subbuf_start(struct rchan_buf *buf, void *subbuf, void *prev_subbuf) { + int full = relay_buf_full(buf); + + if (full) + buf->stats.full_count++; + if (!buf->chan->cb->subbuf_start) - return !relay_buf_full(buf); + return !full; return buf->chan->cb->subbuf_start(buf, subbuf, prev_subbuf); @@ -297,6 +302,7 @@ static void __relay_reset(struct rchan_buf *buf, unsigned int init) buf->finalized = 0; buf->data = buf->start; buf->offset = 0; + buf->stats.full_count = 0; for (i = 0; i < buf->chan->n_subbufs; i++) buf->padding[i] = 0; -- cgit v1.2.3 From a53202ce7fbafd24f854865b02eff891e246c550 Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Thu, 12 Jun 2025 14:11:59 +0800 Subject: relayfs: introduce getting relayfs statistics function In this version, only support getting the counter for buffer full and implement the framework of how it works. Users can pass certain flag to fetch what field/statistics they expect to know. Each time it only returns one result. So do not pass multiple flags. Link: https://lkml.kernel.org/r/20250612061201.34272-4-kerneljasonxing@gmail.com Signed-off-by: Jason Xing Reviewed-by: Yushan Zhou Reviewed-by: Masami Hiramatsu (Google) Cc: Jens Axboe Cc: Mathieu Desnoyers Cc: Steven Rostedt Signed-off-by: Andrew Morton --- include/linux/relay.h | 7 +++++++ kernel/relay.c | 30 ++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+) (limited to 'include/linux') diff --git a/include/linux/relay.h b/include/linux/relay.h index cd77eb285a48..5310967f9d74 100644 --- a/include/linux/relay.h +++ b/include/linux/relay.h @@ -31,6 +31,12 @@ /* * Relay buffer statistics */ +enum { + RELAY_STATS_BUF_FULL = (1 << 0), + + RELAY_STATS_LAST = RELAY_STATS_BUF_FULL, +}; + struct rchan_buf_stats { unsigned int full_count; /* counter for buffer full */ @@ -167,6 +173,7 @@ struct rchan *relay_open(const char *base_filename, void *private_data); extern void relay_close(struct rchan *chan); extern void relay_flush(struct rchan *chan); +size_t relay_stats(struct rchan *chan, int flags); extern void relay_subbufs_consumed(struct rchan *chan, unsigned int cpu, size_t consumed); diff --git a/kernel/relay.c b/kernel/relay.c index 4b07efddc2cf..2fc27c0e771e 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -700,6 +700,36 @@ void relay_flush(struct rchan *chan) } EXPORT_SYMBOL_GPL(relay_flush); +/** + * relay_stats - get channel buffer statistics + * @chan: the channel + * @flags: select particular information to get + * + * Returns the count of certain field that caller specifies. + */ +size_t relay_stats(struct rchan *chan, int flags) +{ + unsigned int i, count = 0; + struct rchan_buf *rbuf; + + if (!chan || flags > RELAY_STATS_LAST) + return 0; + + if (chan->is_global) { + rbuf = *per_cpu_ptr(chan->buf, 0); + if (flags & RELAY_STATS_BUF_FULL) + count = rbuf->stats.full_count; + } else { + for_each_online_cpu(i) { + rbuf = *per_cpu_ptr(chan->buf, i); + if (rbuf && flags & RELAY_STATS_BUF_FULL) + count += rbuf->stats.full_count; + } + } + + return count; +} + /** * relay_file_open - open file op for relay files * @inode: the inode -- cgit v1.2.3 From 19f3cb64a25b80db667a00182785577fae465b3e Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Thu, 12 Jun 2025 14:12:01 +0800 Subject: relayfs: support a counter tracking if data is too big to write It really doesn't matter if the user/admin knows what the last too big value is. Record how many times this case is triggered would be helpful. Solve the existing issue where relay_reset() doesn't restore the value. Store the counter in the per-cpu buffer structure instead of the global buffer structure. It also solves the racy condition which is likely to happen when a few of per-cpu buffers encounter the too big data case and then access the global field last_toobig without lock protection. Remove the printk in relay_close() since kernel module can directly call relay_stats() as they want. Link: https://lkml.kernel.org/r/20250612061201.34272-6-kerneljasonxing@gmail.com Signed-off-by: Jason Xing Reviewed-by: Yushan Zhou Reviewed-by: Masami Hiramatsu (Google) Cc: Jens Axboe Cc: Mathieu Desnoyers Cc: Steven Rostedt Signed-off-by: Andrew Morton --- include/linux/relay.h | 5 +++-- kernel/relay.c | 18 ++++++++++-------- 2 files changed, 13 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/relay.h b/include/linux/relay.h index 5310967f9d74..6772a7075840 100644 --- a/include/linux/relay.h +++ b/include/linux/relay.h @@ -33,13 +33,15 @@ */ enum { RELAY_STATS_BUF_FULL = (1 << 0), + RELAY_STATS_WRT_BIG = (1 << 1), - RELAY_STATS_LAST = RELAY_STATS_BUF_FULL, + RELAY_STATS_LAST = RELAY_STATS_WRT_BIG, }; struct rchan_buf_stats { unsigned int full_count; /* counter for buffer full */ + unsigned int big_count; /* counter for too big to write */ }; /* @@ -79,7 +81,6 @@ struct rchan const struct rchan_callbacks *cb; /* client callbacks */ struct kref kref; /* channel refcount */ void *private_data; /* for user-defined data */ - size_t last_toobig; /* tried to log event > subbuf size */ struct rchan_buf * __percpu *buf; /* per-cpu channel buffers */ int is_global; /* One global buffer ? */ struct list_head list; /* for channel list */ diff --git a/kernel/relay.c b/kernel/relay.c index 2fc27c0e771e..8d915fe98198 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -303,6 +303,7 @@ static void __relay_reset(struct rchan_buf *buf, unsigned int init) buf->data = buf->start; buf->offset = 0; buf->stats.full_count = 0; + buf->stats.big_count = 0; for (i = 0; i < buf->chan->n_subbufs; i++) buf->padding[i] = 0; @@ -602,7 +603,7 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length) return length; toobig: - buf->chan->last_toobig = length; + buf->stats.big_count++; return 0; } EXPORT_SYMBOL_GPL(relay_switch_subbuf); @@ -662,11 +663,6 @@ void relay_close(struct rchan *chan) if ((buf = *per_cpu_ptr(chan->buf, i))) relay_close_buf(buf); - if (chan->last_toobig) - printk(KERN_WARNING "relay: one or more items not logged " - "[item size (%zd) > sub-buffer size (%zd)]\n", - chan->last_toobig, chan->subbuf_size); - list_del(&chan->list); kref_put(&chan->kref, relay_destroy_channel); mutex_unlock(&relay_channels_mutex); @@ -719,11 +715,17 @@ size_t relay_stats(struct rchan *chan, int flags) rbuf = *per_cpu_ptr(chan->buf, 0); if (flags & RELAY_STATS_BUF_FULL) count = rbuf->stats.full_count; + else if (flags & RELAY_STATS_WRT_BIG) + count = rbuf->stats.big_count; } else { for_each_online_cpu(i) { rbuf = *per_cpu_ptr(chan->buf, i); - if (rbuf && flags & RELAY_STATS_BUF_FULL) - count += rbuf->stats.full_count; + if (rbuf) { + if (flags & RELAY_STATS_BUF_FULL) + count += rbuf->stats.full_count; + else if (flags & RELAY_STATS_WRT_BIG) + count += rbuf->stats.big_count; + } } } -- cgit v1.2.3 From 1857fcc847443b0238cb64584b43d8c3a9049a0a Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 17 Mar 2025 17:02:28 +0800 Subject: lib/raid6: replace custom zero page with ZERO_PAGE Use the system-wide zero page instead of a custom zero page. [herbert@gondor.apana.org.au: update lib/raid6/recov_rvv.c, per Klara] Link: https://lkml.kernel.org/r/aFkUnXWtxcgOTVkw@gondor.apana.org.au Link: https://lkml.kernel.org/r/Z9flJNkWQICx0PXk@gondor.apana.org.au Signed-off-by: Herbert Xu Cc: Song Liu Cc: Yu Kuai Cc: Klara Modin Signed-off-by: Andrew Morton --- crypto/async_tx/async_pq.c | 2 +- crypto/async_tx/async_raid6_recov.c | 4 ++-- include/linux/raid/pq.h | 12 +++++++++++- lib/raid6/algos.c | 3 --- lib/raid6/recov.c | 6 +++--- lib/raid6/recov_avx2.c | 6 +++--- lib/raid6/recov_avx512.c | 6 +++--- lib/raid6/recov_loongarch_simd.c | 12 ++++++------ lib/raid6/recov_neon.c | 6 +++--- lib/raid6/recov_s390xc.c | 6 +++--- lib/raid6/recov_ssse3.c | 6 +++--- 11 files changed, 38 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c index 5e2b2680d7db..9e4bb7fbde25 100644 --- a/crypto/async_tx/async_pq.c +++ b/crypto/async_tx/async_pq.c @@ -119,7 +119,7 @@ do_sync_gen_syndrome(struct page **blocks, unsigned int *offsets, int disks, for (i = 0; i < disks; i++) { if (blocks[i] == NULL) { BUG_ON(i > disks - 3); /* P or Q can't be zero */ - srcs[i] = (void*)raid6_empty_zero_page; + srcs[i] = raid6_get_zero_page(); } else { srcs[i] = page_address(blocks[i]) + offsets[i]; diff --git a/crypto/async_tx/async_raid6_recov.c b/crypto/async_tx/async_raid6_recov.c index 354b8cd5537f..539ea5b378dc 100644 --- a/crypto/async_tx/async_raid6_recov.c +++ b/crypto/async_tx/async_raid6_recov.c @@ -414,7 +414,7 @@ async_raid6_2data_recov(int disks, size_t bytes, int faila, int failb, async_tx_quiesce(&submit->depend_tx); for (i = 0; i < disks; i++) if (blocks[i] == NULL) - ptrs[i] = (void *) raid6_empty_zero_page; + ptrs[i] = raid6_get_zero_page(); else ptrs[i] = page_address(blocks[i]) + offs[i]; @@ -497,7 +497,7 @@ async_raid6_datap_recov(int disks, size_t bytes, int faila, async_tx_quiesce(&submit->depend_tx); for (i = 0; i < disks; i++) if (blocks[i] == NULL) - ptrs[i] = (void*)raid6_empty_zero_page; + ptrs[i] = raid6_get_zero_page(); else ptrs[i] = page_address(blocks[i]) + offs[i]; diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h index 72ff44cca864..2467b3be15c9 100644 --- a/include/linux/raid/pq.h +++ b/include/linux/raid/pq.h @@ -11,8 +11,13 @@ #ifdef __KERNEL__ #include +#include -extern const char raid6_empty_zero_page[PAGE_SIZE]; +/* This should be const but the raid6 code is too convoluted for that. */ +static inline void *raid6_get_zero_page(void) +{ + return page_address(ZERO_PAGE(0)); +} #else /* ! __KERNEL__ */ /* Used for testing in user space */ @@ -191,6 +196,11 @@ static inline uint32_t raid6_jiffies(void) return tv.tv_sec*1000 + tv.tv_usec/1000; } +static inline void *raid6_get_zero_page(void) +{ + return raid6_empty_zero_page; +} + #endif /* ! __KERNEL__ */ #endif /* LINUX_RAID_RAID6_H */ diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c index 75ce3e134b7c..799e0e5eac26 100644 --- a/lib/raid6/algos.c +++ b/lib/raid6/algos.c @@ -18,9 +18,6 @@ #else #include #include -/* In .bss so it's zeroed */ -const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(256))); -EXPORT_SYMBOL(raid6_empty_zero_page); #endif struct raid6_calls raid6_call; diff --git a/lib/raid6/recov.c b/lib/raid6/recov.c index a7c1b2bbe40d..b5e47c008b41 100644 --- a/lib/raid6/recov.c +++ b/lib/raid6/recov.c @@ -31,10 +31,10 @@ static void raid6_2data_recov_intx1(int disks, size_t bytes, int faila, Use the dead data pages as temporary storage for delta p and delta q */ dp = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks-2] = dp; dq = (u8 *)ptrs[failb]; - ptrs[failb] = (void *)raid6_empty_zero_page; + ptrs[failb] = raid6_get_zero_page(); ptrs[disks-1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); @@ -72,7 +72,7 @@ static void raid6_datap_recov_intx1(int disks, size_t bytes, int faila, /* Compute syndrome with zero for the missing data page Use the dead data page as temporary storage for delta q */ dq = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks-1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); diff --git a/lib/raid6/recov_avx2.c b/lib/raid6/recov_avx2.c index 4e8095403ee2..97d598d2535c 100644 --- a/lib/raid6/recov_avx2.c +++ b/lib/raid6/recov_avx2.c @@ -28,10 +28,10 @@ static void raid6_2data_recov_avx2(int disks, size_t bytes, int faila, Use the dead data pages as temporary storage for delta p and delta q */ dp = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks-2] = dp; dq = (u8 *)ptrs[failb]; - ptrs[failb] = (void *)raid6_empty_zero_page; + ptrs[failb] = raid6_get_zero_page(); ptrs[disks-1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); @@ -196,7 +196,7 @@ static void raid6_datap_recov_avx2(int disks, size_t bytes, int faila, /* Compute syndrome with zero for the missing data page Use the dead data page as temporary storage for delta q */ dq = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks-1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); diff --git a/lib/raid6/recov_avx512.c b/lib/raid6/recov_avx512.c index 310c715db313..7986120ca444 100644 --- a/lib/raid6/recov_avx512.c +++ b/lib/raid6/recov_avx512.c @@ -37,10 +37,10 @@ static void raid6_2data_recov_avx512(int disks, size_t bytes, int faila, */ dp = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks-2] = dp; dq = (u8 *)ptrs[failb]; - ptrs[failb] = (void *)raid6_empty_zero_page; + ptrs[failb] = raid6_get_zero_page(); ptrs[disks-1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); @@ -238,7 +238,7 @@ static void raid6_datap_recov_avx512(int disks, size_t bytes, int faila, */ dq = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks-1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); diff --git a/lib/raid6/recov_loongarch_simd.c b/lib/raid6/recov_loongarch_simd.c index 94aeac85e6f7..93dc515997a1 100644 --- a/lib/raid6/recov_loongarch_simd.c +++ b/lib/raid6/recov_loongarch_simd.c @@ -42,10 +42,10 @@ static void raid6_2data_recov_lsx(int disks, size_t bytes, int faila, * delta p and delta q */ dp = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks - 2] = dp; dq = (u8 *)ptrs[failb]; - ptrs[failb] = (void *)raid6_empty_zero_page; + ptrs[failb] = raid6_get_zero_page(); ptrs[disks - 1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); @@ -197,7 +197,7 @@ static void raid6_datap_recov_lsx(int disks, size_t bytes, int faila, * Use the dead data page as temporary storage for delta q */ dq = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks - 1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); @@ -316,10 +316,10 @@ static void raid6_2data_recov_lasx(int disks, size_t bytes, int faila, * delta p and delta q */ dp = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks - 2] = dp; dq = (u8 *)ptrs[failb]; - ptrs[failb] = (void *)raid6_empty_zero_page; + ptrs[failb] = raid6_get_zero_page(); ptrs[disks - 1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); @@ -436,7 +436,7 @@ static void raid6_datap_recov_lasx(int disks, size_t bytes, int faila, * Use the dead data page as temporary storage for delta q */ dq = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks - 1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); diff --git a/lib/raid6/recov_neon.c b/lib/raid6/recov_neon.c index 1bfc14174d4d..70e1404c1512 100644 --- a/lib/raid6/recov_neon.c +++ b/lib/raid6/recov_neon.c @@ -36,10 +36,10 @@ static void raid6_2data_recov_neon(int disks, size_t bytes, int faila, * delta p and delta q */ dp = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks - 2] = dp; dq = (u8 *)ptrs[failb]; - ptrs[failb] = (void *)raid6_empty_zero_page; + ptrs[failb] = raid6_get_zero_page(); ptrs[disks - 1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); @@ -74,7 +74,7 @@ static void raid6_datap_recov_neon(int disks, size_t bytes, int faila, * Use the dead data page as temporary storage for delta q */ dq = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks - 1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); diff --git a/lib/raid6/recov_s390xc.c b/lib/raid6/recov_s390xc.c index 179eec900cea..1d32c01261be 100644 --- a/lib/raid6/recov_s390xc.c +++ b/lib/raid6/recov_s390xc.c @@ -35,10 +35,10 @@ static void raid6_2data_recov_s390xc(int disks, size_t bytes, int faila, Use the dead data pages as temporary storage for delta p and delta q */ dp = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks-2] = dp; dq = (u8 *)ptrs[failb]; - ptrs[failb] = (void *)raid6_empty_zero_page; + ptrs[failb] = raid6_get_zero_page(); ptrs[disks-1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); @@ -82,7 +82,7 @@ static void raid6_datap_recov_s390xc(int disks, size_t bytes, int faila, /* Compute syndrome with zero for the missing data page Use the dead data page as temporary storage for delta q */ dq = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks-1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); diff --git a/lib/raid6/recov_ssse3.c b/lib/raid6/recov_ssse3.c index 4bfa3c6b60de..2e849185c32b 100644 --- a/lib/raid6/recov_ssse3.c +++ b/lib/raid6/recov_ssse3.c @@ -30,10 +30,10 @@ static void raid6_2data_recov_ssse3(int disks, size_t bytes, int faila, Use the dead data pages as temporary storage for delta p and delta q */ dp = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks-2] = dp; dq = (u8 *)ptrs[failb]; - ptrs[failb] = (void *)raid6_empty_zero_page; + ptrs[failb] = raid6_get_zero_page(); ptrs[disks-1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); @@ -203,7 +203,7 @@ static void raid6_datap_recov_ssse3(int disks, size_t bytes, int faila, /* Compute syndrome with zero for the missing data page Use the dead data page as temporary storage for delta q */ dq = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; + ptrs[faila] = raid6_get_zero_page(); ptrs[disks-1] = dq; raid6_call.gen_syndrome(disks, bytes, ptrs); -- cgit v1.2.3 From 84f890414a12b8d1480045b92a5e4e6ac4ab3419 Mon Sep 17 00:00:00 2001 From: Michał Winiarski Date: Wed, 2 Jul 2025 11:35:22 +0200 Subject: PCI/IOV: Allow drivers to control VF BAR size MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Drivers could leverage the fact that the VF BAR MMIO reservation is created for total number of VFs supported by the device by resizing the BAR to larger size when smaller number of VFs is enabled. Add pci_iov_vf_bar_set_size() to control the size and a pci_iov_vf_bar_get_sizes() helper to get the VF BAR sizes that will allow up to num_vfs to be successfully enabled with the current underlying reservation size. Signed-off-by: Michał Winiarski Signed-off-by: Bjorn Helgaas Reviewed-by: Ilpo Järvinen Link: https://patch.msgid.link/20250702093522.518099-6-michal.winiarski@intel.com --- drivers/pci/iov.c | 73 +++++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/pci.h | 6 +++++ 2 files changed, 79 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index f34173c70b32..ac4375954c94 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -8,11 +8,15 @@ */ #include +#include +#include #include +#include #include #include #include #include +#include #include "pci.h" #define VIRTFN_ID_LEN 17 /* "virtfn%u\0" for 2^32 - 1 */ @@ -1313,3 +1317,72 @@ int pci_sriov_configure_simple(struct pci_dev *dev, int nr_virtfn) return nr_virtfn; } EXPORT_SYMBOL_GPL(pci_sriov_configure_simple); + +/** + * pci_iov_vf_bar_set_size - set a new size for a VF BAR + * @dev: the PCI device + * @resno: the resource number + * @size: new size as defined in the spec (0=1MB, 31=128TB) + * + * Set the new size of a VF BAR that supports VF resizable BAR capability. + * Unlike pci_resize_resource(), this does not cause the resource that + * reserves the MMIO space (originally up to total_VFs) to be resized, which + * means that following calls to pci_enable_sriov() can fail if the resources + * no longer fit. + * + * Return: 0 on success, or negative on failure. + */ +int pci_iov_vf_bar_set_size(struct pci_dev *dev, int resno, int size) +{ + u32 sizes; + int ret; + + if (!pci_resource_is_iov(resno)) + return -EINVAL; + + if (pci_iov_is_memory_decoding_enabled(dev)) + return -EBUSY; + + sizes = pci_rebar_get_possible_sizes(dev, resno); + if (!sizes) + return -ENOTSUPP; + + if (!(sizes & BIT(size))) + return -EINVAL; + + ret = pci_rebar_set_size(dev, resno, size); + if (ret) + return ret; + + pci_iov_resource_set_size(dev, resno, pci_rebar_size_to_bytes(size)); + + return 0; +} +EXPORT_SYMBOL_GPL(pci_iov_vf_bar_set_size); + +/** + * pci_iov_vf_bar_get_sizes - get VF BAR sizes allowing to create up to num_vfs + * @dev: the PCI device + * @resno: the resource number + * @num_vfs: number of VFs + * + * Get the sizes of a VF resizable BAR that can accommodate @num_vfs within + * the currently assigned size of the resource @resno. + * + * Return: A bitmask of sizes in format defined in the spec (bit 0=1MB, + * bit 31=128TB). + */ +u32 pci_iov_vf_bar_get_sizes(struct pci_dev *dev, int resno, int num_vfs) +{ + u64 vf_len = pci_resource_len(dev, resno); + u32 sizes; + + if (!num_vfs) + return 0; + + do_div(vf_len, num_vfs); + sizes = (roundup_pow_of_two(vf_len + 1) - 1) >> ilog2(SZ_1M); + + return sizes & pci_rebar_get_possible_sizes(dev, resno); +} +EXPORT_SYMBOL_GPL(pci_iov_vf_bar_get_sizes); diff --git a/include/linux/pci.h b/include/linux/pci.h index 05e68f35f392..28f06045ab20 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2438,6 +2438,8 @@ int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs); int pci_sriov_get_totalvfs(struct pci_dev *dev); int pci_sriov_configure_simple(struct pci_dev *dev, int nr_virtfn); resource_size_t pci_iov_resource_size(struct pci_dev *dev, int resno); +int pci_iov_vf_bar_set_size(struct pci_dev *dev, int resno, int size); +u32 pci_iov_vf_bar_get_sizes(struct pci_dev *dev, int resno, int num_vfs); void pci_vf_drivers_autoprobe(struct pci_dev *dev, bool probe); /* Arch may override these (weak) */ @@ -2490,6 +2492,10 @@ static inline int pci_sriov_get_totalvfs(struct pci_dev *dev) #define pci_sriov_configure_simple NULL static inline resource_size_t pci_iov_resource_size(struct pci_dev *dev, int resno) { return 0; } +static inline int pci_iov_vf_bar_set_size(struct pci_dev *dev, int resno, int size) +{ return -ENODEV; } +static inline u32 pci_iov_vf_bar_get_sizes(struct pci_dev *dev, int resno, int num_vfs) +{ return 0; } static inline void pci_vf_drivers_autoprobe(struct pci_dev *dev, bool probe) { } #endif -- cgit v1.2.3 From ce60ab3964782df9ba34f0a64c0bc766dd508bde Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 29 May 2025 06:45:45 -0400 Subject: Expand the type of nfs_fattr->valid We need to be able to track more than 32 attributes per inode. Signed-off-by: Trond Myklebust Signed-off-by: Lance Shelton Signed-off-by: Benjamin Coddington Reviewed-by: Jeff Layton Link: https://lore.kernel.org/r/1e3405fca54efd0be7c91c1da77917b94f5dfcc4.1748515333.git.bcodding@redhat.com Signed-off-by: Trond Myklebust --- fs/nfs/inode.c | 2 +- include/linux/nfs_fs_sb.h | 2 +- include/linux/nfs_xdr.h | 54 +++++++++++++++++++++++------------------------ 3 files changed, 29 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index a2fa6bc4d74e..17f5dcda2a00 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -2209,7 +2209,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) bool attr_changed = false; bool have_delegation; - dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n", + dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%llx)\n", __func__, inode->i_sb->s_id, inode->i_ino, nfs_display_fhandle_hash(NFS_FH(inode)), atomic_read(&inode->i_count), fattr->valid); diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 63141320c2a8..d7895eeccea3 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -172,8 +172,8 @@ struct nfs_server { #define NFS_MOUNT_FORCE_RDIRPLUS 0x20000000 #define NFS_MOUNT_NETUNREACH_FATAL 0x40000000 - unsigned int fattr_valid; /* Valid attributes */ unsigned int caps; /* server capabilities */ + __u64 fattr_valid; /* Valid attributes */ unsigned int rsize; /* read size */ unsigned int rpages; /* read size (in pages) */ unsigned int wsize; /* write size */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 67f6632f723b..9cacbbd14787 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -45,7 +45,7 @@ struct nfs4_threshold { }; struct nfs_fattr { - unsigned int valid; /* which fields are valid */ + __u64 valid; /* which fields are valid */ umode_t mode; __u32 nlink; kuid_t uid; @@ -80,32 +80,32 @@ struct nfs_fattr { struct nfs4_label *label; }; -#define NFS_ATTR_FATTR_TYPE (1U << 0) -#define NFS_ATTR_FATTR_MODE (1U << 1) -#define NFS_ATTR_FATTR_NLINK (1U << 2) -#define NFS_ATTR_FATTR_OWNER (1U << 3) -#define NFS_ATTR_FATTR_GROUP (1U << 4) -#define NFS_ATTR_FATTR_RDEV (1U << 5) -#define NFS_ATTR_FATTR_SIZE (1U << 6) -#define NFS_ATTR_FATTR_PRESIZE (1U << 7) -#define NFS_ATTR_FATTR_BLOCKS_USED (1U << 8) -#define NFS_ATTR_FATTR_SPACE_USED (1U << 9) -#define NFS_ATTR_FATTR_FSID (1U << 10) -#define NFS_ATTR_FATTR_FILEID (1U << 11) -#define NFS_ATTR_FATTR_ATIME (1U << 12) -#define NFS_ATTR_FATTR_MTIME (1U << 13) -#define NFS_ATTR_FATTR_CTIME (1U << 14) -#define NFS_ATTR_FATTR_PREMTIME (1U << 15) -#define NFS_ATTR_FATTR_PRECTIME (1U << 16) -#define NFS_ATTR_FATTR_CHANGE (1U << 17) -#define NFS_ATTR_FATTR_PRECHANGE (1U << 18) -#define NFS_ATTR_FATTR_V4_LOCATIONS (1U << 19) -#define NFS_ATTR_FATTR_V4_REFERRAL (1U << 20) -#define NFS_ATTR_FATTR_MOUNTPOINT (1U << 21) -#define NFS_ATTR_FATTR_MOUNTED_ON_FILEID (1U << 22) -#define NFS_ATTR_FATTR_OWNER_NAME (1U << 23) -#define NFS_ATTR_FATTR_GROUP_NAME (1U << 24) -#define NFS_ATTR_FATTR_V4_SECURITY_LABEL (1U << 25) +#define NFS_ATTR_FATTR_TYPE BIT_ULL(0) +#define NFS_ATTR_FATTR_MODE BIT_ULL(1) +#define NFS_ATTR_FATTR_NLINK BIT_ULL(2) +#define NFS_ATTR_FATTR_OWNER BIT_ULL(3) +#define NFS_ATTR_FATTR_GROUP BIT_ULL(4) +#define NFS_ATTR_FATTR_RDEV BIT_ULL(5) +#define NFS_ATTR_FATTR_SIZE BIT_ULL(6) +#define NFS_ATTR_FATTR_PRESIZE BIT_ULL(7) +#define NFS_ATTR_FATTR_BLOCKS_USED BIT_ULL(8) +#define NFS_ATTR_FATTR_SPACE_USED BIT_ULL(9) +#define NFS_ATTR_FATTR_FSID BIT_ULL(10) +#define NFS_ATTR_FATTR_FILEID BIT_ULL(11) +#define NFS_ATTR_FATTR_ATIME BIT_ULL(12) +#define NFS_ATTR_FATTR_MTIME BIT_ULL(13) +#define NFS_ATTR_FATTR_CTIME BIT_ULL(14) +#define NFS_ATTR_FATTR_PREMTIME BIT_ULL(15) +#define NFS_ATTR_FATTR_PRECTIME BIT_ULL(16) +#define NFS_ATTR_FATTR_CHANGE BIT_ULL(17) +#define NFS_ATTR_FATTR_PRECHANGE BIT_ULL(18) +#define NFS_ATTR_FATTR_V4_LOCATIONS BIT_ULL(19) +#define NFS_ATTR_FATTR_V4_REFERRAL BIT_ULL(20) +#define NFS_ATTR_FATTR_MOUNTPOINT BIT_ULL(21) +#define NFS_ATTR_FATTR_MOUNTED_ON_FILEID BIT_ULL(22) +#define NFS_ATTR_FATTR_OWNER_NAME BIT_ULL(23) +#define NFS_ATTR_FATTR_GROUP_NAME BIT_ULL(24) +#define NFS_ATTR_FATTR_V4_SECURITY_LABEL BIT_ULL(25) #define NFS_ATTR_FATTR (NFS_ATTR_FATTR_TYPE \ | NFS_ATTR_FATTR_MODE \ -- cgit v1.2.3 From 1c7ae2dd3f0e6d07ec0a5a348f2561f2171b9c81 Mon Sep 17 00:00:00 2001 From: Anne Marie Merritt Date: Thu, 29 May 2025 06:45:46 -0400 Subject: nfs: Add timecreate to nfs inode Add tracking of the create time (a.k.a. btime) along with corresponding bitfields, request, and decode xdr routines. Signed-off-by: Anne Marie Merritt Signed-off-by: Lance Shelton Signed-off-by: Benjamin Coddington Reviewed-by: Jeff Layton Link: https://lore.kernel.org/r/1e3677b0655fa2bbaba0817b41d111d94a06e5ee.1748515333.git.bcodding@redhat.com Signed-off-by: Trond Myklebust --- fs/nfs/inode.c | 17 +++++++++++++++-- fs/nfs/nfs4proc.c | 14 +++++++++++++- fs/nfs/nfs4xdr.c | 24 ++++++++++++++++++++++++ fs/nfs/nfstrace.h | 3 ++- include/linux/nfs_fs.h | 8 ++++++++ include/linux/nfs_xdr.h | 3 +++ 6 files changed, 65 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 17f5dcda2a00..c5462aed6bf5 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -197,6 +197,7 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) if (!(flags & NFS_INO_REVAL_FORCED)) flags &= ~(NFS_INO_INVALID_MODE | NFS_INO_INVALID_OTHER | + NFS_INO_INVALID_BTIME | NFS_INO_INVALID_XATTR); flags &= ~(NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE); } @@ -522,6 +523,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) inode_set_atime(inode, 0, 0); inode_set_mtime(inode, 0, 0); inode_set_ctime(inode, 0, 0); + memset(&nfsi->btime, 0, sizeof(nfsi->btime)); inode_set_iversion_raw(inode, 0); inode->i_size = 0; clear_nlink(inode); @@ -545,6 +547,10 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) inode_set_ctime_to_ts(inode, fattr->ctime); else if (fattr_supported & NFS_ATTR_FATTR_CTIME) nfs_set_cache_invalid(inode, NFS_INO_INVALID_CTIME); + if (fattr->valid & NFS_ATTR_FATTR_BTIME) + nfsi->btime = fattr->btime; + else if (fattr_supported & NFS_ATTR_FATTR_BTIME) + nfs_set_cache_invalid(inode, NFS_INO_INVALID_BTIME); if (fattr->valid & NFS_ATTR_FATTR_CHANGE) inode_set_iversion_raw(inode, fattr->change_attr); else @@ -1943,7 +1949,7 @@ static int nfs_inode_finish_partial_attr_update(const struct nfs_fattr *fattr, NFS_INO_INVALID_ATIME | NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE | NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_OTHER | - NFS_INO_INVALID_NLINK; + NFS_INO_INVALID_NLINK | NFS_INO_INVALID_BTIME; unsigned long cache_validity = NFS_I(inode)->cache_validity; enum nfs4_change_attr_type ctype = NFS_SERVER(inode)->change_attr_type; @@ -2304,7 +2310,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) | NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_NLINK | NFS_INO_INVALID_MODE - | NFS_INO_INVALID_OTHER; + | NFS_INO_INVALID_OTHER + | NFS_INO_INVALID_BTIME; if (S_ISDIR(inode->i_mode)) nfs_force_lookup_revalidate(inode); attr_changed = true; @@ -2338,6 +2345,12 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_CTIME; + if (fattr->valid & NFS_ATTR_FATTR_BTIME) + nfsi->btime = fattr->btime; + else if (fattr_supported & NFS_ATTR_FATTR_BTIME) + nfsi->cache_validity |= + save_cache_validity & NFS_INO_INVALID_BTIME; + /* Check if our cached file size is stale */ if (fattr->valid & NFS_ATTR_FATTR_SIZE) { new_isize = nfs_size_to_loff_t(fattr->size); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 341740fa293d..92f1b2601b67 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -222,6 +222,7 @@ const u32 nfs4_fattr_bitmap[3] = { | FATTR4_WORD1_RAWDEV | FATTR4_WORD1_SPACE_USED | FATTR4_WORD1_TIME_ACCESS + | FATTR4_WORD1_TIME_CREATE | FATTR4_WORD1_TIME_METADATA | FATTR4_WORD1_TIME_MODIFY | FATTR4_WORD1_MOUNTED_ON_FILEID, @@ -243,6 +244,7 @@ static const u32 nfs4_pnfs_open_bitmap[3] = { | FATTR4_WORD1_RAWDEV | FATTR4_WORD1_SPACE_USED | FATTR4_WORD1_TIME_ACCESS + | FATTR4_WORD1_TIME_CREATE | FATTR4_WORD1_TIME_METADATA | FATTR4_WORD1_TIME_MODIFY, FATTR4_WORD2_MDSTHRESHOLD @@ -323,6 +325,9 @@ static void nfs4_bitmap_copy_adjust(__u32 *dst, const __u32 *src, if (!(cache_validity & NFS_INO_INVALID_OTHER)) dst[1] &= ~(FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP); + if (!(cache_validity & NFS_INO_INVALID_BTIME)) + dst[1] &= ~FATTR4_WORD1_TIME_CREATE; + if (nfs_have_delegated_mtime(inode)) { if (!(cache_validity & NFS_INO_INVALID_ATIME)) dst[1] &= ~(FATTR4_WORD1_TIME_ACCESS|FATTR4_WORD1_TIME_ACCESS_SET); @@ -1307,7 +1312,8 @@ nfs4_update_changeattr_locked(struct inode *inode, NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_INVALID_SIZE | NFS_INO_INVALID_OTHER | NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_NLINK | - NFS_INO_INVALID_MODE | NFS_INO_INVALID_XATTR; + NFS_INO_INVALID_MODE | NFS_INO_INVALID_BTIME | + NFS_INO_INVALID_XATTR; nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); } nfsi->attrtimeo_timestamp = jiffies; @@ -4047,6 +4053,10 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f server->fattr_valid &= ~NFS_ATTR_FATTR_CTIME; if (!(res.attr_bitmask[1] & FATTR4_WORD1_TIME_MODIFY)) server->fattr_valid &= ~NFS_ATTR_FATTR_MTIME; + if (!(res.attr_bitmask[1] & FATTR4_WORD1_TIME_MODIFY)) + server->fattr_valid &= ~NFS_ATTR_FATTR_MTIME; + if (!(res.attr_bitmask[1] & FATTR4_WORD1_TIME_CREATE)) + server->fattr_valid &= ~NFS_ATTR_FATTR_BTIME; memcpy(server->attr_bitmask_nl, res.attr_bitmask, sizeof(server->attr_bitmask)); server->attr_bitmask_nl[2] &= ~FATTR4_WORD2_SECURITY_LABEL; @@ -5781,6 +5791,8 @@ void nfs4_bitmask_set(__u32 bitmask[], const __u32 src[], bitmask[1] |= FATTR4_WORD1_TIME_MODIFY; if (cache_validity & NFS_INO_INVALID_BLOCKS) bitmask[1] |= FATTR4_WORD1_SPACE_USED; + if (cache_validity & NFS_INO_INVALID_BTIME) + bitmask[1] |= FATTR4_WORD1_TIME_CREATE; if (cache_validity & NFS_INO_INVALID_SIZE) bitmask[0] |= FATTR4_WORD0_SIZE; diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 318afde38057..49ff98571fa5 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1623,6 +1623,7 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg | FATTR4_WORD1_RAWDEV | FATTR4_WORD1_SPACE_USED | FATTR4_WORD1_TIME_ACCESS + | FATTR4_WORD1_TIME_CREATE | FATTR4_WORD1_TIME_METADATA | FATTR4_WORD1_TIME_MODIFY; attrs[2] |= FATTR4_WORD2_SECURITY_LABEL; @@ -4207,6 +4208,24 @@ static int decode_attr_time_access(struct xdr_stream *xdr, uint32_t *bitmap, str return status; } +static int decode_attr_time_create(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec64 *time) +{ + int status = 0; + + time->tv_sec = 0; + time->tv_nsec = 0; + if (unlikely(bitmap[1] & (FATTR4_WORD1_TIME_CREATE - 1U))) + return -EIO; + if (likely(bitmap[1] & FATTR4_WORD1_TIME_CREATE)) { + status = decode_attr_time(xdr, time); + if (status == 0) + status = NFS_ATTR_FATTR_BTIME; + bitmap[1] &= ~FATTR4_WORD1_TIME_CREATE; + } + dprintk("%s: btime=%lld\n", __func__, time->tv_sec); + return status; +} + static int decode_attr_time_metadata(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec64 *time) { int status = 0; @@ -4781,6 +4800,11 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, goto xdr_error; fattr->valid |= status; + status = decode_attr_time_create(xdr, bitmap, &fattr->btime); + if (status < 0) + goto xdr_error; + fattr->valid |= status; + status = decode_attr_time_metadata(xdr, bitmap, &fattr->ctime); if (status < 0) goto xdr_error; diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 7a058bd8c566..f49f064c5ee5 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -32,7 +32,8 @@ { NFS_INO_INVALID_BLOCKS, "INVALID_BLOCKS" }, \ { NFS_INO_INVALID_XATTR, "INVALID_XATTR" }, \ { NFS_INO_INVALID_NLINK, "INVALID_NLINK" }, \ - { NFS_INO_INVALID_MODE, "INVALID_MODE" }) + { NFS_INO_INVALID_MODE, "INVALID_MODE" }, \ + { NFS_INO_INVALID_BTIME, "INVALID_BTIME" }) #define nfs_show_nfsi_flags(v) \ __print_flags(v, "|", \ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 67ae2c3f41d2..c585939b6cd6 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -160,6 +160,12 @@ struct nfs_inode { unsigned long flags; /* atomic bit ops */ unsigned long cache_validity; /* bit mask */ + /* + * NFS Attributes not included in struct inode + */ + + struct timespec64 btime; + /* * read_cache_jiffies is when we started read-caching this inode. * attrtimeo is for how long the cached information is assumed @@ -316,10 +322,12 @@ struct nfs4_copy_state { #define NFS_INO_INVALID_XATTR BIT(15) /* xattrs are invalid */ #define NFS_INO_INVALID_NLINK BIT(16) /* cached nlinks is invalid */ #define NFS_INO_INVALID_MODE BIT(17) /* cached mode is invalid */ +#define NFS_INO_INVALID_BTIME BIT(18) /* cached btime is invalid */ #define NFS_INO_INVALID_ATTR (NFS_INO_INVALID_CHANGE \ | NFS_INO_INVALID_CTIME \ | NFS_INO_INVALID_MTIME \ + | NFS_INO_INVALID_BTIME \ | NFS_INO_INVALID_SIZE \ | NFS_INO_INVALID_NLINK \ | NFS_INO_INVALID_MODE \ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 9cacbbd14787..ac4bff6e9913 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -67,6 +67,7 @@ struct nfs_fattr { struct timespec64 atime; struct timespec64 mtime; struct timespec64 ctime; + struct timespec64 btime; __u64 change_attr; /* NFSv4 change attribute */ __u64 pre_change_attr;/* pre-op NFSv4 change attribute */ __u64 pre_size; /* pre_op_attr.size */ @@ -106,6 +107,7 @@ struct nfs_fattr { #define NFS_ATTR_FATTR_OWNER_NAME BIT_ULL(23) #define NFS_ATTR_FATTR_GROUP_NAME BIT_ULL(24) #define NFS_ATTR_FATTR_V4_SECURITY_LABEL BIT_ULL(25) +#define NFS_ATTR_FATTR_BTIME BIT_ULL(26) #define NFS_ATTR_FATTR (NFS_ATTR_FATTR_TYPE \ | NFS_ATTR_FATTR_MODE \ @@ -126,6 +128,7 @@ struct nfs_fattr { | NFS_ATTR_FATTR_SPACE_USED) #define NFS_ATTR_FATTR_V4 (NFS_ATTR_FATTR \ | NFS_ATTR_FATTR_SPACE_USED \ + | NFS_ATTR_FATTR_BTIME \ | NFS_ATTR_FATTR_V4_SECURITY_LABEL) /* -- cgit v1.2.3 From 0715a72ee9a38461eac4b34388b772914f269119 Mon Sep 17 00:00:00 2001 From: Anthony Iliopoulos Date: Fri, 13 Jun 2025 11:44:37 +0200 Subject: NFS: remove unused wpages field from struct nfs_server The wpages field is not serving any purpose since commit c63c7b051395 ("NFS: Fix a race when doing NFS write coalescing") which was merged in v2.6.22-rc1. Remove it completely. Signed-off-by: Anthony Iliopoulos Link: https://lore.kernel.org/r/20250613094439.82338-2-ailiop@suse.com Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 1 - include/linux/nfs_fs_sb.h | 1 - 2 files changed, 2 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index cf35ad3f818a..23dafc590476 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -814,7 +814,6 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, server->wsize = max_rpc_payload; if (server->wsize > NFS_MAX_FILE_IO_SIZE) server->wsize = NFS_MAX_FILE_IO_SIZE; - server->wpages = (server->wsize + PAGE_SIZE - 1) >> PAGE_SHIFT; server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL); diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index d7895eeccea3..7048f9b867ab 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -177,7 +177,6 @@ struct nfs_server { unsigned int rsize; /* read size */ unsigned int rpages; /* read size (in pages) */ unsigned int wsize; /* write size */ - unsigned int wpages; /* write size (in pages) */ unsigned int wtmult; /* server disk block size */ unsigned int dtsize; /* readdir size */ unsigned short port; /* "port=" setting */ -- cgit v1.2.3 From 74a33326cfe8e62ebe0a65ba01ea8a8bceb532f8 Mon Sep 17 00:00:00 2001 From: Anthony Iliopoulos Date: Fri, 13 Jun 2025 11:44:38 +0200 Subject: NFS: remove unused time_delta field from struct nfs_server The last code that was using this was removed via commit ca0daa277aca ("NFS: Cache aggressively when file is open for writing") which was merged in v4.8-rc1, so it can be removed completely. Signed-off-by: Anthony Iliopoulos Link: https://lore.kernel.org/r/20250613094439.82338-3-ailiop@suse.com Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 1 - include/linux/nfs_fs_sb.h | 1 - 2 files changed, 2 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 23dafc590476..47258dc3af70 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -830,7 +830,6 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, server->maxfilesize = fsinfo->maxfilesize; - server->time_delta = fsinfo->time_delta; server->change_attr_type = fsinfo->change_attr_type; server->clone_blksize = fsinfo->clone_blksize; diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 7048f9b867ab..e1b2cf57e765 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -202,7 +202,6 @@ struct nfs_server { struct nfs_fsid fsid; int s_sysfs_id; /* sysfs dentry index */ __u64 maxfilesize; /* maximum file size */ - struct timespec64 time_delta; /* smallest time granularity */ unsigned long mount_time; /* when this fs was mounted */ struct super_block *super; /* VFS super block */ dev_t s_dev; /* superblock dev numbers */ -- cgit v1.2.3 From 2c665d91c2a2d8b5bdf1374d1253b3c89fca4ede Mon Sep 17 00:00:00 2001 From: Anthony Iliopoulos Date: Fri, 13 Jun 2025 11:44:39 +0200 Subject: NFS: remove unused pnfs_ld_data field from struct nfs_server The last code that was using this was removed via commit 20d655d6197d ("pnfs/blocklayout: use the device id cache") which was merged in v3.18-rc1, so it can be removed completely. Signed-off-by: Anthony Iliopoulos Link: https://lore.kernel.org/r/20250613094439.82338-4-ailiop@suse.com Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index e1b2cf57e765..d2d36711a119 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -246,7 +246,6 @@ struct nfs_server { filesystem */ struct pnfs_layoutdriver_type *pnfs_curr_ld; /* Active layout driver */ struct rpc_wait_queue roc_rpcwaitq; - void *pnfs_ld_data; /* per mount point data */ /* the following fields are protected by nfs_client->cl_lock */ struct rb_root state_owners; -- cgit v1.2.3 From 48693d119b2114f8eaf8b8f972b29e05ae581ad4 Mon Sep 17 00:00:00 2001 From: "Dr. David Alan Gilbert" Date: Sun, 13 Jul 2025 00:30:06 +0100 Subject: SUNRPC: Remove unused xdr functions Remove a bunch of unused xdr_*decode* functions: The last use of xdr_decode_netobj() was removed in 2021 by: commit 7cf96b6d0104 ("lockd: Update the NLMv4 SHARE arguments decoder to use struct xdr_stream") The last use of xdr_decode_string_inplace() was removed in 2021 by: commit 3049e974a7c7 ("lockd: Update the NLMv4 FREE_ALL arguments decoder to use struct xdr_stream") The last use of xdr_stream_decode_opaque() was removed in 2024 by: commit fed8a17c61ff ("xdrgen: typedefs should use the built-in string and opaque functions") The functions xdr_stream_decode_string() and xdr_stream_decode_opaque_dup() were both added in 2018 by the commit 0e779aa70308 ("SUNRPC: Add helpers for decoding opaque and string types") but never used. Remove them. Signed-off-by: Dr. David Alan Gilbert Link: https://lore.kernel.org/r/20250712233006.403226-1-linux@treblig.org Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 9 ---- net/sunrpc/xdr.c | 110 --------------------------------------------- 2 files changed, 119 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index a2ab813a9800..e370886632b0 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -128,10 +128,7 @@ xdr_buf_init(struct xdr_buf *buf, void *start, size_t len) __be32 *xdr_encode_opaque_fixed(__be32 *p, const void *ptr, unsigned int len); __be32 *xdr_encode_opaque(__be32 *p, const void *ptr, unsigned int len); __be32 *xdr_encode_string(__be32 *p, const char *s); -__be32 *xdr_decode_string_inplace(__be32 *p, char **sp, unsigned int *lenp, - unsigned int maxlen); __be32 *xdr_encode_netobj(__be32 *p, const struct xdr_netobj *); -__be32 *xdr_decode_netobj(__be32 *p, struct xdr_netobj *); void xdr_inline_pages(struct xdr_buf *, unsigned int, struct page **, unsigned int, unsigned int); @@ -341,12 +338,6 @@ xdr_stream_remaining(const struct xdr_stream *xdr) return xdr->nwords << 2; } -ssize_t xdr_stream_decode_opaque(struct xdr_stream *xdr, void *ptr, - size_t size); -ssize_t xdr_stream_decode_opaque_dup(struct xdr_stream *xdr, void **ptr, - size_t maxlen, gfp_t gfp_flags); -ssize_t xdr_stream_decode_string(struct xdr_stream *xdr, char *str, - size_t size); ssize_t xdr_stream_decode_string_dup(struct xdr_stream *xdr, char **str, size_t maxlen, gfp_t gfp_flags); ssize_t xdr_stream_decode_opaque_auth(struct xdr_stream *xdr, u32 *flavor, diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 2ea00e354ba6..a0aae1144212 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -37,19 +37,6 @@ xdr_encode_netobj(__be32 *p, const struct xdr_netobj *obj) } EXPORT_SYMBOL_GPL(xdr_encode_netobj); -__be32 * -xdr_decode_netobj(__be32 *p, struct xdr_netobj *obj) -{ - unsigned int len; - - if ((len = be32_to_cpu(*p++)) > XDR_MAX_NETOBJ) - return NULL; - obj->len = len; - obj->data = (u8 *) p; - return p + XDR_QUADLEN(len); -} -EXPORT_SYMBOL_GPL(xdr_decode_netobj); - /** * xdr_encode_opaque_fixed - Encode fixed length opaque data * @p: pointer to current position in XDR buffer. @@ -102,21 +89,6 @@ xdr_encode_string(__be32 *p, const char *string) } EXPORT_SYMBOL_GPL(xdr_encode_string); -__be32 * -xdr_decode_string_inplace(__be32 *p, char **sp, - unsigned int *lenp, unsigned int maxlen) -{ - u32 len; - - len = be32_to_cpu(*p++); - if (len > maxlen) - return NULL; - *lenp = len; - *sp = (char *) p; - return p + XDR_QUADLEN(len); -} -EXPORT_SYMBOL_GPL(xdr_decode_string_inplace); - /** * xdr_terminate_string - '\0'-terminate a string residing in an xdr_buf * @buf: XDR buffer where string resides @@ -2247,88 +2219,6 @@ out: } EXPORT_SYMBOL_GPL(xdr_process_buf); -/** - * xdr_stream_decode_opaque - Decode variable length opaque - * @xdr: pointer to xdr_stream - * @ptr: location to store opaque data - * @size: size of storage buffer @ptr - * - * Return values: - * On success, returns size of object stored in *@ptr - * %-EBADMSG on XDR buffer overflow - * %-EMSGSIZE on overflow of storage buffer @ptr - */ -ssize_t xdr_stream_decode_opaque(struct xdr_stream *xdr, void *ptr, size_t size) -{ - ssize_t ret; - void *p; - - ret = xdr_stream_decode_opaque_inline(xdr, &p, size); - if (ret <= 0) - return ret; - memcpy(ptr, p, ret); - return ret; -} -EXPORT_SYMBOL_GPL(xdr_stream_decode_opaque); - -/** - * xdr_stream_decode_opaque_dup - Decode and duplicate variable length opaque - * @xdr: pointer to xdr_stream - * @ptr: location to store pointer to opaque data - * @maxlen: maximum acceptable object size - * @gfp_flags: GFP mask to use - * - * Return values: - * On success, returns size of object stored in *@ptr - * %-EBADMSG on XDR buffer overflow - * %-EMSGSIZE if the size of the object would exceed @maxlen - * %-ENOMEM on memory allocation failure - */ -ssize_t xdr_stream_decode_opaque_dup(struct xdr_stream *xdr, void **ptr, - size_t maxlen, gfp_t gfp_flags) -{ - ssize_t ret; - void *p; - - ret = xdr_stream_decode_opaque_inline(xdr, &p, maxlen); - if (ret > 0) { - *ptr = kmemdup(p, ret, gfp_flags); - if (*ptr != NULL) - return ret; - ret = -ENOMEM; - } - *ptr = NULL; - return ret; -} -EXPORT_SYMBOL_GPL(xdr_stream_decode_opaque_dup); - -/** - * xdr_stream_decode_string - Decode variable length string - * @xdr: pointer to xdr_stream - * @str: location to store string - * @size: size of storage buffer @str - * - * Return values: - * On success, returns length of NUL-terminated string stored in *@str - * %-EBADMSG on XDR buffer overflow - * %-EMSGSIZE on overflow of storage buffer @str - */ -ssize_t xdr_stream_decode_string(struct xdr_stream *xdr, char *str, size_t size) -{ - ssize_t ret; - void *p; - - ret = xdr_stream_decode_opaque_inline(xdr, &p, size); - if (ret > 0) { - memcpy(str, p, ret); - str[ret] = '\0'; - return strlen(str); - } - *str = '\0'; - return ret; -} -EXPORT_SYMBOL_GPL(xdr_stream_decode_string); - /** * xdr_stream_decode_string_dup - Decode and duplicate variable length string * @xdr: pointer to xdr_stream -- cgit v1.2.3 From 857d18f23ab17284d1b6de6f61f4e74958596376 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 11 Jul 2025 16:49:25 -0700 Subject: cleanup: Introduce ACQUIRE() and ACQUIRE_ERR() for conditional locks scoped_cond_guard(), automatic cleanup for conditional locks, has a couple pain points: * It causes existing straight-line code to be re-indented into a new bracketed scope. While this can be mitigated by a new helper function to contain the scope, that is not always a comfortable conversion. * The return code from the conditional lock is tossed in favor of a scheme to pass a 'return err;' statement to the macro. Other attempts to clean this up, to behave more like guard() [1], got hung up trying to both establish and evaluate the conditional lock in one statement. ACQUIRE() solves this by reflecting the result of the condition in the automatic variable established by the lock CLASS(). The result is separately retrieved with the ACQUIRE_ERR() helper, effectively a PTR_ERR() operation. Link: http://lore.kernel.org/all/Z1LBnX9TpZLR5Dkf@gmail.com [1] Link: http://patch.msgid.link/20250512105026.GP4439@noisy.programming.kicks-ass.net Link: http://patch.msgid.link/20250512185817.GA1808@noisy.programming.kicks-ass.net Cc: Ingo Molnar Cc: Linus Torvalds Cc: David Lechner Cc: Fabio M. De Francesco Signed-off-by: Peter Zijlstra (Intel) [djbw: wrap Peter's proposal with changelog and comments] Co-developed-by: Dan Williams Signed-off-by: Dan Williams Reviewed-by: Jonathan Cameron Link: https://patch.msgid.link/20250711234932.671292-2-dan.j.williams@intel.com Signed-off-by: Dave Jiang --- include/linux/cleanup.h | 95 +++++++++++++++++++++++++++++++++++++++++-------- include/linux/mutex.h | 2 +- include/linux/rwsem.h | 2 +- 3 files changed, 83 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index 7093e1d08af0..4eb83dd71cfe 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -3,6 +3,8 @@ #define _LINUX_CLEANUP_H #include +#include +#include /** * DOC: scope-based cleanup helpers @@ -61,9 +63,21 @@ * Observe the lock is held for the remainder of the "if ()" block not * the remainder of "func()". * - * Now, when a function uses both __free() and guard(), or multiple - * instances of __free(), the LIFO order of variable definition order - * matters. GCC documentation says: + * The ACQUIRE() macro can be used in all places that guard() can be + * used and additionally support conditional locks + * + * + * DEFINE_GUARD_COND(pci_dev, _try, pci_dev_trylock(_T)) + * ... + * ACQUIRE(pci_dev_try, lock)(dev); + * rc = ACQUIRE_ERR(pci_dev_try, &lock); + * if (rc) + * return rc; + * // @lock is held + * + * Now, when a function uses both __free() and guard()/ACQUIRE(), or + * multiple instances of __free(), the LIFO order of variable definition + * order matters. GCC documentation says: * * "When multiple variables in the same scope have cleanup attributes, * at exit from the scope their associated cleanup functions are run in @@ -305,14 +319,46 @@ static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \ * acquire fails. * * Only for conditional locks. + * + * ACQUIRE(name, var): + * a named instance of the (guard) class, suitable for conditional + * locks when paired with ACQUIRE_ERR(). + * + * ACQUIRE_ERR(name, &var): + * a helper that is effectively a PTR_ERR() conversion of the guard + * pointer. Returns 0 when the lock was acquired and a negative + * error code otherwise. */ #define __DEFINE_CLASS_IS_CONDITIONAL(_name, _is_cond) \ static __maybe_unused const bool class_##_name##_is_conditional = _is_cond -#define __DEFINE_GUARD_LOCK_PTR(_name, _exp) \ - static inline void * class_##_name##_lock_ptr(class_##_name##_t *_T) \ - { return (void *)(__force unsigned long)*(_exp); } +#define __GUARD_IS_ERR(_ptr) \ + ({ \ + unsigned long _rc = (__force unsigned long)(_ptr); \ + unlikely((_rc - 1) >= -MAX_ERRNO - 1); \ + }) + +#define __DEFINE_GUARD_LOCK_PTR(_name, _exp) \ + static inline void *class_##_name##_lock_ptr(class_##_name##_t *_T) \ + { \ + void *_ptr = (void *)(__force unsigned long)*(_exp); \ + if (IS_ERR(_ptr)) { \ + _ptr = NULL; \ + } \ + return _ptr; \ + } \ + static inline int class_##_name##_lock_err(class_##_name##_t *_T) \ + { \ + long _rc = (__force unsigned long)*(_exp); \ + if (!_rc) { \ + _rc = -EBUSY; \ + } \ + if (!IS_ERR_VALUE(_rc)) { \ + _rc = 0; \ + } \ + return _rc; \ + } #define DEFINE_CLASS_IS_GUARD(_name) \ __DEFINE_CLASS_IS_CONDITIONAL(_name, false); \ @@ -323,23 +369,37 @@ static __maybe_unused const bool class_##_name##_is_conditional = _is_cond __DEFINE_GUARD_LOCK_PTR(_name, _T) #define DEFINE_GUARD(_name, _type, _lock, _unlock) \ - DEFINE_CLASS(_name, _type, if (_T) { _unlock; }, ({ _lock; _T; }), _type _T); \ + DEFINE_CLASS(_name, _type, if (!__GUARD_IS_ERR(_T)) { _unlock; }, ({ _lock; _T; }), _type _T); \ DEFINE_CLASS_IS_GUARD(_name) -#define DEFINE_GUARD_COND(_name, _ext, _condlock) \ +#define DEFINE_GUARD_COND_4(_name, _ext, _lock, _cond) \ __DEFINE_CLASS_IS_CONDITIONAL(_name##_ext, true); \ EXTEND_CLASS(_name, _ext, \ - ({ void *_t = _T; if (_T && !(_condlock)) _t = NULL; _t; }), \ + ({ void *_t = _T; int _RET = (_lock); if (_T && !(_cond)) _t = ERR_PTR(_RET); _t; }), \ class_##_name##_t _T) \ static inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \ - { return class_##_name##_lock_ptr(_T); } + { return class_##_name##_lock_ptr(_T); } \ + static inline int class_##_name##_ext##_lock_err(class_##_name##_t *_T) \ + { return class_##_name##_lock_err(_T); } + +/* + * Default binary condition; success on 'true'. + */ +#define DEFINE_GUARD_COND_3(_name, _ext, _lock) \ + DEFINE_GUARD_COND_4(_name, _ext, _lock, _RET) + +#define DEFINE_GUARD_COND(X...) CONCATENATE(DEFINE_GUARD_COND_, COUNT_ARGS(X))(X) #define guard(_name) \ CLASS(_name, __UNIQUE_ID(guard)) #define __guard_ptr(_name) class_##_name##_lock_ptr +#define __guard_err(_name) class_##_name##_lock_err #define __is_cond_ptr(_name) class_##_name##_is_conditional +#define ACQUIRE(_name, _var) CLASS(_name, _var) +#define ACQUIRE_ERR(_name, _var) __guard_err(_name)(_var) + /* * Helper macro for scoped_guard(). * @@ -401,7 +461,7 @@ typedef struct { \ \ static inline void class_##_name##_destructor(class_##_name##_t *_T) \ { \ - if (_T->lock) { _unlock; } \ + if (!__GUARD_IS_ERR(_T->lock)) { _unlock; } \ } \ \ __DEFINE_GUARD_LOCK_PTR(_name, &_T->lock) @@ -433,15 +493,22 @@ __DEFINE_CLASS_IS_CONDITIONAL(_name, false); \ __DEFINE_UNLOCK_GUARD(_name, void, _unlock, __VA_ARGS__) \ __DEFINE_LOCK_GUARD_0(_name, _lock) -#define DEFINE_LOCK_GUARD_1_COND(_name, _ext, _condlock) \ +#define DEFINE_LOCK_GUARD_1_COND_4(_name, _ext, _lock, _cond) \ __DEFINE_CLASS_IS_CONDITIONAL(_name##_ext, true); \ EXTEND_CLASS(_name, _ext, \ ({ class_##_name##_t _t = { .lock = l }, *_T = &_t;\ - if (_T->lock && !(_condlock)) _T->lock = NULL; \ + int _RET = (_lock); \ + if (_T->lock && !(_cond)) _T->lock = ERR_PTR(_RET);\ _t; }), \ typeof_member(class_##_name##_t, lock) l) \ static inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \ - { return class_##_name##_lock_ptr(_T); } + { return class_##_name##_lock_ptr(_T); } \ + static inline int class_##_name##_ext##_lock_err(class_##_name##_t *_T) \ + { return class_##_name##_lock_err(_T); } + +#define DEFINE_LOCK_GUARD_1_COND_3(_name, _ext, _lock) \ + DEFINE_LOCK_GUARD_1_COND_4(_name, _ext, _lock, _RET) +#define DEFINE_LOCK_GUARD_1_COND(X...) CONCATENATE(DEFINE_LOCK_GUARD_1_COND_, COUNT_ARGS(X))(X) #endif /* _LINUX_CLEANUP_H */ diff --git a/include/linux/mutex.h b/include/linux/mutex.h index a039fa8c1780..9d5d7ed5c101 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -224,7 +224,7 @@ extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); DEFINE_GUARD(mutex, struct mutex *, mutex_lock(_T), mutex_unlock(_T)) DEFINE_GUARD_COND(mutex, _try, mutex_trylock(_T)) -DEFINE_GUARD_COND(mutex, _intr, mutex_lock_interruptible(_T) == 0) +DEFINE_GUARD_COND(mutex, _intr, mutex_lock_interruptible(_T), _RET == 0) extern unsigned long mutex_get_owner(struct mutex *lock); diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index c8b543d428b0..c810deb88d13 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -240,7 +240,7 @@ extern void up_write(struct rw_semaphore *sem); DEFINE_GUARD(rwsem_read, struct rw_semaphore *, down_read(_T), up_read(_T)) DEFINE_GUARD_COND(rwsem_read, _try, down_read_trylock(_T)) -DEFINE_GUARD_COND(rwsem_read, _intr, down_read_interruptible(_T) == 0) +DEFINE_GUARD_COND(rwsem_read, _intr, down_read_interruptible(_T), _RET == 0) DEFINE_GUARD(rwsem_write, struct rw_semaphore *, down_write(_T), up_write(_T)) DEFINE_GUARD_COND(rwsem_write, _try, down_write_trylock(_T)) -- cgit v1.2.3 From d03fcf50ba56f4479685b951506422eeca230853 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 11 Jul 2025 16:49:32 -0700 Subject: cxl: Convert to ACQUIRE() for conditional rwsem locking Use ACQUIRE() to cleanup conditional locking paths in the CXL driver The ACQUIRE() macro and its associated ACQUIRE_ERR() helpers, like scoped_cond_guard(), arrange for scoped-based conditional locking. Unlike scoped_cond_guard(), these macros arrange for an ERR_PTR() to be retrieved representing the state of the conditional lock. The goal of this conversion is to complete the removal of all explicit unlock calls in the subsystem. I.e. the methods to acquire a lock are solely via guard(), scoped_guard() (for limited cases), or ACQUIRE(). All unlock is implicit / scope-based. In order to make sure all lock sites are converted, the existing rwsem's are consolidated and renamed in 'struct cxl_rwsem'. While that makes the patch noisier it gives a clean cut-off between old-world (explicit unlock allowed), and new world (explicit unlock deleted). Cc: David Lechner Cc: Peter Zijlstra Cc: Linus Torvalds Cc: Ingo Molnar Cc: Fabio M. De Francesco Cc: Davidlohr Bueso Cc: Jonathan Cameron Cc: Dave Jiang Cc: Alison Schofield Cc: Vishal Verma Cc: Ira Weiny Cc: Shiju Jose Acked-by: Peter Zijlstra (Intel) Signed-off-by: Dan Williams Reviewed-by: Jonathan Cameron Reviewed-by: Fabio M. De Francesco Reviewed-by: Dave Jiang Tested-by: Shiju Jose Link: https://patch.msgid.link/20250711234932.671292-9-dan.j.williams@intel.com Signed-off-by: Dave Jiang --- drivers/cxl/core/cdat.c | 6 +- drivers/cxl/core/core.h | 17 ++- drivers/cxl/core/edac.c | 44 ++++--- drivers/cxl/core/hdm.c | 41 +++---- drivers/cxl/core/mbox.c | 6 +- drivers/cxl/core/memdev.c | 50 +++----- drivers/cxl/core/port.c | 18 +-- drivers/cxl/core/region.c | 295 +++++++++++++++++++--------------------------- drivers/cxl/cxl.h | 13 +- include/linux/rwsem.h | 1 + 10 files changed, 212 insertions(+), 279 deletions(-) (limited to 'include/linux') diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c index 0ccef2f2a26a..c0af645425f4 100644 --- a/drivers/cxl/core/cdat.c +++ b/drivers/cxl/core/cdat.c @@ -336,7 +336,7 @@ static int match_cxlrd_hb(struct device *dev, void *data) cxlrd = to_cxl_root_decoder(dev); cxlsd = &cxlrd->cxlsd; - guard(rwsem_read)(&cxl_region_rwsem); + guard(rwsem_read)(&cxl_rwsem.region); for (int i = 0; i < cxlsd->nr_targets; i++) { if (host_bridge == cxlsd->target[i]->dport_dev) return 1; @@ -987,7 +987,7 @@ void cxl_region_shared_upstream_bandwidth_update(struct cxl_region *cxlr) bool is_root; int rc; - lockdep_assert_held(&cxl_dpa_rwsem); + lockdep_assert_held(&cxl_rwsem.dpa); struct xarray *usp_xa __free(free_perf_xa) = kzalloc(sizeof(*usp_xa), GFP_KERNEL); @@ -1057,7 +1057,7 @@ void cxl_region_perf_data_calculate(struct cxl_region *cxlr, { struct cxl_dpa_perf *perf; - lockdep_assert_held(&cxl_dpa_rwsem); + lockdep_assert_held(&cxl_rwsem.dpa); perf = cxled_get_dpa_perf(cxled); if (IS_ERR(perf)) diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h index 2be37084409f..f796731deedf 100644 --- a/drivers/cxl/core/core.h +++ b/drivers/cxl/core/core.h @@ -5,6 +5,7 @@ #define __CXL_CORE_H__ #include +#include extern const struct device_type cxl_nvdimm_bridge_type; extern const struct device_type cxl_nvdimm_type; @@ -107,8 +108,20 @@ u16 cxl_rcrb_to_aer(struct device *dev, resource_size_t rcrb); #define PCI_RCRB_CAP_HDR_NEXT_MASK GENMASK(15, 8) #define PCI_CAP_EXP_SIZEOF 0x3c -extern struct rw_semaphore cxl_dpa_rwsem; -extern struct rw_semaphore cxl_region_rwsem; +struct cxl_rwsem { + /* + * All changes to HPA (interleave configuration) occur with this + * lock held for write. + */ + struct rw_semaphore region; + /* + * All changes to a device DPA space occur with this lock held + * for write. + */ + struct rw_semaphore dpa; +}; + +extern struct cxl_rwsem cxl_rwsem; int cxl_memdev_init(void); void cxl_memdev_exit(void); diff --git a/drivers/cxl/core/edac.c b/drivers/cxl/core/edac.c index 623aaa4439c4..9ed1b670efb8 100644 --- a/drivers/cxl/core/edac.c +++ b/drivers/cxl/core/edac.c @@ -115,10 +115,9 @@ static int cxl_scrub_get_attrbs(struct cxl_patrol_scrub_context *cxl_ps_ctx, flags, min_cycle); } - struct rw_semaphore *region_lock __free(rwsem_read_release) = - rwsem_read_intr_acquire(&cxl_region_rwsem); - if (!region_lock) - return -EINTR; + ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region); + if ((ret = ACQUIRE_ERR(rwsem_read_intr, &rwsem))) + return ret; cxlr = cxl_ps_ctx->cxlr; p = &cxlr->params; @@ -158,10 +157,9 @@ static int cxl_scrub_set_attrbs_region(struct device *dev, struct cxl_region *cxlr; int ret, i; - struct rw_semaphore *region_lock __free(rwsem_read_release) = - rwsem_read_intr_acquire(&cxl_region_rwsem); - if (!region_lock) - return -EINTR; + ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region); + if ((ret = ACQUIRE_ERR(rwsem_read_intr, &rwsem))) + return ret; cxlr = cxl_ps_ctx->cxlr; p = &cxlr->params; @@ -1340,16 +1338,15 @@ cxl_mem_perform_sparing(struct device *dev, struct cxl_memdev_sparing_in_payload sparing_pi; struct cxl_event_dram *rec = NULL; u16 validity_flags = 0; + int ret; - struct rw_semaphore *region_lock __free(rwsem_read_release) = - rwsem_read_intr_acquire(&cxl_region_rwsem); - if (!region_lock) - return -EINTR; + ACQUIRE(rwsem_read_intr, region_rwsem)(&cxl_rwsem.region); + if ((ret = ACQUIRE_ERR(rwsem_read_intr, ®ion_rwsem))) + return ret; - struct rw_semaphore *dpa_lock __free(rwsem_read_release) = - rwsem_read_intr_acquire(&cxl_dpa_rwsem); - if (!dpa_lock) - return -EINTR; + ACQUIRE(rwsem_read_intr, dpa_rwsem)(&cxl_rwsem.dpa); + if ((ret = ACQUIRE_ERR(rwsem_read_intr, &dpa_rwsem))) + return ret; if (!cxl_sparing_ctx->cap_safe_when_in_use) { /* Memory to repair must be offline */ @@ -1787,16 +1784,15 @@ static int cxl_mem_perform_ppr(struct cxl_ppr_context *cxl_ppr_ctx) struct cxl_memdev_ppr_maintenance_attrbs maintenance_attrbs; struct cxl_memdev *cxlmd = cxl_ppr_ctx->cxlmd; struct cxl_mem_repair_attrbs attrbs = { 0 }; + int ret; - struct rw_semaphore *region_lock __free(rwsem_read_release) = - rwsem_read_intr_acquire(&cxl_region_rwsem); - if (!region_lock) - return -EINTR; + ACQUIRE(rwsem_read_intr, region_rwsem)(&cxl_rwsem.region); + if ((ret = ACQUIRE_ERR(rwsem_read_intr, ®ion_rwsem))) + return ret; - struct rw_semaphore *dpa_lock __free(rwsem_read_release) = - rwsem_read_intr_acquire(&cxl_dpa_rwsem); - if (!dpa_lock) - return -EINTR; + ACQUIRE(rwsem_read_intr, dpa_rwsem)(&cxl_rwsem.dpa); + if ((ret = ACQUIRE_ERR(rwsem_read_intr, &dpa_rwsem))) + return ret; if (!cxl_ppr_ctx->media_accessible || !cxl_ppr_ctx->data_retained) { /* Memory to repair must be offline */ diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index e9cb34e30248..865a71bce251 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -16,7 +16,10 @@ * for enumerating these registers and capabilities. */ -DECLARE_RWSEM(cxl_dpa_rwsem); +struct cxl_rwsem cxl_rwsem = { + .region = __RWSEM_INITIALIZER(cxl_rwsem.region), + .dpa = __RWSEM_INITIALIZER(cxl_rwsem.dpa), +}; static int add_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, int *target_map) @@ -214,7 +217,7 @@ void cxl_dpa_debug(struct seq_file *file, struct cxl_dev_state *cxlds) { struct resource *p1, *p2; - guard(rwsem_read)(&cxl_dpa_rwsem); + guard(rwsem_read)(&cxl_rwsem.dpa); for (p1 = cxlds->dpa_res.child; p1; p1 = p1->sibling) { __cxl_dpa_debug(file, p1, 0); for (p2 = p1->child; p2; p2 = p2->sibling) @@ -266,7 +269,7 @@ static void __cxl_dpa_release(struct cxl_endpoint_decoder *cxled) struct resource *res = cxled->dpa_res; resource_size_t skip_start; - lockdep_assert_held_write(&cxl_dpa_rwsem); + lockdep_assert_held_write(&cxl_rwsem.dpa); /* save @skip_start, before @res is released */ skip_start = res->start - cxled->skip; @@ -281,7 +284,7 @@ static void __cxl_dpa_release(struct cxl_endpoint_decoder *cxled) static void cxl_dpa_release(void *cxled) { - guard(rwsem_write)(&cxl_dpa_rwsem); + guard(rwsem_write)(&cxl_rwsem.dpa); __cxl_dpa_release(cxled); } @@ -293,7 +296,7 @@ static void devm_cxl_dpa_release(struct cxl_endpoint_decoder *cxled) { struct cxl_port *port = cxled_to_port(cxled); - lockdep_assert_held_write(&cxl_dpa_rwsem); + lockdep_assert_held_write(&cxl_rwsem.dpa); devm_remove_action(&port->dev, cxl_dpa_release, cxled); __cxl_dpa_release(cxled); } @@ -361,7 +364,7 @@ static int __cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled, struct resource *res; int rc; - lockdep_assert_held_write(&cxl_dpa_rwsem); + lockdep_assert_held_write(&cxl_rwsem.dpa); if (!len) { dev_warn(dev, "decoder%d.%d: empty reservation attempted\n", @@ -470,7 +473,7 @@ int cxl_dpa_setup(struct cxl_dev_state *cxlds, const struct cxl_dpa_info *info) { struct device *dev = cxlds->dev; - guard(rwsem_write)(&cxl_dpa_rwsem); + guard(rwsem_write)(&cxl_rwsem.dpa); if (cxlds->nr_partitions) return -EBUSY; @@ -516,9 +519,8 @@ int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled, struct cxl_port *port = cxled_to_port(cxled); int rc; - down_write(&cxl_dpa_rwsem); - rc = __cxl_dpa_reserve(cxled, base, len, skipped); - up_write(&cxl_dpa_rwsem); + scoped_guard(rwsem_write, &cxl_rwsem.dpa) + rc = __cxl_dpa_reserve(cxled, base, len, skipped); if (rc) return rc; @@ -529,7 +531,7 @@ EXPORT_SYMBOL_NS_GPL(devm_cxl_dpa_reserve, "CXL"); resource_size_t cxl_dpa_size(struct cxl_endpoint_decoder *cxled) { - guard(rwsem_read)(&cxl_dpa_rwsem); + guard(rwsem_read)(&cxl_rwsem.dpa); if (cxled->dpa_res) return resource_size(cxled->dpa_res); @@ -540,7 +542,7 @@ resource_size_t cxl_dpa_resource_start(struct cxl_endpoint_decoder *cxled) { resource_size_t base = -1; - lockdep_assert_held(&cxl_dpa_rwsem); + lockdep_assert_held(&cxl_rwsem.dpa); if (cxled->dpa_res) base = cxled->dpa_res->start; @@ -552,7 +554,7 @@ int cxl_dpa_free(struct cxl_endpoint_decoder *cxled) struct cxl_port *port = cxled_to_port(cxled); struct device *dev = &cxled->cxld.dev; - guard(rwsem_write)(&cxl_dpa_rwsem); + guard(rwsem_write)(&cxl_rwsem.dpa); if (!cxled->dpa_res) return 0; if (cxled->cxld.region) { @@ -582,7 +584,7 @@ int cxl_dpa_set_part(struct cxl_endpoint_decoder *cxled, struct device *dev = &cxled->cxld.dev; int part; - guard(rwsem_write)(&cxl_dpa_rwsem); + guard(rwsem_write)(&cxl_rwsem.dpa); if (cxled->cxld.flags & CXL_DECODER_F_ENABLE) return -EBUSY; @@ -614,7 +616,7 @@ static int __cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, u64 size) struct resource *p, *last; int part; - guard(rwsem_write)(&cxl_dpa_rwsem); + guard(rwsem_write)(&cxl_rwsem.dpa); if (cxled->cxld.region) { dev_dbg(dev, "decoder attached to %s\n", dev_name(&cxled->cxld.region->dev)); @@ -842,9 +844,8 @@ static int cxl_decoder_commit(struct cxl_decoder *cxld) } } - down_read(&cxl_dpa_rwsem); - setup_hw_decoder(cxld, hdm); - up_read(&cxl_dpa_rwsem); + scoped_guard(rwsem_read, &cxl_rwsem.dpa) + setup_hw_decoder(cxld, hdm); port->commit_end++; rc = cxld_await_commit(hdm, cxld->id); @@ -882,7 +883,7 @@ void cxl_port_commit_reap(struct cxl_decoder *cxld) { struct cxl_port *port = to_cxl_port(cxld->dev.parent); - lockdep_assert_held_write(&cxl_region_rwsem); + lockdep_assert_held_write(&cxl_rwsem.region); /* * Once the highest committed decoder is disabled, free any other @@ -1030,7 +1031,7 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, else cxld->target_type = CXL_DECODER_DEVMEM; - guard(rwsem_write)(&cxl_region_rwsem); + guard(rwsem_write)(&cxl_rwsem.region); if (cxld->id != cxl_num_decoders_committed(port)) { dev_warn(&port->dev, "decoder%d.%d: Committed out of order\n", diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 81b21effe8cf..92cd3cbdd8ec 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -909,8 +909,8 @@ void cxl_event_trace_record(const struct cxl_memdev *cxlmd, * translations. Take topology mutation locks and lookup * { HPA, REGION } from { DPA, MEMDEV } in the event record. */ - guard(rwsem_read)(&cxl_region_rwsem); - guard(rwsem_read)(&cxl_dpa_rwsem); + guard(rwsem_read)(&cxl_rwsem.region); + guard(rwsem_read)(&cxl_rwsem.dpa); dpa = le64_to_cpu(evt->media_hdr.phys_addr) & CXL_DPA_MASK; cxlr = cxl_dpa_to_region(cxlmd, dpa); @@ -1265,7 +1265,7 @@ int cxl_mem_sanitize(struct cxl_memdev *cxlmd, u16 cmd) /* synchronize with cxl_mem_probe() and decoder write operations */ guard(device)(&cxlmd->dev); endpoint = cxlmd->endpoint; - guard(rwsem_read)(&cxl_region_rwsem); + guard(rwsem_read)(&cxl_rwsem.region); /* * Require an endpoint to be safe otherwise the driver can not * be sure that the device is unmapped. diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index f88a13adf7fa..f5fbd34310fd 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -232,15 +232,13 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd) if (!port || !is_cxl_endpoint(port)) return -EINVAL; - rc = down_read_interruptible(&cxl_region_rwsem); - if (rc) + ACQUIRE(rwsem_read_intr, region_rwsem)(&cxl_rwsem.region); + if ((rc = ACQUIRE_ERR(rwsem_read_intr, ®ion_rwsem))) return rc; - rc = down_read_interruptible(&cxl_dpa_rwsem); - if (rc) { - up_read(&cxl_region_rwsem); + ACQUIRE(rwsem_read_intr, dpa_rwsem)(&cxl_rwsem.dpa); + if ((rc = ACQUIRE_ERR(rwsem_read_intr, &dpa_rwsem))) return rc; - } if (cxl_num_decoders_committed(port) == 0) { /* No regions mapped to this memdev */ @@ -249,8 +247,6 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd) /* Regions mapped, collect poison by endpoint */ rc = cxl_get_poison_by_endpoint(port); } - up_read(&cxl_dpa_rwsem); - up_read(&cxl_region_rwsem); return rc; } @@ -292,19 +288,17 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) if (!IS_ENABLED(CONFIG_DEBUG_FS)) return 0; - rc = down_read_interruptible(&cxl_region_rwsem); - if (rc) + ACQUIRE(rwsem_read_intr, region_rwsem)(&cxl_rwsem.region); + if ((rc = ACQUIRE_ERR(rwsem_read_intr, ®ion_rwsem))) return rc; - rc = down_read_interruptible(&cxl_dpa_rwsem); - if (rc) { - up_read(&cxl_region_rwsem); + ACQUIRE(rwsem_read_intr, dpa_rwsem)(&cxl_rwsem.dpa); + if ((rc = ACQUIRE_ERR(rwsem_read_intr, &dpa_rwsem))) return rc; - } rc = cxl_validate_poison_dpa(cxlmd, dpa); if (rc) - goto out; + return rc; inject.address = cpu_to_le64(dpa); mbox_cmd = (struct cxl_mbox_cmd) { @@ -314,7 +308,7 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) }; rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc) - goto out; + return rc; cxlr = cxl_dpa_to_region(cxlmd, dpa); if (cxlr) @@ -327,11 +321,8 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) .length = cpu_to_le32(1), }; trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_INJECT); -out: - up_read(&cxl_dpa_rwsem); - up_read(&cxl_region_rwsem); - return rc; + return 0; } EXPORT_SYMBOL_NS_GPL(cxl_inject_poison, "CXL"); @@ -347,19 +338,17 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) if (!IS_ENABLED(CONFIG_DEBUG_FS)) return 0; - rc = down_read_interruptible(&cxl_region_rwsem); - if (rc) + ACQUIRE(rwsem_read_intr, region_rwsem)(&cxl_rwsem.region); + if ((rc = ACQUIRE_ERR(rwsem_read_intr, ®ion_rwsem))) return rc; - rc = down_read_interruptible(&cxl_dpa_rwsem); - if (rc) { - up_read(&cxl_region_rwsem); + ACQUIRE(rwsem_read_intr, dpa_rwsem)(&cxl_rwsem.dpa); + if ((rc = ACQUIRE_ERR(rwsem_read_intr, &dpa_rwsem))) return rc; - } rc = cxl_validate_poison_dpa(cxlmd, dpa); if (rc) - goto out; + return rc; /* * In CXL 3.0 Spec 8.2.9.8.4.3, the Clear Poison mailbox command @@ -378,7 +367,7 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc) - goto out; + return rc; cxlr = cxl_dpa_to_region(cxlmd, dpa); if (cxlr) @@ -391,11 +380,8 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) .length = cpu_to_le32(1), }; trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_CLEAR); -out: - up_read(&cxl_dpa_rwsem); - up_read(&cxl_region_rwsem); - return rc; + return 0; } EXPORT_SYMBOL_NS_GPL(cxl_clear_poison, "CXL"); diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index 087a20a9ee1c..bacf1380dc4d 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -30,18 +30,12 @@ * instantiated by the core. */ -/* - * All changes to the interleave configuration occur with this lock held - * for write. - */ -DECLARE_RWSEM(cxl_region_rwsem); - static DEFINE_IDA(cxl_port_ida); static DEFINE_XARRAY(cxl_root_buses); int cxl_num_decoders_committed(struct cxl_port *port) { - lockdep_assert_held(&cxl_region_rwsem); + lockdep_assert_held(&cxl_rwsem.region); return port->commit_end + 1; } @@ -176,7 +170,7 @@ static ssize_t target_list_show(struct device *dev, ssize_t offset; int rc; - guard(rwsem_read)(&cxl_region_rwsem); + guard(rwsem_read)(&cxl_rwsem.region); rc = emit_target_list(cxlsd, buf); if (rc < 0) return rc; @@ -196,7 +190,7 @@ static ssize_t mode_show(struct device *dev, struct device_attribute *attr, struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev); struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); struct cxl_dev_state *cxlds = cxlmd->cxlds; - /* without @cxl_dpa_rwsem, make sure @part is not reloaded */ + /* without @cxl_rwsem.dpa, make sure @part is not reloaded */ int part = READ_ONCE(cxled->part); const char *desc; @@ -235,7 +229,7 @@ static ssize_t dpa_resource_show(struct device *dev, struct device_attribute *at { struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev); - guard(rwsem_read)(&cxl_dpa_rwsem); + guard(rwsem_read)(&cxl_rwsem.dpa); return sysfs_emit(buf, "%#llx\n", (u64)cxl_dpa_resource_start(cxled)); } static DEVICE_ATTR_RO(dpa_resource); @@ -560,7 +554,7 @@ static ssize_t decoders_committed_show(struct device *dev, { struct cxl_port *port = to_cxl_port(dev); - guard(rwsem_read)(&cxl_region_rwsem); + guard(rwsem_read)(&cxl_rwsem.region); return sysfs_emit(buf, "%d\n", cxl_num_decoders_committed(port)); } @@ -1722,7 +1716,7 @@ static int decoder_populate_targets(struct cxl_switch_decoder *cxlsd, if (xa_empty(&port->dports)) return -EINVAL; - guard(rwsem_write)(&cxl_region_rwsem); + guard(rwsem_write)(&cxl_rwsem.region); for (i = 0; i < cxlsd->cxld.interleave_ways; i++) { struct cxl_dport *dport = find_dport(port, target_map[i]); diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index 4314aaed8ad8..ad60c93be803 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -141,16 +141,12 @@ static ssize_t uuid_show(struct device *dev, struct device_attribute *attr, struct cxl_region_params *p = &cxlr->params; ssize_t rc; - rc = down_read_interruptible(&cxl_region_rwsem); - if (rc) + ACQUIRE(rwsem_read_intr, region_rwsem)(&cxl_rwsem.region); + if ((rc = ACQUIRE_ERR(rwsem_read_intr, ®ion_rwsem))) return rc; if (cxlr->mode != CXL_PARTMODE_PMEM) - rc = sysfs_emit(buf, "\n"); - else - rc = sysfs_emit(buf, "%pUb\n", &p->uuid); - up_read(&cxl_region_rwsem); - - return rc; + return sysfs_emit(buf, "\n"); + return sysfs_emit(buf, "%pUb\n", &p->uuid); } static int is_dup(struct device *match, void *data) @@ -162,7 +158,7 @@ static int is_dup(struct device *match, void *data) if (!is_cxl_region(match)) return 0; - lockdep_assert_held(&cxl_region_rwsem); + lockdep_assert_held(&cxl_rwsem.region); cxlr = to_cxl_region(match); p = &cxlr->params; @@ -192,27 +188,22 @@ static ssize_t uuid_store(struct device *dev, struct device_attribute *attr, if (uuid_is_null(&temp)) return -EINVAL; - rc = down_write_killable(&cxl_region_rwsem); - if (rc) + ACQUIRE(rwsem_write_kill, region_rwsem)(&cxl_rwsem.region); + if ((rc = ACQUIRE_ERR(rwsem_write_kill, ®ion_rwsem))) return rc; if (uuid_equal(&p->uuid, &temp)) - goto out; + return len; - rc = -EBUSY; if (p->state >= CXL_CONFIG_ACTIVE) - goto out; + return -EBUSY; rc = bus_for_each_dev(&cxl_bus_type, NULL, &temp, is_dup); if (rc < 0) - goto out; + return rc; uuid_copy(&p->uuid, &temp); -out: - up_write(&cxl_region_rwsem); - if (rc) - return rc; return len; } static DEVICE_ATTR_RW(uuid); @@ -354,20 +345,17 @@ static int queue_reset(struct cxl_region *cxlr) struct cxl_region_params *p = &cxlr->params; int rc; - rc = down_write_killable(&cxl_region_rwsem); - if (rc) + ACQUIRE(rwsem_write_kill, rwsem)(&cxl_rwsem.region); + if ((rc = ACQUIRE_ERR(rwsem_write_kill, &rwsem))) return rc; /* Already in the requested state? */ if (p->state < CXL_CONFIG_COMMIT) - goto out; + return 0; p->state = CXL_CONFIG_RESET_PENDING; -out: - up_write(&cxl_region_rwsem); - - return rc; + return 0; } static int __commit(struct cxl_region *cxlr) @@ -375,19 +363,17 @@ static int __commit(struct cxl_region *cxlr) struct cxl_region_params *p = &cxlr->params; int rc; - rc = down_write_killable(&cxl_region_rwsem); - if (rc) + ACQUIRE(rwsem_write_kill, rwsem)(&cxl_rwsem.region); + if ((rc = ACQUIRE_ERR(rwsem_write_kill, &rwsem))) return rc; /* Already in the requested state? */ if (p->state >= CXL_CONFIG_COMMIT) - goto out; + return 0; /* Not ready to commit? */ - if (p->state < CXL_CONFIG_ACTIVE) { - rc = -ENXIO; - goto out; - } + if (p->state < CXL_CONFIG_ACTIVE) + return -ENXIO; /* * Invalidate caches before region setup to drop any speculative @@ -395,16 +381,15 @@ static int __commit(struct cxl_region *cxlr) */ rc = cxl_region_invalidate_memregion(cxlr); if (rc) - goto out; + return rc; rc = cxl_region_decode_commit(cxlr); - if (rc == 0) - p->state = CXL_CONFIG_COMMIT; + if (rc) + return rc; -out: - up_write(&cxl_region_rwsem); + p->state = CXL_CONFIG_COMMIT; - return rc; + return 0; } static ssize_t commit_store(struct device *dev, struct device_attribute *attr, @@ -437,10 +422,10 @@ static ssize_t commit_store(struct device *dev, struct device_attribute *attr, device_release_driver(&cxlr->dev); /* - * With the reset pending take cxl_region_rwsem unconditionally + * With the reset pending take cxl_rwsem.region unconditionally * to ensure the reset gets handled before returning. */ - guard(rwsem_write)(&cxl_region_rwsem); + guard(rwsem_write)(&cxl_rwsem.region); /* * Revalidate that the reset is still pending in case another @@ -461,13 +446,10 @@ static ssize_t commit_show(struct device *dev, struct device_attribute *attr, struct cxl_region_params *p = &cxlr->params; ssize_t rc; - rc = down_read_interruptible(&cxl_region_rwsem); - if (rc) + ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region); + if ((rc = ACQUIRE_ERR(rwsem_read_intr, &rwsem))) return rc; - rc = sysfs_emit(buf, "%d\n", p->state >= CXL_CONFIG_COMMIT); - up_read(&cxl_region_rwsem); - - return rc; + return sysfs_emit(buf, "%d\n", p->state >= CXL_CONFIG_COMMIT); } static DEVICE_ATTR_RW(commit); @@ -491,15 +473,12 @@ static ssize_t interleave_ways_show(struct device *dev, { struct cxl_region *cxlr = to_cxl_region(dev); struct cxl_region_params *p = &cxlr->params; - ssize_t rc; + int rc; - rc = down_read_interruptible(&cxl_region_rwsem); - if (rc) + ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region); + if ((rc = ACQUIRE_ERR(rwsem_read_intr, &rwsem))) return rc; - rc = sysfs_emit(buf, "%d\n", p->interleave_ways); - up_read(&cxl_region_rwsem); - - return rc; + return sysfs_emit(buf, "%d\n", p->interleave_ways); } static const struct attribute_group *get_cxl_region_target_group(void); @@ -534,23 +513,21 @@ static ssize_t interleave_ways_store(struct device *dev, return -EINVAL; } - rc = down_write_killable(&cxl_region_rwsem); - if (rc) + ACQUIRE(rwsem_write_kill, rwsem)(&cxl_rwsem.region); + if ((rc = ACQUIRE_ERR(rwsem_write_kill, &rwsem))) return rc; - if (p->state >= CXL_CONFIG_INTERLEAVE_ACTIVE) { - rc = -EBUSY; - goto out; - } + + if (p->state >= CXL_CONFIG_INTERLEAVE_ACTIVE) + return -EBUSY; save = p->interleave_ways; p->interleave_ways = val; rc = sysfs_update_group(&cxlr->dev.kobj, get_cxl_region_target_group()); - if (rc) + if (rc) { p->interleave_ways = save; -out: - up_write(&cxl_region_rwsem); - if (rc) return rc; + } + return len; } static DEVICE_ATTR_RW(interleave_ways); @@ -561,15 +538,12 @@ static ssize_t interleave_granularity_show(struct device *dev, { struct cxl_region *cxlr = to_cxl_region(dev); struct cxl_region_params *p = &cxlr->params; - ssize_t rc; + int rc; - rc = down_read_interruptible(&cxl_region_rwsem); - if (rc) + ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region); + if ((rc = ACQUIRE_ERR(rwsem_read_intr, &rwsem))) return rc; - rc = sysfs_emit(buf, "%d\n", p->interleave_granularity); - up_read(&cxl_region_rwsem); - - return rc; + return sysfs_emit(buf, "%d\n", p->interleave_granularity); } static ssize_t interleave_granularity_store(struct device *dev, @@ -602,19 +576,15 @@ static ssize_t interleave_granularity_store(struct device *dev, if (cxld->interleave_ways > 1 && val != cxld->interleave_granularity) return -EINVAL; - rc = down_write_killable(&cxl_region_rwsem); - if (rc) + ACQUIRE(rwsem_write_kill, rwsem)(&cxl_rwsem.region); + if ((rc = ACQUIRE_ERR(rwsem_write_kill, &rwsem))) return rc; - if (p->state >= CXL_CONFIG_INTERLEAVE_ACTIVE) { - rc = -EBUSY; - goto out; - } + + if (p->state >= CXL_CONFIG_INTERLEAVE_ACTIVE) + return -EBUSY; p->interleave_granularity = val; -out: - up_write(&cxl_region_rwsem); - if (rc) - return rc; + return len; } static DEVICE_ATTR_RW(interleave_granularity); @@ -625,17 +595,15 @@ static ssize_t resource_show(struct device *dev, struct device_attribute *attr, struct cxl_region *cxlr = to_cxl_region(dev); struct cxl_region_params *p = &cxlr->params; u64 resource = -1ULL; - ssize_t rc; + int rc; - rc = down_read_interruptible(&cxl_region_rwsem); - if (rc) + ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region); + if ((rc = ACQUIRE_ERR(rwsem_read_intr, &rwsem))) return rc; + if (p->res) resource = p->res->start; - rc = sysfs_emit(buf, "%#llx\n", resource); - up_read(&cxl_region_rwsem); - - return rc; + return sysfs_emit(buf, "%#llx\n", resource); } static DEVICE_ATTR_RO(resource); @@ -663,7 +631,7 @@ static int alloc_hpa(struct cxl_region *cxlr, resource_size_t size) struct resource *res; u64 remainder = 0; - lockdep_assert_held_write(&cxl_region_rwsem); + lockdep_assert_held_write(&cxl_rwsem.region); /* Nothing to do... */ if (p->res && resource_size(p->res) == size) @@ -705,7 +673,7 @@ static void cxl_region_iomem_release(struct cxl_region *cxlr) struct cxl_region_params *p = &cxlr->params; if (device_is_registered(&cxlr->dev)) - lockdep_assert_held_write(&cxl_region_rwsem); + lockdep_assert_held_write(&cxl_rwsem.region); if (p->res) { /* * Autodiscovered regions may not have been able to insert their @@ -722,7 +690,7 @@ static int free_hpa(struct cxl_region *cxlr) { struct cxl_region_params *p = &cxlr->params; - lockdep_assert_held_write(&cxl_region_rwsem); + lockdep_assert_held_write(&cxl_rwsem.region); if (!p->res) return 0; @@ -746,15 +714,14 @@ static ssize_t size_store(struct device *dev, struct device_attribute *attr, if (rc) return rc; - rc = down_write_killable(&cxl_region_rwsem); - if (rc) + ACQUIRE(rwsem_write_kill, rwsem)(&cxl_rwsem.region); + if ((rc = ACQUIRE_ERR(rwsem_write_kill, &rwsem))) return rc; if (val) rc = alloc_hpa(cxlr, val); else rc = free_hpa(cxlr); - up_write(&cxl_region_rwsem); if (rc) return rc; @@ -770,15 +737,12 @@ static ssize_t size_show(struct device *dev, struct device_attribute *attr, u64 size = 0; ssize_t rc; - rc = down_read_interruptible(&cxl_region_rwsem); - if (rc) + ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region); + if ((rc = ACQUIRE_ERR(rwsem_read_intr, &rwsem))) return rc; if (p->res) size = resource_size(p->res); - rc = sysfs_emit(buf, "%#llx\n", size); - up_read(&cxl_region_rwsem); - - return rc; + return sysfs_emit(buf, "%#llx\n", size); } static DEVICE_ATTR_RW(size); @@ -804,26 +768,20 @@ static size_t show_targetN(struct cxl_region *cxlr, char *buf, int pos) struct cxl_endpoint_decoder *cxled; int rc; - rc = down_read_interruptible(&cxl_region_rwsem); - if (rc) + ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region); + if ((rc = ACQUIRE_ERR(rwsem_read_intr, &rwsem))) return rc; if (pos >= p->interleave_ways) { dev_dbg(&cxlr->dev, "position %d out of range %d\n", pos, p->interleave_ways); - rc = -ENXIO; - goto out; + return -ENXIO; } cxled = p->targets[pos]; if (!cxled) - rc = sysfs_emit(buf, "\n"); - else - rc = sysfs_emit(buf, "%s\n", dev_name(&cxled->cxld.dev)); -out: - up_read(&cxl_region_rwsem); - - return rc; + return sysfs_emit(buf, "\n"); + return sysfs_emit(buf, "%s\n", dev_name(&cxled->cxld.dev)); } static int check_commit_order(struct device *dev, void *data) @@ -938,7 +896,7 @@ cxl_port_pick_region_decoder(struct cxl_port *port, /* * This decoder is pinned registered as long as the endpoint decoder is * registered, and endpoint decoder unregistration holds the - * cxl_region_rwsem over unregister events, so no need to hold on to + * cxl_rwsem.region over unregister events, so no need to hold on to * this extra reference. */ put_device(dev); @@ -1129,7 +1087,7 @@ static int cxl_port_attach_region(struct cxl_port *port, unsigned long index; int rc = -EBUSY; - lockdep_assert_held_write(&cxl_region_rwsem); + lockdep_assert_held_write(&cxl_rwsem.region); cxl_rr = cxl_rr_load(port, cxlr); if (cxl_rr) { @@ -1239,7 +1197,7 @@ static void cxl_port_detach_region(struct cxl_port *port, struct cxl_region_ref *cxl_rr; struct cxl_ep *ep = NULL; - lockdep_assert_held_write(&cxl_region_rwsem); + lockdep_assert_held_write(&cxl_rwsem.region); cxl_rr = cxl_rr_load(port, cxlr); if (!cxl_rr) @@ -2142,7 +2100,7 @@ __cxl_decoder_detach(struct cxl_region *cxlr, { struct cxl_region_params *p; - lockdep_assert_held_write(&cxl_region_rwsem); + lockdep_assert_held_write(&cxl_rwsem.region); if (!cxled) { p = &cxlr->params; @@ -2215,18 +2173,18 @@ int cxl_decoder_detach(struct cxl_region *cxlr, struct cxl_region *detach; /* when the decoder is being destroyed lock unconditionally */ - if (mode == DETACH_INVALIDATE) - down_write(&cxl_region_rwsem); - else { - int rc = down_write_killable(&cxl_region_rwsem); + if (mode == DETACH_INVALIDATE) { + guard(rwsem_write)(&cxl_rwsem.region); + detach = __cxl_decoder_detach(cxlr, cxled, pos, mode); + } else { + int rc; - if (rc) + ACQUIRE(rwsem_write_kill, rwsem)(&cxl_rwsem.region); + if ((rc = ACQUIRE_ERR(rwsem_write_kill, &rwsem))) return rc; + detach = __cxl_decoder_detach(cxlr, cxled, pos, mode); } - detach = __cxl_decoder_detach(cxlr, cxled, pos, mode); - up_write(&cxl_region_rwsem); - if (detach) { device_release_driver(&detach->dev); put_device(&detach->dev); @@ -2234,29 +2192,35 @@ int cxl_decoder_detach(struct cxl_region *cxlr, return 0; } +static int __attach_target(struct cxl_region *cxlr, + struct cxl_endpoint_decoder *cxled, int pos, + unsigned int state) +{ + int rc; + + if (state == TASK_INTERRUPTIBLE) { + ACQUIRE(rwsem_write_kill, rwsem)(&cxl_rwsem.region); + if ((rc = ACQUIRE_ERR(rwsem_write_kill, &rwsem))) + return rc; + guard(rwsem_read)(&cxl_rwsem.dpa); + return cxl_region_attach(cxlr, cxled, pos); + } + guard(rwsem_write)(&cxl_rwsem.region); + guard(rwsem_read)(&cxl_rwsem.dpa); + return cxl_region_attach(cxlr, cxled, pos); +} + static int attach_target(struct cxl_region *cxlr, struct cxl_endpoint_decoder *cxled, int pos, unsigned int state) { - int rc = 0; - - if (state == TASK_INTERRUPTIBLE) - rc = down_write_killable(&cxl_region_rwsem); - else - down_write(&cxl_region_rwsem); - if (rc) - return rc; - - down_read(&cxl_dpa_rwsem); - rc = cxl_region_attach(cxlr, cxled, pos); - up_read(&cxl_dpa_rwsem); - up_write(&cxl_region_rwsem); + int rc = __attach_target(cxlr, cxled, pos, state); - if (rc) - dev_warn(cxled->cxld.dev.parent, - "failed to attach %s to %s: %d\n", - dev_name(&cxled->cxld.dev), dev_name(&cxlr->dev), rc); + if (rc == 0) + return 0; + dev_warn(cxled->cxld.dev.parent, "failed to attach %s to %s: %d\n", + dev_name(&cxled->cxld.dev), dev_name(&cxlr->dev), rc); return rc; } @@ -2516,7 +2480,7 @@ static int cxl_region_perf_attrs_callback(struct notifier_block *nb, return NOTIFY_DONE; /* - * No need to hold cxl_region_rwsem; region parameters are stable + * No need to hold cxl_rwsem.region; region parameters are stable * within the cxl_region driver. */ region_nid = phys_to_target_node(cxlr->params.res->start); @@ -2539,7 +2503,7 @@ static int cxl_region_calculate_adistance(struct notifier_block *nb, int region_nid; /* - * No need to hold cxl_region_rwsem; region parameters are stable + * No need to hold cxl_rwsem.region; region parameters are stable * within the cxl_region driver. */ region_nid = phys_to_target_node(cxlr->params.res->start); @@ -2688,17 +2652,13 @@ static ssize_t region_show(struct device *dev, struct device_attribute *attr, struct cxl_decoder *cxld = to_cxl_decoder(dev); ssize_t rc; - rc = down_read_interruptible(&cxl_region_rwsem); - if (rc) + ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region); + if ((rc = ACQUIRE_ERR(rwsem_read_intr, &rwsem))) return rc; if (cxld->region) - rc = sysfs_emit(buf, "%s\n", dev_name(&cxld->region->dev)); - else - rc = sysfs_emit(buf, "\n"); - up_read(&cxl_region_rwsem); - - return rc; + return sysfs_emit(buf, "%s\n", dev_name(&cxld->region->dev)); + return sysfs_emit(buf, "\n"); } DEVICE_ATTR_RO(region); @@ -3037,7 +2997,7 @@ static int cxl_pmem_region_alloc(struct cxl_region *cxlr) struct device *dev; int i; - guard(rwsem_read)(&cxl_region_rwsem); + guard(rwsem_read)(&cxl_rwsem.region); if (p->state != CXL_CONFIG_COMMIT) return -ENXIO; @@ -3049,7 +3009,7 @@ static int cxl_pmem_region_alloc(struct cxl_region *cxlr) cxlr_pmem->hpa_range.start = p->res->start; cxlr_pmem->hpa_range.end = p->res->end; - /* Snapshot the region configuration underneath the cxl_region_rwsem */ + /* Snapshot the region configuration underneath the cxl_rwsem.region */ cxlr_pmem->nr_mappings = p->nr_targets; for (i = 0; i < p->nr_targets; i++) { struct cxl_endpoint_decoder *cxled = p->targets[i]; @@ -3126,7 +3086,7 @@ static struct cxl_dax_region *cxl_dax_region_alloc(struct cxl_region *cxlr) struct cxl_dax_region *cxlr_dax; struct device *dev; - guard(rwsem_read)(&cxl_region_rwsem); + guard(rwsem_read)(&cxl_rwsem.region); if (p->state != CXL_CONFIG_COMMIT) return ERR_PTR(-ENXIO); @@ -3326,7 +3286,7 @@ static int match_region_by_range(struct device *dev, const void *data) cxlr = to_cxl_region(dev); p = &cxlr->params; - guard(rwsem_read)(&cxl_region_rwsem); + guard(rwsem_read)(&cxl_rwsem.region); if (p->res && p->res->start == r->start && p->res->end == r->end) return 1; @@ -3386,7 +3346,7 @@ static int __construct_region(struct cxl_region *cxlr, struct resource *res; int rc; - guard(rwsem_write)(&cxl_region_rwsem); + guard(rwsem_write)(&cxl_rwsem.region); p = &cxlr->params; if (p->state >= CXL_CONFIG_INTERLEAVE_ACTIVE) { dev_err(cxlmd->dev.parent, @@ -3522,10 +3482,10 @@ int cxl_add_to_region(struct cxl_endpoint_decoder *cxled) attach_target(cxlr, cxled, -1, TASK_UNINTERRUPTIBLE); - down_read(&cxl_region_rwsem); - p = &cxlr->params; - attach = p->state == CXL_CONFIG_COMMIT; - up_read(&cxl_region_rwsem); + scoped_guard(rwsem_read, &cxl_rwsem.region) { + p = &cxlr->params; + attach = p->state == CXL_CONFIG_COMMIT; + } if (attach) { /* @@ -3550,7 +3510,7 @@ u64 cxl_port_get_spa_cache_alias(struct cxl_port *endpoint, u64 spa) if (!endpoint) return ~0ULL; - guard(rwsem_write)(&cxl_region_rwsem); + guard(rwsem_write)(&cxl_rwsem.region); xa_for_each(&endpoint->regions, index, iter) { struct cxl_region_params *p = &iter->region->params; @@ -3592,30 +3552,23 @@ static int cxl_region_can_probe(struct cxl_region *cxlr) struct cxl_region_params *p = &cxlr->params; int rc; - rc = down_read_interruptible(&cxl_region_rwsem); - if (rc) { + ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region); + if ((rc = ACQUIRE_ERR(rwsem_read_intr, &rwsem))) { dev_dbg(&cxlr->dev, "probe interrupted\n"); return rc; } if (p->state < CXL_CONFIG_COMMIT) { dev_dbg(&cxlr->dev, "config state: %d\n", p->state); - rc = -ENXIO; - goto out; + return -ENXIO; } if (test_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags)) { dev_err(&cxlr->dev, "failed to activate, re-commit region and retry\n"); - rc = -ENXIO; - goto out; + return -ENXIO; } -out: - up_read(&cxl_region_rwsem); - - if (rc) - return rc; return 0; } diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index 3f1695c96abc..50799a681231 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -469,7 +469,7 @@ enum cxl_config_state { * @nr_targets: number of targets * @cache_size: extended linear cache size if exists, otherwise zero. * - * State transitions are protected by the cxl_region_rwsem + * State transitions are protected by cxl_rwsem.region */ struct cxl_region_params { enum cxl_config_state state; @@ -912,15 +912,4 @@ bool cxl_endpoint_decoder_reset_detected(struct cxl_port *port); #endif u16 cxl_gpf_get_dvsec(struct device *dev); - -static inline struct rw_semaphore *rwsem_read_intr_acquire(struct rw_semaphore *rwsem) -{ - if (down_read_interruptible(rwsem)) - return NULL; - - return rwsem; -} - -DEFINE_FREE(rwsem_read_release, struct rw_semaphore *, if (_T) up_read(_T)) - #endif /* __CXL_H__ */ diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index c810deb88d13..cbafdc12e743 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -244,6 +244,7 @@ DEFINE_GUARD_COND(rwsem_read, _intr, down_read_interruptible(_T), _RET == 0) DEFINE_GUARD(rwsem_write, struct rw_semaphore *, down_write(_T), up_write(_T)) DEFINE_GUARD_COND(rwsem_write, _try, down_write_trylock(_T)) +DEFINE_GUARD_COND(rwsem_write, _kill, down_write_killable(_T), _RET == 0) /* * downgrade write lock to read lock -- cgit v1.2.3 From ddb8172cdf8854a215ce23ad0f20b2578fa512db Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 8 Jul 2025 16:33:44 +0300 Subject: watchdog: Don't use "proxy" headers Update header inclusions to follow IWYU (Include What You Use) principle. Note that kernel.h is discouraged to be included as it's written at the top of that file. Signed-off-by: Andy Shevchenko Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20250708133646.70384-3-andriy.shevchenko@linux.intel.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/watchdog_core.h | 8 +++++++- drivers/watchdog/watchdog_pretimeout.c | 2 ++ include/linux/watchdog.h | 12 ++++++++---- 3 files changed, 17 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/watchdog/watchdog_core.h b/drivers/watchdog/watchdog_core.h index 5b35a8439e26..ab825d9f9248 100644 --- a/drivers/watchdog/watchdog_core.h +++ b/drivers/watchdog/watchdog_core.h @@ -24,8 +24,14 @@ * This material is provided "AS-IS" and at no charge. */ -#include +#include +#include +#include +#include #include +#include +#include +#include #define MAX_DOGS 32 /* Maximum number of watchdog devices */ diff --git a/drivers/watchdog/watchdog_pretimeout.c b/drivers/watchdog/watchdog_pretimeout.c index e5295c990fa1..2526436dc74d 100644 --- a/drivers/watchdog/watchdog_pretimeout.c +++ b/drivers/watchdog/watchdog_pretimeout.c @@ -7,6 +7,8 @@ #include #include #include +#include +#include #include #include "watchdog_core.h" diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index 99660197a36c..8c60687a3e55 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -9,14 +9,18 @@ #ifndef _LINUX_WATCHDOG_H #define _LINUX_WATCHDOG_H - #include -#include -#include -#include +#include #include +#include +#include + #include +struct attribute_group; +struct device; +struct module; + struct watchdog_ops; struct watchdog_device; struct watchdog_core_data; -- cgit v1.2.3 From 76720eed7d18baf51c0f31fe8a3784702f50e3fc Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Thu, 17 Jul 2025 12:38:04 -0500 Subject: PCI: Add pci_is_display() to check if device is a display controller Several places in the kernel do class shifting to match whether a PCI device is display class. Add pci_is_display() for those places to use. Signed-off-by: Mario Limonciello Signed-off-by: Bjorn Helgaas Reviewed-by: Daniel Dadap Reviewed-by: Simona Vetter Link: https://patch.msgid.link/20250717173812.3633478-2-superm1@kernel.org --- include/linux/pci.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 05e68f35f392..4fff6405a830 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -744,6 +744,21 @@ static inline bool pci_is_vga(struct pci_dev *pdev) return false; } +/** + * pci_is_display - check if the PCI device is a display controller + * @pdev: PCI device + * + * Determine whether the given PCI device corresponds to a display + * controller. Display controllers are typically used for graphical output + * and are identified based on their class code. + * + * Return: true if the PCI device is a display controller, false otherwise. + */ +static inline bool pci_is_display(struct pci_dev *pdev) +{ + return (pdev->class >> 16) == PCI_BASE_CLASS_DISPLAY; +} + #define for_each_pci_bridge(dev, bus) \ list_for_each_entry(dev, &bus->devices, bus_list) \ if (!pci_is_bridge(dev)) {} else -- cgit v1.2.3 From b2df55a98672f4be076ff69d0f0d0b1fc81f2044 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 17 Jul 2025 09:30:36 -0700 Subject: cleanup: Fix documentation build error for ACQUIRE updates Stephen reports: Documentation/core-api/cleanup:7: include/linux/cleanup.h:73: ERROR: Unexpected indentation. [docutils] Documentation/core-api/cleanup:7: include/linux/cleanup.h:74: WARNING: Block quote ends without a blank line; unexpected unindent. [docutils] Which points out that the ACQUIRE() example in cleanup.h missed the "::" suffix to mark the following text as a code-block. Fixes: 857d18f23ab1 ("cleanup: Introduce ACQUIRE() and ACQUIRE_ERR() for conditional locks") Reported-by: Stephen Rothwell Closes: http://lore.kernel.org/20250717173354.34375751@canb.auug.org.au Signed-off-by: Dan Williams Acked-by: Randy Dunlap Tested-by: Randy Dunlap Link: https://patch.msgid.link/20250717163036.1275791-1-dan.j.williams@intel.com Signed-off-by: Dave Jiang --- include/linux/cleanup.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index 4eb83dd71cfe..0fb796db4811 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -64,8 +64,7 @@ * the remainder of "func()". * * The ACQUIRE() macro can be used in all places that guard() can be - * used and additionally support conditional locks - * + * used and additionally support conditional locks:: * * DEFINE_GUARD_COND(pci_dev, _try, pci_dev_trylock(_T)) * ... -- cgit v1.2.3 From 35c18f2933c596b4fd6a98baee36f3137d133a5f Mon Sep 17 00:00:00 2001 From: Jiri Bohac Date: Thu, 12 Jun 2025 12:13:21 +0200 Subject: Add a new optional ",cma" suffix to the crashkernel= command line option Patch series "kdump: crashkernel reservation from CMA", v5. This series implements a way to reserve additional crash kernel memory using CMA. Currently, all the memory for the crash kernel is not usable by the 1st (production) kernel. It is also unmapped so that it can't be corrupted by the fault that will eventually trigger the crash. This makes sense for the memory actually used by the kexec-loaded crash kernel image and initrd and the data prepared during the load (vmcoreinfo, ...). However, the reserved space needs to be much larger than that to provide enough run-time memory for the crash kernel and the kdump userspace. Estimating the amount of memory to reserve is difficult. Being too careful makes kdump likely to end in OOM, being too generous takes even more memory from the production system. Also, the reservation only allows reserving a single contiguous block (or two with the "low" suffix). I've seen systems where this fails because the physical memory is fragmented. By reserving additional crashkernel memory from CMA, the main crashkernel reservation can be just large enough to fit the kernel and initrd image, minimizing the memory taken away from the production system. Most of the run-time memory for the crash kernel will be memory previously available to userspace in the production system. As this memory is no longer wasted, the reservation can be done with a generous margin, making kdump more reliable. Kernel memory that we need to preserve for dumping is normally not allocated from CMA, unless it is explicitly allocated as movable. Currently this is only the case for memory ballooning and zswap. Such movable memory will be missing from the vmcore. User data is typically not dumped by makedumpfile. When dumping of user data is intended this new CMA reservation cannot be used. There are five patches in this series: The first adds a new ",cma" suffix to the recenly introduced generic crashkernel parsing code. parse_crashkernel() takes one more argument to store the cma reservation size. The second patch implements reserve_crashkernel_cma() which performs the reservation. If the requested size is not available in a single range, multiple smaller ranges will be reserved. The third patch updates Documentation/, explicitly mentioning the potential DMA corruption of the CMA-reserved memory. The fourth patch adds a short delay before booting the kdump kernel, allowing pending DMA transfers to finish. The fifth patch enables the functionality for x86 as a proof of concept. There are just three things every arch needs to do: - call reserve_crashkernel_cma() - include the CMA-reserved ranges in the physical memory map - exclude the CMA-reserved ranges from the memory available through /proc/vmcore by excluding them from the vmcoreinfo PT_LOAD ranges. Adding other architectures is easy and I can do that as soon as this series is merged. With this series applied, specifying crashkernel=100M craskhernel=1G,cma on the command line will make a standard crashkernel reservation of 100M, where kexec will load the kernel and initrd. An additional 1G will be reserved from CMA, still usable by the production system. The crash kernel will have 1.1G memory available. The 100M can be reliably predicted based on the size of the kernel and initrd. The new cma suffix is completely optional. When no crashkernel=size,cma is specified, everything works as before. This patch (of 5): Add a new cma_size parameter to parse_crashkernel(). When not NULL, call __parse_crashkernel to parse the CMA reservation size from "crashkernel=size,cma" and store it in cma_size. Set cma_size to NULL in all calls to parse_crashkernel(). Link: https://lkml.kernel.org/r/aEqnxxfLZMllMC8I@dwarf.suse.cz Link: https://lkml.kernel.org/r/aEqoQckgoTQNULnh@dwarf.suse.cz Signed-off-by: Jiri Bohac Cc: Baoquan He Cc: Dave Young Cc: Donald Dutile Cc: Michal Hocko Cc: Philipp Rudo Cc: Pingfan Liu Cc: Tao Liu Cc: Vivek Goyal Cc: David Hildenbrand Signed-off-by: Andrew Morton --- arch/arm/kernel/setup.c | 2 +- arch/arm64/mm/init.c | 2 +- arch/loongarch/kernel/setup.c | 2 +- arch/mips/kernel/setup.c | 2 +- arch/powerpc/kernel/fadump.c | 2 +- arch/powerpc/kexec/core.c | 2 +- arch/powerpc/mm/nohash/kaslr_booke.c | 2 +- arch/riscv/mm/init.c | 2 +- arch/s390/kernel/setup.c | 2 +- arch/sh/kernel/machine_kexec.c | 2 +- arch/x86/kernel/setup.c | 2 +- include/linux/crash_reserve.h | 3 ++- kernel/crash_reserve.c | 16 ++++++++++++++-- 13 files changed, 27 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index a41c93988d2c..0bfd66c7ada0 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -1004,7 +1004,7 @@ static void __init reserve_crashkernel(void) total_mem = get_total_mem(); ret = parse_crashkernel(boot_command_line, total_mem, &crash_size, &crash_base, - NULL, NULL); + NULL, NULL, NULL); /* invalid value specified or crashkernel=0 */ if (ret || !crash_size) return; diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 0c8c35dd645e..ea84a61ed508 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -106,7 +106,7 @@ static void __init arch_reserve_crashkernel(void) ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), &crash_size, &crash_base, - &low_size, &high); + &low_size, NULL, &high); if (ret) return; diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index b99fbb388fe0..22b27cd447a1 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -265,7 +265,7 @@ static void __init arch_reserve_crashkernel(void) return; ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), - &crash_size, &crash_base, &low_size, &high); + &crash_size, &crash_base, &low_size, NULL, &high); if (ret) return; diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index fbfe0771317e..11b9b6b63e19 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -458,7 +458,7 @@ static void __init mips_parse_crashkernel(void) total_mem = memblock_phys_mem_size(); ret = parse_crashkernel(boot_command_line, total_mem, &crash_size, &crash_base, - NULL, NULL); + NULL, NULL, NULL); if (ret != 0 || crash_size <= 0) return; diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 8ca49e40c473..28cab25d5b33 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -333,7 +333,7 @@ static __init u64 fadump_calculate_reserve_size(void) * memory at a predefined offset. */ ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), - &size, &base, NULL, NULL); + &size, &base, NULL, NULL, NULL); if (ret == 0 && size > 0) { unsigned long max_size; diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c index 00e9c267b912..d1a2d755381c 100644 --- a/arch/powerpc/kexec/core.c +++ b/arch/powerpc/kexec/core.c @@ -110,7 +110,7 @@ void __init arch_reserve_crashkernel(void) /* use common parsing */ ret = parse_crashkernel(boot_command_line, total_mem_sz, &crash_size, - &crash_base, NULL, NULL); + &crash_base, NULL, NULL, NULL); if (ret) return; diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c index 5c8d1bb98b3e..5e4897daaaea 100644 --- a/arch/powerpc/mm/nohash/kaslr_booke.c +++ b/arch/powerpc/mm/nohash/kaslr_booke.c @@ -178,7 +178,7 @@ static void __init get_crash_kernel(void *fdt, unsigned long size) int ret; ret = parse_crashkernel(boot_command_line, size, &crash_size, - &crash_base, NULL, NULL); + &crash_base, NULL, NULL, NULL); if (ret != 0 || crash_size == 0) return; if (crash_base == 0) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 8d0374d7ce8e..15683ae13fa5 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -1408,7 +1408,7 @@ static void __init arch_reserve_crashkernel(void) ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), &crash_size, &crash_base, - &low_size, &high); + &low_size, NULL, &high); if (ret) return; diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index f244c5560e7f..b99aeb0db2ee 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -605,7 +605,7 @@ static void __init reserve_crashkernel(void) int rc; rc = parse_crashkernel(boot_command_line, ident_map_size, - &crash_size, &crash_base, NULL, NULL); + &crash_size, &crash_base, NULL, NULL, NULL); crash_base = ALIGN(crash_base, KEXEC_CRASH_MEM_ALIGN); crash_size = ALIGN(crash_size, KEXEC_CRASH_MEM_ALIGN); diff --git a/arch/sh/kernel/machine_kexec.c b/arch/sh/kernel/machine_kexec.c index 8321b31d2e19..37073ca1e0ad 100644 --- a/arch/sh/kernel/machine_kexec.c +++ b/arch/sh/kernel/machine_kexec.c @@ -146,7 +146,7 @@ void __init reserve_crashkernel(void) return; ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), - &crash_size, &crash_base, NULL, NULL); + &crash_size, &crash_base, NULL, NULL, NULL); if (ret == 0 && crash_size > 0) { crashk_res.start = crash_base; crashk_res.end = crash_base + crash_size - 1; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index fb27be697128..c22dc630c297 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -608,7 +608,7 @@ static void __init arch_reserve_crashkernel(void) ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), &crash_size, &crash_base, - &low_size, &high); + &low_size, NULL, &high); if (ret) return; diff --git a/include/linux/crash_reserve.h b/include/linux/crash_reserve.h index 1fe7e7d1b214..e784aaff2f5a 100644 --- a/include/linux/crash_reserve.h +++ b/include/linux/crash_reserve.h @@ -16,7 +16,8 @@ extern struct resource crashk_low_res; int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, unsigned long long *crash_size, unsigned long long *crash_base, - unsigned long long *low_size, bool *high); + unsigned long long *low_size, unsigned long long *cma_size, + bool *high); #ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION #ifndef DEFAULT_CRASH_KERNEL_LOW_SIZE diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c index acb6bf42e30d..86ae1365d04e 100644 --- a/kernel/crash_reserve.c +++ b/kernel/crash_reserve.c @@ -172,17 +172,19 @@ static int __init parse_crashkernel_simple(char *cmdline, #define SUFFIX_HIGH 0 #define SUFFIX_LOW 1 -#define SUFFIX_NULL 2 +#define SUFFIX_CMA 2 +#define SUFFIX_NULL 3 static __initdata char *suffix_tbl[] = { [SUFFIX_HIGH] = ",high", [SUFFIX_LOW] = ",low", + [SUFFIX_CMA] = ",cma", [SUFFIX_NULL] = NULL, }; /* * That function parses "suffix" crashkernel command lines like * - * crashkernel=size,[high|low] + * crashkernel=size,[high|low|cma] * * It returns 0 on success and -EINVAL on failure. */ @@ -298,9 +300,11 @@ int __init parse_crashkernel(char *cmdline, unsigned long long *crash_size, unsigned long long *crash_base, unsigned long long *low_size, + unsigned long long *cma_size, bool *high) { int ret; + unsigned long long __always_unused cma_base; /* crashkernel=X[@offset] */ ret = __parse_crashkernel(cmdline, system_ram, crash_size, @@ -331,6 +335,14 @@ int __init parse_crashkernel(char *cmdline, *high = true; } + + /* + * optional CMA reservation + * cma_base is ignored + */ + if (cma_size) + __parse_crashkernel(cmdline, 0, cma_size, + &cma_base, suffix_tbl[SUFFIX_CMA]); #endif if (!*crash_size) ret = -EINVAL; -- cgit v1.2.3 From ab475510e0422bb5672d465f9d0f523d72fdb7f1 Mon Sep 17 00:00:00 2001 From: Jiri Bohac Date: Thu, 12 Jun 2025 12:16:39 +0200 Subject: kdump: implement reserve_crashkernel_cma reserve_crashkernel_cma() reserves CMA ranges for the crash kernel. If allocating the requested size fails, try to reserve in smaller blocks. Store the reserved ranges in the crashk_cma_ranges array and the number of ranges in crashk_cma_cnt. Link: https://lkml.kernel.org/r/aEqpBwOy_ekm0gw9@dwarf.suse.cz Signed-off-by: Jiri Bohac Cc: Baoquan He Cc: Dave Young Cc: David Hildenbrand Cc: Donald Dutile Cc: Michal Hocko Cc: Philipp Rudo Cc: Pingfan Liu Cc: Tao Liu Cc: Vivek Goyal Signed-off-by: Andrew Morton --- include/linux/crash_reserve.h | 12 ++++++++++ kernel/crash_reserve.c | 52 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 64 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crash_reserve.h b/include/linux/crash_reserve.h index e784aaff2f5a..7b44b41d0a20 100644 --- a/include/linux/crash_reserve.h +++ b/include/linux/crash_reserve.h @@ -13,12 +13,24 @@ */ extern struct resource crashk_res; extern struct resource crashk_low_res; +extern struct range crashk_cma_ranges[]; +#if defined(CONFIG_CMA) && defined(CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION) +#define CRASHKERNEL_CMA +#define CRASHKERNEL_CMA_RANGES_MAX 4 +extern int crashk_cma_cnt; +#else +#define crashk_cma_cnt 0 +#define CRASHKERNEL_CMA_RANGES_MAX 0 +#endif + int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, unsigned long long *crash_size, unsigned long long *crash_base, unsigned long long *low_size, unsigned long long *cma_size, bool *high); +void __init reserve_crashkernel_cma(unsigned long long cma_size); + #ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION #ifndef DEFAULT_CRASH_KERNEL_LOW_SIZE #define DEFAULT_CRASH_KERNEL_LOW_SIZE (128UL << 20) diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c index 86ae1365d04e..87bf4d41eabb 100644 --- a/kernel/crash_reserve.c +++ b/kernel/crash_reserve.c @@ -14,6 +14,8 @@ #include #include #include +#include +#include #include #include @@ -469,6 +471,56 @@ retry: #endif } +struct range crashk_cma_ranges[CRASHKERNEL_CMA_RANGES_MAX]; +#ifdef CRASHKERNEL_CMA +int crashk_cma_cnt; +void __init reserve_crashkernel_cma(unsigned long long cma_size) +{ + unsigned long long request_size = roundup(cma_size, PAGE_SIZE); + unsigned long long reserved_size = 0; + + if (!cma_size) + return; + + while (cma_size > reserved_size && + crashk_cma_cnt < CRASHKERNEL_CMA_RANGES_MAX) { + + struct cma *res; + + if (cma_declare_contiguous(0, request_size, 0, 0, 0, false, + "crashkernel", &res)) { + /* reservation failed, try half-sized blocks */ + if (request_size <= PAGE_SIZE) + break; + + request_size = roundup(request_size / 2, PAGE_SIZE); + continue; + } + + crashk_cma_ranges[crashk_cma_cnt].start = cma_get_base(res); + crashk_cma_ranges[crashk_cma_cnt].end = + crashk_cma_ranges[crashk_cma_cnt].start + + cma_get_size(res) - 1; + ++crashk_cma_cnt; + reserved_size += request_size; + } + + if (cma_size > reserved_size) + pr_warn("crashkernel CMA reservation failed: %lld MB requested, %lld MB reserved in %d ranges\n", + cma_size >> 20, reserved_size >> 20, crashk_cma_cnt); + else + pr_info("crashkernel CMA reserved: %lld MB in %d ranges\n", + reserved_size >> 20, crashk_cma_cnt); +} + +#else /* CRASHKERNEL_CMA */ +void __init reserve_crashkernel_cma(unsigned long long cma_size) +{ + if (cma_size) + pr_warn("crashkernel CMA reservation not supported\n"); +} +#endif + #ifndef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY static __init int insert_crashkernel_resources(void) { -- cgit v1.2.3 From b76e89e50fc3693b7b8a443ed906320d8ccb93fd Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Thu, 3 Jul 2025 10:10:01 +0800 Subject: panic: generalize panic_print's function to show sys info 'panic_print' was introduced to help debugging kernel panic by dumping different kinds of system information like tasks' call stack, memory, ftrace buffer, etc. Actually this function could also be used to help debugging other cases like task-hung, soft/hard lockup, etc. where user may need the snapshot of system info at that time. Extract system info dump function related code from panic.c to separate file sys_info.[ch], for wider usage by other kernel parts for debugging. Also modify the macro names about singulars/plurals. Link: https://lkml.kernel.org/r/20250703021004.42328-3-feng.tang@linux.alibaba.com Signed-off-by: Feng Tang Suggested-by: Petr Mladek Cc: John Ogness Cc: Jonathan Corbet Cc: Lance Yang Cc: "Paul E . McKenney" Cc: Steven Rostedt Cc: Nathan Chancellor Signed-off-by: Andrew Morton --- include/linux/sys_info.h | 20 ++++++++++++++++++++ kernel/panic.c | 36 ++++-------------------------------- lib/Makefile | 2 +- lib/sys_info.c | 32 ++++++++++++++++++++++++++++++++ 4 files changed, 57 insertions(+), 33 deletions(-) create mode 100644 include/linux/sys_info.h create mode 100644 lib/sys_info.c (limited to 'include/linux') diff --git a/include/linux/sys_info.h b/include/linux/sys_info.h new file mode 100644 index 000000000000..53b7e27dbf2a --- /dev/null +++ b/include/linux/sys_info.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_SYS_INFO_H +#define _LINUX_SYS_INFO_H + +/* + * SYS_INFO_PANIC_CONSOLE_REPLAY is for panic case only, as it needs special + * handling which only fits panic case. + */ +#define SYS_INFO_TASKS 0x00000001 +#define SYS_INFO_MEM 0x00000002 +#define SYS_INFO_TIMERS 0x00000004 +#define SYS_INFO_LOCKS 0x00000008 +#define SYS_INFO_FTRACE 0x00000010 +#define SYS_INFO_PANIC_CONSOLE_REPLAY 0x00000020 +#define SYS_INFO_ALL_CPU_BT 0x00000040 +#define SYS_INFO_BLOCKED_TASKS 0x00000080 + +void sys_info(unsigned long si_mask); + +#endif /* _LINUX_SYS_INFO_H */ diff --git a/kernel/panic.c b/kernel/panic.c index 9b6c5dc28a65..cbb0681177b3 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include @@ -69,14 +70,6 @@ bool panic_triggering_all_cpu_backtrace; int panic_timeout = CONFIG_PANIC_TIMEOUT; EXPORT_SYMBOL_GPL(panic_timeout); -#define PANIC_PRINT_TASK_INFO 0x00000001 -#define PANIC_PRINT_MEM_INFO 0x00000002 -#define PANIC_PRINT_TIMER_INFO 0x00000004 -#define PANIC_PRINT_LOCK_INFO 0x00000008 -#define PANIC_PRINT_FTRACE_INFO 0x00000010 -#define PANIC_CONSOLE_REPLAY 0x00000020 -#define PANIC_PRINT_ALL_CPU_BT 0x00000040 -#define PANIC_PRINT_BLOCKED_TASKS 0x00000080 unsigned long panic_print; ATOMIC_NOTIFIER_HEAD(panic_notifier_list); @@ -240,31 +233,10 @@ EXPORT_SYMBOL(nmi_panic); static void panic_console_replay(void) { - if (panic_print & PANIC_CONSOLE_REPLAY) + if (panic_print & SYS_INFO_PANIC_CONSOLE_REPLAY) console_flush_on_panic(CONSOLE_REPLAY_ALL); } -static void panic_print_sys_info(void) -{ - if (panic_print & PANIC_PRINT_TASK_INFO) - show_state(); - - if (panic_print & PANIC_PRINT_MEM_INFO) - show_mem(); - - if (panic_print & PANIC_PRINT_TIMER_INFO) - sysrq_timer_list_show(); - - if (panic_print & PANIC_PRINT_LOCK_INFO) - debug_show_all_locks(); - - if (panic_print & PANIC_PRINT_FTRACE_INFO) - ftrace_dump(DUMP_ALL); - - if (panic_print & PANIC_PRINT_BLOCKED_TASKS) - show_state_filter(TASK_UNINTERRUPTIBLE); -} - void check_panic_on_warn(const char *origin) { unsigned int limit; @@ -285,7 +257,7 @@ void check_panic_on_warn(const char *origin) */ static void panic_other_cpus_shutdown(bool crash_kexec) { - if (panic_print & PANIC_PRINT_ALL_CPU_BT) { + if (panic_print & SYS_INFO_ALL_CPU_BT) { /* Temporary allow non-panic CPUs to write their backtraces. */ panic_triggering_all_cpu_backtrace = true; trigger_all_cpu_backtrace(); @@ -410,7 +382,7 @@ void panic(const char *fmt, ...) */ atomic_notifier_call_chain(&panic_notifier_list, 0, buf); - panic_print_sys_info(); + sys_info(panic_print); kmsg_dump_desc(KMSG_DUMP_PANIC, buf); diff --git a/lib/Makefile b/lib/Makefile index c38582f187dd..88d6228089a8 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -40,7 +40,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ earlycpio.o seq_buf.o siphash.o dec_and_lock.o \ nmi_backtrace.o win_minmax.o memcat_p.o \ - buildid.o objpool.o iomem_copy.o + buildid.o objpool.o iomem_copy.o sys_info.o lib-$(CONFIG_UNION_FIND) += union_find.o lib-$(CONFIG_PRINTK) += dump_stack.o diff --git a/lib/sys_info.c b/lib/sys_info.c new file mode 100644 index 000000000000..53031e5cb98e --- /dev/null +++ b/lib/sys_info.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include +#include +#include + +#include + +void sys_info(unsigned long si_mask) +{ + if (si_mask & SYS_INFO_TASKS) + show_state(); + + if (si_mask & SYS_INFO_MEM) + show_mem(); + + if (si_mask & SYS_INFO_TIMERS) + sysrq_timer_list_show(); + + if (si_mask & SYS_INFO_LOCKS) + debug_show_all_locks(); + + if (si_mask & SYS_INFO_FTRACE) + ftrace_dump(DUMP_ALL); + + if (si_mask & SYS_INFO_ALL_CPU_BT) + trigger_all_cpu_backtrace(); + + if (si_mask & SYS_INFO_BLOCKED_TASKS) + show_state_filter(TASK_UNINTERRUPTIBLE); +} -- cgit v1.2.3 From d747755917bf8ae08f490c3fe7d8e321afab8127 Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Thu, 3 Jul 2025 10:10:02 +0800 Subject: panic: add 'panic_sys_info' sysctl to take human readable string parameter Bitmap definition for 'panic_print' is hard to remember and decode. Add 'panic_sys_info='sysctl to take human readable string like "tasks,mem,timers,locks,ftrace,..." and translate it into bitmap. The detailed mapping is: SYS_INFO_TASKS "tasks" SYS_INFO_MEM "mem" SYS_INFO_TIMERS "timers" SYS_INFO_LOCKS "locks" SYS_INFO_FTRACE "ftrace" SYS_INFO_ALL_CPU_BT "all_bt" SYS_INFO_BLOCKED_TASKS "blocked_tasks" [nathan@kernel.org: add __maybe_unused to sys_info_avail] Link: https://lkml.kernel.org/r/20250708-fix-clang-sys_info_avail-warning-v1-1-60d239eacd64@kernel.org Link: https://lkml.kernel.org/r/20250703021004.42328-4-feng.tang@linux.alibaba.com Signed-off-by: Feng Tang Suggested-by: Petr Mladek Cc: John Ogness Cc: Jonathan Corbet Cc: Lance Yang Cc: "Paul E . McKenney" Cc: Steven Rostedt Cc: Nathan Chancellor Cc: Andy Shevchenko Signed-off-by: Andrew Morton --- Documentation/admin-guide/sysctl/kernel.rst | 18 ++++++ include/linux/sys_info.h | 8 +++ kernel/panic.c | 7 +++ lib/sys_info.c | 90 +++++++++++++++++++++++++++++ 4 files changed, 123 insertions(+) (limited to 'include/linux') diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index 0d08b7a2db2d..cccb06d1a6bf 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -899,6 +899,24 @@ So for example to print tasks and memory info on panic, user can:: echo 3 > /proc/sys/kernel/panic_print +panic_sys_info +============== + +A comma separated list of extra information to be dumped on panic, +for example, "tasks,mem,timers,...". It is a human readable alternative +to 'panic_print'. Possible values are: + +============= =================================================== +tasks print all tasks info +mem print system memory info +timer print timers info +lock print locks info if CONFIG_LOCKDEP is on +ftrace print ftrace buffer +all_bt print all CPUs backtrace (if available in the arch) +blocked_tasks print only tasks in uninterruptible (blocked) state +============= =================================================== + + panic_on_rcu_stall ================== diff --git a/include/linux/sys_info.h b/include/linux/sys_info.h index 53b7e27dbf2a..89d77dc4f2ed 100644 --- a/include/linux/sys_info.h +++ b/include/linux/sys_info.h @@ -2,6 +2,8 @@ #ifndef _LINUX_SYS_INFO_H #define _LINUX_SYS_INFO_H +#include + /* * SYS_INFO_PANIC_CONSOLE_REPLAY is for panic case only, as it needs special * handling which only fits panic case. @@ -16,5 +18,11 @@ #define SYS_INFO_BLOCKED_TASKS 0x00000080 void sys_info(unsigned long si_mask); +unsigned long sys_info_parse_param(char *str); +#ifdef CONFIG_SYSCTL +int sysctl_sys_info_handler(const struct ctl_table *ro_table, int write, + void *buffer, size_t *lenp, + loff_t *ppos); +#endif #endif /* _LINUX_SYS_INFO_H */ diff --git a/kernel/panic.c b/kernel/panic.c index cbb0681177b3..d7aa427dc23c 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -126,6 +126,13 @@ static const struct ctl_table kern_panic_table[] = { .mode = 0644, .proc_handler = proc_douintvec, }, + { + .procname = "panic_sys_info", + .data = &panic_print, + .maxlen = sizeof(panic_print), + .mode = 0644, + .proc_handler = sysctl_sys_info_handler, + }, }; static __init int kernel_panic_sysctls_init(void) diff --git a/lib/sys_info.c b/lib/sys_info.c index 53031e5cb98e..5bf503fd7ec1 100644 --- a/lib/sys_info.c +++ b/lib/sys_info.c @@ -3,10 +3,100 @@ #include #include #include +#include #include #include +struct sys_info_name { + unsigned long bit; + const char *name; +}; + +/* + * When 'si_names' gets updated, please make sure the 'sys_info_avail' + * below is updated accordingly. + */ +static const struct sys_info_name si_names[] = { + { SYS_INFO_TASKS, "tasks" }, + { SYS_INFO_MEM, "mem" }, + { SYS_INFO_TIMERS, "timers" }, + { SYS_INFO_LOCKS, "locks" }, + { SYS_INFO_FTRACE, "ftrace" }, + { SYS_INFO_ALL_CPU_BT, "all_bt" }, + { SYS_INFO_BLOCKED_TASKS, "blocked_tasks" }, +}; + +/* Expecting string like "xxx_sys_info=tasks,mem,timers,locks,ftrace,..." */ +unsigned long sys_info_parse_param(char *str) +{ + unsigned long si_bits = 0; + char *s, *name; + int i; + + s = str; + while ((name = strsep(&s, ",")) && *name) { + for (i = 0; i < ARRAY_SIZE(si_names); i++) { + if (!strcmp(name, si_names[i].name)) { + si_bits |= si_names[i].bit; + break; + } + } + } + + return si_bits; +} + +#ifdef CONFIG_SYSCTL + +static const char sys_info_avail[] __maybe_unused = "tasks,mem,timers,locks,ftrace,all_bt,blocked_tasks"; + +int sysctl_sys_info_handler(const struct ctl_table *ro_table, int write, + void *buffer, size_t *lenp, + loff_t *ppos) +{ + char names[sizeof(sys_info_avail) + 1]; + struct ctl_table table; + unsigned long *si_bits_global; + + si_bits_global = ro_table->data; + + if (write) { + unsigned long si_bits; + int ret; + + table = *ro_table; + table.data = names; + table.maxlen = sizeof(names); + ret = proc_dostring(&table, write, buffer, lenp, ppos); + if (ret) + return ret; + + si_bits = sys_info_parse_param(names); + /* The access to the global value is not synchronized. */ + WRITE_ONCE(*si_bits_global, si_bits); + return 0; + } else { + /* for 'read' operation */ + char *delim = ""; + int i, len = 0; + + for (i = 0; i < ARRAY_SIZE(si_names); i++) { + if (*si_bits_global & si_names[i].bit) { + len += scnprintf(names + len, sizeof(names) - len, + "%s%s", delim, si_names[i].name); + delim = ","; + } + } + + table = *ro_table; + table.data = names; + table.maxlen = sizeof(names); + return proc_dostring(&table, write, buffer, lenp, ppos); + } +} +#endif + void sys_info(unsigned long si_mask) { if (si_mask & SYS_INFO_TASKS) -- cgit v1.2.3 From ae2da51def76020fa16f53cd3446c00cafe41008 Mon Sep 17 00:00:00 2001 From: Lance Yang Date: Fri, 27 Jun 2025 15:29:22 +0800 Subject: locking/rwsem: make owner helpers globally available Patch series "extend hung task blocker tracking to rwsems". Inspired by mutex blocker tracking[1], and having already extended it to semaphores, let's now add support for reader-writer semaphores (rwsems). The approach is simple: when a task enters TASK_UNINTERRUPTIBLE while waiting for an rwsem, we just call hung_task_set_blocker(). The hung task detector can then query the rwsem's owner to identify the lock holder. Tracking works reliably for writers, as there can only be a single writer holding the lock, and its task struct is stored in the owner field. The main challenge lies with readers. The owner field points to only one of many concurrent readers, so we might lose track of the blocker if that specific reader unlocks, even while others remain. This is not a significant issue, however. In practice, long-lasting lock contention is almost always caused by a writer. Therefore, reliably tracking the writer is the primary goal of this patch series ;) With this change, the hung task detector can now show blocker task's info like below: [Fri Jun 27 15:21:34 2025] INFO: task cat:28631 blocked for more than 122 seconds. [Fri Jun 27 15:21:34 2025] Tainted: G S 6.16.0-rc3 #8 [Fri Jun 27 15:21:34 2025] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [Fri Jun 27 15:21:34 2025] task:cat state:D stack:0 pid:28631 tgid:28631 ppid:28501 task_flags:0x400000 flags:0x00004000 [Fri Jun 27 15:21:34 2025] Call Trace: [Fri Jun 27 15:21:34 2025] [Fri Jun 27 15:21:34 2025] __schedule+0x7c7/0x1930 [Fri Jun 27 15:21:34 2025] ? __pfx___schedule+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? policy_nodemask+0x215/0x340 [Fri Jun 27 15:21:34 2025] ? _raw_spin_lock_irq+0x8a/0xe0 [Fri Jun 27 15:21:34 2025] ? __pfx__raw_spin_lock_irq+0x10/0x10 [Fri Jun 27 15:21:34 2025] schedule+0x6a/0x180 [Fri Jun 27 15:21:34 2025] schedule_preempt_disabled+0x15/0x30 [Fri Jun 27 15:21:34 2025] rwsem_down_read_slowpath+0x55e/0xe10 [Fri Jun 27 15:21:34 2025] ? __pfx_rwsem_down_read_slowpath+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? __pfx___might_resched+0x10/0x10 [Fri Jun 27 15:21:34 2025] down_read+0xc9/0x230 [Fri Jun 27 15:21:34 2025] ? __pfx_down_read+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? __debugfs_file_get+0x14d/0x700 [Fri Jun 27 15:21:34 2025] ? __pfx___debugfs_file_get+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? handle_pte_fault+0x52a/0x710 [Fri Jun 27 15:21:34 2025] ? selinux_file_permission+0x3a9/0x590 [Fri Jun 27 15:21:34 2025] read_dummy_rwsem_read+0x4a/0x90 [Fri Jun 27 15:21:34 2025] full_proxy_read+0xff/0x1c0 [Fri Jun 27 15:21:34 2025] ? rw_verify_area+0x6d/0x410 [Fri Jun 27 15:21:34 2025] vfs_read+0x177/0xa50 [Fri Jun 27 15:21:34 2025] ? __pfx_vfs_read+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? fdget_pos+0x1cf/0x4c0 [Fri Jun 27 15:21:34 2025] ksys_read+0xfc/0x1d0 [Fri Jun 27 15:21:34 2025] ? __pfx_ksys_read+0x10/0x10 [Fri Jun 27 15:21:34 2025] do_syscall_64+0x66/0x2d0 [Fri Jun 27 15:21:34 2025] entry_SYSCALL_64_after_hwframe+0x76/0x7e [Fri Jun 27 15:21:34 2025] RIP: 0033:0x7f3f8faefb40 [Fri Jun 27 15:21:34 2025] RSP: 002b:00007ffdeda5ab98 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [Fri Jun 27 15:21:34 2025] RAX: ffffffffffffffda RBX: 0000000000010000 RCX: 00007f3f8faefb40 [Fri Jun 27 15:21:34 2025] RDX: 0000000000010000 RSI: 00000000010fa000 RDI: 0000000000000003 [Fri Jun 27 15:21:34 2025] RBP: 00000000010fa000 R08: 0000000000000000 R09: 0000000000010fff [Fri Jun 27 15:21:34 2025] R10: 00007ffdeda59fe0 R11: 0000000000000246 R12: 00000000010fa000 [Fri Jun 27 15:21:34 2025] R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000fff [Fri Jun 27 15:21:34 2025] [Fri Jun 27 15:21:34 2025] INFO: task cat:28631 blocked on an rw-semaphore likely owned by task cat:28630 [Fri Jun 27 15:21:34 2025] task:cat state:S stack:0 pid:28630 tgid:28630 ppid:28501 task_flags:0x400000 flags:0x00004000 [Fri Jun 27 15:21:34 2025] Call Trace: [Fri Jun 27 15:21:34 2025] [Fri Jun 27 15:21:34 2025] __schedule+0x7c7/0x1930 [Fri Jun 27 15:21:34 2025] ? __pfx___schedule+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? __mod_timer+0x304/0xa80 [Fri Jun 27 15:21:34 2025] schedule+0x6a/0x180 [Fri Jun 27 15:21:34 2025] schedule_timeout+0xfb/0x230 [Fri Jun 27 15:21:34 2025] ? __pfx_schedule_timeout+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? __pfx_process_timeout+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? down_write+0xc4/0x140 [Fri Jun 27 15:21:34 2025] msleep_interruptible+0xbe/0x150 [Fri Jun 27 15:21:34 2025] read_dummy_rwsem_write+0x54/0x90 [Fri Jun 27 15:21:34 2025] full_proxy_read+0xff/0x1c0 [Fri Jun 27 15:21:34 2025] ? rw_verify_area+0x6d/0x410 [Fri Jun 27 15:21:34 2025] vfs_read+0x177/0xa50 [Fri Jun 27 15:21:34 2025] ? __pfx_vfs_read+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? fdget_pos+0x1cf/0x4c0 [Fri Jun 27 15:21:34 2025] ksys_read+0xfc/0x1d0 [Fri Jun 27 15:21:34 2025] ? __pfx_ksys_read+0x10/0x10 [Fri Jun 27 15:21:34 2025] do_syscall_64+0x66/0x2d0 [Fri Jun 27 15:21:34 2025] entry_SYSCALL_64_after_hwframe+0x76/0x7e [Fri Jun 27 15:21:34 2025] RIP: 0033:0x7f8f288efb40 [Fri Jun 27 15:21:34 2025] RSP: 002b:00007ffffb631038 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [Fri Jun 27 15:21:34 2025] RAX: ffffffffffffffda RBX: 0000000000010000 RCX: 00007f8f288efb40 [Fri Jun 27 15:21:34 2025] RDX: 0000000000010000 RSI: 000000002a4b5000 RDI: 0000000000000003 [Fri Jun 27 15:21:34 2025] RBP: 000000002a4b5000 R08: 0000000000000000 R09: 0000000000010fff [Fri Jun 27 15:21:34 2025] R10: 00007ffffb630460 R11: 0000000000000246 R12: 000000002a4b5000 [Fri Jun 27 15:21:34 2025] R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000fff [Fri Jun 27 15:21:34 2025] This patch (of 3): In preparation for extending blocker tracking to support rwsems, make the rwsem_owner() and is_rwsem_reader_owned() helpers globally available for determining if the blocker is a writer or one of the readers. Additionally, a stale owner pointer in a reader-owned rwsem can lead to false positives in blocker tracking when CONFIG_DETECT_HUNG_TASK_BLOCKER is enabled. To mitigate this, clear the owner field on the reader unlock path, similar to what CONFIG_DEBUG_RWSEMS does. A NULL owner is better than a stale one for diagnostics. Link: https://lkml.kernel.org/r/20250627072924.36567-1-lance.yang@linux.dev Link: https://lkml.kernel.org/r/20250627072924.36567-2-lance.yang@linux.dev Link: https://lore.kernel.org/all/174046694331.2194069.15472952050240807469.stgit@mhiramat.tok.corp.google.com/ [1] Signed-off-by: Lance Yang Reviewed-by: Masami Hiramatsu (Google) Cc: Anna Schumaker Cc: Boqun Feng Cc: Ingo Molnar Cc: Joel Granados Cc: John Stultz Cc: Kent Overstreet Cc: Mingzhe Yang Cc: Peter Zijlstra Cc: Sergey Senozhatsky Cc: Steven Rostedt Cc: Tomasz Figa Cc: Waiman Long Cc: Will Deacon Cc: Yongliang Gao Cc: Zi Li Signed-off-by: Andrew Morton --- include/linux/rwsem.h | 12 ++++++++++++ kernel/locking/rwsem.c | 14 +++++++------- 2 files changed, 19 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index c8b543d428b0..544853bed5b9 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -132,6 +132,18 @@ static inline int rwsem_is_contended(struct rw_semaphore *sem) return !list_empty(&sem->wait_list); } +#if defined(CONFIG_DEBUG_RWSEMS) || defined(CONFIG_DETECT_HUNG_TASK_BLOCKER) +/* + * Return just the real task structure pointer of the owner + */ +extern struct task_struct *rwsem_owner(struct rw_semaphore *sem); + +/* + * Return true if the rwsem is owned by a reader. + */ +extern bool is_rwsem_reader_owned(struct rw_semaphore *sem); +#endif + #else /* !CONFIG_PREEMPT_RT */ #include diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 2ddb827e3bea..a310eb9896de 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -181,11 +181,11 @@ static inline void rwsem_set_reader_owned(struct rw_semaphore *sem) __rwsem_set_reader_owned(sem, current); } -#ifdef CONFIG_DEBUG_RWSEMS +#if defined(CONFIG_DEBUG_RWSEMS) || defined(CONFIG_DETECT_HUNG_TASK_BLOCKER) /* * Return just the real task structure pointer of the owner */ -static inline struct task_struct *rwsem_owner(struct rw_semaphore *sem) +struct task_struct *rwsem_owner(struct rw_semaphore *sem) { return (struct task_struct *) (atomic_long_read(&sem->owner) & ~RWSEM_OWNER_FLAGS_MASK); @@ -194,7 +194,7 @@ static inline struct task_struct *rwsem_owner(struct rw_semaphore *sem) /* * Return true if the rwsem is owned by a reader. */ -static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem) +bool is_rwsem_reader_owned(struct rw_semaphore *sem) { /* * Check the count to see if it is write-locked. @@ -207,10 +207,10 @@ static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem) } /* - * With CONFIG_DEBUG_RWSEMS configured, it will make sure that if there - * is a task pointer in owner of a reader-owned rwsem, it will be the - * real owner or one of the real owners. The only exception is when the - * unlock is done by up_read_non_owner(). + * With CONFIG_DEBUG_RWSEMS or CONFIG_DETECT_HUNG_TASK_BLOCKER configured, + * it will make sure that the owner field of a reader-owned rwsem either + * points to a real reader-owner(s) or gets cleared. The only exception is + * when the unlock is done by up_read_non_owner(). */ static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem) { -- cgit v1.2.3 From 77da18de55ac6417e48905bec8b3c66f023b15a9 Mon Sep 17 00:00:00 2001 From: Lance Yang Date: Fri, 27 Jun 2025 15:29:23 +0800 Subject: hung_task: extend hung task blocker tracking to rwsems Inspired by mutex blocker tracking[1], and having already extended it to semaphores, let's now add support for reader-writer semaphores (rwsems). The approach is simple: when a task enters TASK_UNINTERRUPTIBLE while waiting for an rwsem, we just call hung_task_set_blocker(). The hung task detector can then query the rwsem's owner to identify the lock holder. Tracking works reliably for writers, as there can only be a single writer holding the lock, and its task struct is stored in the owner field. The main challenge lies with readers. The owner field points to only one of many concurrent readers, so we might lose track of the blocker if that specific reader unlocks, even while others remain. This is not a significant issue, however. In practice, long-lasting lock contention is almost always caused by a writer. Therefore, reliably tracking the writer is the primary goal of this patch series ;) With this change, the hung task detector can now show blocker task's info like below: [Fri Jun 27 15:21:34 2025] INFO: task cat:28631 blocked for more than 122 seconds. [Fri Jun 27 15:21:34 2025] Tainted: G S 6.16.0-rc3 #8 [Fri Jun 27 15:21:34 2025] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [Fri Jun 27 15:21:34 2025] task:cat state:D stack:0 pid:28631 tgid:28631 ppid:28501 task_flags:0x400000 flags:0x00004000 [Fri Jun 27 15:21:34 2025] Call Trace: [Fri Jun 27 15:21:34 2025] [Fri Jun 27 15:21:34 2025] __schedule+0x7c7/0x1930 [Fri Jun 27 15:21:34 2025] ? __pfx___schedule+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? policy_nodemask+0x215/0x340 [Fri Jun 27 15:21:34 2025] ? _raw_spin_lock_irq+0x8a/0xe0 [Fri Jun 27 15:21:34 2025] ? __pfx__raw_spin_lock_irq+0x10/0x10 [Fri Jun 27 15:21:34 2025] schedule+0x6a/0x180 [Fri Jun 27 15:21:34 2025] schedule_preempt_disabled+0x15/0x30 [Fri Jun 27 15:21:34 2025] rwsem_down_read_slowpath+0x55e/0xe10 [Fri Jun 27 15:21:34 2025] ? __pfx_rwsem_down_read_slowpath+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? __pfx___might_resched+0x10/0x10 [Fri Jun 27 15:21:34 2025] down_read+0xc9/0x230 [Fri Jun 27 15:21:34 2025] ? __pfx_down_read+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? __debugfs_file_get+0x14d/0x700 [Fri Jun 27 15:21:34 2025] ? __pfx___debugfs_file_get+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? handle_pte_fault+0x52a/0x710 [Fri Jun 27 15:21:34 2025] ? selinux_file_permission+0x3a9/0x590 [Fri Jun 27 15:21:34 2025] read_dummy_rwsem_read+0x4a/0x90 [Fri Jun 27 15:21:34 2025] full_proxy_read+0xff/0x1c0 [Fri Jun 27 15:21:34 2025] ? rw_verify_area+0x6d/0x410 [Fri Jun 27 15:21:34 2025] vfs_read+0x177/0xa50 [Fri Jun 27 15:21:34 2025] ? __pfx_vfs_read+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? fdget_pos+0x1cf/0x4c0 [Fri Jun 27 15:21:34 2025] ksys_read+0xfc/0x1d0 [Fri Jun 27 15:21:34 2025] ? __pfx_ksys_read+0x10/0x10 [Fri Jun 27 15:21:34 2025] do_syscall_64+0x66/0x2d0 [Fri Jun 27 15:21:34 2025] entry_SYSCALL_64_after_hwframe+0x76/0x7e [Fri Jun 27 15:21:34 2025] RIP: 0033:0x7f3f8faefb40 [Fri Jun 27 15:21:34 2025] RSP: 002b:00007ffdeda5ab98 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [Fri Jun 27 15:21:34 2025] RAX: ffffffffffffffda RBX: 0000000000010000 RCX: 00007f3f8faefb40 [Fri Jun 27 15:21:34 2025] RDX: 0000000000010000 RSI: 00000000010fa000 RDI: 0000000000000003 [Fri Jun 27 15:21:34 2025] RBP: 00000000010fa000 R08: 0000000000000000 R09: 0000000000010fff [Fri Jun 27 15:21:34 2025] R10: 00007ffdeda59fe0 R11: 0000000000000246 R12: 00000000010fa000 [Fri Jun 27 15:21:34 2025] R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000fff [Fri Jun 27 15:21:34 2025] [Fri Jun 27 15:21:34 2025] INFO: task cat:28631 blocked on an rw-semaphore likely owned by task cat:28630 [Fri Jun 27 15:21:34 2025] task:cat state:S stack:0 pid:28630 tgid:28630 ppid:28501 task_flags:0x400000 flags:0x00004000 [Fri Jun 27 15:21:34 2025] Call Trace: [Fri Jun 27 15:21:34 2025] [Fri Jun 27 15:21:34 2025] __schedule+0x7c7/0x1930 [Fri Jun 27 15:21:34 2025] ? __pfx___schedule+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? __mod_timer+0x304/0xa80 [Fri Jun 27 15:21:34 2025] schedule+0x6a/0x180 [Fri Jun 27 15:21:34 2025] schedule_timeout+0xfb/0x230 [Fri Jun 27 15:21:34 2025] ? __pfx_schedule_timeout+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? __pfx_process_timeout+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? down_write+0xc4/0x140 [Fri Jun 27 15:21:34 2025] msleep_interruptible+0xbe/0x150 [Fri Jun 27 15:21:34 2025] read_dummy_rwsem_write+0x54/0x90 [Fri Jun 27 15:21:34 2025] full_proxy_read+0xff/0x1c0 [Fri Jun 27 15:21:34 2025] ? rw_verify_area+0x6d/0x410 [Fri Jun 27 15:21:34 2025] vfs_read+0x177/0xa50 [Fri Jun 27 15:21:34 2025] ? __pfx_vfs_read+0x10/0x10 [Fri Jun 27 15:21:34 2025] ? fdget_pos+0x1cf/0x4c0 [Fri Jun 27 15:21:34 2025] ksys_read+0xfc/0x1d0 [Fri Jun 27 15:21:34 2025] ? __pfx_ksys_read+0x10/0x10 [Fri Jun 27 15:21:34 2025] do_syscall_64+0x66/0x2d0 [Fri Jun 27 15:21:34 2025] entry_SYSCALL_64_after_hwframe+0x76/0x7e [Fri Jun 27 15:21:34 2025] RIP: 0033:0x7f8f288efb40 [Fri Jun 27 15:21:34 2025] RSP: 002b:00007ffffb631038 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [Fri Jun 27 15:21:34 2025] RAX: ffffffffffffffda RBX: 0000000000010000 RCX: 00007f8f288efb40 [Fri Jun 27 15:21:34 2025] RDX: 0000000000010000 RSI: 000000002a4b5000 RDI: 0000000000000003 [Fri Jun 27 15:21:34 2025] RBP: 000000002a4b5000 R08: 0000000000000000 R09: 0000000000010fff [Fri Jun 27 15:21:34 2025] R10: 00007ffffb630460 R11: 0000000000000246 R12: 000000002a4b5000 [Fri Jun 27 15:21:34 2025] R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000fff [Fri Jun 27 15:21:34 2025] [1] https://lore.kernel.org/all/174046694331.2194069.15472952050240807469.stgit@mhiramat.tok.corp.google.com/ Link: https://lkml.kernel.org/r/20250627072924.36567-3-lance.yang@linux.dev Signed-off-by: Lance Yang Suggested-by: Masami Hiramatsu (Google) Reviewed-by: Masami Hiramatsu (Google) Cc: Anna Schumaker Cc: Boqun Feng Cc: Ingo Molnar Cc: Joel Granados Cc: John Stultz Cc: Kent Overstreet Cc: Mingzhe Yang Cc: Peter Zijlstra Cc: Sergey Senozhatsky Cc: Steven Rostedt Cc: Tomasz Figa Cc: Waiman Long Cc: Will Deacon Cc: Yongliang Gao Cc: Zi Li Signed-off-by: Andrew Morton --- include/linux/hung_task.h | 18 +++++++++--------- kernel/hung_task.c | 29 +++++++++++++++++++++++++---- kernel/locking/rwsem.c | 17 ++++++++++++++++- 3 files changed, 50 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hung_task.h b/include/linux/hung_task.h index 1bc2b3244613..34e615c76ca5 100644 --- a/include/linux/hung_task.h +++ b/include/linux/hung_task.h @@ -21,17 +21,17 @@ * type. * * Type encoding: - * 00 - Blocked on mutex (BLOCKER_TYPE_MUTEX) - * 01 - Blocked on semaphore (BLOCKER_TYPE_SEM) - * 10 - Blocked on rt-mutex (BLOCKER_TYPE_RTMUTEX) - * 11 - Blocked on rw-semaphore (BLOCKER_TYPE_RWSEM) + * 00 - Blocked on mutex (BLOCKER_TYPE_MUTEX) + * 01 - Blocked on semaphore (BLOCKER_TYPE_SEM) + * 10 - Blocked on rw-semaphore as READER (BLOCKER_TYPE_RWSEM_READER) + * 11 - Blocked on rw-semaphore as WRITER (BLOCKER_TYPE_RWSEM_WRITER) */ -#define BLOCKER_TYPE_MUTEX 0x00UL -#define BLOCKER_TYPE_SEM 0x01UL -#define BLOCKER_TYPE_RTMUTEX 0x02UL -#define BLOCKER_TYPE_RWSEM 0x03UL +#define BLOCKER_TYPE_MUTEX 0x00UL +#define BLOCKER_TYPE_SEM 0x01UL +#define BLOCKER_TYPE_RWSEM_READER 0x02UL +#define BLOCKER_TYPE_RWSEM_WRITER 0x03UL -#define BLOCKER_TYPE_MASK 0x03UL +#define BLOCKER_TYPE_MASK 0x03UL #ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER static inline void hung_task_set_blocker(void *lock, unsigned long type) diff --git a/kernel/hung_task.c b/kernel/hung_task.c index d2432df2b905..8708a1205f82 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -23,6 +23,7 @@ #include #include #include +#include #include @@ -100,6 +101,7 @@ static void debug_show_blocker(struct task_struct *task) { struct task_struct *g, *t; unsigned long owner, blocker, blocker_type; + const char *rwsem_blocked_by, *rwsem_blocked_as; RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "No rcu lock held"); @@ -111,12 +113,20 @@ static void debug_show_blocker(struct task_struct *task) switch (blocker_type) { case BLOCKER_TYPE_MUTEX: - owner = mutex_get_owner( - (struct mutex *)hung_task_blocker_to_lock(blocker)); + owner = mutex_get_owner(hung_task_blocker_to_lock(blocker)); break; case BLOCKER_TYPE_SEM: - owner = sem_last_holder( - (struct semaphore *)hung_task_blocker_to_lock(blocker)); + owner = sem_last_holder(hung_task_blocker_to_lock(blocker)); + break; + case BLOCKER_TYPE_RWSEM_READER: + case BLOCKER_TYPE_RWSEM_WRITER: + owner = (unsigned long)rwsem_owner( + hung_task_blocker_to_lock(blocker)); + rwsem_blocked_as = (blocker_type == BLOCKER_TYPE_RWSEM_READER) ? + "reader" : "writer"; + rwsem_blocked_by = is_rwsem_reader_owned( + hung_task_blocker_to_lock(blocker)) ? + "reader" : "writer"; break; default: WARN_ON_ONCE(1); @@ -134,6 +144,11 @@ static void debug_show_blocker(struct task_struct *task) pr_err("INFO: task %s:%d is blocked on a semaphore, but the last holder is not found.\n", task->comm, task->pid); break; + case BLOCKER_TYPE_RWSEM_READER: + case BLOCKER_TYPE_RWSEM_WRITER: + pr_err("INFO: task %s:%d is blocked on an rw-semaphore, but the owner is not found.\n", + task->comm, task->pid); + break; } return; } @@ -152,6 +167,12 @@ static void debug_show_blocker(struct task_struct *task) pr_err("INFO: task %s:%d blocked on a semaphore likely last held by task %s:%d\n", task->comm, task->pid, t->comm, t->pid); break; + case BLOCKER_TYPE_RWSEM_READER: + case BLOCKER_TYPE_RWSEM_WRITER: + pr_err("INFO: task %s:%d <%s> blocked on an rw-semaphore likely owned by task %s:%d <%s>\n", + task->comm, task->pid, rwsem_blocked_as, t->comm, + t->pid, rwsem_blocked_by); + break; } sched_show_task(t); return; diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index a310eb9896de..92c6332da401 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #ifndef CONFIG_PREEMPT_RT @@ -1065,10 +1066,13 @@ queue: wake_up_q(&wake_q); trace_contention_begin(sem, LCB_F_READ); + set_current_state(state); + + if (state == TASK_UNINTERRUPTIBLE) + hung_task_set_blocker(sem, BLOCKER_TYPE_RWSEM_READER); /* wait to be given the lock */ for (;;) { - set_current_state(state); if (!smp_load_acquire(&waiter.task)) { /* Matches rwsem_mark_wake()'s smp_store_release(). */ break; @@ -1083,8 +1087,12 @@ queue: } schedule_preempt_disabled(); lockevent_inc(rwsem_sleep_reader); + set_current_state(state); } + if (state == TASK_UNINTERRUPTIBLE) + hung_task_clear_blocker(); + __set_current_state(TASK_RUNNING); lockevent_inc(rwsem_rlock); trace_contention_end(sem, 0); @@ -1146,6 +1154,9 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) set_current_state(state); trace_contention_begin(sem, LCB_F_WRITE); + if (state == TASK_UNINTERRUPTIBLE) + hung_task_set_blocker(sem, BLOCKER_TYPE_RWSEM_WRITER); + for (;;) { if (rwsem_try_write_lock(sem, &waiter)) { /* rwsem_try_write_lock() implies ACQUIRE on success */ @@ -1179,6 +1190,10 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) trylock_again: raw_spin_lock_irq(&sem->wait_lock); } + + if (state == TASK_UNINTERRUPTIBLE) + hung_task_clear_blocker(); + __set_current_state(TASK_RUNNING); raw_spin_unlock_irq(&sem->wait_lock); lockevent_inc(rwsem_wlock); -- cgit v1.2.3 From b3d5fd6f82dde8c906dc2a587003a44252ae5eae Mon Sep 17 00:00:00 2001 From: Kuan-Wei Chiu Date: Fri, 6 Jun 2025 21:47:56 +0800 Subject: lib/math/gcd: use static key to select implementation at runtime Patch series "Optimize GCD performance on RISC-V by selecting implementation at runtime", v3. The current implementation of gcd() selects between the binary GCD and the odd-even GCD algorithm at compile time, depending on whether CONFIG_CPU_NO_EFFICIENT_FFS is set. On platforms like RISC-V, however, this compile-time decision can be misleading: even when the compiler emits ctz instructions based on the assumption that they are efficient (as is the case when CONFIG_RISCV_ISA_ZBB is enabled), the actual hardware may lack support for the Zbb extension. In such cases, ffs() falls back to a software implementation at runtime, making the binary GCD algorithm significantly slower than the odd-even variant. To address this, we introduce a static key to allow runtime selection between the binary and odd-even GCD implementations. On RISC-V, the kernel now checks for Zbb support during boot. If Zbb is unavailable, the static key is disabled so that gcd() consistently uses the more efficient odd-even algorithm in that scenario. Additionally, to further reduce code size, we select CONFIG_CPU_NO_EFFICIENT_FFS automatically when CONFIG_RISCV_ISA_ZBB is not enabled, avoiding compilation of the unused binary GCD implementation entirely on systems where it would never be executed. This series ensures that the most efficient GCD algorithm is used in practice and avoids compiling unnecessary code based on hardware capabilities and kernel configuration. This patch (of 3): On platforms like RISC-V, the compiler may generate hardware FFS instructions even if the underlying CPU does not actually support them. Currently, the GCD implementation is chosen at compile time based on CONFIG_CPU_NO_EFFICIENT_FFS, which can result in suboptimal behavior on such systems. Introduce a static key, efficient_ffs_key, to enable runtime selection between the binary GCD (using ffs) and the odd-even GCD implementation. This allows the kernel to default to the faster binary GCD when FFS is efficient, while retaining the ability to fall back when needed. Link: https://lkml.kernel.org/r/20250606134758.1308400-1-visitorckw@gmail.com Link: https://lkml.kernel.org/r/20250606134758.1308400-2-visitorckw@gmail.com Co-developed-by: Yu-Chun Lin Signed-off-by: Yu-Chun Lin Signed-off-by: Kuan-Wei Chiu Cc: Albert Ou Cc: Ching-Chun (Jim) Huang Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Alexandre Ghiti Signed-off-by: Andrew Morton --- include/linux/gcd.h | 3 +++ lib/math/gcd.c | 27 +++++++++++++++------------ 2 files changed, 18 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gcd.h b/include/linux/gcd.h index cb572677fd7f..616e81a7f7e3 100644 --- a/include/linux/gcd.h +++ b/include/linux/gcd.h @@ -3,6 +3,9 @@ #define _GCD_H #include +#include + +DECLARE_STATIC_KEY_TRUE(efficient_ffs_key); unsigned long gcd(unsigned long a, unsigned long b) __attribute_const__; diff --git a/lib/math/gcd.c b/lib/math/gcd.c index e3b042214d1b..62efca6787ae 100644 --- a/lib/math/gcd.c +++ b/lib/math/gcd.c @@ -11,22 +11,16 @@ * has decent hardware division. */ +DEFINE_STATIC_KEY_TRUE(efficient_ffs_key); + #if !defined(CONFIG_CPU_NO_EFFICIENT_FFS) /* If __ffs is available, the even/odd algorithm benchmarks slower. */ -/** - * gcd - calculate and return the greatest common divisor of 2 unsigned longs - * @a: first value - * @b: second value - */ -unsigned long gcd(unsigned long a, unsigned long b) +static unsigned long binary_gcd(unsigned long a, unsigned long b) { unsigned long r = a | b; - if (!a || !b) - return r; - b >>= __ffs(b); if (b == 1) return r & -r; @@ -44,9 +38,15 @@ unsigned long gcd(unsigned long a, unsigned long b) } } -#else +#endif /* If normalization is done by loops, the even/odd algorithm is a win. */ + +/** + * gcd - calculate and return the greatest common divisor of 2 unsigned longs + * @a: first value + * @b: second value + */ unsigned long gcd(unsigned long a, unsigned long b) { unsigned long r = a | b; @@ -54,6 +54,11 @@ unsigned long gcd(unsigned long a, unsigned long b) if (!a || !b) return r; +#if !defined(CONFIG_CPU_NO_EFFICIENT_FFS) + if (static_branch_likely(&efficient_ffs_key)) + return binary_gcd(a, b); +#endif + /* Isolate lsbit of r */ r &= -r; @@ -80,6 +85,4 @@ unsigned long gcd(unsigned long a, unsigned long b) } } -#endif - EXPORT_SYMBOL_GPL(gcd); -- cgit v1.2.3 From 34b1cb4ec286603127aa8c4191ea527eb8dd3567 Mon Sep 17 00:00:00 2001 From: Venkata Prasad Potturu Date: Tue, 15 Jul 2025 17:40:41 +0530 Subject: soundwire: amd: Add support for acp7.2 platform Add soundwire support for acp7.2 platform. Signed-off-by: Venkata Prasad Potturu Link: https://lore.kernel.org/r/20250715121048.1795607-1-venkataprasad.potturu@amd.com Signed-off-by: Vinod Koul --- drivers/soundwire/amd_manager.c | 4 ++++ include/linux/soundwire/sdw_amd.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c index d4e62c383b12..3632838f3ed9 100644 --- a/drivers/soundwire/amd_manager.c +++ b/drivers/soundwire/amd_manager.c @@ -499,6 +499,7 @@ static int amd_sdw_port_params(struct sdw_bus *bus, struct sdw_port_params *p_pa break; case ACP70_PCI_REV_ID: case ACP71_PCI_REV_ID: + case ACP72_PCI_REV_ID: frame_fmt_reg = acp70_sdw_dp_reg[p_params->num].frame_fmt_reg; break; default: @@ -551,6 +552,7 @@ static int amd_sdw_transport_params(struct sdw_bus *bus, break; case ACP70_PCI_REV_ID: case ACP71_PCI_REV_ID: + case ACP72_PCI_REV_ID: frame_fmt_reg = acp70_sdw_dp_reg[params->port_num].frame_fmt_reg; sample_int_reg = acp70_sdw_dp_reg[params->port_num].sample_int_reg; hctrl_dp0_reg = acp70_sdw_dp_reg[params->port_num].hctrl_dp0_reg; @@ -614,6 +616,7 @@ static int amd_sdw_port_enable(struct sdw_bus *bus, break; case ACP70_PCI_REV_ID: case ACP71_PCI_REV_ID: + case ACP72_PCI_REV_ID: lane_ctrl_ch_en_reg = acp70_sdw_dp_reg[enable_ch->port_num].lane_ctrl_ch_en_reg; break; default: @@ -1038,6 +1041,7 @@ static int amd_sdw_manager_probe(struct platform_device *pdev) break; case ACP70_PCI_REV_ID: case ACP71_PCI_REV_ID: + case ACP72_PCI_REV_ID: amd_manager->num_dout_ports = AMD_ACP70_SDW_MAX_TX_PORTS; amd_manager->num_din_ports = AMD_ACP70_SDW_MAX_RX_PORTS; break; diff --git a/include/linux/soundwire/sdw_amd.h b/include/linux/soundwire/sdw_amd.h index 6b839987f14c..fe31773d5210 100644 --- a/include/linux/soundwire/sdw_amd.h +++ b/include/linux/soundwire/sdw_amd.h @@ -30,6 +30,7 @@ #define ACP63_PCI_REV_ID 0x63 #define ACP70_PCI_REV_ID 0x70 #define ACP71_PCI_REV_ID 0x71 +#define ACP72_PCI_REV_ID 0x72 struct acp_sdw_pdata { u16 instance; -- cgit v1.2.3 From 2fb4af5ea3c735a205d97de10f044f809b20af51 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 18 Jul 2025 10:14:49 +0200 Subject: NFS: track active delegations per-server The active delegation watermark was added to avoid overloading servers. Track the active delegation per-server instead of globally so that clients talking to multiple servers aren't limited by the global limit. Signed-off-by: Christoph Hellwig Reviewed-by: Jeff Layton Link: https://lore.kernel.org/r/20250718081509.2607553-5-hch@lst.de Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 1 + fs/nfs/delegation.c | 35 +++++++++++++++++++---------------- include/linux/nfs_fs_sb.h | 1 + 3 files changed, 21 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 47258dc3af70..e13eb429b8b5 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -1005,6 +1005,7 @@ struct nfs_server *nfs_alloc_server(void) INIT_LIST_HEAD(&server->ss_src_copies); atomic_set(&server->active, 0); + atomic_long_set(&server->nr_active_delegations, 0); server->io_stats = nfs_alloc_iostats(); if (!server->io_stats) { diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 5f85966d7709..ea96f77e38c2 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -27,7 +27,6 @@ #define NFS_DEFAULT_DELEGATION_WATERMARK (5000U) -static atomic_long_t nfs_active_delegations; static unsigned nfs_delegation_watermark = NFS_DEFAULT_DELEGATION_WATERMARK; module_param_named(delegation_watermark, nfs_delegation_watermark, uint, 0644); @@ -38,11 +37,12 @@ static void __nfs_free_delegation(struct nfs_delegation *delegation) kfree_rcu(delegation, rcu); } -static void nfs_mark_delegation_revoked(struct nfs_delegation *delegation) +static void nfs_mark_delegation_revoked(struct nfs_server *server, + struct nfs_delegation *delegation) { if (!test_and_set_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) { delegation->stateid.type = NFS4_INVALID_STATEID_TYPE; - atomic_long_dec(&nfs_active_delegations); + atomic_long_dec(&server->nr_active_delegations); if (!test_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) nfs_clear_verifier_delegated(delegation->inode); } @@ -60,9 +60,10 @@ static void nfs_put_delegation(struct nfs_delegation *delegation) __nfs_free_delegation(delegation); } -static void nfs_free_delegation(struct nfs_delegation *delegation) +static void nfs_free_delegation(struct nfs_server *server, + struct nfs_delegation *delegation) { - nfs_mark_delegation_revoked(delegation); + nfs_mark_delegation_revoked(server, delegation); nfs_put_delegation(delegation); } @@ -261,7 +262,7 @@ void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred, } clear_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags); if (test_and_clear_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) - atomic_long_inc(&nfs_active_delegations); + atomic_long_inc(&NFS_SERVER(inode)->nr_active_delegations); spin_unlock(&delegation->lock); rcu_read_unlock(); put_cred(oldcred); @@ -413,7 +414,8 @@ nfs_update_delegation_cred(struct nfs_delegation *delegation, } static void -nfs_update_inplace_delegation(struct nfs_delegation *delegation, +nfs_update_inplace_delegation(struct nfs_server *server, + struct nfs_delegation *delegation, const struct nfs_delegation *update) { if (nfs4_stateid_is_newer(&update->stateid, &delegation->stateid)) { @@ -426,7 +428,7 @@ nfs_update_inplace_delegation(struct nfs_delegation *delegation, nfs_update_delegation_cred(delegation, update->cred); /* smp_mb__before_atomic() is implicit due to xchg() */ clear_bit(NFS_DELEGATION_REVOKED, &delegation->flags); - atomic_long_inc(&nfs_active_delegations); + atomic_long_inc(&server->nr_active_delegations); } } } @@ -481,7 +483,7 @@ int nfs_inode_set_delegation(struct inode *inode, const struct cred *cred, if (nfs4_stateid_match_other(&old_delegation->stateid, &delegation->stateid)) { spin_lock(&old_delegation->lock); - nfs_update_inplace_delegation(old_delegation, + nfs_update_inplace_delegation(server, old_delegation, delegation); spin_unlock(&old_delegation->lock); goto out; @@ -530,7 +532,7 @@ add_new: rcu_assign_pointer(nfsi->delegation, delegation); delegation = NULL; - atomic_long_inc(&nfs_active_delegations); + atomic_long_inc(&server->nr_active_delegations); trace_nfs4_set_delegation(inode, type); @@ -544,7 +546,7 @@ out: __nfs_free_delegation(delegation); if (freeme != NULL) { nfs_do_return_delegation(inode, freeme, 0); - nfs_free_delegation(freeme); + nfs_free_delegation(server, freeme); } return status; } @@ -756,7 +758,7 @@ void nfs_inode_evict_delegation(struct inode *inode) set_bit(NFS_DELEGATION_RETURNING, &delegation->flags); set_bit(NFS_DELEGATION_INODE_FREEING, &delegation->flags); nfs_do_return_delegation(inode, delegation, 1); - nfs_free_delegation(delegation); + nfs_free_delegation(NFS_SERVER(inode), delegation); } } @@ -842,7 +844,8 @@ void nfs4_inode_return_delegation_on_close(struct inode *inode) if (!delegation) goto out; if (test_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags) || - atomic_long_read(&nfs_active_delegations) >= nfs_delegation_watermark) { + atomic_long_read(&NFS_SERVER(inode)->nr_active_delegations) >= + nfs_delegation_watermark) { spin_lock(&delegation->lock); if (delegation->inode && list_empty(&NFS_I(inode)->open_files) && @@ -1018,7 +1021,7 @@ static void nfs_revoke_delegation(struct inode *inode, } spin_unlock(&delegation->lock); } - nfs_mark_delegation_revoked(delegation); + nfs_mark_delegation_revoked(NFS_SERVER(inode), delegation); ret = true; out: rcu_read_unlock(); @@ -1050,7 +1053,7 @@ void nfs_delegation_mark_returned(struct inode *inode, delegation->stateid.seqid = stateid->seqid; } - nfs_mark_delegation_revoked(delegation); + nfs_mark_delegation_revoked(NFS_SERVER(inode), delegation); clear_bit(NFS_DELEGATION_RETURNING, &delegation->flags); spin_unlock(&delegation->lock); if (nfs_detach_delegation(NFS_I(inode), delegation, NFS_SERVER(inode))) @@ -1270,7 +1273,7 @@ restart: if (delegation != NULL) { if (nfs_detach_delegation(NFS_I(inode), delegation, server) != NULL) - nfs_free_delegation(delegation); + nfs_free_delegation(server, delegation); /* Match nfs_start_delegation_return_locked */ nfs_put_delegation(delegation); } diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index d2d36711a119..a9b44f12623f 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -254,6 +254,7 @@ struct nfs_server { struct list_head state_owners_lru; struct list_head layouts; struct list_head delegations; + atomic_long_t nr_active_delegations; struct list_head ss_copies; struct list_head ss_src_copies; -- cgit v1.2.3 From f5b3108e6a14418b120a3c38ca589b8d6cf87627 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 18 Jul 2025 10:14:50 +0200 Subject: NFS: use a hash table for delegation lookup nfs_delegation_find_inode currently has to walk the entire list of delegations per inode, which can become pretty large, and can become even larger when increasing the delegation watermark. Add a hash table to speed up the delegation lookup, sized as a fraction of the delegation watermark. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20250718081509.2607553-6-hch@lst.de Signed-off-by: Trond Myklebust --- fs/nfs/delegation.c | 28 +++++++++++++++++++++++++++- fs/nfs/delegation.h | 3 +++ fs/nfs/nfs4client.c | 5 +++++ fs/nfs/nfs4proc.c | 22 +++++++++++++++++++++- include/linux/nfs_fs_sb.h | 2 ++ 5 files changed, 58 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index ea96f77e38c2..9d3a5f29f17f 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -30,6 +30,13 @@ static unsigned nfs_delegation_watermark = NFS_DEFAULT_DELEGATION_WATERMARK; module_param_named(delegation_watermark, nfs_delegation_watermark, uint, 0644); +static struct hlist_head *nfs_delegation_hash(struct nfs_server *server, + const struct nfs_fh *fhandle) +{ + return server->delegation_hash_table + + (nfs_fhandle_hash(fhandle) & server->delegation_hash_mask); +} + static void __nfs_free_delegation(struct nfs_delegation *delegation) { put_cred(delegation->cred); @@ -367,6 +374,7 @@ nfs_detach_delegation_locked(struct nfs_inode *nfsi, spin_unlock(&delegation->lock); return NULL; } + hlist_del_init_rcu(&delegation->hash); list_del_rcu(&delegation->super_list); delegation->inode = NULL; rcu_assign_pointer(nfsi->delegation, NULL); @@ -529,6 +537,8 @@ add_new: spin_unlock(&inode->i_lock); list_add_tail_rcu(&delegation->super_list, &server->delegations); + hlist_add_head_rcu(&delegation->hash, + nfs_delegation_hash(server, &NFS_I(inode)->fh)); rcu_assign_pointer(nfsi->delegation, delegation); delegation = NULL; @@ -1166,11 +1176,12 @@ static struct inode * nfs_delegation_find_inode_server(struct nfs_server *server, const struct nfs_fh *fhandle) { + struct hlist_head *head = nfs_delegation_hash(server, fhandle); struct nfs_delegation *delegation; struct super_block *freeme = NULL; struct inode *res = NULL; - list_for_each_entry_rcu(delegation, &server->delegations, super_list) { + hlist_for_each_entry_rcu(delegation, head, hash) { spin_lock(&delegation->lock); if (delegation->inode != NULL && !test_bit(NFS_DELEGATION_REVOKED, &delegation->flags) && @@ -1577,3 +1588,18 @@ out: rcu_read_unlock(); return ret; } + +int nfs4_delegation_hash_alloc(struct nfs_server *server) +{ + int delegation_buckets, i; + + delegation_buckets = roundup_pow_of_two(nfs_delegation_watermark / 16); + server->delegation_hash_mask = delegation_buckets - 1; + server->delegation_hash_table = kmalloc_array(delegation_buckets, + sizeof(*server->delegation_hash_table), GFP_KERNEL); + if (!server->delegation_hash_table) + return -ENOMEM; + for (i = 0; i < delegation_buckets; i++) + INIT_HLIST_HEAD(&server->delegation_hash_table[i]); + return 0; +} diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index 8ff5ab9c5c25..08ec2e9c68a4 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -14,6 +14,7 @@ * NFSv4 delegation */ struct nfs_delegation { + struct hlist_node hash; struct list_head super_list; const struct cred *cred; struct inode *inode; @@ -123,4 +124,6 @@ static inline int nfs_have_delegated_mtime(struct inode *inode) NFS_DELEGATION_FLAG_TIME); } +int nfs4_delegation_hash_alloc(struct nfs_server *server); + #endif diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 5943a192f36b..2ea98f1f116f 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -802,6 +802,7 @@ static void nfs4_destroy_server(struct nfs_server *server) unset_pnfs_layoutdriver(server); nfs4_purge_state_owners(server, &freeme); nfs4_free_state_owners(&freeme); + kfree(server->delegation_hash_table); } /* @@ -1096,6 +1097,10 @@ static int nfs4_server_common_setup(struct nfs_server *server, { int error; + error = nfs4_delegation_hash_alloc(server); + if (error) + return error; + /* data servers support only a subset of NFSv4.1 */ if (is_ds_only_client(server->nfs_client)) return -EPROTONOSUPPORT; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ef2077e185b6..d8bebd757af3 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -10967,6 +10967,26 @@ static const struct inode_operations nfs4_file_inode_operations = { .listxattr = nfs4_listxattr, }; +static struct nfs_server *nfs4_clone_server(struct nfs_server *source, + struct nfs_fh *fh, struct nfs_fattr *fattr, + rpc_authflavor_t flavor) +{ + struct nfs_server *server; + int error; + + server = nfs_clone_server(source, fh, fattr, flavor); + if (IS_ERR(server)) + return server; + + error = nfs4_delegation_hash_alloc(server); + if (error) { + nfs_free_server(server); + return ERR_PTR(error); + } + + return server; +} + const struct nfs_rpc_ops nfs_v4_clientops = { .version = 4, /* protocol version */ .dentry_ops = &nfs4_dentry_operations, @@ -11019,7 +11039,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .init_client = nfs4_init_client, .free_client = nfs4_free_client, .create_server = nfs4_create_server, - .clone_server = nfs_clone_server, + .clone_server = nfs4_clone_server, .discover_trunking = nfs4_discover_trunking, .enable_swap = nfs4_enable_swap, .disable_swap = nfs4_disable_swap, diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index a9b44f12623f..d30c0245031c 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -255,6 +255,8 @@ struct nfs_server { struct list_head layouts; struct list_head delegations; atomic_long_t nr_active_delegations; + unsigned int delegation_hash_mask; + struct hlist_head *delegation_hash_table; struct list_head ss_copies; struct list_head ss_src_copies; -- cgit v1.2.3 From ad38574a8e8223361e265973fbd87013ea058c5d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 8 Jul 2025 18:03:33 +0100 Subject: f2fs: Pass a folio to ADDRS_PER_PAGE() All callers now have a folio so pass it in. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/data.c | 2 +- fs/f2fs/file.c | 18 +++++++++--------- fs/f2fs/recovery.c | 4 ++-- fs/f2fs/segment.c | 2 +- include/linux/f2fs_fs.h | 2 +- 5 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 0e261caf2f91..8a2414ce39ff 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1588,7 +1588,7 @@ next_dnode: start_pgofs = pgofs; prealloc = 0; last_ofs_in_node = ofs_in_node = dn.ofs_in_node; - end_offset = ADDRS_PER_PAGE(&dn.node_folio->page, inode); + end_offset = ADDRS_PER_PAGE(dn.node_folio, inode); next_block: blkaddr = f2fs_data_blkaddr(&dn); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 04a5a1089320..60618c52ba50 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -489,7 +489,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) } } - end_offset = ADDRS_PER_PAGE(&dn.node_folio->page, inode); + end_offset = ADDRS_PER_PAGE(dn.node_folio, inode); /* find data/hole in dnode block */ for (; dn.ofs_in_node < end_offset; @@ -814,7 +814,7 @@ int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock) goto out; } - count = ADDRS_PER_PAGE(&dn.node_folio->page, inode); + count = ADDRS_PER_PAGE(dn.node_folio, inode); count -= dn.ofs_in_node; f2fs_bug_on(sbi, count < 0); @@ -1233,7 +1233,7 @@ int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end) return err; } - end_offset = ADDRS_PER_PAGE(&dn.node_folio->page, inode); + end_offset = ADDRS_PER_PAGE(dn.node_folio, inode); count = min(end_offset - dn.ofs_in_node, pg_end - pg_start); f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset); @@ -1332,7 +1332,7 @@ next_dnode: goto next; } - done = min((pgoff_t)ADDRS_PER_PAGE(&dn.node_folio->page, inode) - + done = min((pgoff_t)ADDRS_PER_PAGE(dn.node_folio, inode) - dn.ofs_in_node, len); for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) { *blkaddr = f2fs_data_blkaddr(&dn); @@ -1421,7 +1421,7 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode, } ilen = min((pgoff_t) - ADDRS_PER_PAGE(&dn.node_folio->page, dst_inode) - + ADDRS_PER_PAGE(dn.node_folio, dst_inode) - dn.ofs_in_node, len - i); do { dn.data_blkaddr = f2fs_data_blkaddr(&dn); @@ -1717,7 +1717,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, goto out; } - end_offset = ADDRS_PER_PAGE(&dn.node_folio->page, inode); + end_offset = ADDRS_PER_PAGE(dn.node_folio, inode); end = min(pg_end, end_offset - dn.ofs_in_node + index); ret = f2fs_do_zero_range(&dn, index, end); @@ -3885,7 +3885,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg) break; } - end_offset = ADDRS_PER_PAGE(&dn.node_folio->page, inode); + end_offset = ADDRS_PER_PAGE(dn.node_folio, inode); count = min(end_offset - dn.ofs_in_node, last_idx - page_idx); count = round_up(count, fi->i_cluster_size); @@ -4063,7 +4063,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) break; } - end_offset = ADDRS_PER_PAGE(&dn.node_folio->page, inode); + end_offset = ADDRS_PER_PAGE(dn.node_folio, inode); count = min(end_offset - dn.ofs_in_node, last_idx - page_idx); count = round_up(count, fi->i_cluster_size); @@ -4227,7 +4227,7 @@ static int f2fs_sec_trim_file(struct file *filp, unsigned long arg) goto out; } - end_offset = ADDRS_PER_PAGE(&dn.node_folio->page, inode); + end_offset = ADDRS_PER_PAGE(dn.node_folio, inode); count = min(end_offset - dn.ofs_in_node, pg_end - index); for (i = 0; i < count; i++, index++, dn.ofs_in_node++) { struct block_device *cur_bdev; diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 5a45d0d1f05c..894b27b0329d 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -527,7 +527,7 @@ got_it: nid = le32_to_cpu(sum.nid); ofs_in_node = le16_to_cpu(sum.ofs_in_node); - max_addrs = ADDRS_PER_PAGE(&dn->node_folio->page, dn->inode); + max_addrs = ADDRS_PER_PAGE(dn->node_folio, dn->inode); if (ofs_in_node >= max_addrs) { f2fs_err(sbi, "Inconsistent ofs_in_node:%u in summary, ino:%lu, nid:%u, max:%u", ofs_in_node, dn->inode->i_ino, nid, max_addrs); @@ -649,7 +649,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, /* step 3: recover data indices */ start = f2fs_start_bidx_of_node(ofs_of_node(folio), inode); - end = start + ADDRS_PER_PAGE(&folio->page, inode); + end = start + ADDRS_PER_PAGE(folio, inode); set_new_dnode(&dn, inode, NULL, NULL, 0); retry_dn: diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 2a6dcfba911f..909637873ff7 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -334,7 +334,7 @@ static int __f2fs_commit_atomic_write(struct inode *inode) goto next; } - blen = min((pgoff_t)ADDRS_PER_PAGE(&dn.node_folio->page, cow_inode), + blen = min((pgoff_t)ADDRS_PER_PAGE(dn.node_folio, cow_inode), len); index = off; for (i = 0; i < blen; i++, dn.ofs_in_node++, index++) { diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 5206d63b3386..25857877eaec 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -268,7 +268,7 @@ struct node_footer { /* Node IDs in an Indirect Block */ #define NIDS_PER_BLOCK ((F2FS_BLKSIZE - sizeof(struct node_footer)) / sizeof(__le32)) -#define ADDRS_PER_PAGE(page, inode) (addrs_per_page(inode, IS_INODE(page))) +#define ADDRS_PER_PAGE(folio, inode) (addrs_per_page(inode, IS_INODE(&folio->page))) #define NODE_DIR1_BLOCK (DEF_ADDRS_PER_INODE + 1) #define NODE_DIR2_BLOCK (DEF_ADDRS_PER_INODE + 2) -- cgit v1.2.3 From a5f3be6e652a7beaaf6c482bc013b64129a5d239 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 8 Jul 2025 18:03:34 +0100 Subject: f2fs: Pass a folio to IS_INODE() All callers now have a folio so pass it in. Also make it const to help the compiler. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/f2fs.h | 6 +++--- fs/f2fs/file.c | 2 +- fs/f2fs/gc.c | 2 +- fs/f2fs/inline.c | 2 +- fs/f2fs/inode.c | 2 +- fs/f2fs/node.c | 14 ++++++-------- fs/f2fs/recovery.c | 8 ++++---- include/linux/f2fs_fs.h | 2 +- 8 files changed, 18 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 3933327d8cc3..09ddc0626dfe 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3019,9 +3019,9 @@ static inline void f2fs_radix_tree_insert(struct radix_tree_root *root, #define RAW_IS_INODE(p) ((p)->footer.nid == (p)->footer.ino) -static inline bool IS_INODE(struct page *page) +static inline bool IS_INODE(const struct folio *folio) { - struct f2fs_node *p = F2FS_NODE(page); + struct f2fs_node *p = F2FS_NODE(&folio->page); return RAW_IS_INODE(p); } @@ -3041,7 +3041,7 @@ static inline int f2fs_has_extra_attr(struct inode *inode); static inline unsigned int get_dnode_base(struct inode *inode, struct folio *node_folio) { - if (!IS_INODE(&node_folio->page)) + if (!IS_INODE(node_folio)) return 0; return inode ? get_extra_isize(inode) : diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 60618c52ba50..36b32757d5b9 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -819,7 +819,7 @@ int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock) count -= dn.ofs_in_node; f2fs_bug_on(sbi, count < 0); - if (dn.ofs_in_node || IS_INODE(&dn.node_folio->page)) { + if (dn.ofs_in_node || IS_INODE(dn.node_folio)) { f2fs_truncate_data_blocks_range(&dn, count); free_from += count; } diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 781b955cbb77..c1d4ecbd2505 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1162,7 +1162,7 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, return false; } - if (IS_INODE(&node_folio->page)) { + if (IS_INODE(node_folio)) { base = offset_in_addr(F2FS_INODE(node_folio)); max_addrs = DEF_ADDRS_PER_INODE; } else { diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 9851310cdb87..51adc43d5a5c 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -305,7 +305,7 @@ int f2fs_recover_inline_data(struct inode *inode, struct folio *nfolio) * x o -> remove data blocks, and then recover inline_data * x x -> recover data blocks */ - if (IS_INODE(&nfolio->page)) + if (IS_INODE(nfolio)) ri = F2FS_INODE(nfolio); if (f2fs_has_inline_data(inode) && diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index a8f64d206d19..dd3b43c24831 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -124,7 +124,7 @@ bool f2fs_enable_inode_chksum(struct f2fs_sb_info *sbi, struct folio *folio) if (!f2fs_sb_has_inode_chksum(sbi)) return false; - if (!IS_INODE(&folio->page) || !(ri->i_inline & F2FS_EXTRA_ATTR)) + if (!IS_INODE(folio) || !(ri->i_inline & F2FS_EXTRA_ATTR)) return false; if (!F2FS_FITS_IN_INODE(ri, le16_to_cpu(ri->i_extra_isize), diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index b56e627e0b56..908a1eb9c415 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -973,7 +973,7 @@ static int truncate_dnode(struct dnode_of_data *dn) else if (IS_ERR(folio)) return PTR_ERR(folio); - if (IS_INODE(&folio->page) || ino_of_node(folio) != dn->inode->i_ino) { + if (IS_INODE(folio) || ino_of_node(folio) != dn->inode->i_ino) { f2fs_err(sbi, "incorrect node reference, ino: %lu, nid: %u, ino_of_node: %u", dn->inode->i_ino, dn->nid, ino_of_node(folio)); set_sbi_flag(sbi, SBI_NEED_FSCK); @@ -1474,10 +1474,8 @@ static int sanity_check_node_footer(struct f2fs_sb_info *sbi, struct folio *folio, pgoff_t nid, enum node_type ntype) { - struct page *page = &folio->page; - if (unlikely(nid != nid_of_node(folio) || - (ntype == NODE_TYPE_INODE && !IS_INODE(page)) || + (ntype == NODE_TYPE_INODE && !IS_INODE(folio)) || (ntype == NODE_TYPE_XATTR && !f2fs_has_xattr_block(ofs_of_node(folio))) || time_to_inject(sbi, FAULT_INCONSISTENT_FOOTER))) { @@ -1867,7 +1865,7 @@ continue_unlock: if (!atomic || folio == last_folio) { set_fsync_mark(folio, 1); percpu_counter_inc(&sbi->rf_node_block_count); - if (IS_INODE(&folio->page)) { + if (IS_INODE(folio)) { if (is_inode_flag_set(inode, FI_DIRTY_INODE)) f2fs_update_inode(inode, folio); @@ -1976,7 +1974,7 @@ void f2fs_flush_inline_data(struct f2fs_sb_info *sbi) for (i = 0; i < nr_folios; i++) { struct folio *folio = fbatch.folios[i]; - if (!IS_INODE(&folio->page)) + if (!IS_INODE(folio)) continue; folio_lock(folio); @@ -2077,7 +2075,7 @@ continue_unlock: } /* flush dirty inode */ - if (IS_INODE(&folio->page) && flush_dirty_inode(folio)) + if (IS_INODE(folio) && flush_dirty_inode(folio)) goto lock_node; write_node: f2fs_folio_wait_writeback(folio, NODE, true, true); @@ -2213,7 +2211,7 @@ static bool f2fs_dirty_node_folio(struct address_space *mapping, if (!folio_test_uptodate(folio)) folio_mark_uptodate(folio); #ifdef CONFIG_F2FS_CHECK_FS - if (IS_INODE(&folio->page)) + if (IS_INODE(folio)) f2fs_inode_chksum_set(F2FS_M_SB(mapping), folio); #endif if (filemap_dirty_folio(mapping, folio)) { diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 894b27b0329d..4cb3a91801b4 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -437,7 +437,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, bool quota_inode = false; if (!check_only && - IS_INODE(&folio->page) && + IS_INODE(folio) && is_dent_dnode(folio)) { err = f2fs_recover_inode_page(sbi, folio); if (err) { @@ -463,7 +463,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, } entry->blkaddr = blkaddr; - if (IS_INODE(&folio->page) && is_dent_dnode(folio)) + if (IS_INODE(folio) && is_dent_dnode(folio)) entry->last_dentry = blkaddr; next: /* check next segment */ @@ -628,7 +628,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, int err = 0, recovered = 0; /* step 1: recover xattr */ - if (IS_INODE(&folio->page)) { + if (IS_INODE(folio)) { err = f2fs_recover_inline_xattr(inode, folio); if (err) goto out; @@ -821,7 +821,7 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list, * In this case, we can lose the latest inode(x). * So, call recover_inode for the inode update. */ - if (IS_INODE(&folio->page)) { + if (IS_INODE(folio)) { err = recover_inode(entry->inode, folio); if (err) { f2fs_folio_put(folio, true); diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 25857877eaec..2f8b8bfc0e73 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -268,7 +268,7 @@ struct node_footer { /* Node IDs in an Indirect Block */ #define NIDS_PER_BLOCK ((F2FS_BLKSIZE - sizeof(struct node_footer)) / sizeof(__le32)) -#define ADDRS_PER_PAGE(folio, inode) (addrs_per_page(inode, IS_INODE(&folio->page))) +#define ADDRS_PER_PAGE(folio, inode) (addrs_per_page(inode, IS_INODE(folio))) #define NODE_DIR1_BLOCK (DEF_ADDRS_PER_INODE + 1) #define NODE_DIR2_BLOCK (DEF_ADDRS_PER_INODE + 2) -- cgit v1.2.3 From a824388d911927b2a82bf7dcfd7cef6ee45c8b43 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 8 Jul 2025 18:03:36 +0100 Subject: f2fs: Use a folio in f2fs_is_cp_guaranteed() Convert the passed page to a folio and use it throughout. Removes a use of fscrypt_is_bounce_page(), which we're trying to remove. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/data.c | 11 ++++++----- fs/f2fs/f2fs.h | 2 +- include/linux/fscrypt.h | 10 ++++++---- 3 files changed, 13 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index f3e11f5672ec..c1fc8c7b1256 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -47,14 +47,15 @@ void f2fs_destroy_bioset(void) bioset_exit(&f2fs_bioset); } -bool f2fs_is_cp_guaranteed(struct page *page) +bool f2fs_is_cp_guaranteed(const struct page *page) { - struct address_space *mapping = page_folio(page)->mapping; + const struct folio *folio = page_folio(page); + struct address_space *mapping = folio->mapping; struct inode *inode; struct f2fs_sb_info *sbi; - if (fscrypt_is_bounce_page(page)) - return page_private_gcing(fscrypt_pagecache_page(page)); + if (fscrypt_is_bounce_folio(folio)) + return folio_test_f2fs_gcing(fscrypt_pagecache_folio(folio)); inode = mapping->host; sbi = F2FS_I_SB(inode); @@ -65,7 +66,7 @@ bool f2fs_is_cp_guaranteed(struct page *page) return true; if ((S_ISREG(inode->i_mode) && IS_NOQUOTA(inode)) || - page_private_gcing(page)) + folio_test_f2fs_gcing(folio)) return true; return false; } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 0e607305e308..be9b7a0120a9 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3990,7 +3990,7 @@ void f2fs_init_ckpt_req_control(struct f2fs_sb_info *sbi); */ int __init f2fs_init_bioset(void); void f2fs_destroy_bioset(void); -bool f2fs_is_cp_guaranteed(struct page *page); +bool f2fs_is_cp_guaranteed(const struct page *page); int f2fs_init_bio_entry_cache(void); void f2fs_destroy_bio_entry_cache(void); void f2fs_submit_read_bio(struct f2fs_sb_info *sbi, struct bio *bio, diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 56fad33043d5..8d9127a0fdb3 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -332,12 +332,13 @@ static inline struct page *fscrypt_pagecache_page(struct page *bounce_page) return (struct page *)page_private(bounce_page); } -static inline bool fscrypt_is_bounce_folio(struct folio *folio) +static inline bool fscrypt_is_bounce_folio(const struct folio *folio) { return folio->mapping == NULL; } -static inline struct folio *fscrypt_pagecache_folio(struct folio *bounce_folio) +static inline +struct folio *fscrypt_pagecache_folio(const struct folio *bounce_folio) { return bounce_folio->private; } @@ -518,12 +519,13 @@ static inline struct page *fscrypt_pagecache_page(struct page *bounce_page) return ERR_PTR(-EINVAL); } -static inline bool fscrypt_is_bounce_folio(struct folio *folio) +static inline bool fscrypt_is_bounce_folio(const struct folio *folio) { return false; } -static inline struct folio *fscrypt_pagecache_folio(struct folio *bounce_folio) +static inline +struct folio *fscrypt_pagecache_folio(const struct folio *bounce_folio) { WARN_ON_ONCE(1); return ERR_PTR(-EINVAL); -- cgit v1.2.3 From e612423be33465d2b9822bf09e03d4e6c165e384 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 8 Jul 2025 18:34:04 +0100 Subject: cpu/hotplug: Remove unused cpuhp_state CPUHP_PCI_XGENE_DEAD Now that the XGene MSI driver has been mostly rewritten and doesn't use the CPU hotplug infrastructure, CPUHP_PCI_XGENE_DEAD is unused. Remove it to reduce the size of cpuhp_hp_states[]. Signed-off-by: Marc Zyngier Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20250708173404.1278635-14-maz@kernel.org --- include/linux/cpuhotplug.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index df366ee15456..eaca70eb6136 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -90,7 +90,6 @@ enum cpuhp_state { CPUHP_RADIX_DEAD, CPUHP_PAGE_ALLOC, CPUHP_NET_DEV_DEAD, - CPUHP_PCI_XGENE_DEAD, CPUHP_IOMMU_IOVA_DEAD, CPUHP_AP_ARM_CACHE_B15_RAC_DEAD, CPUHP_PADATA_DEAD, -- cgit v1.2.3 From 07c3f391bcb217b6949b49785ccb5fee02be21fe Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 2 Jul 2025 14:36:57 -0400 Subject: tracing: Remove EVENT_FILE_FL_SOFT_MODE flag When soft disabling of trace events was first created, it needed to have a way to know if a file had a user that was using it with soft disabled (for triggers that need to enable or disable events from a context that can not really enable or disable the event, it would set SOFT_DISABLED to state it is disabled). The flag SOFT_MODE was used to denote that an event had a user that would enable or disable it via the SOFT_DISABLED flag. Commit 1cf4c0732db3c ("tracing: Modify soft-mode only if there's no other referrer") fixed a bug where if two users were using the SOFT_DISABLED flag the accounting would get messed up as the SOFT_MODE flag could only handle one user. That commit added the sm_ref counter which kept track of how many users were using the event in "soft mode". This made the SOFT_MODE flag redundant as it should only be set if the sm_ref counter is non zero. Remove the SOFT_MODE flag and just use the sm_ref counter to know the event is in soft mode or not. This makes the code a bit simpler. Link: https://lore.kernel.org/all/20250702111908.03759998@batman.local.home/ Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Gabriele Paoloni Link: https://lore.kernel.org/20250702143657.18dd1882@batman.local.home Signed-off-by: Steven Rostedt (Google) --- include/linux/trace_events.h | 3 --- kernel/trace/trace_events.c | 24 ++++++++++++------------ 2 files changed, 12 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index fa9cf4292dff..04307a19cde3 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -480,7 +480,6 @@ enum { EVENT_FILE_FL_RECORDED_TGID_BIT, EVENT_FILE_FL_FILTERED_BIT, EVENT_FILE_FL_NO_SET_FILTER_BIT, - EVENT_FILE_FL_SOFT_MODE_BIT, EVENT_FILE_FL_SOFT_DISABLED_BIT, EVENT_FILE_FL_TRIGGER_MODE_BIT, EVENT_FILE_FL_TRIGGER_COND_BIT, @@ -618,7 +617,6 @@ extern int __kprobe_event_add_fields(struct dynevent_cmd *cmd, ...); * RECORDED_TGID - The tgids should be recorded at sched_switch * FILTERED - The event has a filter attached * NO_SET_FILTER - Set when filter has error and is to be ignored - * SOFT_MODE - The event is enabled/disabled by SOFT_DISABLED * SOFT_DISABLED - When set, do not trace the event (even though its * tracepoint may be enabled) * TRIGGER_MODE - When set, invoke the triggers associated with the event @@ -633,7 +631,6 @@ enum { EVENT_FILE_FL_RECORDED_TGID = (1 << EVENT_FILE_FL_RECORDED_TGID_BIT), EVENT_FILE_FL_FILTERED = (1 << EVENT_FILE_FL_FILTERED_BIT), EVENT_FILE_FL_NO_SET_FILTER = (1 << EVENT_FILE_FL_NO_SET_FILTER_BIT), - EVENT_FILE_FL_SOFT_MODE = (1 << EVENT_FILE_FL_SOFT_MODE_BIT), EVENT_FILE_FL_SOFT_DISABLED = (1 << EVENT_FILE_FL_SOFT_DISABLED_BIT), EVENT_FILE_FL_TRIGGER_MODE = (1 << EVENT_FILE_FL_TRIGGER_MODE_BIT), EVENT_FILE_FL_TRIGGER_COND = (1 << EVENT_FILE_FL_TRIGGER_COND_BIT), diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 120531268abf..0980f4def360 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -768,6 +768,7 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file, { struct trace_event_call *call = file->event_call; struct trace_array *tr = file->tr; + bool soft_mode = atomic_read(&file->sm_ref) != 0; int ret = 0; int disable; @@ -782,7 +783,7 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file, * is set we do not want the event to be enabled before we * clear the bit. * - * When soft_disable is not set but the SOFT_MODE flag is, + * When soft_disable is not set but the soft_mode is, * we do nothing. Do not disable the tracepoint, otherwise * "soft enable"s (clearing the SOFT_DISABLED bit) wont work. */ @@ -790,11 +791,11 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file, if (atomic_dec_return(&file->sm_ref) > 0) break; disable = file->flags & EVENT_FILE_FL_SOFT_DISABLED; - clear_bit(EVENT_FILE_FL_SOFT_MODE_BIT, &file->flags); + soft_mode = false; /* Disable use of trace_buffered_event */ trace_buffered_event_disable(); } else - disable = !(file->flags & EVENT_FILE_FL_SOFT_MODE); + disable = !soft_mode; if (disable && (file->flags & EVENT_FILE_FL_ENABLED)) { clear_bit(EVENT_FILE_FL_ENABLED_BIT, &file->flags); @@ -812,8 +813,8 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file, WARN_ON_ONCE(ret); } - /* If in SOFT_MODE, just set the SOFT_DISABLE_BIT, else clear it */ - if (file->flags & EVENT_FILE_FL_SOFT_MODE) + /* If in soft mode, just set the SOFT_DISABLE_BIT, else clear it */ + if (soft_mode) set_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags); else clear_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags); @@ -823,7 +824,7 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file, * When soft_disable is set and enable is set, we want to * register the tracepoint for the event, but leave the event * as is. That means, if the event was already enabled, we do - * nothing (but set SOFT_MODE). If the event is disabled, we + * nothing (but set soft_mode). If the event is disabled, we * set SOFT_DISABLED before enabling the event tracepoint, so * it still seems to be disabled. */ @@ -832,7 +833,7 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file, else { if (atomic_inc_return(&file->sm_ref) > 1) break; - set_bit(EVENT_FILE_FL_SOFT_MODE_BIT, &file->flags); + soft_mode = true; /* Enable use of trace_buffered_event */ trace_buffered_event_enable(); } @@ -840,7 +841,7 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file, if (!(file->flags & EVENT_FILE_FL_ENABLED)) { bool cmd = false, tgid = false; - /* Keep the event disabled, when going to SOFT_MODE. */ + /* Keep the event disabled, when going to soft mode. */ if (soft_disable) set_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags); @@ -1792,8 +1793,7 @@ event_enable_read(struct file *filp, char __user *ubuf, size_t cnt, !(flags & EVENT_FILE_FL_SOFT_DISABLED)) strcpy(buf, "1"); - if (flags & EVENT_FILE_FL_SOFT_DISABLED || - flags & EVENT_FILE_FL_SOFT_MODE) + if (atomic_read(&file->sm_ref) != 0) strcat(buf, "*"); strcat(buf, "\n"); @@ -3584,7 +3584,7 @@ static int probe_remove_event_call(struct trace_event_call *call) continue; /* * We can't rely on ftrace_event_enable_disable(enable => 0) - * we are going to do, EVENT_FILE_FL_SOFT_MODE can suppress + * we are going to do, soft mode can suppress * TRACE_REG_UNREGISTER. */ if (file->flags & EVENT_FILE_FL_ENABLED) @@ -3997,7 +3997,7 @@ static int free_probe_data(void *data) edata->ref--; if (!edata->ref) { - /* Remove the SOFT_MODE flag */ + /* Remove soft mode */ __ftrace_event_enable_disable(edata->file, 0, 1); trace_event_put_ref(edata->file->event_call); kfree(edata); -- cgit v1.2.3 From 1c3b002c6bf684b445a7107609979bca5f21bc03 Mon Sep 17 00:00:00 2001 From: Frank Li Date: Thu, 10 Jul 2025 15:13:49 -0400 Subject: PCI: endpoint: Add RC-to-EP doorbell support using platform MSI controller Implement the doorbell feature by mapping the EP's MSI interrupt controller message address to a dedicated BAR. The EPF driver should pass the actual message data to be written to the message address by the host through implementation-specific logic. Signed-off-by: Frank Li [mani: minor code cleanups and reworded commit message] Signed-off-by: Manivannan Sadhasivam [bhelgaas: fix kernel-doc] Signed-off-by: Bjorn Helgaas Tested-by: Niklas Cassel Link: https://patch.msgid.link/20250710-ep-msi-v21-3-57683fc7fb25@nxp.com --- drivers/pci/endpoint/Kconfig | 8 ++++ drivers/pci/endpoint/Makefile | 1 + drivers/pci/endpoint/pci-ep-msi.c | 92 +++++++++++++++++++++++++++++++++++++++ include/linux/pci-ep-msi.h | 28 ++++++++++++ include/linux/pci-epf.h | 15 +++++++ 5 files changed, 144 insertions(+) create mode 100644 drivers/pci/endpoint/pci-ep-msi.c create mode 100644 include/linux/pci-ep-msi.h (limited to 'include/linux') diff --git a/drivers/pci/endpoint/Kconfig b/drivers/pci/endpoint/Kconfig index 1c5d82eb57d4..8dad291be8b8 100644 --- a/drivers/pci/endpoint/Kconfig +++ b/drivers/pci/endpoint/Kconfig @@ -28,6 +28,14 @@ config PCI_ENDPOINT_CONFIGFS configure the endpoint function and used to bind the function with an endpoint controller. +config PCI_ENDPOINT_MSI_DOORBELL + bool "PCI Endpoint MSI Doorbell Support" + depends on PCI_ENDPOINT && GENERIC_MSI_IRQ + help + This enables the EP's MSI interrupt controller to function as a + doorbell. The RC can trigger doorbell in EP by writing data to a + dedicated BAR, which the EP maps to the controller's message address. + source "drivers/pci/endpoint/functions/Kconfig" endmenu diff --git a/drivers/pci/endpoint/Makefile b/drivers/pci/endpoint/Makefile index 95b2fe47e3b0..b4869d52053a 100644 --- a/drivers/pci/endpoint/Makefile +++ b/drivers/pci/endpoint/Makefile @@ -6,3 +6,4 @@ obj-$(CONFIG_PCI_ENDPOINT_CONFIGFS) += pci-ep-cfs.o obj-$(CONFIG_PCI_ENDPOINT) += pci-epc-core.o pci-epf-core.o\ pci-epc-mem.o functions/ +obj-$(CONFIG_PCI_ENDPOINT_MSI_DOORBELL) += pci-ep-msi.o diff --git a/drivers/pci/endpoint/pci-ep-msi.c b/drivers/pci/endpoint/pci-ep-msi.c new file mode 100644 index 000000000000..95a47ce155ac --- /dev/null +++ b/drivers/pci/endpoint/pci-ep-msi.c @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCI Endpoint *Controller* (EPC) MSI library + * + * Copyright (C) 2025 NXP + * Author: Frank Li + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static void pci_epf_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg) +{ + struct pci_epc *epc; + struct pci_epf *epf; + + epc = pci_epc_get(dev_name(msi_desc_to_dev(desc))); + if (!epc) + return; + + epf = list_first_entry_or_null(&epc->pci_epf, struct pci_epf, list); + + if (epf && epf->db_msg && desc->msi_index < epf->num_db) + memcpy(&epf->db_msg[desc->msi_index].msg, msg, sizeof(*msg)); + + pci_epc_put(epc); +} + +int pci_epf_alloc_doorbell(struct pci_epf *epf, u16 num_db) +{ + struct pci_epc *epc = epf->epc; + struct device *dev = &epf->dev; + struct irq_domain *domain; + void *msg; + int ret; + int i; + + /* TODO: Multi-EPF support */ + if (list_first_entry_or_null(&epc->pci_epf, struct pci_epf, list) != epf) { + dev_err(dev, "MSI doorbell doesn't support multiple EPF\n"); + return -EINVAL; + } + + domain = of_msi_map_get_device_domain(epc->dev.parent, 0, + DOMAIN_BUS_PLATFORM_MSI); + if (!domain) { + dev_err(dev, "Can't find MSI domain for EPC\n"); + return -ENODEV; + } + + dev_set_msi_domain(epc->dev.parent, domain); + + msg = kcalloc(num_db, sizeof(struct pci_epf_doorbell_msg), GFP_KERNEL); + if (!msg) + return -ENOMEM; + + epf->num_db = num_db; + epf->db_msg = msg; + + ret = platform_device_msi_init_and_alloc_irqs(epc->dev.parent, num_db, + pci_epf_write_msi_msg); + if (ret) { + dev_err(dev, "Failed to allocate MSI\n"); + kfree(msg); + return ret; + } + + for (i = 0; i < num_db; i++) + epf->db_msg[i].virq = msi_get_virq(epc->dev.parent, i); + + return ret; +} +EXPORT_SYMBOL_GPL(pci_epf_alloc_doorbell); + +void pci_epf_free_doorbell(struct pci_epf *epf) +{ + platform_device_msi_free_irqs_all(epf->epc->dev.parent); + + kfree(epf->db_msg); + epf->db_msg = NULL; + epf->num_db = 0; +} +EXPORT_SYMBOL_GPL(pci_epf_free_doorbell); diff --git a/include/linux/pci-ep-msi.h b/include/linux/pci-ep-msi.h new file mode 100644 index 000000000000..7c5db90f9620 --- /dev/null +++ b/include/linux/pci-ep-msi.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * PCI Endpoint *Function* side MSI header file + * + * Copyright (C) 2024 NXP + * Author: Frank Li + */ + +#ifndef __PCI_EP_MSI__ +#define __PCI_EP_MSI__ + +struct pci_epf; + +#ifdef CONFIG_PCI_ENDPOINT_MSI_DOORBELL +int pci_epf_alloc_doorbell(struct pci_epf *epf, u16 nums); +void pci_epf_free_doorbell(struct pci_epf *epf); +#else +static inline int pci_epf_alloc_doorbell(struct pci_epf *epf, u16 nums) +{ + return -ENODATA; +} + +static inline void pci_epf_free_doorbell(struct pci_epf *epf) +{ +} +#endif /* CONFIG_GENERIC_MSI_IRQ */ + +#endif /* __PCI_EP_MSI__ */ diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index 749cee0bcf2c..52e07602f08e 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -12,6 +12,7 @@ #include #include #include +#include #include struct pci_epf; @@ -128,6 +129,16 @@ struct pci_epf_bar { int flags; }; +/** + * struct pci_epf_doorbell_msg - represents doorbell message + * @msg: MSI message + * @virq: IRQ number of this doorbell MSI message + */ +struct pci_epf_doorbell_msg { + struct msi_msg msg; + int virq; +}; + /** * struct pci_epf - represents the PCI EPF device * @dev: the PCI EPF device @@ -155,6 +166,8 @@ struct pci_epf_bar { * @vfunction_num_map: bitmap to manage virtual function number * @pci_vepf: list of virtual endpoint functions associated with this function * @event_ops: callbacks for capturing the EPC events + * @db_msg: data for MSI from RC side + * @num_db: number of doorbells */ struct pci_epf { struct device dev; @@ -185,6 +198,8 @@ struct pci_epf { unsigned long vfunction_num_map; struct list_head pci_vepf; const struct pci_epc_event_ops *event_ops; + struct pci_epf_doorbell_msg *db_msg; + u16 num_db; }; /** -- cgit v1.2.3 From 4ff4252a2355f585c5cad8dc959ff1097300aa47 Mon Sep 17 00:00:00 2001 From: Frank Li Date: Thu, 10 Jul 2025 15:13:51 -0400 Subject: PCI: endpoint: Add pci_epf_align_inbound_addr() helper for inbound address alignment Add pci_epf_align_inbound_addr() to align the inbound addresses according to PCI BAR alignment requirements. The aligned base address and offset are returned via 'base' and 'off' parameters. Signed-off-by: Frank Li [mani: reworded kernel-doc and commit message] Signed-off-by: Manivannan Sadhasivam Signed-off-by: Bjorn Helgaas Tested-by: Niklas Cassel Link: https://patch.msgid.link/20250710-ep-msi-v21-5-57683fc7fb25@nxp.com --- drivers/pci/endpoint/pci-epf-core.c | 38 +++++++++++++++++++++++++++++++++++++ include/linux/pci-epf.h | 3 +++ 2 files changed, 41 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c index 577a9e490115..09b90e1631d5 100644 --- a/drivers/pci/endpoint/pci-epf-core.c +++ b/drivers/pci/endpoint/pci-epf-core.c @@ -477,6 +477,44 @@ struct pci_epf *pci_epf_create(const char *name) } EXPORT_SYMBOL_GPL(pci_epf_create); +/** + * pci_epf_align_inbound_addr() - Align the given address based on the BAR + * alignment requirement + * @epf: the EPF device + * @addr: inbound address to be aligned + * @bar: the BAR number corresponding to the given addr + * @base: base address matching the @bar alignment requirement + * @off: offset to be added to the @base address + * + * Helper function to align input @addr based on BAR's alignment requirement. + * The aligned base address and offset are returned via @base and @off. + * + * NOTE: The pci_epf_alloc_space() function already accounts for alignment. + * This API is primarily intended for use with other memory regions not + * allocated by pci_epf_alloc_space(), such as peripheral register spaces or + * the message address of a platform MSI controller. + * + * Return: 0 on success, errno otherwise. + */ +int pci_epf_align_inbound_addr(struct pci_epf *epf, enum pci_barno bar, + u64 addr, dma_addr_t *base, size_t *off) +{ + /* + * Most EP controllers require the BAR start address to be aligned to + * the BAR size, because they mask off the lower bits. + * + * Alignment to BAR size also works for controllers that support + * unaligned addresses. + */ + u64 align = epf->bar[bar].size; + + *base = round_down(addr, align); + *off = addr & (align - 1); + + return 0; +} +EXPORT_SYMBOL_GPL(pci_epf_align_inbound_addr); + static void pci_epf_dev_release(struct device *dev) { struct pci_epf *epf = to_pci_epf(dev); diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index 52e07602f08e..2e85504ba2ba 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -241,6 +241,9 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar, enum pci_epc_interface_type type); void pci_epf_free_space(struct pci_epf *epf, void *addr, enum pci_barno bar, enum pci_epc_interface_type type); + +int pci_epf_align_inbound_addr(struct pci_epf *epf, enum pci_barno bar, + u64 addr, dma_addr_t *base, size_t *off); int pci_epf_bind(struct pci_epf *epf); void pci_epf_unbind(struct pci_epf *epf); int pci_epf_add_vepf(struct pci_epf *epf_pf, struct pci_epf *epf_vf); -- cgit v1.2.3 From 6cff20ce3b92ffbf2fc5eb9e5a030b3672aa414a Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sun, 13 Jul 2025 16:31:01 +0200 Subject: PCI/ACPI: Fix runtime PM ref imbalance on Hot-Plug Capable ports pci_bridge_d3_possible() is called from both pcie_portdrv_probe() and pcie_portdrv_remove() to determine whether runtime power management shall be enabled (on probe) or disabled (on remove) on a PCIe port. The underlying assumption is that pci_bridge_d3_possible() always returns the same value, else a runtime PM reference imbalance would occur. That assumption is not given if the PCIe port is inaccessible on remove due to hot-unplug: pci_bridge_d3_possible() calls pciehp_is_native(), which accesses Config Space to determine whether the port is Hot-Plug Capable. An inaccessible port returns "all ones", which is converted to "all zeroes" by pcie_capability_read_dword(). Hence the port no longer seems Hot-Plug Capable on remove even though it was on probe. The resulting runtime PM ref imbalance causes warning messages such as: pcieport 0000:02:04.0: Runtime PM usage count underflow! Avoid the Config Space access (and thus the runtime PM ref imbalance) by caching the Hot-Plug Capable bit in struct pci_dev. The struct already contains an "is_hotplug_bridge" flag, which however is not only set on Hot-Plug Capable PCIe ports, but also Conventional PCI Hot-Plug bridges and ACPI slots. The flag identifies bridges which are allocated additional MMIO and bus number resources to allow for hierarchy expansion. The kernel is somewhat sloppily using "is_hotplug_bridge" in a number of places to identify Hot-Plug Capable PCIe ports, even though the flag encompasses other devices. Subsequent commits replace these occurrences with the new flag to clearly delineate Hot-Plug Capable PCIe ports from other kinds of hotplug bridges. Document the existing "is_hotplug_bridge" and the new "is_pciehp" flag and document the (non-obvious) requirement that pci_bridge_d3_possible() always returns the same value across the entire lifetime of a bridge, including its hot-removal. Fixes: 5352a44a561d ("PCI: pciehp: Make pciehp_is_native() stricter") Reported-by: Laurent Bigonville Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220216 Reported-by: Mario Limonciello Closes: https://lore.kernel.org/r/20250609020223.269407-3-superm1@kernel.org/ Link: https://lore.kernel.org/all/20250620025535.3425049-3-superm1@kernel.org/T/#u Signed-off-by: Lukas Wunner Signed-off-by: Bjorn Helgaas Acked-by: Rafael J. Wysocki Cc: stable@vger.kernel.org # v4.18+ Link: https://patch.msgid.link/fe5dcc3b2e62ee1df7905d746bde161eb1b3291c.1752390101.git.lukas@wunner.de --- drivers/pci/pci-acpi.c | 4 +--- drivers/pci/pci.c | 6 +++++- drivers/pci/probe.c | 2 +- include/linux/pci.h | 6 ++++++ 4 files changed, 13 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index b78e0e417324..efe478e5073e 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -816,13 +816,11 @@ int pci_acpi_program_hp_params(struct pci_dev *dev) bool pciehp_is_native(struct pci_dev *bridge) { const struct pci_host_bridge *host; - u32 slot_cap; if (!IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)) return false; - pcie_capability_read_dword(bridge, PCI_EXP_SLTCAP, &slot_cap); - if (!(slot_cap & PCI_EXP_SLTCAP_HPC)) + if (!bridge->is_pciehp) return false; if (pcie_ports_native) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e9448d55113b..23d8fe98ddf9 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3030,8 +3030,12 @@ static const struct dmi_system_id bridge_d3_blacklist[] = { * pci_bridge_d3_possible - Is it possible to put the bridge into D3 * @bridge: Bridge to check * - * This function checks if it is possible to move the bridge to D3. * Currently we only allow D3 for some PCIe ports and for Thunderbolt. + * + * Return: Whether it is possible to move the bridge to D3. + * + * The return value is guaranteed to be constant across the entire lifetime + * of the bridge, including its hot-removal. */ bool pci_bridge_d3_possible(struct pci_dev *bridge) { diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 4b8693ec9e4c..cf50be63bf5f 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1678,7 +1678,7 @@ void set_pcie_hotplug_bridge(struct pci_dev *pdev) pcie_capability_read_dword(pdev, PCI_EXP_SLTCAP, ®32); if (reg32 & PCI_EXP_SLTCAP_HPC) - pdev->is_hotplug_bridge = 1; + pdev->is_hotplug_bridge = pdev->is_pciehp = 1; } static void set_pcie_thunderbolt(struct pci_dev *dev) diff --git a/include/linux/pci.h b/include/linux/pci.h index 05e68f35f392..d56d0dd80afb 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -328,6 +328,11 @@ struct rcec_ea; * determined (e.g., for Root Complex Integrated * Endpoints without the relevant Capability * Registers). + * @is_hotplug_bridge: Hotplug bridge of any kind (e.g. PCIe Hot-Plug Capable, + * Conventional PCI Hot-Plug, ACPI slot). + * Such bridges are allocated additional MMIO and bus + * number resources to allow for hierarchy expansion. + * @is_pciehp: PCIe Hot-Plug Capable bridge. */ struct pci_dev { struct list_head bus_list; /* Node in per-bus list */ @@ -451,6 +456,7 @@ struct pci_dev { unsigned int is_physfn:1; unsigned int is_virtfn:1; unsigned int is_hotplug_bridge:1; + unsigned int is_pciehp:1; unsigned int shpc_managed:1; /* SHPC owned by shpchp */ unsigned int is_thunderbolt:1; /* Thunderbolt controller */ /* -- cgit v1.2.3 From c2f9de5e2db29158a8caa86a37aa479488e4ba43 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sun, 13 Jul 2025 16:31:04 +0200 Subject: PCI: Move is_pciehp check out of pciehp_is_native() pci_bridge_d3_possible() seeks to forbid runtime power management on: * Non Hot-Plug Capable PCIe ports which are nevertheless ACPI slots (recognizable as: bridge->is_hotplug_bridge && !bridge->is_pciehp) * Hot-Plug Capable PCIe ports for which platform firmware has not granted PCIe Native Hot-Plug control to the operating system (recognizable as: bridge->is_pciehp && !pciehp_is_native(bridge)) Somewhat confusingly, the check for is_hotplug_bridge is in pci_bridge_d3_possible(), whereas the one for is_pciehp is in pciehp_is_native(). For clarity, check is_pciehp directly in pci_bridge_d3_possible() (and in the other caller of pciehp_is_native(), hotplug_is_native()). Rephrase the code comment preceding these checks to no longer mention "System Management Mode", which is an x86 term inappropriate in generic PCI code. Likewise no longer mention "Thunderbolt on non-Macs", because there is nothing Thunderbolt-specific about these checks. It used to be the case that non-Macs relied on the platform for Thunderbolt tunnel management and hotplug, but they've since moved to OS-native tunnel management (as Macs always have), hence the code comment is no longer accurate. There is a subsequent check for is_hotplug_bridge further down in pci_bridge_d3_possible(). Change the check to is_pciehp because any ports matching "bridge->is_hotplug_bridge && !bridge->is_pciehp" are already filtered out at the top of the function. Do the same for another check in acpi_pci_bridge_d3(), which is called from pci_bridge_d3_possible() via platform_pci_bridge_d3(). No functional change intended. Signed-off-by: Lukas Wunner Signed-off-by: Bjorn Helgaas Link: https://patch.msgid.link/18b2c2110ad0f27a34b189d793310b9c4f2f24a0.1752390102.git.lukas@wunner.de --- drivers/pci/pci-acpi.c | 5 +---- drivers/pci/pci.c | 12 ++++++++---- include/linux/pci_hotplug.h | 3 ++- 3 files changed, 11 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index efe478e5073e..ed7ed66a595b 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -820,9 +820,6 @@ bool pciehp_is_native(struct pci_dev *bridge) if (!IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)) return false; - if (!bridge->is_pciehp) - return false; - if (pcie_ports_native) return true; @@ -1000,7 +997,7 @@ bool acpi_pci_bridge_d3(struct pci_dev *dev) struct acpi_device *adev, *rpadev; const union acpi_object *obj; - if (acpi_pci_disabled || !dev->is_hotplug_bridge) + if (acpi_pci_disabled || !dev->is_pciehp) return false; adev = ACPI_COMPANION(&dev->dev); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 23d8fe98ddf9..749994dad9dc 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3050,10 +3050,14 @@ bool pci_bridge_d3_possible(struct pci_dev *bridge) return false; /* - * Hotplug ports handled by firmware in System Management Mode - * may not be put into D3 by the OS (Thunderbolt on non-Macs). + * Hotplug ports handled by platform firmware may not be put + * into D3 by the OS, e.g. ACPI slots ... */ - if (bridge->is_hotplug_bridge && !pciehp_is_native(bridge)) + if (bridge->is_hotplug_bridge && !bridge->is_pciehp) + return false; + + /* ... or PCIe hotplug ports not handled natively by the OS. */ + if (bridge->is_pciehp && !pciehp_is_native(bridge)) return false; if (pci_bridge_d3_force) @@ -3072,7 +3076,7 @@ bool pci_bridge_d3_possible(struct pci_dev *bridge) * by vendors for runtime D3 at least until 2018 because there * was no OS support. */ - if (bridge->is_hotplug_bridge) + if (bridge->is_pciehp) return false; if (dmi_check_system(bridge_d3_blacklist)) diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index ec77ccf1fc4d..ddf79641917f 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -104,6 +104,7 @@ static inline bool shpchp_is_native(struct pci_dev *bridge) { return true; } static inline bool hotplug_is_native(struct pci_dev *bridge) { - return pciehp_is_native(bridge) || shpchp_is_native(bridge); + return (bridge->is_pciehp && pciehp_is_native(bridge)) || + shpchp_is_native(bridge); } #endif -- cgit v1.2.3 From 71753c6ed2bf2aee5be26c1bc06a94c9e3713ade Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 29 Jul 2025 14:23:05 -0400 Subject: unwind_user: Add user space unwinding API with frame pointer support Introduce a generic API for unwinding user stacks. In order to expand user space unwinding to be able to handle more complex scenarios, such as deferred unwinding and reading user space information, create a generic interface that all architectures can use that support the various unwinding methods. This is an alternative method for handling user space stack traces from the simple stack_trace_save_user() API. This does not replace that interface, but this interface will be used to expand the functionality of user space stack walking. None of the structures introduced will be exposed to user space tooling. Support for frame pointer unwinding is added. For an architecture to support frame pointer unwinding it needs to enable CONFIG_HAVE_UNWIND_USER_FP and define ARCH_INIT_USER_FP_FRAME. By encoding the frame offsets in struct unwind_user_frame, much of this code can also be reused for future unwinder implementations like sframe. Cc: Masami Hiramatsu Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Jiri Olsa Cc: Arnaldo Carvalho de Melo Cc: Namhyung Kim Cc: Thomas Gleixner Cc: Andrii Nakryiko Cc: Indu Bhagat Cc: "Jose E. Marchesi" Cc: Beau Belgrave Cc: Linus Torvalds Cc: Andrew Morton Cc: Jens Axboe Cc: Florian Weimer Cc: Sam James Link: https://lore.kernel.org/20250729182404.975790139@kernel.org Reviewed-by: Jens Remus Signed-off-by: Josh Poimboeuf Co-developed-by: Mathieu Desnoyers Link: https://lore.kernel.org/all/20250710164301.3094-2-mathieu.desnoyers@efficios.com/ Signed-off-by: Mathieu Desnoyers Co-developed-by: Steven Rostedt (Google) Signed-off-by: Steven Rostedt (Google) --- MAINTAINERS | 8 +++ arch/Kconfig | 7 +++ include/asm-generic/Kbuild | 1 + include/asm-generic/unwind_user.h | 5 ++ include/linux/unwind_user.h | 14 +++++ include/linux/unwind_user_types.h | 44 +++++++++++++ kernel/Makefile | 1 + kernel/unwind/Makefile | 1 + kernel/unwind/user.c | 128 ++++++++++++++++++++++++++++++++++++++ 9 files changed, 209 insertions(+) create mode 100644 include/asm-generic/unwind_user.h create mode 100644 include/linux/unwind_user.h create mode 100644 include/linux/unwind_user_types.h create mode 100644 kernel/unwind/Makefile create mode 100644 kernel/unwind/user.c (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index fad6cb025a19..370d780fd5f8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -25928,6 +25928,14 @@ F: Documentation/driver-api/uio-howto.rst F: drivers/uio/ F: include/linux/uio_driver.h +USERSPACE STACK UNWINDING +M: Josh Poimboeuf +M: Steven Rostedt +S: Maintained +F: include/linux/unwind*.h +F: kernel/unwind/ + + UTIL-LINUX PACKAGE M: Karel Zak L: util-linux@vger.kernel.org diff --git a/arch/Kconfig b/arch/Kconfig index a3308a220f86..8e3fd723bd74 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -435,6 +435,13 @@ config HAVE_HARDLOCKUP_DETECTOR_ARCH It uses the same command line parameters, and sysctl interface, as the generic hardlockup detectors. +config UNWIND_USER + bool + +config HAVE_UNWIND_USER_FP + bool + select UNWIND_USER + config HAVE_PERF_REGS bool help diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild index 8675b7b4ad23..295c94a3ccc1 100644 --- a/include/asm-generic/Kbuild +++ b/include/asm-generic/Kbuild @@ -59,6 +59,7 @@ mandatory-y += tlbflush.h mandatory-y += topology.h mandatory-y += trace_clock.h mandatory-y += uaccess.h +mandatory-y += unwind_user.h mandatory-y += vermagic.h mandatory-y += vga.h mandatory-y += video.h diff --git a/include/asm-generic/unwind_user.h b/include/asm-generic/unwind_user.h new file mode 100644 index 000000000000..b8882b909944 --- /dev/null +++ b/include/asm-generic/unwind_user.h @@ -0,0 +1,5 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_GENERIC_UNWIND_USER_H +#define _ASM_GENERIC_UNWIND_USER_H + +#endif /* _ASM_GENERIC_UNWIND_USER_H */ diff --git a/include/linux/unwind_user.h b/include/linux/unwind_user.h new file mode 100644 index 000000000000..7f7282516bf5 --- /dev/null +++ b/include/linux/unwind_user.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_UNWIND_USER_H +#define _LINUX_UNWIND_USER_H + +#include +#include + +#ifndef ARCH_INIT_USER_FP_FRAME + #define ARCH_INIT_USER_FP_FRAME +#endif + +int unwind_user(struct unwind_stacktrace *trace, unsigned int max_entries); + +#endif /* _LINUX_UNWIND_USER_H */ diff --git a/include/linux/unwind_user_types.h b/include/linux/unwind_user_types.h new file mode 100644 index 000000000000..a449f15be890 --- /dev/null +++ b/include/linux/unwind_user_types.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_UNWIND_USER_TYPES_H +#define _LINUX_UNWIND_USER_TYPES_H + +#include + +/* + * Unwind types, listed in priority order: lower numbers are attempted first if + * available. + */ +enum unwind_user_type_bits { + UNWIND_USER_TYPE_FP_BIT = 0, + + NR_UNWIND_USER_TYPE_BITS, +}; + +enum unwind_user_type { + /* Type "none" for the start of stack walk iteration. */ + UNWIND_USER_TYPE_NONE = 0, + UNWIND_USER_TYPE_FP = BIT(UNWIND_USER_TYPE_FP_BIT), +}; + +struct unwind_stacktrace { + unsigned int nr; + unsigned long *entries; +}; + +struct unwind_user_frame { + s32 cfa_off; + s32 ra_off; + s32 fp_off; + bool use_fp; +}; + +struct unwind_user_state { + unsigned long ip; + unsigned long sp; + unsigned long fp; + enum unwind_user_type current_type; + unsigned int available_types; + bool done; +}; + +#endif /* _LINUX_UNWIND_USER_TYPES_H */ diff --git a/kernel/Makefile b/kernel/Makefile index 32e80dd626af..541186050251 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -55,6 +55,7 @@ obj-y += rcu/ obj-y += livepatch/ obj-y += dma/ obj-y += entry/ +obj-y += unwind/ obj-$(CONFIG_MODULES) += module/ obj-$(CONFIG_KCMP) += kcmp.o diff --git a/kernel/unwind/Makefile b/kernel/unwind/Makefile new file mode 100644 index 000000000000..349ce3677526 --- /dev/null +++ b/kernel/unwind/Makefile @@ -0,0 +1 @@ + obj-$(CONFIG_UNWIND_USER) += user.o diff --git a/kernel/unwind/user.c b/kernel/unwind/user.c new file mode 100644 index 000000000000..97a8415e3216 --- /dev/null +++ b/kernel/unwind/user.c @@ -0,0 +1,128 @@ +// SPDX-License-Identifier: GPL-2.0 +/* +* Generic interfaces for unwinding user space +*/ +#include +#include +#include +#include +#include + +static const struct unwind_user_frame fp_frame = { + ARCH_INIT_USER_FP_FRAME +}; + +#define for_each_user_frame(state) \ + for (unwind_user_start(state); !(state)->done; unwind_user_next(state)) + +static int unwind_user_next_fp(struct unwind_user_state *state) +{ + const struct unwind_user_frame *frame = &fp_frame; + unsigned long cfa, fp, ra; + unsigned int shift; + + if (frame->use_fp) { + if (state->fp < state->sp) + return -EINVAL; + cfa = state->fp; + } else { + cfa = state->sp; + } + + /* Get the Canonical Frame Address (CFA) */ + cfa += frame->cfa_off; + + /* stack going in wrong direction? */ + if (cfa <= state->sp) + return -EINVAL; + + /* Make sure that the address is word aligned */ + shift = sizeof(long) == 4 ? 2 : 3; + if (cfa & ((1 << shift) - 1)) + return -EINVAL; + + /* Find the Return Address (RA) */ + if (get_user(ra, (unsigned long *)(cfa + frame->ra_off))) + return -EINVAL; + + if (frame->fp_off && get_user(fp, (unsigned long __user *)(cfa + frame->fp_off))) + return -EINVAL; + + state->ip = ra; + state->sp = cfa; + if (frame->fp_off) + state->fp = fp; + return 0; +} + +static int unwind_user_next(struct unwind_user_state *state) +{ + unsigned long iter_mask = state->available_types; + unsigned int bit; + + if (state->done) + return -EINVAL; + + for_each_set_bit(bit, &iter_mask, NR_UNWIND_USER_TYPE_BITS) { + enum unwind_user_type type = BIT(bit); + + state->current_type = type; + switch (type) { + case UNWIND_USER_TYPE_FP: + if (!unwind_user_next_fp(state)) + return 0; + continue; + default: + WARN_ONCE(1, "Undefined unwind bit %d", bit); + break; + } + break; + } + + /* No successful unwind method. */ + state->current_type = UNWIND_USER_TYPE_NONE; + state->done = true; + return -EINVAL; +} + +static int unwind_user_start(struct unwind_user_state *state) +{ + struct pt_regs *regs = task_pt_regs(current); + + memset(state, 0, sizeof(*state)); + + if ((current->flags & PF_KTHREAD) || !user_mode(regs)) { + state->done = true; + return -EINVAL; + } + + if (IS_ENABLED(CONFIG_HAVE_UNWIND_USER_FP)) + state->available_types |= UNWIND_USER_TYPE_FP; + + state->ip = instruction_pointer(regs); + state->sp = user_stack_pointer(regs); + state->fp = frame_pointer(regs); + + return 0; +} + +int unwind_user(struct unwind_stacktrace *trace, unsigned int max_entries) +{ + struct unwind_user_state state; + + trace->nr = 0; + + if (!max_entries) + return -EINVAL; + + if (current->flags & PF_KTHREAD) + return 0; + + for_each_user_frame(&state) { + trace->entries[trace->nr++] = state.ip; + if (trace->nr >= max_entries) + break; + } + + return 0; +} -- cgit v1.2.3 From 5e32d0f15cc5c843a4115c4644d984d42524c794 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 29 Jul 2025 14:23:06 -0400 Subject: unwind_user/deferred: Add unwind_user_faultable() Add a new API to retrieve a user space callstack called unwind_user_faultable(). The difference between this user space stack tracer from the current user space stack tracer is that this must be called from faultable context as it may use routines to access user space data that needs to be faulted in. It can be safely called from entering or exiting a system call as the code can still be faulted in there. This code is based on work by Josh Poimboeuf's deferred unwinding code: Link: https://lore.kernel.org/all/6052e8487746603bdb29b65f4033e739092d9925.1737511963.git.jpoimboe@kernel.org/ Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Jiri Olsa Cc: Arnaldo Carvalho de Melo Cc: Namhyung Kim Cc: Thomas Gleixner Cc: Andrii Nakryiko Cc: Indu Bhagat Cc: "Jose E. Marchesi" Cc: Beau Belgrave Cc: Linus Torvalds Cc: Andrew Morton Cc: Jens Axboe Cc: Florian Weimer Cc: Sam James Link: https://lore.kernel.org/20250729182405.147896868@kernel.org Reviewed-by: Jens Remus Signed-off-by: Steven Rostedt (Google) --- include/linux/sched.h | 5 +++ include/linux/unwind_deferred.h | 24 ++++++++++++++ include/linux/unwind_deferred_types.h | 9 ++++++ kernel/fork.c | 4 +++ kernel/unwind/Makefile | 2 +- kernel/unwind/deferred.c | 60 +++++++++++++++++++++++++++++++++++ 6 files changed, 103 insertions(+), 1 deletion(-) create mode 100644 include/linux/unwind_deferred.h create mode 100644 include/linux/unwind_deferred_types.h create mode 100644 kernel/unwind/deferred.c (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4f78a64beb52..59fdf7d9bb1e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -46,6 +46,7 @@ #include #include #include +#include #include /* task_struct member predeclarations (sorted alphabetically): */ @@ -1654,6 +1655,10 @@ struct task_struct { struct user_event_mm *user_event_mm; #endif +#ifdef CONFIG_UNWIND_USER + struct unwind_task_info unwind_info; +#endif + /* CPU-specific state of this task: */ struct thread_struct thread; diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h new file mode 100644 index 000000000000..a5f6e8f8a1a2 --- /dev/null +++ b/include/linux/unwind_deferred.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_UNWIND_USER_DEFERRED_H +#define _LINUX_UNWIND_USER_DEFERRED_H + +#include +#include + +#ifdef CONFIG_UNWIND_USER + +void unwind_task_init(struct task_struct *task); +void unwind_task_free(struct task_struct *task); + +int unwind_user_faultable(struct unwind_stacktrace *trace); + +#else /* !CONFIG_UNWIND_USER */ + +static inline void unwind_task_init(struct task_struct *task) {} +static inline void unwind_task_free(struct task_struct *task) {} + +static inline int unwind_user_faultable(struct unwind_stacktrace *trace) { return -ENOSYS; } + +#endif /* !CONFIG_UNWIND_USER */ + +#endif /* _LINUX_UNWIND_USER_DEFERRED_H */ diff --git a/include/linux/unwind_deferred_types.h b/include/linux/unwind_deferred_types.h new file mode 100644 index 000000000000..aa32db574e43 --- /dev/null +++ b/include/linux/unwind_deferred_types.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_UNWIND_USER_DEFERRED_TYPES_H +#define _LINUX_UNWIND_USER_DEFERRED_TYPES_H + +struct unwind_task_info { + unsigned long *entries; +}; + +#endif /* _LINUX_UNWIND_USER_DEFERRED_TYPES_H */ diff --git a/kernel/fork.c b/kernel/fork.c index 1ee8eb11f38b..3341d50c61f2 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -105,6 +105,7 @@ #include #include #include +#include #include #include @@ -732,6 +733,7 @@ void __put_task_struct(struct task_struct *tsk) WARN_ON(refcount_read(&tsk->usage)); WARN_ON(tsk == current); + unwind_task_free(tsk); sched_ext_free(tsk); io_uring_free(tsk); cgroup_free(tsk); @@ -2135,6 +2137,8 @@ __latent_entropy struct task_struct *copy_process( p->bpf_ctx = NULL; #endif + unwind_task_init(p); + /* Perform scheduler related setup. Assign this task to a CPU. */ retval = sched_fork(clone_flags, p); if (retval) diff --git a/kernel/unwind/Makefile b/kernel/unwind/Makefile index 349ce3677526..eae37bea54fd 100644 --- a/kernel/unwind/Makefile +++ b/kernel/unwind/Makefile @@ -1 +1 @@ - obj-$(CONFIG_UNWIND_USER) += user.o + obj-$(CONFIG_UNWIND_USER) += user.o deferred.o diff --git a/kernel/unwind/deferred.c b/kernel/unwind/deferred.c new file mode 100644 index 000000000000..a0badbeb3cc1 --- /dev/null +++ b/kernel/unwind/deferred.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Deferred user space unwinding + */ +#include +#include +#include +#include + +#define UNWIND_MAX_ENTRIES 512 + +/** + * unwind_user_faultable - Produce a user stacktrace in faultable context + * @trace: The descriptor that will store the user stacktrace + * + * This must be called in a known faultable context (usually when entering + * or exiting user space). Depending on the available implementations + * the @trace will be loaded with the addresses of the user space stacktrace + * if it can be found. + * + * Return: 0 on success and negative on error + * On success @trace will contain the user space stacktrace + */ +int unwind_user_faultable(struct unwind_stacktrace *trace) +{ + struct unwind_task_info *info = ¤t->unwind_info; + + /* Should always be called from faultable context */ + might_fault(); + + if (current->flags & PF_EXITING) + return -EINVAL; + + if (!info->entries) { + info->entries = kmalloc_array(UNWIND_MAX_ENTRIES, sizeof(long), + GFP_KERNEL); + if (!info->entries) + return -ENOMEM; + } + + trace->nr = 0; + trace->entries = info->entries; + unwind_user(trace, UNWIND_MAX_ENTRIES); + + return 0; +} + +void unwind_task_init(struct task_struct *task) +{ + struct unwind_task_info *info = &task->unwind_info; + + memset(info, 0, sizeof(*info)); +} + +void unwind_task_free(struct task_struct *task) +{ + struct unwind_task_info *info = &task->unwind_info; + + kfree(info->entries); +} -- cgit v1.2.3 From 5523a466e905b6287b94654ddb364536f2f948cf Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 25 Jul 2025 11:06:03 +0200 Subject: i3c: fix module_i3c_i2c_driver() with I3C=n When CONFIG_I3C is disabled and the i3c_i2c_driver_register() happens to not be inlined, any driver calling it still references the i3c_driver instance, which then causes a link failure: x86_64-linux-ld: drivers/hwmon/lm75.o: in function `lm75_i3c_reg_read': lm75.c:(.text+0xc61): undefined reference to `i3cdev_to_dev' x86_64-linux-ld: lm75.c:(.text+0xd25): undefined reference to `i3c_device_do_priv_xfers' x86_64-linux-ld: lm75.c:(.text+0xdd8): undefined reference to `i3c_device_do_priv_xfers' This issue was part of the original i3c code, but only now caused problems when i3c support got added to lm75. Change the 'inline' annotations in the header to '__always_inline' to ensure that the dead-code-elimination pass in the compiler can optimize it out as intended. Fixes: 6071d10413ff ("hwmon: (lm75) add I3C support for P3T1755") Fixes: 3a379bbcea0a ("i3c: Add core I3C infrastructure") Signed-off-by: Arnd Bergmann Reviewed-by: Randy Dunlap Tested-by: Randy Dunlap Reviewed-by: Guenter Roeck Reviewed-by: Frank Li Link: https://lore.kernel.org/r/20250725090609.2456262-1-arnd@kernel.org Signed-off-by: Alexandre Belloni --- include/linux/i3c/device.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i3c/device.h b/include/linux/i3c/device.h index b674f64d0822..7f136de4b73e 100644 --- a/include/linux/i3c/device.h +++ b/include/linux/i3c/device.h @@ -245,7 +245,7 @@ void i3c_driver_unregister(struct i3c_driver *drv); * * Return: 0 if both registrations succeeds, a negative error code otherwise. */ -static inline int i3c_i2c_driver_register(struct i3c_driver *i3cdrv, +static __always_inline int i3c_i2c_driver_register(struct i3c_driver *i3cdrv, struct i2c_driver *i2cdrv) { int ret; @@ -270,7 +270,7 @@ static inline int i3c_i2c_driver_register(struct i3c_driver *i3cdrv, * Note that when CONFIG_I3C is not enabled, this function only unregisters the * @i2cdrv. */ -static inline void i3c_i2c_driver_unregister(struct i3c_driver *i3cdrv, +static __always_inline void i3c_i2c_driver_unregister(struct i3c_driver *i3cdrv, struct i2c_driver *i2cdrv) { if (IS_ENABLED(CONFIG_I3C)) -- cgit v1.2.3 From 9c0609d685b27a0bb392390680207baa820ed118 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Thu, 24 Jul 2025 11:41:40 +0200 Subject: i3c: Standardize defines for specification parameters Align existing defines to follow the consistent pattern: I3C_BUS___. Prepare the codebase for adding new parameters and help avoid duplication. Signed-off-by: Wolfram Sang Tested-by: Tommaso Merciai Reviewed-by: Frank Li Link: https://lore.kernel.org/r/20250724094146.6443-2-wsa+renesas@sang-engineering.com Signed-off-by: Alexandre Belloni --- drivers/i3c/master.c | 12 ++++++------ drivers/i3c/master/dw-i3c-master.c | 4 ++-- include/linux/i3c/master.h | 9 +++++---- 3 files changed, 13 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index e00991444f31..2ef898a8fd80 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -727,12 +727,12 @@ static int i3c_bus_set_mode(struct i3c_bus *i3cbus, enum i3c_bus_mode mode, switch (i3cbus->mode) { case I3C_BUS_MODE_PURE: if (!i3cbus->scl_rate.i3c) - i3cbus->scl_rate.i3c = I3C_BUS_TYP_I3C_SCL_RATE; + i3cbus->scl_rate.i3c = I3C_BUS_I3C_SCL_TYP_RATE; break; case I3C_BUS_MODE_MIXED_FAST: case I3C_BUS_MODE_MIXED_LIMITED: if (!i3cbus->scl_rate.i3c) - i3cbus->scl_rate.i3c = I3C_BUS_TYP_I3C_SCL_RATE; + i3cbus->scl_rate.i3c = I3C_BUS_I3C_SCL_TYP_RATE; if (!i3cbus->scl_rate.i2c) i3cbus->scl_rate.i2c = max_i2c_scl_rate; break; @@ -754,8 +754,8 @@ static int i3c_bus_set_mode(struct i3c_bus *i3cbus, enum i3c_bus_mode mode, * I3C/I2C frequency may have been overridden, check that user-provided * values are not exceeding max possible frequency. */ - if (i3cbus->scl_rate.i3c > I3C_BUS_MAX_I3C_SCL_RATE || - i3cbus->scl_rate.i2c > I3C_BUS_I2C_FM_PLUS_SCL_RATE) + if (i3cbus->scl_rate.i3c > I3C_BUS_I3C_SCL_MAX_RATE || + i3cbus->scl_rate.i2c > I3C_BUS_I2C_FM_PLUS_SCL_MAX_RATE) return -EINVAL; return 0; @@ -2787,7 +2787,7 @@ int i3c_master_register(struct i3c_master_controller *master, const struct i3c_master_controller_ops *ops, bool secondary) { - unsigned long i2c_scl_rate = I3C_BUS_I2C_FM_PLUS_SCL_RATE; + unsigned long i2c_scl_rate = I3C_BUS_I2C_FM_PLUS_SCL_MAX_RATE; struct i3c_bus *i3cbus = i3c_master_get_bus(master); enum i3c_bus_mode mode = I3C_BUS_MODE_PURE; struct i2c_dev_boardinfo *i2cbi; @@ -2846,7 +2846,7 @@ int i3c_master_register(struct i3c_master_controller *master, } if (i2cbi->lvr & I3C_LVR_I2C_FM_MODE) - i2c_scl_rate = I3C_BUS_I2C_FM_SCL_RATE; + i2c_scl_rate = I3C_BUS_I2C_FM_SCL_MAX_RATE; } ret = i3c_bus_set_mode(i3cbus, mode, i2c_scl_rate); diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index cc872b481691..e61be28cd1e3 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -605,14 +605,14 @@ static int dw_i2c_clk_cfg(struct dw_i3c_master *master) core_period = DIV_ROUND_UP(1000000000, core_rate); lcnt = DIV_ROUND_UP(I3C_BUS_I2C_FMP_TLOW_MIN_NS, core_period); - hcnt = DIV_ROUND_UP(core_rate, I3C_BUS_I2C_FM_PLUS_SCL_RATE) - lcnt; + hcnt = DIV_ROUND_UP(core_rate, I3C_BUS_I2C_FM_PLUS_SCL_MAX_RATE) - lcnt; scl_timing = SCL_I2C_FMP_TIMING_HCNT(hcnt) | SCL_I2C_FMP_TIMING_LCNT(lcnt); writel(scl_timing, master->regs + SCL_I2C_FMP_TIMING); master->i2c_fmp_timing = scl_timing; lcnt = DIV_ROUND_UP(I3C_BUS_I2C_FM_TLOW_MIN_NS, core_period); - hcnt = DIV_ROUND_UP(core_rate, I3C_BUS_I2C_FM_SCL_RATE) - lcnt; + hcnt = DIV_ROUND_UP(core_rate, I3C_BUS_I2C_FM_SCL_MAX_RATE) - lcnt; scl_timing = SCL_I2C_FM_TIMING_HCNT(hcnt) | SCL_I2C_FM_TIMING_LCNT(lcnt); writel(scl_timing, master->regs + SCL_I2C_FM_TIMING); diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h index c67922ece617..7dfcbe530515 100644 --- a/include/linux/i3c/master.h +++ b/include/linux/i3c/master.h @@ -249,10 +249,11 @@ struct i3c_device { */ #define I3C_BUS_MAX_DEVS 11 -#define I3C_BUS_MAX_I3C_SCL_RATE 12900000 -#define I3C_BUS_TYP_I3C_SCL_RATE 12500000 -#define I3C_BUS_I2C_FM_PLUS_SCL_RATE 1000000 -#define I3C_BUS_I2C_FM_SCL_RATE 400000 +/* Taken from the I3C Spec V1.1.1, chapter 6.2. "Timing specification" */ +#define I3C_BUS_I2C_FM_PLUS_SCL_MAX_RATE 1000000 +#define I3C_BUS_I2C_FM_SCL_MAX_RATE 400000 +#define I3C_BUS_I3C_SCL_MAX_RATE 12900000 +#define I3C_BUS_I3C_SCL_TYP_RATE 12500000 #define I3C_BUS_TLOW_OD_MIN_NS 200 /** -- cgit v1.2.3 From 8acf1f3bae1ea48949458b67d68a72a95c3244a4 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Thu, 24 Jul 2025 11:41:41 +0200 Subject: i3c: Add more parameters for controllers to the header Add standard timing value definition from specification. Signed-off-by: Wolfram Sang Tested-by: Tommaso Merciai Reviewed-by: Frank Li Link: https://lore.kernel.org/r/20250724094146.6443-3-wsa+renesas@sang-engineering.com Signed-off-by: Alexandre Belloni --- include/linux/i3c/master.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h index 7dfcbe530515..043f5c7ff398 100644 --- a/include/linux/i3c/master.h +++ b/include/linux/i3c/master.h @@ -254,6 +254,10 @@ struct i3c_device { #define I3C_BUS_I2C_FM_SCL_MAX_RATE 400000 #define I3C_BUS_I3C_SCL_MAX_RATE 12900000 #define I3C_BUS_I3C_SCL_TYP_RATE 12500000 +#define I3C_BUS_TAVAL_MIN_NS 1000 +#define I3C_BUS_TBUF_MIXED_FM_MIN_NS 1300 +#define I3C_BUS_THIGH_MIXED_MAX_NS 41 +#define I3C_BUS_TIDLE_MIN_NS 200000 #define I3C_BUS_TLOW_OD_MIN_NS 200 /** -- cgit v1.2.3 From 0060beec0bfa647c4b510df188b1c4673a197839 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 28 Jul 2025 13:04:29 +0900 Subject: ata: libata-sata: Add link_power_management_supported sysfs attribute A port link power management (LPM) policy can be controlled using the link_power_management_policy sysfs host attribute. However, this attribute exists also for hosts that do not support LPM and in such case, attempting to change the LPM policy for the host (port) will fail with -EOPNOTSUPP. Introduce the new sysfs link_power_management_supported host attribute to indicate to the user if a the port and the devices connected to the port for the host support LPM, which implies that the link_power_management_policy attribute can be used. Since checking that a port and its devices support LPM is common between the new ata_scsi_lpm_supported_show() function and the existing ata_scsi_lpm_store() function, the new helper ata_scsi_lpm_supported() is introduced. Fixes: 413e800cadbf ("ata: libata-sata: Disallow changing LPM state if not supported") Reported-by: Borah, Chaitanya Kumar Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202507251014.a5becc3b-lkp@intel.com Signed-off-by: Damien Le Moal Reviewed-by: Martin K. Petersen --- drivers/ata/ata_piix.c | 1 + drivers/ata/libahci.c | 1 + drivers/ata/libata-sata.c | 53 ++++++++++++++++++++++++++++++++++++----------- include/linux/libata.h | 1 + 4 files changed, 44 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c index 229429ba5027..495fa096dd65 100644 --- a/drivers/ata/ata_piix.c +++ b/drivers/ata/ata_piix.c @@ -1089,6 +1089,7 @@ static struct ata_port_operations ich_pata_ops = { }; static struct attribute *piix_sidpr_shost_attrs[] = { + &dev_attr_link_power_management_supported.attr, &dev_attr_link_power_management_policy.attr, NULL }; diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index b335fb7e5cb4..c79abdfcd7a9 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -111,6 +111,7 @@ static DEVICE_ATTR(em_buffer, S_IWUSR | S_IRUGO, static DEVICE_ATTR(em_message_supported, S_IRUGO, ahci_show_em_supported, NULL); static struct attribute *ahci_shost_attrs[] = { + &dev_attr_link_power_management_supported.attr, &dev_attr_link_power_management_policy.attr, &dev_attr_em_message_type.attr, &dev_attr_em_message.attr, diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index 4734465d3b1e..b2817a2995d6 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -900,14 +900,52 @@ static const char *ata_lpm_policy_names[] = { [ATA_LPM_MIN_POWER] = "min_power", }; +/* + * Check if a port supports link power management. + * Must be called with the port locked. + */ +static bool ata_scsi_lpm_supported(struct ata_port *ap) +{ + struct ata_link *link; + struct ata_device *dev; + + if (ap->flags & ATA_FLAG_NO_LPM) + return false; + + ata_for_each_link(link, ap, EDGE) { + ata_for_each_dev(dev, &ap->link, ENABLED) { + if (dev->quirks & ATA_QUIRK_NOLPM) + return false; + } + } + + return true; +} + +static ssize_t ata_scsi_lpm_supported_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = class_to_shost(dev); + struct ata_port *ap = ata_shost_to_port(shost); + unsigned long flags; + bool supported; + + spin_lock_irqsave(ap->lock, flags); + supported = ata_scsi_lpm_supported(ap); + spin_unlock_irqrestore(ap->lock, flags); + + return sysfs_emit(buf, "%d\n", supported); +} +DEVICE_ATTR(link_power_management_supported, S_IRUGO, + ata_scsi_lpm_supported_show, NULL); +EXPORT_SYMBOL_GPL(dev_attr_link_power_management_supported); + static ssize_t ata_scsi_lpm_store(struct device *device, struct device_attribute *attr, const char *buf, size_t count) { struct Scsi_Host *shost = class_to_shost(device); struct ata_port *ap = ata_shost_to_port(shost); - struct ata_link *link; - struct ata_device *dev; enum ata_lpm_policy policy; unsigned long flags; @@ -924,20 +962,11 @@ static ssize_t ata_scsi_lpm_store(struct device *device, spin_lock_irqsave(ap->lock, flags); - if (ap->flags & ATA_FLAG_NO_LPM) { + if (!ata_scsi_lpm_supported(ap)) { count = -EOPNOTSUPP; goto out_unlock; } - ata_for_each_link(link, ap, EDGE) { - ata_for_each_dev(dev, &ap->link, ENABLED) { - if (dev->quirks & ATA_QUIRK_NOLPM) { - count = -EOPNOTSUPP; - goto out_unlock; - } - } - } - ap->target_lpm_policy = policy; ata_port_schedule_eh(ap); out_unlock: diff --git a/include/linux/libata.h b/include/linux/libata.h index 912ace523880..0620dd67369f 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -545,6 +545,7 @@ typedef void (*ata_postreset_fn_t)(struct ata_link *link, unsigned int *classes) extern struct device_attribute dev_attr_unload_heads; #ifdef CONFIG_SATA_HOST +extern struct device_attribute dev_attr_link_power_management_supported; extern struct device_attribute dev_attr_link_power_management_policy; extern struct device_attribute dev_attr_ncq_prio_supported; extern struct device_attribute dev_attr_ncq_prio_enable; -- cgit v1.2.3 From 199d9ffb31650f948dd342ade1c1b920e157630f Mon Sep 17 00:00:00 2001 From: Thomas Weißschuh Date: Fri, 11 Jul 2025 15:31:36 +0200 Subject: module: move 'struct module_use' to internal.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The struct was moved to the public header file in commit c8e21ced08b3 ("module: fix kdb's illicit use of struct module_use."). Back then the structure was used outside of the module core. Nowadays this is not true anymore, so the structure can be made internal. Signed-off-by: Thomas Weißschuh Reviewed-by: Daniel Gomez Reviewed-by: Petr Pavlu Link: https://lore.kernel.org/r/20250711-kunit-ifdef-modules-v2-1-39443decb1f8@linutronix.de Signed-off-by: Daniel Gomez --- include/linux/module.h | 7 ------- kernel/module/internal.h | 7 +++++++ 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index a7cac01d95e7..97c38e1cd377 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -313,13 +313,6 @@ void *__symbol_get_gpl(const char *symbol); __used __section(".no_trim_symbol") = __stringify(x); \ (typeof(&x))(__symbol_get(__stringify(x))); }) -/* modules using other modules: kdb wants to see this. */ -struct module_use { - struct list_head source_list; - struct list_head target_list; - struct module *source, *target; -}; - enum module_state { MODULE_STATE_LIVE, /* Normal state. */ MODULE_STATE_COMING, /* Full formed, running module_init. */ diff --git a/kernel/module/internal.h b/kernel/module/internal.h index 51ddd8866ef3..618202578b42 100644 --- a/kernel/module/internal.h +++ b/kernel/module/internal.h @@ -112,6 +112,13 @@ struct find_symbol_arg { enum mod_license license; }; +/* modules using other modules */ +struct module_use { + struct list_head source_list; + struct list_head target_list; + struct module *source, *target; +}; + int mod_verify_sig(const void *mod, struct load_info *info); int try_to_force_load(struct module *mod, const char *reason); bool find_symbol(struct find_symbol_arg *fsa); -- cgit v1.2.3 From 818783c804bc051f7faf0ac226b5597f8259c6f8 Mon Sep 17 00:00:00 2001 From: Thomas Weißschuh Date: Fri, 11 Jul 2025 15:31:37 +0200 Subject: module: make structure definitions always visible MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To write code that works with both CONFIG_MODULES=y and CONFIG_MODULES=n it is convenient to use "if (IS_ENABLED(CONFIG_MODULES))" over raw #ifdef. The code will still fully typechecked but the unreachable parts are discarded by the compiler. This prevents accidental breakage when a certain kconfig combination was not specifically tested by the developer. This pattern is already supported to some extend by module.h defining empty stub functions if CONFIG_MODULES=n. However some users of module.h work on the structured defined by module.h. Therefore these structure definitions need to be visible, too. Many structure members are still gated by specific configuration settings. The assumption for those is that the code using them will be gated behind the same configuration setting anyways. Signed-off-by: Thomas Weißschuh Reviewed-by: Daniel Gomez Link: https://lore.kernel.org/r/20250711-kunit-ifdef-modules-v2-2-39443decb1f8@linutronix.de Signed-off-by: Daniel Gomez --- include/linux/module.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 97c38e1cd377..5fe812de2d84 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -303,16 +303,6 @@ static typeof(name) __mod_device_table__##type##__##name \ struct notifier_block; -#ifdef CONFIG_MODULES - -/* Get/put a kernel symbol (calls must be symmetric) */ -void *__symbol_get(const char *symbol); -void *__symbol_get_gpl(const char *symbol); -#define symbol_get(x) ({ \ - static const char __notrim[] \ - __used __section(".no_trim_symbol") = __stringify(x); \ - (typeof(&x))(__symbol_get(__stringify(x))); }) - enum module_state { MODULE_STATE_LIVE, /* Normal state. */ MODULE_STATE_COMING, /* Full formed, running module_init. */ @@ -597,6 +587,16 @@ struct module { #define MODULE_ARCH_INIT {} #endif +#ifdef CONFIG_MODULES + +/* Get/put a kernel symbol (calls must be symmetric) */ +void *__symbol_get(const char *symbol); +void *__symbol_get_gpl(const char *symbol); +#define symbol_get(x) ({ \ + static const char __notrim[] \ + __used __section(".no_trim_symbol") = __stringify(x); \ + (typeof(&x))(__symbol_get(__stringify(x))); }) + #ifndef HAVE_ARCH_KALLSYMS_SYMBOL_VALUE static inline unsigned long kallsyms_symbol_value(const Elf_Sym *sym) { -- cgit v1.2.3 From bdc877ba6b7ff1b6d2ebeff11e63da4a50a54854 Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Mon, 30 Jun 2025 16:32:34 +0200 Subject: module: Restore the moduleparam prefix length check The moduleparam code allows modules to provide their own definition of MODULE_PARAM_PREFIX, instead of using the default KBUILD_MODNAME ".". Commit 730b69d22525 ("module: check kernel param length at compile time, not runtime") added a check to ensure the prefix doesn't exceed MODULE_NAME_LEN, as this is what param_sysfs_builtin() expects. Later, commit 58f86cc89c33 ("VERIFY_OCTAL_PERMISSIONS: stricter checking for sysfs perms.") removed this check, but there is no indication this was intentional. Since the check is still useful for param_sysfs_builtin() to function properly, reintroduce it in __module_param_call(), but in a modernized form using static_assert(). While here, clean up the __module_param_call() comments. In particular, remove the comment "Default value instead of permissions?", which comes from commit 9774a1f54f17 ("[PATCH] Compile-time check re world-writeable module params"). This comment was related to the test variable __param_perm_check_##name, which was removed in the previously mentioned commit 58f86cc89c33. Fixes: 58f86cc89c33 ("VERIFY_OCTAL_PERMISSIONS: stricter checking for sysfs perms.") Signed-off-by: Petr Pavlu Reviewed-by: Daniel Gomez Link: https://lore.kernel.org/r/20250630143535.267745-4-petr.pavlu@suse.com Signed-off-by: Daniel Gomez --- include/linux/moduleparam.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index bfb85fd13e1f..110e9d09de24 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -282,10 +282,9 @@ struct kparam_array #define __moduleparam_const const #endif -/* This is the fundamental function for registering boot/module - parameters. */ +/* This is the fundamental function for registering boot/module parameters. */ #define __module_param_call(prefix, name, ops, arg, perm, level, flags) \ - /* Default value instead of permissions? */ \ + static_assert(sizeof(""prefix) - 1 <= MAX_PARAM_PREFIX_LEN); \ static const char __param_str_##name[] = prefix #name; \ static struct kernel_param __moduleparam_const __param_##name \ __used __section("__param") \ -- cgit v1.2.3 From 40a826bd6c82ae45cfd3a19cd2a60a10f56b74c0 Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Mon, 30 Jun 2025 16:32:36 +0200 Subject: module: Rename MAX_PARAM_PREFIX_LEN to __MODULE_NAME_LEN The maximum module name length (MODULE_NAME_LEN) is somewhat confusingly defined in terms of the maximum parameter prefix length (MAX_PARAM_PREFIX_LEN), when in fact the dependency is in the opposite direction. This split originates from commit 730b69d22525 ("module: check kernel param length at compile time, not runtime"). The code needed to use MODULE_NAME_LEN in moduleparam.h, but because module.h requires moduleparam.h, this created a circular dependency. It was resolved by introducing MAX_PARAM_PREFIX_LEN in moduleparam.h and defining MODULE_NAME_LEN in module.h in terms of MAX_PARAM_PREFIX_LEN. Rename MAX_PARAM_PREFIX_LEN to __MODULE_NAME_LEN for clarity. This matches the similar approach of defining MODULE_INFO in module.h and __MODULE_INFO in moduleparam.h. Signed-off-by: Petr Pavlu Reviewed-by: Daniel Gomez Link: https://lore.kernel.org/r/20250630143535.267745-6-petr.pavlu@suse.com Signed-off-by: Daniel Gomez --- include/linux/module.h | 2 +- include/linux/moduleparam.h | 12 ++++++++---- 2 files changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 5fe812de2d84..313ecb8e5181 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -33,7 +33,7 @@ #include #include -#define MODULE_NAME_LEN MAX_PARAM_PREFIX_LEN +#define MODULE_NAME_LEN __MODULE_NAME_LEN struct modversion_info { unsigned long crc; diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 110e9d09de24..a04a2bc4f51e 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -6,6 +6,13 @@ #include #include +/* + * The maximum module name length, including the NUL byte. + * Chosen so that structs with an unsigned long line up, specifically + * modversion_info. + */ +#define __MODULE_NAME_LEN (64 - sizeof(unsigned long)) + /* You can override this manually, but generally this should match the module name. */ #ifdef MODULE @@ -17,9 +24,6 @@ #define __MODULE_INFO_PREFIX KBUILD_MODNAME "." #endif -/* Chosen so that structs with an unsigned long line up. */ -#define MAX_PARAM_PREFIX_LEN (64 - sizeof(unsigned long)) - #define __MODULE_INFO(tag, name, info) \ static const char __UNIQUE_ID(name)[] \ __used __section(".modinfo") __aligned(1) \ @@ -284,7 +288,7 @@ struct kparam_array /* This is the fundamental function for registering boot/module parameters. */ #define __module_param_call(prefix, name, ops, arg, perm, level, flags) \ - static_assert(sizeof(""prefix) - 1 <= MAX_PARAM_PREFIX_LEN); \ + static_assert(sizeof(""prefix) - 1 <= __MODULE_NAME_LEN); \ static const char __param_str_##name[] = prefix #name; \ static struct kernel_param __moduleparam_const __param_##name \ __used __section("__param") \ -- cgit v1.2.3 From b9c73524106e1c0c857006fb9ff2e5a510dc4021 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 29 Jul 2025 14:23:07 -0400 Subject: unwind_user/deferred: Add unwind cache Cache the results of the unwind to ensure the unwind is only performed once, even when called by multiple tracers. The cache nr_entries gets cleared every time the task exits the kernel. When a stacktrace is requested, nr_entries gets set to the number of entries in the stacktrace. If another stacktrace is requested, if nr_entries is not zero, then it contains the same stacktrace that would be retrieved so it is not processed again and the entries is given to the caller. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Jiri Olsa Cc: Arnaldo Carvalho de Melo Cc: Namhyung Kim Cc: Thomas Gleixner Cc: Andrii Nakryiko Cc: Indu Bhagat Cc: "Jose E. Marchesi" Cc: Beau Belgrave Cc: Linus Torvalds Cc: Andrew Morton Cc: Jens Axboe Cc: Florian Weimer Cc: Sam James Link: https://lore.kernel.org/20250729182405.319691167@kernel.org Reviewed-by: Jens Remus Reviewed-By: Indu Bhagat Co-developed-by: Steven Rostedt (Google) Signed-off-by: Josh Poimboeuf Signed-off-by: Steven Rostedt (Google) --- include/linux/entry-common.h | 2 ++ include/linux/unwind_deferred.h | 8 ++++++++ include/linux/unwind_deferred_types.h | 7 ++++++- kernel/unwind/deferred.c | 31 ++++++++++++++++++++++++------- 4 files changed, 40 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index f94f3fdf15fc..8908b8eeb99b 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -12,6 +12,7 @@ #include #include #include +#include #include #include @@ -362,6 +363,7 @@ static __always_inline void exit_to_user_mode(void) lockdep_hardirqs_on_prepare(); instrumentation_end(); + unwind_reset_info(); user_enter_irqoff(); arch_exit_to_user_mode(); lockdep_hardirqs_on(CALLER_ADDR0); diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h index a5f6e8f8a1a2..baacf4a1eb4c 100644 --- a/include/linux/unwind_deferred.h +++ b/include/linux/unwind_deferred.h @@ -12,6 +12,12 @@ void unwind_task_free(struct task_struct *task); int unwind_user_faultable(struct unwind_stacktrace *trace); +static __always_inline void unwind_reset_info(void) +{ + if (unlikely(current->unwind_info.cache)) + current->unwind_info.cache->nr_entries = 0; +} + #else /* !CONFIG_UNWIND_USER */ static inline void unwind_task_init(struct task_struct *task) {} @@ -19,6 +25,8 @@ static inline void unwind_task_free(struct task_struct *task) {} static inline int unwind_user_faultable(struct unwind_stacktrace *trace) { return -ENOSYS; } +static inline void unwind_reset_info(void) {} + #endif /* !CONFIG_UNWIND_USER */ #endif /* _LINUX_UNWIND_USER_DEFERRED_H */ diff --git a/include/linux/unwind_deferred_types.h b/include/linux/unwind_deferred_types.h index aa32db574e43..db5b54b18828 100644 --- a/include/linux/unwind_deferred_types.h +++ b/include/linux/unwind_deferred_types.h @@ -2,8 +2,13 @@ #ifndef _LINUX_UNWIND_USER_DEFERRED_TYPES_H #define _LINUX_UNWIND_USER_DEFERRED_TYPES_H +struct unwind_cache { + unsigned int nr_entries; + unsigned long entries[]; +}; + struct unwind_task_info { - unsigned long *entries; + struct unwind_cache *cache; }; #endif /* _LINUX_UNWIND_USER_DEFERRED_TYPES_H */ diff --git a/kernel/unwind/deferred.c b/kernel/unwind/deferred.c index a0badbeb3cc1..96368a5aa522 100644 --- a/kernel/unwind/deferred.c +++ b/kernel/unwind/deferred.c @@ -4,10 +4,13 @@ */ #include #include +#include #include #include -#define UNWIND_MAX_ENTRIES 512 +/* Make the cache fit in a 4K page */ +#define UNWIND_MAX_ENTRIES \ + ((SZ_4K - sizeof(struct unwind_cache)) / sizeof(long)) /** * unwind_user_faultable - Produce a user stacktrace in faultable context @@ -24,6 +27,7 @@ int unwind_user_faultable(struct unwind_stacktrace *trace) { struct unwind_task_info *info = ¤t->unwind_info; + struct unwind_cache *cache; /* Should always be called from faultable context */ might_fault(); @@ -31,17 +35,30 @@ int unwind_user_faultable(struct unwind_stacktrace *trace) if (current->flags & PF_EXITING) return -EINVAL; - if (!info->entries) { - info->entries = kmalloc_array(UNWIND_MAX_ENTRIES, sizeof(long), - GFP_KERNEL); - if (!info->entries) + if (!info->cache) { + info->cache = kzalloc(struct_size(cache, entries, UNWIND_MAX_ENTRIES), + GFP_KERNEL); + if (!info->cache) return -ENOMEM; } + cache = info->cache; + trace->entries = cache->entries; + + if (cache->nr_entries) { + /* + * The user stack has already been previously unwound in this + * entry context. Skip the unwind and use the cache. + */ + trace->nr = cache->nr_entries; + return 0; + } + trace->nr = 0; - trace->entries = info->entries; unwind_user(trace, UNWIND_MAX_ENTRIES); + cache->nr_entries = trace->nr; + return 0; } @@ -56,5 +73,5 @@ void unwind_task_free(struct task_struct *task) { struct unwind_task_info *info = &task->unwind_info; - kfree(info->entries); + kfree(info->cache); } -- cgit v1.2.3 From 2dffa355f6c279e7d2e574abf9446c41a631c9e5 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 29 Jul 2025 14:23:08 -0400 Subject: unwind_user/deferred: Add deferred unwinding interface Add an interface for scheduling task work to unwind the user space stack before returning to user space. This solves several problems for its callers: - Ensure the unwind happens in task context even if the caller may be running in interrupt context. - Avoid duplicate unwinds, whether called multiple times by the same caller or by different callers. - Create a "context cookie" which allows trace post-processing to correlate kernel unwinds/traces with the user unwind. A concept of a "cookie" is created to detect when the stacktrace is the same. A cookie is generated the first time a user space stacktrace is requested after the task enters the kernel. As the stacktrace is saved on the task_struct while the task is in the kernel, if another request comes in, if the cookie is still the same, it will use the saved stacktrace, and not have to regenerate one. The cookie is passed to the caller on request, and when the stacktrace is generated upon returning to user space, it calls the requester's callback with the cookie as well as the stacktrace. The cookie is cleared when it goes back to user space. Note, this currently adds another conditional to the unwind_reset_info() path that is always called returning to user space, but future changes will put this back to a single conditional. A global list is created and protected by a global mutex that holds tracers that register with the unwind infrastructure. The number of registered tracers will be limited in future changes. Each perf program or ftrace instance will register its own descriptor to use for deferred unwind stack traces. Note, in the function unwind_deferred_task_work() that gets called when returning to user space, it uses a global mutex for synchronization which will cause a big bottleneck. This will be replaced by SRCU, but that change adds some complex synchronization that deservers its own commit. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Jiri Olsa Cc: Arnaldo Carvalho de Melo Cc: Namhyung Kim Cc: Thomas Gleixner Cc: Andrii Nakryiko Cc: Indu Bhagat Cc: "Jose E. Marchesi" Cc: Beau Belgrave Cc: Jens Remus Cc: Linus Torvalds Cc: Andrew Morton Cc: Jens Axboe Cc: Florian Weimer Cc: Sam James Link: https://lore.kernel.org/20250729182405.488066537@kernel.org Co-developed-by: Steven Rostedt (Google) Signed-off-by: Josh Poimboeuf Signed-off-by: Steven Rostedt (Google) --- include/linux/unwind_deferred.h | 24 ++++++ include/linux/unwind_deferred_types.h | 24 ++++++ kernel/unwind/deferred.c | 156 +++++++++++++++++++++++++++++++++- 3 files changed, 203 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h index baacf4a1eb4c..14efd8c027aa 100644 --- a/include/linux/unwind_deferred.h +++ b/include/linux/unwind_deferred.h @@ -2,9 +2,19 @@ #ifndef _LINUX_UNWIND_USER_DEFERRED_H #define _LINUX_UNWIND_USER_DEFERRED_H +#include #include #include +struct unwind_work; + +typedef void (*unwind_callback_t)(struct unwind_work *work, struct unwind_stacktrace *trace, u64 cookie); + +struct unwind_work { + struct list_head list; + unwind_callback_t func; +}; + #ifdef CONFIG_UNWIND_USER void unwind_task_init(struct task_struct *task); @@ -12,8 +22,19 @@ void unwind_task_free(struct task_struct *task); int unwind_user_faultable(struct unwind_stacktrace *trace); +int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func); +int unwind_deferred_request(struct unwind_work *work, u64 *cookie); +void unwind_deferred_cancel(struct unwind_work *work); + static __always_inline void unwind_reset_info(void) { + if (unlikely(current->unwind_info.id.id)) + current->unwind_info.id.id = 0; + /* + * As unwind_user_faultable() can be called directly and + * depends on nr_entries being cleared on exit to user, + * this needs to be a separate conditional. + */ if (unlikely(current->unwind_info.cache)) current->unwind_info.cache->nr_entries = 0; } @@ -24,6 +45,9 @@ static inline void unwind_task_init(struct task_struct *task) {} static inline void unwind_task_free(struct task_struct *task) {} static inline int unwind_user_faultable(struct unwind_stacktrace *trace) { return -ENOSYS; } +static inline int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func) { return -ENOSYS; } +static inline int unwind_deferred_request(struct unwind_work *work, u64 *timestamp) { return -ENOSYS; } +static inline void unwind_deferred_cancel(struct unwind_work *work) {} static inline void unwind_reset_info(void) {} diff --git a/include/linux/unwind_deferred_types.h b/include/linux/unwind_deferred_types.h index db5b54b18828..104c477d5609 100644 --- a/include/linux/unwind_deferred_types.h +++ b/include/linux/unwind_deferred_types.h @@ -7,8 +7,32 @@ struct unwind_cache { unsigned long entries[]; }; +/* + * The unwind_task_id is a unique identifier that maps to a user space + * stacktrace. It is generated the first time a deferred user space + * stacktrace is requested after a task has entered the kerenl and + * is cleared to zero when it exits. The mapped id will be a non-zero + * number. + * + * To simplify the generation of the 64 bit number, 32 bits will be + * the CPU it was generated on, and the other 32 bits will be a per + * cpu counter that gets incremented by two every time a new identifier + * is generated. The LSB will always be set to keep the value + * from being zero. + */ +union unwind_task_id { + struct { + u32 cpu; + u32 cnt; + }; + u64 id; +}; + struct unwind_task_info { struct unwind_cache *cache; + struct callback_head work; + union unwind_task_id id; + int pending; }; #endif /* _LINUX_UNWIND_USER_DEFERRED_TYPES_H */ diff --git a/kernel/unwind/deferred.c b/kernel/unwind/deferred.c index 96368a5aa522..2cbae2ada309 100644 --- a/kernel/unwind/deferred.c +++ b/kernel/unwind/deferred.c @@ -2,16 +2,63 @@ /* * Deferred user space unwinding */ +#include +#include +#include +#include #include #include #include #include -#include +#include /* Make the cache fit in a 4K page */ #define UNWIND_MAX_ENTRIES \ ((SZ_4K - sizeof(struct unwind_cache)) / sizeof(long)) +/* Guards adding to and reading the list of callbacks */ +static DEFINE_MUTEX(callback_mutex); +static LIST_HEAD(callbacks); + +/* + * This is a unique percpu identifier for a given task entry context. + * Conceptually, it's incremented every time the CPU enters the kernel from + * user space, so that each "entry context" on the CPU gets a unique ID. In + * reality, as an optimization, it's only incremented on demand for the first + * deferred unwind request after a given entry-from-user. + * + * It's combined with the CPU id to make a systemwide-unique "context cookie". + */ +static DEFINE_PER_CPU(u32, unwind_ctx_ctr); + +/* + * The context cookie is a unique identifier that is assigned to a user + * space stacktrace. As the user space stacktrace remains the same while + * the task is in the kernel, the cookie is an identifier for the stacktrace. + * Although it is possible for the stacktrace to get another cookie if another + * request is made after the cookie was cleared and before reentering user + * space. + */ +static u64 get_cookie(struct unwind_task_info *info) +{ + u32 cnt = 1; + u32 old = 0; + + if (info->id.cpu) + return info->id.id; + + /* LSB is always set to ensure 0 is an invalid value */ + cnt |= __this_cpu_read(unwind_ctx_ctr) + 2; + if (try_cmpxchg(&info->id.cnt, &old, cnt)) { + /* Update the per cpu counter */ + __this_cpu_write(unwind_ctx_ctr, cnt); + } + /* Interrupts are disabled, the CPU will always be same */ + info->id.cpu = smp_processor_id() + 1; /* Must be non zero */ + + return info->id.id; +} + /** * unwind_user_faultable - Produce a user stacktrace in faultable context * @trace: The descriptor that will store the user stacktrace @@ -62,11 +109,117 @@ int unwind_user_faultable(struct unwind_stacktrace *trace) return 0; } +static void unwind_deferred_task_work(struct callback_head *head) +{ + struct unwind_task_info *info = container_of(head, struct unwind_task_info, work); + struct unwind_stacktrace trace; + struct unwind_work *work; + u64 cookie; + + if (WARN_ON_ONCE(!info->pending)) + return; + + /* Allow work to come in again */ + WRITE_ONCE(info->pending, 0); + + /* + * From here on out, the callback must always be called, even if it's + * just an empty trace. + */ + trace.nr = 0; + trace.entries = NULL; + + unwind_user_faultable(&trace); + + cookie = info->id.id; + + guard(mutex)(&callback_mutex); + list_for_each_entry(work, &callbacks, list) { + work->func(work, &trace, cookie); + } +} + +/** + * unwind_deferred_request - Request a user stacktrace on task kernel exit + * @work: Unwind descriptor requesting the trace + * @cookie: The cookie of the first request made for this task + * + * Schedule a user space unwind to be done in task work before exiting the + * kernel. + * + * The returned @cookie output is the generated cookie of the very first + * request for a user space stacktrace for this task since it entered the + * kernel. It can be from a request by any caller of this infrastructure. + * Its value will also be passed to the callback function. It can be + * used to stitch kernel and user stack traces together in post-processing. + * + * It's valid to call this function multiple times for the same @work within + * the same task entry context. Each call will return the same cookie + * while the task hasn't left the kernel. If the callback is not pending + * because it has already been previously called for the same entry context, + * it will be called again with the same stack trace and cookie. + * + * Return: 1 if the the callback was already queued. + * 0 if the callback successfully was queued. + * Negative if there's an error. + * @cookie holds the cookie of the first request by any user + */ +int unwind_deferred_request(struct unwind_work *work, u64 *cookie) +{ + struct unwind_task_info *info = ¤t->unwind_info; + int ret; + + *cookie = 0; + + if (WARN_ON_ONCE(in_nmi())) + return -EINVAL; + + if ((current->flags & (PF_KTHREAD | PF_EXITING)) || + !user_mode(task_pt_regs(current))) + return -EINVAL; + + guard(irqsave)(); + + *cookie = get_cookie(info); + + /* callback already pending? */ + if (info->pending) + return 1; + + /* The work has been claimed, now schedule it. */ + ret = task_work_add(current, &info->work, TWA_RESUME); + if (WARN_ON_ONCE(ret)) + return ret; + + info->pending = 1; + return 0; +} + +void unwind_deferred_cancel(struct unwind_work *work) +{ + if (!work) + return; + + guard(mutex)(&callback_mutex); + list_del(&work->list); +} + +int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func) +{ + memset(work, 0, sizeof(*work)); + + guard(mutex)(&callback_mutex); + list_add(&work->list, &callbacks); + work->func = func; + return 0; +} + void unwind_task_init(struct task_struct *task) { struct unwind_task_info *info = &task->unwind_info; memset(info, 0, sizeof(*info)); + init_task_work(&info->work, unwind_deferred_task_work); } void unwind_task_free(struct task_struct *task) @@ -74,4 +227,5 @@ void unwind_task_free(struct task_struct *task) struct unwind_task_info *info = &task->unwind_info; kfree(info->cache); + task_work_cancel(task, &info->work); } -- cgit v1.2.3 From be3d526a5b34109cecf3bc23b96f0081ad600a5b Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 29 Jul 2025 14:23:10 -0400 Subject: unwind deferred: Use bitmask to determine which callbacks to call In order to know which registered callback requested a stacktrace for when the task goes back to user space, add a bitmask to keep track of all registered tracers. The bitmask is the size of long, which means that on a 32 bit machine, it can have at most 32 registered tracers, and on 64 bit, it can have at most 64 registered tracers. This should not be an issue as there should not be more than 10 (unless BPF can abuse this?). When a tracer registers with unwind_deferred_init() it will get a bit number assigned to it. When a tracer requests a stacktrace, it will have its bit set within the task_struct. When the task returns back to user space, it will call the callbacks for all the registered tracers where their bits are set in the task's mask. When a tracer is removed by the unwind_deferred_cancel() all current tasks will clear the associated bit, just in case another tracer gets registered immediately afterward and then gets their callback called unexpectedly. To prevent live locks from happening if an event that happens between the task_work and when the task goes back to user space, triggers the deferred unwind, have the unwind_mask get cleared on exit to user space and not after the callback is made. Move the pending bit from a value on the task_struct to bit zero of the unwind_mask (saves space on the task_struct). This will allow modifying the pending bit along with the work bits atomically. Instead of clearing a work's bit after its callback is called, it is delayed until exit. If the work is requested again, the task_work is not queued again and the request will be notified that the task has already been called by returning a positive number (the same as if it was already pending). The pending bit is cleared before calling the callback functions but the current work bits remain. If one of the called works registers again, it will not trigger a task_work if its bit is still present in the task's unwind_mask. If a new work requests a deferred unwind, then it will set both the pending bit and its own bit. Note this will also cause any work that was previously queued and had their callback already executed to be executed again. Future work will remove these spurious callbacks. The use of atomic_long bit operations were suggested by Peter Zijlstra: Link: https://lore.kernel.org/all/20250715102912.GQ1613200@noisy.programming.kicks-ass.net/ The unwind_mask could not be converted to atomic_long_t do to atomic_long not having all the bit operations needed by unwind_mask. Instead it follows other use cases in the kernel and just typecasts the unwind_mask to atomic_long_t when using the two atomic_long functions. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Jiri Olsa Cc: Arnaldo Carvalho de Melo Cc: Namhyung Kim Cc: Thomas Gleixner Cc: Andrii Nakryiko Cc: Indu Bhagat Cc: "Jose E. Marchesi" Cc: Beau Belgrave Cc: Jens Remus Cc: Linus Torvalds Cc: Andrew Morton Cc: Jens Axboe Cc: Florian Weimer Cc: Sam James Link: https://lore.kernel.org/20250729182405.822789300@kernel.org Signed-off-by: Steven Rostedt (Google) --- include/linux/unwind_deferred.h | 26 +++++++++-- include/linux/unwind_deferred_types.h | 2 +- kernel/unwind/deferred.c | 87 +++++++++++++++++++++++++++-------- 3 files changed, 92 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h index 14efd8c027aa..337ead927d4d 100644 --- a/include/linux/unwind_deferred.h +++ b/include/linux/unwind_deferred.h @@ -13,10 +13,19 @@ typedef void (*unwind_callback_t)(struct unwind_work *work, struct unwind_stackt struct unwind_work { struct list_head list; unwind_callback_t func; + int bit; }; #ifdef CONFIG_UNWIND_USER +enum { + UNWIND_PENDING_BIT = 0, +}; + +enum { + UNWIND_PENDING = BIT(UNWIND_PENDING_BIT), +}; + void unwind_task_init(struct task_struct *task); void unwind_task_free(struct task_struct *task); @@ -28,15 +37,26 @@ void unwind_deferred_cancel(struct unwind_work *work); static __always_inline void unwind_reset_info(void) { - if (unlikely(current->unwind_info.id.id)) + struct unwind_task_info *info = ¤t->unwind_info; + unsigned long bits; + + /* Was there any unwinding? */ + if (unlikely(info->unwind_mask)) { + bits = info->unwind_mask; + do { + /* Is a task_work going to run again before going back */ + if (bits & UNWIND_PENDING) + return; + } while (!try_cmpxchg(&info->unwind_mask, &bits, 0UL)); current->unwind_info.id.id = 0; + } /* * As unwind_user_faultable() can be called directly and * depends on nr_entries being cleared on exit to user, * this needs to be a separate conditional. */ - if (unlikely(current->unwind_info.cache)) - current->unwind_info.cache->nr_entries = 0; + if (unlikely(info->cache)) + info->cache->nr_entries = 0; } #else /* !CONFIG_UNWIND_USER */ diff --git a/include/linux/unwind_deferred_types.h b/include/linux/unwind_deferred_types.h index 104c477d5609..5dc9cda141ff 100644 --- a/include/linux/unwind_deferred_types.h +++ b/include/linux/unwind_deferred_types.h @@ -29,10 +29,10 @@ union unwind_task_id { }; struct unwind_task_info { + unsigned long unwind_mask; struct unwind_cache *cache; struct callback_head work; union unwind_task_id id; - int pending; }; #endif /* _LINUX_UNWIND_USER_DEFERRED_TYPES_H */ diff --git a/kernel/unwind/deferred.c b/kernel/unwind/deferred.c index c5ac087d2396..e19f02ef416d 100644 --- a/kernel/unwind/deferred.c +++ b/kernel/unwind/deferred.c @@ -45,6 +45,16 @@ static inline bool try_assign_cnt(struct unwind_task_info *info, u32 cnt) static DEFINE_MUTEX(callback_mutex); static LIST_HEAD(callbacks); +#define RESERVED_BITS (UNWIND_PENDING) + +/* Zero'd bits are available for assigning callback users */ +static unsigned long unwind_mask = RESERVED_BITS; + +static inline bool unwind_pending(struct unwind_task_info *info) +{ + return test_bit(UNWIND_PENDING_BIT, &info->unwind_mask); +} + /* * This is a unique percpu identifier for a given task entry context. * Conceptually, it's incremented every time the CPU enters the kernel from @@ -138,14 +148,15 @@ static void unwind_deferred_task_work(struct callback_head *head) struct unwind_task_info *info = container_of(head, struct unwind_task_info, work); struct unwind_stacktrace trace; struct unwind_work *work; + unsigned long bits; u64 cookie; - if (WARN_ON_ONCE(!info->pending)) + if (WARN_ON_ONCE(!unwind_pending(info))) return; - /* Allow work to come in again */ - WRITE_ONCE(info->pending, 0); - + /* Clear pending bit but make sure to have the current bits */ + bits = atomic_long_fetch_andnot(UNWIND_PENDING, + (atomic_long_t *)&info->unwind_mask); /* * From here on out, the callback must always be called, even if it's * just an empty trace. @@ -159,7 +170,8 @@ static void unwind_deferred_task_work(struct callback_head *head) guard(mutex)(&callback_mutex); list_for_each_entry(work, &callbacks, list) { - work->func(work, &trace, cookie); + if (test_bit(work->bit, &bits)) + work->func(work, &trace, cookie); } } @@ -183,15 +195,16 @@ static void unwind_deferred_task_work(struct callback_head *head) * because it has already been previously called for the same entry context, * it will be called again with the same stack trace and cookie. * - * Return: 1 if the the callback was already queued. - * 0 if the callback successfully was queued. + * Return: 0 if the callback successfully was queued. + * 1 if the callback is pending or was already executed. * Negative if there's an error. * @cookie holds the cookie of the first request by any user */ int unwind_deferred_request(struct unwind_work *work, u64 *cookie) { struct unwind_task_info *info = ¤t->unwind_info; - long pending; + unsigned long old, bits; + unsigned long bit = BIT(work->bit); int ret; *cookie = 0; @@ -212,32 +225,59 @@ int unwind_deferred_request(struct unwind_work *work, u64 *cookie) *cookie = get_cookie(info); - /* callback already pending? */ - pending = READ_ONCE(info->pending); - if (pending) - return 1; + old = READ_ONCE(info->unwind_mask); - /* Claim the work unless an NMI just now swooped in to do so. */ - if (!try_cmpxchg(&info->pending, &pending, 1)) + /* Is this already queued or executed */ + if (old & bit) return 1; + /* + * This work's bit hasn't been set yet. Now set it with the PENDING + * bit and fetch the current value of unwind_mask. If ether the + * work's bit or PENDING was already set, then this is already queued + * to have a callback. + */ + bits = UNWIND_PENDING | bit; + old = atomic_long_fetch_or(bits, (atomic_long_t *)&info->unwind_mask); + if (old & bits) { + /* + * If the work's bit was set, whatever set it had better + * have also set pending and queued a callback. + */ + WARN_ON_ONCE(!(old & UNWIND_PENDING)); + return old & bit; + } + /* The work has been claimed, now schedule it. */ ret = task_work_add(current, &info->work, TWA_RESUME); - if (WARN_ON_ONCE(ret)) { - WRITE_ONCE(info->pending, 0); - return ret; - } - return 0; + if (WARN_ON_ONCE(ret)) + WRITE_ONCE(info->unwind_mask, 0); + + return ret; } void unwind_deferred_cancel(struct unwind_work *work) { + struct task_struct *g, *t; + if (!work) return; + /* No work should be using a reserved bit */ + if (WARN_ON_ONCE(BIT(work->bit) & RESERVED_BITS)) + return; + guard(mutex)(&callback_mutex); list_del(&work->list); + + __clear_bit(work->bit, &unwind_mask); + + guard(rcu)(); + /* Clear this bit from all threads */ + for_each_process_thread(g, t) { + clear_bit(work->bit, &t->unwind_info.unwind_mask); + } } int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func) @@ -245,6 +285,14 @@ int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func) memset(work, 0, sizeof(*work)); guard(mutex)(&callback_mutex); + + /* See if there's a bit in the mask available */ + if (unwind_mask == ~0UL) + return -EBUSY; + + work->bit = ffz(unwind_mask); + __set_bit(work->bit, &unwind_mask); + list_add(&work->list, &callbacks); work->func = func; return 0; @@ -256,6 +304,7 @@ void unwind_task_init(struct task_struct *task) memset(info, 0, sizeof(*info)); init_task_work(&info->work, unwind_deferred_task_work); + info->unwind_mask = 0; } void unwind_task_free(struct task_struct *task) -- cgit v1.2.3 From 4c75133e745aa95636c9ccbab1603ed363dabcd4 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 29 Jul 2025 14:23:11 -0400 Subject: unwind deferred: Add unwind_completed mask to stop spurious callbacks If there's more than one registered tracer to the unwind deferred infrastructure, it is currently possible that one tracer could cause extra callbacks to happen for another tracer if the former requests a deferred stacktrace after the latter's callback was executed and before the task went back to user space. Here's an example of how this could occur: [Task enters kernel] tracer 1 request -> add cookie to its buffer tracer 1 request -> add cookie to its buffer <..> [ task work executes ] tracer 1 callback -> add trace + cookie to its buffer [tracer 2 requests and triggers the task work again] [ task work executes again ] tracer 1 callback -> add trace + cookie to its buffer tracer 2 callback -> add trace + cookie to its buffer [Task exits back to user space] This is because the bit for tracer 1 gets set in the task's unwind_mask when it did its request and does not get cleared until the task returns back to user space. But if another tracer were to request another deferred stacktrace, then the next task work will executed all tracer's callbacks that have their bits set in the task's unwind_mask. To fix this issue, add another mask called unwind_completed and place it into the task's info->cache structure. The cache structure is allocated on the first occurrence of a deferred stacktrace and this unwind_completed mask is not needed until then. It's better to have it in the cache than to permanently waste space in the task_struct. After a tracer's callback is executed, it's bit gets set in this unwind_completed mask. When the task_work enters, it will AND the task's unwind_mask with the inverse of the unwind_completed which will eliminate any work that already had its callback executed since the task entered the kernel. When the task leaves the kernel, it will reset this unwind_completed mask just like it resets the other values as it enters user space. Link: https://lore.kernel.org/all/20250716142609.47f0e4a5@batman.local.home/ Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Jiri Olsa Cc: Arnaldo Carvalho de Melo Cc: Namhyung Kim Cc: Thomas Gleixner Cc: Andrii Nakryiko Cc: Indu Bhagat Cc: "Jose E. Marchesi" Cc: Beau Belgrave Cc: Jens Remus Cc: Linus Torvalds Cc: Andrew Morton Cc: Jens Axboe Cc: Florian Weimer Cc: Sam James Link: https://lore.kernel.org/20250729182405.989222722@kernel.org Signed-off-by: Steven Rostedt (Google) --- include/linux/unwind_deferred.h | 4 +++- include/linux/unwind_deferred_types.h | 1 + kernel/unwind/deferred.c | 19 +++++++++++++++---- 3 files changed, 19 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h index 337ead927d4d..b9ec4c8515c7 100644 --- a/include/linux/unwind_deferred.h +++ b/include/linux/unwind_deferred.h @@ -55,8 +55,10 @@ static __always_inline void unwind_reset_info(void) * depends on nr_entries being cleared on exit to user, * this needs to be a separate conditional. */ - if (unlikely(info->cache)) + if (unlikely(info->cache)) { info->cache->nr_entries = 0; + info->cache->unwind_completed = 0; + } } #else /* !CONFIG_UNWIND_USER */ diff --git a/include/linux/unwind_deferred_types.h b/include/linux/unwind_deferred_types.h index 5dc9cda141ff..33b62ac25c86 100644 --- a/include/linux/unwind_deferred_types.h +++ b/include/linux/unwind_deferred_types.h @@ -3,6 +3,7 @@ #define _LINUX_UNWIND_USER_DEFERRED_TYPES_H struct unwind_cache { + unsigned long unwind_completed; unsigned int nr_entries; unsigned long entries[]; }; diff --git a/kernel/unwind/deferred.c b/kernel/unwind/deferred.c index e19f02ef416d..a3d26014a2e6 100644 --- a/kernel/unwind/deferred.c +++ b/kernel/unwind/deferred.c @@ -166,12 +166,18 @@ static void unwind_deferred_task_work(struct callback_head *head) unwind_user_faultable(&trace); + if (info->cache) + bits &= ~(info->cache->unwind_completed); + cookie = info->id.id; guard(mutex)(&callback_mutex); list_for_each_entry(work, &callbacks, list) { - if (test_bit(work->bit, &bits)) + if (test_bit(work->bit, &bits)) { work->func(work, &trace, cookie); + if (info->cache) + info->cache->unwind_completed |= BIT(work->bit); + } } } @@ -260,23 +266,28 @@ int unwind_deferred_request(struct unwind_work *work, u64 *cookie) void unwind_deferred_cancel(struct unwind_work *work) { struct task_struct *g, *t; + int bit; if (!work) return; + bit = work->bit; + /* No work should be using a reserved bit */ - if (WARN_ON_ONCE(BIT(work->bit) & RESERVED_BITS)) + if (WARN_ON_ONCE(BIT(bit) & RESERVED_BITS)) return; guard(mutex)(&callback_mutex); list_del(&work->list); - __clear_bit(work->bit, &unwind_mask); + __clear_bit(bit, &unwind_mask); guard(rcu)(); /* Clear this bit from all threads */ for_each_process_thread(g, t) { - clear_bit(work->bit, &t->unwind_info.unwind_mask); + clear_bit(bit, &t->unwind_info.unwind_mask); + if (t->unwind_info.cache) + clear_bit(bit, &t->unwind_info.cache->unwind_completed); } } -- cgit v1.2.3 From 858fa8a3b083e862114bb6483b9fb50b3e2bc4c3 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 29 Jul 2025 14:23:12 -0400 Subject: unwind: Add USED bit to only have one conditional on way back to user space On the way back to user space, the function unwind_reset_info() is called unconditionally (but always inlined). It currently has two conditionals. One that checks the unwind_mask which is set whenever a deferred trace is called and is used to know that the mask needs to be cleared. The other checks if the cache has been allocated, and if so, it resets the nr_entries so that the unwinder knows it needs to do the work to get a new user space stack trace again (it only does it once per entering the kernel). Use one of the bits in the unwind mask as a "USED" bit that gets set whenever a trace is created. This will make it possible to only check the unwind_mask in the unwind_reset_info() to know if it needs to do work or not and eliminates a conditional that happens every time the task goes back to user space. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Jiri Olsa Cc: Arnaldo Carvalho de Melo Cc: Namhyung Kim Cc: Thomas Gleixner Cc: Andrii Nakryiko Cc: Indu Bhagat Cc: "Jose E. Marchesi" Cc: Beau Belgrave Cc: Jens Remus Cc: Linus Torvalds Cc: Andrew Morton Cc: Jens Axboe Cc: Florian Weimer Cc: Sam James Link: https://lore.kernel.org/20250729182406.155422551@kernel.org Signed-off-by: Steven Rostedt (Google) --- include/linux/unwind_deferred.h | 18 +++++++++--------- kernel/unwind/deferred.c | 5 ++++- 2 files changed, 13 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h index b9ec4c8515c7..2efbda01e959 100644 --- a/include/linux/unwind_deferred.h +++ b/include/linux/unwind_deferred.h @@ -20,10 +20,14 @@ struct unwind_work { enum { UNWIND_PENDING_BIT = 0, + UNWIND_USED_BIT, }; enum { UNWIND_PENDING = BIT(UNWIND_PENDING_BIT), + + /* Set if the unwinding was used (directly or deferred) */ + UNWIND_USED = BIT(UNWIND_USED_BIT) }; void unwind_task_init(struct task_struct *task); @@ -49,15 +53,11 @@ static __always_inline void unwind_reset_info(void) return; } while (!try_cmpxchg(&info->unwind_mask, &bits, 0UL)); current->unwind_info.id.id = 0; - } - /* - * As unwind_user_faultable() can be called directly and - * depends on nr_entries being cleared on exit to user, - * this needs to be a separate conditional. - */ - if (unlikely(info->cache)) { - info->cache->nr_entries = 0; - info->cache->unwind_completed = 0; + + if (unlikely(info->cache)) { + info->cache->nr_entries = 0; + info->cache->unwind_completed = 0; + } } } diff --git a/kernel/unwind/deferred.c b/kernel/unwind/deferred.c index a3d26014a2e6..2311b725d691 100644 --- a/kernel/unwind/deferred.c +++ b/kernel/unwind/deferred.c @@ -45,7 +45,7 @@ static inline bool try_assign_cnt(struct unwind_task_info *info, u32 cnt) static DEFINE_MUTEX(callback_mutex); static LIST_HEAD(callbacks); -#define RESERVED_BITS (UNWIND_PENDING) +#define RESERVED_BITS (UNWIND_PENDING | UNWIND_USED) /* Zero'd bits are available for assigning callback users */ static unsigned long unwind_mask = RESERVED_BITS; @@ -140,6 +140,9 @@ int unwind_user_faultable(struct unwind_stacktrace *trace) cache->nr_entries = trace->nr; + /* Clear nr_entries on way back to user space */ + set_bit(UNWIND_USED_BIT, &info->unwind_mask); + return 0; } -- cgit v1.2.3 From b3b9cb11aa034cfa9eb880bb9bb3d5aaf732e479 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 29 Jul 2025 14:23:14 -0400 Subject: unwind: Finish up unwind when a task exits On do_exit() when a task is exiting, if a unwind is requested and the deferred user stacktrace is deferred via the task_work, the task_work callback is called after exit_mm() is called in do_exit(). This means that the user stack trace will not be retrieved and an empty stack is created. Instead, add a function unwind_deferred_task_exit() and call it just before exit_mm() so that the unwinder can call the requested callbacks with the user space stack. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Jiri Olsa Cc: Arnaldo Carvalho de Melo Cc: Namhyung Kim Cc: Thomas Gleixner Cc: Andrii Nakryiko Cc: Indu Bhagat Cc: "Jose E. Marchesi" Cc: Beau Belgrave Cc: Jens Remus Cc: Linus Torvalds Cc: Andrew Morton Cc: Jens Axboe Cc: Florian Weimer Cc: Sam James Link: https://lore.kernel.org/20250729182406.504259474@kernel.org Signed-off-by: Steven Rostedt (Google) --- include/linux/unwind_deferred.h | 3 +++ kernel/exit.c | 2 ++ kernel/unwind/deferred.c | 23 ++++++++++++++++++++--- 3 files changed, 25 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h index 2efbda01e959..26122d00708a 100644 --- a/include/linux/unwind_deferred.h +++ b/include/linux/unwind_deferred.h @@ -39,6 +39,8 @@ int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func); int unwind_deferred_request(struct unwind_work *work, u64 *cookie); void unwind_deferred_cancel(struct unwind_work *work); +void unwind_deferred_task_exit(struct task_struct *task); + static __always_inline void unwind_reset_info(void) { struct unwind_task_info *info = ¤t->unwind_info; @@ -71,6 +73,7 @@ static inline int unwind_deferred_init(struct unwind_work *work, unwind_callback static inline int unwind_deferred_request(struct unwind_work *work, u64 *timestamp) { return -ENOSYS; } static inline void unwind_deferred_cancel(struct unwind_work *work) {} +static inline void unwind_deferred_task_exit(struct task_struct *task) {} static inline void unwind_reset_info(void) {} #endif /* !CONFIG_UNWIND_USER */ diff --git a/kernel/exit.c b/kernel/exit.c index bb184a67ac73..1d8c8ac33c4f 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -68,6 +68,7 @@ #include #include #include +#include #include #include @@ -938,6 +939,7 @@ void __noreturn do_exit(long code) tsk->exit_code = code; taskstats_exit(tsk, group_dead); + unwind_deferred_task_exit(tsk); trace_sched_process_exit(tsk, group_dead); /* diff --git a/kernel/unwind/deferred.c b/kernel/unwind/deferred.c index a5ef1c1f915e..dc6040aae3ee 100644 --- a/kernel/unwind/deferred.c +++ b/kernel/unwind/deferred.c @@ -114,7 +114,7 @@ int unwind_user_faultable(struct unwind_stacktrace *trace) /* Should always be called from faultable context */ might_fault(); - if (current->flags & PF_EXITING) + if (!current->mm) return -EINVAL; if (!info->cache) { @@ -147,9 +147,9 @@ int unwind_user_faultable(struct unwind_stacktrace *trace) return 0; } -static void unwind_deferred_task_work(struct callback_head *head) +static void process_unwind_deferred(struct task_struct *task) { - struct unwind_task_info *info = container_of(head, struct unwind_task_info, work); + struct unwind_task_info *info = &task->unwind_info; struct unwind_stacktrace trace; struct unwind_work *work; unsigned long bits; @@ -186,6 +186,23 @@ static void unwind_deferred_task_work(struct callback_head *head) } } +static void unwind_deferred_task_work(struct callback_head *head) +{ + process_unwind_deferred(current); +} + +void unwind_deferred_task_exit(struct task_struct *task) +{ + struct unwind_task_info *info = ¤t->unwind_info; + + if (!unwind_pending(info)) + return; + + process_unwind_deferred(task); + + task_work_cancel(task, &info->work); +} + /** * unwind_deferred_request - Request a user stacktrace on task kernel exit * @work: Unwind descriptor requesting the trace -- cgit v1.2.3 From 12df58ad294253ac1d8df0c9bb9cf726397a671d Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 31 Jul 2025 01:47:30 +0200 Subject: bpf: Add cookie object to bpf maps Add a cookie to BPF maps to uniquely identify BPF maps for the timespan when the node is up. This is different to comparing a pointer or BPF map id which could get rolled over and reused. Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/r/20250730234733.530041-1-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + kernel/bpf/syscall.c | 6 ++++++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f9cd2164ed23..308530c8326b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -310,6 +310,7 @@ struct bpf_map { bool free_after_rcu_gp; atomic64_t sleepable_refcnt; s64 __percpu *elem_count; + u64 cookie; /* write-once */ }; static inline const char *btf_field_type_name(enum btf_field_type type) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index e63039817af3..7a814e98d5f5 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include @@ -53,6 +54,7 @@ #define BPF_OBJ_FLAG_MASK (BPF_F_RDONLY | BPF_F_WRONLY) DEFINE_PER_CPU(int, bpf_prog_active); +DEFINE_COOKIE(bpf_map_cookie); static DEFINE_IDR(prog_idr); static DEFINE_SPINLOCK(prog_idr_lock); static DEFINE_IDR(map_idr); @@ -1487,6 +1489,10 @@ static int map_create(union bpf_attr *attr, bool kernel) if (err < 0) goto free_map; + preempt_disable(); + map->cookie = gen_cookie_next(&bpf_map_cookie); + preempt_enable(); + atomic64_set(&map->refcnt, 1); atomic64_set(&map->usercnt, 1); mutex_init(&map->freeze_mutex); -- cgit v1.2.3 From fd1c98f0ef5cbcec842209776505d9e70d8fcd53 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 31 Jul 2025 01:47:31 +0200 Subject: bpf: Move bpf map owner out of common struct Given this is only relevant for BPF tail call maps, it is adding up space and penalizing other map types. We also need to extend this with further objects to track / compare to. Therefore, lets move this out into a separate structure and dynamically allocate it only for BPF tail call maps. Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/r/20250730234733.530041-2-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 36 ++++++++++++++++++++++++------------ kernel/bpf/core.c | 35 ++++++++++++++++++----------------- kernel/bpf/syscall.c | 13 +++++++------ 3 files changed, 49 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 308530c8326b..a87646cc5398 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -260,6 +260,18 @@ struct bpf_list_node_kern { void *owner; } __attribute__((aligned(8))); +/* 'Ownership' of program-containing map is claimed by the first program + * that is going to use this map or by the first program which FD is + * stored in the map to make sure that all callers and callees have the + * same prog type, JITed flag and xdp_has_frags flag. + */ +struct bpf_map_owner { + enum bpf_prog_type type; + bool jited; + bool xdp_has_frags; + const struct btf_type *attach_func_proto; +}; + struct bpf_map { const struct bpf_map_ops *ops; struct bpf_map *inner_map_meta; @@ -292,18 +304,8 @@ struct bpf_map { struct rcu_head rcu; }; atomic64_t writecnt; - /* 'Ownership' of program-containing map is claimed by the first program - * that is going to use this map or by the first program which FD is - * stored in the map to make sure that all callers and callees have the - * same prog type, JITed flag and xdp_has_frags flag. - */ - struct { - const struct btf_type *attach_func_proto; - spinlock_t lock; - enum bpf_prog_type type; - bool jited; - bool xdp_has_frags; - } owner; + spinlock_t owner_lock; + struct bpf_map_owner *owner; bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ bool free_after_mult_rcu_gp; @@ -2109,6 +2111,16 @@ static inline bool bpf_map_flags_access_ok(u32 access_flags) (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG); } +static inline struct bpf_map_owner *bpf_map_owner_alloc(struct bpf_map *map) +{ + return kzalloc(sizeof(*map->owner), GFP_ATOMIC); +} + +static inline void bpf_map_owner_free(struct bpf_map *map) +{ + kfree(map->owner); +} + struct bpf_event_entry { struct perf_event *event; struct file *perf_file; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 09dde5b00d0c..6e5b3a67e87f 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2377,28 +2377,29 @@ static bool __bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp) { enum bpf_prog_type prog_type = resolve_prog_type(fp); - bool ret; struct bpf_prog_aux *aux = fp->aux; + bool ret = false; if (fp->kprobe_override) - return false; + return ret; - spin_lock(&map->owner.lock); - if (!map->owner.type) { - /* There's no owner yet where we could check for - * compatibility. - */ - map->owner.type = prog_type; - map->owner.jited = fp->jited; - map->owner.xdp_has_frags = aux->xdp_has_frags; - map->owner.attach_func_proto = aux->attach_func_proto; + spin_lock(&map->owner_lock); + /* There's no owner yet where we could check for compatibility. */ + if (!map->owner) { + map->owner = bpf_map_owner_alloc(map); + if (!map->owner) + goto err; + map->owner->type = prog_type; + map->owner->jited = fp->jited; + map->owner->xdp_has_frags = aux->xdp_has_frags; + map->owner->attach_func_proto = aux->attach_func_proto; ret = true; } else { - ret = map->owner.type == prog_type && - map->owner.jited == fp->jited && - map->owner.xdp_has_frags == aux->xdp_has_frags; + ret = map->owner->type == prog_type && + map->owner->jited == fp->jited && + map->owner->xdp_has_frags == aux->xdp_has_frags; if (ret && - map->owner.attach_func_proto != aux->attach_func_proto) { + map->owner->attach_func_proto != aux->attach_func_proto) { switch (prog_type) { case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_LSM: @@ -2411,8 +2412,8 @@ static bool __bpf_prog_map_compatible(struct bpf_map *map, } } } - spin_unlock(&map->owner.lock); - +err: + spin_unlock(&map->owner_lock); return ret; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 7a814e98d5f5..0fbfa8532c39 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -887,6 +887,7 @@ static void bpf_map_free_deferred(struct work_struct *work) security_bpf_map_free(map); bpf_map_release_memcg(map); + bpf_map_owner_free(map); bpf_map_free(map); } @@ -981,12 +982,12 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) struct bpf_map *map = filp->private_data; u32 type = 0, jited = 0; - if (map_type_contains_progs(map)) { - spin_lock(&map->owner.lock); - type = map->owner.type; - jited = map->owner.jited; - spin_unlock(&map->owner.lock); + spin_lock(&map->owner_lock); + if (map->owner) { + type = map->owner->type; + jited = map->owner->jited; } + spin_unlock(&map->owner_lock); seq_printf(m, "map_type:\t%u\n" @@ -1496,7 +1497,7 @@ static int map_create(union bpf_attr *attr, bool kernel) atomic64_set(&map->refcnt, 1); atomic64_set(&map->usercnt, 1); mutex_init(&map->freeze_mutex); - spin_lock_init(&map->owner.lock); + spin_lock_init(&map->owner_lock); if (attr->btf_key_type_id || attr->btf_value_type_id || /* Even the map's value is a kernel's struct, -- cgit v1.2.3 From 9621e60f59eae87eb9ffe88d90f24f391a1ef0f0 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 31 Jul 2025 01:47:32 +0200 Subject: bpf: Move cgroup iterator helpers to bpf.h Move them into bpf.h given we also need them in core code. Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/r/20250730234733.530041-3-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov --- include/linux/bpf-cgroup.h | 5 ----- include/linux/bpf.h | 22 ++++++++++++++-------- 2 files changed, 14 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 082ccd8ad96b..aedf573bdb42 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -77,9 +77,6 @@ to_cgroup_bpf_attach_type(enum bpf_attach_type attach_type) extern struct static_key_false cgroup_bpf_enabled_key[MAX_CGROUP_BPF_ATTACH_TYPE]; #define cgroup_bpf_enabled(atype) static_branch_unlikely(&cgroup_bpf_enabled_key[atype]) -#define for_each_cgroup_storage_type(stype) \ - for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++) - struct bpf_cgroup_storage_map; struct bpf_storage_buffer { @@ -510,8 +507,6 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \ kernel_optval) ({ 0; }) -#define for_each_cgroup_storage_type(stype) for (; false; ) - #endif /* CONFIG_CGROUP_BPF */ #endif /* _BPF_CGROUP_H */ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a87646cc5398..02aa41e301a5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -208,6 +208,20 @@ enum btf_field_type { BPF_RES_SPIN_LOCK = (1 << 12), }; +enum bpf_cgroup_storage_type { + BPF_CGROUP_STORAGE_SHARED, + BPF_CGROUP_STORAGE_PERCPU, + __BPF_CGROUP_STORAGE_MAX +#define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX +}; + +#ifdef CONFIG_CGROUP_BPF +# define for_each_cgroup_storage_type(stype) \ + for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++) +#else +# define for_each_cgroup_storage_type(stype) for (; false; ) +#endif /* CONFIG_CGROUP_BPF */ + typedef void (*btf_dtor_kfunc_t)(void *); struct btf_field_kptr { @@ -1085,14 +1099,6 @@ struct bpf_prog_offload { u32 jited_len; }; -enum bpf_cgroup_storage_type { - BPF_CGROUP_STORAGE_SHARED, - BPF_CGROUP_STORAGE_PERCPU, - __BPF_CGROUP_STORAGE_MAX -}; - -#define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX - /* The longest tracepoint has 12 args. * See include/trace/bpf_probe.h */ -- cgit v1.2.3 From abad3d0bad72a52137e0c350c59542d75ae4f513 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 31 Jul 2025 01:47:33 +0200 Subject: bpf: Fix oob access in cgroup local storage Lonial reported that an out-of-bounds access in cgroup local storage can be crafted via tail calls. Given two programs each utilizing a cgroup local storage with a different value size, and one program doing a tail call into the other. The verifier will validate each of the indivial programs just fine. However, in the runtime context the bpf_cg_run_ctx holds an bpf_prog_array_item which contains the BPF program as well as any cgroup local storage flavor the program uses. Helpers such as bpf_get_local_storage() pick this up from the runtime context: ctx = container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx); storage = ctx->prog_item->cgroup_storage[stype]; if (stype == BPF_CGROUP_STORAGE_SHARED) ptr = &READ_ONCE(storage->buf)->data[0]; else ptr = this_cpu_ptr(storage->percpu_buf); For the second program which was called from the originally attached one, this means bpf_get_local_storage() will pick up the former program's map, not its own. With mismatching sizes, this can result in an unintended out-of-bounds access. To fix this issue, we need to extend bpf_map_owner with an array of storage_cookie[] to match on i) the exact maps from the original program if the second program was using bpf_get_local_storage(), or ii) allow the tail call combination if the second program was not using any of the cgroup local storage maps. Fixes: 7d9c3427894f ("bpf: Make cgroup storages shared between programs on the same cgroup") Reported-by: Lonial Con Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/r/20250730234733.530041-4-daniel@iogearbox.net Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + kernel/bpf/core.c | 15 +++++++++++++++ 2 files changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 02aa41e301a5..cc700925b802 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -283,6 +283,7 @@ struct bpf_map_owner { enum bpf_prog_type type; bool jited; bool xdp_has_frags; + u64 storage_cookie[MAX_BPF_CGROUP_STORAGE_TYPE]; const struct btf_type *attach_func_proto; }; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 6e5b3a67e87f..5d1650af899d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2378,7 +2378,9 @@ static bool __bpf_prog_map_compatible(struct bpf_map *map, { enum bpf_prog_type prog_type = resolve_prog_type(fp); struct bpf_prog_aux *aux = fp->aux; + enum bpf_cgroup_storage_type i; bool ret = false; + u64 cookie; if (fp->kprobe_override) return ret; @@ -2393,11 +2395,24 @@ static bool __bpf_prog_map_compatible(struct bpf_map *map, map->owner->jited = fp->jited; map->owner->xdp_has_frags = aux->xdp_has_frags; map->owner->attach_func_proto = aux->attach_func_proto; + for_each_cgroup_storage_type(i) { + map->owner->storage_cookie[i] = + aux->cgroup_storage[i] ? + aux->cgroup_storage[i]->cookie : 0; + } ret = true; } else { ret = map->owner->type == prog_type && map->owner->jited == fp->jited && map->owner->xdp_has_frags == aux->xdp_has_frags; + for_each_cgroup_storage_type(i) { + if (!ret) + break; + cookie = aux->cgroup_storage[i] ? + aux->cgroup_storage[i]->cookie : 0; + ret = map->owner->storage_cookie[i] == cookie || + !cookie; + } if (ret && map->owner->attach_func_proto != aux->attach_func_proto) { switch (prog_type) { -- cgit v1.2.3 From e2ba58ccc9099514380c3300cbc0750b5055fc1c Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Wed, 30 Jul 2025 21:49:53 -0700 Subject: block: Fix default IO priority if there is no IO context Upstream commit 53889bcaf536 ("block: make __get_task_ioprio() easier to read") changes the IO priority returned to the caller if no IO context is defined for the task. Prior to this commit, the returned IO priority was determined by task_nice_ioclass() and task_nice_ioprio(). Now it is always IOPRIO_DEFAULT, which translates to IOPRIO_CLASS_NONE with priority 0. However, task_nice_ioclass() returns IOPRIO_CLASS_IDLE, IOPRIO_CLASS_RT, or IOPRIO_CLASS_BE depending on the task scheduling policy, and task_nice_ioprio() returns a value determined by task_nice(). This causes regressions in test code checking the IO priority and class of IO operations on tasks with no IO context. Fix the problem by returning the IO priority calculated from task_nice_ioclass() and task_nice_ioprio() if no IO context is defined to match earlier behavior. Fixes: 53889bcaf536 ("block: make __get_task_ioprio() easier to read") Cc: Jens Axboe Cc: Bart Van Assche Signed-off-by: Guenter Roeck Reviewed-by: Yu Kuai Reviewed-by: Damien Le Moal Link: https://lore.kernel.org/r/20250731044953.1852690-1-linux@roeck-us.net Signed-off-by: Jens Axboe --- include/linux/ioprio.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index b25377b6ea98..5210e8371238 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -60,7 +60,8 @@ static inline int __get_task_ioprio(struct task_struct *p) int prio; if (!ioc) - return IOPRIO_DEFAULT; + return IOPRIO_PRIO_VALUE(task_nice_ioclass(p), + task_nice_ioprio(p)); if (p != current) lockdep_assert_held(&p->alloc_lock); -- cgit v1.2.3 From 5ccaeedb489b41ce6cb857d0de488992746be282 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 1 Aug 2025 00:10:06 +0000 Subject: cfi: add C CFI type macro Currently x86 and riscv open-code 4 instances of the same logic to define a u32 variable with the KCFI typeid of a given function. Replace the duplicate logic with a common macro. Signed-off-by: Mark Rutland Co-developed-by: Maxwell Bland Signed-off-by: Maxwell Bland Co-developed-by: Sami Tolvanen Signed-off-by: Sami Tolvanen Tested-by: Dao Huang Acked-by: Will Deacon Link: https://lore.kernel.org/r/20250801001004.1859976-6-samitolvanen@google.com Signed-off-by: Alexei Starovoitov --- arch/riscv/kernel/cfi.c | 35 +++-------------------------------- arch/x86/kernel/alternative.c | 31 +++---------------------------- include/linux/cfi_types.h | 23 +++++++++++++++++++++++ 3 files changed, 29 insertions(+), 60 deletions(-) (limited to 'include/linux') diff --git a/arch/riscv/kernel/cfi.c b/arch/riscv/kernel/cfi.c index 64bdd3e1ab8c..e7aec5f36dd5 100644 --- a/arch/riscv/kernel/cfi.c +++ b/arch/riscv/kernel/cfi.c @@ -4,6 +4,7 @@ * * Copyright (C) 2023 Google LLC */ +#include #include #include @@ -82,41 +83,11 @@ struct bpf_insn; /* Must match bpf_func_t / DEFINE_BPF_PROG_RUN() */ extern unsigned int __bpf_prog_runX(const void *ctx, const struct bpf_insn *insn); - -/* - * Force a reference to the external symbol so the compiler generates - * __kcfi_typid. - */ -__ADDRESSABLE(__bpf_prog_runX); - -/* u32 __ro_after_init cfi_bpf_hash = __kcfi_typeid___bpf_prog_runX; */ -asm ( -" .pushsection .data..ro_after_init,\"aw\",@progbits \n" -" .type cfi_bpf_hash,@object \n" -" .globl cfi_bpf_hash \n" -" .p2align 2, 0x0 \n" -"cfi_bpf_hash: \n" -" .word __kcfi_typeid___bpf_prog_runX \n" -" .size cfi_bpf_hash, 4 \n" -" .popsection \n" -); +DEFINE_CFI_TYPE(cfi_bpf_hash, __bpf_prog_runX); /* Must match bpf_callback_t */ extern u64 __bpf_callback_fn(u64, u64, u64, u64, u64); - -__ADDRESSABLE(__bpf_callback_fn); - -/* u32 __ro_after_init cfi_bpf_subprog_hash = __kcfi_typeid___bpf_callback_fn; */ -asm ( -" .pushsection .data..ro_after_init,\"aw\",@progbits \n" -" .type cfi_bpf_subprog_hash,@object \n" -" .globl cfi_bpf_subprog_hash \n" -" .p2align 2, 0x0 \n" -"cfi_bpf_subprog_hash: \n" -" .word __kcfi_typeid___bpf_callback_fn \n" -" .size cfi_bpf_subprog_hash, 4 \n" -" .popsection \n" -); +DEFINE_CFI_TYPE(cfi_bpf_subprog_hash, __bpf_callback_fn); u32 cfi_get_func_hash(void *func) { diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index ea1d984166cd..a555665b4d9c 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -2,6 +2,7 @@ #define pr_fmt(fmt) "SMP alternatives: " fmt #include +#include #include #include #include @@ -1189,37 +1190,11 @@ struct bpf_insn; /* Must match bpf_func_t / DEFINE_BPF_PROG_RUN() */ extern unsigned int __bpf_prog_runX(const void *ctx, const struct bpf_insn *insn); - -KCFI_REFERENCE(__bpf_prog_runX); - -/* u32 __ro_after_init cfi_bpf_hash = __kcfi_typeid___bpf_prog_runX; */ -asm ( -" .pushsection .data..ro_after_init,\"aw\",@progbits \n" -" .type cfi_bpf_hash,@object \n" -" .globl cfi_bpf_hash \n" -" .p2align 2, 0x0 \n" -"cfi_bpf_hash: \n" -" .long __kcfi_typeid___bpf_prog_runX \n" -" .size cfi_bpf_hash, 4 \n" -" .popsection \n" -); +DEFINE_CFI_TYPE(cfi_bpf_hash, __bpf_prog_runX); /* Must match bpf_callback_t */ extern u64 __bpf_callback_fn(u64, u64, u64, u64, u64); - -KCFI_REFERENCE(__bpf_callback_fn); - -/* u32 __ro_after_init cfi_bpf_subprog_hash = __kcfi_typeid___bpf_callback_fn; */ -asm ( -" .pushsection .data..ro_after_init,\"aw\",@progbits \n" -" .type cfi_bpf_subprog_hash,@object \n" -" .globl cfi_bpf_subprog_hash \n" -" .p2align 2, 0x0 \n" -"cfi_bpf_subprog_hash: \n" -" .long __kcfi_typeid___bpf_callback_fn \n" -" .size cfi_bpf_subprog_hash, 4 \n" -" .popsection \n" -); +DEFINE_CFI_TYPE(cfi_bpf_subprog_hash, __bpf_callback_fn); u32 cfi_get_func_hash(void *func) { diff --git a/include/linux/cfi_types.h b/include/linux/cfi_types.h index 6b8713675765..685f7181780f 100644 --- a/include/linux/cfi_types.h +++ b/include/linux/cfi_types.h @@ -41,5 +41,28 @@ SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #endif +#else /* __ASSEMBLY__ */ + +#ifdef CONFIG_CFI_CLANG +#define DEFINE_CFI_TYPE(name, func) \ + /* \ + * Force a reference to the function so the compiler generates \ + * __kcfi_typeid_. \ + */ \ + __ADDRESSABLE(func); \ + /* u32 name __ro_after_init = __kcfi_typeid_ */ \ + extern u32 name; \ + asm ( \ + " .pushsection .data..ro_after_init,\"aw\",\%progbits \n" \ + " .type " #name ",\%object \n" \ + " .globl " #name " \n" \ + " .p2align 2, 0x0 \n" \ + #name ": \n" \ + " .4byte __kcfi_typeid_" #func " \n" \ + " .size " #name ", 4 \n" \ + " .popsection \n" \ + ); +#endif + #endif /* __ASSEMBLY__ */ #endif /* _LINUX_CFI_TYPES_H */ -- cgit v1.2.3 From f1befc82addda926c8301436123d041bf3249505 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Fri, 1 Aug 2025 00:10:07 +0000 Subject: cfi: Move BPF CFI types and helpers to generic code Instead of duplicating the same code for each architecture, move the CFI type hash variables for BPF function types and related helper functions to generic CFI code, and allow architectures to override the function definitions if needed. Signed-off-by: Sami Tolvanen Link: https://lore.kernel.org/r/20250801001004.1859976-7-samitolvanen@google.com Signed-off-by: Alexei Starovoitov --- arch/riscv/include/asm/cfi.h | 16 --------------- arch/riscv/kernel/cfi.c | 24 ---------------------- arch/x86/include/asm/cfi.h | 10 ++------- arch/x86/kernel/alternative.c | 12 ----------- include/linux/cfi.h | 47 +++++++++++++++++++++++++++++++++++-------- kernel/cfi.c | 15 ++++++++++++++ 6 files changed, 56 insertions(+), 68 deletions(-) (limited to 'include/linux') diff --git a/arch/riscv/include/asm/cfi.h b/arch/riscv/include/asm/cfi.h index fb9696d7a3f2..4508aaa7a2fd 100644 --- a/arch/riscv/include/asm/cfi.h +++ b/arch/riscv/include/asm/cfi.h @@ -14,27 +14,11 @@ struct pt_regs; #ifdef CONFIG_CFI_CLANG enum bug_trap_type handle_cfi_failure(struct pt_regs *regs); #define __bpfcall -static inline int cfi_get_offset(void) -{ - return 4; -} - -#define cfi_get_offset cfi_get_offset -extern u32 cfi_bpf_hash; -extern u32 cfi_bpf_subprog_hash; -extern u32 cfi_get_func_hash(void *func); #else static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs) { return BUG_TRAP_TYPE_NONE; } - -#define cfi_bpf_hash 0U -#define cfi_bpf_subprog_hash 0U -static inline u32 cfi_get_func_hash(void *func) -{ - return 0; -} #endif /* CONFIG_CFI_CLANG */ #endif /* _ASM_RISCV_CFI_H */ diff --git a/arch/riscv/kernel/cfi.c b/arch/riscv/kernel/cfi.c index e7aec5f36dd5..6ec9dbd7292e 100644 --- a/arch/riscv/kernel/cfi.c +++ b/arch/riscv/kernel/cfi.c @@ -4,7 +4,6 @@ * * Copyright (C) 2023 Google LLC */ -#include #include #include @@ -76,26 +75,3 @@ enum bug_trap_type handle_cfi_failure(struct pt_regs *regs) return report_cfi_failure(regs, regs->epc, &target, type); } - -#ifdef CONFIG_CFI_CLANG -struct bpf_insn; - -/* Must match bpf_func_t / DEFINE_BPF_PROG_RUN() */ -extern unsigned int __bpf_prog_runX(const void *ctx, - const struct bpf_insn *insn); -DEFINE_CFI_TYPE(cfi_bpf_hash, __bpf_prog_runX); - -/* Must match bpf_callback_t */ -extern u64 __bpf_callback_fn(u64, u64, u64, u64, u64); -DEFINE_CFI_TYPE(cfi_bpf_subprog_hash, __bpf_callback_fn); - -u32 cfi_get_func_hash(void *func) -{ - u32 hash; - - if (get_kernel_nofault(hash, func - cfi_get_offset())) - return 0; - - return hash; -} -#endif diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h index 3e51ba459154..1751f1eb95ef 100644 --- a/arch/x86/include/asm/cfi.h +++ b/arch/x86/include/asm/cfi.h @@ -116,8 +116,6 @@ struct pt_regs; #ifdef CONFIG_CFI_CLANG enum bug_trap_type handle_cfi_failure(struct pt_regs *regs); #define __bpfcall -extern u32 cfi_bpf_hash; -extern u32 cfi_bpf_subprog_hash; static inline int cfi_get_offset(void) { @@ -135,6 +133,8 @@ static inline int cfi_get_offset(void) #define cfi_get_offset cfi_get_offset extern u32 cfi_get_func_hash(void *func); +#define cfi_get_func_hash cfi_get_func_hash + extern int cfi_get_func_arity(void *func); #ifdef CONFIG_FINEIBT @@ -153,12 +153,6 @@ static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs) { return BUG_TRAP_TYPE_NONE; } -#define cfi_bpf_hash 0U -#define cfi_bpf_subprog_hash 0U -static inline u32 cfi_get_func_hash(void *func) -{ - return 0; -} static inline int cfi_get_func_arity(void *func) { return 0; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index a555665b4d9c..9f6b7dab2d9a 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -2,7 +2,6 @@ #define pr_fmt(fmt) "SMP alternatives: " fmt #include -#include #include #include #include @@ -1185,17 +1184,6 @@ bool cfi_bhi __ro_after_init = false; #endif #ifdef CONFIG_CFI_CLANG -struct bpf_insn; - -/* Must match bpf_func_t / DEFINE_BPF_PROG_RUN() */ -extern unsigned int __bpf_prog_runX(const void *ctx, - const struct bpf_insn *insn); -DEFINE_CFI_TYPE(cfi_bpf_hash, __bpf_prog_runX); - -/* Must match bpf_callback_t */ -extern u64 __bpf_callback_fn(u64, u64, u64, u64, u64); -DEFINE_CFI_TYPE(cfi_bpf_subprog_hash, __bpf_callback_fn); - u32 cfi_get_func_hash(void *func) { u32 hash; diff --git a/include/linux/cfi.h b/include/linux/cfi.h index 1db17ecbb86c..52a98886a455 100644 --- a/include/linux/cfi.h +++ b/include/linux/cfi.h @@ -11,16 +11,9 @@ #include #include +#ifdef CONFIG_CFI_CLANG extern bool cfi_warn; -#ifndef cfi_get_offset -static inline int cfi_get_offset(void) -{ - return 0; -} -#endif - -#ifdef CONFIG_CFI_CLANG enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr, unsigned long *target, u32 type); @@ -29,6 +22,44 @@ static inline enum bug_trap_type report_cfi_failure_noaddr(struct pt_regs *regs, { return report_cfi_failure(regs, addr, NULL, 0); } + +#ifndef cfi_get_offset +/* + * Returns the CFI prefix offset. By default, the compiler emits only + * a 4-byte CFI type hash before the function. If an architecture + * uses -fpatchable-function-entry=N,M where M>0 to change the prefix + * offset, they must override this function. + */ +static inline int cfi_get_offset(void) +{ + return 4; +} +#endif + +#ifndef cfi_get_func_hash +static inline u32 cfi_get_func_hash(void *func) +{ + u32 hash; + + if (get_kernel_nofault(hash, func - cfi_get_offset())) + return 0; + + return hash; +} +#endif + +/* CFI type hashes for BPF function types */ +extern u32 cfi_bpf_hash; +extern u32 cfi_bpf_subprog_hash; + +#else /* CONFIG_CFI_CLANG */ + +static inline int cfi_get_offset(void) { return 0; } +static inline u32 cfi_get_func_hash(void *func) { return 0; } + +#define cfi_bpf_hash 0U +#define cfi_bpf_subprog_hash 0U + #endif /* CONFIG_CFI_CLANG */ #ifdef CONFIG_ARCH_USES_CFI_TRAPS diff --git a/kernel/cfi.c b/kernel/cfi.c index 422fa4f958ae..4dad04ead06c 100644 --- a/kernel/cfi.c +++ b/kernel/cfi.c @@ -5,6 +5,8 @@ * Copyright (C) 2022 Google LLC */ +#include +#include #include bool cfi_warn __ro_after_init = IS_ENABLED(CONFIG_CFI_PERMISSIVE); @@ -27,6 +29,19 @@ enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr, return BUG_TRAP_TYPE_BUG; } +/* + * Declare two non-existent functions with types that match bpf_func_t and + * bpf_callback_t pointers, and use DEFINE_CFI_TYPE to define type hash + * variables for each function type. The cfi_bpf_* variables are used by + * arch-specific BPF JIT implementations to ensure indirectly callable JIT + * code has matching CFI type hashes. + */ +extern typeof(*(bpf_func_t)0) __bpf_prog_runX; +DEFINE_CFI_TYPE(cfi_bpf_hash, __bpf_prog_runX); + +extern typeof(*(bpf_callback_t)0) __bpf_callback_fn; +DEFINE_CFI_TYPE(cfi_bpf_subprog_hash, __bpf_callback_fn); + #ifdef CONFIG_ARCH_USES_CFI_TRAPS static inline unsigned long trap_address(s32 *p) { -- cgit v1.2.3 From 564a69ad90d15c782176e1a8c9e1c95661e1aed0 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 21 May 2025 17:03:46 +0530 Subject: virtio-mmio: Remove virtqueue list from mmio device The MMIO transport implementation creates a list of virtqueues for a virtio device, while the same is already available in the struct virtio_device. Don't create a duplicate list, and use the other one instead. While at it, fix the virtio_device_for_each_vq() macro to accept an argument like "&vm_dev->vdev" (which currently fails to build). Signed-off-by: Viresh Kumar Message-Id: <3e56c6f74002987e22f364d883cbad177cd9ad9c.1747827066.git.viresh.kumar@linaro.org> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/virtio/virtio_mmio.c | 52 +++----------------------------------------- include/linux/virtio.h | 2 +- 2 files changed, 4 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index 5d78c2d572ab..b152a1eca05a 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -65,7 +65,6 @@ #include #include #include -#include #include #include #include @@ -88,22 +87,8 @@ struct virtio_mmio_device { void __iomem *base; unsigned long version; - - /* a list of queues so we can dispatch IRQs */ - spinlock_t lock; - struct list_head virtqueues; -}; - -struct virtio_mmio_vq_info { - /* the actual virtqueue */ - struct virtqueue *vq; - - /* the list node for the virtqueues list */ - struct list_head node; }; - - /* Configuration interface */ static u64 vm_get_features(struct virtio_device *vdev) @@ -300,9 +285,8 @@ static bool vm_notify_with_data(struct virtqueue *vq) static irqreturn_t vm_interrupt(int irq, void *opaque) { struct virtio_mmio_device *vm_dev = opaque; - struct virtio_mmio_vq_info *info; + struct virtqueue *vq; unsigned long status; - unsigned long flags; irqreturn_t ret = IRQ_NONE; /* Read and acknowledge interrupts */ @@ -315,10 +299,8 @@ static irqreturn_t vm_interrupt(int irq, void *opaque) } if (likely(status & VIRTIO_MMIO_INT_VRING)) { - spin_lock_irqsave(&vm_dev->lock, flags); - list_for_each_entry(info, &vm_dev->virtqueues, node) - ret |= vring_interrupt(irq, info->vq); - spin_unlock_irqrestore(&vm_dev->lock, flags); + virtio_device_for_each_vq(&vm_dev->vdev, vq) + ret |= vring_interrupt(irq, vq); } return ret; @@ -329,14 +311,8 @@ static irqreturn_t vm_interrupt(int irq, void *opaque) static void vm_del_vq(struct virtqueue *vq) { struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev); - struct virtio_mmio_vq_info *info = vq->priv; - unsigned long flags; unsigned int index = vq->index; - spin_lock_irqsave(&vm_dev->lock, flags); - list_del(&info->node); - spin_unlock_irqrestore(&vm_dev->lock, flags); - /* Select and deactivate the queue */ writel(index, vm_dev->base + VIRTIO_MMIO_QUEUE_SEL); if (vm_dev->version == 1) { @@ -347,8 +323,6 @@ static void vm_del_vq(struct virtqueue *vq) } vring_del_virtqueue(vq); - - kfree(info); } static void vm_del_vqs(struct virtio_device *vdev) @@ -375,9 +349,7 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned int in { struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev); bool (*notify)(struct virtqueue *vq); - struct virtio_mmio_vq_info *info; struct virtqueue *vq; - unsigned long flags; unsigned int num; int err; @@ -399,13 +371,6 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned int in goto error_available; } - /* Allocate and fill out our active queue description */ - info = kmalloc(sizeof(*info), GFP_KERNEL); - if (!info) { - err = -ENOMEM; - goto error_kmalloc; - } - num = readl(vm_dev->base + VIRTIO_MMIO_QUEUE_NUM_MAX); if (num == 0) { err = -ENOENT; @@ -463,13 +428,6 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned int in writel(1, vm_dev->base + VIRTIO_MMIO_QUEUE_READY); } - vq->priv = info; - info->vq = vq; - - spin_lock_irqsave(&vm_dev->lock, flags); - list_add(&info->node, &vm_dev->virtqueues); - spin_unlock_irqrestore(&vm_dev->lock, flags); - return vq; error_bad_pfn: @@ -481,8 +439,6 @@ error_new_virtqueue: writel(0, vm_dev->base + VIRTIO_MMIO_QUEUE_READY); WARN_ON(readl(vm_dev->base + VIRTIO_MMIO_QUEUE_READY)); } - kfree(info); -error_kmalloc: error_available: return ERR_PTR(err); } @@ -627,8 +583,6 @@ static int virtio_mmio_probe(struct platform_device *pdev) vm_dev->vdev.dev.release = virtio_mmio_release_dev; vm_dev->vdev.config = &virtio_mmio_config_ops; vm_dev->pdev = pdev; - INIT_LIST_HEAD(&vm_dev->virtqueues); - spin_lock_init(&vm_dev->lock); vm_dev->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(vm_dev->base)) { diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 64cb4b04be7a..8b745ce0cf5f 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -196,7 +196,7 @@ int virtio_device_reset_done(struct virtio_device *dev); size_t virtio_max_dma_size(const struct virtio_device *vdev); #define virtio_device_for_each_vq(vdev, vq) \ - list_for_each_entry(vq, &vdev->vqs, list) + list_for_each_entry(vq, &(vdev)->vqs, list) /** * struct virtio_driver - operations for a virtio I/O driver -- cgit v1.2.3 From 569c392e191361cd05fba1fd87ed02ef0d130ef7 Mon Sep 17 00:00:00 2001 From: "Dr. David Alan Gilbert" Date: Tue, 17 Jun 2025 01:18:36 +0100 Subject: vhost: vringh: Remove unused iotlb functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The functions: vringh_abandon_iotlb() vringh_notify_disable_iotlb() and vringh_notify_enable_iotlb() were added in 2020 by commit 9ad9c49cfe97 ("vringh: IOTLB support") but have remained unused. Remove them. Signed-off-by: Dr. David Alan Gilbert Reviewed-by: Simon Horman Message-Id: <20250617001838.114457-2-linux@treblig.org> Signed-off-by: Michael S. Tsirkin Acked-by: Eugenio Pérez Tested-by: Lei Yang --- drivers/vhost/vringh.c | 43 ------------------------------------------- include/linux/vringh.h | 5 ----- 2 files changed, 48 deletions(-) (limited to 'include/linux') diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index bbce65452701..67a028d6fb5f 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -1534,23 +1534,6 @@ ssize_t vringh_iov_push_iotlb(struct vringh *vrh, } EXPORT_SYMBOL(vringh_iov_push_iotlb); -/** - * vringh_abandon_iotlb - we've decided not to handle the descriptor(s). - * @vrh: the vring. - * @num: the number of descriptors to put back (ie. num - * vringh_get_iotlb() to undo). - * - * The next vringh_get_iotlb() will return the old descriptor(s) again. - */ -void vringh_abandon_iotlb(struct vringh *vrh, unsigned int num) -{ - /* We only update vring_avail_event(vr) when we want to be notified, - * so we haven't changed that yet. - */ - vrh->last_avail_idx -= num; -} -EXPORT_SYMBOL(vringh_abandon_iotlb); - /** * vringh_complete_iotlb - we've finished with descriptor, publish it. * @vrh: the vring. @@ -1571,32 +1554,6 @@ int vringh_complete_iotlb(struct vringh *vrh, u16 head, u32 len) } EXPORT_SYMBOL(vringh_complete_iotlb); -/** - * vringh_notify_enable_iotlb - we want to know if something changes. - * @vrh: the vring. - * - * This always enables notifications, but returns false if there are - * now more buffers available in the vring. - */ -bool vringh_notify_enable_iotlb(struct vringh *vrh) -{ - return __vringh_notify_enable(vrh, getu16_iotlb, putu16_iotlb); -} -EXPORT_SYMBOL(vringh_notify_enable_iotlb); - -/** - * vringh_notify_disable_iotlb - don't tell us if something changes. - * @vrh: the vring. - * - * This is our normal running state: we disable and then only enable when - * we're going to sleep. - */ -void vringh_notify_disable_iotlb(struct vringh *vrh) -{ - __vringh_notify_disable(vrh, putu16_iotlb); -} -EXPORT_SYMBOL(vringh_notify_disable_iotlb); - /** * vringh_need_notify_iotlb - must we tell the other side about used buffers? * @vrh: the vring we've called vringh_complete_iotlb() on. diff --git a/include/linux/vringh.h b/include/linux/vringh.h index c3a8117dabe8..af8bd2695a7b 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -319,13 +319,8 @@ ssize_t vringh_iov_push_iotlb(struct vringh *vrh, struct vringh_kiov *wiov, const void *src, size_t len); -void vringh_abandon_iotlb(struct vringh *vrh, unsigned int num); - int vringh_complete_iotlb(struct vringh *vrh, u16 head, u32 len); -bool vringh_notify_enable_iotlb(struct vringh *vrh); -void vringh_notify_disable_iotlb(struct vringh *vrh); - int vringh_need_notify_iotlb(struct vringh *vrh); #endif /* CONFIG_VHOST_IOTLB */ -- cgit v1.2.3 From 6e9ef6937c726b97d4a6d49332d06e999acc15f5 Mon Sep 17 00:00:00 2001 From: "Dr. David Alan Gilbert" Date: Tue, 17 Jun 2025 01:18:37 +0100 Subject: vhost: vringh: Remove unused functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The functions: vringh_abandon_kern() vringh_abandon_user() vringh_iov_pull_kern() and vringh_iov_push_kern() were all added in 2013 by commit f87d0fbb5798 ("vringh: host-side implementation of virtio rings.") but have remained unused. Remove them and the two helper functions they used. Signed-off-by: Dr. David Alan Gilbert Message-Id: <20250617001838.114457-3-linux@treblig.org> Signed-off-by: Michael S. Tsirkin Acked-by: Eugenio Pérez Tested-by: Lei Yang Reviewed-by: Simon Horman --- drivers/vhost/vringh.c | 75 -------------------------------------------------- include/linux/vringh.h | 7 ----- 2 files changed, 82 deletions(-) (limited to 'include/linux') diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index 67a028d6fb5f..9f27c3f6091b 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -779,22 +779,6 @@ ssize_t vringh_iov_push_user(struct vringh_iov *wiov, } EXPORT_SYMBOL(vringh_iov_push_user); -/** - * vringh_abandon_user - we've decided not to handle the descriptor(s). - * @vrh: the vring. - * @num: the number of descriptors to put back (ie. num - * vringh_get_user() to undo). - * - * The next vringh_get_user() will return the old descriptor(s) again. - */ -void vringh_abandon_user(struct vringh *vrh, unsigned int num) -{ - /* We only update vring_avail_event(vr) when we want to be notified, - * so we haven't changed that yet. */ - vrh->last_avail_idx -= num; -} -EXPORT_SYMBOL(vringh_abandon_user); - /** * vringh_complete_user - we've finished with descriptor, publish it. * @vrh: the vring. @@ -900,20 +884,6 @@ static inline int putused_kern(const struct vringh *vrh, return 0; } -static inline int xfer_kern(const struct vringh *vrh, void *src, - void *dst, size_t len) -{ - memcpy(dst, src, len); - return 0; -} - -static inline int kern_xfer(const struct vringh *vrh, void *dst, - void *src, size_t len) -{ - memcpy(dst, src, len); - return 0; -} - /** * vringh_init_kern - initialize a vringh for a kernelspace vring. * @vrh: the vringh to initialize. @@ -998,51 +968,6 @@ int vringh_getdesc_kern(struct vringh *vrh, } EXPORT_SYMBOL(vringh_getdesc_kern); -/** - * vringh_iov_pull_kern - copy bytes from vring_iov. - * @riov: the riov as passed to vringh_getdesc_kern() (updated as we consume) - * @dst: the place to copy. - * @len: the maximum length to copy. - * - * Returns the bytes copied <= len or a negative errno. - */ -ssize_t vringh_iov_pull_kern(struct vringh_kiov *riov, void *dst, size_t len) -{ - return vringh_iov_xfer(NULL, riov, dst, len, xfer_kern); -} -EXPORT_SYMBOL(vringh_iov_pull_kern); - -/** - * vringh_iov_push_kern - copy bytes into vring_iov. - * @wiov: the wiov as passed to vringh_getdesc_kern() (updated as we consume) - * @src: the place to copy from. - * @len: the maximum length to copy. - * - * Returns the bytes copied <= len or a negative errno. - */ -ssize_t vringh_iov_push_kern(struct vringh_kiov *wiov, - const void *src, size_t len) -{ - return vringh_iov_xfer(NULL, wiov, (void *)src, len, kern_xfer); -} -EXPORT_SYMBOL(vringh_iov_push_kern); - -/** - * vringh_abandon_kern - we've decided not to handle the descriptor(s). - * @vrh: the vring. - * @num: the number of descriptors to put back (ie. num - * vringh_get_kern() to undo). - * - * The next vringh_get_kern() will return the old descriptor(s) again. - */ -void vringh_abandon_kern(struct vringh *vrh, unsigned int num) -{ - /* We only update vring_avail_event(vr) when we want to be notified, - * so we haven't changed that yet. */ - vrh->last_avail_idx -= num; -} -EXPORT_SYMBOL(vringh_abandon_kern); - /** * vringh_complete_kern - we've finished with descriptor, publish it. * @vrh: the vring. diff --git a/include/linux/vringh.h b/include/linux/vringh.h index af8bd2695a7b..49e7cbc9697a 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -175,9 +175,6 @@ int vringh_complete_multi_user(struct vringh *vrh, const struct vring_used_elem used[], unsigned num_used); -/* Pretend we've never seen descriptor (for easy error handling). */ -void vringh_abandon_user(struct vringh *vrh, unsigned int num); - /* Do we need to fire the eventfd to notify the other side? */ int vringh_need_notify_user(struct vringh *vrh); @@ -235,10 +232,6 @@ int vringh_getdesc_kern(struct vringh *vrh, u16 *head, gfp_t gfp); -ssize_t vringh_iov_pull_kern(struct vringh_kiov *riov, void *dst, size_t len); -ssize_t vringh_iov_push_kern(struct vringh_kiov *wiov, - const void *src, size_t len); -void vringh_abandon_kern(struct vringh *vrh, unsigned int num); int vringh_complete_kern(struct vringh *vrh, u16 head, u32 len); bool vringh_notify_enable_kern(struct vringh *vrh); -- cgit v1.2.3 From 87dbae5e36613a6020f3d64a2eaeac0a1e0e6dc6 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 17 Jul 2025 10:01:10 +0100 Subject: vsock/virtio: Move length check to callers of virtio_vsock_skb_rx_put() virtio_vsock_skb_rx_put() only calls skb_put() if the length in the packet header is not zero even though skb_put() handles this case gracefully. Remove the functionally redundant check from virtio_vsock_skb_rx_put() and, on the assumption that this is a worthwhile optimisation for handling credit messages, augment the existing length checks in virtio_transport_rx_work() to elide the call for zero-length payloads. Since the callers all have the length, extend virtio_vsock_skb_rx_put() to take it as an additional parameter rather than fish it back out of the packet header. Note that the vhost code already has similar logic in vhost_vsock_alloc_skb(). Reviewed-by: Stefano Garzarella Signed-off-by: Will Deacon Message-Id: <20250717090116.11987-4-will@kernel.org> Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vsock.c | 2 +- include/linux/virtio_vsock.h | 9 ++------- net/vmw_vsock/virtio_transport.c | 4 +++- 3 files changed, 6 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 66a0f060770e..4c4a642945eb 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -375,7 +375,7 @@ vhost_vsock_alloc_skb(struct vhost_virtqueue *vq, return NULL; } - virtio_vsock_skb_rx_put(skb); + virtio_vsock_skb_rx_put(skb, payload_len); nbytes = copy_from_iter(skb->data, payload_len, &iov_iter); if (nbytes != payload_len) { diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 36fb3edfa403..97465f378ade 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -47,14 +47,9 @@ static inline void virtio_vsock_skb_clear_tap_delivered(struct sk_buff *skb) VIRTIO_VSOCK_SKB_CB(skb)->tap_delivered = false; } -static inline void virtio_vsock_skb_rx_put(struct sk_buff *skb) +static inline void virtio_vsock_skb_rx_put(struct sk_buff *skb, u32 len) { - u32 len; - - len = le32_to_cpu(virtio_vsock_hdr(skb)->len); - - if (len > 0) - skb_put(skb, len); + skb_put(skb, len); } static inline struct sk_buff *virtio_vsock_alloc_skb(unsigned int size, gfp_t mask) diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index eb08a393413d..0166919f8705 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -656,7 +656,9 @@ static void virtio_transport_rx_work(struct work_struct *work) continue; } - virtio_vsock_skb_rx_put(skb); + if (payload_len) + virtio_vsock_skb_rx_put(skb, payload_len); + virtio_transport_deliver_tap_pkt(skb); virtio_transport_recv_pkt(&virtio_transport, skb); } -- cgit v1.2.3 From 03a92f036a04fed2b00d69f5f46f1a486e70dc5c Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 17 Jul 2025 10:01:11 +0100 Subject: vsock/virtio: Resize receive buffers so that each SKB fits in a 4K page When allocating receive buffers for the vsock virtio RX virtqueue, an SKB is allocated with a 4140 data payload (the 44-byte packet header + VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE). Even when factoring in the SKB overhead, the resulting 8KiB allocation thanks to the rounding in kmalloc_reserve() is wasteful (~3700 unusable bytes) and results in a higher-order page allocation on systems with 4KiB pages just for the sake of a few hundred bytes of packet data. Limit the vsock virtio RX buffers to 4KiB per SKB, resulting in much better memory utilisation and removing the need to allocate higher-order pages entirely. Reviewed-by: Stefano Garzarella Signed-off-by: Will Deacon Message-Id: <20250717090116.11987-5-will@kernel.org> Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_vsock.h | 7 ++++++- net/vmw_vsock/virtio_transport.c | 2 +- 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 97465f378ade..879f1dfa7d3a 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -106,7 +106,12 @@ static inline size_t virtio_vsock_skb_len(struct sk_buff *skb) return (size_t)(skb_end_pointer(skb) - skb->head); } -#define VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE (1024 * 4) +/* Dimension the RX SKB so that the entire thing fits exactly into + * a single 4KiB page. This avoids wasting memory due to alloc_skb() + * rounding up to the next page order and also means that we + * don't leave higher-order pages sitting around in the RX queue. + */ +#define VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE SKB_WITH_OVERHEAD(1024 * 4) #define VIRTIO_VSOCK_MAX_BUF_SIZE 0xFFFFFFFFUL #define VIRTIO_VSOCK_MAX_PKT_BUF_SIZE (1024 * 64) diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 0166919f8705..39f346890f7f 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -307,7 +307,7 @@ out_rcu: static void virtio_vsock_rx_fill(struct virtio_vsock *vsock) { - int total_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE + VIRTIO_VSOCK_SKB_HEADROOM; + int total_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE; struct scatterlist pkt, *p; struct virtqueue *vq; struct sk_buff *skb; -- cgit v1.2.3 From 2304c64a2866c58534560c63dc6e79d09b8f8d8d Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 17 Jul 2025 10:01:12 +0100 Subject: vsock/virtio: Rename virtio_vsock_alloc_skb() In preparation for nonlinear allocations for large SKBs, rename virtio_vsock_alloc_skb() to virtio_vsock_alloc_linear_skb() to indicate that it returns linear SKBs unconditionally and switch all callers over to this new interface for now. No functional change. Reviewed-by: Stefano Garzarella Signed-off-by: Will Deacon Message-Id: <20250717090116.11987-6-will@kernel.org> Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vsock.c | 2 +- include/linux/virtio_vsock.h | 3 ++- net/vmw_vsock/virtio_transport.c | 2 +- net/vmw_vsock/virtio_transport_common.c | 2 +- 4 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 4c4a642945eb..1ad96613680e 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -348,7 +348,7 @@ vhost_vsock_alloc_skb(struct vhost_virtqueue *vq, return NULL; /* len contains both payload and hdr */ - skb = virtio_vsock_alloc_skb(len, GFP_KERNEL); + skb = virtio_vsock_alloc_linear_skb(len, GFP_KERNEL); if (!skb) return NULL; diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 879f1dfa7d3a..4504ea29ff82 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -52,7 +52,8 @@ static inline void virtio_vsock_skb_rx_put(struct sk_buff *skb, u32 len) skb_put(skb, len); } -static inline struct sk_buff *virtio_vsock_alloc_skb(unsigned int size, gfp_t mask) +static inline struct sk_buff * +virtio_vsock_alloc_linear_skb(unsigned int size, gfp_t mask) { struct sk_buff *skb; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 39f346890f7f..80dcf6ac1e72 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -316,7 +316,7 @@ static void virtio_vsock_rx_fill(struct virtio_vsock *vsock) vq = vsock->vqs[VSOCK_VQ_RX]; do { - skb = virtio_vsock_alloc_skb(total_len, GFP_KERNEL); + skb = virtio_vsock_alloc_linear_skb(total_len, GFP_KERNEL); if (!skb) break; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 1b5d9896edae..c9eb7f7ac00d 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -261,7 +261,7 @@ static struct sk_buff *virtio_transport_alloc_skb(struct virtio_vsock_pkt_info * if (!zcopy) skb_len += payload_len; - skb = virtio_vsock_alloc_skb(skb_len, GFP_KERNEL); + skb = virtio_vsock_alloc_linear_skb(skb_len, GFP_KERNEL); if (!skb) return NULL; -- cgit v1.2.3 From fac6b82e0f3eaca33c8c67ec401681b21143ae17 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 17 Jul 2025 10:01:13 +0100 Subject: vsock/virtio: Move SKB allocation lower-bound check to callers virtio_vsock_alloc_linear_skb() checks that the requested size is at least big enough for the packet header (VIRTIO_VSOCK_SKB_HEADROOM). Of the three callers of virtio_vsock_alloc_linear_skb(), only vhost_vsock_alloc_skb() can potentially pass a packet smaller than the header size and, as it already has a check against the maximum packet size, extend its bounds checking to consider the minimum packet size and remove the check from virtio_vsock_alloc_linear_skb(). Reviewed-by: Stefano Garzarella Signed-off-by: Will Deacon Message-Id: <20250717090116.11987-7-will@kernel.org> Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vsock.c | 3 ++- include/linux/virtio_vsock.h | 3 --- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 1ad96613680e..24b7547b05a6 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -344,7 +344,8 @@ vhost_vsock_alloc_skb(struct vhost_virtqueue *vq, len = iov_length(vq->iov, out); - if (len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + VIRTIO_VSOCK_SKB_HEADROOM) + if (len < VIRTIO_VSOCK_SKB_HEADROOM || + len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + VIRTIO_VSOCK_SKB_HEADROOM) return NULL; /* len contains both payload and hdr */ diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 4504ea29ff82..36dd0cd55368 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -57,9 +57,6 @@ virtio_vsock_alloc_linear_skb(unsigned int size, gfp_t mask) { struct sk_buff *skb; - if (size < VIRTIO_VSOCK_SKB_HEADROOM) - return NULL; - skb = alloc_skb(size, mask); if (!skb) return NULL; -- cgit v1.2.3 From ab9aa2f3afc2713c14f6c4c6b90c9a0933b837f1 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 17 Jul 2025 10:01:14 +0100 Subject: vhost/vsock: Allocate nonlinear SKBs for handling large receive buffers When receiving a packet from a guest, vhost_vsock_handle_tx_kick() calls vhost_vsock_alloc_linear_skb() to allocate and fill an SKB with the receive data. Unfortunately, these are always linear allocations and can therefore result in significant pressure on kmalloc() considering that the maximum packet size (VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + VIRTIO_VSOCK_SKB_HEADROOM) is a little over 64KiB, resulting in a 128KiB allocation for each packet. Rework the vsock SKB allocation so that, for sizes with page order greater than PAGE_ALLOC_COSTLY_ORDER, a nonlinear SKB is allocated instead with the packet header in the SKB and the receive data in the fragments. Finally, add a debug warning if virtio_vsock_skb_rx_put() is ever called on an SKB with a non-zero length, as this would be destructive for the nonlinear case. Reviewed-by: Stefano Garzarella Signed-off-by: Will Deacon Message-Id: <20250717090116.11987-8-will@kernel.org> Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vsock.c | 8 +++----- include/linux/virtio_vsock.h | 32 +++++++++++++++++++++++++++++--- 2 files changed, 32 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 24b7547b05a6..0679a706ebc0 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -349,7 +349,7 @@ vhost_vsock_alloc_skb(struct vhost_virtqueue *vq, return NULL; /* len contains both payload and hdr */ - skb = virtio_vsock_alloc_linear_skb(len, GFP_KERNEL); + skb = virtio_vsock_alloc_skb(len, GFP_KERNEL); if (!skb) return NULL; @@ -378,10 +378,8 @@ vhost_vsock_alloc_skb(struct vhost_virtqueue *vq, virtio_vsock_skb_rx_put(skb, payload_len); - nbytes = copy_from_iter(skb->data, payload_len, &iov_iter); - if (nbytes != payload_len) { - vq_err(vq, "Expected %zu byte payload, got %zu bytes\n", - payload_len, nbytes); + if (skb_copy_datagram_from_iter(skb, 0, &iov_iter, payload_len)) { + vq_err(vq, "Failed to copy %zu byte payload\n", payload_len); kfree_skb(skb); return NULL; } diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 36dd0cd55368..fa5934ea9c81 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -49,22 +49,48 @@ static inline void virtio_vsock_skb_clear_tap_delivered(struct sk_buff *skb) static inline void virtio_vsock_skb_rx_put(struct sk_buff *skb, u32 len) { - skb_put(skb, len); + DEBUG_NET_WARN_ON_ONCE(skb->len); + + if (skb_is_nonlinear(skb)) + skb->len = len; + else + skb_put(skb, len); } static inline struct sk_buff * -virtio_vsock_alloc_linear_skb(unsigned int size, gfp_t mask) +__virtio_vsock_alloc_skb_with_frags(unsigned int header_len, + unsigned int data_len, + gfp_t mask) { struct sk_buff *skb; + int err; - skb = alloc_skb(size, mask); + skb = alloc_skb_with_frags(header_len, data_len, + PAGE_ALLOC_COSTLY_ORDER, &err, mask); if (!skb) return NULL; skb_reserve(skb, VIRTIO_VSOCK_SKB_HEADROOM); + skb->data_len = data_len; return skb; } +static inline struct sk_buff * +virtio_vsock_alloc_linear_skb(unsigned int size, gfp_t mask) +{ + return __virtio_vsock_alloc_skb_with_frags(size, 0, mask); +} + +static inline struct sk_buff *virtio_vsock_alloc_skb(unsigned int size, gfp_t mask) +{ + if (size <= SKB_WITH_OVERHEAD(PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) + return virtio_vsock_alloc_linear_skb(size, mask); + + size -= VIRTIO_VSOCK_SKB_HEADROOM; + return __virtio_vsock_alloc_skb_with_frags(VIRTIO_VSOCK_SKB_HEADROOM, + size, mask); +} + static inline void virtio_vsock_skb_queue_head(struct sk_buff_head *list, struct sk_buff *skb) { -- cgit v1.2.3 From 8ca76151d2c8219edea82f1925a2a25907ff6a9d Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 17 Jul 2025 10:01:15 +0100 Subject: vsock/virtio: Rename virtio_vsock_skb_rx_put() In preparation for using virtio_vsock_skb_rx_put() when populating SKBs on the vsock TX path, rename virtio_vsock_skb_rx_put() to virtio_vsock_skb_put(). No functional change. Reviewed-by: Stefano Garzarella Signed-off-by: Will Deacon Message-Id: <20250717090116.11987-9-will@kernel.org> Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vsock.c | 2 +- include/linux/virtio_vsock.h | 2 +- net/vmw_vsock/virtio_transport.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 0679a706ebc0..ae01457ea2cd 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -376,7 +376,7 @@ vhost_vsock_alloc_skb(struct vhost_virtqueue *vq, return NULL; } - virtio_vsock_skb_rx_put(skb, payload_len); + virtio_vsock_skb_put(skb, payload_len); if (skb_copy_datagram_from_iter(skb, 0, &iov_iter, payload_len)) { vq_err(vq, "Failed to copy %zu byte payload\n", payload_len); diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index fa5934ea9c81..0c67543a45c8 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -47,7 +47,7 @@ static inline void virtio_vsock_skb_clear_tap_delivered(struct sk_buff *skb) VIRTIO_VSOCK_SKB_CB(skb)->tap_delivered = false; } -static inline void virtio_vsock_skb_rx_put(struct sk_buff *skb, u32 len) +static inline void virtio_vsock_skb_put(struct sk_buff *skb, u32 len) { DEBUG_NET_WARN_ON_ONCE(skb->len); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 80dcf6ac1e72..b6569b0ca2bb 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -657,7 +657,7 @@ static void virtio_transport_rx_work(struct work_struct *work) } if (payload_len) - virtio_vsock_skb_rx_put(skb, payload_len); + virtio_vsock_skb_put(skb, payload_len); virtio_transport_deliver_tap_pkt(skb); virtio_transport_recv_pkt(&virtio_transport, skb); -- cgit v1.2.3 From 788fa4b47cdcd9b3d8c2d02ac0b3cd2540305f18 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 1 Aug 2025 16:37:24 -0400 Subject: tracing: Add guard(ring_buffer_nest) Some calls to the tracing ring buffer can happen when the ring buffer is already being written to by the same context (for example, a trace_printk() in between a ring_buffer_lock_reserve() and a ring_buffer_unlock_commit()). In order to not trigger the recursion detection, these functions use ring_buffer_nest_start() and ring_buffer_nest_end(). Create a guard() for these functions so that their use cases can be simplified and not need to use goto for the release. Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Link: https://lore.kernel.org/20250801203857.710501021@kernel.org Signed-off-by: Steven Rostedt (Google) --- include/linux/ring_buffer.h | 3 ++ kernel/trace/trace.c | 69 ++++++++++++++++----------------------- kernel/trace/trace_events_synth.c | 6 ++-- 3 files changed, 34 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index cd7f0ae26615..8253cb69540c 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -144,6 +144,9 @@ int ring_buffer_write(struct trace_buffer *buffer, void ring_buffer_nest_start(struct trace_buffer *buffer); void ring_buffer_nest_end(struct trace_buffer *buffer); +DEFINE_GUARD(ring_buffer_nest, struct trace_buffer *, + ring_buffer_nest_start(_T), ring_buffer_nest_end(_T)) + struct ring_buffer_event * ring_buffer_peek(struct trace_buffer *buffer, int cpu, u64 *ts, unsigned long *lost_events); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 0ec9cab9a812..332487179e1d 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1160,13 +1160,11 @@ int __trace_array_puts(struct trace_array *tr, unsigned long ip, trace_ctx = tracing_gen_ctx(); buffer = tr->array_buffer.buffer; - ring_buffer_nest_start(buffer); + guard(ring_buffer_nest)(buffer); event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, trace_ctx); - if (!event) { - size = 0; - goto out; - } + if (!event) + return 0; entry = ring_buffer_event_data(event); entry->ip = ip; @@ -1182,8 +1180,6 @@ int __trace_array_puts(struct trace_array *tr, unsigned long ip, __buffer_unlock_commit(buffer, event); ftrace_trace_stack(tr, buffer, trace_ctx, 4, NULL); - out: - ring_buffer_nest_end(buffer); return size; } EXPORT_SYMBOL_GPL(__trace_array_puts); @@ -1213,7 +1209,6 @@ int __trace_bputs(unsigned long ip, const char *str) struct bputs_entry *entry; unsigned int trace_ctx; int size = sizeof(struct bputs_entry); - int ret = 0; if (!printk_binsafe(tr)) return __trace_puts(ip, str, strlen(str)); @@ -1227,11 +1222,11 @@ int __trace_bputs(unsigned long ip, const char *str) trace_ctx = tracing_gen_ctx(); buffer = tr->array_buffer.buffer; - ring_buffer_nest_start(buffer); + guard(ring_buffer_nest)(buffer); event = __trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size, trace_ctx); if (!event) - goto out; + return 0; entry = ring_buffer_event_data(event); entry->ip = ip; @@ -1240,10 +1235,7 @@ int __trace_bputs(unsigned long ip, const char *str) __buffer_unlock_commit(buffer, event); ftrace_trace_stack(tr, buffer, trace_ctx, 4, NULL); - ret = 1; - out: - ring_buffer_nest_end(buffer); - return ret; + return 1; } EXPORT_SYMBOL_GPL(__trace_bputs); @@ -3397,21 +3389,19 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) size = sizeof(*entry) + sizeof(u32) * len; buffer = tr->array_buffer.buffer; - ring_buffer_nest_start(buffer); - event = __trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size, - trace_ctx); - if (!event) - goto out; - entry = ring_buffer_event_data(event); - entry->ip = ip; - entry->fmt = fmt; - - memcpy(entry->buf, tbuffer, sizeof(u32) * len); - __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(tr, buffer, trace_ctx, 6, NULL); + scoped_guard(ring_buffer_nest, buffer) { + event = __trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size, + trace_ctx); + if (!event) + goto out_put; + entry = ring_buffer_event_data(event); + entry->ip = ip; + entry->fmt = fmt; -out: - ring_buffer_nest_end(buffer); + memcpy(entry->buf, tbuffer, sizeof(u32) * len); + __buffer_unlock_commit(buffer, event); + ftrace_trace_stack(tr, buffer, trace_ctx, 6, NULL); + } out_put: put_trace_buf(); @@ -3452,20 +3442,19 @@ int __trace_array_vprintk(struct trace_buffer *buffer, len = vscnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args); size = sizeof(*entry) + len + 1; - ring_buffer_nest_start(buffer); - event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, - trace_ctx); - if (!event) - goto out; - entry = ring_buffer_event_data(event); - entry->ip = ip; - - memcpy(&entry->buf, tbuffer, len + 1); - __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(printk_trace, buffer, trace_ctx, 6, NULL); + scoped_guard(ring_buffer_nest, buffer) { + event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, + trace_ctx); + if (!event) + goto out; + entry = ring_buffer_event_data(event); + entry->ip = ip; + memcpy(&entry->buf, tbuffer, len + 1); + __buffer_unlock_commit(buffer, event); + ftrace_trace_stack(printk_trace, buffer, trace_ctx, 6, NULL); + } out: - ring_buffer_nest_end(buffer); put_trace_buf(); out_nobuffer: diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index 33cfbd4ed76d..f24ee61f8884 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -536,12 +536,12 @@ static notrace void trace_event_raw_event_synth(void *__data, * is being performed within another event. */ buffer = trace_file->tr->array_buffer.buffer; - ring_buffer_nest_start(buffer); + guard(ring_buffer_nest)(buffer); entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry) + fields_size); if (!entry) - goto out; + return; for (i = 0, n_u64 = 0; i < event->n_fields; i++) { val_idx = var_ref_idx[i]; @@ -584,8 +584,6 @@ static notrace void trace_event_raw_event_synth(void *__data, } trace_event_buffer_commit(&fbuffer); -out: - ring_buffer_nest_end(buffer); } static void free_synth_event_print_fmt(struct trace_event_call *call) -- cgit v1.2.3 From d45cf1e7d7180256e17c9ce88e32e8061a7887fe Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 30 Jul 2025 13:17:38 +0000 Subject: ipv6: reject malicious packets in ipv6_gso_segment() syzbot was able to craft a packet with very long IPv6 extension headers leading to an overflow of skb->transport_header. This 16bit field has a limited range. Add skb_reset_transport_header_careful() helper and use it from ipv6_gso_segment() WARNING: CPU: 0 PID: 5871 at ./include/linux/skbuff.h:3032 skb_reset_transport_header include/linux/skbuff.h:3032 [inline] WARNING: CPU: 0 PID: 5871 at ./include/linux/skbuff.h:3032 ipv6_gso_segment+0x15e2/0x21e0 net/ipv6/ip6_offload.c:151 Modules linked in: CPU: 0 UID: 0 PID: 5871 Comm: syz-executor211 Not tainted 6.16.0-rc6-syzkaller-g7abc678e3084 #0 PREEMPT(full) Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/12/2025 RIP: 0010:skb_reset_transport_header include/linux/skbuff.h:3032 [inline] RIP: 0010:ipv6_gso_segment+0x15e2/0x21e0 net/ipv6/ip6_offload.c:151 Call Trace: skb_mac_gso_segment+0x31c/0x640 net/core/gso.c:53 nsh_gso_segment+0x54a/0xe10 net/nsh/nsh.c:110 skb_mac_gso_segment+0x31c/0x640 net/core/gso.c:53 __skb_gso_segment+0x342/0x510 net/core/gso.c:124 skb_gso_segment include/net/gso.h:83 [inline] validate_xmit_skb+0x857/0x11b0 net/core/dev.c:3950 validate_xmit_skb_list+0x84/0x120 net/core/dev.c:4000 sch_direct_xmit+0xd3/0x4b0 net/sched/sch_generic.c:329 __dev_xmit_skb net/core/dev.c:4102 [inline] __dev_queue_xmit+0x17b6/0x3a70 net/core/dev.c:4679 Fixes: d1da932ed4ec ("ipv6: Separate ipv6 offload support") Reported-by: syzbot+af43e647fd835acc02df@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/688a1a05.050a0220.5d226.0008.GAE@google.com/T/#u Signed-off-by: Eric Dumazet Reviewed-by: Dawid Osuchowski Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20250730131738.3385939-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 23 +++++++++++++++++++++++ net/ipv6/ip6_offload.c | 4 +++- 2 files changed, 26 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b8b06e71b73e..14b923ddb6df 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3033,6 +3033,29 @@ static inline void skb_reset_transport_header(struct sk_buff *skb) skb->transport_header = offset; } +/** + * skb_reset_transport_header_careful - conditionally reset transport header + * @skb: buffer to alter + * + * Hardened version of skb_reset_transport_header(). + * + * Returns: true if the operation was a success. + */ +static inline bool __must_check +skb_reset_transport_header_careful(struct sk_buff *skb) +{ + long offset = skb->data - skb->head; + + if (unlikely(offset != (typeof(skb->transport_header))offset)) + return false; + + if (unlikely(offset == (typeof(skb->transport_header))~0U)) + return false; + + skb->transport_header = offset; + return true; +} + static inline void skb_set_transport_header(struct sk_buff *skb, const int offset) { diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 9822163428b0..fce91183797a 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -148,7 +148,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, ops = rcu_dereference(inet6_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) { - skb_reset_transport_header(skb); + if (!skb_reset_transport_header_careful(skb)) + goto out; + segs = ops->callbacks.gso_segment(skb, features); if (!segs) skb->network_header = skb_mac_header(skb) + nhoff - skb->head; -- cgit v1.2.3 From 6c6d8f8ba7789c221a2e4c43a0ed982c7a41f428 Mon Sep 17 00:00:00 2001 From: "Dr. David Alan Gilbert" Date: Wed, 16 Jul 2025 14:32:45 +0100 Subject: lib/xxhash: remove unused functions xxh32_digest() and xxh32_update() were added in 2017 in the original xxhash commit, but have remained unused. Remove them. Link: https://lkml.kernel.org/r/20250716133245.243363-1-linux@treblig.org Signed-off-by: Dr. David Alan Gilbert Reviewed-by: Christoph Hellwig Cc: Dave Gilbert Cc: Nick Terrell Signed-off-by: Andrew Morton --- include/linux/xxhash.h | 26 ------------ lib/xxhash.c | 107 ------------------------------------------------- 2 files changed, 133 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xxhash.h b/include/linux/xxhash.h index df42511438d0..27f57eca8cb1 100644 --- a/include/linux/xxhash.h +++ b/include/linux/xxhash.h @@ -177,32 +177,6 @@ struct xxh64_state { */ void xxh32_reset(struct xxh32_state *state, uint32_t seed); -/** - * xxh32_update() - hash the data given and update the xxh32 state - * - * @state: The xxh32 state to update. - * @input: The data to hash. - * @length: The length of the data to hash. - * - * After calling xxh32_reset() call xxh32_update() as many times as necessary. - * - * Return: Zero on success, otherwise an error code. - */ -int xxh32_update(struct xxh32_state *state, const void *input, size_t length); - -/** - * xxh32_digest() - produce the current xxh32 hash - * - * @state: Produce the current xxh32 hash of this state. - * - * A hash value can be produced at any time. It is still possible to continue - * inserting input into the hash state after a call to xxh32_digest(), and - * generate new hashes later on, by calling xxh32_digest() again. - * - * Return: The xxh32 hash stored in the state. - */ -uint32_t xxh32_digest(const struct xxh32_state *state); - /** * xxh64_reset() - reset the xxh64 state to start a new hashing operation * diff --git a/lib/xxhash.c b/lib/xxhash.c index b5bd567aa6b3..cf629766f376 100644 --- a/lib/xxhash.c +++ b/lib/xxhash.c @@ -267,113 +267,6 @@ void xxh64_reset(struct xxh64_state *statePtr, const uint64_t seed) } EXPORT_SYMBOL(xxh64_reset); -int xxh32_update(struct xxh32_state *state, const void *input, const size_t len) -{ - const uint8_t *p = (const uint8_t *)input; - const uint8_t *const b_end = p + len; - - if (input == NULL) - return -EINVAL; - - state->total_len_32 += (uint32_t)len; - state->large_len |= (len >= 16) | (state->total_len_32 >= 16); - - if (state->memsize + len < 16) { /* fill in tmp buffer */ - memcpy((uint8_t *)(state->mem32) + state->memsize, input, len); - state->memsize += (uint32_t)len; - return 0; - } - - if (state->memsize) { /* some data left from previous update */ - const uint32_t *p32 = state->mem32; - - memcpy((uint8_t *)(state->mem32) + state->memsize, input, - 16 - state->memsize); - - state->v1 = xxh32_round(state->v1, get_unaligned_le32(p32)); - p32++; - state->v2 = xxh32_round(state->v2, get_unaligned_le32(p32)); - p32++; - state->v3 = xxh32_round(state->v3, get_unaligned_le32(p32)); - p32++; - state->v4 = xxh32_round(state->v4, get_unaligned_le32(p32)); - p32++; - - p += 16-state->memsize; - state->memsize = 0; - } - - if (p <= b_end - 16) { - const uint8_t *const limit = b_end - 16; - uint32_t v1 = state->v1; - uint32_t v2 = state->v2; - uint32_t v3 = state->v3; - uint32_t v4 = state->v4; - - do { - v1 = xxh32_round(v1, get_unaligned_le32(p)); - p += 4; - v2 = xxh32_round(v2, get_unaligned_le32(p)); - p += 4; - v3 = xxh32_round(v3, get_unaligned_le32(p)); - p += 4; - v4 = xxh32_round(v4, get_unaligned_le32(p)); - p += 4; - } while (p <= limit); - - state->v1 = v1; - state->v2 = v2; - state->v3 = v3; - state->v4 = v4; - } - - if (p < b_end) { - memcpy(state->mem32, p, (size_t)(b_end-p)); - state->memsize = (uint32_t)(b_end-p); - } - - return 0; -} -EXPORT_SYMBOL(xxh32_update); - -uint32_t xxh32_digest(const struct xxh32_state *state) -{ - const uint8_t *p = (const uint8_t *)state->mem32; - const uint8_t *const b_end = (const uint8_t *)(state->mem32) + - state->memsize; - uint32_t h32; - - if (state->large_len) { - h32 = xxh_rotl32(state->v1, 1) + xxh_rotl32(state->v2, 7) + - xxh_rotl32(state->v3, 12) + xxh_rotl32(state->v4, 18); - } else { - h32 = state->v3 /* == seed */ + PRIME32_5; - } - - h32 += state->total_len_32; - - while (p + 4 <= b_end) { - h32 += get_unaligned_le32(p) * PRIME32_3; - h32 = xxh_rotl32(h32, 17) * PRIME32_4; - p += 4; - } - - while (p < b_end) { - h32 += (*p) * PRIME32_5; - h32 = xxh_rotl32(h32, 11) * PRIME32_1; - p++; - } - - h32 ^= h32 >> 15; - h32 *= PRIME32_2; - h32 ^= h32 >> 13; - h32 *= PRIME32_3; - h32 ^= h32 >> 16; - - return h32; -} -EXPORT_SYMBOL(xxh32_digest); - int xxh64_update(struct xxh64_state *state, const void *input, const size_t len) { const uint8_t *p = (const uint8_t *)input; -- cgit v1.2.3 From 07d24902977e4704fab8472981e73a0ad6dfa1fd Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Tue, 10 Jun 2025 08:53:27 +0000 Subject: kexec: enable CMA based contiguous allocation When booting a new kernel with kexec_file, the kernel picks a target location that the kernel should live at, then allocates random pages, checks whether any of those patches magically happens to coincide with a target address range and if so, uses them for that range. For every page allocated this way, it then creates a page list that the relocation code - code that executes while all CPUs are off and we are just about to jump into the new kernel - copies to their final memory location. We can not put them there before, because chances are pretty good that at least some page in the target range is already in use by the currently running Linux environment. Copying is happening from a single CPU at RAM rate, which takes around 4-50 ms per 100 MiB. All of this is inefficient and error prone. To successfully kexec, we need to quiesce all devices of the outgoing kernel so they don't scribble over the new kernel's memory. We have seen cases where that does not happen properly (*cough* GIC *cough*) and hence the new kernel was corrupted. This started a month long journey to root cause failing kexecs to eventually see memory corruption, because the new kernel was corrupted severely enough that it could not emit output to tell us about the fact that it was corrupted. By allocating memory for the next kernel from a memory range that is guaranteed scribbling free, we can boot the next kernel up to a point where it is at least able to detect corruption and maybe even stop it before it becomes severe. This increases the chance for successful kexecs. Since kexec got introduced, Linux has gained the CMA framework which can perform physically contiguous memory mappings, while keeping that memory available for movable memory when it is not needed for contiguous allocations. The default CMA allocator is for DMA allocations. This patch adds logic to the kexec file loader to attempt to place the target payload at a location allocated from CMA. If successful, it uses that memory range directly instead of creating copy instructions during the hot phase. To ensure that there is a safety net in case anything goes wrong with the CMA allocation, it also adds a flag for user space to force disable CMA allocations. Using CMA allocations has two advantages: 1) Faster by 4-50 ms per 100 MiB. There is no more need to copy in the hot phase. 2) More robust. Even if by accident some page is still in use for DMA, the new kernel image will be safe from that access because it resides in a memory region that is considered allocated in the old kernel and has a chance to reinitialize that component. Link: https://lkml.kernel.org/r/20250610085327.51817-1-graf@amazon.com Signed-off-by: Alexander Graf Acked-by: Baoquan He Reviewed-by: Pasha Tatashin Cc: Zhongkun He Signed-off-by: Andrew Morton --- arch/riscv/kernel/kexec_elf.c | 1 + include/linux/kexec.h | 10 +++++ include/uapi/linux/kexec.h | 1 + kernel/kexec.c | 2 +- kernel/kexec_core.c | 100 ++++++++++++++++++++++++++++++++++++++---- kernel/kexec_file.c | 51 ++++++++++++++++++++- kernel/kexec_internal.h | 2 +- 7 files changed, 156 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/arch/riscv/kernel/kexec_elf.c b/arch/riscv/kernel/kexec_elf.c index f4755d49b89e..56444c7bd34e 100644 --- a/arch/riscv/kernel/kexec_elf.c +++ b/arch/riscv/kernel/kexec_elf.c @@ -95,6 +95,7 @@ static int elf_find_pbase(struct kimage *image, unsigned long kernel_len, kbuf.buf_align = PMD_SIZE; kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; kbuf.memsz = ALIGN(kernel_len, PAGE_SIZE); + kbuf.cma = NULL; kbuf.top_down = false; ret = arch_kexec_locate_mem_hole(&kbuf); if (!ret) { diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 03f85ad03025..1b10a5d84b68 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -79,6 +79,12 @@ extern note_buf_t __percpu *crash_notes; typedef unsigned long kimage_entry_t; +/* + * This is a copy of the UAPI struct kexec_segment and must be identical + * to it because it gets copied straight from user space into kernel + * memory. Do not modify this structure unless you change the way segments + * get ingested from user space. + */ struct kexec_segment { /* * This pointer can point to user memory if kexec_load() system @@ -172,6 +178,7 @@ int kexec_image_post_load_cleanup_default(struct kimage *image); * @buf_align: Minimum alignment needed. * @buf_min: The buffer can't be placed below this address. * @buf_max: The buffer can't be placed above this address. + * @cma: CMA page if the buffer is backed by CMA. * @top_down: Allocate from top of memory. * @random: Place the buffer at a random position. */ @@ -184,6 +191,7 @@ struct kexec_buf { unsigned long buf_align; unsigned long buf_min; unsigned long buf_max; + struct page *cma; bool top_down; #ifdef CONFIG_CRASH_DUMP bool random; @@ -340,6 +348,7 @@ struct kimage { unsigned long nr_segments; struct kexec_segment segment[KEXEC_SEGMENT_MAX]; + struct page *segment_cma[KEXEC_SEGMENT_MAX]; struct list_head control_pages; struct list_head dest_pages; @@ -361,6 +370,7 @@ struct kimage { */ unsigned int hotplug_support:1; #endif + unsigned int no_cma:1; #ifdef ARCH_HAS_KIMAGE_ARCH struct kimage_arch arch; diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h index 5ae1741ea8ea..8958ebfcff94 100644 --- a/include/uapi/linux/kexec.h +++ b/include/uapi/linux/kexec.h @@ -27,6 +27,7 @@ #define KEXEC_FILE_ON_CRASH 0x00000002 #define KEXEC_FILE_NO_INITRAMFS 0x00000004 #define KEXEC_FILE_DEBUG 0x00000008 +#define KEXEC_FILE_NO_CMA 0x00000010 /* These values match the ELF architecture values. * Unless there is a good reason that should continue to be the case. diff --git a/kernel/kexec.c b/kernel/kexec.c index a6b3f96bb50c..28008e3d462e 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -152,7 +152,7 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments, goto out; for (i = 0; i < nr_segments; i++) { - ret = kimage_load_segment(image, &image->segment[i]); + ret = kimage_load_segment(image, i); if (ret) goto out; } diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 3a9a9f240dbc..e390c0df6d55 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include @@ -553,6 +554,24 @@ static void kimage_free_entry(kimage_entry_t entry) kimage_free_pages(page); } +static void kimage_free_cma(struct kimage *image) +{ + unsigned long i; + + for (i = 0; i < image->nr_segments; i++) { + struct page *cma = image->segment_cma[i]; + u32 nr_pages = image->segment[i].memsz >> PAGE_SHIFT; + + if (!cma) + continue; + + arch_kexec_pre_free_pages(page_address(cma), nr_pages); + dma_release_from_contiguous(NULL, cma, nr_pages); + image->segment_cma[i] = NULL; + } + +} + void kimage_free(struct kimage *image) { kimage_entry_t *ptr, entry; @@ -591,6 +610,9 @@ void kimage_free(struct kimage *image) /* Free the kexec control pages... */ kimage_free_page_list(&image->control_pages); + /* Free CMA allocations */ + kimage_free_cma(image); + /* * Free up any temporary buffers allocated. This might hit if * error occurred much later after buffer allocation. @@ -716,9 +738,69 @@ static struct page *kimage_alloc_page(struct kimage *image, return page; } -static int kimage_load_normal_segment(struct kimage *image, - struct kexec_segment *segment) +static int kimage_load_cma_segment(struct kimage *image, int idx) +{ + struct kexec_segment *segment = &image->segment[idx]; + struct page *cma = image->segment_cma[idx]; + char *ptr = page_address(cma); + unsigned long maddr; + size_t ubytes, mbytes; + int result = 0; + unsigned char __user *buf = NULL; + unsigned char *kbuf = NULL; + + if (image->file_mode) + kbuf = segment->kbuf; + else + buf = segment->buf; + ubytes = segment->bufsz; + mbytes = segment->memsz; + maddr = segment->mem; + + /* Then copy from source buffer to the CMA one */ + while (mbytes) { + size_t uchunk, mchunk; + + ptr += maddr & ~PAGE_MASK; + mchunk = min_t(size_t, mbytes, + PAGE_SIZE - (maddr & ~PAGE_MASK)); + uchunk = min(ubytes, mchunk); + + if (uchunk) { + /* For file based kexec, source pages are in kernel memory */ + if (image->file_mode) + memcpy(ptr, kbuf, uchunk); + else + result = copy_from_user(ptr, buf, uchunk); + ubytes -= uchunk; + if (image->file_mode) + kbuf += uchunk; + else + buf += uchunk; + } + + if (result) { + result = -EFAULT; + goto out; + } + + ptr += mchunk; + maddr += mchunk; + mbytes -= mchunk; + + cond_resched(); + } + + /* Clear any remainder */ + memset(ptr, 0, mbytes); + +out: + return result; +} + +static int kimage_load_normal_segment(struct kimage *image, int idx) { + struct kexec_segment *segment = &image->segment[idx]; unsigned long maddr; size_t ubytes, mbytes; int result; @@ -733,6 +815,9 @@ static int kimage_load_normal_segment(struct kimage *image, mbytes = segment->memsz; maddr = segment->mem; + if (image->segment_cma[idx]) + return kimage_load_cma_segment(image, idx); + result = kimage_set_destination(image, maddr); if (result < 0) goto out; @@ -787,13 +872,13 @@ out: } #ifdef CONFIG_CRASH_DUMP -static int kimage_load_crash_segment(struct kimage *image, - struct kexec_segment *segment) +static int kimage_load_crash_segment(struct kimage *image, int idx) { /* For crash dumps kernels we simply copy the data from * user space to it's destination. * We do things a page at a time for the sake of kmap. */ + struct kexec_segment *segment = &image->segment[idx]; unsigned long maddr; size_t ubytes, mbytes; int result; @@ -858,18 +943,17 @@ out: } #endif -int kimage_load_segment(struct kimage *image, - struct kexec_segment *segment) +int kimage_load_segment(struct kimage *image, int idx) { int result = -ENOMEM; switch (image->type) { case KEXEC_TYPE_DEFAULT: - result = kimage_load_normal_segment(image, segment); + result = kimage_load_normal_segment(image, idx); break; #ifdef CONFIG_CRASH_DUMP case KEXEC_TYPE_CRASH: - result = kimage_load_crash_segment(image, segment); + result = kimage_load_crash_segment(image, idx); break; #endif } diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 69fe76fd9233..41271eee0f99 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -26,6 +26,7 @@ #include #include #include +#include #include "kexec_internal.h" #ifdef CONFIG_KEXEC_SIG @@ -253,6 +254,8 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd, ret = 0; } + image->no_cma = !!(flags & KEXEC_FILE_NO_CMA); + if (cmdline_len) { image->cmdline_buf = memdup_user(cmdline_ptr, cmdline_len); if (IS_ERR(image->cmdline_buf)) { @@ -434,7 +437,7 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, i, ksegment->buf, ksegment->bufsz, ksegment->mem, ksegment->memsz); - ret = kimage_load_segment(image, &image->segment[i]); + ret = kimage_load_segment(image, i); if (ret) goto out; } @@ -663,6 +666,43 @@ static int kexec_walk_resources(struct kexec_buf *kbuf, return walk_system_ram_res(0, ULONG_MAX, kbuf, func); } +static int kexec_alloc_contig(struct kexec_buf *kbuf) +{ + size_t nr_pages = kbuf->memsz >> PAGE_SHIFT; + unsigned long mem; + struct page *p; + + /* User space disabled CMA allocations, bail out. */ + if (kbuf->image->no_cma) + return -EPERM; + + /* Skip CMA logic for crash kernel */ + if (kbuf->image->type == KEXEC_TYPE_CRASH) + return -EPERM; + + p = dma_alloc_from_contiguous(NULL, nr_pages, get_order(kbuf->buf_align), true); + if (!p) + return -ENOMEM; + + pr_debug("allocated %zu DMA pages at 0x%lx", nr_pages, page_to_boot_pfn(p)); + + mem = page_to_boot_pfn(p) << PAGE_SHIFT; + + if (kimage_is_destination_range(kbuf->image, mem, mem + kbuf->memsz)) { + /* Our region is already in use by a statically defined one. Bail out. */ + pr_debug("CMA overlaps existing mem: 0x%lx+0x%lx\n", mem, kbuf->memsz); + dma_release_from_contiguous(NULL, p, nr_pages); + return -EBUSY; + } + + kbuf->mem = page_to_boot_pfn(p) << PAGE_SHIFT; + kbuf->cma = p; + + arch_kexec_post_alloc_pages(page_address(p), (int)nr_pages, 0); + + return 0; +} + /** * kexec_locate_mem_hole - find free memory for the purgatory or the next kernel * @kbuf: Parameters for the memory search. @@ -687,6 +727,13 @@ int kexec_locate_mem_hole(struct kexec_buf *kbuf) if (ret <= 0) return ret; + /* + * Try to find a free physically contiguous block of memory first. With that, we + * can avoid any copying at kexec time. + */ + if (!kexec_alloc_contig(kbuf)) + return 0; + if (!IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) ret = kexec_walk_resources(kbuf, locate_mem_hole_callback); else @@ -732,6 +779,7 @@ int kexec_add_buffer(struct kexec_buf *kbuf) /* Ensure minimum alignment needed for segments. */ kbuf->memsz = ALIGN(kbuf->memsz, PAGE_SIZE); kbuf->buf_align = max(kbuf->buf_align, PAGE_SIZE); + kbuf->cma = NULL; /* Walk the RAM ranges and allocate a suitable range for the buffer */ ret = arch_kexec_locate_mem_hole(kbuf); @@ -744,6 +792,7 @@ int kexec_add_buffer(struct kexec_buf *kbuf) ksegment->bufsz = kbuf->bufsz; ksegment->mem = kbuf->mem; ksegment->memsz = kbuf->memsz; + kbuf->image->segment_cma[kbuf->image->nr_segments] = kbuf->cma; kbuf->image->nr_segments++; return 0; } diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h index 30a733a55a67..228bb88c018b 100644 --- a/kernel/kexec_internal.h +++ b/kernel/kexec_internal.h @@ -10,7 +10,7 @@ struct kimage *do_kimage_alloc_init(void); int sanity_check_segment_list(struct kimage *image); void kimage_free_page_list(struct list_head *list); void kimage_free(struct kimage *image); -int kimage_load_segment(struct kimage *image, struct kexec_segment *segment); +int kimage_load_segment(struct kimage *image, int idx); void kimage_terminate(struct kimage *image); int kimage_is_destination_range(struct kimage *image, unsigned long start, unsigned long end); -- cgit v1.2.3 From d171b10b2d7b067c16d79e1d069a23a34f088d23 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Tue, 22 Jul 2025 11:22:30 -0700 Subject: mm/page-flags: remove folio_start_writeback_keepwrite() Commit cd57b77197a4 ("ext4: Convert ext4_bio_write_page() to use a folio) removed set_page_writeback_keepwrite() which was the last/only caller of folio_start_writeback_keepwrite(). Link: https://lkml.kernel.org/r/20250722182230.2114587-1-joannelkoong@gmail.com Signed-off-by: Joanne Koong Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 8e4d6eda8a8d..8d3fa3a91ce4 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -837,8 +837,6 @@ void set_page_writeback(struct page *page); #define folio_start_writeback(folio) \ __folio_start_writeback(folio, false) -#define folio_start_writeback_keepwrite(folio) \ - __folio_start_writeback(folio, true) static __always_inline bool folio_test_head(const struct folio *folio) { -- cgit v1.2.3 From f225b34f1e6c81c50e48f6207ddb6d290be1b932 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Fri, 25 Jul 2025 09:29:41 +0100 Subject: mm/mseal: always define VM_SEALED Patch series "mseal cleanups", v4. Perform a number of cleanups to the mseal logic. Firstly, VM_SEALED is treated differently from every other VMA flag, it really doesn't make sense to do this, so we start by making this consistent with everything else. Next we place the madvise logic where it belongs - in mm/madvise.c. It really makes no sense to abstract this elsewhere. In doing so, we go to great lengths to explain very clearly the previously very confusing logic as to what sealed mappings are impacted here. In doing so, we retain existing logic regarding treatment of madvise() discard operations for a sealed, read-only MAP_PRIVATE file-backed mapping. This is something we likely need to revisit. We then abstract out and explain the 'are there are any gaps in this range in the mm?' check being performed as a prerequisite to mseal being performed. Finally, we simplify the actual mseal logic which is really quite straightforward. No functional change is intended. This patch (of 4): There is no reason to treat VM_SEALED in a special way, in each other case in which a VMA flag is unavailable due to configuration, we simply assign that flag to VM_NONE, so make VM_SEALED consistent with all other VMA flags in this respect. Additionally, use the next available bit for VM_SEALED, 42, rather than arbitrarily putting it at 63 and update the declaration to match all other VMA flags. No functional change intended. Link: https://lkml.kernel.org/r/cover.1753431105.git.lorenzo.stoakes@oracle.com Link: https://lkml.kernel.org/r/aeb398a77029b6e7377cd944328bc9bbc3c90537.1753431105.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes Reviewed-by: Liam R. Howlett Reviewed-by: Pedro Falcato Acked-by: David Hildenbrand Cc: Jann Horn Cc: Jeff Xu Cc: Kees Cook Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/mm.h | 6 ++++-- tools/testing/vma/vma_internal.h | 6 ++++-- 2 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 8e3a4c5b78ff..ceaa780a703a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -414,8 +414,10 @@ extern unsigned int kobjsize(const void *objp); #endif #ifdef CONFIG_64BIT -/* VM is sealed, in vm_flags */ -#define VM_SEALED _BITUL(63) +#define VM_SEALED_BIT 42 +#define VM_SEALED BIT(VM_SEALED_BIT) +#else +#define VM_SEALED VM_NONE #endif /* Bits set in the VMA until the stack is in its final location */ diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h index 991022e9e0d3..0fe52fd6782b 100644 --- a/tools/testing/vma/vma_internal.h +++ b/tools/testing/vma/vma_internal.h @@ -108,8 +108,10 @@ extern unsigned long dac_mmap_min_addr; #define CAP_IPC_LOCK 14 #ifdef CONFIG_64BIT -/* VM is sealed, in vm_flags */ -#define VM_SEALED _BITUL(63) +#define VM_SEALED_BIT 42 +#define VM_SEALED BIT(VM_SEALED_BIT) +#else +#define VM_SEALED VM_NONE #endif #define FIRST_USER_ADDRESS 0UL -- cgit v1.2.3 From 3dfde97800e06882960cc926d2c428f2128b7c70 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 24 Jul 2025 10:52:59 +0530 Subject: mm: add get_and_clear_ptes() and clear_ptes() Patch series "Optimizations for khugepaged", v4. If the underlying folio mapped by the ptes is large, we can process those ptes in a batch using folio_pte_batch(). For arm64 specifically, this results in a 16x reduction in the number of ptep_get() calls, since on a contig block, ptep_get() on arm64 will iterate through all 16 entries to collect a/d bits. Next, ptep_clear() will cause a TLBI for every contig block in the range via contpte_try_unfold(). Instead, use clear_ptes() to only do the TLBI at the first and last contig block of the range. For split folios, there will be no pte batching; the batch size returned by folio_pte_batch() will be 1. For pagetable split folios, the ptes will still point to the same large folio; for arm64, this results in the optimization described above, and for other arches, a minor improvement is expected due to a reduction in the number of function calls and batching atomic operations. This patch (of 3): Let's add variants to be used where "full" does not apply -- which will be the majority of cases in the future. "full" really only applies if we are about to tear down a full MM. Use get_and_clear_ptes() in existing code, clear_ptes() users will be added next. Link: https://lkml.kernel.org/r/20250724052301.23844-2-dev.jain@arm.com Signed-off-by: David Hildenbrand Signed-off-by: Dev Jain Reviewed-by: Baolin Wang Reviewed-by: Barry Song Reviewed-by: Lorenzo Stoakes Reviewed-by: Zi Yan Cc: Liam Howlett Cc: Mariano Pache Cc: Ryan Roberts Signed-off-by: Andrew Morton --- arch/arm64/mm/mmu.c | 2 +- include/linux/pgtable.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ mm/mremap.c | 2 +- mm/rmap.c | 2 +- 4 files changed, 48 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index abd9725796e9..20a89ab97dc5 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1528,7 +1528,7 @@ early_initcall(prevent_bootmem_remove_init); pte_t modify_prot_start_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr) { - pte_t pte = get_and_clear_full_ptes(vma->vm_mm, addr, ptep, nr, /* full = */ 0); + pte_t pte = get_and_clear_ptes(vma->vm_mm, addr, ptep, nr); if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) { /* diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index e3b99920be05..4c035637eeb7 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -736,6 +736,29 @@ static inline pte_t get_and_clear_full_ptes(struct mm_struct *mm, } #endif +/** + * get_and_clear_ptes - Clear present PTEs that map consecutive pages of + * the same folio, collecting dirty/accessed bits. + * @mm: Address space the pages are mapped into. + * @addr: Address the first page is mapped at. + * @ptep: Page table pointer for the first entry. + * @nr: Number of entries to clear. + * + * Use this instead of get_and_clear_full_ptes() if it is known that we don't + * need to clear the full mm, which is mostly the case. + * + * Note that PTE bits in the PTE range besides the PFN can differ. For example, + * some PTEs might be write-protected. + * + * Context: The caller holds the page table lock. The PTEs map consecutive + * pages that belong to the same folio. The PTEs are all in the same PMD. + */ +static inline pte_t get_and_clear_ptes(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, unsigned int nr) +{ + return get_and_clear_full_ptes(mm, addr, ptep, nr, 0); +} + #ifndef clear_full_ptes /** * clear_full_ptes - Clear present PTEs that map consecutive pages of the same @@ -768,6 +791,28 @@ static inline void clear_full_ptes(struct mm_struct *mm, unsigned long addr, } #endif +/** + * clear_ptes - Clear present PTEs that map consecutive pages of the same folio. + * @mm: Address space the pages are mapped into. + * @addr: Address the first page is mapped at. + * @ptep: Page table pointer for the first entry. + * @nr: Number of entries to clear. + * + * Use this instead of clear_full_ptes() if it is known that we don't need to + * clear the full mm, which is mostly the case. + * + * Note that PTE bits in the PTE range besides the PFN can differ. For example, + * some PTEs might be write-protected. + * + * Context: The caller holds the page table lock. The PTEs map consecutive + * pages that belong to the same folio. The PTEs are all in the same PMD. + */ +static inline void clear_ptes(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, unsigned int nr) +{ + clear_full_ptes(mm, addr, ptep, nr, 0); +} + /* * If two threads concurrently fault at the same page, the thread that * won the race updates the PTE and its local TLB/Cache. The other thread diff --git a/mm/mremap.c b/mm/mremap.c index ac39845e9718..677a4d744df9 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -280,7 +280,7 @@ static int move_ptes(struct pagetable_move_control *pmc, old_pte, max_nr_ptes); force_flush = true; } - pte = get_and_clear_full_ptes(mm, old_addr, old_ptep, nr_ptes, 0); + pte = get_and_clear_ptes(mm, old_addr, old_ptep, nr_ptes); pte = move_pte(pte, old_addr, new_addr); pte = move_soft_dirty_pte(pte); diff --git a/mm/rmap.c b/mm/rmap.c index f93ce27132ab..568198e9efc2 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -2036,7 +2036,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, flush_cache_range(vma, address, end_addr); /* Nuke the page table entry. */ - pteval = get_and_clear_full_ptes(mm, address, pvmw.pte, nr_pages, 0); + pteval = get_and_clear_ptes(mm, address, pvmw.pte, nr_pages); /* * We clear the PTE but do not flush so potentially * a remote CPU could still be writing to the folio. -- cgit v1.2.3 From 9a4f90e246615d1f42a9b907deb9b4c0a418d996 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Fri, 25 Jul 2025 15:29:01 +0100 Subject: mm: remove mm/io-mapping.c This is dead code, which was used from commit b739f125e4eb ("i915: use io_mapping_map_user") but reverted a month later by commit 0e4fe0c9f2f9 ("Revert "i915: use io_mapping_map_user"") back in 2021. Since then nobody has used it, so remove it. [akpm@linux-foundation.org: update Documentation/core-api/mm-api.rst, per Vlastimil] Link: https://lkml.kernel.org/r/20250725142901.81502-1-lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes Acked-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: Michal Hocko Cc: Mike Rapoport Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- Documentation/core-api/mm-api.rst | 1 - include/linux/io-mapping.h | 3 --- mm/Kconfig | 4 ---- mm/Makefile | 1 - mm/io-mapping.c | 30 ------------------------------ 5 files changed, 39 deletions(-) delete mode 100644 mm/io-mapping.c (limited to 'include/linux') diff --git a/Documentation/core-api/mm-api.rst b/Documentation/core-api/mm-api.rst index af8151db88b2..24970b91ac15 100644 --- a/Documentation/core-api/mm-api.rst +++ b/Documentation/core-api/mm-api.rst @@ -139,4 +139,3 @@ More Memory Management Functions .. kernel-doc:: mm/mmu_notifier.c .. kernel-doc:: mm/balloon_compaction.c .. kernel-doc:: mm/huge_memory.c -.. kernel-doc:: mm/io-mapping.c diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 7376c1df9c90..c16353cc6e3c 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -225,7 +225,4 @@ io_mapping_free(struct io_mapping *iomap) kfree(iomap); } -int io_mapping_map_user(struct io_mapping *iomap, struct vm_area_struct *vma, - unsigned long addr, unsigned long pfn, unsigned long size); - #endif /* _LINUX_IO_MAPPING_H */ diff --git a/mm/Kconfig b/mm/Kconfig index d5d4eca947a6..e443fe8cd6cf 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1242,10 +1242,6 @@ config KMAP_LOCAL config KMAP_LOCAL_NON_LINEAR_PTE_ARRAY bool -# struct io_mapping based helper. Selected by drivers that need them -config IO_MAPPING - bool - config MEMFD_CREATE bool "Enable memfd_create() system call" if EXPERT diff --git a/mm/Makefile b/mm/Makefile index 1a7a11d4933d..ef54aa615d9d 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -141,7 +141,6 @@ obj-$(CONFIG_MEMFD_CREATE) += memfd.o obj-$(CONFIG_MAPPING_DIRTY_HELPERS) += mapping_dirty_helpers.o obj-$(CONFIG_PTDUMP) += ptdump.o obj-$(CONFIG_PAGE_REPORTING) += page_reporting.o -obj-$(CONFIG_IO_MAPPING) += io-mapping.o obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o obj-$(CONFIG_SHRINKER_DEBUG) += shrinker_debug.o diff --git a/mm/io-mapping.c b/mm/io-mapping.c deleted file mode 100644 index d3586e95c12c..000000000000 --- a/mm/io-mapping.c +++ /dev/null @@ -1,30 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only - -#include -#include - -/** - * io_mapping_map_user - remap an I/O mapping to userspace - * @iomap: the source io_mapping - * @vma: user vma to map to - * @addr: target user address to start at - * @pfn: physical address of kernel memory - * @size: size of map area - * - * Note: this is only safe if the mm semaphore is held when called. - */ -int io_mapping_map_user(struct io_mapping *iomap, struct vm_area_struct *vma, - unsigned long addr, unsigned long pfn, unsigned long size) -{ - vm_flags_t expected_flags = VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; - - if (WARN_ON_ONCE((vma->vm_flags & expected_flags) != expected_flags)) - return -EINVAL; - - pgprot_t remap_prot = __pgprot((pgprot_val(iomap->prot) & _PAGE_CACHE_MASK) | - (pgprot_val(vma->vm_page_prot) & ~_PAGE_CACHE_MASK)); - - /* We rely on prevalidation of the io-mapping to skip pfnmap tracking. */ - return remap_pfn_range_notrack(vma, addr, pfn, size, remap_prot); -} -EXPORT_SYMBOL_GPL(io_mapping_map_user); -- cgit v1.2.3 From a222439e1e273fa0f4e37ce17aeb109f3e91824f Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Fri, 25 Jul 2025 14:16:24 +0200 Subject: mm/rmap: add anon_vma lifetime debug check If an anon folio is mapped into userspace, its anon_vma must be alive, otherwise rmap walks can hit UAF. There have been syzkaller reports a few months ago[1][2] of UAF in rmap walks that seems to indicate that there can be pages with elevated mapcount whose anon_vma has already been freed, but I think we never figured out what the cause is; and syzkaller only hit these UAFs when memory pressure randomly caused reclaim to rmap-walk the affected pages, so it of course didn't manage to create a reproducer. Add a VM_WARN_ON_FOLIO() when we add/remove mappings of anonymous folios to hopefully catch such issues more reliably. [1] https://lore.kernel.org/r/67abaeaf.050a0220.110943.0041.GAE@google.com [2] https://lore.kernel.org/r/67a76f33.050a0220.3d72c.0028.GAE@google.com Link: https://lkml.kernel.org/r/20250725-anonvma-uaf-debug-v2-1-bc3c7e5ba5b1@google.com Signed-off-by: Jann Horn Acked-by: David Hildenbrand Reviewed-by: Lorenzo Stoakes Acked-by: Vlastimil Babka Acked-by: Harry Yoo Cc: David Hildenbrand Cc: Jann Horn Cc: Liam Howlett Cc: Rik van Riel Signed-off-by: Andrew Morton --- include/linux/rmap.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 20803fcb49a7..6cd020eea37a 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -449,6 +449,28 @@ static inline void __folio_rmap_sanity_checks(const struct folio *folio, default: VM_WARN_ON_ONCE(true); } + + /* + * Anon folios must have an associated live anon_vma as long as they're + * mapped into userspace. + * Note that the atomic_read() mainly does two things: + * + * 1. In KASAN builds with CONFIG_SLUB_RCU_DEBUG, it causes KASAN to + * check that the associated anon_vma has not yet been freed (subject + * to KASAN's usual limitations). This check will pass if the + * anon_vma's refcount has already dropped to 0 but an RCU grace + * period hasn't passed since then. + * 2. If the anon_vma has not yet been freed, it checks that the + * anon_vma still has a nonzero refcount (as opposed to being in the + * middle of an RCU delay for getting freed). + */ + if (folio_test_anon(folio) && !folio_test_ksm(folio)) { + unsigned long mapping = (unsigned long)folio->mapping; + struct anon_vma *anon_vma; + + anon_vma = (void *)(mapping - FOLIO_MAPPING_ANON); + VM_WARN_ON_FOLIO(atomic_read(&anon_vma->refcount) == 0, folio); + } } /* -- cgit v1.2.3 From 9bbffee67ffd16360179327b57f3b1245579ef08 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 28 Jul 2025 10:53:55 -0700 Subject: mm: fix a UAF when vma->mm is freed after vma->vm_refcnt got dropped By inducing delays in the right places, Jann Horn created a reproducer for a hard to hit UAF issue that became possible after VMAs were allowed to be recycled by adding SLAB_TYPESAFE_BY_RCU to their cache. Race description is borrowed from Jann's discovery report: lock_vma_under_rcu() looks up a VMA locklessly with mas_walk() under rcu_read_lock(). At that point, the VMA may be concurrently freed, and it can be recycled by another process. vma_start_read() then increments the vma->vm_refcnt (if it is in an acceptable range), and if this succeeds, vma_start_read() can return a recycled VMA. In this scenario where the VMA has been recycled, lock_vma_under_rcu() will then detect the mismatching ->vm_mm pointer and drop the VMA through vma_end_read(), which calls vma_refcount_put(). vma_refcount_put() drops the refcount and then calls rcuwait_wake_up() using a copy of vma->vm_mm. This is wrong: It implicitly assumes that the caller is keeping the VMA's mm alive, but in this scenario the caller has no relation to the VMA's mm, so the rcuwait_wake_up() can cause UAF. The diagram depicting the race: T1 T2 T3 == == == lock_vma_under_rcu mas_walk mmap vma_start_read __refcount_inc_not_zero_limited_acquire munmap __vma_enter_locked refcount_add_not_zero vma_end_read vma_refcount_put __refcount_dec_and_test rcuwait_wait_event rcuwait_wake_up [UAF] Note that rcuwait_wait_event() in T3 does not block because refcount was already dropped by T1. At this point T3 can exit and free the mm causing UAF in T1. To avoid this we move vma->vm_mm verification into vma_start_read() and grab vma->vm_mm to stabilize it before vma_refcount_put() operation. [surenb@google.com: v3] Link: https://lkml.kernel.org/r/20250729145709.2731370-1-surenb@google.com Link: https://lkml.kernel.org/r/20250728175355.2282375-1-surenb@google.com Fixes: 3104138517fc ("mm: make vma cache SLAB_TYPESAFE_BY_RCU") Signed-off-by: Suren Baghdasaryan Reported-by: Jann Horn Closes: https://lore.kernel.org/all/CAG48ez0-deFbVH=E3jbkWx=X3uVbd8nWeo6kbJPQ0KoUD+m2tA@mail.gmail.com/ Reviewed-by: Vlastimil Babka Acked-by: Lorenzo Stoakes Cc: Jann Horn Cc: Liam Howlett Cc: Signed-off-by: Andrew Morton --- include/linux/mmap_lock.h | 30 ++++++++++++++++++++++++++++++ mm/mmap_lock.c | 10 +++------- 2 files changed, 33 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 1f4f44951abe..11a078de9150 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -12,6 +12,7 @@ extern int rcuwait_wake_up(struct rcuwait *w); #include #include #include +#include #define MMAP_LOCK_INITIALIZER(name) \ .mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock), @@ -154,6 +155,10 @@ static inline void vma_refcount_put(struct vm_area_struct *vma) * reused and attached to a different mm before we lock it. * Returns the vma on success, NULL on failure to lock and EAGAIN if vma got * detached. + * + * WARNING! The vma passed to this function cannot be used if the function + * fails to lock it because in certain cases RCU lock is dropped and then + * reacquired. Once RCU lock is dropped the vma can be concurently freed. */ static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm, struct vm_area_struct *vma) @@ -183,6 +188,31 @@ static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm, } rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_); + + /* + * If vma got attached to another mm from under us, that mm is not + * stable and can be freed in the narrow window after vma->vm_refcnt + * is dropped and before rcuwait_wake_up(mm) is called. Grab it before + * releasing vma->vm_refcnt. + */ + if (unlikely(vma->vm_mm != mm)) { + /* Use a copy of vm_mm in case vma is freed after we drop vm_refcnt */ + struct mm_struct *other_mm = vma->vm_mm; + + /* + * __mmdrop() is a heavy operation and we don't need RCU + * protection here. Release RCU lock during these operations. + * We reinstate the RCU read lock as the caller expects it to + * be held when this function returns even on error. + */ + rcu_read_unlock(); + mmgrab(other_mm); + vma_refcount_put(vma); + mmdrop(other_mm); + rcu_read_lock(); + return NULL; + } + /* * Overflow of vm_lock_seq/mm_lock_seq might produce false locked result. * False unlocked result is impossible because we modify and check diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c index 729fb7d0dd59..b006cec8e6fe 100644 --- a/mm/mmap_lock.c +++ b/mm/mmap_lock.c @@ -164,8 +164,7 @@ retry: */ /* Check if the vma we locked is the right one. */ - if (unlikely(vma->vm_mm != mm || - address < vma->vm_start || address >= vma->vm_end)) + if (unlikely(address < vma->vm_start || address >= vma->vm_end)) goto inval_end_read; rcu_read_unlock(); @@ -236,11 +235,8 @@ retry: goto fallback; } - /* - * Verify the vma we locked belongs to the same address space and it's - * not behind of the last search position. - */ - if (unlikely(vma->vm_mm != mm || from_addr >= vma->vm_end)) + /* Verify the vma is not behind the last search position. */ + if (unlikely(from_addr >= vma->vm_end)) goto fallback_unlock; /* -- cgit v1.2.3 From fcd90ad31e29d0b403f3a074a64cd7f0876175dd Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Sun, 13 Jul 2025 10:17:23 +0300 Subject: execmem: drop unused execmem_update_copy() Patch series "x86: enable EXECMEM_ROX_CACHE for ftrace and kprobes", v3. These patches enable use of EXECMEM_ROX_CACHE for ftrace and kprobes allocations on x86. They also include some ground work in execmem. Since the execmem model for caching large ROX pages changed from the initial assumption that the memory that is allocated from ROX cache is always ROX to the current state where memory can be temporarily made RW and then restored to ROX, we can stop using text poking to update it. This also saves the hassle of trying lock text_mutex in execmem_cache_free() when kprobes already hold that mutex. This patch (of 8): The execmem_update_copy() that used text poking was required when memory allocated from ROX cache was always read-only. Since now its permissions can be switched to read-write there is no need in a function that updates memory with text poking. Remove it. Link: https://lkml.kernel.org/r/20250713071730.4117334-1-rppt@kernel.org Link: https://lkml.kernel.org/r/20250713071730.4117334-2-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Acked-by: Peter Zijlstra (Intel) Cc: Daniel Gomez Cc: Masami Hiramatsu (Google) Cc: Petr Pavlu Cc: Steven Rostedt (Google) Signed-off-by: Andrew Morton --- include/linux/execmem.h | 13 ------------- mm/execmem.c | 5 ----- 2 files changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/execmem.h b/include/linux/execmem.h index 3be35680a54f..734fbe83d98e 100644 --- a/include/linux/execmem.h +++ b/include/linux/execmem.h @@ -185,19 +185,6 @@ DEFINE_FREE(execmem, void *, if (_T) execmem_free(_T)); struct vm_struct *execmem_vmap(size_t size); #endif -/** - * execmem_update_copy - copy an update to executable memory - * @dst: destination address to update - * @src: source address containing the data - * @size: how many bytes of memory shold be copied - * - * Copy @size bytes from @src to @dst using text poking if the memory at - * @dst is read-only. - * - * Return: a pointer to @dst or NULL on error - */ -void *execmem_update_copy(void *dst, const void *src, size_t size); - /** * execmem_is_rox - check if execmem is read-only * @type - the execmem type to check diff --git a/mm/execmem.c b/mm/execmem.c index 627e6cf64f4f..aac211bc88c5 100644 --- a/mm/execmem.c +++ b/mm/execmem.c @@ -399,11 +399,6 @@ void execmem_free(void *ptr) vfree(ptr); } -void *execmem_update_copy(void *dst, const void *src, size_t size) -{ - return text_poke_copy(dst, src, size); -} - bool execmem_is_rox(enum execmem_type type) { return !!(execmem_info->ranges[type].flags & EXECMEM_ROX_CACHE); -- cgit v1.2.3 From 838955f64ae7582f009a3538889bb9244f37ab26 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Sun, 13 Jul 2025 10:17:24 +0300 Subject: execmem: introduce execmem_alloc_rw() Some callers of execmem_alloc() require the memory to be temporarily writable even when it is allocated from ROX cache. These callers use execemem_make_temp_rw() right after the call to execmem_alloc(). Wrap this sequence in execmem_alloc_rw() API. Link: https://lkml.kernel.org/r/20250713071730.4117334-3-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Reviewed-by: Daniel Gomez Reviewed-by: Petr Pavlu Acked-by: Peter Zijlstra (Intel) Cc: Masami Hiramatsu (Google) Cc: Steven Rostedt (Google) Signed-off-by: Andrew Morton --- arch/x86/kernel/alternative.c | 3 +-- include/linux/execmem.h | 38 ++++++++++++++++++++++---------------- kernel/module/main.c | 13 ++----------- mm/execmem.c | 27 ++++++++++++++++++++++++++- 4 files changed, 51 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index ea1d984166cd..526a5fef93ab 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -120,7 +120,7 @@ struct its_array its_pages; static void *__its_alloc(struct its_array *pages) { - void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE); + void *page __free(execmem) = execmem_alloc_rw(EXECMEM_MODULE_TEXT, PAGE_SIZE); if (!page) return NULL; @@ -237,7 +237,6 @@ static void *its_alloc(void) if (!page) return NULL; - execmem_make_temp_rw(page, PAGE_SIZE); if (pages == &its_pages) set_memory_x((unsigned long)page, 1); diff --git a/include/linux/execmem.h b/include/linux/execmem.h index 734fbe83d98e..8b61b05da7d5 100644 --- a/include/linux/execmem.h +++ b/include/linux/execmem.h @@ -67,21 +67,6 @@ enum execmem_range_flags { */ void execmem_fill_trapping_insns(void *ptr, size_t size, bool writable); -/** - * execmem_make_temp_rw - temporarily remap region with read-write - * permissions - * @ptr: address of the region to remap - * @size: size of the region to remap - * - * Remaps a part of the cached large page in the ROX cache in the range - * [@ptr, @ptr + @size) as writable and not executable. The caller must - * have exclusive ownership of this range and ensure nothing will try to - * execute code in this range. - * - * Return: 0 on success or negative error code on failure. - */ -int execmem_make_temp_rw(void *ptr, size_t size); - /** * execmem_restore_rox - restore read-only-execute permissions * @ptr: address of the region to remap @@ -95,7 +80,6 @@ int execmem_make_temp_rw(void *ptr, size_t size); */ int execmem_restore_rox(void *ptr, size_t size); #else -static inline int execmem_make_temp_rw(void *ptr, size_t size) { return 0; } static inline int execmem_restore_rox(void *ptr, size_t size) { return 0; } #endif @@ -165,6 +149,28 @@ struct execmem_info *execmem_arch_setup(void); */ void *execmem_alloc(enum execmem_type type, size_t size); +/** + * execmem_alloc_rw - allocate writable executable memory + * @type: type of the allocation + * @size: how many bytes of memory are required + * + * Allocates memory that will contain executable code, either generated or + * loaded from kernel modules. + * + * Allocates memory that will contain data coupled with executable code, + * like data sections in kernel modules. + * + * Forces writable permissions on the allocated memory and the caller is + * responsible to manage the permissions afterwards. + * + * For architectures that use ROX cache the permissions will be set to R+W. + * For architectures that don't use ROX cache the default permissions for @type + * will be used as they must be writable. + * + * Return: a pointer to the allocated memory or %NULL + */ +void *execmem_alloc_rw(enum execmem_type type, size_t size); + /** * execmem_free - free executable memory * @ptr: pointer to the memory that should be freed diff --git a/kernel/module/main.c b/kernel/module/main.c index 413ac6ea3702..d009326ef7bb 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1292,20 +1292,11 @@ static int module_memory_alloc(struct module *mod, enum mod_mem_type type) else execmem_type = EXECMEM_MODULE_TEXT; - ptr = execmem_alloc(execmem_type, size); + ptr = execmem_alloc_rw(execmem_type, size); if (!ptr) return -ENOMEM; - if (execmem_is_rox(execmem_type)) { - int err = execmem_make_temp_rw(ptr, size); - - if (err) { - execmem_free(ptr); - return -ENOMEM; - } - - mod->mem[type].is_rox = true; - } + mod->mem[type].is_rox = execmem_is_rox(execmem_type); /* * The pointer to these blocks of memory are stored on the module diff --git a/mm/execmem.c b/mm/execmem.c index aac211bc88c5..d0bf0123bce4 100644 --- a/mm/execmem.c +++ b/mm/execmem.c @@ -336,7 +336,7 @@ static bool execmem_cache_free(void *ptr) return true; } -int execmem_make_temp_rw(void *ptr, size_t size) +static int execmem_force_rw(void *ptr, size_t size) { unsigned int nr = PAGE_ALIGN(size) >> PAGE_SHIFT; unsigned long addr = (unsigned long)ptr; @@ -358,6 +358,16 @@ int execmem_restore_rox(void *ptr, size_t size) } #else /* CONFIG_ARCH_HAS_EXECMEM_ROX */ +/* + * when ROX cache is not used the permissions defined by architectures for + * execmem ranges that are updated before use (e.g. EXECMEM_MODULE_TEXT) must + * be writable anyway + */ +static inline int execmem_force_rw(void *ptr, size_t size) +{ + return 0; +} + static void *execmem_cache_alloc(struct execmem_range *range, size_t size) { return NULL; @@ -387,6 +397,21 @@ void *execmem_alloc(enum execmem_type type, size_t size) return kasan_reset_tag(p); } +void *execmem_alloc_rw(enum execmem_type type, size_t size) +{ + void *p __free(execmem) = execmem_alloc(type, size); + int err; + + if (!p) + return NULL; + + err = execmem_force_rw(p, size); + if (err) + return NULL; + + return no_free_ptr(p); +} + void execmem_free(void *ptr) { /* -- cgit v1.2.3 From ab674b6871b049aab2e86d1d7375526368ed175a Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Sun, 13 Jul 2025 10:17:28 +0300 Subject: execmem: drop writable parameter from execmem_fill_trapping_insns() After update of execmem_cache_free() that made memory writable before updating it, there is no need to update read only memory, so the writable parameter to execmem_fill_trapping_insns() is not needed. Drop it. Link: https://lkml.kernel.org/r/20250713071730.4117334-7-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) Acked-by: Peter Zijlstra (Intel) Cc: Daniel Gomez Cc: Masami Hiramatsu (Google) Cc: Petr Pavlu Cc: Steven Rostedt (Google) Signed-off-by: Andrew Morton --- arch/x86/mm/init.c | 8 ++------ include/linux/execmem.h | 3 +-- mm/execmem.c | 4 ++-- 3 files changed, 5 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 7456df985d96..dbc63f0d538f 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -1063,13 +1063,9 @@ unsigned long arch_max_swapfile_size(void) static struct execmem_info execmem_info __ro_after_init; #ifdef CONFIG_ARCH_HAS_EXECMEM_ROX -void execmem_fill_trapping_insns(void *ptr, size_t size, bool writeable) +void execmem_fill_trapping_insns(void *ptr, size_t size) { - /* fill memory with INT3 instructions */ - if (writeable) - memset(ptr, INT3_INSN_OPCODE, size); - else - text_poke_set(ptr, INT3_INSN_OPCODE, size); + memset(ptr, INT3_INSN_OPCODE, size); } #endif diff --git a/include/linux/execmem.h b/include/linux/execmem.h index 8b61b05da7d5..7de229134e30 100644 --- a/include/linux/execmem.h +++ b/include/linux/execmem.h @@ -60,12 +60,11 @@ enum execmem_range_flags { * will trap * @ptr: pointer to memory to fill * @size: size of the range to fill - * @writable: is the memory poited by @ptr is writable or ROX * * A hook for architecures to fill execmem ranges with invalid instructions. * Architectures that use EXECMEM_ROX_CACHE must implement this. */ -void execmem_fill_trapping_insns(void *ptr, size_t size, bool writable); +void execmem_fill_trapping_insns(void *ptr, size_t size); /** * execmem_restore_rox - restore read-only-execute permissions diff --git a/mm/execmem.c b/mm/execmem.c index 9abf76a63a79..1785d7f435e4 100644 --- a/mm/execmem.c +++ b/mm/execmem.c @@ -304,7 +304,7 @@ static int execmem_cache_populate(struct execmem_range *range, size_t size) goto err_free_mem; /* fill memory with instructions that will trap */ - execmem_fill_trapping_insns(p, alloc_size, /* writable = */ true); + execmem_fill_trapping_insns(p, alloc_size); err = set_memory_rox((unsigned long)p, vm->nr_pages); if (err) @@ -363,7 +363,7 @@ static int __execmem_cache_free(struct ma_state *mas, void *ptr, gfp_t gfp_mask) if (err) return err; - execmem_fill_trapping_insns(ptr, size, /* writable = */ true); + execmem_fill_trapping_insns(ptr, size); execmem_restore_rox(ptr, size); err = execmem_cache_add_locked(ptr, size, gfp_mask); -- cgit v1.2.3 From bb5b0b4317c9516bdc5e9a4235e3b5f1a73b7e48 Mon Sep 17 00:00:00 2001 From: Joshua Kinard Date: Mon, 21 Jul 2025 13:00:51 -0400 Subject: rtc: ds1685: Update Joshua Kinard's email address. I am switching my address to a personal domain, so need to update the driver's files and the entry in MAINTAINERS. Signed-off-by: Joshua Kinard Link: https://lore.kernel.org/r/20250721170051.32407-1-kumba@gentoo.org Signed-off-by: Alexandre Belloni --- MAINTAINERS | 2 +- drivers/rtc/rtc-ds1685.c | 4 ++-- include/linux/rtc/ds1685.h | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index a92290fffa16..536befd32be8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6608,7 +6608,7 @@ S: Supported F: drivers/input/keyboard/dlink-dir685-touchkeys.c DALLAS/MAXIM DS1685-FAMILY REAL TIME CLOCK -M: Joshua Kinard +M: Joshua Kinard S: Maintained F: drivers/rtc/rtc-ds1685.c F: include/linux/rtc/ds1685.h diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c index 38e25f63597a..97423f1d0361 100644 --- a/drivers/rtc/rtc-ds1685.c +++ b/drivers/rtc/rtc-ds1685.c @@ -3,7 +3,7 @@ * An rtc driver for the Dallas/Maxim DS1685/DS1687 and related real-time * chips. * - * Copyright (C) 2011-2014 Joshua Kinard . + * Copyright (C) 2011-2014 Joshua Kinard . * Copyright (C) 2009 Matthias Fuchs . * * References: @@ -1436,7 +1436,7 @@ EXPORT_SYMBOL_GPL(ds1685_rtc_poweroff); /* ----------------------------------------------------------------------- */ -MODULE_AUTHOR("Joshua Kinard "); +MODULE_AUTHOR("Joshua Kinard "); MODULE_AUTHOR("Matthias Fuchs "); MODULE_DESCRIPTION("Dallas/Maxim DS1685/DS1687-series RTC driver"); MODULE_LICENSE("GPL"); diff --git a/include/linux/rtc/ds1685.h b/include/linux/rtc/ds1685.h index 5a41c3bbcbe3..01da4582db6d 100644 --- a/include/linux/rtc/ds1685.h +++ b/include/linux/rtc/ds1685.h @@ -8,7 +8,7 @@ * include larger, battery-backed NV-SRAM, burst-mode access, and an RTC * write counter. * - * Copyright (C) 2011-2014 Joshua Kinard . + * Copyright (C) 2011-2014 Joshua Kinard . * Copyright (C) 2009 Matthias Fuchs . * * References: -- cgit v1.2.3 From 7c527c15cdda2e0a26a05ac15a44d3e14738fc55 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Sun, 3 Aug 2025 21:20:12 +0900 Subject: firewire: core: use reference counting to invoke address handlers safely The lifetime of address handler has been managed by linked list and RCU. This approach was introduced in commit 35202f7d8420 ("firewire: remove global lock around address handlers, convert to RCU"). The invocations of address handler are performed within RCU read-side critical sections. In commit 57e6d9f85fff ("firewire: ohci: use workqueue to handle events of AR request/response contexts"), the invocations are in a workqueue context. The approach still imposes limitation that sleeping is not allowed within RCU read-side critical sections. However, since sleeping is not permitted within RCU read-side critical sections, this approach still has a limitation. This commit adds reference counting to decouple handler invocation from handler discovery. The linked list and RCU is used to discover the handlers, while the reference counting is used to invoke them safely. Link: https://lore.kernel.org/r/20250803122015.236493-2-o-takashi@sakamocchi.jp Signed-off-by: Takashi Sakamoto --- drivers/firewire/core-transaction.c | 32 ++++++++++++++++++++++++++++++-- include/linux/firewire.h | 4 ++++ 2 files changed, 34 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/firewire/core-transaction.c b/drivers/firewire/core-transaction.c index d28477d84697..29ca9f3f14ce 100644 --- a/drivers/firewire/core-transaction.c +++ b/drivers/firewire/core-transaction.c @@ -550,6 +550,23 @@ const struct fw_address_region fw_unit_space_region = { .start = 0xfffff0000900ULL, .end = 0x1000000000000ULL, }; #endif /* 0 */ +static void complete_address_handler(struct kref *kref) +{ + struct fw_address_handler *handler = container_of(kref, struct fw_address_handler, kref); + + complete(&handler->done); +} + +static void get_address_handler(struct fw_address_handler *handler) +{ + kref_get(&handler->kref); +} + +static int put_address_handler(struct fw_address_handler *handler) +{ + return kref_put(&handler->kref, complete_address_handler); +} + /** * fw_core_add_address_handler() - register for incoming requests * @handler: callback @@ -596,6 +613,8 @@ int fw_core_add_address_handler(struct fw_address_handler *handler, if (other != NULL) { handler->offset += other->length; } else { + init_completion(&handler->done); + kref_init(&handler->kref); list_add_tail_rcu(&handler->link, &address_handler_list); ret = 0; break; @@ -621,6 +640,9 @@ void fw_core_remove_address_handler(struct fw_address_handler *handler) list_del_rcu(&handler->link); synchronize_rcu(); + + if (!put_address_handler(handler)) + wait_for_completion(&handler->done); } EXPORT_SYMBOL(fw_core_remove_address_handler); @@ -913,10 +935,13 @@ static void handle_exclusive_region_request(struct fw_card *card, scoped_guard(rcu) { handler = lookup_enclosing_address_handler(&address_handler_list, offset, request->length); - if (handler) + if (handler) { + get_address_handler(handler); handler->address_callback(card, request, tcode, destination, source, p->generation, offset, request->data, request->length, handler->callback_data); + put_address_handler(handler); + } } if (!handler) @@ -952,10 +977,13 @@ static void handle_fcp_region_request(struct fw_card *card, scoped_guard(rcu) { list_for_each_entry_rcu(handler, &address_handler_list, link) { - if (is_enclosing_handler(handler, offset, request->length)) + if (is_enclosing_handler(handler, offset, request->length)) { + get_address_handler(handler); handler->address_callback(card, request, tcode, destination, source, p->generation, offset, request->data, request->length, handler->callback_data); + put_address_handler(handler); + } } } diff --git a/include/linux/firewire.h b/include/linux/firewire.h index cceb70415ed2..d38c6e538e5c 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -341,7 +341,11 @@ struct fw_address_handler { u64 length; fw_address_callback_t address_callback; void *callback_data; + + // Only for core functions. struct list_head link; + struct kref kref; + struct completion done; }; struct fw_address_region { -- cgit v1.2.3 From 86624ba3b522b6512def25534341da93356c8da4 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 14 Jul 2025 13:08:25 -0300 Subject: vfio/pci: Do vf_token checks for VFIO_DEVICE_BIND_IOMMUFD This was missed during the initial implementation. The VFIO PCI encodes the vf_token inside the device name when opening the device from the group FD, something like: "0000:04:10.0 vf_token=bd8d9d2b-5a5f-4f5a-a211-f591514ba1f3" This is used to control access to a VF unless there is co-ordination with the owner of the PF. Since we no longer have a device name in the cdev path, pass the token directly through VFIO_DEVICE_BIND_IOMMUFD using an optional field indicated by VFIO_DEVICE_BIND_FLAG_TOKEN. Fixes: 5fcc26969a16 ("vfio: Add VFIO_DEVICE_BIND_IOMMUFD") Tested-by: Shameer Kolothum Reviewed-by: Yi Liu Signed-off-by: Jason Gunthorpe Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/0-v3-bdd8716e85fe+3978a-vfio_token_jgg@nvidia.com Signed-off-by: Alex Williamson --- drivers/vfio/device_cdev.c | 38 ++++++++++++++++++++++++-- drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c | 1 + drivers/vfio/pci/mlx5/main.c | 1 + drivers/vfio/pci/nvgrace-gpu/main.c | 2 ++ drivers/vfio/pci/pds/vfio_dev.c | 1 + drivers/vfio/pci/qat/main.c | 1 + drivers/vfio/pci/vfio_pci.c | 1 + drivers/vfio/pci/vfio_pci_core.c | 22 +++++++++------ drivers/vfio/pci/virtio/main.c | 3 ++ include/linux/vfio.h | 4 +++ include/linux/vfio_pci_core.h | 2 ++ include/uapi/linux/vfio.h | 12 +++++++- 12 files changed, 76 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/vfio/device_cdev.c b/drivers/vfio/device_cdev.c index 281a8dc3ed49..480cac3a0c27 100644 --- a/drivers/vfio/device_cdev.c +++ b/drivers/vfio/device_cdev.c @@ -60,22 +60,50 @@ static void vfio_df_get_kvm_safe(struct vfio_device_file *df) spin_unlock(&df->kvm_ref_lock); } +static int vfio_df_check_token(struct vfio_device *device, + const struct vfio_device_bind_iommufd *bind) +{ + uuid_t uuid; + + if (!device->ops->match_token_uuid) { + if (bind->flags & VFIO_DEVICE_BIND_FLAG_TOKEN) + return -EINVAL; + return 0; + } + + if (!(bind->flags & VFIO_DEVICE_BIND_FLAG_TOKEN)) + return device->ops->match_token_uuid(device, NULL); + + if (copy_from_user(&uuid, u64_to_user_ptr(bind->token_uuid_ptr), + sizeof(uuid))) + return -EFAULT; + return device->ops->match_token_uuid(device, &uuid); +} + long vfio_df_ioctl_bind_iommufd(struct vfio_device_file *df, struct vfio_device_bind_iommufd __user *arg) { + const u32 VALID_FLAGS = VFIO_DEVICE_BIND_FLAG_TOKEN; struct vfio_device *device = df->device; struct vfio_device_bind_iommufd bind; unsigned long minsz; + u32 user_size; int ret; static_assert(__same_type(arg->out_devid, df->devid)); minsz = offsetofend(struct vfio_device_bind_iommufd, out_devid); - if (copy_from_user(&bind, arg, minsz)) - return -EFAULT; + ret = get_user(user_size, &arg->argsz); + if (ret) + return ret; + if (user_size < minsz) + return -EINVAL; + ret = copy_struct_from_user(&bind, minsz, arg, user_size); + if (ret) + return ret; - if (bind.argsz < minsz || bind.flags || bind.iommufd < 0) + if (bind.iommufd < 0 || bind.flags & ~VALID_FLAGS) return -EINVAL; /* BIND_IOMMUFD only allowed for cdev fds */ @@ -93,6 +121,10 @@ long vfio_df_ioctl_bind_iommufd(struct vfio_device_file *df, goto out_unlock; } + ret = vfio_df_check_token(device, &bind); + if (ret) + goto out_unlock; + df->iommufd = iommufd_ctx_from_fd(bind.iommufd); if (IS_ERR(df->iommufd)) { ret = PTR_ERR(df->iommufd); diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c index 2149f49aeec7..397f5e445136 100644 --- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c +++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c @@ -1583,6 +1583,7 @@ static const struct vfio_device_ops hisi_acc_vfio_pci_ops = { .mmap = vfio_pci_core_mmap, .request = vfio_pci_core_request, .match = vfio_pci_core_match, + .match_token_uuid = vfio_pci_core_match_token_uuid, .bind_iommufd = vfio_iommufd_physical_bind, .unbind_iommufd = vfio_iommufd_physical_unbind, .attach_ioas = vfio_iommufd_physical_attach_ioas, diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c index 93f894fe60d2..7ec47e736a8e 100644 --- a/drivers/vfio/pci/mlx5/main.c +++ b/drivers/vfio/pci/mlx5/main.c @@ -1372,6 +1372,7 @@ static const struct vfio_device_ops mlx5vf_pci_ops = { .mmap = vfio_pci_core_mmap, .request = vfio_pci_core_request, .match = vfio_pci_core_match, + .match_token_uuid = vfio_pci_core_match_token_uuid, .bind_iommufd = vfio_iommufd_physical_bind, .unbind_iommufd = vfio_iommufd_physical_unbind, .attach_ioas = vfio_iommufd_physical_attach_ioas, diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c index e5ac39c4cc6b..d95761dcdd58 100644 --- a/drivers/vfio/pci/nvgrace-gpu/main.c +++ b/drivers/vfio/pci/nvgrace-gpu/main.c @@ -696,6 +696,7 @@ static const struct vfio_device_ops nvgrace_gpu_pci_ops = { .mmap = nvgrace_gpu_mmap, .request = vfio_pci_core_request, .match = vfio_pci_core_match, + .match_token_uuid = vfio_pci_core_match_token_uuid, .bind_iommufd = vfio_iommufd_physical_bind, .unbind_iommufd = vfio_iommufd_physical_unbind, .attach_ioas = vfio_iommufd_physical_attach_ioas, @@ -715,6 +716,7 @@ static const struct vfio_device_ops nvgrace_gpu_pci_core_ops = { .mmap = vfio_pci_core_mmap, .request = vfio_pci_core_request, .match = vfio_pci_core_match, + .match_token_uuid = vfio_pci_core_match_token_uuid, .bind_iommufd = vfio_iommufd_physical_bind, .unbind_iommufd = vfio_iommufd_physical_unbind, .attach_ioas = vfio_iommufd_physical_attach_ioas, diff --git a/drivers/vfio/pci/pds/vfio_dev.c b/drivers/vfio/pci/pds/vfio_dev.c index f6e0253a8a14..f3ccb0008f67 100644 --- a/drivers/vfio/pci/pds/vfio_dev.c +++ b/drivers/vfio/pci/pds/vfio_dev.c @@ -201,6 +201,7 @@ static const struct vfio_device_ops pds_vfio_ops = { .mmap = vfio_pci_core_mmap, .request = vfio_pci_core_request, .match = vfio_pci_core_match, + .match_token_uuid = vfio_pci_core_match_token_uuid, .bind_iommufd = vfio_iommufd_physical_bind, .unbind_iommufd = vfio_iommufd_physical_unbind, .attach_ioas = vfio_iommufd_physical_attach_ioas, diff --git a/drivers/vfio/pci/qat/main.c b/drivers/vfio/pci/qat/main.c index 845ed15b6771..5cce6b0b8d2f 100644 --- a/drivers/vfio/pci/qat/main.c +++ b/drivers/vfio/pci/qat/main.c @@ -614,6 +614,7 @@ static const struct vfio_device_ops qat_vf_pci_ops = { .mmap = vfio_pci_core_mmap, .request = vfio_pci_core_request, .match = vfio_pci_core_match, + .match_token_uuid = vfio_pci_core_match_token_uuid, .bind_iommufd = vfio_iommufd_physical_bind, .unbind_iommufd = vfio_iommufd_physical_unbind, .attach_ioas = vfio_iommufd_physical_attach_ioas, diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 5ba39f7623bb..ac10f14417f2 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -138,6 +138,7 @@ static const struct vfio_device_ops vfio_pci_ops = { .mmap = vfio_pci_core_mmap, .request = vfio_pci_core_request, .match = vfio_pci_core_match, + .match_token_uuid = vfio_pci_core_match_token_uuid, .bind_iommufd = vfio_iommufd_physical_bind, .unbind_iommufd = vfio_iommufd_physical_unbind, .attach_ioas = vfio_iommufd_physical_attach_ioas, diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 261a6dc5a5fc..fad410cf91bc 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -1821,9 +1821,13 @@ void vfio_pci_core_request(struct vfio_device *core_vdev, unsigned int count) } EXPORT_SYMBOL_GPL(vfio_pci_core_request); -static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, - bool vf_token, uuid_t *uuid) +int vfio_pci_core_match_token_uuid(struct vfio_device *core_vdev, + const uuid_t *uuid) + { + struct vfio_pci_core_device *vdev = + container_of(core_vdev, struct vfio_pci_core_device, vdev); + /* * There's always some degree of trust or collaboration between SR-IOV * PF and VFs, even if just that the PF hosts the SR-IOV capability and @@ -1854,7 +1858,7 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, bool match; if (!pf_vdev) { - if (!vf_token) + if (!uuid) return 0; /* PF is not vfio-pci, no VF token */ pci_info_ratelimited(vdev->pdev, @@ -1862,7 +1866,7 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, return -EINVAL; } - if (!vf_token) { + if (!uuid) { pci_info_ratelimited(vdev->pdev, "VF token required to access device\n"); return -EACCES; @@ -1880,7 +1884,7 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, } else if (vdev->vf_token) { mutex_lock(&vdev->vf_token->lock); if (vdev->vf_token->users) { - if (!vf_token) { + if (!uuid) { mutex_unlock(&vdev->vf_token->lock); pci_info_ratelimited(vdev->pdev, "VF token required to access device\n"); @@ -1893,12 +1897,12 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, "Incorrect VF token provided for device\n"); return -EACCES; } - } else if (vf_token) { + } else if (uuid) { uuid_copy(&vdev->vf_token->uuid, uuid); } mutex_unlock(&vdev->vf_token->lock); - } else if (vf_token) { + } else if (uuid) { pci_info_ratelimited(vdev->pdev, "VF token incorrectly provided, not a PF or VF\n"); return -EINVAL; @@ -1906,6 +1910,7 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, return 0; } +EXPORT_SYMBOL_GPL(vfio_pci_core_match_token_uuid); #define VF_TOKEN_ARG "vf_token=" @@ -1952,7 +1957,8 @@ int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf) } } - ret = vfio_pci_validate_vf_token(vdev, vf_token, &uuid); + ret = core_vdev->ops->match_token_uuid(core_vdev, + vf_token ? &uuid : NULL); if (ret) return ret; diff --git a/drivers/vfio/pci/virtio/main.c b/drivers/vfio/pci/virtio/main.c index 515fe1b9f94d..8084f3e36a9f 100644 --- a/drivers/vfio/pci/virtio/main.c +++ b/drivers/vfio/pci/virtio/main.c @@ -94,6 +94,7 @@ static const struct vfio_device_ops virtiovf_vfio_pci_lm_ops = { .mmap = vfio_pci_core_mmap, .request = vfio_pci_core_request, .match = vfio_pci_core_match, + .match_token_uuid = vfio_pci_core_match_token_uuid, .bind_iommufd = vfio_iommufd_physical_bind, .unbind_iommufd = vfio_iommufd_physical_unbind, .attach_ioas = vfio_iommufd_physical_attach_ioas, @@ -114,6 +115,7 @@ static const struct vfio_device_ops virtiovf_vfio_pci_tran_lm_ops = { .mmap = vfio_pci_core_mmap, .request = vfio_pci_core_request, .match = vfio_pci_core_match, + .match_token_uuid = vfio_pci_core_match_token_uuid, .bind_iommufd = vfio_iommufd_physical_bind, .unbind_iommufd = vfio_iommufd_physical_unbind, .attach_ioas = vfio_iommufd_physical_attach_ioas, @@ -134,6 +136,7 @@ static const struct vfio_device_ops virtiovf_vfio_pci_ops = { .mmap = vfio_pci_core_mmap, .request = vfio_pci_core_request, .match = vfio_pci_core_match, + .match_token_uuid = vfio_pci_core_match_token_uuid, .bind_iommufd = vfio_iommufd_physical_bind, .unbind_iommufd = vfio_iommufd_physical_unbind, .attach_ioas = vfio_iommufd_physical_attach_ioas, diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 707b00772ce1..eb563f538dee 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -105,6 +105,9 @@ struct vfio_device { * @match: Optional device name match callback (return: 0 for no-match, >0 for * match, -errno for abort (ex. match with insufficient or incorrect * additional args) + * @match_token_uuid: Optional device token match/validation. Return 0 + * if the uuid is valid for the device, -errno otherwise. uuid is NULL + * if none was provided. * @dma_unmap: Called when userspace unmaps IOVA from the container * this device is attached to. * @device_feature: Optional, fill in the VFIO_DEVICE_FEATURE ioctl @@ -132,6 +135,7 @@ struct vfio_device_ops { int (*mmap)(struct vfio_device *vdev, struct vm_area_struct *vma); void (*request)(struct vfio_device *vdev, unsigned int count); int (*match)(struct vfio_device *vdev, char *buf); + int (*match_token_uuid)(struct vfio_device *vdev, const uuid_t *uuid); void (*dma_unmap)(struct vfio_device *vdev, u64 iova, u64 length); int (*device_feature)(struct vfio_device *device, u32 flags, void __user *arg, size_t argsz); diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index fbb472dd99b3..f541044e42a2 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -122,6 +122,8 @@ ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *bu int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma); void vfio_pci_core_request(struct vfio_device *core_vdev, unsigned int count); int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf); +int vfio_pci_core_match_token_uuid(struct vfio_device *core_vdev, + const uuid_t *uuid); int vfio_pci_core_enable(struct vfio_pci_core_device *vdev); void vfio_pci_core_disable(struct vfio_pci_core_device *vdev); void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev); diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 5764f315137f..75100bf009ba 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -905,10 +905,12 @@ struct vfio_device_feature { * VFIO_DEVICE_BIND_IOMMUFD - _IOR(VFIO_TYPE, VFIO_BASE + 18, * struct vfio_device_bind_iommufd) * @argsz: User filled size of this data. - * @flags: Must be 0. + * @flags: Must be 0 or a bit flags of VFIO_DEVICE_BIND_* * @iommufd: iommufd to bind. * @out_devid: The device id generated by this bind. devid is a handle for * this device/iommufd bond and can be used in IOMMUFD commands. + * @token_uuid_ptr: Valid if VFIO_DEVICE_BIND_FLAG_TOKEN. Points to a 16 byte + * UUID in the same format as VFIO_DEVICE_FEATURE_PCI_VF_TOKEN. * * Bind a vfio_device to the specified iommufd. * @@ -917,13 +919,21 @@ struct vfio_device_feature { * * Unbind is automatically conducted when device fd is closed. * + * A token is sometimes required to open the device, unless this is known to be + * needed VFIO_DEVICE_BIND_FLAG_TOKEN should not be set and token_uuid_ptr is + * ignored. The only case today is a PF/VF relationship where the VF bind must + * be provided the same token as VFIO_DEVICE_FEATURE_PCI_VF_TOKEN provided to + * the PF. + * * Return: 0 on success, -errno on failure. */ struct vfio_device_bind_iommufd { __u32 argsz; __u32 flags; +#define VFIO_DEVICE_BIND_FLAG_TOKEN (1 << 0) __s32 iommufd; __u32 out_devid; + __aligned_u64 token_uuid_ptr; }; #define VFIO_DEVICE_BIND_IOMMUFD _IO(VFIO_TYPE, VFIO_BASE + 18) -- cgit v1.2.3 From 397a46c9aa3343e8efe6847bdaa124945bab1de4 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 25 Jul 2025 09:46:50 +0200 Subject: gpio: remove legacy GPIO line value setter callbacks With no more users of the legacy GPIO line value setters - .set() and .set_multiple() - we can now remove them from the kernel. Link: https://lore.kernel.org/r/20250725074651.14002-1-brgl@bgdev.pl Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpiolib.c | 27 ++++++--------------------- include/linux/gpio/driver.h | 7 ------- 2 files changed, 6 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index a93d2a9355e2..9ac4c23d656a 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1037,11 +1037,6 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, int base = 0; int ret; - /* Only allow one set() and one set_multiple(). */ - if ((gc->set && gc->set_rv) || - (gc->set_multiple && gc->set_multiple_rv)) - return -EINVAL; - /* * First: allocate and populate the internal stat container, and * set up the struct device. @@ -2891,19 +2886,14 @@ static int gpiochip_set(struct gpio_chip *gc, unsigned int offset, int value) lockdep_assert_held(&gc->gpiodev->srcu); - if (WARN_ON(unlikely(!gc->set && !gc->set_rv))) + if (WARN_ON(unlikely(!gc->set_rv))) return -EOPNOTSUPP; - if (gc->set_rv) { - ret = gc->set_rv(gc, offset, value); - if (ret > 0) - ret = -EBADE; - - return ret; - } + ret = gc->set_rv(gc, offset, value); + if (ret > 0) + ret = -EBADE; - gc->set(gc, offset, value); - return 0; + return ret; } static int gpiod_direction_output_raw_commit(struct gpio_desc *desc, int value) @@ -2919,7 +2909,7 @@ static int gpiod_direction_output_raw_commit(struct gpio_desc *desc, int value) * output-only, but if there is then not even a .set() operation it * is pretty tricky to drive the output line. */ - if (!guard.gc->set && !guard.gc->set_rv && !guard.gc->direction_output) { + if (!guard.gc->set_rv && !guard.gc->direction_output) { gpiod_warn(desc, "%s: missing set() and direction_output() operations\n", __func__); @@ -3673,11 +3663,6 @@ static int gpiochip_set_multiple(struct gpio_chip *gc, return ret; } - if (gc->set_multiple) { - gc->set_multiple(gc, mask, bits); - return 0; - } - /* set outputs if the corresponding mask bit is set */ for_each_set_bit(i, mask, gc->ngpio) { ret = gpiochip_set(gc, i, test_bit(i, bits)); diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 4b984e8f8fcd..90567dde7d8e 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -347,8 +347,6 @@ struct gpio_irq_chip { * @get: returns value for signal "offset", 0=low, 1=high, or negative error * @get_multiple: reads values for multiple signals defined by "mask" and * stores them in "bits", returns 0 on success or negative error - * @set: **DEPRECATED** - please use set_rv() instead - * @set_multiple: **DEPRECATED** - please use set_multiple_rv() instead * @set_rv: assigns output value for signal "offset", returns 0 on success or * negative error value * @set_multiple_rv: assigns output values for multiple signals defined by @@ -445,11 +443,6 @@ struct gpio_chip { int (*get_multiple)(struct gpio_chip *gc, unsigned long *mask, unsigned long *bits); - void (*set)(struct gpio_chip *gc, - unsigned int offset, int value); - void (*set_multiple)(struct gpio_chip *gc, - unsigned long *mask, - unsigned long *bits); int (*set_rv)(struct gpio_chip *gc, unsigned int offset, int value); -- cgit v1.2.3 From d9d87d90cc0b10cd56ae353f50b11417e7d21712 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Thu, 17 Jul 2025 15:21:26 +0200 Subject: treewide: rename GPIO set callbacks back to their original names The conversion of all GPIO drivers to using the .set_rv() and .set_multiple_rv() callbacks from struct gpio_chip (which - unlike their predecessors - return an integer and allow the controller drivers to indicate failures to users) is now complete and the legacy ones have been removed. Rename the new callbacks back to their original names in one sweeping change. Signed-off-by: Bartosz Golaszewski --- arch/arm/common/sa1111.c | 4 ++-- arch/arm/common/scoop.c | 2 +- arch/arm/mach-s3c/gpio-samsung.c | 2 +- arch/arm/mach-sa1100/assabet.c | 2 +- arch/arm/mach-sa1100/neponset.c | 2 +- arch/arm/plat-orion/gpio.c | 2 +- arch/m68k/coldfire/gpio.c | 2 +- arch/mips/alchemy/common/gpiolib.c | 6 +++--- arch/mips/bcm63xx/gpio.c | 2 +- arch/mips/kernel/gpio_txx9.c | 2 +- arch/mips/rb532/gpio.c | 2 +- arch/mips/txx9/generic/setup.c | 2 +- arch/powerpc/platforms/44x/gpio.c | 2 +- arch/powerpc/platforms/52xx/mpc52xx_gpt.c | 2 +- arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c | 2 +- arch/powerpc/platforms/8xx/cpm1.c | 4 ++-- arch/powerpc/sysdev/cpm_common.c | 2 +- drivers/bcma/driver_gpio.c | 2 +- drivers/gpio/gpio-74x164.c | 4 ++-- drivers/gpio/gpio-adnp.c | 2 +- drivers/gpio/gpio-adp5520.c | 2 +- drivers/gpio/gpio-adp5585.c | 2 +- drivers/gpio/gpio-aggregator.c | 4 ++-- drivers/gpio/gpio-altera-a10sr.c | 2 +- drivers/gpio/gpio-altera.c | 2 +- drivers/gpio/gpio-amd-fch.c | 2 +- drivers/gpio/gpio-amd8111.c | 2 +- drivers/gpio/gpio-arizona.c | 2 +- drivers/gpio/gpio-aspeed-sgpio.c | 2 +- drivers/gpio/gpio-aspeed.c | 2 +- drivers/gpio/gpio-bcm-kona.c | 2 +- drivers/gpio/gpio-bd71815.c | 2 +- drivers/gpio/gpio-bd71828.c | 2 +- drivers/gpio/gpio-bd9571mwv.c | 2 +- drivers/gpio/gpio-bt8xx.c | 2 +- drivers/gpio/gpio-cgbc.c | 2 +- drivers/gpio/gpio-creg-snps.c | 2 +- drivers/gpio/gpio-cros-ec.c | 2 +- drivers/gpio/gpio-crystalcove.c | 2 +- drivers/gpio/gpio-cs5535.c | 2 +- drivers/gpio/gpio-da9052.c | 2 +- drivers/gpio/gpio-da9055.c | 2 +- drivers/gpio/gpio-davinci.c | 2 +- drivers/gpio/gpio-dln2.c | 2 +- drivers/gpio/gpio-eic-sprd.c | 2 +- drivers/gpio/gpio-em.c | 2 +- drivers/gpio/gpio-exar.c | 2 +- drivers/gpio/gpio-f7188x.c | 2 +- drivers/gpio/gpio-graniterapids.c | 2 +- drivers/gpio/gpio-gw-pld.c | 2 +- drivers/gpio/gpio-htc-egpio.c | 2 +- drivers/gpio/gpio-ich.c | 2 +- drivers/gpio/gpio-imx-scu.c | 2 +- drivers/gpio/gpio-it87.c | 2 +- drivers/gpio/gpio-janz-ttl.c | 2 +- drivers/gpio/gpio-kempld.c | 2 +- drivers/gpio/gpio-latch.c | 4 ++-- drivers/gpio/gpio-ljca.c | 2 +- drivers/gpio/gpio-logicvc.c | 2 +- drivers/gpio/gpio-loongson-64bit.c | 2 +- drivers/gpio/gpio-loongson.c | 2 +- drivers/gpio/gpio-lp3943.c | 2 +- drivers/gpio/gpio-lp873x.c | 2 +- drivers/gpio/gpio-lp87565.c | 2 +- drivers/gpio/gpio-lpc18xx.c | 2 +- drivers/gpio/gpio-lpc32xx.c | 10 ++++----- drivers/gpio/gpio-macsmc.c | 2 +- drivers/gpio/gpio-madera.c | 2 +- drivers/gpio/gpio-max730x.c | 2 +- drivers/gpio/gpio-max732x.c | 4 ++-- drivers/gpio/gpio-max77620.c | 2 +- drivers/gpio/gpio-max77650.c | 2 +- drivers/gpio/gpio-max77759.c | 2 +- drivers/gpio/gpio-mb86s7x.c | 2 +- drivers/gpio/gpio-mc33880.c | 2 +- drivers/gpio/gpio-ml-ioh.c | 2 +- drivers/gpio/gpio-mm-lantiq.c | 2 +- drivers/gpio/gpio-mmio.c | 24 +++++++++++----------- drivers/gpio/gpio-mockup.c | 4 ++-- drivers/gpio/gpio-moxtet.c | 2 +- drivers/gpio/gpio-mpc5200.c | 4 ++-- drivers/gpio/gpio-mpfs.c | 2 +- drivers/gpio/gpio-mpsse.c | 4 ++-- drivers/gpio/gpio-msc313.c | 2 +- drivers/gpio/gpio-mvebu.c | 2 +- drivers/gpio/gpio-nomadik.c | 2 +- drivers/gpio/gpio-npcm-sgpio.c | 4 ++-- drivers/gpio/gpio-octeon.c | 2 +- drivers/gpio/gpio-omap.c | 4 ++-- drivers/gpio/gpio-palmas.c | 2 +- drivers/gpio/gpio-pca953x.c | 4 ++-- drivers/gpio/gpio-pca9570.c | 2 +- drivers/gpio/gpio-pcf857x.c | 4 ++-- drivers/gpio/gpio-pch.c | 2 +- drivers/gpio/gpio-pl061.c | 2 +- drivers/gpio/gpio-pxa.c | 2 +- drivers/gpio/gpio-raspberrypi-exp.c | 2 +- drivers/gpio/gpio-rc5t583.c | 2 +- drivers/gpio/gpio-rcar.c | 4 ++-- drivers/gpio/gpio-rdc321x.c | 2 +- drivers/gpio/gpio-reg.c | 6 +++--- drivers/gpio/gpio-regmap.c | 4 ++-- drivers/gpio/gpio-rockchip.c | 2 +- drivers/gpio/gpio-rtd.c | 2 +- drivers/gpio/gpio-sa1100.c | 2 +- drivers/gpio/gpio-sama5d2-piobu.c | 2 +- drivers/gpio/gpio-sch.c | 2 +- drivers/gpio/gpio-sch311x.c | 2 +- drivers/gpio/gpio-sim.c | 4 ++-- drivers/gpio/gpio-siox.c | 2 +- drivers/gpio/gpio-spear-spics.c | 2 +- drivers/gpio/gpio-sprd.c | 2 +- drivers/gpio/gpio-stmpe.c | 2 +- drivers/gpio/gpio-stp-xway.c | 2 +- drivers/gpio/gpio-syscon.c | 4 ++-- drivers/gpio/gpio-tangier.c | 2 +- drivers/gpio/gpio-tc3589x.c | 2 +- drivers/gpio/gpio-tegra.c | 2 +- drivers/gpio/gpio-tegra186.c | 2 +- drivers/gpio/gpio-thunderx.c | 4 ++-- drivers/gpio/gpio-timberdale.c | 2 +- drivers/gpio/gpio-tpic2810.c | 4 ++-- drivers/gpio/gpio-tps65086.c | 2 +- drivers/gpio/gpio-tps65218.c | 2 +- drivers/gpio/gpio-tps65219.c | 4 ++-- drivers/gpio/gpio-tps6586x.c | 2 +- drivers/gpio/gpio-tps65910.c | 2 +- drivers/gpio/gpio-tps65912.c | 2 +- drivers/gpio/gpio-tps68470.c | 2 +- drivers/gpio/gpio-tqmx86.c | 2 +- drivers/gpio/gpio-ts4900.c | 2 +- drivers/gpio/gpio-ts5500.c | 2 +- drivers/gpio/gpio-twl4030.c | 2 +- drivers/gpio/gpio-twl6040.c | 2 +- drivers/gpio/gpio-uniphier.c | 4 ++-- drivers/gpio/gpio-viperboard.c | 4 ++-- drivers/gpio/gpio-virtio.c | 2 +- drivers/gpio/gpio-vx855.c | 2 +- drivers/gpio/gpio-wcd934x.c | 2 +- drivers/gpio/gpio-wcove.c | 2 +- drivers/gpio/gpio-winbond.c | 2 +- drivers/gpio/gpio-wm831x.c | 2 +- drivers/gpio/gpio-wm8350.c | 2 +- drivers/gpio/gpio-wm8994.c | 2 +- drivers/gpio/gpio-xgene.c | 2 +- drivers/gpio/gpio-xilinx.c | 4 ++-- drivers/gpio/gpio-xlp.c | 2 +- drivers/gpio/gpio-xra1403.c | 2 +- drivers/gpio/gpio-xtensa.c | 2 +- drivers/gpio/gpio-zevio.c | 2 +- drivers/gpio/gpio-zynq.c | 2 +- drivers/gpio/gpio-zynqmp-modepin.c | 2 +- drivers/gpio/gpiolib.c | 10 ++++----- drivers/gpu/drm/bridge/ti-sn65dsi86.c | 2 +- drivers/hid/hid-cp2112.c | 2 +- drivers/hid/hid-mcp2200.c | 4 ++-- drivers/hid/hid-mcp2221.c | 2 +- drivers/hwmon/ltc2992.c | 4 ++-- drivers/hwmon/pmbus/ucd9000.c | 2 +- drivers/i2c/muxes/i2c-mux-ltc4306.c | 2 +- drivers/iio/adc/ad4130.c | 2 +- drivers/iio/adc/ad4170-4.c | 2 +- drivers/iio/adc/ad7768-1.c | 2 +- drivers/iio/adc/rohm-bd79124.c | 4 ++-- drivers/iio/adc/ti-ads7950.c | 2 +- drivers/iio/addac/ad74115.c | 2 +- drivers/iio/addac/ad74413r.c | 4 ++-- drivers/iio/dac/ad5592r-base.c | 2 +- drivers/input/keyboard/adp5588-keys.c | 2 +- drivers/input/touchscreen/ad7879.c | 2 +- drivers/leds/blink/leds-lgm-sso.c | 2 +- drivers/leds/leds-pca9532.c | 2 +- drivers/leds/leds-pca955x.c | 2 +- drivers/leds/leds-tca6507.c | 2 +- drivers/media/dvb-frontends/cxd2820r_core.c | 2 +- drivers/media/i2c/ds90ub913.c | 2 +- drivers/media/i2c/ds90ub953.c | 2 +- drivers/media/i2c/max9286.c | 2 +- drivers/media/i2c/max96717.c | 2 +- drivers/media/pci/solo6x10/solo6x10-gpio.c | 2 +- drivers/mfd/sm501.c | 2 +- drivers/mfd/tps65010.c | 2 +- drivers/mfd/ucb1x00-core.c | 2 +- drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c | 2 +- drivers/misc/ti_fpc202.c | 2 +- drivers/net/can/spi/mcp251x.c | 4 ++-- drivers/net/dsa/mt7530.c | 2 +- drivers/net/dsa/vitesse-vsc73xx-core.c | 2 +- drivers/net/phy/qcom/qca807x.c | 2 +- drivers/pinctrl/actions/pinctrl-owl.c | 2 +- drivers/pinctrl/bcm/pinctrl-bcm2835.c | 4 ++-- drivers/pinctrl/bcm/pinctrl-iproc-gpio.c | 2 +- drivers/pinctrl/bcm/pinctrl-nsp-gpio.c | 2 +- drivers/pinctrl/cirrus/pinctrl-cs42l43.c | 2 +- drivers/pinctrl/cirrus/pinctrl-lochnagar.c | 2 +- drivers/pinctrl/intel/pinctrl-baytrail.c | 2 +- drivers/pinctrl/intel/pinctrl-cherryview.c | 2 +- drivers/pinctrl/intel/pinctrl-intel.c | 2 +- drivers/pinctrl/intel/pinctrl-lynxpoint.c | 2 +- drivers/pinctrl/mediatek/pinctrl-airoha.c | 2 +- drivers/pinctrl/mediatek/pinctrl-moore.c | 2 +- drivers/pinctrl/mediatek/pinctrl-mtk-common.c | 2 +- drivers/pinctrl/mediatek/pinctrl-paris.c | 2 +- drivers/pinctrl/meson/pinctrl-amlogic-a4.c | 2 +- drivers/pinctrl/meson/pinctrl-meson.c | 2 +- drivers/pinctrl/mvebu/pinctrl-armada-37xx.c | 2 +- drivers/pinctrl/nomadik/pinctrl-abx500.c | 2 +- drivers/pinctrl/nuvoton/pinctrl-ma35.c | 2 +- drivers/pinctrl/pinctrl-amd.c | 2 +- drivers/pinctrl/pinctrl-amdisp.c | 2 +- drivers/pinctrl/pinctrl-apple-gpio.c | 2 +- drivers/pinctrl/pinctrl-as3722.c | 2 +- drivers/pinctrl/pinctrl-at91-pio4.c | 4 ++-- drivers/pinctrl/pinctrl-at91.c | 4 ++-- drivers/pinctrl/pinctrl-aw9523.c | 4 ++-- drivers/pinctrl/pinctrl-axp209.c | 4 ++-- drivers/pinctrl/pinctrl-cy8c95x0.c | 4 ++-- drivers/pinctrl/pinctrl-da9062.c | 2 +- drivers/pinctrl/pinctrl-digicolor.c | 2 +- drivers/pinctrl/pinctrl-ingenic.c | 2 +- drivers/pinctrl/pinctrl-keembay.c | 2 +- drivers/pinctrl/pinctrl-mcp23s08.c | 4 ++-- drivers/pinctrl/pinctrl-microchip-sgpio.c | 2 +- drivers/pinctrl/pinctrl-ocelot.c | 2 +- drivers/pinctrl/pinctrl-pic32.c | 2 +- drivers/pinctrl/pinctrl-pistachio.c | 2 +- drivers/pinctrl/pinctrl-rk805.c | 2 +- drivers/pinctrl/pinctrl-rp1.c | 2 +- drivers/pinctrl/pinctrl-st.c | 2 +- drivers/pinctrl/pinctrl-stmfx.c | 2 +- drivers/pinctrl/pinctrl-sx150x.c | 4 ++-- drivers/pinctrl/pinctrl-xway.c | 2 +- drivers/pinctrl/qcom/pinctrl-lpass-lpi.c | 2 +- drivers/pinctrl/qcom/pinctrl-msm.c | 2 +- drivers/pinctrl/qcom/pinctrl-spmi-gpio.c | 2 +- drivers/pinctrl/qcom/pinctrl-spmi-mpp.c | 2 +- drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c | 2 +- drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c | 2 +- drivers/pinctrl/renesas/gpio.c | 2 +- drivers/pinctrl/renesas/pinctrl-rza1.c | 2 +- drivers/pinctrl/renesas/pinctrl-rza2.c | 2 +- drivers/pinctrl/renesas/pinctrl-rzg2l.c | 2 +- drivers/pinctrl/renesas/pinctrl-rzv2m.c | 2 +- drivers/pinctrl/samsung/pinctrl-samsung.c | 2 +- drivers/pinctrl/spear/pinctrl-plgpio.c | 2 +- drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c | 2 +- drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c | 2 +- drivers/pinctrl/stm32/pinctrl-stm32.c | 2 +- drivers/pinctrl/sunplus/sppctl.c | 2 +- drivers/pinctrl/sunxi/pinctrl-sunxi.c | 2 +- drivers/pinctrl/vt8500/pinctrl-wmt.c | 2 +- drivers/platform/cznic/turris-omnia-mcu-gpio.c | 4 ++-- drivers/platform/x86/barco-p50-gpio.c | 2 +- drivers/platform/x86/intel/int0002_vgpio.c | 2 +- drivers/platform/x86/portwell-ec.c | 4 ++-- drivers/platform/x86/silicom-platform.c | 2 +- drivers/pwm/pwm-pca9685.c | 2 +- drivers/regulator/rpi-panel-attiny-regulator.c | 2 +- drivers/soc/fsl/qe/gpio.c | 4 ++-- drivers/soc/renesas/pwc-rzv2m.c | 2 +- drivers/spi/spi-xcomm.c | 2 +- drivers/ssb/driver_gpio.c | 4 ++-- drivers/staging/greybus/gpio.c | 2 +- drivers/tty/serial/max310x.c | 2 +- drivers/tty/serial/sc16is7xx.c | 2 +- drivers/usb/serial/cp210x.c | 2 +- drivers/usb/serial/ftdi_sio.c | 4 ++-- drivers/video/fbdev/via/via-gpio.c | 2 +- include/linux/gpio/driver.h | 19 ++++++++--------- include/linux/gpio/generic.h | 4 ++-- sound/hda/codecs/side-codecs/cirrus_scodec_test.c | 2 +- sound/soc/codecs/idt821034.c | 2 +- sound/soc/codecs/peb2466.c | 2 +- sound/soc/codecs/rt5677.c | 2 +- sound/soc/codecs/tlv320adc3xxx.c | 2 +- sound/soc/codecs/wm5100.c | 2 +- sound/soc/codecs/wm8903.c | 2 +- sound/soc/codecs/wm8962.c | 2 +- sound/soc/codecs/wm8996.c | 2 +- sound/soc/codecs/zl38060.c | 2 +- sound/soc/soc-ac97.c | 2 +- sound/soc/ti/davinci-mcasp.c | 2 +- 282 files changed, 355 insertions(+), 356 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c index d7e2ea27ce59..3389a70e4d49 100644 --- a/arch/arm/common/sa1111.c +++ b/arch/arm/common/sa1111.c @@ -617,8 +617,8 @@ static int sa1111_setup_gpios(struct sa1111 *sachip) sachip->gc.direction_input = sa1111_gpio_direction_input; sachip->gc.direction_output = sa1111_gpio_direction_output; sachip->gc.get = sa1111_gpio_get; - sachip->gc.set_rv = sa1111_gpio_set; - sachip->gc.set_multiple_rv = sa1111_gpio_set_multiple; + sachip->gc.set = sa1111_gpio_set; + sachip->gc.set_multiple = sa1111_gpio_set_multiple; sachip->gc.to_irq = sa1111_gpio_to_irq; sachip->gc.base = -1; sachip->gc.ngpio = 18; diff --git a/arch/arm/common/scoop.c b/arch/arm/common/scoop.c index 2d3ee76c8e17..dddb73c96826 100644 --- a/arch/arm/common/scoop.c +++ b/arch/arm/common/scoop.c @@ -218,7 +218,7 @@ static int scoop_probe(struct platform_device *pdev) devptr->gpio.label = dev_name(&pdev->dev); devptr->gpio.base = inf->gpio_base; devptr->gpio.ngpio = 12; /* PA11 = 0, PA12 = 1, etc. up to PA22 = 11 */ - devptr->gpio.set_rv = scoop_gpio_set; + devptr->gpio.set = scoop_gpio_set; devptr->gpio.get = scoop_gpio_get; devptr->gpio.direction_input = scoop_gpio_direction_input; devptr->gpio.direction_output = scoop_gpio_direction_output; diff --git a/arch/arm/mach-s3c/gpio-samsung.c b/arch/arm/mach-s3c/gpio-samsung.c index 206a492fbaf5..81e198e5a6d3 100644 --- a/arch/arm/mach-s3c/gpio-samsung.c +++ b/arch/arm/mach-s3c/gpio-samsung.c @@ -517,7 +517,7 @@ static void __init samsung_gpiolib_add(struct samsung_gpio_chip *chip) if (!gc->direction_output) gc->direction_output = samsung_gpiolib_2bit_output; if (!gc->set) - gc->set_rv = samsung_gpiolib_set; + gc->set = samsung_gpiolib_set; if (!gc->get) gc->get = samsung_gpiolib_get; diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c index bad8aa661e9d..2b833aa0212b 100644 --- a/arch/arm/mach-sa1100/assabet.c +++ b/arch/arm/mach-sa1100/assabet.c @@ -80,7 +80,7 @@ void ASSABET_BCR_frob(unsigned int mask, unsigned int val) { unsigned long m = mask, v = val; - assabet_bcr_gc->set_multiple_rv(assabet_bcr_gc, &m, &v); + assabet_bcr_gc->set_multiple(assabet_bcr_gc, &m, &v); } EXPORT_SYMBOL(ASSABET_BCR_frob); diff --git a/arch/arm/mach-sa1100/neponset.c b/arch/arm/mach-sa1100/neponset.c index 6516598c8a71..88fe79f0a4ed 100644 --- a/arch/arm/mach-sa1100/neponset.c +++ b/arch/arm/mach-sa1100/neponset.c @@ -126,7 +126,7 @@ void neponset_ncr_frob(unsigned int mask, unsigned int val) unsigned long m = mask, v = val; if (nep) - n->gpio[0]->set_multiple_rv(n->gpio[0], &m, &v); + n->gpio[0]->set_multiple(n->gpio[0], &m, &v); else WARN(1, "nep unset\n"); } diff --git a/arch/arm/plat-orion/gpio.c b/arch/arm/plat-orion/gpio.c index 6f09f65e3d95..49e29b7894a3 100644 --- a/arch/arm/plat-orion/gpio.c +++ b/arch/arm/plat-orion/gpio.c @@ -540,7 +540,7 @@ void __init orion_gpio_init(int gpio_base, int ngpio, ochip->chip.direction_input = orion_gpio_direction_input; ochip->chip.get = orion_gpio_get; ochip->chip.direction_output = orion_gpio_direction_output; - ochip->chip.set_rv = orion_gpio_set; + ochip->chip.set = orion_gpio_set; ochip->chip.to_irq = orion_gpio_to_irq; ochip->chip.base = gpio_base; ochip->chip.ngpio = ngpio; diff --git a/arch/m68k/coldfire/gpio.c b/arch/m68k/coldfire/gpio.c index 30e5a4ed799d..e2f7af1facb2 100644 --- a/arch/m68k/coldfire/gpio.c +++ b/arch/m68k/coldfire/gpio.c @@ -160,7 +160,7 @@ static struct gpio_chip mcfgpio_chip = { .direction_input = mcfgpio_direction_input, .direction_output = mcfgpio_direction_output, .get = mcfgpio_get_value, - .set_rv = mcfgpio_set_value, + .set = mcfgpio_set_value, .to_irq = mcfgpio_to_irq, .base = 0, .ngpio = MCFGPIO_PIN_MAX, diff --git a/arch/mips/alchemy/common/gpiolib.c b/arch/mips/alchemy/common/gpiolib.c index 194034eba75f..e79e26ffac99 100644 --- a/arch/mips/alchemy/common/gpiolib.c +++ b/arch/mips/alchemy/common/gpiolib.c @@ -101,7 +101,7 @@ struct gpio_chip alchemy_gpio_chip[] = { .direction_input = gpio1_direction_input, .direction_output = gpio1_direction_output, .get = gpio1_get, - .set_rv = gpio1_set, + .set = gpio1_set, .to_irq = gpio1_to_irq, .base = ALCHEMY_GPIO1_BASE, .ngpio = ALCHEMY_GPIO1_NUM, @@ -111,7 +111,7 @@ struct gpio_chip alchemy_gpio_chip[] = { .direction_input = gpio2_direction_input, .direction_output = gpio2_direction_output, .get = gpio2_get, - .set_rv = gpio2_set, + .set = gpio2_set, .to_irq = gpio2_to_irq, .base = ALCHEMY_GPIO2_BASE, .ngpio = ALCHEMY_GPIO2_NUM, @@ -151,7 +151,7 @@ static struct gpio_chip au1300_gpiochip = { .direction_input = alchemy_gpic_dir_input, .direction_output = alchemy_gpic_dir_output, .get = alchemy_gpic_get, - .set_rv = alchemy_gpic_set, + .set = alchemy_gpic_set, .to_irq = alchemy_gpic_gpio_to_irq, .base = AU1300_GPIO_BASE, .ngpio = AU1300_GPIO_NUM, diff --git a/arch/mips/bcm63xx/gpio.c b/arch/mips/bcm63xx/gpio.c index e7a53cd0dec5..ff45a6989c3a 100644 --- a/arch/mips/bcm63xx/gpio.c +++ b/arch/mips/bcm63xx/gpio.c @@ -131,7 +131,7 @@ static struct gpio_chip bcm63xx_gpio_chip = { .direction_input = bcm63xx_gpio_direction_input, .direction_output = bcm63xx_gpio_direction_output, .get = bcm63xx_gpio_get, - .set_rv = bcm63xx_gpio_set, + .set = bcm63xx_gpio_set, .base = 0, }; diff --git a/arch/mips/kernel/gpio_txx9.c b/arch/mips/kernel/gpio_txx9.c index 027fb57d0d79..96ac40d20c23 100644 --- a/arch/mips/kernel/gpio_txx9.c +++ b/arch/mips/kernel/gpio_txx9.c @@ -70,7 +70,7 @@ static int txx9_gpio_dir_out(struct gpio_chip *chip, unsigned int offset, static struct gpio_chip txx9_gpio_chip = { .get = txx9_gpio_get, - .set_rv = txx9_gpio_set, + .set = txx9_gpio_set, .direction_input = txx9_gpio_dir_in, .direction_output = txx9_gpio_dir_out, .label = "TXx9", diff --git a/arch/mips/rb532/gpio.c b/arch/mips/rb532/gpio.c index 0e47cd59b6cb..9aa5ef374465 100644 --- a/arch/mips/rb532/gpio.c +++ b/arch/mips/rb532/gpio.c @@ -164,7 +164,7 @@ static struct rb532_gpio_chip rb532_gpio_chip[] = { .direction_input = rb532_gpio_direction_input, .direction_output = rb532_gpio_direction_output, .get = rb532_gpio_get, - .set_rv = rb532_gpio_set, + .set = rb532_gpio_set, .to_irq = rb532_gpio_to_irq, .base = 0, .ngpio = 32, diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c index 5a37e8b234a3..5dc867ea2c69 100644 --- a/arch/mips/txx9/generic/setup.c +++ b/arch/mips/txx9/generic/setup.c @@ -655,7 +655,7 @@ void __init txx9_iocled_init(unsigned long baseaddr, if (!iocled->mmioaddr) goto out_free; iocled->chip.get = txx9_iocled_get; - iocled->chip.set_rv = txx9_iocled_set; + iocled->chip.set = txx9_iocled_set; iocled->chip.direction_input = txx9_iocled_dir_in; iocled->chip.direction_output = txx9_iocled_dir_out; iocled->chip.label = "iocled"; diff --git a/arch/powerpc/platforms/44x/gpio.c b/arch/powerpc/platforms/44x/gpio.c index d540e261d85a..08ab76582568 100644 --- a/arch/powerpc/platforms/44x/gpio.c +++ b/arch/powerpc/platforms/44x/gpio.c @@ -180,7 +180,7 @@ static int __init ppc4xx_add_gpiochips(void) gc->direction_input = ppc4xx_gpio_dir_in; gc->direction_output = ppc4xx_gpio_dir_out; gc->get = ppc4xx_gpio_get; - gc->set_rv = ppc4xx_gpio_set; + gc->set = ppc4xx_gpio_set; ret = of_mm_gpiochip_add_data(np, mm_gc, ppc4xx_gc); if (ret) diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c index bda707d848a6..7748b6641a3c 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c @@ -336,7 +336,7 @@ static void mpc52xx_gpt_gpio_setup(struct mpc52xx_gpt_priv *gpt) gpt->gc.direction_input = mpc52xx_gpt_gpio_dir_in; gpt->gc.direction_output = mpc52xx_gpt_gpio_dir_out; gpt->gc.get = mpc52xx_gpt_gpio_get; - gpt->gc.set_rv = mpc52xx_gpt_gpio_set; + gpt->gc.set = mpc52xx_gpt_gpio_set; gpt->gc.base = -1; gpt->gc.parent = gpt->dev; diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c index 6e37dfc6c5c9..cb7b9498f291 100644 --- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c +++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c @@ -126,7 +126,7 @@ static int mcu_gpiochip_add(struct mcu *mcu) gc->can_sleep = 1; gc->ngpio = MCU_NUM_GPIO; gc->base = -1; - gc->set_rv = mcu_gpio_set; + gc->set = mcu_gpio_set; gc->direction_output = mcu_gpio_dir_out; gc->parent = dev; diff --git a/arch/powerpc/platforms/8xx/cpm1.c b/arch/powerpc/platforms/8xx/cpm1.c index 7462c221115c..7433be7d66ee 100644 --- a/arch/powerpc/platforms/8xx/cpm1.c +++ b/arch/powerpc/platforms/8xx/cpm1.c @@ -499,7 +499,7 @@ int cpm1_gpiochip_add16(struct device *dev) gc->direction_input = cpm1_gpio16_dir_in; gc->direction_output = cpm1_gpio16_dir_out; gc->get = cpm1_gpio16_get; - gc->set_rv = cpm1_gpio16_set; + gc->set = cpm1_gpio16_set; gc->to_irq = cpm1_gpio16_to_irq; gc->parent = dev; gc->owner = THIS_MODULE; @@ -622,7 +622,7 @@ int cpm1_gpiochip_add32(struct device *dev) gc->direction_input = cpm1_gpio32_dir_in; gc->direction_output = cpm1_gpio32_dir_out; gc->get = cpm1_gpio32_get; - gc->set_rv = cpm1_gpio32_set; + gc->set = cpm1_gpio32_set; gc->parent = dev; gc->owner = THIS_MODULE; diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c index e22fc638dbc7..f469f6a9f6e0 100644 --- a/arch/powerpc/sysdev/cpm_common.c +++ b/arch/powerpc/sysdev/cpm_common.c @@ -210,7 +210,7 @@ int cpm2_gpiochip_add32(struct device *dev) gc->direction_input = cpm2_gpio32_dir_in; gc->direction_output = cpm2_gpio32_dir_out; gc->get = cpm2_gpio32_get; - gc->set_rv = cpm2_gpio32_set; + gc->set = cpm2_gpio32_set; gc->parent = dev; gc->owner = THIS_MODULE; diff --git a/drivers/bcma/driver_gpio.c b/drivers/bcma/driver_gpio.c index f021e27644e0..658c7e2ac8bf 100644 --- a/drivers/bcma/driver_gpio.c +++ b/drivers/bcma/driver_gpio.c @@ -186,7 +186,7 @@ int bcma_gpio_init(struct bcma_drv_cc *cc) chip->request = bcma_gpio_request; chip->free = bcma_gpio_free; chip->get = bcma_gpio_get_value; - chip->set_rv = bcma_gpio_set_value; + chip->set = bcma_gpio_set_value; chip->direction_input = bcma_gpio_direction_input; chip->direction_output = bcma_gpio_direction_output; chip->parent = bus->dev; diff --git a/drivers/gpio/gpio-74x164.c b/drivers/gpio/gpio-74x164.c index 4dd5c2c330bb..c226524efeba 100644 --- a/drivers/gpio/gpio-74x164.c +++ b/drivers/gpio/gpio-74x164.c @@ -141,8 +141,8 @@ static int gen_74x164_probe(struct spi_device *spi) chip->gpio_chip.label = spi->modalias; chip->gpio_chip.direction_output = gen_74x164_direction_output; chip->gpio_chip.get = gen_74x164_get_value; - chip->gpio_chip.set_rv = gen_74x164_set_value; - chip->gpio_chip.set_multiple_rv = gen_74x164_set_multiple; + chip->gpio_chip.set = gen_74x164_set_value; + chip->gpio_chip.set_multiple = gen_74x164_set_multiple; chip->gpio_chip.base = -1; chip->gpio_chip.ngpio = GEN_74X164_NUMBER_GPIOS * chip->registers; chip->gpio_chip.can_sleep = true; diff --git a/drivers/gpio/gpio-adnp.c b/drivers/gpio/gpio-adnp.c index dc2b941c3726..e5ac2d211013 100644 --- a/drivers/gpio/gpio-adnp.c +++ b/drivers/gpio/gpio-adnp.c @@ -430,7 +430,7 @@ static int adnp_gpio_setup(struct adnp *adnp, unsigned int num_gpios, chip->direction_input = adnp_gpio_direction_input; chip->direction_output = adnp_gpio_direction_output; chip->get = adnp_gpio_get; - chip->set_rv = adnp_gpio_set; + chip->set = adnp_gpio_set; chip->can_sleep = true; if (IS_ENABLED(CONFIG_DEBUG_FS)) diff --git a/drivers/gpio/gpio-adp5520.c b/drivers/gpio/gpio-adp5520.c index 57d12c10cbda..6305c8b7dc05 100644 --- a/drivers/gpio/gpio-adp5520.c +++ b/drivers/gpio/gpio-adp5520.c @@ -122,7 +122,7 @@ static int adp5520_gpio_probe(struct platform_device *pdev) gc->direction_input = adp5520_gpio_direction_input; gc->direction_output = adp5520_gpio_direction_output; gc->get = adp5520_gpio_get_value; - gc->set_rv = adp5520_gpio_set_value; + gc->set = adp5520_gpio_set_value; gc->can_sleep = true; gc->base = pdata->gpio_start; diff --git a/drivers/gpio/gpio-adp5585.c b/drivers/gpio/gpio-adp5585.c index b2c8836c5f84..0fd3cc26d017 100644 --- a/drivers/gpio/gpio-adp5585.c +++ b/drivers/gpio/gpio-adp5585.c @@ -428,7 +428,7 @@ static int adp5585_gpio_probe(struct platform_device *pdev) gc->direction_input = adp5585_gpio_direction_input; gc->direction_output = adp5585_gpio_direction_output; gc->get = adp5585_gpio_get_value; - gc->set_rv = adp5585_gpio_set_value; + gc->set = adp5585_gpio_set_value; gc->set_config = adp5585_gpio_set_config; gc->request = adp5585_gpio_request; gc->free = adp5585_gpio_free; diff --git a/drivers/gpio/gpio-aggregator.c b/drivers/gpio/gpio-aggregator.c index 6f941db02c04..af9d8b3a711d 100644 --- a/drivers/gpio/gpio-aggregator.c +++ b/drivers/gpio/gpio-aggregator.c @@ -534,8 +534,8 @@ static struct gpiochip_fwd *gpiochip_fwd_create(struct device *dev, chip->direction_output = gpio_fwd_direction_output; chip->get = gpio_fwd_get; chip->get_multiple = gpio_fwd_get_multiple_locked; - chip->set_rv = gpio_fwd_set; - chip->set_multiple_rv = gpio_fwd_set_multiple_locked; + chip->set = gpio_fwd_set; + chip->set_multiple = gpio_fwd_set_multiple_locked; chip->to_irq = gpio_fwd_to_irq; chip->base = -1; chip->ngpio = ngpios; diff --git a/drivers/gpio/gpio-altera-a10sr.c b/drivers/gpio/gpio-altera-a10sr.c index 77a674cf99e4..4524c18a87e7 100644 --- a/drivers/gpio/gpio-altera-a10sr.c +++ b/drivers/gpio/gpio-altera-a10sr.c @@ -69,7 +69,7 @@ static const struct gpio_chip altr_a10sr_gc = { .label = "altr_a10sr_gpio", .owner = THIS_MODULE, .get = altr_a10sr_gpio_get, - .set_rv = altr_a10sr_gpio_set, + .set = altr_a10sr_gpio_set, .direction_input = altr_a10sr_gpio_direction_input, .direction_output = altr_a10sr_gpio_direction_output, .can_sleep = true, diff --git a/drivers/gpio/gpio-altera.c b/drivers/gpio/gpio-altera.c index 1b28525726d7..9508d764cce4 100644 --- a/drivers/gpio/gpio-altera.c +++ b/drivers/gpio/gpio-altera.c @@ -259,7 +259,7 @@ static int altera_gpio_probe(struct platform_device *pdev) altera_gc->gc.direction_input = altera_gpio_direction_input; altera_gc->gc.direction_output = altera_gpio_direction_output; altera_gc->gc.get = altera_gpio_get; - altera_gc->gc.set_rv = altera_gpio_set; + altera_gc->gc.set = altera_gpio_set; altera_gc->gc.owner = THIS_MODULE; altera_gc->gc.parent = &pdev->dev; altera_gc->gc.base = -1; diff --git a/drivers/gpio/gpio-amd-fch.c b/drivers/gpio/gpio-amd-fch.c index f8d0cea46049..e6c6c3ec7656 100644 --- a/drivers/gpio/gpio-amd-fch.c +++ b/drivers/gpio/gpio-amd-fch.c @@ -165,7 +165,7 @@ static int amd_fch_gpio_probe(struct platform_device *pdev) priv->gc.direction_output = amd_fch_gpio_direction_output; priv->gc.get_direction = amd_fch_gpio_get_direction; priv->gc.get = amd_fch_gpio_get; - priv->gc.set_rv = amd_fch_gpio_set; + priv->gc.set = amd_fch_gpio_set; spin_lock_init(&priv->lock); diff --git a/drivers/gpio/gpio-amd8111.c b/drivers/gpio/gpio-amd8111.c index 425d8472f744..15fd5e210d74 100644 --- a/drivers/gpio/gpio-amd8111.c +++ b/drivers/gpio/gpio-amd8111.c @@ -165,7 +165,7 @@ static struct amd_gpio gp = { .ngpio = 32, .request = amd_gpio_request, .free = amd_gpio_free, - .set_rv = amd_gpio_set, + .set = amd_gpio_set, .get = amd_gpio_get, .direction_output = amd_gpio_dirout, .direction_input = amd_gpio_dirin, diff --git a/drivers/gpio/gpio-arizona.c b/drivers/gpio/gpio-arizona.c index 89ffde693019..a7e98d395d8e 100644 --- a/drivers/gpio/gpio-arizona.c +++ b/drivers/gpio/gpio-arizona.c @@ -138,7 +138,7 @@ static const struct gpio_chip template_chip = { .direction_input = arizona_gpio_direction_in, .get = arizona_gpio_get, .direction_output = arizona_gpio_direction_out, - .set_rv = arizona_gpio_set, + .set = arizona_gpio_set, .can_sleep = true, }; diff --git a/drivers/gpio/gpio-aspeed-sgpio.c b/drivers/gpio/gpio-aspeed-sgpio.c index 00b31497ecff..7622f9e9f54a 100644 --- a/drivers/gpio/gpio-aspeed-sgpio.c +++ b/drivers/gpio/gpio-aspeed-sgpio.c @@ -596,7 +596,7 @@ static int __init aspeed_sgpio_probe(struct platform_device *pdev) gpio->chip.request = NULL; gpio->chip.free = NULL; gpio->chip.get = aspeed_sgpio_get; - gpio->chip.set_rv = aspeed_sgpio_set; + gpio->chip.set = aspeed_sgpio_set; gpio->chip.set_config = aspeed_sgpio_set_config; gpio->chip.label = dev_name(&pdev->dev); gpio->chip.base = -1; diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c index 2d340a343a17..7953a9c4e36d 100644 --- a/drivers/gpio/gpio-aspeed.c +++ b/drivers/gpio/gpio-aspeed.c @@ -1352,7 +1352,7 @@ static int aspeed_gpio_probe(struct platform_device *pdev) gpio->chip.request = aspeed_gpio_request; gpio->chip.free = aspeed_gpio_free; gpio->chip.get = aspeed_gpio_get; - gpio->chip.set_rv = aspeed_gpio_set; + gpio->chip.set = aspeed_gpio_set; gpio->chip.set_config = aspeed_gpio_set_config; gpio->chip.label = dev_name(&pdev->dev); gpio->chip.base = -1; diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c index 8f22cb36004d..208b71c59d58 100644 --- a/drivers/gpio/gpio-bcm-kona.c +++ b/drivers/gpio/gpio-bcm-kona.c @@ -339,7 +339,7 @@ static const struct gpio_chip template_chip = { .direction_input = bcm_kona_gpio_direction_input, .get = bcm_kona_gpio_get, .direction_output = bcm_kona_gpio_direction_output, - .set_rv = bcm_kona_gpio_set, + .set = bcm_kona_gpio_set, .set_config = bcm_kona_gpio_set_config, .to_irq = bcm_kona_gpio_to_irq, .base = 0, diff --git a/drivers/gpio/gpio-bd71815.c b/drivers/gpio/gpio-bd71815.c index 36701500925e..afb18a5a9d79 100644 --- a/drivers/gpio/gpio-bd71815.c +++ b/drivers/gpio/gpio-bd71815.c @@ -85,7 +85,7 @@ static const struct gpio_chip bd71815gpo_chip = { .owner = THIS_MODULE, .get = bd71815gpo_get, .get_direction = bd71815gpo_direction_get, - .set_rv = bd71815gpo_set, + .set = bd71815gpo_set, .set_config = bd71815_gpio_set_config, .can_sleep = true, }; diff --git a/drivers/gpio/gpio-bd71828.c b/drivers/gpio/gpio-bd71828.c index 4ba151e5cf25..e439dbfffc62 100644 --- a/drivers/gpio/gpio-bd71828.c +++ b/drivers/gpio/gpio-bd71828.c @@ -109,7 +109,7 @@ static int bd71828_probe(struct platform_device *pdev) bdgpio->gpio.set_config = bd71828_gpio_set_config; bdgpio->gpio.can_sleep = true; bdgpio->gpio.get = bd71828_gpio_get; - bdgpio->gpio.set_rv = bd71828_gpio_set; + bdgpio->gpio.set = bd71828_gpio_set; bdgpio->gpio.base = -1; /* diff --git a/drivers/gpio/gpio-bd9571mwv.c b/drivers/gpio/gpio-bd9571mwv.c index 8df1361e3e84..7c95bb36511e 100644 --- a/drivers/gpio/gpio-bd9571mwv.c +++ b/drivers/gpio/gpio-bd9571mwv.c @@ -88,7 +88,7 @@ static const struct gpio_chip template_chip = { .direction_input = bd9571mwv_gpio_direction_input, .direction_output = bd9571mwv_gpio_direction_output, .get = bd9571mwv_gpio_get, - .set_rv = bd9571mwv_gpio_set, + .set = bd9571mwv_gpio_set, .base = -1, .ngpio = 2, .can_sleep = true, diff --git a/drivers/gpio/gpio-bt8xx.c b/drivers/gpio/gpio-bt8xx.c index 7c9e81fea37a..05401da03ca3 100644 --- a/drivers/gpio/gpio-bt8xx.c +++ b/drivers/gpio/gpio-bt8xx.c @@ -145,7 +145,7 @@ static void bt8xxgpio_gpio_setup(struct bt8xxgpio *bg) c->direction_input = bt8xxgpio_gpio_direction_input; c->get = bt8xxgpio_gpio_get; c->direction_output = bt8xxgpio_gpio_direction_output; - c->set_rv = bt8xxgpio_gpio_set; + c->set = bt8xxgpio_gpio_set; c->dbg_show = NULL; c->base = modparam_gpiobase; c->ngpio = BT8XXGPIO_NR_GPIOS; diff --git a/drivers/gpio/gpio-cgbc.c b/drivers/gpio/gpio-cgbc.c index 1495bec62456..0efa1b61001a 100644 --- a/drivers/gpio/gpio-cgbc.c +++ b/drivers/gpio/gpio-cgbc.c @@ -171,7 +171,7 @@ static int cgbc_gpio_probe(struct platform_device *pdev) chip->direction_output = cgbc_gpio_direction_output; chip->get_direction = cgbc_gpio_get_direction; chip->get = cgbc_gpio_get; - chip->set_rv = cgbc_gpio_set; + chip->set = cgbc_gpio_set; chip->ngpio = CGBC_GPIO_NGPIO; ret = devm_mutex_init(dev, &gpio->lock); diff --git a/drivers/gpio/gpio-creg-snps.c b/drivers/gpio/gpio-creg-snps.c index 8b49f02c7896..f8ea961fa1de 100644 --- a/drivers/gpio/gpio-creg-snps.c +++ b/drivers/gpio/gpio-creg-snps.c @@ -167,7 +167,7 @@ static int creg_gpio_probe(struct platform_device *pdev) hcg->gc.label = dev_name(dev); hcg->gc.base = -1; hcg->gc.ngpio = ngpios; - hcg->gc.set_rv = creg_gpio_set; + hcg->gc.set = creg_gpio_set; hcg->gc.direction_output = creg_gpio_dir_out; ret = devm_gpiochip_add_data(dev, &hcg->gc, hcg); diff --git a/drivers/gpio/gpio-cros-ec.c b/drivers/gpio/gpio-cros-ec.c index 53cd5ff6247b..435483826c6e 100644 --- a/drivers/gpio/gpio-cros-ec.c +++ b/drivers/gpio/gpio-cros-ec.c @@ -188,7 +188,7 @@ static int cros_ec_gpio_probe(struct platform_device *pdev) gc->can_sleep = true; gc->label = dev_name(dev); gc->base = -1; - gc->set_rv = cros_ec_gpio_set; + gc->set = cros_ec_gpio_set; gc->get = cros_ec_gpio_get; gc->get_direction = cros_ec_gpio_get_direction; diff --git a/drivers/gpio/gpio-crystalcove.c b/drivers/gpio/gpio-crystalcove.c index 8db7cca3a060..0fb5c06d0886 100644 --- a/drivers/gpio/gpio-crystalcove.c +++ b/drivers/gpio/gpio-crystalcove.c @@ -349,7 +349,7 @@ static int crystalcove_gpio_probe(struct platform_device *pdev) cg->chip.direction_input = crystalcove_gpio_dir_in; cg->chip.direction_output = crystalcove_gpio_dir_out; cg->chip.get = crystalcove_gpio_get; - cg->chip.set_rv = crystalcove_gpio_set; + cg->chip.set = crystalcove_gpio_set; cg->chip.base = -1; cg->chip.ngpio = CRYSTALCOVE_VGPIO_NUM; cg->chip.can_sleep = true; diff --git a/drivers/gpio/gpio-cs5535.c b/drivers/gpio/gpio-cs5535.c index 143d1f4173a6..8affe4e9f90e 100644 --- a/drivers/gpio/gpio-cs5535.c +++ b/drivers/gpio/gpio-cs5535.c @@ -296,7 +296,7 @@ static struct cs5535_gpio_chip cs5535_gpio_chip = { .request = chip_gpio_request, .get = chip_gpio_get, - .set_rv = chip_gpio_set, + .set = chip_gpio_set, .direction_input = chip_direction_input, .direction_output = chip_direction_output, diff --git a/drivers/gpio/gpio-da9052.c b/drivers/gpio/gpio-da9052.c index 6482c5b267db..495f0ee58505 100644 --- a/drivers/gpio/gpio-da9052.c +++ b/drivers/gpio/gpio-da9052.c @@ -172,7 +172,7 @@ static const struct gpio_chip reference_gp = { .label = "da9052-gpio", .owner = THIS_MODULE, .get = da9052_gpio_get, - .set_rv = da9052_gpio_set, + .set = da9052_gpio_set, .direction_input = da9052_gpio_direction_input, .direction_output = da9052_gpio_direction_output, .to_irq = da9052_gpio_to_irq, diff --git a/drivers/gpio/gpio-da9055.c b/drivers/gpio/gpio-da9055.c index 3d9d0c700100..a09bd6eb93cf 100644 --- a/drivers/gpio/gpio-da9055.c +++ b/drivers/gpio/gpio-da9055.c @@ -116,7 +116,7 @@ static const struct gpio_chip reference_gp = { .label = "da9055-gpio", .owner = THIS_MODULE, .get = da9055_gpio_get, - .set_rv = da9055_gpio_set, + .set = da9055_gpio_set, .direction_input = da9055_gpio_direction_input, .direction_output = da9055_gpio_direction_output, .to_irq = da9055_gpio_to_irq, diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c index 8f3a36d0191d..538f27209ce7 100644 --- a/drivers/gpio/gpio-davinci.c +++ b/drivers/gpio/gpio-davinci.c @@ -202,7 +202,7 @@ static int davinci_gpio_probe(struct platform_device *pdev) chips->chip.direction_input = davinci_direction_in; chips->chip.get = davinci_gpio_get; chips->chip.direction_output = davinci_direction_out; - chips->chip.set_rv = davinci_gpio_set; + chips->chip.set = davinci_gpio_set; chips->chip.ngpio = ngpio; chips->chip.base = -1; diff --git a/drivers/gpio/gpio-dln2.c b/drivers/gpio/gpio-dln2.c index 4bd3c47eaf93..4670ffd7ea7f 100644 --- a/drivers/gpio/gpio-dln2.c +++ b/drivers/gpio/gpio-dln2.c @@ -469,7 +469,7 @@ static int dln2_gpio_probe(struct platform_device *pdev) dln2->gpio.base = -1; dln2->gpio.ngpio = pins; dln2->gpio.can_sleep = true; - dln2->gpio.set_rv = dln2_gpio_set; + dln2->gpio.set = dln2_gpio_set; dln2->gpio.get = dln2_gpio_get; dln2->gpio.request = dln2_gpio_request; dln2->gpio.free = dln2_gpio_free; diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c index f2973d0b7138..50fafeda8d7e 100644 --- a/drivers/gpio/gpio-eic-sprd.c +++ b/drivers/gpio/gpio-eic-sprd.c @@ -663,7 +663,7 @@ static int sprd_eic_probe(struct platform_device *pdev) sprd_eic->chip.request = sprd_eic_request; sprd_eic->chip.free = sprd_eic_free; sprd_eic->chip.set_config = sprd_eic_set_config; - sprd_eic->chip.set_rv = sprd_eic_set; + sprd_eic->chip.set = sprd_eic_set; fallthrough; case SPRD_EIC_ASYNC: case SPRD_EIC_SYNC: diff --git a/drivers/gpio/gpio-em.c b/drivers/gpio/gpio-em.c index 015f1ac32dd9..a214b0672726 100644 --- a/drivers/gpio/gpio-em.c +++ b/drivers/gpio/gpio-em.c @@ -306,7 +306,7 @@ static int em_gio_probe(struct platform_device *pdev) gpio_chip->direction_input = em_gio_direction_input; gpio_chip->get = em_gio_get; gpio_chip->direction_output = em_gio_direction_output; - gpio_chip->set_rv = em_gio_set; + gpio_chip->set = em_gio_set; gpio_chip->to_irq = em_gio_to_irq; gpio_chip->request = pinctrl_gpio_request; gpio_chip->free = em_gio_free; diff --git a/drivers/gpio/gpio-exar.c b/drivers/gpio/gpio-exar.c index beb98286d13e..9053662f1817 100644 --- a/drivers/gpio/gpio-exar.c +++ b/drivers/gpio/gpio-exar.c @@ -211,7 +211,7 @@ static int gpio_exar_probe(struct platform_device *pdev) exar_gpio->gpio_chip.direction_input = exar_direction_input; exar_gpio->gpio_chip.get_direction = exar_get_direction; exar_gpio->gpio_chip.get = exar_get_value; - exar_gpio->gpio_chip.set_rv = exar_set_value; + exar_gpio->gpio_chip.set = exar_set_value; exar_gpio->gpio_chip.base = -1; exar_gpio->gpio_chip.ngpio = ngpios; exar_gpio->index = index; diff --git a/drivers/gpio/gpio-f7188x.c b/drivers/gpio/gpio-f7188x.c index dfcd3634f279..4d5b927ad70f 100644 --- a/drivers/gpio/gpio-f7188x.c +++ b/drivers/gpio/gpio-f7188x.c @@ -173,7 +173,7 @@ static int f7188x_gpio_set_config(struct gpio_chip *chip, unsigned offset, .direction_input = f7188x_gpio_direction_in, \ .get = f7188x_gpio_get, \ .direction_output = f7188x_gpio_direction_out, \ - .set_rv = f7188x_gpio_set, \ + .set = f7188x_gpio_set, \ .set_config = f7188x_gpio_set_config, \ .base = -1, \ .ngpio = _ngpio, \ diff --git a/drivers/gpio/gpio-graniterapids.c b/drivers/gpio/gpio-graniterapids.c index f25283e5239d..121bf29a27f5 100644 --- a/drivers/gpio/gpio-graniterapids.c +++ b/drivers/gpio/gpio-graniterapids.c @@ -159,7 +159,7 @@ static const struct gpio_chip gnr_gpio_chip = { .owner = THIS_MODULE, .request = gnr_gpio_request, .get = gnr_gpio_get, - .set_rv = gnr_gpio_set, + .set = gnr_gpio_set, .get_direction = gnr_gpio_get_direction, .direction_input = gnr_gpio_direction_input, .direction_output = gnr_gpio_direction_output, diff --git a/drivers/gpio/gpio-gw-pld.c b/drivers/gpio/gpio-gw-pld.c index a40ba99a3aea..2e5d97b7363f 100644 --- a/drivers/gpio/gpio-gw-pld.c +++ b/drivers/gpio/gpio-gw-pld.c @@ -86,7 +86,7 @@ static int gw_pld_probe(struct i2c_client *client) gw->chip.direction_input = gw_pld_input8; gw->chip.get = gw_pld_get8; gw->chip.direction_output = gw_pld_output8; - gw->chip.set_rv = gw_pld_set8; + gw->chip.set = gw_pld_set8; gw->client = client; /* diff --git a/drivers/gpio/gpio-htc-egpio.c b/drivers/gpio/gpio-htc-egpio.c index b1844a676c7c..2eaed83214d8 100644 --- a/drivers/gpio/gpio-htc-egpio.c +++ b/drivers/gpio/gpio-htc-egpio.c @@ -324,7 +324,7 @@ static int __init egpio_probe(struct platform_device *pdev) chip->parent = &pdev->dev; chip->owner = THIS_MODULE; chip->get = egpio_get; - chip->set_rv = egpio_set; + chip->set = egpio_set; chip->direction_input = egpio_direction_input; chip->direction_output = egpio_direction_output; chip->get_direction = egpio_get_direction; diff --git a/drivers/gpio/gpio-ich.c b/drivers/gpio/gpio-ich.c index 67089b2423d8..1802c9116ffe 100644 --- a/drivers/gpio/gpio-ich.c +++ b/drivers/gpio/gpio-ich.c @@ -273,7 +273,7 @@ static void ichx_gpiolib_setup(struct gpio_chip *chip) chip->get = ichx_priv.desc->get ? ichx_priv.desc->get : ichx_gpio_get; - chip->set_rv = ichx_gpio_set; + chip->set = ichx_gpio_set; chip->get_direction = ichx_gpio_get_direction; chip->direction_input = ichx_gpio_direction_input; chip->direction_output = ichx_gpio_direction_output; diff --git a/drivers/gpio/gpio-imx-scu.c b/drivers/gpio/gpio-imx-scu.c index 1693dbf1b777..0a75afecf9f8 100644 --- a/drivers/gpio/gpio-imx-scu.c +++ b/drivers/gpio/gpio-imx-scu.c @@ -102,7 +102,7 @@ static int imx_scu_gpio_probe(struct platform_device *pdev) gc->ngpio = ARRAY_SIZE(scu_rsrc_arr); gc->label = dev_name(dev); gc->get = imx_scu_gpio_get; - gc->set_rv = imx_scu_gpio_set; + gc->set = imx_scu_gpio_set; gc->get_direction = imx_scu_gpio_get_direction; platform_set_drvdata(pdev, priv); diff --git a/drivers/gpio/gpio-it87.c b/drivers/gpio/gpio-it87.c index d8184b527bac..5d677bcfccf2 100644 --- a/drivers/gpio/gpio-it87.c +++ b/drivers/gpio/gpio-it87.c @@ -267,7 +267,7 @@ static const struct gpio_chip it87_template_chip = { .request = it87_gpio_request, .get = it87_gpio_get, .direction_input = it87_gpio_direction_in, - .set_rv = it87_gpio_set, + .set = it87_gpio_set, .direction_output = it87_gpio_direction_out, .base = -1 }; diff --git a/drivers/gpio/gpio-janz-ttl.c b/drivers/gpio/gpio-janz-ttl.c index 9f548eda3888..b0c4a3346e7d 100644 --- a/drivers/gpio/gpio-janz-ttl.c +++ b/drivers/gpio/gpio-janz-ttl.c @@ -171,7 +171,7 @@ static int ttl_probe(struct platform_device *pdev) gpio->parent = &pdev->dev; gpio->label = pdev->name; gpio->get = ttl_get_value; - gpio->set_rv = ttl_set_value; + gpio->set = ttl_set_value; gpio->owner = THIS_MODULE; /* request dynamic allocation */ diff --git a/drivers/gpio/gpio-kempld.c b/drivers/gpio/gpio-kempld.c index e38e604baa22..923aad3ab4d4 100644 --- a/drivers/gpio/gpio-kempld.c +++ b/drivers/gpio/gpio-kempld.c @@ -169,7 +169,7 @@ static int kempld_gpio_probe(struct platform_device *pdev) chip->direction_output = kempld_gpio_direction_output; chip->get_direction = kempld_gpio_get_direction; chip->get = kempld_gpio_get; - chip->set_rv = kempld_gpio_set; + chip->set = kempld_gpio_set; chip->ngpio = kempld_gpio_pincount(pld); if (chip->ngpio == 0) { dev_err(dev, "No GPIO pins detected\n"); diff --git a/drivers/gpio/gpio-latch.c b/drivers/gpio/gpio-latch.c index 3d0ff09284fb..c64aaa896766 100644 --- a/drivers/gpio/gpio-latch.c +++ b/drivers/gpio/gpio-latch.c @@ -166,11 +166,11 @@ static int gpio_latch_probe(struct platform_device *pdev) if (gpio_latch_can_sleep(priv, n_latches)) { priv->gc.can_sleep = true; - priv->gc.set_rv = gpio_latch_set_can_sleep; + priv->gc.set = gpio_latch_set_can_sleep; mutex_init(&priv->mutex); } else { priv->gc.can_sleep = false; - priv->gc.set_rv = gpio_latch_set; + priv->gc.set = gpio_latch_set; spin_lock_init(&priv->spinlock); } diff --git a/drivers/gpio/gpio-ljca.c b/drivers/gpio/gpio-ljca.c index 61524a9ba765..3b4f8830c741 100644 --- a/drivers/gpio/gpio-ljca.c +++ b/drivers/gpio/gpio-ljca.c @@ -437,7 +437,7 @@ static int ljca_gpio_probe(struct auxiliary_device *auxdev, ljca_gpio->gc.direction_output = ljca_gpio_direction_output; ljca_gpio->gc.get_direction = ljca_gpio_get_direction; ljca_gpio->gc.get = ljca_gpio_get_value; - ljca_gpio->gc.set_rv = ljca_gpio_set_value; + ljca_gpio->gc.set = ljca_gpio_set_value; ljca_gpio->gc.set_config = ljca_gpio_set_config; ljca_gpio->gc.init_valid_mask = ljca_gpio_init_valid_mask; ljca_gpio->gc.can_sleep = true; diff --git a/drivers/gpio/gpio-logicvc.c b/drivers/gpio/gpio-logicvc.c index 19cd2847467c..cb9dbcc290ad 100644 --- a/drivers/gpio/gpio-logicvc.c +++ b/drivers/gpio/gpio-logicvc.c @@ -134,7 +134,7 @@ static int logicvc_gpio_probe(struct platform_device *pdev) logicvc->chip.ngpio = LOGICVC_CTRL_GPIO_BITS + LOGICVC_POWER_CTRL_GPIO_BITS; logicvc->chip.get = logicvc_gpio_get; - logicvc->chip.set_rv = logicvc_gpio_set; + logicvc->chip.set = logicvc_gpio_set; logicvc->chip.direction_output = logicvc_gpio_direction_output; return devm_gpiochip_add_data(dev, &logicvc->chip, logicvc); diff --git a/drivers/gpio/gpio-loongson-64bit.c b/drivers/gpio/gpio-loongson-64bit.c index add09971d26a..818c606fbc51 100644 --- a/drivers/gpio/gpio-loongson-64bit.c +++ b/drivers/gpio/gpio-loongson-64bit.c @@ -157,7 +157,7 @@ static int loongson_gpio_init(struct device *dev, struct loongson_gpio_chip *lgp lgpio->chip.get = loongson_gpio_get; lgpio->chip.get_direction = loongson_gpio_get_direction; lgpio->chip.direction_output = loongson_gpio_direction_output; - lgpio->chip.set_rv = loongson_gpio_set; + lgpio->chip.set = loongson_gpio_set; lgpio->chip.parent = dev; spin_lock_init(&lgpio->lock); } diff --git a/drivers/gpio/gpio-loongson.c b/drivers/gpio/gpio-loongson.c index 8f3668169ebf..f3e0559f969d 100644 --- a/drivers/gpio/gpio-loongson.c +++ b/drivers/gpio/gpio-loongson.c @@ -106,7 +106,7 @@ static int loongson_gpio_probe(struct platform_device *pdev) gc->base = 0; gc->ngpio = LOONGSON_N_GPIO; gc->get = loongson_gpio_get_value; - gc->set_rv = loongson_gpio_set_value; + gc->set = loongson_gpio_set_value; gc->direction_input = loongson_gpio_direction_input; gc->direction_output = loongson_gpio_direction_output; diff --git a/drivers/gpio/gpio-lp3943.c b/drivers/gpio/gpio-lp3943.c index 52ab3ac4844c..e8e00daff7df 100644 --- a/drivers/gpio/gpio-lp3943.c +++ b/drivers/gpio/gpio-lp3943.c @@ -184,7 +184,7 @@ static const struct gpio_chip lp3943_gpio_chip = { .direction_input = lp3943_gpio_direction_input, .get = lp3943_gpio_get, .direction_output = lp3943_gpio_direction_output, - .set_rv = lp3943_gpio_set, + .set = lp3943_gpio_set, .base = -1, .ngpio = LP3943_MAX_GPIO, .can_sleep = 1, diff --git a/drivers/gpio/gpio-lp873x.c b/drivers/gpio/gpio-lp873x.c index 1908ed302e92..5376708a81bf 100644 --- a/drivers/gpio/gpio-lp873x.c +++ b/drivers/gpio/gpio-lp873x.c @@ -124,7 +124,7 @@ static const struct gpio_chip template_chip = { .direction_input = lp873x_gpio_direction_input, .direction_output = lp873x_gpio_direction_output, .get = lp873x_gpio_get, - .set_rv = lp873x_gpio_set, + .set = lp873x_gpio_set, .set_config = lp873x_gpio_set_config, .base = -1, .ngpio = 2, diff --git a/drivers/gpio/gpio-lp87565.c b/drivers/gpio/gpio-lp87565.c index 8ea687d5d028..0f337c1283b2 100644 --- a/drivers/gpio/gpio-lp87565.c +++ b/drivers/gpio/gpio-lp87565.c @@ -139,7 +139,7 @@ static const struct gpio_chip template_chip = { .direction_input = lp87565_gpio_direction_input, .direction_output = lp87565_gpio_direction_output, .get = lp87565_gpio_get, - .set_rv = lp87565_gpio_set, + .set = lp87565_gpio_set, .set_config = lp87565_gpio_set_config, .base = -1, .ngpio = 3, diff --git a/drivers/gpio/gpio-lpc18xx.c b/drivers/gpio/gpio-lpc18xx.c index 2dbfbf90176c..37a2342eb2e6 100644 --- a/drivers/gpio/gpio-lpc18xx.c +++ b/drivers/gpio/gpio-lpc18xx.c @@ -327,7 +327,7 @@ static const struct gpio_chip lpc18xx_chip = { .free = gpiochip_generic_free, .direction_input = lpc18xx_gpio_direction_input, .direction_output = lpc18xx_gpio_direction_output, - .set_rv = lpc18xx_gpio_set, + .set = lpc18xx_gpio_set, .get = lpc18xx_gpio_get, .ngpio = LPC18XX_MAX_PORTS * LPC18XX_PINS_PER_PORT, .owner = THIS_MODULE, diff --git a/drivers/gpio/gpio-lpc32xx.c b/drivers/gpio/gpio-lpc32xx.c index 6668b8bd9f1e..37fc54fc7385 100644 --- a/drivers/gpio/gpio-lpc32xx.c +++ b/drivers/gpio/gpio-lpc32xx.c @@ -407,7 +407,7 @@ static struct lpc32xx_gpio_chip lpc32xx_gpiochip[] = { .direction_input = lpc32xx_gpio_dir_input_p012, .get = lpc32xx_gpio_get_value_p012, .direction_output = lpc32xx_gpio_dir_output_p012, - .set_rv = lpc32xx_gpio_set_value_p012, + .set = lpc32xx_gpio_set_value_p012, .request = lpc32xx_gpio_request, .to_irq = lpc32xx_gpio_to_irq_p01, .base = LPC32XX_GPIO_P0_GRP, @@ -423,7 +423,7 @@ static struct lpc32xx_gpio_chip lpc32xx_gpiochip[] = { .direction_input = lpc32xx_gpio_dir_input_p012, .get = lpc32xx_gpio_get_value_p012, .direction_output = lpc32xx_gpio_dir_output_p012, - .set_rv = lpc32xx_gpio_set_value_p012, + .set = lpc32xx_gpio_set_value_p012, .request = lpc32xx_gpio_request, .to_irq = lpc32xx_gpio_to_irq_p01, .base = LPC32XX_GPIO_P1_GRP, @@ -439,7 +439,7 @@ static struct lpc32xx_gpio_chip lpc32xx_gpiochip[] = { .direction_input = lpc32xx_gpio_dir_input_p012, .get = lpc32xx_gpio_get_value_p012, .direction_output = lpc32xx_gpio_dir_output_p012, - .set_rv = lpc32xx_gpio_set_value_p012, + .set = lpc32xx_gpio_set_value_p012, .request = lpc32xx_gpio_request, .base = LPC32XX_GPIO_P2_GRP, .ngpio = LPC32XX_GPIO_P2_MAX, @@ -454,7 +454,7 @@ static struct lpc32xx_gpio_chip lpc32xx_gpiochip[] = { .direction_input = lpc32xx_gpio_dir_input_p3, .get = lpc32xx_gpio_get_value_p3, .direction_output = lpc32xx_gpio_dir_output_p3, - .set_rv = lpc32xx_gpio_set_value_p3, + .set = lpc32xx_gpio_set_value_p3, .request = lpc32xx_gpio_request, .to_irq = lpc32xx_gpio_to_irq_gpio_p3, .base = LPC32XX_GPIO_P3_GRP, @@ -482,7 +482,7 @@ static struct lpc32xx_gpio_chip lpc32xx_gpiochip[] = { .chip = { .label = "gpo_p3", .direction_output = lpc32xx_gpio_dir_out_always, - .set_rv = lpc32xx_gpo_set_value, + .set = lpc32xx_gpo_set_value, .get = lpc32xx_gpo_get_value, .request = lpc32xx_gpio_request, .base = LPC32XX_GPO_P3_GRP, diff --git a/drivers/gpio/gpio-macsmc.c b/drivers/gpio/gpio-macsmc.c index 7570d9e89adf..30ef258e7655 100644 --- a/drivers/gpio/gpio-macsmc.c +++ b/drivers/gpio/gpio-macsmc.c @@ -261,7 +261,7 @@ static int macsmc_gpio_probe(struct platform_device *pdev) smcgp->gc.label = "macsmc-pmu-gpio"; smcgp->gc.owner = THIS_MODULE; smcgp->gc.get = macsmc_gpio_get; - smcgp->gc.set_rv = macsmc_gpio_set; + smcgp->gc.set = macsmc_gpio_set; smcgp->gc.get_direction = macsmc_gpio_get_direction; smcgp->gc.init_valid_mask = macsmc_gpio_init_valid_mask; smcgp->gc.can_sleep = true; diff --git a/drivers/gpio/gpio-madera.c b/drivers/gpio/gpio-madera.c index e73e72d62bc8..551faf9655b2 100644 --- a/drivers/gpio/gpio-madera.c +++ b/drivers/gpio/gpio-madera.c @@ -109,7 +109,7 @@ static const struct gpio_chip madera_gpio_chip = { .direction_input = madera_gpio_direction_in, .get = madera_gpio_get, .direction_output = madera_gpio_direction_out, - .set_rv = madera_gpio_set, + .set = madera_gpio_set, .set_config = gpiochip_generic_config, .can_sleep = true, }; diff --git a/drivers/gpio/gpio-max730x.c b/drivers/gpio/gpio-max730x.c index 75d414d8c992..84c7c2dca822 100644 --- a/drivers/gpio/gpio-max730x.c +++ b/drivers/gpio/gpio-max730x.c @@ -188,7 +188,7 @@ int __max730x_probe(struct max7301 *ts) ts->chip.direction_input = max7301_direction_input; ts->chip.get = max7301_get; ts->chip.direction_output = max7301_direction_output; - ts->chip.set_rv = max7301_set; + ts->chip.set = max7301_set; ts->chip.ngpio = PIN_NUMBER; ts->chip.can_sleep = true; diff --git a/drivers/gpio/gpio-max732x.c b/drivers/gpio/gpio-max732x.c index d5ffedb086af..a61d670ceeda 100644 --- a/drivers/gpio/gpio-max732x.c +++ b/drivers/gpio/gpio-max732x.c @@ -585,8 +585,8 @@ static int max732x_setup_gpio(struct max732x_chip *chip, gc->direction_input = max732x_gpio_direction_input; if (chip->dir_output) { gc->direction_output = max732x_gpio_direction_output; - gc->set_rv = max732x_gpio_set_value; - gc->set_multiple_rv = max732x_gpio_set_multiple; + gc->set = max732x_gpio_set_value; + gc->set_multiple = max732x_gpio_set_multiple; } gc->get = max732x_gpio_get_value; gc->can_sleep = true; diff --git a/drivers/gpio/gpio-max77620.c b/drivers/gpio/gpio-max77620.c index af7af8e40afe..02eca400b307 100644 --- a/drivers/gpio/gpio-max77620.c +++ b/drivers/gpio/gpio-max77620.c @@ -311,7 +311,7 @@ static int max77620_gpio_probe(struct platform_device *pdev) mgpio->gpio_chip.direction_input = max77620_gpio_dir_input; mgpio->gpio_chip.get = max77620_gpio_get; mgpio->gpio_chip.direction_output = max77620_gpio_dir_output; - mgpio->gpio_chip.set_rv = max77620_gpio_set; + mgpio->gpio_chip.set = max77620_gpio_set; mgpio->gpio_chip.set_config = max77620_gpio_set_config; mgpio->gpio_chip.ngpio = MAX77620_GPIO_NR; mgpio->gpio_chip.can_sleep = 1; diff --git a/drivers/gpio/gpio-max77650.c b/drivers/gpio/gpio-max77650.c index a553e141059f..4540da4c1418 100644 --- a/drivers/gpio/gpio-max77650.c +++ b/drivers/gpio/gpio-max77650.c @@ -166,7 +166,7 @@ static int max77650_gpio_probe(struct platform_device *pdev) chip->gc.direction_input = max77650_gpio_direction_input; chip->gc.direction_output = max77650_gpio_direction_output; - chip->gc.set_rv = max77650_gpio_set_value; + chip->gc.set = max77650_gpio_set_value; chip->gc.get = max77650_gpio_get_value; chip->gc.get_direction = max77650_gpio_get_direction; chip->gc.set_config = max77650_gpio_set_config; diff --git a/drivers/gpio/gpio-max77759.c b/drivers/gpio/gpio-max77759.c index 7fe8e6f697d0..5e48eb03e7b3 100644 --- a/drivers/gpio/gpio-max77759.c +++ b/drivers/gpio/gpio-max77759.c @@ -469,7 +469,7 @@ static int max77759_gpio_probe(struct platform_device *pdev) chip->gc.direction_input = max77759_gpio_direction_input; chip->gc.direction_output = max77759_gpio_direction_output; chip->gc.get = max77759_gpio_get_value; - chip->gc.set_rv = max77759_gpio_set_value; + chip->gc.set = max77759_gpio_set_value; girq = &chip->gc.irq; gpio_irq_chip_set_chip(girq, &max77759_gpio_irq_chip); diff --git a/drivers/gpio/gpio-mb86s7x.c b/drivers/gpio/gpio-mb86s7x.c index 5ee2991ecdfd..581a71872eab 100644 --- a/drivers/gpio/gpio-mb86s7x.c +++ b/drivers/gpio/gpio-mb86s7x.c @@ -180,7 +180,7 @@ static int mb86s70_gpio_probe(struct platform_device *pdev) gchip->gc.request = mb86s70_gpio_request; gchip->gc.free = mb86s70_gpio_free; gchip->gc.get = mb86s70_gpio_get; - gchip->gc.set_rv = mb86s70_gpio_set; + gchip->gc.set = mb86s70_gpio_set; gchip->gc.to_irq = mb86s70_gpio_to_irq; gchip->gc.label = dev_name(&pdev->dev); gchip->gc.ngpio = 32; diff --git a/drivers/gpio/gpio-mc33880.c b/drivers/gpio/gpio-mc33880.c index e68956104161..9a40e9579e95 100644 --- a/drivers/gpio/gpio-mc33880.c +++ b/drivers/gpio/gpio-mc33880.c @@ -103,7 +103,7 @@ static int mc33880_probe(struct spi_device *spi) mc->spi = spi; mc->chip.label = DRIVER_NAME; - mc->chip.set_rv = mc33880_set; + mc->chip.set = mc33880_set; mc->chip.base = pdata->base; mc->chip.ngpio = PIN_NUMBER; mc->chip.can_sleep = true; diff --git a/drivers/gpio/gpio-ml-ioh.c b/drivers/gpio/gpio-ml-ioh.c index 12cf36f9ca63..f6af81bf2b13 100644 --- a/drivers/gpio/gpio-ml-ioh.c +++ b/drivers/gpio/gpio-ml-ioh.c @@ -224,7 +224,7 @@ static void ioh_gpio_setup(struct ioh_gpio *chip, int num_port) gpio->direction_input = ioh_gpio_direction_input; gpio->get = ioh_gpio_get; gpio->direction_output = ioh_gpio_direction_output; - gpio->set_rv = ioh_gpio_set; + gpio->set = ioh_gpio_set; gpio->dbg_show = NULL; gpio->base = -1; gpio->ngpio = num_port; diff --git a/drivers/gpio/gpio-mm-lantiq.c b/drivers/gpio/gpio-mm-lantiq.c index 897a1e004681..8f1405733d98 100644 --- a/drivers/gpio/gpio-mm-lantiq.c +++ b/drivers/gpio/gpio-mm-lantiq.c @@ -111,7 +111,7 @@ static int ltq_mm_probe(struct platform_device *pdev) chip->mmchip.gc.ngpio = 16; chip->mmchip.gc.direction_output = ltq_mm_dir_out; - chip->mmchip.gc.set_rv = ltq_mm_set; + chip->mmchip.gc.set = ltq_mm_set; chip->mmchip.save_regs = ltq_mm_save_regs; /* store the shadow value if one was passed by the devicetree */ diff --git a/drivers/gpio/gpio-mmio.c b/drivers/gpio/gpio-mmio.c index cf878c2ea6bf..021ad62778c2 100644 --- a/drivers/gpio/gpio-mmio.c +++ b/drivers/gpio/gpio-mmio.c @@ -367,7 +367,7 @@ static int bgpio_dir_out_err(struct gpio_chip *gc, unsigned int gpio, static int bgpio_simple_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) { - gc->set_rv(gc, gpio, val); + gc->set(gc, gpio, val); return bgpio_dir_return(gc, gpio, true); } @@ -432,14 +432,14 @@ static int bgpio_dir_out_dir_first(struct gpio_chip *gc, unsigned int gpio, int val) { bgpio_dir_out(gc, gpio, val); - gc->set_rv(gc, gpio, val); + gc->set(gc, gpio, val); return bgpio_dir_return(gc, gpio, true); } static int bgpio_dir_out_val_first(struct gpio_chip *gc, unsigned int gpio, int val) { - gc->set_rv(gc, gpio, val); + gc->set(gc, gpio, val); bgpio_dir_out(gc, gpio, val); return bgpio_dir_return(gc, gpio, true); } @@ -528,18 +528,18 @@ static int bgpio_setup_io(struct gpio_chip *gc, if (set && clr) { gc->reg_set = set; gc->reg_clr = clr; - gc->set_rv = bgpio_set_with_clear; - gc->set_multiple_rv = bgpio_set_multiple_with_clear; + gc->set = bgpio_set_with_clear; + gc->set_multiple = bgpio_set_multiple_with_clear; } else if (set && !clr) { gc->reg_set = set; - gc->set_rv = bgpio_set_set; - gc->set_multiple_rv = bgpio_set_multiple_set; + gc->set = bgpio_set_set; + gc->set_multiple = bgpio_set_multiple_set; } else if (flags & BGPIOF_NO_OUTPUT) { - gc->set_rv = bgpio_set_none; - gc->set_multiple_rv = NULL; + gc->set = bgpio_set_none; + gc->set_multiple = NULL; } else { - gc->set_rv = bgpio_set; - gc->set_multiple_rv = bgpio_set_multiple; + gc->set = bgpio_set; + gc->set_multiple = bgpio_set_multiple; } if (!(flags & BGPIOF_UNREADABLE_REG_SET) && @@ -676,7 +676,7 @@ int bgpio_init(struct gpio_chip *gc, struct device *dev, } gc->bgpio_data = gc->read_reg(gc->reg_dat); - if (gc->set_rv == bgpio_set_set && + if (gc->set == bgpio_set_set && !(flags & BGPIOF_UNREADABLE_REG_SET)) gc->bgpio_data = gc->read_reg(gc->reg_set); diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c index 266c0953d914..a7d69f3835c1 100644 --- a/drivers/gpio/gpio-mockup.c +++ b/drivers/gpio/gpio-mockup.c @@ -449,9 +449,9 @@ static int gpio_mockup_probe(struct platform_device *pdev) gc->owner = THIS_MODULE; gc->parent = dev; gc->get = gpio_mockup_get; - gc->set_rv = gpio_mockup_set; + gc->set = gpio_mockup_set; gc->get_multiple = gpio_mockup_get_multiple; - gc->set_multiple_rv = gpio_mockup_set_multiple; + gc->set_multiple = gpio_mockup_set_multiple; gc->direction_output = gpio_mockup_dirout; gc->direction_input = gpio_mockup_dirin; gc->get_direction = gpio_mockup_get_direction; diff --git a/drivers/gpio/gpio-moxtet.c b/drivers/gpio/gpio-moxtet.c index 27dd9c3e7b77..4eb9f1a2779b 100644 --- a/drivers/gpio/gpio-moxtet.c +++ b/drivers/gpio/gpio-moxtet.c @@ -140,7 +140,7 @@ static int moxtet_gpio_probe(struct device *dev) chip->gpio_chip.direction_input = moxtet_gpio_direction_input; chip->gpio_chip.direction_output = moxtet_gpio_direction_output; chip->gpio_chip.get = moxtet_gpio_get_value; - chip->gpio_chip.set_rv = moxtet_gpio_set_value; + chip->gpio_chip.set = moxtet_gpio_set_value; chip->gpio_chip.base = -1; chip->gpio_chip.ngpio = MOXTET_GPIO_NGPIOS; diff --git a/drivers/gpio/gpio-mpc5200.c b/drivers/gpio/gpio-mpc5200.c index 40d587176a75..dad0eca1ca2e 100644 --- a/drivers/gpio/gpio-mpc5200.c +++ b/drivers/gpio/gpio-mpc5200.c @@ -153,7 +153,7 @@ static int mpc52xx_wkup_gpiochip_probe(struct platform_device *ofdev) gc->direction_input = mpc52xx_wkup_gpio_dir_in; gc->direction_output = mpc52xx_wkup_gpio_dir_out; gc->get = mpc52xx_wkup_gpio_get; - gc->set_rv = mpc52xx_wkup_gpio_set; + gc->set = mpc52xx_wkup_gpio_set; ret = of_mm_gpiochip_add_data(ofdev->dev.of_node, &chip->mmchip, chip); if (ret) @@ -315,7 +315,7 @@ static int mpc52xx_simple_gpiochip_probe(struct platform_device *ofdev) gc->direction_input = mpc52xx_simple_gpio_dir_in; gc->direction_output = mpc52xx_simple_gpio_dir_out; gc->get = mpc52xx_simple_gpio_get; - gc->set_rv = mpc52xx_simple_gpio_set; + gc->set = mpc52xx_simple_gpio_set; ret = of_mm_gpiochip_add_data(ofdev->dev.of_node, &chip->mmchip, chip); if (ret) diff --git a/drivers/gpio/gpio-mpfs.c b/drivers/gpio/gpio-mpfs.c index 3415cb7ebb0f..82d557a7e5d8 100644 --- a/drivers/gpio/gpio-mpfs.c +++ b/drivers/gpio/gpio-mpfs.c @@ -150,7 +150,7 @@ static int mpfs_gpio_probe(struct platform_device *pdev) mpfs_gpio->gc.direction_output = mpfs_gpio_direction_output; mpfs_gpio->gc.get_direction = mpfs_gpio_get_direction; mpfs_gpio->gc.get = mpfs_gpio_get; - mpfs_gpio->gc.set_rv = mpfs_gpio_set; + mpfs_gpio->gc.set = mpfs_gpio_set; mpfs_gpio->gc.base = -1; mpfs_gpio->gc.ngpio = ngpios; mpfs_gpio->gc.label = dev_name(dev); diff --git a/drivers/gpio/gpio-mpsse.c b/drivers/gpio/gpio-mpsse.c index b17de08e9e03..9f42bb30b4ec 100644 --- a/drivers/gpio/gpio-mpsse.c +++ b/drivers/gpio/gpio-mpsse.c @@ -448,9 +448,9 @@ static int gpio_mpsse_probe(struct usb_interface *interface, priv->gpio.direction_input = gpio_mpsse_direction_input; priv->gpio.direction_output = gpio_mpsse_direction_output; priv->gpio.get = gpio_mpsse_gpio_get; - priv->gpio.set_rv = gpio_mpsse_gpio_set; + priv->gpio.set = gpio_mpsse_gpio_set; priv->gpio.get_multiple = gpio_mpsse_get_multiple; - priv->gpio.set_multiple_rv = gpio_mpsse_set_multiple; + priv->gpio.set_multiple = gpio_mpsse_set_multiple; priv->gpio.base = -1; priv->gpio.ngpio = 16; priv->gpio.offset = priv->intf_id * priv->gpio.ngpio; diff --git a/drivers/gpio/gpio-msc313.c b/drivers/gpio/gpio-msc313.c index 992339a89d19..b0cccd856840 100644 --- a/drivers/gpio/gpio-msc313.c +++ b/drivers/gpio/gpio-msc313.c @@ -658,7 +658,7 @@ static int msc313_gpio_probe(struct platform_device *pdev) gpiochip->direction_input = msc313_gpio_direction_input; gpiochip->direction_output = msc313_gpio_direction_output; gpiochip->get = msc313_gpio_get; - gpiochip->set_rv = msc313_gpio_set; + gpiochip->set = msc313_gpio_set; gpiochip->base = -1; gpiochip->ngpio = gpio->gpio_data->num; gpiochip->names = gpio->gpio_data->names; diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c index 24792b8eb083..5e3f54cb8bc4 100644 --- a/drivers/gpio/gpio-mvebu.c +++ b/drivers/gpio/gpio-mvebu.c @@ -1168,7 +1168,7 @@ static int mvebu_gpio_probe(struct platform_device *pdev) mvchip->chip.direction_input = mvebu_gpio_direction_input; mvchip->chip.get = mvebu_gpio_get; mvchip->chip.direction_output = mvebu_gpio_direction_output; - mvchip->chip.set_rv = mvebu_gpio_set; + mvchip->chip.set = mvebu_gpio_set; if (have_irqs) mvchip->chip.to_irq = mvebu_gpio_to_irq; mvchip->chip.base = id * MVEBU_MAX_GPIO_PER_BANK; diff --git a/drivers/gpio/gpio-nomadik.c b/drivers/gpio/gpio-nomadik.c index 296d13845b30..bcf4b07dd458 100644 --- a/drivers/gpio/gpio-nomadik.c +++ b/drivers/gpio/gpio-nomadik.c @@ -674,7 +674,7 @@ static int nmk_gpio_probe(struct platform_device *pdev) chip->direction_input = nmk_gpio_make_input; chip->get = nmk_gpio_get_input; chip->direction_output = nmk_gpio_make_output; - chip->set_rv = nmk_gpio_set_output; + chip->set = nmk_gpio_set_output; chip->dbg_show = nmk_gpio_dbg_show; chip->can_sleep = false; chip->owner = THIS_MODULE; diff --git a/drivers/gpio/gpio-npcm-sgpio.c b/drivers/gpio/gpio-npcm-sgpio.c index 25b203a89e38..83c77a2c0623 100644 --- a/drivers/gpio/gpio-npcm-sgpio.c +++ b/drivers/gpio/gpio-npcm-sgpio.c @@ -211,7 +211,7 @@ static int npcm_sgpio_dir_in(struct gpio_chip *gc, unsigned int offset) static int npcm_sgpio_dir_out(struct gpio_chip *gc, unsigned int offset, int val) { - return gc->set_rv(gc, offset, val); + return gc->set(gc, offset, val); } static int npcm_sgpio_get_direction(struct gpio_chip *gc, unsigned int offset) @@ -546,7 +546,7 @@ static int npcm_sgpio_probe(struct platform_device *pdev) gpio->chip.direction_output = npcm_sgpio_dir_out; gpio->chip.get_direction = npcm_sgpio_get_direction; gpio->chip.get = npcm_sgpio_get; - gpio->chip.set_rv = npcm_sgpio_set; + gpio->chip.set = npcm_sgpio_set; gpio->chip.label = dev_name(&pdev->dev); gpio->chip.base = -1; diff --git a/drivers/gpio/gpio-octeon.c b/drivers/gpio/gpio-octeon.c index 24966161742a..777e20c608dc 100644 --- a/drivers/gpio/gpio-octeon.c +++ b/drivers/gpio/gpio-octeon.c @@ -108,7 +108,7 @@ static int octeon_gpio_probe(struct platform_device *pdev) chip->direction_input = octeon_gpio_dir_in; chip->get = octeon_gpio_get; chip->direction_output = octeon_gpio_dir_out; - chip->set_rv = octeon_gpio_set; + chip->set = octeon_gpio_set; err = devm_gpiochip_add_data(&pdev->dev, chip, gpio); if (err) return err; diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c index ed5c88a5c520..a268c76bdca6 100644 --- a/drivers/gpio/gpio-omap.c +++ b/drivers/gpio/gpio-omap.c @@ -1046,8 +1046,8 @@ static int omap_gpio_chip_init(struct gpio_bank *bank, struct device *pm_dev) bank->chip.get_multiple = omap_gpio_get_multiple; bank->chip.direction_output = omap_gpio_output; bank->chip.set_config = omap_gpio_set_config; - bank->chip.set_rv = omap_gpio_set; - bank->chip.set_multiple_rv = omap_gpio_set_multiple; + bank->chip.set = omap_gpio_set; + bank->chip.set_multiple = omap_gpio_set_multiple; if (bank->is_mpuio) { bank->chip.label = "mpuio"; if (bank->regs->wkup_en) diff --git a/drivers/gpio/gpio-palmas.c b/drivers/gpio/gpio-palmas.c index 9329d8ce8f59..e377f6dd4ccf 100644 --- a/drivers/gpio/gpio-palmas.c +++ b/drivers/gpio/gpio-palmas.c @@ -166,7 +166,7 @@ static int palmas_gpio_probe(struct platform_device *pdev) palmas_gpio->gpio_chip.direction_input = palmas_gpio_input; palmas_gpio->gpio_chip.direction_output = palmas_gpio_output; palmas_gpio->gpio_chip.to_irq = palmas_gpio_to_irq; - palmas_gpio->gpio_chip.set_rv = palmas_gpio_set; + palmas_gpio->gpio_chip.set = palmas_gpio_set; palmas_gpio->gpio_chip.get = palmas_gpio_get; palmas_gpio->gpio_chip.parent = &pdev->dev; diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index 69906a9af7e6..b46927f55038 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -789,10 +789,10 @@ static void pca953x_setup_gpio(struct pca953x_chip *chip, int gpios) gc->direction_input = pca953x_gpio_direction_input; gc->direction_output = pca953x_gpio_direction_output; gc->get = pca953x_gpio_get_value; - gc->set_rv = pca953x_gpio_set_value; + gc->set = pca953x_gpio_set_value; gc->get_direction = pca953x_gpio_get_direction; gc->get_multiple = pca953x_gpio_get_multiple; - gc->set_multiple_rv = pca953x_gpio_set_multiple; + gc->set_multiple = pca953x_gpio_set_multiple; gc->set_config = pca953x_gpio_set_config; gc->can_sleep = true; diff --git a/drivers/gpio/gpio-pca9570.c b/drivers/gpio/gpio-pca9570.c index a33246f20fd8..c5a1287079a0 100644 --- a/drivers/gpio/gpio-pca9570.c +++ b/drivers/gpio/gpio-pca9570.c @@ -126,7 +126,7 @@ static int pca9570_probe(struct i2c_client *client) gpio->chip.owner = THIS_MODULE; gpio->chip.get_direction = pca9570_get_direction; gpio->chip.get = pca9570_get; - gpio->chip.set_rv = pca9570_set; + gpio->chip.set = pca9570_set; gpio->chip.base = -1; gpio->chip_data = device_get_match_data(&client->dev); gpio->chip.ngpio = gpio->chip_data->ngpio; diff --git a/drivers/gpio/gpio-pcf857x.c b/drivers/gpio/gpio-pcf857x.c index a04203680333..3b9de8c3d924 100644 --- a/drivers/gpio/gpio-pcf857x.c +++ b/drivers/gpio/gpio-pcf857x.c @@ -295,8 +295,8 @@ static int pcf857x_probe(struct i2c_client *client) gpio->chip.owner = THIS_MODULE; gpio->chip.get = pcf857x_get; gpio->chip.get_multiple = pcf857x_get_multiple; - gpio->chip.set_rv = pcf857x_set; - gpio->chip.set_multiple_rv = pcf857x_set_multiple; + gpio->chip.set = pcf857x_set; + gpio->chip.set_multiple = pcf857x_set_multiple; gpio->chip.direction_input = pcf857x_input; gpio->chip.direction_output = pcf857x_output; gpio->chip.ngpio = (uintptr_t)i2c_get_match_data(client); diff --git a/drivers/gpio/gpio-pch.c b/drivers/gpio/gpio-pch.c index c6f313342ba0..9925687e05fb 100644 --- a/drivers/gpio/gpio-pch.c +++ b/drivers/gpio/gpio-pch.c @@ -219,7 +219,7 @@ static void pch_gpio_setup(struct pch_gpio *chip) gpio->direction_input = pch_gpio_direction_input; gpio->get = pch_gpio_get; gpio->direction_output = pch_gpio_direction_output; - gpio->set_rv = pch_gpio_set; + gpio->set = pch_gpio_set; gpio->base = -1; gpio->ngpio = gpio_pins[chip->ioh]; gpio->can_sleep = false; diff --git a/drivers/gpio/gpio-pl061.c b/drivers/gpio/gpio-pl061.c index 98cfac4eac85..02e4ffcf5a6f 100644 --- a/drivers/gpio/gpio-pl061.c +++ b/drivers/gpio/gpio-pl061.c @@ -330,7 +330,7 @@ static int pl061_probe(struct amba_device *adev, const struct amba_id *id) pl061->gc.direction_input = pl061_direction_input; pl061->gc.direction_output = pl061_direction_output; pl061->gc.get = pl061_get_value; - pl061->gc.set_rv = pl061_set_value; + pl061->gc.set = pl061_set_value; pl061->gc.ngpio = PL061_GPIO_NR; pl061->gc.label = dev_name(dev); pl061->gc.parent = dev; diff --git a/drivers/gpio/gpio-pxa.c b/drivers/gpio/gpio-pxa.c index cbcdd416f8b9..fa22f3faa163 100644 --- a/drivers/gpio/gpio-pxa.c +++ b/drivers/gpio/gpio-pxa.c @@ -355,7 +355,7 @@ static int pxa_init_gpio_chip(struct pxa_gpio_chip *pchip, int ngpio, void __iom pchip->chip.direction_input = pxa_gpio_direction_input; pchip->chip.direction_output = pxa_gpio_direction_output; pchip->chip.get = pxa_gpio_get; - pchip->chip.set_rv = pxa_gpio_set; + pchip->chip.set = pxa_gpio_set; pchip->chip.to_irq = pxa_gpio_to_irq; pchip->chip.ngpio = ngpio; pchip->chip.request = gpiochip_generic_request; diff --git a/drivers/gpio/gpio-raspberrypi-exp.c b/drivers/gpio/gpio-raspberrypi-exp.c index b4b607515a04..40413e06b69c 100644 --- a/drivers/gpio/gpio-raspberrypi-exp.c +++ b/drivers/gpio/gpio-raspberrypi-exp.c @@ -232,7 +232,7 @@ static int rpi_exp_gpio_probe(struct platform_device *pdev) rpi_gpio->gc.direction_output = rpi_exp_gpio_dir_out; rpi_gpio->gc.get_direction = rpi_exp_gpio_get_direction; rpi_gpio->gc.get = rpi_exp_gpio_get; - rpi_gpio->gc.set_rv = rpi_exp_gpio_set; + rpi_gpio->gc.set = rpi_exp_gpio_set; rpi_gpio->gc.can_sleep = true; return devm_gpiochip_add_data(dev, &rpi_gpio->gc, rpi_gpio); diff --git a/drivers/gpio/gpio-rc5t583.c b/drivers/gpio/gpio-rc5t583.c index cf3e91d235df..5a69e4534591 100644 --- a/drivers/gpio/gpio-rc5t583.c +++ b/drivers/gpio/gpio-rc5t583.c @@ -118,7 +118,7 @@ static int rc5t583_gpio_probe(struct platform_device *pdev) rc5t583_gpio->gpio_chip.free = rc5t583_gpio_free, rc5t583_gpio->gpio_chip.direction_input = rc5t583_gpio_dir_input, rc5t583_gpio->gpio_chip.direction_output = rc5t583_gpio_dir_output, - rc5t583_gpio->gpio_chip.set_rv = rc5t583_gpio_set, + rc5t583_gpio->gpio_chip.set = rc5t583_gpio_set, rc5t583_gpio->gpio_chip.get = rc5t583_gpio_get, rc5t583_gpio->gpio_chip.to_irq = rc5t583_gpio_to_irq, rc5t583_gpio->gpio_chip.ngpio = RC5T583_MAX_GPIO, diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c index cd31580effa9..86777e097fd8 100644 --- a/drivers/gpio/gpio-rcar.c +++ b/drivers/gpio/gpio-rcar.c @@ -535,8 +535,8 @@ static int gpio_rcar_probe(struct platform_device *pdev) gpio_chip->get = gpio_rcar_get; gpio_chip->get_multiple = gpio_rcar_get_multiple; gpio_chip->direction_output = gpio_rcar_direction_output; - gpio_chip->set_rv = gpio_rcar_set; - gpio_chip->set_multiple_rv = gpio_rcar_set_multiple; + gpio_chip->set = gpio_rcar_set; + gpio_chip->set_multiple = gpio_rcar_set_multiple; gpio_chip->label = name; gpio_chip->parent = dev; gpio_chip->owner = THIS_MODULE; diff --git a/drivers/gpio/gpio-rdc321x.c b/drivers/gpio/gpio-rdc321x.c index a75ed8021de5..ba62b81aa8ae 100644 --- a/drivers/gpio/gpio-rdc321x.c +++ b/drivers/gpio/gpio-rdc321x.c @@ -159,7 +159,7 @@ static int rdc321x_gpio_probe(struct platform_device *pdev) rdc321x_gpio_dev->chip.direction_input = rdc_gpio_direction_input; rdc321x_gpio_dev->chip.direction_output = rdc_gpio_config; rdc321x_gpio_dev->chip.get = rdc_gpio_get_value; - rdc321x_gpio_dev->chip.set_rv = rdc_gpio_set_value; + rdc321x_gpio_dev->chip.set = rdc_gpio_set_value; rdc321x_gpio_dev->chip.base = 0; rdc321x_gpio_dev->chip.ngpio = pdata->max_gpios; diff --git a/drivers/gpio/gpio-reg.c b/drivers/gpio/gpio-reg.c index d8da99f97385..f2238196faf1 100644 --- a/drivers/gpio/gpio-reg.c +++ b/drivers/gpio/gpio-reg.c @@ -46,7 +46,7 @@ static int gpio_reg_direction_output(struct gpio_chip *gc, unsigned offset, if (r->direction & BIT(offset)) return -ENOTSUPP; - gc->set_rv(gc, offset, value); + gc->set(gc, offset, value); return 0; } @@ -161,9 +161,9 @@ struct gpio_chip *gpio_reg_init(struct device *dev, void __iomem *reg, r->gc.get_direction = gpio_reg_get_direction; r->gc.direction_input = gpio_reg_direction_input; r->gc.direction_output = gpio_reg_direction_output; - r->gc.set_rv = gpio_reg_set; + r->gc.set = gpio_reg_set; r->gc.get = gpio_reg_get; - r->gc.set_multiple_rv = gpio_reg_set_multiple; + r->gc.set_multiple = gpio_reg_set_multiple; if (irqs) r->gc.to_irq = gpio_reg_to_irq; r->gc.base = base; diff --git a/drivers/gpio/gpio-regmap.c b/drivers/gpio/gpio-regmap.c index 87c4225784cf..e8a32dfebdcb 100644 --- a/drivers/gpio/gpio-regmap.c +++ b/drivers/gpio/gpio-regmap.c @@ -260,9 +260,9 @@ struct gpio_regmap *gpio_regmap_register(const struct gpio_regmap_config *config chip->free = gpiochip_generic_free; chip->get = gpio_regmap_get; if (gpio->reg_set_base && gpio->reg_clr_base) - chip->set_rv = gpio_regmap_set_with_clear; + chip->set = gpio_regmap_set_with_clear; else if (gpio->reg_set_base) - chip->set_rv = gpio_regmap_set; + chip->set = gpio_regmap_set; chip->get_direction = gpio_regmap_get_direction; if (gpio->reg_dir_in_base || gpio->reg_dir_out_base) { diff --git a/drivers/gpio/gpio-rockchip.c b/drivers/gpio/gpio-rockchip.c index ecd60ff9e1dd..bcfc323a8315 100644 --- a/drivers/gpio/gpio-rockchip.c +++ b/drivers/gpio/gpio-rockchip.c @@ -327,7 +327,7 @@ static int rockchip_gpio_to_irq(struct gpio_chip *gc, unsigned int offset) static const struct gpio_chip rockchip_gpiolib_chip = { .request = gpiochip_generic_request, .free = gpiochip_generic_free, - .set_rv = rockchip_gpio_set, + .set = rockchip_gpio_set, .get = rockchip_gpio_get, .get_direction = rockchip_gpio_get_direction, .direction_input = rockchip_gpio_direction_input, diff --git a/drivers/gpio/gpio-rtd.c b/drivers/gpio/gpio-rtd.c index 25bbd749b019..d46b40dd5283 100644 --- a/drivers/gpio/gpio-rtd.c +++ b/drivers/gpio/gpio-rtd.c @@ -565,7 +565,7 @@ static int rtd_gpio_probe(struct platform_device *pdev) data->gpio_chip.get_direction = rtd_gpio_get_direction; data->gpio_chip.direction_input = rtd_gpio_direction_input; data->gpio_chip.direction_output = rtd_gpio_direction_output; - data->gpio_chip.set_rv = rtd_gpio_set; + data->gpio_chip.set = rtd_gpio_set; data->gpio_chip.get = rtd_gpio_get; data->gpio_chip.set_config = rtd_gpio_set_config; data->gpio_chip.parent = dev; diff --git a/drivers/gpio/gpio-sa1100.c b/drivers/gpio/gpio-sa1100.c index e9d054d78ccb..7f6a62f5d1ee 100644 --- a/drivers/gpio/gpio-sa1100.c +++ b/drivers/gpio/gpio-sa1100.c @@ -99,7 +99,7 @@ static struct sa1100_gpio_chip sa1100_gpio_chip = { .get_direction = sa1100_get_direction, .direction_input = sa1100_direction_input, .direction_output = sa1100_direction_output, - .set_rv = sa1100_gpio_set, + .set = sa1100_gpio_set, .get = sa1100_gpio_get, .to_irq = sa1100_to_irq, .base = 0, diff --git a/drivers/gpio/gpio-sama5d2-piobu.c b/drivers/gpio/gpio-sama5d2-piobu.c index c31244cf5e89..5005688f6e67 100644 --- a/drivers/gpio/gpio-sama5d2-piobu.c +++ b/drivers/gpio/gpio-sama5d2-piobu.c @@ -196,7 +196,7 @@ static int sama5d2_piobu_probe(struct platform_device *pdev) piobu->chip.direction_input = sama5d2_piobu_direction_input; piobu->chip.direction_output = sama5d2_piobu_direction_output; piobu->chip.get = sama5d2_piobu_get; - piobu->chip.set_rv = sama5d2_piobu_set; + piobu->chip.set = sama5d2_piobu_set; piobu->chip.base = -1; piobu->chip.ngpio = PIOBU_NUM; piobu->chip.can_sleep = 0; diff --git a/drivers/gpio/gpio-sch.c b/drivers/gpio/gpio-sch.c index 833ffdd98d74..966d16a6d515 100644 --- a/drivers/gpio/gpio-sch.c +++ b/drivers/gpio/gpio-sch.c @@ -167,7 +167,7 @@ static const struct gpio_chip sch_gpio_chip = { .direction_input = sch_gpio_direction_in, .get = sch_gpio_get, .direction_output = sch_gpio_direction_out, - .set_rv = sch_gpio_set, + .set = sch_gpio_set, .get_direction = sch_gpio_get_direction, }; diff --git a/drivers/gpio/gpio-sch311x.c b/drivers/gpio/gpio-sch311x.c index 44fb5fc21fb8..f95566998d30 100644 --- a/drivers/gpio/gpio-sch311x.c +++ b/drivers/gpio/gpio-sch311x.c @@ -297,7 +297,7 @@ static int sch311x_gpio_probe(struct platform_device *pdev) block->chip.get_direction = sch311x_gpio_get_direction; block->chip.set_config = sch311x_gpio_set_config; block->chip.get = sch311x_gpio_get; - block->chip.set_rv = sch311x_gpio_set; + block->chip.set = sch311x_gpio_set; block->chip.ngpio = 8; block->chip.parent = &pdev->dev; block->chip.base = sch311x_gpio_blocks[i].base; diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index 9503296422fd..050092583f79 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -486,9 +486,9 @@ static int gpio_sim_add_bank(struct fwnode_handle *swnode, struct device *dev) gc->parent = dev; gc->fwnode = swnode; gc->get = gpio_sim_get; - gc->set_rv = gpio_sim_set; + gc->set = gpio_sim_set; gc->get_multiple = gpio_sim_get_multiple; - gc->set_multiple_rv = gpio_sim_set_multiple; + gc->set_multiple = gpio_sim_set_multiple; gc->direction_output = gpio_sim_direction_output; gc->direction_input = gpio_sim_direction_input; gc->get_direction = gpio_sim_get_direction; diff --git a/drivers/gpio/gpio-siox.c b/drivers/gpio/gpio-siox.c index 95355dda621b..958034b9f3f3 100644 --- a/drivers/gpio/gpio-siox.c +++ b/drivers/gpio/gpio-siox.c @@ -237,7 +237,7 @@ static int gpio_siox_probe(struct siox_device *sdevice) gc->parent = dev; gc->owner = THIS_MODULE; gc->get = gpio_siox_get; - gc->set_rv = gpio_siox_set; + gc->set = gpio_siox_set; gc->direction_input = gpio_siox_direction_input; gc->direction_output = gpio_siox_direction_output; gc->get_direction = gpio_siox_get_direction; diff --git a/drivers/gpio/gpio-spear-spics.c b/drivers/gpio/gpio-spear-spics.c index 55f0e8afa291..96a0e1211500 100644 --- a/drivers/gpio/gpio-spear-spics.c +++ b/drivers/gpio/gpio-spear-spics.c @@ -140,7 +140,7 @@ static int spics_gpio_probe(struct platform_device *pdev) spics->chip.request = spics_request; spics->chip.free = spics_free; spics->chip.direction_output = spics_direction_output; - spics->chip.set_rv = spics_set_value; + spics->chip.set = spics_set_value; spics->chip.label = dev_name(&pdev->dev); spics->chip.parent = &pdev->dev; spics->chip.owner = THIS_MODULE; diff --git a/drivers/gpio/gpio-sprd.c b/drivers/gpio/gpio-sprd.c index bbd5bf51c088..413bcd0a4240 100644 --- a/drivers/gpio/gpio-sprd.c +++ b/drivers/gpio/gpio-sprd.c @@ -245,7 +245,7 @@ static int sprd_gpio_probe(struct platform_device *pdev) sprd_gpio->chip.request = sprd_gpio_request; sprd_gpio->chip.free = sprd_gpio_free; sprd_gpio->chip.get = sprd_gpio_get; - sprd_gpio->chip.set_rv = sprd_gpio_set; + sprd_gpio->chip.set = sprd_gpio_set; sprd_gpio->chip.direction_input = sprd_gpio_direction_input; sprd_gpio->chip.direction_output = sprd_gpio_direction_output; diff --git a/drivers/gpio/gpio-stmpe.c b/drivers/gpio/gpio-stmpe.c index 0a270156e0be..5dd4c21a8e60 100644 --- a/drivers/gpio/gpio-stmpe.c +++ b/drivers/gpio/gpio-stmpe.c @@ -136,7 +136,7 @@ static const struct gpio_chip template_chip = { .direction_input = stmpe_gpio_direction_input, .get = stmpe_gpio_get, .direction_output = stmpe_gpio_direction_output, - .set_rv = stmpe_gpio_set, + .set = stmpe_gpio_set, .request = stmpe_gpio_request, .can_sleep = true, }; diff --git a/drivers/gpio/gpio-stp-xway.c b/drivers/gpio/gpio-stp-xway.c index fdda8de6ca36..493c027afdd6 100644 --- a/drivers/gpio/gpio-stp-xway.c +++ b/drivers/gpio/gpio-stp-xway.c @@ -249,7 +249,7 @@ static int xway_stp_probe(struct platform_device *pdev) chip->gc.label = "stp-xway"; chip->gc.direction_output = xway_stp_dir_out; chip->gc.get = xway_stp_get; - chip->gc.set_rv = xway_stp_set; + chip->gc.set = xway_stp_set; chip->gc.request = xway_stp_request; chip->gc.base = -1; chip->gc.owner = THIS_MODULE; diff --git a/drivers/gpio/gpio-syscon.c b/drivers/gpio/gpio-syscon.c index f86f78655c24..40064d4cf47f 100644 --- a/drivers/gpio/gpio-syscon.c +++ b/drivers/gpio/gpio-syscon.c @@ -115,7 +115,7 @@ static int syscon_gpio_dir_out(struct gpio_chip *chip, unsigned offset, int val) BIT(offs % SYSCON_REG_BITS)); } - return chip->set_rv(chip, offset, val); + return chip->set(chip, offset, val); } static const struct syscon_gpio_data clps711x_mctrl_gpio = { @@ -251,7 +251,7 @@ static int syscon_gpio_probe(struct platform_device *pdev) if (priv->data->flags & GPIO_SYSCON_FEAT_IN) priv->chip.direction_input = syscon_gpio_dir_in; if (priv->data->flags & GPIO_SYSCON_FEAT_OUT) { - priv->chip.set_rv = priv->data->set ? : syscon_gpio_set; + priv->chip.set = priv->data->set ? : syscon_gpio_set; priv->chip.direction_output = syscon_gpio_dir_out; } diff --git a/drivers/gpio/gpio-tangier.c b/drivers/gpio/gpio-tangier.c index ce17b98e0623..ba5a8ede8912 100644 --- a/drivers/gpio/gpio-tangier.c +++ b/drivers/gpio/gpio-tangier.c @@ -430,7 +430,7 @@ int devm_tng_gpio_probe(struct device *dev, struct tng_gpio *gpio) gpio->chip.direction_input = tng_gpio_direction_input; gpio->chip.direction_output = tng_gpio_direction_output; gpio->chip.get = tng_gpio_get; - gpio->chip.set_rv = tng_gpio_set; + gpio->chip.set = tng_gpio_set; gpio->chip.get_direction = tng_gpio_get_direction; gpio->chip.set_config = tng_gpio_set_config; gpio->chip.base = info->base; diff --git a/drivers/gpio/gpio-tc3589x.c b/drivers/gpio/gpio-tc3589x.c index 0bd32809fd68..90d048f9da08 100644 --- a/drivers/gpio/gpio-tc3589x.c +++ b/drivers/gpio/gpio-tc3589x.c @@ -149,7 +149,7 @@ static const struct gpio_chip template_chip = { .label = "tc3589x", .owner = THIS_MODULE, .get = tc3589x_gpio_get, - .set_rv = tc3589x_gpio_set, + .set = tc3589x_gpio_set, .direction_output = tc3589x_gpio_direction_output, .direction_input = tc3589x_gpio_direction_input, .get_direction = tc3589x_gpio_get_direction, diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c index 126fd12550aa..15a5762a82c2 100644 --- a/drivers/gpio/gpio-tegra.c +++ b/drivers/gpio/gpio-tegra.c @@ -720,7 +720,7 @@ static int tegra_gpio_probe(struct platform_device *pdev) tgi->gc.direction_input = tegra_gpio_direction_input; tgi->gc.get = tegra_gpio_get; tgi->gc.direction_output = tegra_gpio_direction_output; - tgi->gc.set_rv = tegra_gpio_set; + tgi->gc.set = tegra_gpio_set; tgi->gc.get_direction = tegra_gpio_get_direction; tgi->gc.base = 0; tgi->gc.ngpio = tgi->bank_count * 32; diff --git a/drivers/gpio/gpio-tegra186.c b/drivers/gpio/gpio-tegra186.c index f902da15c419..5fd3ec3e2c53 100644 --- a/drivers/gpio/gpio-tegra186.c +++ b/drivers/gpio/gpio-tegra186.c @@ -891,7 +891,7 @@ static int tegra186_gpio_probe(struct platform_device *pdev) gpio->gpio.direction_input = tegra186_gpio_direction_input; gpio->gpio.direction_output = tegra186_gpio_direction_output; gpio->gpio.get = tegra186_gpio_get; - gpio->gpio.set_rv = tegra186_gpio_set; + gpio->gpio.set = tegra186_gpio_set; gpio->gpio.set_config = tegra186_gpio_set_config; gpio->gpio.add_pin_ranges = tegra186_gpio_add_pin_ranges; gpio->gpio.init_valid_mask = tegra186_init_valid_mask; diff --git a/drivers/gpio/gpio-thunderx.c b/drivers/gpio/gpio-thunderx.c index eb6a1f0279c0..be96853063ba 100644 --- a/drivers/gpio/gpio-thunderx.c +++ b/drivers/gpio/gpio-thunderx.c @@ -533,8 +533,8 @@ static int thunderx_gpio_probe(struct pci_dev *pdev, chip->direction_input = thunderx_gpio_dir_in; chip->get = thunderx_gpio_get; chip->direction_output = thunderx_gpio_dir_out; - chip->set_rv = thunderx_gpio_set; - chip->set_multiple_rv = thunderx_gpio_set_multiple; + chip->set = thunderx_gpio_set; + chip->set_multiple = thunderx_gpio_set_multiple; chip->set_config = thunderx_gpio_set_config; girq = &chip->irq; gpio_irq_chip_set_chip(girq, &thunderx_gpio_irq_chip); diff --git a/drivers/gpio/gpio-timberdale.c b/drivers/gpio/gpio-timberdale.c index fbb883089189..679e27f00ff6 100644 --- a/drivers/gpio/gpio-timberdale.c +++ b/drivers/gpio/gpio-timberdale.c @@ -253,7 +253,7 @@ static int timbgpio_probe(struct platform_device *pdev) gc->direction_input = timbgpio_gpio_direction_input; gc->get = timbgpio_gpio_get; gc->direction_output = timbgpio_gpio_direction_output; - gc->set_rv = timbgpio_gpio_set; + gc->set = timbgpio_gpio_set; gc->to_irq = (irq >= 0 && tgpio->irq_base > 0) ? timbgpio_to_irq : NULL; gc->dbg_show = NULL; gc->base = pdata->gpio_base; diff --git a/drivers/gpio/gpio-tpic2810.c b/drivers/gpio/gpio-tpic2810.c index d5b8568ab061..866ff2d436d5 100644 --- a/drivers/gpio/gpio-tpic2810.c +++ b/drivers/gpio/gpio-tpic2810.c @@ -80,8 +80,8 @@ static const struct gpio_chip template_chip = { .owner = THIS_MODULE, .get_direction = tpic2810_get_direction, .direction_output = tpic2810_direction_output, - .set_rv = tpic2810_set, - .set_multiple_rv = tpic2810_set_multiple, + .set = tpic2810_set, + .set_multiple = tpic2810_set_multiple, .base = -1, .ngpio = 8, .can_sleep = true, diff --git a/drivers/gpio/gpio-tps65086.c b/drivers/gpio/gpio-tps65086.c index 08fa061b73ef..84b17b83476f 100644 --- a/drivers/gpio/gpio-tps65086.c +++ b/drivers/gpio/gpio-tps65086.c @@ -69,7 +69,7 @@ static const struct gpio_chip template_chip = { .direction_input = tps65086_gpio_direction_input, .direction_output = tps65086_gpio_direction_output, .get = tps65086_gpio_get, - .set_rv = tps65086_gpio_set, + .set = tps65086_gpio_set, .base = -1, .ngpio = 4, .can_sleep = true, diff --git a/drivers/gpio/gpio-tps65218.c b/drivers/gpio/gpio-tps65218.c index 49cd7754ed05..3b4c41f5ef55 100644 --- a/drivers/gpio/gpio-tps65218.c +++ b/drivers/gpio/gpio-tps65218.c @@ -169,7 +169,7 @@ static const struct gpio_chip template_chip = { .request = tps65218_gpio_request, .direction_output = tps65218_gpio_output, .get = tps65218_gpio_get, - .set_rv = tps65218_gpio_set, + .set = tps65218_gpio_set, .set_config = tps65218_gpio_set_config, .can_sleep = true, .ngpio = 3, diff --git a/drivers/gpio/gpio-tps65219.c b/drivers/gpio/gpio-tps65219.c index c0177088c54c..158f63bcf10c 100644 --- a/drivers/gpio/gpio-tps65219.c +++ b/drivers/gpio/gpio-tps65219.c @@ -203,7 +203,7 @@ static const struct gpio_chip tps65214_template_chip = { .direction_input = tps65219_gpio_direction_input, .direction_output = tps65219_gpio_direction_output, .get = tps65219_gpio_get, - .set_rv = tps65219_gpio_set, + .set = tps65219_gpio_set, .base = -1, .ngpio = 2, .can_sleep = true, @@ -216,7 +216,7 @@ static const struct gpio_chip tps65219_template_chip = { .direction_input = tps65219_gpio_direction_input, .direction_output = tps65219_gpio_direction_output, .get = tps65219_gpio_get, - .set_rv = tps65219_gpio_set, + .set = tps65219_gpio_set, .base = -1, .ngpio = 3, .can_sleep = true, diff --git a/drivers/gpio/gpio-tps6586x.c b/drivers/gpio/gpio-tps6586x.c index f1ced092f38a..aaacbb54bf5d 100644 --- a/drivers/gpio/gpio-tps6586x.c +++ b/drivers/gpio/gpio-tps6586x.c @@ -98,7 +98,7 @@ static int tps6586x_gpio_probe(struct platform_device *pdev) /* FIXME: add handling of GPIOs as dedicated inputs */ tps6586x_gpio->gpio_chip.direction_output = tps6586x_gpio_output; - tps6586x_gpio->gpio_chip.set_rv = tps6586x_gpio_set; + tps6586x_gpio->gpio_chip.set = tps6586x_gpio_set; tps6586x_gpio->gpio_chip.get = tps6586x_gpio_get; tps6586x_gpio->gpio_chip.to_irq = tps6586x_gpio_to_irq; diff --git a/drivers/gpio/gpio-tps65910.c b/drivers/gpio/gpio-tps65910.c index 3204f55394cf..25e9f41efe78 100644 --- a/drivers/gpio/gpio-tps65910.c +++ b/drivers/gpio/gpio-tps65910.c @@ -139,7 +139,7 @@ static int tps65910_gpio_probe(struct platform_device *pdev) tps65910_gpio->gpio_chip.can_sleep = true; tps65910_gpio->gpio_chip.direction_input = tps65910_gpio_input; tps65910_gpio->gpio_chip.direction_output = tps65910_gpio_output; - tps65910_gpio->gpio_chip.set_rv = tps65910_gpio_set; + tps65910_gpio->gpio_chip.set = tps65910_gpio_set; tps65910_gpio->gpio_chip.get = tps65910_gpio_get; tps65910_gpio->gpio_chip.parent = &pdev->dev; diff --git a/drivers/gpio/gpio-tps65912.c b/drivers/gpio/gpio-tps65912.c index d586ccfbfc56..7a2c5685c2fd 100644 --- a/drivers/gpio/gpio-tps65912.c +++ b/drivers/gpio/gpio-tps65912.c @@ -92,7 +92,7 @@ static const struct gpio_chip template_chip = { .direction_input = tps65912_gpio_direction_input, .direction_output = tps65912_gpio_direction_output, .get = tps65912_gpio_get, - .set_rv = tps65912_gpio_set, + .set = tps65912_gpio_set, .base = -1, .ngpio = 5, .can_sleep = true, diff --git a/drivers/gpio/gpio-tps68470.c b/drivers/gpio/gpio-tps68470.c index 3b8805c854f7..d4fbdf90e190 100644 --- a/drivers/gpio/gpio-tps68470.c +++ b/drivers/gpio/gpio-tps68470.c @@ -142,7 +142,7 @@ static int tps68470_gpio_probe(struct platform_device *pdev) tps68470_gpio->gc.direction_output = tps68470_gpio_output; tps68470_gpio->gc.get = tps68470_gpio_get; tps68470_gpio->gc.get_direction = tps68470_gpio_get_direction; - tps68470_gpio->gc.set_rv = tps68470_gpio_set; + tps68470_gpio->gc.set = tps68470_gpio_set; tps68470_gpio->gc.can_sleep = true; tps68470_gpio->gc.names = tps68470_names; tps68470_gpio->gc.ngpio = TPS68470_N_GPIO; diff --git a/drivers/gpio/gpio-tqmx86.c b/drivers/gpio/gpio-tqmx86.c index 056799ecce6a..27dd09273292 100644 --- a/drivers/gpio/gpio-tqmx86.c +++ b/drivers/gpio/gpio-tqmx86.c @@ -370,7 +370,7 @@ static int tqmx86_gpio_probe(struct platform_device *pdev) chip->direction_output = tqmx86_gpio_direction_output; chip->get_direction = tqmx86_gpio_get_direction; chip->get = tqmx86_gpio_get; - chip->set_rv = tqmx86_gpio_set; + chip->set = tqmx86_gpio_set; chip->ngpio = TQMX86_NGPIO; chip->parent = pdev->dev.parent; diff --git a/drivers/gpio/gpio-ts4900.c b/drivers/gpio/gpio-ts4900.c index 35dd2d09b4d4..d9ee8fc77ccd 100644 --- a/drivers/gpio/gpio-ts4900.c +++ b/drivers/gpio/gpio-ts4900.c @@ -119,7 +119,7 @@ static const struct gpio_chip template_chip = { .direction_input = ts4900_gpio_direction_input, .direction_output = ts4900_gpio_direction_output, .get = ts4900_gpio_get, - .set_rv = ts4900_gpio_set, + .set = ts4900_gpio_set, .base = -1, .can_sleep = true, }; diff --git a/drivers/gpio/gpio-ts5500.c b/drivers/gpio/gpio-ts5500.c index bb432ed73698..3c7f2efe10fd 100644 --- a/drivers/gpio/gpio-ts5500.c +++ b/drivers/gpio/gpio-ts5500.c @@ -340,7 +340,7 @@ static int ts5500_dio_probe(struct platform_device *pdev) priv->gpio_chip.direction_input = ts5500_gpio_input; priv->gpio_chip.direction_output = ts5500_gpio_output; priv->gpio_chip.get = ts5500_gpio_get; - priv->gpio_chip.set_rv = ts5500_gpio_set; + priv->gpio_chip.set = ts5500_gpio_set; priv->gpio_chip.to_irq = ts5500_gpio_to_irq; priv->gpio_chip.base = -1; diff --git a/drivers/gpio/gpio-twl4030.c b/drivers/gpio/gpio-twl4030.c index e39e39e3ef85..a33dc7c7e7a0 100644 --- a/drivers/gpio/gpio-twl4030.c +++ b/drivers/gpio/gpio-twl4030.c @@ -419,7 +419,7 @@ static const struct gpio_chip template_chip = { .direction_output = twl_direction_out, .get_direction = twl_get_direction, .get = twl_get, - .set_rv = twl_set, + .set = twl_set, .to_irq = twl_to_irq, .can_sleep = true, }; diff --git a/drivers/gpio/gpio-twl6040.c b/drivers/gpio/gpio-twl6040.c index b2196b62b528..4ec9bcd40439 100644 --- a/drivers/gpio/gpio-twl6040.c +++ b/drivers/gpio/gpio-twl6040.c @@ -69,7 +69,7 @@ static struct gpio_chip twl6040gpo_chip = { .get = twl6040gpo_get, .direction_output = twl6040gpo_direction_out, .get_direction = twl6040gpo_get_direction, - .set_rv = twl6040gpo_set, + .set = twl6040gpo_set, .can_sleep = true, }; diff --git a/drivers/gpio/gpio-uniphier.c b/drivers/gpio/gpio-uniphier.c index 8939556f42b6..197bb1d22b3c 100644 --- a/drivers/gpio/gpio-uniphier.c +++ b/drivers/gpio/gpio-uniphier.c @@ -386,8 +386,8 @@ static int uniphier_gpio_probe(struct platform_device *pdev) chip->direction_input = uniphier_gpio_direction_input; chip->direction_output = uniphier_gpio_direction_output; chip->get = uniphier_gpio_get; - chip->set_rv = uniphier_gpio_set; - chip->set_multiple_rv = uniphier_gpio_set_multiple; + chip->set = uniphier_gpio_set; + chip->set_multiple = uniphier_gpio_set_multiple; chip->to_irq = uniphier_gpio_to_irq; chip->base = -1; chip->ngpio = ngpios; diff --git a/drivers/gpio/gpio-viperboard.c b/drivers/gpio/gpio-viperboard.c index e8e906b54d51..15e495c109d2 100644 --- a/drivers/gpio/gpio-viperboard.c +++ b/drivers/gpio/gpio-viperboard.c @@ -408,7 +408,7 @@ static int vprbrd_gpio_probe(struct platform_device *pdev) vb_gpio->gpioa.base = -1; vb_gpio->gpioa.ngpio = 16; vb_gpio->gpioa.can_sleep = true; - vb_gpio->gpioa.set_rv = vprbrd_gpioa_set; + vb_gpio->gpioa.set = vprbrd_gpioa_set; vb_gpio->gpioa.get = vprbrd_gpioa_get; vb_gpio->gpioa.direction_input = vprbrd_gpioa_direction_input; vb_gpio->gpioa.direction_output = vprbrd_gpioa_direction_output; @@ -424,7 +424,7 @@ static int vprbrd_gpio_probe(struct platform_device *pdev) vb_gpio->gpiob.base = -1; vb_gpio->gpiob.ngpio = 16; vb_gpio->gpiob.can_sleep = true; - vb_gpio->gpiob.set_rv = vprbrd_gpiob_set; + vb_gpio->gpiob.set = vprbrd_gpiob_set; vb_gpio->gpiob.get = vprbrd_gpiob_get; vb_gpio->gpiob.direction_input = vprbrd_gpiob_direction_input; vb_gpio->gpiob.direction_output = vprbrd_gpiob_direction_output; diff --git a/drivers/gpio/gpio-virtio.c b/drivers/gpio/gpio-virtio.c index 07552611da98..17e040991e46 100644 --- a/drivers/gpio/gpio-virtio.c +++ b/drivers/gpio/gpio-virtio.c @@ -567,7 +567,7 @@ static int virtio_gpio_probe(struct virtio_device *vdev) vgpio->gc.direction_input = virtio_gpio_direction_input; vgpio->gc.direction_output = virtio_gpio_direction_output; vgpio->gc.get = virtio_gpio_get; - vgpio->gc.set_rv = virtio_gpio_set; + vgpio->gc.set = virtio_gpio_set; vgpio->gc.ngpio = ngpio; vgpio->gc.base = -1; /* Allocate base dynamically */ vgpio->gc.label = dev_name(dev); diff --git a/drivers/gpio/gpio-vx855.c b/drivers/gpio/gpio-vx855.c index a3bceac7854c..84b3a973a503 100644 --- a/drivers/gpio/gpio-vx855.c +++ b/drivers/gpio/gpio-vx855.c @@ -216,7 +216,7 @@ static void vx855gpio_gpio_setup(struct vx855_gpio *vg) c->direction_input = vx855gpio_direction_input; c->direction_output = vx855gpio_direction_output; c->get = vx855gpio_get; - c->set_rv = vx855gpio_set; + c->set = vx855gpio_set; c->set_config = vx855gpio_set_config; c->dbg_show = NULL; c->base = 0; diff --git a/drivers/gpio/gpio-wcd934x.c b/drivers/gpio/gpio-wcd934x.c index c89da9a22016..4af504c23e6f 100644 --- a/drivers/gpio/gpio-wcd934x.c +++ b/drivers/gpio/gpio-wcd934x.c @@ -98,7 +98,7 @@ static int wcd_gpio_probe(struct platform_device *pdev) chip->direction_output = wcd_gpio_direction_output; chip->get_direction = wcd_gpio_get_direction; chip->get = wcd_gpio_get; - chip->set_rv = wcd_gpio_set; + chip->set = wcd_gpio_set; chip->parent = dev; chip->base = -1; chip->ngpio = WCD934X_NPINS; diff --git a/drivers/gpio/gpio-wcove.c b/drivers/gpio/gpio-wcove.c index f7df3d5fc71c..4a5e20e936a9 100644 --- a/drivers/gpio/gpio-wcove.c +++ b/drivers/gpio/gpio-wcove.c @@ -439,7 +439,7 @@ static int wcove_gpio_probe(struct platform_device *pdev) wg->chip.direction_output = wcove_gpio_dir_out; wg->chip.get_direction = wcove_gpio_get_direction; wg->chip.get = wcove_gpio_get; - wg->chip.set_rv = wcove_gpio_set; + wg->chip.set = wcove_gpio_set; wg->chip.set_config = wcove_gpio_set_config; wg->chip.base = -1; wg->chip.ngpio = WCOVE_VGPIO_NUM; diff --git a/drivers/gpio/gpio-winbond.c b/drivers/gpio/gpio-winbond.c index 421655b5d4c2..dcfda738fd69 100644 --- a/drivers/gpio/gpio-winbond.c +++ b/drivers/gpio/gpio-winbond.c @@ -494,7 +494,7 @@ static struct gpio_chip winbond_gpio_chip = { .can_sleep = true, .get = winbond_gpio_get, .direction_input = winbond_gpio_direction_in, - .set_rv = winbond_gpio_set, + .set = winbond_gpio_set, .direction_output = winbond_gpio_direction_out, }; diff --git a/drivers/gpio/gpio-wm831x.c b/drivers/gpio/gpio-wm831x.c index ab58aa7c0b99..f03c0e808fab 100644 --- a/drivers/gpio/gpio-wm831x.c +++ b/drivers/gpio/gpio-wm831x.c @@ -253,7 +253,7 @@ static const struct gpio_chip template_chip = { .direction_input = wm831x_gpio_direction_in, .get = wm831x_gpio_get, .direction_output = wm831x_gpio_direction_out, - .set_rv = wm831x_gpio_set, + .set = wm831x_gpio_set, .to_irq = wm831x_gpio_to_irq, .set_config = wm831x_set_config, .dbg_show = wm831x_gpio_dbg_show, diff --git a/drivers/gpio/gpio-wm8350.c b/drivers/gpio/gpio-wm8350.c index 9a7677f841fc..46923b23a72e 100644 --- a/drivers/gpio/gpio-wm8350.c +++ b/drivers/gpio/gpio-wm8350.c @@ -93,7 +93,7 @@ static const struct gpio_chip template_chip = { .direction_input = wm8350_gpio_direction_in, .get = wm8350_gpio_get, .direction_output = wm8350_gpio_direction_out, - .set_rv = wm8350_gpio_set, + .set = wm8350_gpio_set, .to_irq = wm8350_gpio_to_irq, .can_sleep = true, }; diff --git a/drivers/gpio/gpio-wm8994.c b/drivers/gpio/gpio-wm8994.c index ccc005628dd2..df47a27f508d 100644 --- a/drivers/gpio/gpio-wm8994.c +++ b/drivers/gpio/gpio-wm8994.c @@ -256,7 +256,7 @@ static const struct gpio_chip template_chip = { .direction_input = wm8994_gpio_direction_in, .get = wm8994_gpio_get, .direction_output = wm8994_gpio_direction_out, - .set_rv = wm8994_gpio_set, + .set = wm8994_gpio_set, .set_config = wm8994_gpio_set_config, .to_irq = wm8994_gpio_to_irq, .dbg_show = wm8994_gpio_dbg_show, diff --git a/drivers/gpio/gpio-xgene.c b/drivers/gpio/gpio-xgene.c index 28f794e5eb26..4f627de3f56c 100644 --- a/drivers/gpio/gpio-xgene.c +++ b/drivers/gpio/gpio-xgene.c @@ -178,7 +178,7 @@ static int xgene_gpio_probe(struct platform_device *pdev) gpio->chip.direction_input = xgene_gpio_dir_in; gpio->chip.direction_output = xgene_gpio_dir_out; gpio->chip.get = xgene_gpio_get; - gpio->chip.set_rv = xgene_gpio_set; + gpio->chip.set = xgene_gpio_set; gpio->chip.label = dev_name(&pdev->dev); gpio->chip.base = -1; diff --git a/drivers/gpio/gpio-xilinx.c b/drivers/gpio/gpio-xilinx.c index 36d91cacc2d9..83675ac81077 100644 --- a/drivers/gpio/gpio-xilinx.c +++ b/drivers/gpio/gpio-xilinx.c @@ -604,10 +604,10 @@ static int xgpio_probe(struct platform_device *pdev) chip->gc.direction_input = xgpio_dir_in; chip->gc.direction_output = xgpio_dir_out; chip->gc.get = xgpio_get; - chip->gc.set_rv = xgpio_set; + chip->gc.set = xgpio_set; chip->gc.request = xgpio_request; chip->gc.free = xgpio_free; - chip->gc.set_multiple_rv = xgpio_set_multiple; + chip->gc.set_multiple = xgpio_set_multiple; chip->gc.label = dev_name(dev); diff --git a/drivers/gpio/gpio-xlp.c b/drivers/gpio/gpio-xlp.c index bcd2dfec462d..aede6324387f 100644 --- a/drivers/gpio/gpio-xlp.c +++ b/drivers/gpio/gpio-xlp.c @@ -274,7 +274,7 @@ static int xlp_gpio_probe(struct platform_device *pdev) gc->ngpio = 70; gc->direction_output = xlp_gpio_dir_output; gc->direction_input = xlp_gpio_dir_input; - gc->set_rv = xlp_gpio_set; + gc->set = xlp_gpio_set; gc->get = xlp_gpio_get; spin_lock_init(&priv->lock); diff --git a/drivers/gpio/gpio-xra1403.c b/drivers/gpio/gpio-xra1403.c index 70402c6b5407..faadcb4b0b2d 100644 --- a/drivers/gpio/gpio-xra1403.c +++ b/drivers/gpio/gpio-xra1403.c @@ -164,7 +164,7 @@ static int xra1403_probe(struct spi_device *spi) xra->chip.direction_output = xra1403_direction_output; xra->chip.get_direction = xra1403_get_direction; xra->chip.get = xra1403_get; - xra->chip.set_rv = xra1403_set; + xra->chip.set = xra1403_set; xra->chip.dbg_show = xra1403_dbg_show; diff --git a/drivers/gpio/gpio-xtensa.c b/drivers/gpio/gpio-xtensa.c index e7ff3c60324d..4418947a10e5 100644 --- a/drivers/gpio/gpio-xtensa.c +++ b/drivers/gpio/gpio-xtensa.c @@ -132,7 +132,7 @@ static struct gpio_chip expstate_chip = { .ngpio = 32, .get_direction = xtensa_expstate_get_direction, .get = xtensa_expstate_get_value, - .set_rv = xtensa_expstate_set_value, + .set = xtensa_expstate_set_value, }; static int xtensa_gpio_probe(struct platform_device *pdev) diff --git a/drivers/gpio/gpio-zevio.c b/drivers/gpio/gpio-zevio.c index 0799f7976710..29375bea2289 100644 --- a/drivers/gpio/gpio-zevio.c +++ b/drivers/gpio/gpio-zevio.c @@ -161,7 +161,7 @@ static int zevio_gpio_to_irq(struct gpio_chip *chip, unsigned pin) static const struct gpio_chip zevio_gpio_chip = { .direction_input = zevio_gpio_direction_input, .direction_output = zevio_gpio_direction_output, - .set_rv = zevio_gpio_set, + .set = zevio_gpio_set, .get = zevio_gpio_get, .to_irq = zevio_gpio_to_irq, .base = 0, diff --git a/drivers/gpio/gpio-zynq.c b/drivers/gpio/gpio-zynq.c index b22b4e25c68d..0ffd76e8951f 100644 --- a/drivers/gpio/gpio-zynq.c +++ b/drivers/gpio/gpio-zynq.c @@ -932,7 +932,7 @@ static int zynq_gpio_probe(struct platform_device *pdev) chip->owner = THIS_MODULE; chip->parent = &pdev->dev; chip->get = zynq_gpio_get_value; - chip->set_rv = zynq_gpio_set_value; + chip->set = zynq_gpio_set_value; chip->request = zynq_gpio_request; chip->free = zynq_gpio_free; chip->direction_input = zynq_gpio_dir_in; diff --git a/drivers/gpio/gpio-zynqmp-modepin.c b/drivers/gpio/gpio-zynqmp-modepin.c index 6dc5d7acb89c..5e651482e985 100644 --- a/drivers/gpio/gpio-zynqmp-modepin.c +++ b/drivers/gpio/gpio-zynqmp-modepin.c @@ -130,7 +130,7 @@ static int modepin_gpio_probe(struct platform_device *pdev) chip->owner = THIS_MODULE; chip->parent = &pdev->dev; chip->get = modepin_gpio_get_value; - chip->set_rv = modepin_gpio_set_value; + chip->set = modepin_gpio_set_value; chip->direction_input = modepin_gpio_dir_in; chip->direction_output = modepin_gpio_dir_out; chip->label = dev_name(&pdev->dev); diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 9ac4c23d656a..0d2b470a252e 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -2886,10 +2886,10 @@ static int gpiochip_set(struct gpio_chip *gc, unsigned int offset, int value) lockdep_assert_held(&gc->gpiodev->srcu); - if (WARN_ON(unlikely(!gc->set_rv))) + if (WARN_ON(unlikely(!gc->set))) return -EOPNOTSUPP; - ret = gc->set_rv(gc, offset, value); + ret = gc->set(gc, offset, value); if (ret > 0) ret = -EBADE; @@ -2909,7 +2909,7 @@ static int gpiod_direction_output_raw_commit(struct gpio_desc *desc, int value) * output-only, but if there is then not even a .set() operation it * is pretty tricky to drive the output line. */ - if (!guard.gc->set_rv && !guard.gc->direction_output) { + if (!guard.gc->set && !guard.gc->direction_output) { gpiod_warn(desc, "%s: missing set() and direction_output() operations\n", __func__); @@ -3655,8 +3655,8 @@ static int gpiochip_set_multiple(struct gpio_chip *gc, lockdep_assert_held(&gc->gpiodev->srcu); - if (gc->set_multiple_rv) { - ret = gc->set_multiple_rv(gc, mask, bits); + if (gc->set_multiple) { + ret = gc->set_multiple(gc, mask, bits); if (ret > 0) ret = -EBADE; diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index e3a8c0c0c945..464390372b34 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -1836,7 +1836,7 @@ static int ti_sn_gpio_probe(struct auxiliary_device *adev, pdata->gchip.direction_input = ti_sn_bridge_gpio_direction_input; pdata->gchip.direction_output = ti_sn_bridge_gpio_direction_output; pdata->gchip.get = ti_sn_bridge_gpio_get; - pdata->gchip.set_rv = ti_sn_bridge_gpio_set; + pdata->gchip.set = ti_sn_bridge_gpio_set; pdata->gchip.can_sleep = true; pdata->gchip.names = ti_sn_bridge_gpio_names; pdata->gchip.ngpio = SN_NUM_GPIOS; diff --git a/drivers/hid/hid-cp2112.c b/drivers/hid/hid-cp2112.c index 234fa82eab07..482f62a78c41 100644 --- a/drivers/hid/hid-cp2112.c +++ b/drivers/hid/hid-cp2112.c @@ -1288,7 +1288,7 @@ static int cp2112_probe(struct hid_device *hdev, const struct hid_device_id *id) dev->gc.label = "cp2112_gpio"; dev->gc.direction_input = cp2112_gpio_direction_input; dev->gc.direction_output = cp2112_gpio_direction_output; - dev->gc.set_rv = cp2112_gpio_set; + dev->gc.set = cp2112_gpio_set; dev->gc.get = cp2112_gpio_get; dev->gc.base = -1; dev->gc.ngpio = CP2112_GPIO_MAX_GPIO; diff --git a/drivers/hid/hid-mcp2200.c b/drivers/hid/hid-mcp2200.c index e6ea0a2140eb..dafdd5b4a079 100644 --- a/drivers/hid/hid-mcp2200.c +++ b/drivers/hid/hid-mcp2200.c @@ -279,8 +279,8 @@ static const struct gpio_chip template_chip = { .get_direction = mcp_get_direction, .direction_input = mcp_direction_input, .direction_output = mcp_direction_output, - .set_rv = mcp_set, - .set_multiple_rv = mcp_set_multiple, + .set = mcp_set, + .set_multiple = mcp_set_multiple, .get = mcp_get, .get_multiple = mcp_get_multiple, .base = -1, diff --git a/drivers/hid/hid-mcp2221.c b/drivers/hid/hid-mcp2221.c index fcfe9370a887..475ac352df30 100644 --- a/drivers/hid/hid-mcp2221.c +++ b/drivers/hid/hid-mcp2221.c @@ -1298,7 +1298,7 @@ static int mcp2221_probe(struct hid_device *hdev, mcp->gc->direction_input = mcp_gpio_direction_input; mcp->gc->direction_output = mcp_gpio_direction_output; mcp->gc->get_direction = mcp_gpio_get_direction; - mcp->gc->set_rv = mcp_gpio_set; + mcp->gc->set = mcp_gpio_set; mcp->gc->get = mcp_gpio_get; mcp->gc->ngpio = MCP_NGPIO; mcp->gc->base = -1; diff --git a/drivers/hwmon/ltc2992.c b/drivers/hwmon/ltc2992.c index a07e2eb93c71..1fcd320d6161 100644 --- a/drivers/hwmon/ltc2992.c +++ b/drivers/hwmon/ltc2992.c @@ -339,8 +339,8 @@ static int ltc2992_config_gpio(struct ltc2992_state *st) st->gc.ngpio = ARRAY_SIZE(st->gpio_names); st->gc.get = ltc2992_gpio_get; st->gc.get_multiple = ltc2992_gpio_get_multiple; - st->gc.set_rv = ltc2992_gpio_set; - st->gc.set_multiple_rv = ltc2992_gpio_set_multiple; + st->gc.set = ltc2992_gpio_set; + st->gc.set_multiple = ltc2992_gpio_set_multiple; ret = devm_gpiochip_add_data(&st->client->dev, &st->gc, st); if (ret) diff --git a/drivers/hwmon/pmbus/ucd9000.c b/drivers/hwmon/pmbus/ucd9000.c index 52d4000902d5..55e7af3a5f98 100644 --- a/drivers/hwmon/pmbus/ucd9000.c +++ b/drivers/hwmon/pmbus/ucd9000.c @@ -364,7 +364,7 @@ static void ucd9000_probe_gpio(struct i2c_client *client, data->gpio.direction_input = ucd9000_gpio_direction_input; data->gpio.direction_output = ucd9000_gpio_direction_output; data->gpio.get = ucd9000_gpio_get; - data->gpio.set_rv = ucd9000_gpio_set; + data->gpio.set = ucd9000_gpio_set; data->gpio.can_sleep = true; data->gpio.base = -1; data->gpio.parent = &client->dev; diff --git a/drivers/i2c/muxes/i2c-mux-ltc4306.c b/drivers/i2c/muxes/i2c-mux-ltc4306.c index c688af270a11..50fbc0d06e62 100644 --- a/drivers/i2c/muxes/i2c-mux-ltc4306.c +++ b/drivers/i2c/muxes/i2c-mux-ltc4306.c @@ -164,7 +164,7 @@ static int ltc4306_gpio_init(struct ltc4306 *data) data->gpiochip.direction_input = ltc4306_gpio_direction_input; data->gpiochip.direction_output = ltc4306_gpio_direction_output; data->gpiochip.get = ltc4306_gpio_get; - data->gpiochip.set_rv = ltc4306_gpio_set; + data->gpiochip.set = ltc4306_gpio_set; data->gpiochip.set_config = ltc4306_gpio_set_config; data->gpiochip.owner = THIS_MODULE; diff --git a/drivers/iio/adc/ad4130.c b/drivers/iio/adc/ad4130.c index 6cf790ff3eb5..dcdb5778f7d6 100644 --- a/drivers/iio/adc/ad4130.c +++ b/drivers/iio/adc/ad4130.c @@ -2064,7 +2064,7 @@ static int ad4130_probe(struct spi_device *spi) st->gc.can_sleep = true; st->gc.init_valid_mask = ad4130_gpio_init_valid_mask; st->gc.get_direction = ad4130_gpio_get_direction; - st->gc.set_rv = ad4130_gpio_set; + st->gc.set = ad4130_gpio_set; ret = devm_gpiochip_add_data(dev, &st->gc, st); if (ret) diff --git a/drivers/iio/adc/ad4170-4.c b/drivers/iio/adc/ad4170-4.c index 6cd84d6fb08b..efaed92191f1 100644 --- a/drivers/iio/adc/ad4170-4.c +++ b/drivers/iio/adc/ad4170-4.c @@ -1807,7 +1807,7 @@ static int ad4170_gpio_init(struct iio_dev *indio_dev) st->gpiochip.direction_input = ad4170_gpio_direction_input; st->gpiochip.direction_output = ad4170_gpio_direction_output; st->gpiochip.get = ad4170_gpio_get; - st->gpiochip.set_rv = ad4170_gpio_set; + st->gpiochip.set = ad4170_gpio_set; st->gpiochip.owner = THIS_MODULE; return devm_gpiochip_add_data(&st->spi->dev, &st->gpiochip, indio_dev); diff --git a/drivers/iio/adc/ad7768-1.c b/drivers/iio/adc/ad7768-1.c index a2e061f0cb08..ca8fa91796ca 100644 --- a/drivers/iio/adc/ad7768-1.c +++ b/drivers/iio/adc/ad7768-1.c @@ -673,7 +673,7 @@ static int ad7768_gpio_init(struct iio_dev *indio_dev) .direction_input = ad7768_gpio_direction_input, .direction_output = ad7768_gpio_direction_output, .get = ad7768_gpio_get, - .set_rv = ad7768_gpio_set, + .set = ad7768_gpio_set, .owner = THIS_MODULE, }; diff --git a/drivers/iio/adc/rohm-bd79124.c b/drivers/iio/adc/rohm-bd79124.c index bb7c93ae4055..06c55c8da93f 100644 --- a/drivers/iio/adc/rohm-bd79124.c +++ b/drivers/iio/adc/rohm-bd79124.c @@ -246,8 +246,8 @@ static int bd79124_init_valid_mask(struct gpio_chip *gc, static const struct gpio_chip bd79124gpo_chip = { .label = "bd79124-gpo", .get_direction = bd79124gpo_direction_get, - .set_rv = bd79124gpo_set, - .set_multiple_rv = bd79124gpo_set_multiple, + .set = bd79124gpo_set, + .set_multiple = bd79124gpo_set_multiple, .init_valid_mask = bd79124_init_valid_mask, .can_sleep = true, .ngpio = 8, diff --git a/drivers/iio/adc/ti-ads7950.c b/drivers/iio/adc/ti-ads7950.c index 0356ccf23fea..bbe1ce577789 100644 --- a/drivers/iio/adc/ti-ads7950.c +++ b/drivers/iio/adc/ti-ads7950.c @@ -648,7 +648,7 @@ static int ti_ads7950_probe(struct spi_device *spi) st->chip.direction_input = ti_ads7950_direction_input; st->chip.direction_output = ti_ads7950_direction_output; st->chip.get = ti_ads7950_get; - st->chip.set_rv = ti_ads7950_set; + st->chip.set = ti_ads7950_set; ret = gpiochip_add_data(&st->chip, st); if (ret) { diff --git a/drivers/iio/addac/ad74115.c b/drivers/iio/addac/ad74115.c index 4d8b64048e4f..f8b04d86b01f 100644 --- a/drivers/iio/addac/ad74115.c +++ b/drivers/iio/addac/ad74115.c @@ -1577,7 +1577,7 @@ static int ad74115_setup_gpio_chip(struct ad74115_state *st) .direction_input = ad74115_gpio_direction_input, .direction_output = ad74115_gpio_direction_output, .get = ad74115_gpio_get, - .set_rv = ad74115_gpio_set, + .set = ad74115_gpio_set, }; return devm_gpiochip_add_data(dev, &st->gc, st); diff --git a/drivers/iio/addac/ad74413r.c b/drivers/iio/addac/ad74413r.c index a0bb1dbcb7ad..a20b4d48c5f7 100644 --- a/drivers/iio/addac/ad74413r.c +++ b/drivers/iio/addac/ad74413r.c @@ -1425,8 +1425,8 @@ static int ad74413r_probe(struct spi_device *spi) st->gpo_gpiochip.ngpio = st->num_gpo_gpios; st->gpo_gpiochip.parent = st->dev; st->gpo_gpiochip.can_sleep = true; - st->gpo_gpiochip.set_rv = ad74413r_gpio_set; - st->gpo_gpiochip.set_multiple_rv = ad74413r_gpio_set_multiple; + st->gpo_gpiochip.set = ad74413r_gpio_set; + st->gpo_gpiochip.set_multiple = ad74413r_gpio_set_multiple; st->gpo_gpiochip.set_config = ad74413r_gpio_set_gpo_config; st->gpo_gpiochip.get_direction = ad74413r_gpio_get_gpo_direction; diff --git a/drivers/iio/dac/ad5592r-base.c b/drivers/iio/dac/ad5592r-base.c index 5f2cd51723f6..4720733d66b2 100644 --- a/drivers/iio/dac/ad5592r-base.c +++ b/drivers/iio/dac/ad5592r-base.c @@ -129,7 +129,7 @@ static int ad5592r_gpio_init(struct ad5592r_state *st) st->gpiochip.direction_input = ad5592r_gpio_direction_input; st->gpiochip.direction_output = ad5592r_gpio_direction_output; st->gpiochip.get = ad5592r_gpio_get; - st->gpiochip.set_rv = ad5592r_gpio_set; + st->gpiochip.set = ad5592r_gpio_set; st->gpiochip.request = ad5592r_gpio_request; st->gpiochip.owner = THIS_MODULE; st->gpiochip.names = ad5592r_gpio_names; diff --git a/drivers/input/keyboard/adp5588-keys.c b/drivers/input/keyboard/adp5588-keys.c index 2b2aca08423a..414fbef4abf9 100644 --- a/drivers/input/keyboard/adp5588-keys.c +++ b/drivers/input/keyboard/adp5588-keys.c @@ -425,7 +425,7 @@ static int adp5588_gpio_add(struct adp5588_kpad *kpad) kpad->gc.direction_input = adp5588_gpio_direction_input; kpad->gc.direction_output = adp5588_gpio_direction_output; kpad->gc.get = adp5588_gpio_get_value; - kpad->gc.set_rv = adp5588_gpio_set_value; + kpad->gc.set = adp5588_gpio_set_value; kpad->gc.set_config = adp5588_gpio_set_config; kpad->gc.can_sleep = 1; diff --git a/drivers/input/touchscreen/ad7879.c b/drivers/input/touchscreen/ad7879.c index d2a3a5e016b6..8b4f3e3660b8 100644 --- a/drivers/input/touchscreen/ad7879.c +++ b/drivers/input/touchscreen/ad7879.c @@ -475,7 +475,7 @@ static int ad7879_gpio_add(struct ad7879 *ts) ts->gc.direction_input = ad7879_gpio_direction_input; ts->gc.direction_output = ad7879_gpio_direction_output; ts->gc.get = ad7879_gpio_get_value; - ts->gc.set_rv = ad7879_gpio_set_value; + ts->gc.set = ad7879_gpio_set_value; ts->gc.can_sleep = 1; ts->gc.base = -1; ts->gc.ngpio = 1; diff --git a/drivers/leds/blink/leds-lgm-sso.c b/drivers/leds/blink/leds-lgm-sso.c index c9027f9c4bb7..8923d2df4704 100644 --- a/drivers/leds/blink/leds-lgm-sso.c +++ b/drivers/leds/blink/leds-lgm-sso.c @@ -471,7 +471,7 @@ static int sso_gpio_gc_init(struct device *dev, struct sso_led_priv *priv) gc->get_direction = sso_gpio_get_dir; gc->direction_output = sso_gpio_dir_out; gc->get = sso_gpio_get; - gc->set_rv = sso_gpio_set; + gc->set = sso_gpio_set; gc->label = "lgm-sso"; gc->base = -1; diff --git a/drivers/leds/leds-pca9532.c b/drivers/leds/leds-pca9532.c index 7d4c071a6cd0..0344189bb991 100644 --- a/drivers/leds/leds-pca9532.c +++ b/drivers/leds/leds-pca9532.c @@ -473,7 +473,7 @@ static int pca9532_configure(struct i2c_client *client, data->gpio.label = "gpio-pca9532"; data->gpio.direction_input = pca9532_gpio_direction_input; data->gpio.direction_output = pca9532_gpio_direction_output; - data->gpio.set_rv = pca9532_gpio_set_value; + data->gpio.set = pca9532_gpio_set_value; data->gpio.get = pca9532_gpio_get_value; data->gpio.request = pca9532_gpio_request_pin; data->gpio.can_sleep = 1; diff --git a/drivers/leds/leds-pca955x.c b/drivers/leds/leds-pca955x.c index 70d109246088..2007fe6217ec 100644 --- a/drivers/leds/leds-pca955x.c +++ b/drivers/leds/leds-pca955x.c @@ -737,7 +737,7 @@ static int pca955x_probe(struct i2c_client *client) pca955x->gpio.label = "gpio-pca955x"; pca955x->gpio.direction_input = pca955x_gpio_direction_input; pca955x->gpio.direction_output = pca955x_gpio_direction_output; - pca955x->gpio.set_rv = pca955x_gpio_set_value; + pca955x->gpio.set = pca955x_gpio_set_value; pca955x->gpio.get = pca955x_gpio_get_value; pca955x->gpio.request = pca955x_gpio_request_pin; pca955x->gpio.free = pca955x_gpio_free_pin; diff --git a/drivers/leds/leds-tca6507.c b/drivers/leds/leds-tca6507.c index 89c165c8ee9c..fd0e8bab9a4b 100644 --- a/drivers/leds/leds-tca6507.c +++ b/drivers/leds/leds-tca6507.c @@ -637,7 +637,7 @@ static int tca6507_probe_gpios(struct device *dev, tca->gpio.base = -1; tca->gpio.owner = THIS_MODULE; tca->gpio.direction_output = tca6507_gpio_direction_output; - tca->gpio.set_rv = tca6507_gpio_set_value; + tca->gpio.set = tca6507_gpio_set_value; tca->gpio.parent = dev; err = devm_gpiochip_add_data(dev, &tca->gpio, tca); if (err) { diff --git a/drivers/media/dvb-frontends/cxd2820r_core.c b/drivers/media/dvb-frontends/cxd2820r_core.c index a31a8a6a4946..5aa3d45a691a 100644 --- a/drivers/media/dvb-frontends/cxd2820r_core.c +++ b/drivers/media/dvb-frontends/cxd2820r_core.c @@ -651,7 +651,7 @@ static int cxd2820r_probe(struct i2c_client *client) priv->gpio_chip.parent = &client->dev; priv->gpio_chip.owner = THIS_MODULE; priv->gpio_chip.direction_output = cxd2820r_gpio_direction_output; - priv->gpio_chip.set_rv = cxd2820r_gpio_set; + priv->gpio_chip.set = cxd2820r_gpio_set; priv->gpio_chip.get = cxd2820r_gpio_get; priv->gpio_chip.base = -1; /* Dynamic allocation */ priv->gpio_chip.ngpio = GPIO_COUNT; diff --git a/drivers/media/i2c/ds90ub913.c b/drivers/media/i2c/ds90ub913.c index bc74499b0a96..a80da2b4a8fa 100644 --- a/drivers/media/i2c/ds90ub913.c +++ b/drivers/media/i2c/ds90ub913.c @@ -235,7 +235,7 @@ static int ub913_gpiochip_probe(struct ub913_data *priv) gc->ngpio = UB913_NUM_GPIOS; gc->get_direction = ub913_gpio_get_direction; gc->direction_output = ub913_gpio_direction_out; - gc->set_rv = ub913_gpio_set; + gc->set = ub913_gpio_set; gc->of_xlate = ub913_gpio_of_xlate; gc->of_gpio_n_cells = 2; diff --git a/drivers/media/i2c/ds90ub953.c b/drivers/media/i2c/ds90ub953.c index a865bfc89500..e3fc9d66970a 100644 --- a/drivers/media/i2c/ds90ub953.c +++ b/drivers/media/i2c/ds90ub953.c @@ -361,7 +361,7 @@ static int ub953_gpiochip_probe(struct ub953_data *priv) gc->direction_input = ub953_gpio_direction_in; gc->direction_output = ub953_gpio_direction_out; gc->get = ub953_gpio_get; - gc->set_rv = ub953_gpio_set; + gc->set = ub953_gpio_set; gc->of_xlate = ub953_gpio_of_xlate; gc->of_gpio_n_cells = 2; diff --git a/drivers/media/i2c/max9286.c b/drivers/media/i2c/max9286.c index 1d0b5f56f989..7c0961688d61 100644 --- a/drivers/media/i2c/max9286.c +++ b/drivers/media/i2c/max9286.c @@ -1220,7 +1220,7 @@ static int max9286_register_gpio(struct max9286_priv *priv) gpio->owner = THIS_MODULE; gpio->ngpio = 2; gpio->base = -1; - gpio->set_rv = max9286_gpiochip_set; + gpio->set = max9286_gpiochip_set; gpio->get = max9286_gpiochip_get; gpio->can_sleep = true; diff --git a/drivers/media/i2c/max96717.c b/drivers/media/i2c/max96717.c index 015e42fbe246..c8ae7890d9fa 100644 --- a/drivers/media/i2c/max96717.c +++ b/drivers/media/i2c/max96717.c @@ -355,7 +355,7 @@ static int max96717_gpiochip_probe(struct max96717_priv *priv) gc->get_direction = max96717_gpio_get_direction; gc->direction_input = max96717_gpio_direction_in; gc->direction_output = max96717_gpio_direction_out; - gc->set_rv = max96717_gpiochip_set; + gc->set = max96717_gpiochip_set; gc->get = max96717_gpiochip_get; /* Disable GPIO forwarding */ diff --git a/drivers/media/pci/solo6x10/solo6x10-gpio.c b/drivers/media/pci/solo6x10/solo6x10-gpio.c index b16a8453a62a..71848741c55c 100644 --- a/drivers/media/pci/solo6x10/solo6x10-gpio.c +++ b/drivers/media/pci/solo6x10/solo6x10-gpio.c @@ -158,7 +158,7 @@ int solo_gpio_init(struct solo_dev *solo_dev) solo_dev->gpio_dev.get_direction = solo_gpiochip_get_direction; solo_dev->gpio_dev.get = solo_gpiochip_get; - solo_dev->gpio_dev.set_rv = solo_gpiochip_set; + solo_dev->gpio_dev.set = solo_gpiochip_set; ret = gpiochip_add_data(&solo_dev->gpio_dev, solo_dev); diff --git a/drivers/mfd/sm501.c b/drivers/mfd/sm501.c index a5f9241fa3f2..50bf3260f65d 100644 --- a/drivers/mfd/sm501.c +++ b/drivers/mfd/sm501.c @@ -965,7 +965,7 @@ static const struct gpio_chip gpio_chip_template = { .ngpio = 32, .direction_input = sm501_gpio_input, .direction_output = sm501_gpio_output, - .set_rv = sm501_gpio_set, + .set = sm501_gpio_set, .get = sm501_gpio_get, }; diff --git a/drivers/mfd/tps65010.c b/drivers/mfd/tps65010.c index 03bd5cd66798..8a144ec52201 100644 --- a/drivers/mfd/tps65010.c +++ b/drivers/mfd/tps65010.c @@ -620,7 +620,7 @@ static int tps65010_probe(struct i2c_client *client) tps->chip.parent = &client->dev; tps->chip.owner = THIS_MODULE; - tps->chip.set_rv = tps65010_gpio_set; + tps->chip.set = tps65010_gpio_set; tps->chip.direction_output = tps65010_output; /* NOTE: only partial support for inputs; nyet IRQs */ diff --git a/drivers/mfd/ucb1x00-core.c b/drivers/mfd/ucb1x00-core.c index fd71ba29f6b5..4b450d78a65f 100644 --- a/drivers/mfd/ucb1x00-core.c +++ b/drivers/mfd/ucb1x00-core.c @@ -570,7 +570,7 @@ static int ucb1x00_probe(struct mcp *mcp) ucb->gpio.owner = THIS_MODULE; ucb->gpio.base = pdata->gpio_base; ucb->gpio.ngpio = 10; - ucb->gpio.set_rv = ucb1x00_gpio_set; + ucb->gpio.set = ucb1x00_gpio_set; ucb->gpio.get = ucb1x00_gpio_get; ucb->gpio.direction_input = ucb1x00_gpio_direction_input; ucb->gpio.direction_output = ucb1x00_gpio_direction_output; diff --git a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c index ff8f4404d10f..8eddbaa1fccd 100644 --- a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c +++ b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c @@ -438,7 +438,7 @@ static int pci1xxxx_gpio_setup(struct pci1xxxx_gpio *priv, int irq) gchip->direction_output = pci1xxxx_gpio_direction_output; gchip->get_direction = pci1xxxx_gpio_get_direction; gchip->get = pci1xxxx_gpio_get; - gchip->set_rv = pci1xxxx_gpio_set; + gchip->set = pci1xxxx_gpio_set; gchip->set_config = pci1xxxx_gpio_set_config; gchip->dbg_show = NULL; gchip->base = -1; diff --git a/drivers/misc/ti_fpc202.c b/drivers/misc/ti_fpc202.c index 0b1a6350c02b..7964e46c7448 100644 --- a/drivers/misc/ti_fpc202.c +++ b/drivers/misc/ti_fpc202.c @@ -333,7 +333,7 @@ static int fpc202_probe(struct i2c_client *client) priv->gpio.base = -1; priv->gpio.direction_input = fpc202_gpio_direction_input; priv->gpio.direction_output = fpc202_gpio_direction_output; - priv->gpio.set_rv = fpc202_gpio_set; + priv->gpio.set = fpc202_gpio_set; priv->gpio.get = fpc202_gpio_get; priv->gpio.ngpio = FPC202_GPIO_COUNT; priv->gpio.parent = dev; diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index 5a95877b7419..313e1d241f01 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -607,8 +607,8 @@ static int mcp251x_gpio_setup(struct mcp251x_priv *priv) gpio->get_direction = mcp251x_gpio_get_direction; gpio->get = mcp251x_gpio_get; gpio->get_multiple = mcp251x_gpio_get_multiple; - gpio->set_rv = mcp251x_gpio_set; - gpio->set_multiple_rv = mcp251x_gpio_set_multiple; + gpio->set = mcp251x_gpio_set; + gpio->set_multiple = mcp251x_gpio_set_multiple; gpio->base = -1; gpio->ngpio = ARRAY_SIZE(mcp251x_gpio_names); gpio->names = mcp251x_gpio_names; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index e5bed4237ff4..548b85befbf4 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -2187,7 +2187,7 @@ mt7530_setup_gpio(struct mt7530_priv *priv) gc->direction_input = mt7530_gpio_direction_input; gc->direction_output = mt7530_gpio_direction_output; gc->get = mt7530_gpio_get; - gc->set_rv = mt7530_gpio_set; + gc->set = mt7530_gpio_set; gc->base = -1; gc->ngpio = 15; gc->can_sleep = true; diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c index 4f9687ab3b2b..9d31b8258268 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-core.c +++ b/drivers/net/dsa/vitesse-vsc73xx-core.c @@ -2317,7 +2317,7 @@ static int vsc73xx_gpio_probe(struct vsc73xx *vsc) vsc->gc.parent = vsc->dev; vsc->gc.base = -1; vsc->gc.get = vsc73xx_gpio_get; - vsc->gc.set_rv = vsc73xx_gpio_set; + vsc->gc.set = vsc73xx_gpio_set; vsc->gc.direction_input = vsc73xx_gpio_direction_input; vsc->gc.direction_output = vsc73xx_gpio_direction_output; vsc->gc.get_direction = vsc73xx_gpio_get_direction; diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c index 04e84ebb646c..070dc8c00835 100644 --- a/drivers/net/phy/qcom/qca807x.c +++ b/drivers/net/phy/qcom/qca807x.c @@ -427,7 +427,7 @@ static int qca807x_gpio(struct phy_device *phydev) gc->get_direction = qca807x_gpio_get_direction; gc->direction_output = qca807x_gpio_dir_out; gc->get = qca807x_gpio_get; - gc->set_rv = qca807x_gpio_set; + gc->set = qca807x_gpio_set; return devm_gpiochip_add_data(dev, gc, priv); } diff --git a/drivers/pinctrl/actions/pinctrl-owl.c b/drivers/pinctrl/actions/pinctrl-owl.c index 86f3d5c69e36..1f0ef4727ba7 100644 --- a/drivers/pinctrl/actions/pinctrl-owl.c +++ b/drivers/pinctrl/actions/pinctrl-owl.c @@ -962,7 +962,7 @@ int owl_pinctrl_probe(struct platform_device *pdev, pctrl->chip.direction_input = owl_gpio_direction_input; pctrl->chip.direction_output = owl_gpio_direction_output; pctrl->chip.get = owl_gpio_get; - pctrl->chip.set_rv = owl_gpio_set; + pctrl->chip.set = owl_gpio_set; pctrl->chip.request = owl_gpio_request; pctrl->chip.free = owl_gpio_free; diff --git a/drivers/pinctrl/bcm/pinctrl-bcm2835.c b/drivers/pinctrl/bcm/pinctrl-bcm2835.c index 826827800474..7dbf079739bc 100644 --- a/drivers/pinctrl/bcm/pinctrl-bcm2835.c +++ b/drivers/pinctrl/bcm/pinctrl-bcm2835.c @@ -397,7 +397,7 @@ static const struct gpio_chip bcm2835_gpio_chip = { .direction_output = bcm2835_gpio_direction_output, .get_direction = bcm2835_gpio_get_direction, .get = bcm2835_gpio_get, - .set_rv = bcm2835_gpio_set, + .set = bcm2835_gpio_set, .set_config = gpiochip_generic_config, .base = -1, .ngpio = BCM2835_NUM_GPIOS, @@ -414,7 +414,7 @@ static const struct gpio_chip bcm2711_gpio_chip = { .direction_output = bcm2835_gpio_direction_output, .get_direction = bcm2835_gpio_get_direction, .get = bcm2835_gpio_get, - .set_rv = bcm2835_gpio_set, + .set = bcm2835_gpio_set, .set_config = gpiochip_generic_config, .base = -1, .ngpio = BCM2711_NUM_GPIOS, diff --git a/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c b/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c index 1d08b8d4cdd7..8c353676f2af 100644 --- a/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c +++ b/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c @@ -865,7 +865,7 @@ static int iproc_gpio_probe(struct platform_device *pdev) gc->direction_input = iproc_gpio_direction_input; gc->direction_output = iproc_gpio_direction_output; gc->get_direction = iproc_gpio_get_direction; - gc->set_rv = iproc_gpio_set; + gc->set = iproc_gpio_set; gc->get = iproc_gpio_get; chip->pinmux_is_supported = of_property_read_bool(dev->of_node, diff --git a/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c b/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c index b08f8480ddc6..b425ecacd1b0 100644 --- a/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c +++ b/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c @@ -656,7 +656,7 @@ static int nsp_gpio_probe(struct platform_device *pdev) gc->direction_input = nsp_gpio_direction_input; gc->direction_output = nsp_gpio_direction_output; gc->get_direction = nsp_gpio_get_direction; - gc->set_rv = nsp_gpio_set; + gc->set = nsp_gpio_set; gc->get = nsp_gpio_get; /* optional GPIO interrupt support */ diff --git a/drivers/pinctrl/cirrus/pinctrl-cs42l43.c b/drivers/pinctrl/cirrus/pinctrl-cs42l43.c index 4e47710eb3d5..68abb6d6cecd 100644 --- a/drivers/pinctrl/cirrus/pinctrl-cs42l43.c +++ b/drivers/pinctrl/cirrus/pinctrl-cs42l43.c @@ -555,7 +555,7 @@ static int cs42l43_pin_probe(struct platform_device *pdev) priv->gpio_chip.direction_output = cs42l43_gpio_direction_out; priv->gpio_chip.add_pin_ranges = cs42l43_gpio_add_pin_ranges; priv->gpio_chip.get = cs42l43_gpio_get; - priv->gpio_chip.set_rv = cs42l43_gpio_set; + priv->gpio_chip.set = cs42l43_gpio_set; priv->gpio_chip.label = dev_name(priv->dev); priv->gpio_chip.parent = priv->dev; priv->gpio_chip.can_sleep = true; diff --git a/drivers/pinctrl/cirrus/pinctrl-lochnagar.c b/drivers/pinctrl/cirrus/pinctrl-lochnagar.c index dcc0a2f3c7dd..ca6ae566082b 100644 --- a/drivers/pinctrl/cirrus/pinctrl-lochnagar.c +++ b/drivers/pinctrl/cirrus/pinctrl-lochnagar.c @@ -1161,7 +1161,7 @@ static int lochnagar_pin_probe(struct platform_device *pdev) priv->gpio_chip.request = gpiochip_generic_request; priv->gpio_chip.free = gpiochip_generic_free; priv->gpio_chip.direction_output = lochnagar_gpio_direction_out; - priv->gpio_chip.set_rv = lochnagar_gpio_set; + priv->gpio_chip.set = lochnagar_gpio_set; priv->gpio_chip.can_sleep = true; priv->gpio_chip.parent = dev; priv->gpio_chip.base = -1; diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c index 6eb649f1ffd6..5fd107a00ef8 100644 --- a/drivers/pinctrl/intel/pinctrl-baytrail.c +++ b/drivers/pinctrl/intel/pinctrl-baytrail.c @@ -1231,7 +1231,7 @@ static const struct gpio_chip byt_gpio_chip = { .direction_input = byt_gpio_direction_input, .direction_output = byt_gpio_direction_output, .get = byt_gpio_get, - .set_rv = byt_gpio_set, + .set = byt_gpio_set, .set_config = gpiochip_generic_config, .dbg_show = byt_gpio_dbg_show, }; diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index 769e8c4102a5..f81f7929cd3b 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -1168,7 +1168,7 @@ static const struct gpio_chip chv_gpio_chip = { .direction_input = chv_gpio_direction_input, .direction_output = chv_gpio_direction_output, .get = chv_gpio_get, - .set_rv = chv_gpio_set, + .set = chv_gpio_set, }; static void chv_gpio_irq_ack(struct irq_data *d) diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index f2ff71e5ea6f..d68cef4ec52a 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -1114,7 +1114,7 @@ static const struct gpio_chip intel_gpio_chip = { .direction_input = intel_gpio_direction_input, .direction_output = intel_gpio_direction_output, .get = intel_gpio_get, - .set_rv = intel_gpio_set, + .set = intel_gpio_set, .set_config = gpiochip_generic_config, }; diff --git a/drivers/pinctrl/intel/pinctrl-lynxpoint.c b/drivers/pinctrl/intel/pinctrl-lynxpoint.c index 5d4a5dd493d1..3fb628309fb2 100644 --- a/drivers/pinctrl/intel/pinctrl-lynxpoint.c +++ b/drivers/pinctrl/intel/pinctrl-lynxpoint.c @@ -777,7 +777,7 @@ static int lp_gpio_probe(struct platform_device *pdev) gc->direction_input = lp_gpio_direction_input; gc->direction_output = lp_gpio_direction_output; gc->get = lp_gpio_get; - gc->set_rv = lp_gpio_set; + gc->set = lp_gpio_set; gc->set_config = gpiochip_generic_config; gc->get_direction = lp_gpio_get_direction; gc->base = -1; diff --git a/drivers/pinctrl/mediatek/pinctrl-airoha.c b/drivers/pinctrl/mediatek/pinctrl-airoha.c index 1737b88530c3..5f1ec9e0de21 100644 --- a/drivers/pinctrl/mediatek/pinctrl-airoha.c +++ b/drivers/pinctrl/mediatek/pinctrl-airoha.c @@ -2418,7 +2418,7 @@ static int airoha_pinctrl_add_gpiochip(struct airoha_pinctrl *pinctrl, gc->free = gpiochip_generic_free; gc->direction_input = pinctrl_gpio_direction_input; gc->direction_output = airoha_gpio_direction_output; - gc->set_rv = airoha_gpio_set; + gc->set = airoha_gpio_set; gc->get = airoha_gpio_get; gc->base = -1; gc->ngpio = AIROHA_NUM_PINS; diff --git a/drivers/pinctrl/mediatek/pinctrl-moore.c b/drivers/pinctrl/mediatek/pinctrl-moore.c index ba0d6f880c6e..6e4f6c07a509 100644 --- a/drivers/pinctrl/mediatek/pinctrl-moore.c +++ b/drivers/pinctrl/mediatek/pinctrl-moore.c @@ -569,7 +569,7 @@ static int mtk_build_gpiochip(struct mtk_pinctrl *hw) chip->direction_input = pinctrl_gpio_direction_input; chip->direction_output = mtk_gpio_direction_output; chip->get = mtk_gpio_get; - chip->set_rv = mtk_gpio_set; + chip->set = mtk_gpio_set; chip->to_irq = mtk_gpio_to_irq; chip->set_config = mtk_gpio_set_config; chip->base = -1; diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c index a4cb6d511fcd..d10306024111 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c +++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c @@ -898,7 +898,7 @@ static const struct gpio_chip mtk_gpio_chip = { .direction_input = pinctrl_gpio_direction_input, .direction_output = mtk_gpio_direction_output, .get = mtk_gpio_get, - .set_rv = mtk_gpio_set, + .set = mtk_gpio_set, .to_irq = mtk_gpio_to_irq, .set_config = mtk_gpio_set_config, }; diff --git a/drivers/pinctrl/mediatek/pinctrl-paris.c b/drivers/pinctrl/mediatek/pinctrl-paris.c index 89ef4e530fcc..3e714554789d 100644 --- a/drivers/pinctrl/mediatek/pinctrl-paris.c +++ b/drivers/pinctrl/mediatek/pinctrl-paris.c @@ -949,7 +949,7 @@ static int mtk_build_gpiochip(struct mtk_pinctrl *hw) chip->direction_input = mtk_gpio_direction_input; chip->direction_output = mtk_gpio_direction_output; chip->get = mtk_gpio_get; - chip->set_rv = mtk_gpio_set; + chip->set = mtk_gpio_set; chip->to_irq = mtk_gpio_to_irq; chip->set_config = mtk_gpio_set_config; chip->base = -1; diff --git a/drivers/pinctrl/meson/pinctrl-amlogic-a4.c b/drivers/pinctrl/meson/pinctrl-amlogic-a4.c index c8958222df8c..e34e984c2b38 100644 --- a/drivers/pinctrl/meson/pinctrl-amlogic-a4.c +++ b/drivers/pinctrl/meson/pinctrl-amlogic-a4.c @@ -888,7 +888,7 @@ static const struct gpio_chip aml_gpio_template = { .request = gpiochip_generic_request, .free = gpiochip_generic_free, .set_config = gpiochip_generic_config, - .set_rv = aml_gpio_set, + .set = aml_gpio_set, .get = aml_gpio_get, .direction_input = aml_gpio_direction_input, .direction_output = aml_gpio_direction_output, diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c index f5be61f2ede4..277e9c40490d 100644 --- a/drivers/pinctrl/meson/pinctrl-meson.c +++ b/drivers/pinctrl/meson/pinctrl-meson.c @@ -616,7 +616,7 @@ static int meson_gpiolib_register(struct meson_pinctrl *pc) pc->chip.direction_input = meson_gpio_direction_input; pc->chip.direction_output = meson_gpio_direction_output; pc->chip.get = meson_gpio_get; - pc->chip.set_rv = meson_gpio_set; + pc->chip.set = meson_gpio_set; pc->chip.base = -1; pc->chip.ngpio = pc->data->num_pins; pc->chip.can_sleep = false; diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c index a6b106984e12..881df5e08f61 100644 --- a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c +++ b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c @@ -518,7 +518,7 @@ static const struct pinmux_ops armada_37xx_pmx_ops = { static const struct gpio_chip armada_37xx_gpiolib_chip = { .request = gpiochip_generic_request, .free = gpiochip_generic_free, - .set_rv = armada_37xx_gpio_set, + .set = armada_37xx_gpio_set, .get = armada_37xx_gpio_get, .get_direction = armada_37xx_gpio_get_direction, .direction_input = armada_37xx_gpio_direction_input, diff --git a/drivers/pinctrl/nomadik/pinctrl-abx500.c b/drivers/pinctrl/nomadik/pinctrl-abx500.c index 2f55f83127cf..7b5f94d8cb23 100644 --- a/drivers/pinctrl/nomadik/pinctrl-abx500.c +++ b/drivers/pinctrl/nomadik/pinctrl-abx500.c @@ -536,7 +536,7 @@ static const struct gpio_chip abx500gpio_chip = { .direction_input = abx500_gpio_direction_input, .get = abx500_gpio_get, .direction_output = abx500_gpio_direction_output, - .set_rv = abx500_gpio_set, + .set = abx500_gpio_set, .to_irq = abx500_gpio_to_irq, .dbg_show = abx500_gpio_dbg_show, }; diff --git a/drivers/pinctrl/nuvoton/pinctrl-ma35.c b/drivers/pinctrl/nuvoton/pinctrl-ma35.c index da5220da5149..54652bfbe6ac 100644 --- a/drivers/pinctrl/nuvoton/pinctrl-ma35.c +++ b/drivers/pinctrl/nuvoton/pinctrl-ma35.c @@ -526,7 +526,7 @@ static int ma35_gpiolib_register(struct platform_device *pdev, struct ma35_pinct bank->chip.direction_input = ma35_gpio_core_direction_in; bank->chip.direction_output = ma35_gpio_core_direction_out; bank->chip.get = ma35_gpio_core_get; - bank->chip.set_rv = ma35_gpio_core_set; + bank->chip.set = ma35_gpio_core_set; bank->chip.base = -1; bank->chip.ngpio = bank->nr_pins; bank->chip.can_sleep = false; diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index b90ef3a26ae8..09a5425d54ba 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -1187,7 +1187,7 @@ static int amd_gpio_probe(struct platform_device *pdev) gpio_dev->gc.direction_input = amd_gpio_direction_input; gpio_dev->gc.direction_output = amd_gpio_direction_output; gpio_dev->gc.get = amd_gpio_get_value; - gpio_dev->gc.set_rv = amd_gpio_set_value; + gpio_dev->gc.set = amd_gpio_set_value; gpio_dev->gc.set_config = amd_gpio_set_config; gpio_dev->gc.dbg_show = amd_gpio_dbg_show; diff --git a/drivers/pinctrl/pinctrl-amdisp.c b/drivers/pinctrl/pinctrl-amdisp.c index 2e706bf8bcde..efbf40c776ea 100644 --- a/drivers/pinctrl/pinctrl-amdisp.c +++ b/drivers/pinctrl/pinctrl-amdisp.c @@ -151,7 +151,7 @@ static int amdisp_gpiochip_add(struct platform_device *pdev, gc->direction_input = amdisp_gpio_direction_input; gc->direction_output = amdisp_gpio_direction_output; gc->get = amdisp_gpio_get; - gc->set_rv = amdisp_gpio_set; + gc->set = amdisp_gpio_set; gc->base = -1; gc->ngpio = ARRAY_SIZE(amdisp_range_pins); diff --git a/drivers/pinctrl/pinctrl-apple-gpio.c b/drivers/pinctrl/pinctrl-apple-gpio.c index dcf3a921b4df..a09daa72bfe4 100644 --- a/drivers/pinctrl/pinctrl-apple-gpio.c +++ b/drivers/pinctrl/pinctrl-apple-gpio.c @@ -378,7 +378,7 @@ static int apple_gpio_register(struct apple_gpio_pinctrl *pctl) pctl->gpio_chip.direction_input = apple_gpio_direction_input; pctl->gpio_chip.direction_output = apple_gpio_direction_output; pctl->gpio_chip.get = apple_gpio_get; - pctl->gpio_chip.set_rv = apple_gpio_set; + pctl->gpio_chip.set = apple_gpio_set; pctl->gpio_chip.base = -1; pctl->gpio_chip.ngpio = pctl->pinctrl_desc.npins; pctl->gpio_chip.parent = pctl->dev; diff --git a/drivers/pinctrl/pinctrl-as3722.c b/drivers/pinctrl/pinctrl-as3722.c index 30ed758bbe9d..e713dea98aa8 100644 --- a/drivers/pinctrl/pinctrl-as3722.c +++ b/drivers/pinctrl/pinctrl-as3722.c @@ -529,7 +529,7 @@ static const struct gpio_chip as3722_gpio_chip = { .request = gpiochip_generic_request, .free = gpiochip_generic_free, .get = as3722_gpio_get, - .set_rv = as3722_gpio_set, + .set = as3722_gpio_set, .direction_input = pinctrl_gpio_direction_input, .direction_output = as3722_gpio_direction_output, .to_irq = as3722_gpio_to_irq, diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c index 57f105ac962d..35ea3414cb96 100644 --- a/drivers/pinctrl/pinctrl-at91-pio4.c +++ b/drivers/pinctrl/pinctrl-at91-pio4.c @@ -442,8 +442,8 @@ static struct gpio_chip atmel_gpio_chip = { .get = atmel_gpio_get, .get_multiple = atmel_gpio_get_multiple, .direction_output = atmel_gpio_direction_output, - .set_rv = atmel_gpio_set, - .set_multiple_rv = atmel_gpio_set_multiple, + .set = atmel_gpio_set, + .set_multiple = atmel_gpio_set_multiple, .to_irq = atmel_gpio_to_irq, .base = 0, }; diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c index 6c2727bd55bc..0a57ed51d4c9 100644 --- a/drivers/pinctrl/pinctrl-at91.c +++ b/drivers/pinctrl/pinctrl-at91.c @@ -1801,8 +1801,8 @@ static const struct gpio_chip at91_gpio_template = { .direction_input = at91_gpio_direction_input, .get = at91_gpio_get, .direction_output = at91_gpio_direction_output, - .set_rv = at91_gpio_set, - .set_multiple_rv = at91_gpio_set_multiple, + .set = at91_gpio_set, + .set_multiple = at91_gpio_set_multiple, .dbg_show = at91_gpio_dbg_show, .can_sleep = false, .ngpio = MAX_NB_GPIO_PER_BANK, diff --git a/drivers/pinctrl/pinctrl-aw9523.c b/drivers/pinctrl/pinctrl-aw9523.c index 9570ef346af6..890b83fddea3 100644 --- a/drivers/pinctrl/pinctrl-aw9523.c +++ b/drivers/pinctrl/pinctrl-aw9523.c @@ -785,8 +785,8 @@ static int aw9523_init_gpiochip(struct aw9523 *awi, unsigned int npins) gc->direction_output = aw9523_direction_output; gc->get = aw9523_gpio_get; gc->get_multiple = aw9523_gpio_get_multiple; - gc->set_rv = aw9523_gpio_set; - gc->set_multiple_rv = aw9523_gpio_set_multiple; + gc->set = aw9523_gpio_set; + gc->set_multiple = aw9523_gpio_set_multiple; gc->set_config = gpiochip_generic_config; gc->parent = dev; gc->owner = THIS_MODULE; diff --git a/drivers/pinctrl/pinctrl-axp209.c b/drivers/pinctrl/pinctrl-axp209.c index fff408b60c4a..2bd8487484a8 100644 --- a/drivers/pinctrl/pinctrl-axp209.c +++ b/drivers/pinctrl/pinctrl-axp209.c @@ -192,7 +192,7 @@ static int axp20x_gpio_get_direction(struct gpio_chip *chip, static int axp20x_gpio_output(struct gpio_chip *chip, unsigned int offset, int value) { - return chip->set_rv(chip, offset, value); + return chip->set(chip, offset, value); } static int axp20x_gpio_set(struct gpio_chip *chip, unsigned int offset, @@ -463,7 +463,7 @@ static int axp20x_pctl_probe(struct platform_device *pdev) pctl->chip.owner = THIS_MODULE; pctl->chip.get = axp20x_gpio_get; pctl->chip.get_direction = axp20x_gpio_get_direction; - pctl->chip.set_rv = axp20x_gpio_set; + pctl->chip.set = axp20x_gpio_set; pctl->chip.direction_input = pinctrl_gpio_direction_input; pctl->chip.direction_output = axp20x_gpio_output; diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c index 8a2fd632bdd4..cf7f80497fde 100644 --- a/drivers/pinctrl/pinctrl-cy8c95x0.c +++ b/drivers/pinctrl/pinctrl-cy8c95x0.c @@ -939,10 +939,10 @@ static int cy8c95x0_setup_gpiochip(struct cy8c95x0_pinctrl *chip) gc->direction_input = cy8c95x0_gpio_direction_input; gc->direction_output = cy8c95x0_gpio_direction_output; gc->get = cy8c95x0_gpio_get_value; - gc->set_rv = cy8c95x0_gpio_set_value; + gc->set = cy8c95x0_gpio_set_value; gc->get_direction = cy8c95x0_gpio_get_direction; gc->get_multiple = cy8c95x0_gpio_get_multiple; - gc->set_multiple_rv = cy8c95x0_gpio_set_multiple; + gc->set_multiple = cy8c95x0_gpio_set_multiple; gc->set_config = gpiochip_generic_config; gc->can_sleep = true; gc->add_pin_ranges = cy8c95x0_add_pin_ranges; diff --git a/drivers/pinctrl/pinctrl-da9062.c b/drivers/pinctrl/pinctrl-da9062.c index 3295b09dfc3d..53298cbcc5cf 100644 --- a/drivers/pinctrl/pinctrl-da9062.c +++ b/drivers/pinctrl/pinctrl-da9062.c @@ -233,7 +233,7 @@ static int da9062_gpio_to_irq(struct gpio_chip *gc, unsigned int offset) static const struct gpio_chip reference_gc = { .owner = THIS_MODULE, .get = da9062_gpio_get, - .set_rv = da9062_gpio_set, + .set = da9062_gpio_set, .get_direction = da9062_gpio_get_direction, .direction_input = da9062_gpio_direction_input, .direction_output = da9062_gpio_direction_output, diff --git a/drivers/pinctrl/pinctrl-digicolor.c b/drivers/pinctrl/pinctrl-digicolor.c index 1676cb3cc4c9..2e16f09aeb47 100644 --- a/drivers/pinctrl/pinctrl-digicolor.c +++ b/drivers/pinctrl/pinctrl-digicolor.c @@ -248,7 +248,7 @@ static int dc_gpiochip_add(struct dc_pinmap *pmap) chip->direction_input = dc_gpio_direction_input; chip->direction_output = dc_gpio_direction_output; chip->get = dc_gpio_get; - chip->set_rv = dc_gpio_set; + chip->set = dc_gpio_set; chip->base = -1; chip->ngpio = PINS_COUNT; diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c index 79119cf20efc..2900513467fa 100644 --- a/drivers/pinctrl/pinctrl-ingenic.c +++ b/drivers/pinctrl/pinctrl-ingenic.c @@ -4451,7 +4451,7 @@ static int __init ingenic_gpio_probe(struct ingenic_pinctrl *jzpc, jzgc->gc.fwnode = fwnode; jzgc->gc.owner = THIS_MODULE; - jzgc->gc.set_rv = ingenic_gpio_set; + jzgc->gc.set = ingenic_gpio_set; jzgc->gc.get = ingenic_gpio_get; jzgc->gc.direction_input = pinctrl_gpio_direction_input; jzgc->gc.direction_output = ingenic_gpio_direction_output; diff --git a/drivers/pinctrl/pinctrl-keembay.c b/drivers/pinctrl/pinctrl-keembay.c index 30e641571cfe..60cf017498b3 100644 --- a/drivers/pinctrl/pinctrl-keembay.c +++ b/drivers/pinctrl/pinctrl-keembay.c @@ -1481,7 +1481,7 @@ static int keembay_gpiochip_probe(struct keembay_pinctrl *kpc, gc->direction_input = keembay_gpio_set_direction_in; gc->direction_output = keembay_gpio_set_direction_out; gc->get = keembay_gpio_get; - gc->set_rv = keembay_gpio_set; + gc->set = keembay_gpio_set; gc->set_config = gpiochip_generic_config; gc->base = -1; gc->ngpio = kpc->npins; diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c index c8027ef03ecc..a17fcaddf490 100644 --- a/drivers/pinctrl/pinctrl-mcp23s08.c +++ b/drivers/pinctrl/pinctrl-mcp23s08.c @@ -632,8 +632,8 @@ int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev, mcp->chip.get = mcp23s08_get; mcp->chip.get_multiple = mcp23s08_get_multiple; mcp->chip.direction_output = mcp23s08_direction_output; - mcp->chip.set_rv = mcp23s08_set; - mcp->chip.set_multiple_rv = mcp23s08_set_multiple; + mcp->chip.set = mcp23s08_set; + mcp->chip.set_multiple = mcp23s08_set_multiple; mcp->chip.base = base; mcp->chip.can_sleep = true; diff --git a/drivers/pinctrl/pinctrl-microchip-sgpio.c b/drivers/pinctrl/pinctrl-microchip-sgpio.c index 88c2f14cfc6b..6191e5c13815 100644 --- a/drivers/pinctrl/pinctrl-microchip-sgpio.c +++ b/drivers/pinctrl/pinctrl-microchip-sgpio.c @@ -858,7 +858,7 @@ static int microchip_sgpio_register_bank(struct device *dev, gc->direction_input = microchip_sgpio_direction_input; gc->direction_output = microchip_sgpio_direction_output; gc->get = microchip_sgpio_get_value; - gc->set_rv = microchip_sgpio_set_value; + gc->set = microchip_sgpio_set_value; gc->request = gpiochip_generic_request; gc->free = gpiochip_generic_free; gc->of_xlate = microchip_sgpio_of_xlate; diff --git a/drivers/pinctrl/pinctrl-ocelot.c b/drivers/pinctrl/pinctrl-ocelot.c index fbb3d43746bb..b82bf83fed25 100644 --- a/drivers/pinctrl/pinctrl-ocelot.c +++ b/drivers/pinctrl/pinctrl-ocelot.c @@ -1997,7 +1997,7 @@ static int ocelot_gpio_direction_output(struct gpio_chip *chip, static const struct gpio_chip ocelot_gpiolib_chip = { .request = gpiochip_generic_request, .free = gpiochip_generic_free, - .set_rv = ocelot_gpio_set, + .set = ocelot_gpio_set, .get = ocelot_gpio_get, .get_direction = ocelot_gpio_get_direction, .direction_input = pinctrl_gpio_direction_input, diff --git a/drivers/pinctrl/pinctrl-pic32.c b/drivers/pinctrl/pinctrl-pic32.c index 6d64cab97e81..37c2bf752154 100644 --- a/drivers/pinctrl/pinctrl-pic32.c +++ b/drivers/pinctrl/pinctrl-pic32.c @@ -2120,7 +2120,7 @@ static void pic32_gpio_irq_handler(struct irq_desc *desc) .direction_input = pic32_gpio_direction_input, \ .direction_output = pic32_gpio_direction_output, \ .get = pic32_gpio_get, \ - .set_rv = pic32_gpio_set, \ + .set = pic32_gpio_set, \ .ngpio = _npins, \ .base = GPIO_BANK_START(_bank), \ .owner = THIS_MODULE, \ diff --git a/drivers/pinctrl/pinctrl-pistachio.c b/drivers/pinctrl/pinctrl-pistachio.c index 7f8b562c81c9..0b33b01dbaad 100644 --- a/drivers/pinctrl/pinctrl-pistachio.c +++ b/drivers/pinctrl/pinctrl-pistachio.c @@ -1331,7 +1331,7 @@ static void pistachio_gpio_irq_handler(struct irq_desc *desc) .direction_input = pistachio_gpio_direction_input, \ .direction_output = pistachio_gpio_direction_output, \ .get = pistachio_gpio_get, \ - .set_rv = pistachio_gpio_set, \ + .set = pistachio_gpio_set, \ .base = _pin_base, \ .ngpio = _npins, \ }, \ diff --git a/drivers/pinctrl/pinctrl-rk805.c b/drivers/pinctrl/pinctrl-rk805.c index fc0e330b1d11..3acf770316c1 100644 --- a/drivers/pinctrl/pinctrl-rk805.c +++ b/drivers/pinctrl/pinctrl-rk805.c @@ -378,7 +378,7 @@ static const struct gpio_chip rk805_gpio_chip = { .free = gpiochip_generic_free, .get_direction = rk805_gpio_get_direction, .get = rk805_gpio_get, - .set_rv = rk805_gpio_set, + .set = rk805_gpio_set, .direction_input = pinctrl_gpio_direction_input, .direction_output = rk805_gpio_direction_output, .can_sleep = true, diff --git a/drivers/pinctrl/pinctrl-rp1.c b/drivers/pinctrl/pinctrl-rp1.c index 6080b57a5d87..dadafc935dbb 100644 --- a/drivers/pinctrl/pinctrl-rp1.c +++ b/drivers/pinctrl/pinctrl-rp1.c @@ -851,7 +851,7 @@ static const struct gpio_chip rp1_gpio_chip = { .direction_output = rp1_gpio_direction_output, .get_direction = rp1_gpio_get_direction, .get = rp1_gpio_get, - .set_rv = rp1_gpio_set, + .set = rp1_gpio_set, .base = -1, .set_config = rp1_gpio_set_config, .ngpio = RP1_NUM_GPIOS, diff --git a/drivers/pinctrl/pinctrl-st.c b/drivers/pinctrl/pinctrl-st.c index 574fe2cbfbec..d3cea3437d7f 100644 --- a/drivers/pinctrl/pinctrl-st.c +++ b/drivers/pinctrl/pinctrl-st.c @@ -1467,7 +1467,7 @@ static const struct gpio_chip st_gpio_template = { .request = gpiochip_generic_request, .free = gpiochip_generic_free, .get = st_gpio_get, - .set_rv = st_gpio_set, + .set = st_gpio_set, .direction_input = pinctrl_gpio_direction_input, .direction_output = st_gpio_direction_output, .get_direction = st_gpio_get_direction, diff --git a/drivers/pinctrl/pinctrl-stmfx.c b/drivers/pinctrl/pinctrl-stmfx.c index f4fdcaa043e6..c89b99003b71 100644 --- a/drivers/pinctrl/pinctrl-stmfx.c +++ b/drivers/pinctrl/pinctrl-stmfx.c @@ -697,7 +697,7 @@ static int stmfx_pinctrl_probe(struct platform_device *pdev) pctl->gpio_chip.direction_input = stmfx_gpio_direction_input; pctl->gpio_chip.direction_output = stmfx_gpio_direction_output; pctl->gpio_chip.get = stmfx_gpio_get; - pctl->gpio_chip.set_rv = stmfx_gpio_set; + pctl->gpio_chip.set = stmfx_gpio_set; pctl->gpio_chip.set_config = gpiochip_generic_config; pctl->gpio_chip.base = -1; pctl->gpio_chip.ngpio = pctl->pctl_desc.npins; diff --git a/drivers/pinctrl/pinctrl-sx150x.c b/drivers/pinctrl/pinctrl-sx150x.c index d3a12c1c0de2..53cf8168b274 100644 --- a/drivers/pinctrl/pinctrl-sx150x.c +++ b/drivers/pinctrl/pinctrl-sx150x.c @@ -1176,7 +1176,7 @@ static int sx150x_probe(struct i2c_client *client) pctl->gpio.direction_input = sx150x_gpio_direction_input; pctl->gpio.direction_output = sx150x_gpio_direction_output; pctl->gpio.get = sx150x_gpio_get; - pctl->gpio.set_rv = sx150x_gpio_set; + pctl->gpio.set = sx150x_gpio_set; pctl->gpio.set_config = gpiochip_generic_config; pctl->gpio.parent = dev; pctl->gpio.can_sleep = true; @@ -1191,7 +1191,7 @@ static int sx150x_probe(struct i2c_client *client) * would require locking that is not in place at this time. */ if (pctl->data->model != SX150X_789) - pctl->gpio.set_multiple_rv = sx150x_gpio_set_multiple; + pctl->gpio.set_multiple = sx150x_gpio_set_multiple; /* Add Interrupt support if an irq is specified */ if (client->irq > 0) { diff --git a/drivers/pinctrl/pinctrl-xway.c b/drivers/pinctrl/pinctrl-xway.c index 53c6c22ff24d..3d4ad61d0da9 100644 --- a/drivers/pinctrl/pinctrl-xway.c +++ b/drivers/pinctrl/pinctrl-xway.c @@ -1354,7 +1354,7 @@ static struct gpio_chip xway_chip = { .direction_input = xway_gpio_dir_in, .direction_output = xway_gpio_dir_out, .get = xway_gpio_get, - .set_rv = xway_gpio_set, + .set = xway_gpio_set, .request = gpiochip_generic_request, .free = gpiochip_generic_free, .to_irq = xway_gpio_to_irq, diff --git a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c index 57fefeb603f0..54c77e0b96e9 100644 --- a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c +++ b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c @@ -398,7 +398,7 @@ static const struct gpio_chip lpi_gpio_template = { .direction_input = lpi_gpio_direction_input, .direction_output = lpi_gpio_direction_output, .get = lpi_gpio_get, - .set_rv = lpi_gpio_set, + .set = lpi_gpio_set, .request = gpiochip_generic_request, .free = gpiochip_generic_free, .dbg_show = lpi_gpio_dbg_show, diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index f713c80d7f3e..83eb075b6bfa 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -792,7 +792,7 @@ static const struct gpio_chip msm_gpio_template = { .direction_output = msm_gpio_direction_output, .get_direction = msm_gpio_get_direction, .get = msm_gpio_get, - .set_rv = msm_gpio_set, + .set = msm_gpio_set, .request = gpiochip_generic_request, .free = gpiochip_generic_free, .dbg_show = msm_gpio_dbg_show, diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c index 606becc160eb..b7b15874e488 100644 --- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c +++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c @@ -802,7 +802,7 @@ static const struct gpio_chip pmic_gpio_gpio_template = { .direction_input = pmic_gpio_direction_input, .direction_output = pmic_gpio_direction_output, .get = pmic_gpio_get, - .set_rv = pmic_gpio_set, + .set = pmic_gpio_set, .request = gpiochip_generic_request, .free = gpiochip_generic_free, .of_xlate = pmic_gpio_of_xlate, diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c b/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c index ba9084978f90..22d76b1013a3 100644 --- a/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c +++ b/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c @@ -638,7 +638,7 @@ static const struct gpio_chip pmic_mpp_gpio_template = { .direction_input = pmic_mpp_direction_input, .direction_output = pmic_mpp_direction_output, .get = pmic_mpp_get, - .set_rv = pmic_mpp_set, + .set = pmic_mpp_set, .request = gpiochip_generic_request, .free = gpiochip_generic_free, .of_xlate = pmic_mpp_of_xlate, diff --git a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c index 3a8014ebf064..fb37b1c1acb4 100644 --- a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c +++ b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c @@ -597,7 +597,7 @@ static const struct gpio_chip pm8xxx_gpio_template = { .direction_input = pm8xxx_gpio_direction_input, .direction_output = pm8xxx_gpio_direction_output, .get = pm8xxx_gpio_get, - .set_rv = pm8xxx_gpio_set, + .set = pm8xxx_gpio_set, .of_xlate = pm8xxx_gpio_of_xlate, .dbg_show = pm8xxx_gpio_dbg_show, .owner = THIS_MODULE, diff --git a/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c b/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c index 087c37d304fc..6103849af042 100644 --- a/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c +++ b/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c @@ -634,7 +634,7 @@ static const struct gpio_chip pm8xxx_mpp_template = { .direction_input = pm8xxx_mpp_direction_input, .direction_output = pm8xxx_mpp_direction_output, .get = pm8xxx_mpp_get, - .set_rv = pm8xxx_mpp_set, + .set = pm8xxx_mpp_set, .of_xlate = pm8xxx_mpp_of_xlate, .dbg_show = pm8xxx_mpp_dbg_show, .owner = THIS_MODULE, diff --git a/drivers/pinctrl/renesas/gpio.c b/drivers/pinctrl/renesas/gpio.c index 8efbdc1b0078..2293af642849 100644 --- a/drivers/pinctrl/renesas/gpio.c +++ b/drivers/pinctrl/renesas/gpio.c @@ -234,7 +234,7 @@ static int gpio_pin_setup(struct sh_pfc_chip *chip) gc->direction_input = gpio_pin_direction_input; gc->get = gpio_pin_get; gc->direction_output = gpio_pin_direction_output; - gc->set_rv = gpio_pin_set; + gc->set = gpio_pin_set; gc->to_irq = gpio_pin_to_irq; gc->label = pfc->info->name; diff --git a/drivers/pinctrl/renesas/pinctrl-rza1.c b/drivers/pinctrl/renesas/pinctrl-rza1.c index 3d8492c91710..23812116ef42 100644 --- a/drivers/pinctrl/renesas/pinctrl-rza1.c +++ b/drivers/pinctrl/renesas/pinctrl-rza1.c @@ -846,7 +846,7 @@ static const struct gpio_chip rza1_gpiochip_template = { .direction_input = rza1_gpio_direction_input, .direction_output = rza1_gpio_direction_output, .get = rza1_gpio_get, - .set_rv = rza1_gpio_set, + .set = rza1_gpio_set, }; /* ---------------------------------------------------------------------------- * pinctrl operations diff --git a/drivers/pinctrl/renesas/pinctrl-rza2.c b/drivers/pinctrl/renesas/pinctrl-rza2.c index 7a0b268d3eb9..b78b5b4ec5af 100644 --- a/drivers/pinctrl/renesas/pinctrl-rza2.c +++ b/drivers/pinctrl/renesas/pinctrl-rza2.c @@ -237,7 +237,7 @@ static struct gpio_chip chip = { .direction_input = rza2_chip_direction_input, .direction_output = rza2_chip_direction_output, .get = rza2_chip_get, - .set_rv = rza2_chip_set, + .set = rza2_chip_set, }; static int rza2_gpio_register(struct rza2_pinctrl_priv *priv) diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c index 2a10ae0bf5bd..c52263c2a7b0 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c +++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c @@ -2795,7 +2795,7 @@ static int rzg2l_gpio_register(struct rzg2l_pinctrl *pctrl) chip->direction_input = rzg2l_gpio_direction_input; chip->direction_output = rzg2l_gpio_direction_output; chip->get = rzg2l_gpio_get; - chip->set_rv = rzg2l_gpio_set; + chip->set = rzg2l_gpio_set; chip->label = name; chip->parent = pctrl->dev; chip->owner = THIS_MODULE; diff --git a/drivers/pinctrl/renesas/pinctrl-rzv2m.c b/drivers/pinctrl/renesas/pinctrl-rzv2m.c index a17b68b4c466..daaa986d994d 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzv2m.c +++ b/drivers/pinctrl/renesas/pinctrl-rzv2m.c @@ -957,7 +957,7 @@ static int rzv2m_gpio_register(struct rzv2m_pinctrl *pctrl) chip->direction_input = rzv2m_gpio_direction_input; chip->direction_output = rzv2m_gpio_direction_output; chip->get = rzv2m_gpio_get; - chip->set_rv = rzv2m_gpio_set; + chip->set = rzv2m_gpio_set; chip->label = name; chip->parent = pctrl->dev; chip->owner = THIS_MODULE; diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c index fe1ac82b9d79..24745e1d78ce 100644 --- a/drivers/pinctrl/samsung/pinctrl-samsung.c +++ b/drivers/pinctrl/samsung/pinctrl-samsung.c @@ -1067,7 +1067,7 @@ static int samsung_gpio_set_config(struct gpio_chip *gc, unsigned int offset, static const struct gpio_chip samsung_gpiolib_chip = { .request = gpiochip_generic_request, .free = gpiochip_generic_free, - .set_rv = samsung_gpio_set, + .set = samsung_gpio_set, .get = samsung_gpio_get, .direction_input = samsung_gpio_direction_input, .direction_output = samsung_gpio_direction_output, diff --git a/drivers/pinctrl/spear/pinctrl-plgpio.c b/drivers/pinctrl/spear/pinctrl-plgpio.c index e8234d2156da..1ec22010a3f9 100644 --- a/drivers/pinctrl/spear/pinctrl-plgpio.c +++ b/drivers/pinctrl/spear/pinctrl-plgpio.c @@ -582,7 +582,7 @@ static int plgpio_probe(struct platform_device *pdev) plgpio->chip.direction_input = plgpio_direction_input; plgpio->chip.direction_output = plgpio_direction_output; plgpio->chip.get = plgpio_get_value; - plgpio->chip.set_rv = plgpio_set_value; + plgpio->chip.set = plgpio_set_value; plgpio->chip.label = dev_name(&pdev->dev); plgpio->chip.parent = &pdev->dev; plgpio->chip.owner = THIS_MODULE; diff --git a/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c b/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c index b729ca4de422..7fa13f282b85 100644 --- a/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c +++ b/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c @@ -1302,7 +1302,7 @@ static int starfive_probe(struct platform_device *pdev) sfp->gc.direction_input = starfive_gpio_direction_input; sfp->gc.direction_output = starfive_gpio_direction_output; sfp->gc.get = starfive_gpio_get; - sfp->gc.set_rv = starfive_gpio_set; + sfp->gc.set = starfive_gpio_set; sfp->gc.set_config = starfive_gpio_set_config; sfp->gc.add_pin_ranges = starfive_gpio_add_pin_ranges; sfp->gc.base = -1; diff --git a/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c b/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c index 082bb1c6cea9..05e3af75b09f 100644 --- a/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c +++ b/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c @@ -935,7 +935,7 @@ int jh7110_pinctrl_probe(struct platform_device *pdev) sfp->gc.direction_input = jh7110_gpio_direction_input; sfp->gc.direction_output = jh7110_gpio_direction_output; sfp->gc.get = jh7110_gpio_get; - sfp->gc.set_rv = jh7110_gpio_set; + sfp->gc.set = jh7110_gpio_set; sfp->gc.set_config = jh7110_gpio_set_config; sfp->gc.add_pin_ranges = jh7110_gpio_add_pin_ranges; sfp->gc.base = info->gc_base; diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c index f47c4e6f12b4..823c8fe758e2 100644 --- a/drivers/pinctrl/stm32/pinctrl-stm32.c +++ b/drivers/pinctrl/stm32/pinctrl-stm32.c @@ -433,7 +433,7 @@ static const struct gpio_chip stm32_gpio_template = { .request = stm32_gpio_request, .free = stm32_gpio_free, .get = stm32_gpio_get, - .set_rv = stm32_gpio_set, + .set = stm32_gpio_set, .direction_input = pinctrl_gpio_direction_input, .direction_output = stm32_gpio_direction_output, .to_irq = stm32_gpio_to_irq, diff --git a/drivers/pinctrl/sunplus/sppctl.c b/drivers/pinctrl/sunplus/sppctl.c index 3c3357f80889..3e924aa86cc2 100644 --- a/drivers/pinctrl/sunplus/sppctl.c +++ b/drivers/pinctrl/sunplus/sppctl.c @@ -547,7 +547,7 @@ static int sppctl_gpio_new(struct platform_device *pdev, struct sppctl_pdata *pc gchip->direction_input = sppctl_gpio_direction_input; gchip->direction_output = sppctl_gpio_direction_output; gchip->get = sppctl_gpio_get; - gchip->set_rv = sppctl_gpio_set; + gchip->set = sppctl_gpio_set; gchip->set_config = sppctl_gpio_set_config; gchip->dbg_show = IS_ENABLED(CONFIG_DEBUG_FS) ? sppctl_gpio_dbg_show : NULL; diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c index 0db8429a013f..0fb057a07dcc 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c @@ -1604,7 +1604,7 @@ int sunxi_pinctrl_init_with_flags(struct platform_device *pdev, pctl->chip->direction_input = sunxi_pinctrl_gpio_direction_input; pctl->chip->direction_output = sunxi_pinctrl_gpio_direction_output; pctl->chip->get = sunxi_pinctrl_gpio_get; - pctl->chip->set_rv = sunxi_pinctrl_gpio_set; + pctl->chip->set = sunxi_pinctrl_gpio_set; pctl->chip->of_xlate = sunxi_pinctrl_gpio_of_xlate; pctl->chip->to_irq = sunxi_pinctrl_gpio_to_irq; pctl->chip->of_gpio_n_cells = 3; diff --git a/drivers/pinctrl/vt8500/pinctrl-wmt.c b/drivers/pinctrl/vt8500/pinctrl-wmt.c index 767c6808a463..7213a8d4bf09 100644 --- a/drivers/pinctrl/vt8500/pinctrl-wmt.c +++ b/drivers/pinctrl/vt8500/pinctrl-wmt.c @@ -549,7 +549,7 @@ static const struct gpio_chip wmt_gpio_chip = { .direction_input = pinctrl_gpio_direction_input, .direction_output = wmt_gpio_direction_output, .get = wmt_gpio_get_value, - .set_rv = wmt_gpio_set_value, + .set = wmt_gpio_set_value, .can_sleep = false, }; diff --git a/drivers/platform/cznic/turris-omnia-mcu-gpio.c b/drivers/platform/cznic/turris-omnia-mcu-gpio.c index 77184c8b42ea..7f0ada4fa606 100644 --- a/drivers/platform/cznic/turris-omnia-mcu-gpio.c +++ b/drivers/platform/cznic/turris-omnia-mcu-gpio.c @@ -1024,8 +1024,8 @@ int omnia_mcu_register_gpiochip(struct omnia_mcu *mcu) mcu->gc.direction_output = omnia_gpio_direction_output; mcu->gc.get = omnia_gpio_get; mcu->gc.get_multiple = omnia_gpio_get_multiple; - mcu->gc.set_rv = omnia_gpio_set; - mcu->gc.set_multiple_rv = omnia_gpio_set_multiple; + mcu->gc.set = omnia_gpio_set; + mcu->gc.set_multiple = omnia_gpio_set_multiple; mcu->gc.init_valid_mask = omnia_gpio_init_valid_mask; mcu->gc.can_sleep = true; mcu->gc.names = omnia_mcu_gpio_names; diff --git a/drivers/platform/x86/barco-p50-gpio.c b/drivers/platform/x86/barco-p50-gpio.c index bb3393bbfb89..28012eebdb10 100644 --- a/drivers/platform/x86/barco-p50-gpio.c +++ b/drivers/platform/x86/barco-p50-gpio.c @@ -316,7 +316,7 @@ static int p50_gpio_probe(struct platform_device *pdev) p50->gc.base = -1; p50->gc.get_direction = p50_gpio_get_direction; p50->gc.get = p50_gpio_get; - p50->gc.set_rv = p50_gpio_set; + p50->gc.set = p50_gpio_set; /* reset mbox */ diff --git a/drivers/platform/x86/intel/int0002_vgpio.c b/drivers/platform/x86/intel/int0002_vgpio.c index 9bc24ed19c64..6f5629dc3f8d 100644 --- a/drivers/platform/x86/intel/int0002_vgpio.c +++ b/drivers/platform/x86/intel/int0002_vgpio.c @@ -193,7 +193,7 @@ static int int0002_probe(struct platform_device *pdev) chip->parent = dev; chip->owner = THIS_MODULE; chip->get = int0002_gpio_get; - chip->set_rv = int0002_gpio_set; + chip->set = int0002_gpio_set; chip->direction_input = int0002_gpio_get; chip->direction_output = int0002_gpio_direction_output; chip->base = -1; diff --git a/drivers/platform/x86/portwell-ec.c b/drivers/platform/x86/portwell-ec.c index 3e019c51913e..322f296e9315 100644 --- a/drivers/platform/x86/portwell-ec.c +++ b/drivers/platform/x86/portwell-ec.c @@ -86,7 +86,7 @@ static int pwec_gpio_get(struct gpio_chip *chip, unsigned int offset) return pwec_read(PORTWELL_GPIO_VAL_REG) & BIT(offset) ? 1 : 0; } -static int pwec_gpio_set_rv(struct gpio_chip *chip, unsigned int offset, int val) +static int pwec_gpio_set(struct gpio_chip *chip, unsigned int offset, int val) { u8 tmp = pwec_read(PORTWELL_GPIO_VAL_REG); @@ -130,7 +130,7 @@ static struct gpio_chip pwec_gpio_chip = { .direction_input = pwec_gpio_direction_input, .direction_output = pwec_gpio_direction_output, .get = pwec_gpio_get, - .set_rv = pwec_gpio_set_rv, + .set = pwec_gpio_set, .base = -1, .ngpio = PORTWELL_GPIO_PINS, }; diff --git a/drivers/platform/x86/silicom-platform.c b/drivers/platform/x86/silicom-platform.c index 63b5da410ed5..266f7bc5e416 100644 --- a/drivers/platform/x86/silicom-platform.c +++ b/drivers/platform/x86/silicom-platform.c @@ -466,7 +466,7 @@ static struct gpio_chip silicom_gpio_chip = { .direction_input = silicom_gpio_direction_input, .direction_output = silicom_gpio_direction_output, .get = silicom_gpio_get, - .set_rv = silicom_gpio_set, + .set = silicom_gpio_set, .base = -1, .ngpio = ARRAY_SIZE(plat_0222_gpio_channels), .names = plat_0222_gpio_names, diff --git a/drivers/pwm/pwm-pca9685.c b/drivers/pwm/pwm-pca9685.c index eb03ccd5b688..9ce75704a15f 100644 --- a/drivers/pwm/pwm-pca9685.c +++ b/drivers/pwm/pwm-pca9685.c @@ -323,7 +323,7 @@ static int pca9685_pwm_gpio_probe(struct pwm_chip *chip) pca->gpio.direction_input = pca9685_pwm_gpio_direction_input; pca->gpio.direction_output = pca9685_pwm_gpio_direction_output; pca->gpio.get = pca9685_pwm_gpio_get; - pca->gpio.set_rv = pca9685_pwm_gpio_set; + pca->gpio.set = pca9685_pwm_gpio_set; pca->gpio.base = -1; pca->gpio.ngpio = PCA9685_MAXCHAN; pca->gpio.can_sleep = true; diff --git a/drivers/regulator/rpi-panel-attiny-regulator.c b/drivers/regulator/rpi-panel-attiny-regulator.c index 58dbf8bffa5d..3020839b9ef1 100644 --- a/drivers/regulator/rpi-panel-attiny-regulator.c +++ b/drivers/regulator/rpi-panel-attiny-regulator.c @@ -351,7 +351,7 @@ static int attiny_i2c_probe(struct i2c_client *i2c) state->gc.base = -1; state->gc.ngpio = NUM_GPIO; - state->gc.set_rv = attiny_gpio_set; + state->gc.set = attiny_gpio_set; state->gc.get_direction = attiny_gpio_get_direction; state->gc.can_sleep = true; diff --git a/drivers/soc/fsl/qe/gpio.c b/drivers/soc/fsl/qe/gpio.c index 710a3a03758b..8df1e8fa86a5 100644 --- a/drivers/soc/fsl/qe/gpio.c +++ b/drivers/soc/fsl/qe/gpio.c @@ -321,8 +321,8 @@ static int __init qe_add_gpiochips(void) gc->direction_input = qe_gpio_dir_in; gc->direction_output = qe_gpio_dir_out; gc->get = qe_gpio_get; - gc->set_rv = qe_gpio_set; - gc->set_multiple_rv = qe_gpio_set_multiple; + gc->set = qe_gpio_set; + gc->set_multiple = qe_gpio_set_multiple; ret = of_mm_gpiochip_add_data(np, mm_gc, qe_gc); if (ret) diff --git a/drivers/soc/renesas/pwc-rzv2m.c b/drivers/soc/renesas/pwc-rzv2m.c index 4dbcb3d4a90c..6209168b3734 100644 --- a/drivers/soc/renesas/pwc-rzv2m.c +++ b/drivers/soc/renesas/pwc-rzv2m.c @@ -64,7 +64,7 @@ static const struct gpio_chip rzv2m_pwc_gc = { .label = "gpio_rzv2m_pwc", .owner = THIS_MODULE, .get = rzv2m_pwc_gpio_get, - .set_rv = rzv2m_pwc_gpio_set, + .set = rzv2m_pwc_gpio_set, .direction_output = rzv2m_pwc_gpio_direction_output, .can_sleep = false, .ngpio = 2, diff --git a/drivers/spi/spi-xcomm.c b/drivers/spi/spi-xcomm.c index 1a40c4866ce1..33b78c537520 100644 --- a/drivers/spi/spi-xcomm.c +++ b/drivers/spi/spi-xcomm.c @@ -70,7 +70,7 @@ static int spi_xcomm_gpio_add(struct spi_xcomm *spi_xcomm) return 0; spi_xcomm->gc.get_direction = spi_xcomm_gpio_get_direction; - spi_xcomm->gc.set_rv = spi_xcomm_gpio_set_value; + spi_xcomm->gc.set = spi_xcomm_gpio_set_value; spi_xcomm->gc.can_sleep = 1; spi_xcomm->gc.base = -1; spi_xcomm->gc.ngpio = 1; diff --git a/drivers/ssb/driver_gpio.c b/drivers/ssb/driver_gpio.c index e1f5f0a9c8a2..905657c925bc 100644 --- a/drivers/ssb/driver_gpio.c +++ b/drivers/ssb/driver_gpio.c @@ -225,7 +225,7 @@ static int ssb_gpio_chipco_init(struct ssb_bus *bus) chip->request = ssb_gpio_chipco_request; chip->free = ssb_gpio_chipco_free; chip->get = ssb_gpio_chipco_get_value; - chip->set_rv = ssb_gpio_chipco_set_value; + chip->set = ssb_gpio_chipco_set_value; chip->direction_input = ssb_gpio_chipco_direction_input; chip->direction_output = ssb_gpio_chipco_direction_output; #if IS_ENABLED(CONFIG_SSB_EMBEDDED) @@ -422,7 +422,7 @@ static int ssb_gpio_extif_init(struct ssb_bus *bus) chip->label = "ssb_extif_gpio"; chip->owner = THIS_MODULE; chip->get = ssb_gpio_extif_get_value; - chip->set_rv = ssb_gpio_extif_set_value; + chip->set = ssb_gpio_extif_set_value; chip->direction_input = ssb_gpio_extif_direction_input; chip->direction_output = ssb_gpio_extif_direction_output; #if IS_ENABLED(CONFIG_SSB_EMBEDDED) diff --git a/drivers/staging/greybus/gpio.c b/drivers/staging/greybus/gpio.c index 1280530c8987..ac62b932e6a4 100644 --- a/drivers/staging/greybus/gpio.c +++ b/drivers/staging/greybus/gpio.c @@ -551,7 +551,7 @@ static int gb_gpio_probe(struct gbphy_device *gbphy_dev, gpio->direction_input = gb_gpio_direction_input; gpio->direction_output = gb_gpio_direction_output; gpio->get = gb_gpio_get; - gpio->set_rv = gb_gpio_set; + gpio->set = gb_gpio_set; gpio->set_config = gb_gpio_set_config; gpio->base = -1; /* Allocate base dynamically */ gpio->ngpio = ggc->line_max + 1; diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c index 541c790c0109..ce260e9949c3 100644 --- a/drivers/tty/serial/max310x.c +++ b/drivers/tty/serial/max310x.c @@ -1414,7 +1414,7 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty s->gpio.direction_input = max310x_gpio_direction_input; s->gpio.get = max310x_gpio_get; s->gpio.direction_output= max310x_gpio_direction_output; - s->gpio.set_rv = max310x_gpio_set; + s->gpio.set = max310x_gpio_set; s->gpio.set_config = max310x_gpio_set_config; s->gpio.base = -1; s->gpio.ngpio = devtype->nr * 4; diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index 5ea8aadb6e69..3f38fba8f6ea 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -1425,7 +1425,7 @@ static int sc16is7xx_setup_gpio_chip(struct sc16is7xx_port *s) s->gpio.direction_input = sc16is7xx_gpio_direction_input; s->gpio.get = sc16is7xx_gpio_get; s->gpio.direction_output = sc16is7xx_gpio_direction_output; - s->gpio.set_rv = sc16is7xx_gpio_set; + s->gpio.set = sc16is7xx_gpio_set; s->gpio.base = -1; s->gpio.ngpio = s->devtype->nr_gpio; s->gpio.can_sleep = 1; diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index cfa1d68c7919..36b25418b214 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -1962,7 +1962,7 @@ static int cp210x_gpio_init(struct usb_serial *serial) priv->gc.direction_input = cp210x_gpio_direction_input; priv->gc.direction_output = cp210x_gpio_direction_output; priv->gc.get = cp210x_gpio_get; - priv->gc.set_rv = cp210x_gpio_set; + priv->gc.set = cp210x_gpio_set; priv->gc.set_config = cp210x_gpio_set_config; priv->gc.init_valid_mask = cp210x_gpio_init_valid_mask; priv->gc.owner = THIS_MODULE; diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 7737285a84ba..49666c33b41f 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -2150,9 +2150,9 @@ static int ftdi_gpio_init(struct usb_serial_port *port) priv->gc.direction_output = ftdi_gpio_direction_output; priv->gc.init_valid_mask = ftdi_gpio_init_valid_mask; priv->gc.get = ftdi_gpio_get; - priv->gc.set_rv = ftdi_gpio_set; + priv->gc.set = ftdi_gpio_set; priv->gc.get_multiple = ftdi_gpio_get_multiple; - priv->gc.set_multiple_rv = ftdi_gpio_set_multiple; + priv->gc.set_multiple = ftdi_gpio_set_multiple; priv->gc.owner = THIS_MODULE; priv->gc.parent = &serial->interface->dev; priv->gc.base = -1; diff --git a/drivers/video/fbdev/via/via-gpio.c b/drivers/video/fbdev/via/via-gpio.c index 72302384bf77..45c0a4a6f85c 100644 --- a/drivers/video/fbdev/via/via-gpio.c +++ b/drivers/video/fbdev/via/via-gpio.c @@ -145,7 +145,7 @@ static struct viafb_gpio_cfg viafb_gpio_config = { .label = "VIAFB onboard GPIO", .owner = THIS_MODULE, .direction_output = via_gpio_dir_out, - .set_rv = via_gpio_set, + .set = via_gpio_set, .direction_input = via_gpio_dir_input, .get = via_gpio_get, .base = -1, diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 90567dde7d8e..667f8fd58a79 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -347,10 +347,10 @@ struct gpio_irq_chip { * @get: returns value for signal "offset", 0=low, 1=high, or negative error * @get_multiple: reads values for multiple signals defined by "mask" and * stores them in "bits", returns 0 on success or negative error - * @set_rv: assigns output value for signal "offset", returns 0 on success or - * negative error value - * @set_multiple_rv: assigns output values for multiple signals defined by - * "mask", returns 0 on success or negative error value + * @set: assigns output value for signal "offset", returns 0 on success or + * negative error value + * @set_multiple: assigns output values for multiple signals defined by + * "mask", returns 0 on success or negative error value * @set_config: optional hook for all kinds of settings. Uses the same * packed config format as generic pinconf. Must return 0 on success and * a negative error number on failure. @@ -443,12 +443,11 @@ struct gpio_chip { int (*get_multiple)(struct gpio_chip *gc, unsigned long *mask, unsigned long *bits); - int (*set_rv)(struct gpio_chip *gc, - unsigned int offset, - int value); - int (*set_multiple_rv)(struct gpio_chip *gc, - unsigned long *mask, - unsigned long *bits); + int (*set)(struct gpio_chip *gc, + unsigned int offset, int value); + int (*set_multiple)(struct gpio_chip *gc, + unsigned long *mask, + unsigned long *bits); int (*set_config)(struct gpio_chip *gc, unsigned int offset, unsigned long config); diff --git a/include/linux/gpio/generic.h b/include/linux/gpio/generic.h index b511acd58ab0..f3a8db4598bb 100644 --- a/include/linux/gpio/generic.h +++ b/include/linux/gpio/generic.h @@ -88,10 +88,10 @@ static inline int gpio_generic_chip_set(struct gpio_generic_chip *chip, unsigned int offset, int value) { - if (WARN_ON(!chip->gc.set_rv)) + if (WARN_ON(!chip->gc.set)) return -EOPNOTSUPP; - return chip->gc.set_rv(&chip->gc, offset, value); + return chip->gc.set(&chip->gc, offset, value); } #define gpio_generic_chip_lock(gen_gc) \ diff --git a/sound/hda/codecs/side-codecs/cirrus_scodec_test.c b/sound/hda/codecs/side-codecs/cirrus_scodec_test.c index 93b9cbf1f08a..9ba14c09c07f 100644 --- a/sound/hda/codecs/side-codecs/cirrus_scodec_test.c +++ b/sound/hda/codecs/side-codecs/cirrus_scodec_test.c @@ -86,7 +86,7 @@ static const struct gpio_chip cirrus_scodec_test_gpio_chip = { .direction_input = cirrus_scodec_test_gpio_direction_in, .get = cirrus_scodec_test_gpio_get, .direction_output = cirrus_scodec_test_gpio_direction_out, - .set_rv = cirrus_scodec_test_gpio_set, + .set = cirrus_scodec_test_gpio_set, .set_config = cirrus_scodec_test_gpio_set_config, .base = -1, .ngpio = 32, diff --git a/sound/soc/codecs/idt821034.c b/sound/soc/codecs/idt821034.c index 55e90604bbaa..6738cf21983b 100644 --- a/sound/soc/codecs/idt821034.c +++ b/sound/soc/codecs/idt821034.c @@ -1117,7 +1117,7 @@ static int idt821034_gpio_init(struct idt821034 *idt821034) idt821034->gpio_chip.direction_input = idt821034_chip_direction_input; idt821034->gpio_chip.direction_output = idt821034_chip_direction_output; idt821034->gpio_chip.get = idt821034_chip_gpio_get; - idt821034->gpio_chip.set_rv = idt821034_chip_gpio_set; + idt821034->gpio_chip.set = idt821034_chip_gpio_set; idt821034->gpio_chip.can_sleep = true; return devm_gpiochip_add_data(&idt821034->spi->dev, &idt821034->gpio_chip, diff --git a/sound/soc/codecs/peb2466.c b/sound/soc/codecs/peb2466.c index b8905c03445e..c0c5b3c3e98b 100644 --- a/sound/soc/codecs/peb2466.c +++ b/sound/soc/codecs/peb2466.c @@ -1945,7 +1945,7 @@ static int peb2466_gpio_init(struct peb2466 *peb2466) peb2466->gpio.gpio_chip.direction_input = peb2466_chip_direction_input; peb2466->gpio.gpio_chip.direction_output = peb2466_chip_direction_output; peb2466->gpio.gpio_chip.get = peb2466_chip_gpio_get; - peb2466->gpio.gpio_chip.set_rv = peb2466_chip_gpio_set; + peb2466->gpio.gpio_chip.set = peb2466_chip_gpio_set; peb2466->gpio.gpio_chip.can_sleep = true; return devm_gpiochip_add_data(&peb2466->spi->dev, &peb2466->gpio.gpio_chip, diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c index 69a0fb8d7f77..6b6c690a9e45 100644 --- a/sound/soc/codecs/rt5677.c +++ b/sound/soc/codecs/rt5677.c @@ -4835,7 +4835,7 @@ static const struct gpio_chip rt5677_template_chip = { .label = RT5677_DRV_NAME, .owner = THIS_MODULE, .direction_output = rt5677_gpio_direction_out, - .set_rv = rt5677_gpio_set, + .set = rt5677_gpio_set, .direction_input = rt5677_gpio_direction_in, .get = rt5677_gpio_get, .to_irq = rt5677_to_irq, diff --git a/sound/soc/codecs/tlv320adc3xxx.c b/sound/soc/codecs/tlv320adc3xxx.c index 1035ba17dc5d..258fbcaf345a 100644 --- a/sound/soc/codecs/tlv320adc3xxx.c +++ b/sound/soc/codecs/tlv320adc3xxx.c @@ -1052,7 +1052,7 @@ static const struct gpio_chip adc3xxx_gpio_chip = { .owner = THIS_MODULE, .request = adc3xxx_gpio_request, .direction_output = adc3xxx_gpio_direction_out, - .set_rv = adc3xxx_gpio_set, + .set = adc3xxx_gpio_set, .get = adc3xxx_gpio_get, .can_sleep = 1, }; diff --git a/sound/soc/codecs/wm5100.c b/sound/soc/codecs/wm5100.c index fb5ed4ba7f60..2d0a20f2fd8c 100644 --- a/sound/soc/codecs/wm5100.c +++ b/sound/soc/codecs/wm5100.c @@ -2290,7 +2290,7 @@ static const struct gpio_chip wm5100_template_chip = { .label = "wm5100", .owner = THIS_MODULE, .direction_output = wm5100_gpio_direction_out, - .set_rv = wm5100_gpio_set, + .set = wm5100_gpio_set, .direction_input = wm5100_gpio_direction_in, .get = wm5100_gpio_get, .can_sleep = 1, diff --git a/sound/soc/codecs/wm8903.c b/sound/soc/codecs/wm8903.c index 2ed9f493d507..f7d726e3052c 100644 --- a/sound/soc/codecs/wm8903.c +++ b/sound/soc/codecs/wm8903.c @@ -1843,7 +1843,7 @@ static const struct gpio_chip wm8903_template_chip = { .direction_input = wm8903_gpio_direction_in, .get = wm8903_gpio_get, .direction_output = wm8903_gpio_direction_out, - .set_rv = wm8903_gpio_set, + .set = wm8903_gpio_set, .can_sleep = 1, }; diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c index d69aa8b15629..7bf6b88c056c 100644 --- a/sound/soc/codecs/wm8962.c +++ b/sound/soc/codecs/wm8962.c @@ -3442,7 +3442,7 @@ static const struct gpio_chip wm8962_template_chip = { .owner = THIS_MODULE, .request = wm8962_gpio_request, .direction_output = wm8962_gpio_direction_out, - .set_rv = wm8962_gpio_set, + .set = wm8962_gpio_set, .can_sleep = 1, }; diff --git a/sound/soc/codecs/wm8996.c b/sound/soc/codecs/wm8996.c index e364d0da9044..459b39998307 100644 --- a/sound/soc/codecs/wm8996.c +++ b/sound/soc/codecs/wm8996.c @@ -2186,7 +2186,7 @@ static const struct gpio_chip wm8996_template_chip = { .label = "wm8996", .owner = THIS_MODULE, .direction_output = wm8996_gpio_direction_out, - .set_rv = wm8996_gpio_set, + .set = wm8996_gpio_set, .direction_input = wm8996_gpio_direction_in, .get = wm8996_gpio_get, .can_sleep = 1, diff --git a/sound/soc/codecs/zl38060.c b/sound/soc/codecs/zl38060.c index 180d45a349ac..7de4014e626d 100644 --- a/sound/soc/codecs/zl38060.c +++ b/sound/soc/codecs/zl38060.c @@ -440,7 +440,7 @@ static const struct gpio_chip template_chip = { .direction_input = chip_direction_input, .direction_output = chip_direction_output, .get = chip_gpio_get, - .set_rv = chip_gpio_set, + .set = chip_gpio_set, .can_sleep = true, }; diff --git a/sound/soc/soc-ac97.c b/sound/soc/soc-ac97.c index 29790807d785..37486d6a438e 100644 --- a/sound/soc/soc-ac97.c +++ b/sound/soc/soc-ac97.c @@ -125,7 +125,7 @@ static const struct gpio_chip snd_soc_ac97_gpio_chip = { .direction_input = snd_soc_ac97_gpio_direction_in, .get = snd_soc_ac97_gpio_get, .direction_output = snd_soc_ac97_gpio_direction_out, - .set_rv = snd_soc_ac97_gpio_set, + .set = snd_soc_ac97_gpio_set, .can_sleep = 1, }; diff --git a/sound/soc/ti/davinci-mcasp.c b/sound/soc/ti/davinci-mcasp.c index caf1887cc9d1..621a9d5f9377 100644 --- a/sound/soc/ti/davinci-mcasp.c +++ b/sound/soc/ti/davinci-mcasp.c @@ -2218,7 +2218,7 @@ static const struct gpio_chip davinci_mcasp_template_chip = { .request = davinci_mcasp_gpio_request, .free = davinci_mcasp_gpio_free, .direction_output = davinci_mcasp_gpio_direction_out, - .set_rv = davinci_mcasp_gpio_set, + .set = davinci_mcasp_gpio_set, .direction_input = davinci_mcasp_gpio_direction_in, .get = davinci_mcasp_gpio_get, .get_direction = davinci_mcasp_gpio_get_direction, -- cgit v1.2.3 From 42e6c6ce03fd3e41e39a0f93f9b1a1d9fa664338 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Thu, 7 Aug 2025 11:24:12 +0800 Subject: lib/sbitmap: convert shallow_depth from one word to the whole sbitmap Currently elevators will record internal 'async_depth' to throttle asynchronous requests, and they both calculate shallow_dpeth based on sb->shift, with the respect that sb->shift is the available tags in one word. However, sb->shift is not the availbale tags in the last word, see __map_depth: if (index == sb->map_nr - 1) return sb->depth - (index << sb->shift); For consequence, if the last word is used, more tags can be get than expected, for example, assume nr_requests=256 and there are four words, in the worst case if user set nr_requests=32, then the first word is the last word, and still use bits per word, which is 64, to calculate async_depth is wrong. One the ohter hand, due to cgroup qos, bfq can allow only one request to be allocated, and set shallow_dpeth=1 will still allow the number of words request to be allocated. Fix this problems by using shallow_depth to the whole sbitmap instead of per word, also change kyber, mq-deadline and bfq to follow this, a new helper __map_depth_with_shallow() is introduced to calculate available bits in each word. Signed-off-by: Yu Kuai Link: https://lore.kernel.org/r/20250807032413.1469456-2-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe --- block/bfq-iosched.c | 35 ++++++++++++++----------------- block/bfq-iosched.h | 3 +-- block/kyber-iosched.c | 9 ++------ block/mq-deadline.c | 16 +------------- include/linux/sbitmap.h | 6 +++--- lib/sbitmap.c | 56 +++++++++++++++++++++++++------------------------ 6 files changed, 52 insertions(+), 73 deletions(-) (limited to 'include/linux') diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index aca9886c9ee3..3bf76902f07f 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -694,17 +694,13 @@ static void bfq_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data) { struct bfq_data *bfqd = data->q->elevator->elevator_data; struct bfq_io_cq *bic = bfq_bic_lookup(data->q); - int depth; - unsigned limit = data->q->nr_requests; - unsigned int act_idx; + unsigned int limit, act_idx; /* Sync reads have full depth available */ - if (op_is_sync(opf) && !op_is_write(opf)) { - depth = 0; - } else { - depth = bfqd->word_depths[!!bfqd->wr_busy_queues][op_is_sync(opf)]; - limit = (limit * depth) >> bfqd->full_depth_shift; - } + if (op_is_sync(opf) && !op_is_write(opf)) + limit = data->q->nr_requests; + else + limit = bfqd->async_depths[!!bfqd->wr_busy_queues][op_is_sync(opf)]; for (act_idx = 0; bic && act_idx < bfqd->num_actuators; act_idx++) { /* Fast path to check if bfqq is already allocated. */ @@ -718,14 +714,16 @@ static void bfq_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data) * available requests and thus starve other entities. */ if (bfqq_request_over_limit(bfqd, bic, opf, act_idx, limit)) { - depth = 1; + limit = 1; break; } } + bfq_log(bfqd, "[%s] wr_busy %d sync %d depth %u", - __func__, bfqd->wr_busy_queues, op_is_sync(opf), depth); - if (depth) - data->shallow_depth = depth; + __func__, bfqd->wr_busy_queues, op_is_sync(opf), limit); + + if (limit < data->q->nr_requests) + data->shallow_depth = limit; } static struct bfq_queue * @@ -7114,9 +7112,8 @@ void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg) */ static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt) { - unsigned int depth = 1U << bt->sb.shift; + unsigned int nr_requests = bfqd->queue->nr_requests; - bfqd->full_depth_shift = bt->sb.shift; /* * In-word depths if no bfq_queue is being weight-raised: * leaving 25% of tags only for sync reads. @@ -7128,13 +7125,13 @@ static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt) * limit 'something'. */ /* no more than 50% of tags for async I/O */ - bfqd->word_depths[0][0] = max(depth >> 1, 1U); + bfqd->async_depths[0][0] = max(nr_requests >> 1, 1U); /* * no more than 75% of tags for sync writes (25% extra tags * w.r.t. async I/O, to prevent async I/O from starving sync * writes) */ - bfqd->word_depths[0][1] = max((depth * 3) >> 2, 1U); + bfqd->async_depths[0][1] = max((nr_requests * 3) >> 2, 1U); /* * In-word depths in case some bfq_queue is being weight- @@ -7144,9 +7141,9 @@ static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt) * shortage. */ /* no more than ~18% of tags for async I/O */ - bfqd->word_depths[1][0] = max((depth * 3) >> 4, 1U); + bfqd->async_depths[1][0] = max((nr_requests * 3) >> 4, 1U); /* no more than ~37% of tags for sync writes (~20% extra tags) */ - bfqd->word_depths[1][1] = max((depth * 6) >> 4, 1U); + bfqd->async_depths[1][1] = max((nr_requests * 6) >> 4, 1U); } static void bfq_depth_updated(struct blk_mq_hw_ctx *hctx) diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index 0b4704932d72..34a498e6b2a5 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -813,8 +813,7 @@ struct bfq_data { * Depth limits used in bfq_limit_depth (see comments on the * function) */ - unsigned int word_depths[2][2]; - unsigned int full_depth_shift; + unsigned int async_depths[2][2]; /* * Number of independent actuators. This is equal to 1 in diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index 7b6832cb3a8d..70cbc7b2deb4 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -157,10 +157,7 @@ struct kyber_queue_data { */ struct sbitmap_queue domain_tokens[KYBER_NUM_DOMAINS]; - /* - * Async request percentage, converted to per-word depth for - * sbitmap_get_shallow(). - */ + /* Number of allowed async requests. */ unsigned int async_depth; struct kyber_cpu_latency __percpu *cpu_latency; @@ -447,10 +444,8 @@ static void kyber_depth_updated(struct blk_mq_hw_ctx *hctx) { struct kyber_queue_data *kqd = hctx->queue->elevator->elevator_data; struct blk_mq_tags *tags = hctx->sched_tags; - unsigned int shift = tags->bitmap_tags.sb.shift; - - kqd->async_depth = (1U << shift) * KYBER_ASYNC_PERCENT / 100U; + kqd->async_depth = hctx->queue->nr_requests * KYBER_ASYNC_PERCENT / 100U; sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, kqd->async_depth); } diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 7b6caf30e00a..b9b7cdf1d3c9 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -487,20 +487,6 @@ unlock: return rq; } -/* - * 'depth' is a number in the range 1..INT_MAX representing a number of - * requests. Scale it with a factor (1 << bt->sb.shift) / q->nr_requests since - * 1..(1 << bt->sb.shift) is the range expected by sbitmap_get_shallow(). - * Values larger than q->nr_requests have the same effect as q->nr_requests. - */ -static int dd_to_word_depth(struct blk_mq_hw_ctx *hctx, unsigned int qdepth) -{ - struct sbitmap_queue *bt = &hctx->sched_tags->bitmap_tags; - const unsigned int nrr = hctx->queue->nr_requests; - - return ((qdepth << bt->sb.shift) + nrr - 1) / nrr; -} - /* * Called by __blk_mq_alloc_request(). The shallow_depth value set by this * function is used by __blk_mq_get_tag(). @@ -517,7 +503,7 @@ static void dd_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data) * Throttle asynchronous requests and writes such that these requests * do not block the allocation of synchronous requests. */ - data->shallow_depth = dd_to_word_depth(data->hctx, dd->async_depth); + data->shallow_depth = dd->async_depth; } /* Called by blk_mq_update_nr_requests(). */ diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index 189140bf11fc..4adf4b364fcd 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -213,12 +213,12 @@ int sbitmap_get(struct sbitmap *sb); * sbitmap_get_shallow() - Try to allocate a free bit from a &struct sbitmap, * limiting the depth used from each word. * @sb: Bitmap to allocate from. - * @shallow_depth: The maximum number of bits to allocate from a single word. + * @shallow_depth: The maximum number of bits to allocate from the bitmap. * * This rather specific operation allows for having multiple users with * different allocation limits. E.g., there can be a high-priority class that * uses sbitmap_get() and a low-priority class that uses sbitmap_get_shallow() - * with a @shallow_depth of (1 << (@sb->shift - 1)). Then, the low-priority + * with a @shallow_depth of (sb->depth >> 1). Then, the low-priority * class can only allocate half of the total bits in the bitmap, preventing it * from starving out the high-priority class. * @@ -478,7 +478,7 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags, * sbitmap_queue, limiting the depth used from each word, with preemption * already disabled. * @sbq: Bitmap queue to allocate from. - * @shallow_depth: The maximum number of bits to allocate from a single word. + * @shallow_depth: The maximum number of bits to allocate from the queue. * See sbitmap_get_shallow(). * * If you call this, make sure to call sbitmap_queue_min_shallow_depth() after diff --git a/lib/sbitmap.c b/lib/sbitmap.c index d3412984170c..c07e3cd82e29 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -208,8 +208,28 @@ static int sbitmap_find_bit_in_word(struct sbitmap_word *map, return nr; } +static unsigned int __map_depth_with_shallow(const struct sbitmap *sb, + int index, + unsigned int shallow_depth) +{ + u64 shallow_word_depth; + unsigned int word_depth, reminder; + + word_depth = __map_depth(sb, index); + if (shallow_depth >= sb->depth) + return word_depth; + + shallow_word_depth = word_depth * shallow_depth; + reminder = do_div(shallow_word_depth, sb->depth); + + if (reminder >= (index + 1) * word_depth) + shallow_word_depth++; + + return (unsigned int)shallow_word_depth; +} + static int sbitmap_find_bit(struct sbitmap *sb, - unsigned int depth, + unsigned int shallow_depth, unsigned int index, unsigned int alloc_hint, bool wrap) @@ -218,12 +238,12 @@ static int sbitmap_find_bit(struct sbitmap *sb, int nr = -1; for (i = 0; i < sb->map_nr; i++) { - nr = sbitmap_find_bit_in_word(&sb->map[index], - min_t(unsigned int, - __map_depth(sb, index), - depth), - alloc_hint, wrap); + unsigned int depth = __map_depth_with_shallow(sb, index, + shallow_depth); + if (depth) + nr = sbitmap_find_bit_in_word(&sb->map[index], depth, + alloc_hint, wrap); if (nr != -1) { nr += index << sb->shift; break; @@ -406,27 +426,9 @@ EXPORT_SYMBOL_GPL(sbitmap_bitmap_show); static unsigned int sbq_calc_wake_batch(struct sbitmap_queue *sbq, unsigned int depth) { - unsigned int wake_batch; - unsigned int shallow_depth; - - /* - * Each full word of the bitmap has bits_per_word bits, and there might - * be a partial word. There are depth / bits_per_word full words and - * depth % bits_per_word bits left over. In bitwise arithmetic: - * - * bits_per_word = 1 << shift - * depth / bits_per_word = depth >> shift - * depth % bits_per_word = depth & ((1 << shift) - 1) - * - * Each word can be limited to sbq->min_shallow_depth bits. - */ - shallow_depth = min(1U << sbq->sb.shift, sbq->min_shallow_depth); - depth = ((depth >> sbq->sb.shift) * shallow_depth + - min(depth & ((1U << sbq->sb.shift) - 1), shallow_depth)); - wake_batch = clamp_t(unsigned int, depth / SBQ_WAIT_QUEUES, 1, - SBQ_WAKE_BATCH); - - return wake_batch; + return clamp_t(unsigned int, + min(depth, sbq->min_shallow_depth) / SBQ_WAIT_QUEUES, + 1, SBQ_WAKE_BATCH); } int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth, -- cgit v1.2.3 From 45fa9f97e65231a9fd4f9429489cb74c10ccd0fd Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Thu, 7 Aug 2025 11:24:13 +0800 Subject: lib/sbitmap: make sbitmap_get_shallow() internal Because it's only used in sbitmap.c Signed-off-by: Yu Kuai Reviewed-by: Damien Le Moal Reviewed-by: Jan Kara Reviewed-by: Bart Van Assche Link: https://lore.kernel.org/r/20250807032413.1469456-3-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe --- include/linux/sbitmap.h | 17 ----------------- lib/sbitmap.c | 18 ++++++++++++++++-- 2 files changed, 16 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index 4adf4b364fcd..ffb9907c7070 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -209,23 +209,6 @@ void sbitmap_resize(struct sbitmap *sb, unsigned int depth); */ int sbitmap_get(struct sbitmap *sb); -/** - * sbitmap_get_shallow() - Try to allocate a free bit from a &struct sbitmap, - * limiting the depth used from each word. - * @sb: Bitmap to allocate from. - * @shallow_depth: The maximum number of bits to allocate from the bitmap. - * - * This rather specific operation allows for having multiple users with - * different allocation limits. E.g., there can be a high-priority class that - * uses sbitmap_get() and a low-priority class that uses sbitmap_get_shallow() - * with a @shallow_depth of (sb->depth >> 1). Then, the low-priority - * class can only allocate half of the total bits in the bitmap, preventing it - * from starving out the high-priority class. - * - * Return: Non-negative allocated bit number if successful, -1 otherwise. - */ -int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth); - /** * sbitmap_any_bit_set() - Check for a set bit in a &struct sbitmap. * @sb: Bitmap to check. diff --git a/lib/sbitmap.c b/lib/sbitmap.c index c07e3cd82e29..4d188d05db15 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -307,7 +307,22 @@ static int __sbitmap_get_shallow(struct sbitmap *sb, return sbitmap_find_bit(sb, shallow_depth, index, alloc_hint, true); } -int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth) +/** + * sbitmap_get_shallow() - Try to allocate a free bit from a &struct sbitmap, + * limiting the depth used from each word. + * @sb: Bitmap to allocate from. + * @shallow_depth: The maximum number of bits to allocate from the bitmap. + * + * This rather specific operation allows for having multiple users with + * different allocation limits. E.g., there can be a high-priority class that + * uses sbitmap_get() and a low-priority class that uses sbitmap_get_shallow() + * with a @shallow_depth of (sb->depth >> 1). Then, the low-priority + * class can only allocate half of the total bits in the bitmap, preventing it + * from starving out the high-priority class. + * + * Return: Non-negative allocated bit number if successful, -1 otherwise. + */ +static int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth) { int nr; unsigned int hint, depth; @@ -322,7 +337,6 @@ int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth) return nr; } -EXPORT_SYMBOL_GPL(sbitmap_get_shallow); bool sbitmap_any_bit_set(const struct sbitmap *sb) { -- cgit v1.2.3 From 2c223f7239f376a90d71903ec474ba887cf21d94 Mon Sep 17 00:00:00 2001 From: Oreoluwa Babatunde Date: Wed, 6 Aug 2025 10:24:21 -0700 Subject: of: reserved_mem: Restructure call site for dma_contiguous_early_fixup() Restructure the call site for dma_contiguous_early_fixup() to where the reserved_mem nodes are being parsed from the DT so that dma_mmu_remap[] is populated before dma_contiguous_remap() is called. Fixes: 8a6e02d0c00e ("of: reserved_mem: Restructure how the reserved memory regions are processed") Signed-off-by: Oreoluwa Babatunde Tested-by: William Zhang Signed-off-by: Marek Szyprowski Link: https://lore.kernel.org/r/20250806172421.2748302-1-oreoluwa.babatunde@oss.qualcomm.com --- drivers/of/of_reserved_mem.c | 16 ++++++++++++---- include/linux/dma-map-ops.h | 3 +++ kernel/dma/contiguous.c | 2 -- 3 files changed, 15 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c index 77016c0cc296..7350b23cb734 100644 --- a/drivers/of/of_reserved_mem.c +++ b/drivers/of/of_reserved_mem.c @@ -25,6 +25,7 @@ #include #include #include +#include #include "of_private.h" @@ -175,13 +176,17 @@ static int __init __reserved_mem_reserve_reg(unsigned long node, base = dt_mem_next_cell(dt_root_addr_cells, &prop); size = dt_mem_next_cell(dt_root_size_cells, &prop); - if (size && - early_init_dt_reserve_memory(base, size, nomap) == 0) + if (size && early_init_dt_reserve_memory(base, size, nomap) == 0) { + /* Architecture specific contiguous memory fixup. */ + if (of_flat_dt_is_compatible(node, "shared-dma-pool") && + of_get_flat_dt_prop(node, "reusable", NULL)) + dma_contiguous_early_fixup(base, size); pr_debug("Reserved memory: reserved region for node '%s': base %pa, size %lu MiB\n", uname, &base, (unsigned long)(size / SZ_1M)); - else + } else { pr_err("Reserved memory: failed to reserve memory for node '%s': base %pa, size %lu MiB\n", uname, &base, (unsigned long)(size / SZ_1M)); + } len -= t_len; } @@ -472,7 +477,10 @@ static int __init __reserved_mem_alloc_size(unsigned long node, const char *unam uname, (unsigned long)(size / SZ_1M)); return -ENOMEM; } - + /* Architecture specific contiguous memory fixup. */ + if (of_flat_dt_is_compatible(node, "shared-dma-pool") && + of_get_flat_dt_prop(node, "reusable", NULL)) + dma_contiguous_early_fixup(base, size); /* Save region in the reserved_mem array */ fdt_reserved_mem_save_node(node, uname, base, size); return 0; diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index f48e5fb88bd5..332b80c42b6f 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -153,6 +153,9 @@ static inline void dma_free_contiguous(struct device *dev, struct page *page, { __free_pages(page, get_order(size)); } +static inline void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) +{ +} #endif /* CONFIG_DMA_CMA*/ #ifdef CONFIG_DMA_DECLARE_COHERENT diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c index 67af8a55185d..d9b9dcba6ff7 100644 --- a/kernel/dma/contiguous.c +++ b/kernel/dma/contiguous.c @@ -483,8 +483,6 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem) pr_err("Reserved memory: unable to setup CMA region\n"); return err; } - /* Architecture specific contiguous memory fixup. */ - dma_contiguous_early_fixup(rmem->base, rmem->size); if (default_cma) dma_contiguous_default_area = cma; -- cgit v1.2.3 From 6d3c3ca4c77e93660cce5819bf707f75df03e0c8 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 8 Aug 2025 15:28:47 +0200 Subject: module: Rename EXPORT_SYMBOL_GPL_FOR_MODULES to EXPORT_SYMBOL_FOR_MODULES Christoph suggested that the explicit _GPL_ can be dropped from the module namespace export macro, as it's intended for in-tree modules only. It would be possible to restrict it technically, but it was pointed out [2] that some cases of using an out-of-tree build of an in-tree module with the same name are legitimate. But in that case those also have to be GPL anyway so it's unnecessary to spell it out in the macro name. Link: https://lore.kernel.org/all/aFleJN_fE-RbSoFD@infradead.org/ [1] Link: https://lore.kernel.org/all/CAK7LNATRkZHwJGpojCnvdiaoDnP%2BaeUXgdey5sb_8muzdWTMkA@mail.gmail.com/ [2] Suggested-by: Christoph Hellwig Reviewed-by: Shivank Garg Acked-by: David Hildenbrand Acked-by: Nicolas Schier Reviewed-by: Daniel Gomez Reviewed-by: Christian Brauner Signed-off-by: Vlastimil Babka Link: https://lore.kernel.org/20250808-export_modules-v4-1-426945bcc5e1@suse.cz Signed-off-by: Christian Brauner --- Documentation/core-api/symbol-namespaces.rst | 11 ++++++----- drivers/tty/serial/8250/8250_rsa.c | 8 ++++---- fs/anon_inodes.c | 2 +- include/linux/export.h | 2 +- 4 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/Documentation/core-api/symbol-namespaces.rst b/Documentation/core-api/symbol-namespaces.rst index 32fc73dc5529..034898e81ba2 100644 --- a/Documentation/core-api/symbol-namespaces.rst +++ b/Documentation/core-api/symbol-namespaces.rst @@ -76,20 +76,21 @@ unit as preprocessor statement. The above example would then read:: within the corresponding compilation unit before the #include for . Typically it's placed before the first #include statement. -Using the EXPORT_SYMBOL_GPL_FOR_MODULES() macro ------------------------------------------------ +Using the EXPORT_SYMBOL_FOR_MODULES() macro +------------------------------------------- Symbols exported using this macro are put into a module namespace. This -namespace cannot be imported. +namespace cannot be imported. These exports are GPL-only as they are only +intended for in-tree modules. The macro takes a comma separated list of module names, allowing only those modules to access this symbol. Simple tail-globs are supported. For example:: - EXPORT_SYMBOL_GPL_FOR_MODULES(preempt_notifier_inc, "kvm,kvm-*") + EXPORT_SYMBOL_FOR_MODULES(preempt_notifier_inc, "kvm,kvm-*") -will limit usage of this symbol to modules whoes name matches the given +will limit usage of this symbol to modules whose name matches the given patterns. How to use Symbols exported in Namespaces diff --git a/drivers/tty/serial/8250/8250_rsa.c b/drivers/tty/serial/8250/8250_rsa.c index d34093cc03ad..12a65b79583c 100644 --- a/drivers/tty/serial/8250/8250_rsa.c +++ b/drivers/tty/serial/8250/8250_rsa.c @@ -147,7 +147,7 @@ void rsa_enable(struct uart_8250_port *up) if (up->port.uartclk == SERIAL_RSA_BAUD_BASE * 16) serial_out(up, UART_RSA_FRR, 0); } -EXPORT_SYMBOL_GPL_FOR_MODULES(rsa_enable, "8250_base"); +EXPORT_SYMBOL_FOR_MODULES(rsa_enable, "8250_base"); /* * Attempts to turn off the RSA FIFO and resets the RSA board back to 115kbps compat mode. It is @@ -179,7 +179,7 @@ void rsa_disable(struct uart_8250_port *up) up->port.uartclk = SERIAL_RSA_BAUD_BASE_LO * 16; uart_port_unlock_irq(&up->port); } -EXPORT_SYMBOL_GPL_FOR_MODULES(rsa_disable, "8250_base"); +EXPORT_SYMBOL_FOR_MODULES(rsa_disable, "8250_base"); void rsa_autoconfig(struct uart_8250_port *up) { @@ -192,7 +192,7 @@ void rsa_autoconfig(struct uart_8250_port *up) if (__rsa_enable(up)) up->port.type = PORT_RSA; } -EXPORT_SYMBOL_GPL_FOR_MODULES(rsa_autoconfig, "8250_base"); +EXPORT_SYMBOL_FOR_MODULES(rsa_autoconfig, "8250_base"); void rsa_reset(struct uart_8250_port *up) { @@ -201,7 +201,7 @@ void rsa_reset(struct uart_8250_port *up) serial_out(up, UART_RSA_FRR, 0); } -EXPORT_SYMBOL_GPL_FOR_MODULES(rsa_reset, "8250_base"); +EXPORT_SYMBOL_FOR_MODULES(rsa_reset, "8250_base"); #ifdef CONFIG_SERIAL_8250_DEPRECATED_OPTIONS #ifndef MODULE diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 1d847a939f29..180a458fc4f7 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -129,7 +129,7 @@ struct inode *anon_inode_make_secure_inode(struct super_block *sb, const char *n } return inode; } -EXPORT_SYMBOL_GPL_FOR_MODULES(anon_inode_make_secure_inode, "kvm"); +EXPORT_SYMBOL_FOR_MODULES(anon_inode_make_secure_inode, "kvm"); static struct file *__anon_inode_getfile(const char *name, const struct file_operations *fops, diff --git a/include/linux/export.h b/include/linux/export.h index f35d03b4113b..a686fd0ba406 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -91,6 +91,6 @@ #define EXPORT_SYMBOL_NS(sym, ns) __EXPORT_SYMBOL(sym, "", ns) #define EXPORT_SYMBOL_NS_GPL(sym, ns) __EXPORT_SYMBOL(sym, "GPL", ns) -#define EXPORT_SYMBOL_GPL_FOR_MODULES(sym, mods) __EXPORT_SYMBOL(sym, "GPL", "module:" mods) +#define EXPORT_SYMBOL_FOR_MODULES(sym, mods) __EXPORT_SYMBOL(sym, "GPL", "module:" mods) #endif /* _LINUX_EXPORT_H */ -- cgit v1.2.3 From 5634c8cb298a7146b4e38873473e280b50e27a2c Mon Sep 17 00:00:00 2001 From: Nitin Gote Date: Fri, 18 Jul 2025 16:20:51 +0530 Subject: iosys-map: Fix undefined behavior in iosys_map_clear() The current iosys_map_clear() implementation reads the potentially uninitialized 'is_iomem' boolean field to decide which union member to clear. This causes undefined behavior when called on uninitialized structures, as 'is_iomem' may contain garbage values like 0xFF. UBSAN detects this as: UBSAN: invalid-load in include/linux/iosys-map.h:267 load of value 255 is not a valid value for type '_Bool' Fix by unconditionally clearing the entire structure with memset(), eliminating the need to read uninitialized data and ensuring all fields are set to known good values. Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14639 Fixes: 01fd30da0474 ("dma-buf: Add struct dma-buf-map for storing struct dma_buf.vaddr_ptr") Signed-off-by: Nitin Gote Reviewed-by: Andi Shyti Reviewed-by: Thomas Zimmermann Signed-off-by: Thomas Zimmermann Link: https://lore.kernel.org/r/20250718105051.2709487-1-nitin.r.gote@intel.com --- include/linux/iosys-map.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iosys-map.h b/include/linux/iosys-map.h index 4696abfd311c..3e85afe794c0 100644 --- a/include/linux/iosys-map.h +++ b/include/linux/iosys-map.h @@ -264,12 +264,7 @@ static inline bool iosys_map_is_set(const struct iosys_map *map) */ static inline void iosys_map_clear(struct iosys_map *map) { - if (map->is_iomem) { - map->vaddr_iomem = NULL; - map->is_iomem = false; - } else { - map->vaddr = NULL; - } + memset(map, 0, sizeof(*map)); } /** -- cgit v1.2.3 From ccba9f6baa900e31ad1a4c36e6f3c176694f9eac Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 8 Aug 2025 17:12:04 -0700 Subject: net: update NAPI threaded config even for disabled NAPIs We have to make sure that all future NAPIs will have the right threaded state when the state is configured on the device level. We chose not to have an "unset" state for threaded, and not to wipe the NAPI config clean when channels are explicitly disabled. This means the persistent config structs "exist" even when their NAPIs are not instantiated. Differently put - the NAPI persistent state lives in the net_device (ncfg == struct napi_config): ,--- [napi 0] - [napi 1] [dev] | | `--- [ncfg 0] - [ncfg 1] so say we a device with 2 queues but only 1 enabled: ,--- [napi 0] [dev] | `--- [ncfg 0] - [ncfg 1] now we set the device to threaded=1: ,---------- [napi 0 (thr:1)] [dev(thr:1)] | `---------- [ncfg 0 (thr:1)] - [ncfg 1 (thr:?)] Since [ncfg 1] was not attached to a NAPI during configuration we skipped it. If we create a NAPI for it later it will have the old setting (presumably disabled). One could argue if this is right or not "in principle", but it's definitely not how things worked before per-NAPI config.. Fixes: 2677010e7793 ("Add support to set NAPI threaded for individual NAPI") Signed-off-by: Jakub Kicinski Reviewed-by: Joe Damato Link: https://patch.msgid.link/20250809001205.1147153-3-kuba@kernel.org Signed-off-by: Paolo Abeni --- include/linux/netdevice.h | 5 ++++- net/core/dev.c | 7 ++++++- 2 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5e5de4b0a433..f3a3b761abfb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2071,6 +2071,8 @@ enum netdev_reg_state { * @max_pacing_offload_horizon: max EDT offload horizon in nsec. * @napi_config: An array of napi_config structures containing per-NAPI * settings. + * @num_napi_configs: number of allocated NAPI config structs, + * always >= max(num_rx_queues, num_tx_queues). * @gro_flush_timeout: timeout for GRO layer in NAPI * @napi_defer_hard_irqs: If not zero, provides a counter that would * allow to avoid NIC hard IRQ, on busy queues. @@ -2482,8 +2484,9 @@ struct net_device { u64 max_pacing_offload_horizon; struct napi_config *napi_config; - unsigned long gro_flush_timeout; + u32 num_napi_configs; u32 napi_defer_hard_irqs; + unsigned long gro_flush_timeout; /** * @up: copy of @state's IFF_UP, but safe to read with just @lock. diff --git a/net/core/dev.c b/net/core/dev.c index 68dc47d7e700..f180746382a1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6999,7 +6999,7 @@ int netif_set_threaded(struct net_device *dev, enum netdev_napi_threaded threaded) { struct napi_struct *napi; - int err = 0; + int i, err = 0; netdev_assert_locked_or_invisible(dev); @@ -7021,6 +7021,10 @@ int netif_set_threaded(struct net_device *dev, list_for_each_entry(napi, &dev->napi_list, dev_list) WARN_ON_ONCE(napi_set_threaded(napi, threaded)); + /* Override the config for all NAPIs even if currently not listed */ + for (i = 0; i < dev->num_napi_configs; i++) + dev->napi_config[i].threaded = threaded; + return err; } @@ -11873,6 +11877,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, goto free_all; dev->cfg_pending = dev->cfg; + dev->num_napi_configs = maxqs; napi_config_sz = array_size(maxqs, sizeof(*dev->napi_config)); dev->napi_config = kvzalloc(napi_config_sz, GFP_KERNEL_ACCOUNT); if (!dev->napi_config) -- cgit v1.2.3 From 21924af67d69d7c9fdaf845be69043cfe75196a1 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Tue, 5 Aug 2025 00:10:02 +0000 Subject: locking: Fix __clear_task_blocked_on() warning from __ww_mutex_wound() path The __clear_task_blocked_on() helper added a number of sanity checks ensuring we hold the mutex wait lock and that the task we are clearing blocked_on pointer (if set) matches the mutex. However, there is an edge case in the _ww_mutex_wound() logic where we need to clear the blocked_on pointer for the task that owns the mutex, not the task that is waiting on the mutex. For this case the sanity checks aren't valid, so handle this by allowing a NULL lock to skip the additional checks. K Prateek Nayak and Maarten Lankhorst also pointed out that in this case where we don't hold the owner's mutex wait_lock, we need to be a bit more careful using READ_ONCE/WRITE_ONCE in both the __clear_task_blocked_on() and __set_task_blocked_on() implementations to avoid accidentally tripping WARN_ONs if two instances race. So do that here as well. This issue was easier to miss, I realized, as the test-ww_mutex driver only exercises the wait-die class of ww_mutexes. I've sent a patch[1] to address this so the logic will be easier to test. [1]: https://lore.kernel.org/lkml/20250801023358.562525-2-jstultz@google.com/ Fixes: a4f0b6fef4b0 ("locking/mutex: Add p->blocked_on wrappers for correctness checks") Closes: https://lore.kernel.org/lkml/68894443.a00a0220.26d0e1.0015.GAE@google.com/ Reported-by: syzbot+602c4720aed62576cd79@syzkaller.appspotmail.com Reported-by: Maarten Lankhorst Signed-off-by: John Stultz Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: K Prateek Nayak Acked-by: Maarten Lankhorst Tested-by: K Prateek Nayak Link: https://lore.kernel.org/r/20250805001026.2247040-1-jstultz@google.com --- include/linux/sched.h | 29 +++++++++++++++++------------ kernel/locking/ww_mutex.h | 6 +++++- 2 files changed, 22 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 40d2fa90df42..62103dd6a48e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2144,6 +2144,8 @@ static inline struct mutex *__get_task_blocked_on(struct task_struct *p) static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m) { + struct mutex *blocked_on = READ_ONCE(p->blocked_on); + WARN_ON_ONCE(!m); /* The task should only be setting itself as blocked */ WARN_ON_ONCE(p != current); @@ -2154,8 +2156,8 @@ static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m) * with a different mutex. Note, setting it to the same * lock repeatedly is ok. */ - WARN_ON_ONCE(p->blocked_on && p->blocked_on != m); - p->blocked_on = m; + WARN_ON_ONCE(blocked_on && blocked_on != m); + WRITE_ONCE(p->blocked_on, m); } static inline void set_task_blocked_on(struct task_struct *p, struct mutex *m) @@ -2166,16 +2168,19 @@ static inline void set_task_blocked_on(struct task_struct *p, struct mutex *m) static inline void __clear_task_blocked_on(struct task_struct *p, struct mutex *m) { - WARN_ON_ONCE(!m); - /* Currently we serialize blocked_on under the mutex::wait_lock */ - lockdep_assert_held_once(&m->wait_lock); - /* - * There may be cases where we re-clear already cleared - * blocked_on relationships, but make sure we are not - * clearing the relationship with a different lock. - */ - WARN_ON_ONCE(m && p->blocked_on && p->blocked_on != m); - p->blocked_on = NULL; + if (m) { + struct mutex *blocked_on = READ_ONCE(p->blocked_on); + + /* Currently we serialize blocked_on under the mutex::wait_lock */ + lockdep_assert_held_once(&m->wait_lock); + /* + * There may be cases where we re-clear already cleared + * blocked_on relationships, but make sure we are not + * clearing the relationship with a different lock. + */ + WARN_ON_ONCE(blocked_on && blocked_on != m); + } + WRITE_ONCE(p->blocked_on, NULL); } static inline void clear_task_blocked_on(struct task_struct *p, struct mutex *m) diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h index 086fd5487ca7..31a785afee6c 100644 --- a/kernel/locking/ww_mutex.h +++ b/kernel/locking/ww_mutex.h @@ -342,8 +342,12 @@ static bool __ww_mutex_wound(struct MUTEX *lock, * When waking up the task to wound, be sure to clear the * blocked_on pointer. Otherwise we can see circular * blocked_on relationships that can't resolve. + * + * NOTE: We pass NULL here instead of lock, because we + * are waking the mutex owner, who may be currently + * blocked on a different mutex. */ - __clear_task_blocked_on(owner, lock); + __clear_task_blocked_on(owner, NULL); wake_q_add(wake_q, owner); } return true; -- cgit v1.2.3 From 9528d32873b38281ae105f2f5799e79ae9d086c2 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 11 Aug 2025 10:27:45 +0200 Subject: kcov, usb: Don't disable interrupts in kcov_remote_start_usb_softirq() kcov_remote_start_usb_softirq() the begin of urb's completion callback. HCDs marked HCD_BH will invoke this function from the softirq and in_serving_softirq() will detect this properly. Root-HUB (RH) requests will not be delayed to softirq but complete immediately in IRQ context. This will confuse kcov because in_serving_softirq() will report true if the softirq is served after the hardirq and if the softirq got interrupted by the hardirq in which currently runs. This was addressed by simply disabling interrupts in kcov_remote_start_usb_softirq() which avoided the interruption by the RH while a regular completion callback was invoked. This not only changes the behaviour while kconv is enabled but also breaks PREEMPT_RT because now sleeping locks can no longer be acquired. Revert the previous fix. Address the issue by invoking kcov_remote_start_usb() only if the context is just "serving softirqs" which is identified by checking in_serving_softirq() and in_hardirq() must be false. Fixes: f85d39dd7ed89 ("kcov, usb: disable interrupts in kcov_remote_start_usb_softirq") Cc: stable Reported-by: Yunseong Kim Closes: https://lore.kernel.org/all/20250725201400.1078395-2-ysk@kzalloc.com/ Tested-by: Yunseong Kim Signed-off-by: Sebastian Andrzej Siewior Link: https://lore.kernel.org/r/20250811082745.ycJqBXMs@linutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hcd.c | 12 +++++------- include/linux/kcov.h | 47 +++++++++-------------------------------------- 2 files changed, 14 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index c4a1875b5d3d..6270fbb5c699 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -1636,7 +1636,6 @@ static void __usb_hcd_giveback_urb(struct urb *urb) struct usb_hcd *hcd = bus_to_hcd(urb->dev->bus); struct usb_anchor *anchor = urb->anchor; int status = urb->unlinked; - unsigned long flags; urb->hcpriv = NULL; if (unlikely((urb->transfer_flags & URB_SHORT_NOT_OK) && @@ -1654,14 +1653,13 @@ static void __usb_hcd_giveback_urb(struct urb *urb) /* pass ownership to the completion handler */ urb->status = status; /* - * Only collect coverage in the softirq context and disable interrupts - * to avoid scenarios with nested remote coverage collection sections - * that KCOV does not support. - * See the comment next to kcov_remote_start_usb_softirq() for details. + * This function can be called in task context inside another remote + * coverage collection section, but kcov doesn't support that kind of + * recursion yet. Only collect coverage in softirq context for now. */ - flags = kcov_remote_start_usb_softirq((u64)urb->dev->bus->busnum); + kcov_remote_start_usb_softirq((u64)urb->dev->bus->busnum); urb->complete(urb); - kcov_remote_stop_softirq(flags); + kcov_remote_stop_softirq(); usb_anchor_resume_wakeups(anchor); atomic_dec(&urb->use_count); diff --git a/include/linux/kcov.h b/include/linux/kcov.h index 75a2fb8b16c3..0143358874b0 100644 --- a/include/linux/kcov.h +++ b/include/linux/kcov.h @@ -57,47 +57,21 @@ static inline void kcov_remote_start_usb(u64 id) /* * The softirq flavor of kcov_remote_*() functions is introduced as a temporary - * workaround for KCOV's lack of nested remote coverage sections support. - * - * Adding support is tracked in https://bugzilla.kernel.org/show_bug.cgi?id=210337. - * - * kcov_remote_start_usb_softirq(): - * - * 1. Only collects coverage when called in the softirq context. This allows - * avoiding nested remote coverage collection sections in the task context. - * For example, USB/IP calls usb_hcd_giveback_urb() in the task context - * within an existing remote coverage collection section. Thus, KCOV should - * not attempt to start collecting coverage within the coverage collection - * section in __usb_hcd_giveback_urb() in this case. - * - * 2. Disables interrupts for the duration of the coverage collection section. - * This allows avoiding nested remote coverage collection sections in the - * softirq context (a softirq might occur during the execution of a work in - * the BH workqueue, which runs with in_serving_softirq() > 0). - * For example, usb_giveback_urb_bh() runs in the BH workqueue with - * interrupts enabled, so __usb_hcd_giveback_urb() might be interrupted in - * the middle of its remote coverage collection section, and the interrupt - * handler might invoke __usb_hcd_giveback_urb() again. + * work around for kcov's lack of nested remote coverage sections support in + * task context. Adding support for nested sections is tracked in: + * https://bugzilla.kernel.org/show_bug.cgi?id=210337 */ -static inline unsigned long kcov_remote_start_usb_softirq(u64 id) +static inline void kcov_remote_start_usb_softirq(u64 id) { - unsigned long flags = 0; - - if (in_serving_softirq()) { - local_irq_save(flags); + if (in_serving_softirq() && !in_hardirq()) kcov_remote_start_usb(id); - } - - return flags; } -static inline void kcov_remote_stop_softirq(unsigned long flags) +static inline void kcov_remote_stop_softirq(void) { - if (in_serving_softirq()) { + if (in_serving_softirq() && !in_hardirq()) kcov_remote_stop(); - local_irq_restore(flags); - } } #ifdef CONFIG_64BIT @@ -131,11 +105,8 @@ static inline u64 kcov_common_handle(void) } static inline void kcov_remote_start_common(u64 id) {} static inline void kcov_remote_start_usb(u64 id) {} -static inline unsigned long kcov_remote_start_usb_softirq(u64 id) -{ - return 0; -} -static inline void kcov_remote_stop_softirq(unsigned long flags) {} +static inline void kcov_remote_start_usb_softirq(u64 id) {} +static inline void kcov_remote_stop_softirq(void) {} #endif /* CONFIG_KCOV */ #endif /* _LINUX_KCOV_H */ -- cgit v1.2.3 From a3de58b12ce074ec05b8741fa28d62ccb1070468 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 14 Aug 2025 22:45:50 +0100 Subject: netfs: Fix unbuffered write error handling If all the subrequests in an unbuffered write stream fail, the subrequest collector doesn't update the stream->transferred value and it retains its initial LONG_MAX value. Unfortunately, if all active streams fail, then we take the smallest value of { LONG_MAX, LONG_MAX, ... } as the value to set in wreq->transferred - which is then returned from ->write_iter(). LONG_MAX was chosen as the initial value so that all the streams can be quickly assessed by taking the smallest value of all stream->transferred - but this only works if we've set any of them. Fix this by adding a flag to indicate whether the value in stream->transferred is valid and checking that when we integrate the values. stream->transferred can then be initialised to zero. This was found by running the generic/750 xfstest against cifs with cache=none. It splices data to the target file. Once (if) it has used up all the available scratch space, the writes start failing with ENOSPC. This causes ->write_iter() to fail. However, it was returning wreq->transferred, i.e. LONG_MAX, rather than an error (because it thought the amount transferred was non-zero) and iter_file_splice_write() would then try to clean up that amount of pipe bufferage - leading to an oops when it overran. The kernel log showed: CIFS: VFS: Send error in write = -28 followed by: BUG: kernel NULL pointer dereference, address: 0000000000000008 with: RIP: 0010:iter_file_splice_write+0x3a4/0x520 do_splice+0x197/0x4e0 or: RIP: 0010:pipe_buf_release (include/linux/pipe_fs_i.h:282) iter_file_splice_write (fs/splice.c:755) Also put a warning check into splice to announce if ->write_iter() returned that it had written more than it was asked to. Fixes: 288ace2f57c9 ("netfs: New writeback implementation") Reported-by: Xiaoli Feng Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220445 Signed-off-by: David Howells Link: https://lore.kernel.org/915443.1755207950@warthog.procyon.org.uk cc: Paulo Alcantara cc: Steve French cc: Shyam Prasad N cc: netfs@lists.linux.dev cc: linux-cifs@vger.kernel.org cc: linux-fsdevel@vger.kernel.org cc: stable@vger.kernel.org Signed-off-by: Christian Brauner --- fs/netfs/read_collect.c | 4 +++- fs/netfs/write_collect.c | 10 ++++++++-- fs/netfs/write_issue.c | 4 ++-- fs/splice.c | 3 +++ include/linux/netfs.h | 1 + 5 files changed, 17 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index 3e804da1e1eb..a95e7aadafd0 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -281,8 +281,10 @@ reassess: } else if (test_bit(NETFS_RREQ_SHORT_TRANSFER, &rreq->flags)) { notes |= MADE_PROGRESS; } else { - if (!stream->failed) + if (!stream->failed) { stream->transferred += transferred; + stream->transferred_valid = true; + } if (front->transferred < front->len) set_bit(NETFS_RREQ_SHORT_TRANSFER, &rreq->flags); notes |= MADE_PROGRESS; diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 0f3a36852a4d..cbf3d9194c7b 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -254,6 +254,7 @@ reassess_streams: if (front->start + front->transferred > stream->collected_to) { stream->collected_to = front->start + front->transferred; stream->transferred = stream->collected_to - wreq->start; + stream->transferred_valid = true; notes |= MADE_PROGRESS; } if (test_bit(NETFS_SREQ_FAILED, &front->flags)) { @@ -356,6 +357,7 @@ bool netfs_write_collection(struct netfs_io_request *wreq) { struct netfs_inode *ictx = netfs_inode(wreq->inode); size_t transferred; + bool transferred_valid = false; int s; _enter("R=%x", wreq->debug_id); @@ -376,12 +378,16 @@ bool netfs_write_collection(struct netfs_io_request *wreq) continue; if (!list_empty(&stream->subrequests)) return false; - if (stream->transferred < transferred) + if (stream->transferred_valid && + stream->transferred < transferred) { transferred = stream->transferred; + transferred_valid = true; + } } /* Okay, declare that all I/O is complete. */ - wreq->transferred = transferred; + if (transferred_valid) + wreq->transferred = transferred; trace_netfs_rreq(wreq, netfs_rreq_trace_write_done); if (wreq->io_streams[1].active && diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 50bee2c4130d..0584cba1a043 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -118,12 +118,12 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, wreq->io_streams[0].prepare_write = ictx->ops->prepare_write; wreq->io_streams[0].issue_write = ictx->ops->issue_write; wreq->io_streams[0].collected_to = start; - wreq->io_streams[0].transferred = LONG_MAX; + wreq->io_streams[0].transferred = 0; wreq->io_streams[1].stream_nr = 1; wreq->io_streams[1].source = NETFS_WRITE_TO_CACHE; wreq->io_streams[1].collected_to = start; - wreq->io_streams[1].transferred = LONG_MAX; + wreq->io_streams[1].transferred = 0; if (fscache_resources_valid(&wreq->cache_resources)) { wreq->io_streams[1].avail = true; wreq->io_streams[1].active = true; diff --git a/fs/splice.c b/fs/splice.c index 4d6df083e0c0..f5094b6d00a0 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -739,6 +739,9 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, sd.pos = kiocb.ki_pos; if (ret <= 0) break; + WARN_ONCE(ret > sd.total_len - left, + "Splice Exceeded! ret=%zd tot=%zu left=%zu\n", + ret, sd.total_len, left); sd.num_spliced += ret; sd.total_len -= ret; diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 185bd8196503..98c96d649bf9 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -150,6 +150,7 @@ struct netfs_io_stream { bool active; /* T if stream is active */ bool need_retry; /* T if this stream needs retrying */ bool failed; /* T if this stream failed */ + bool transferred_valid; /* T is ->transferred is valid */ }; /* -- cgit v1.2.3 From a032fe30cf09b6723ab61a05aee057311b00f9e1 Mon Sep 17 00:00:00 2001 From: Dongcheng Yan Date: Fri, 25 Apr 2025 18:43:30 +0800 Subject: platform/x86: int3472: add hpd pin support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Typically HDMI to MIPI CSI-2 bridges have a pin to signal image data is being received. On the host side this is wired to a GPIO for polling or interrupts. This includes the Lontium HDMI to MIPI CSI-2 bridges lt6911uxe and lt6911uxc. The GPIO "hpd" is used already by other HDMI to CSI-2 bridges, use it here as well. Signed-off-by: Dongcheng Yan Reviewed-by: Sakari Ailus Acked-by: Ilpo Järvinen Reviewed-by: Hans de Goede Reviewed-by: Andy Shevchenko Fixes: 20244cbafbd6 ("media: i2c: change lt6911uxe irq_gpio name to "hpd"") Cc: stable@vger.kernel.org Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil --- drivers/platform/x86/intel/int3472/discrete.c | 6 ++++++ include/linux/platform_data/x86/int3472.h | 1 + 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/drivers/platform/x86/intel/int3472/discrete.c b/drivers/platform/x86/intel/int3472/discrete.c index 4c0aed6e626f..bdfb8a800c54 100644 --- a/drivers/platform/x86/intel/int3472/discrete.c +++ b/drivers/platform/x86/intel/int3472/discrete.c @@ -193,6 +193,10 @@ static void int3472_get_con_id_and_polarity(struct int3472_discrete_device *int3 *con_id = "privacy-led"; *gpio_flags = GPIO_ACTIVE_HIGH; break; + case INT3472_GPIO_TYPE_HOTPLUG_DETECT: + *con_id = "hpd"; + *gpio_flags = GPIO_ACTIVE_HIGH; + break; case INT3472_GPIO_TYPE_POWER_ENABLE: *con_id = "avdd"; *gpio_flags = GPIO_ACTIVE_HIGH; @@ -223,6 +227,7 @@ static void int3472_get_con_id_and_polarity(struct int3472_discrete_device *int3 * 0x0b Power enable * 0x0c Clock enable * 0x0d Privacy LED + * 0x13 Hotplug detect * * There are some known platform specific quirks where that does not quite * hold up; for example where a pin with type 0x01 (Power down) is mapped to @@ -292,6 +297,7 @@ static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares, switch (type) { case INT3472_GPIO_TYPE_RESET: case INT3472_GPIO_TYPE_POWERDOWN: + case INT3472_GPIO_TYPE_HOTPLUG_DETECT: ret = skl_int3472_map_gpio_to_sensor(int3472, agpio, con_id, gpio_flags); if (ret) err_msg = "Failed to map GPIO pin to sensor\n"; diff --git a/include/linux/platform_data/x86/int3472.h b/include/linux/platform_data/x86/int3472.h index 78276a11c48d..1571e9157fa5 100644 --- a/include/linux/platform_data/x86/int3472.h +++ b/include/linux/platform_data/x86/int3472.h @@ -27,6 +27,7 @@ #define INT3472_GPIO_TYPE_CLK_ENABLE 0x0c #define INT3472_GPIO_TYPE_PRIVACY_LED 0x0d #define INT3472_GPIO_TYPE_HANDSHAKE 0x12 +#define INT3472_GPIO_TYPE_HOTPLUG_DETECT 0x13 #define INT3472_PDEV_MAX_NAME_LEN 23 #define INT3472_MAX_SENSOR_GPIOS 3 -- cgit v1.2.3 From 8ea815399c3fcce1889bd951fec25b5b9a3979c1 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Mon, 14 Apr 2025 16:41:07 +0200 Subject: compiler: remove __ADDRESSABLE_ASM{_STR,}() again __ADDRESSABLE_ASM_STR() is where the necessary stringification happens. As long as "sym" doesn't contain any odd characters, no quoting is required for its use with .quad / .long. In fact the quotation gets in the way with gas 2.25; it's only from 2.26 onwards that quoted symbols are half-way properly supported. However, assembly being different from C anyway, drop __ADDRESSABLE_ASM_STR() and its helper macro altogether. A simple .global directive will suffice to get the symbol "declared", i.e. into the symbol table. While there also stop open-coding STATIC_CALL_TRAMP() and STATIC_CALL_KEY(). Fixes: 0ef8047b737d ("x86/static-call: provide a way to do very early static-call updates") Signed-off-by: Jan Beulich Acked-by: Josh Poimboeuf Cc: stable@vger.kernel.org Signed-off-by: Juergen Gross Message-ID: <609d2c74-de13-4fae-ab1a-1ec44afb948d@suse.com> --- arch/x86/include/asm/xen/hypercall.h | 5 +++-- include/linux/compiler.h | 8 -------- 2 files changed, 3 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 59a62c3780a2..a16d4631547c 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -94,12 +94,13 @@ DECLARE_STATIC_CALL(xen_hypercall, xen_hypercall_func); #ifdef MODULE #define __ADDRESSABLE_xen_hypercall #else -#define __ADDRESSABLE_xen_hypercall __ADDRESSABLE_ASM_STR(__SCK__xen_hypercall) +#define __ADDRESSABLE_xen_hypercall \ + __stringify(.global STATIC_CALL_KEY(xen_hypercall);) #endif #define __HYPERCALL \ __ADDRESSABLE_xen_hypercall \ - "call __SCT__xen_hypercall" + __stringify(call STATIC_CALL_TRAMP(xen_hypercall)) #define __HYPERCALL_ENTRY(x) "a" (x) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 6f04a1d8c720..64ff73c533e5 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -288,14 +288,6 @@ static inline void *offset_to_ptr(const int *off) #define __ADDRESSABLE(sym) \ ___ADDRESSABLE(sym, __section(".discard.addressable")) -#define __ADDRESSABLE_ASM(sym) \ - .pushsection .discard.addressable,"aw"; \ - .align ARCH_SEL(8,4); \ - ARCH_SEL(.quad, .long) __stringify(sym); \ - .popsection; - -#define __ADDRESSABLE_ASM_STR(sym) __stringify(__ADDRESSABLE_ASM(sym)) - /* * This returns a constant expression while determining if an argument is * a constant expression, most importantly without evaluating the argument. -- cgit v1.2.3 From 76d2e3890fb169168c73f2e4f8375c7cc24a765e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 16 Aug 2025 07:25:20 -0700 Subject: NFS: Fix a race when updating an existing write After nfs_lock_and_join_requests() tests for whether the request is still attached to the mapping, nothing prevents a call to nfs_inode_remove_request() from succeeding until we actually lock the page group. The reason is that whoever called nfs_inode_remove_request() doesn't necessarily have a lock on the page group head. So in order to avoid races, let's take the page group lock earlier in nfs_lock_and_join_requests(), and hold it across the removal of the request in nfs_inode_remove_request(). Reported-by: Jeff Layton Tested-by: Joe Quanaim Tested-by: Andrew Steffen Reviewed-by: Jeff Layton Fixes: bd37d6fce184 ("NFSv4: Convert nfs_lock_and_join_requests() to use nfs_page_find_head_request()") Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust --- fs/nfs/pagelist.c | 9 +++++---- fs/nfs/write.c | 29 ++++++++++------------------- include/linux/nfs_page.h | 1 + 3 files changed, 16 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 11968dcb7243..6e69ce43a13f 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -253,13 +253,14 @@ nfs_page_group_unlock(struct nfs_page *req) nfs_page_clear_headlock(req); } -/* - * nfs_page_group_sync_on_bit_locked +/** + * nfs_page_group_sync_on_bit_locked - Test if all requests have @bit set + * @req: request in page group + * @bit: PG_* bit that is used to sync page group * * must be called with page group lock held */ -static bool -nfs_page_group_sync_on_bit_locked(struct nfs_page *req, unsigned int bit) +bool nfs_page_group_sync_on_bit_locked(struct nfs_page *req, unsigned int bit) { struct nfs_page *head = req->wb_head; struct nfs_page *tmp; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index fa5c41d0989a..8b7c04737967 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -153,20 +153,10 @@ nfs_page_set_inode_ref(struct nfs_page *req, struct inode *inode) } } -static int -nfs_cancel_remove_inode(struct nfs_page *req, struct inode *inode) +static void nfs_cancel_remove_inode(struct nfs_page *req, struct inode *inode) { - int ret; - - if (!test_bit(PG_REMOVE, &req->wb_flags)) - return 0; - ret = nfs_page_group_lock(req); - if (ret) - return ret; if (test_and_clear_bit(PG_REMOVE, &req->wb_flags)) nfs_page_set_inode_ref(req, inode); - nfs_page_group_unlock(req); - return 0; } /** @@ -585,19 +575,18 @@ retry: } } + ret = nfs_page_group_lock(head); + if (ret < 0) + goto out_unlock; + /* Ensure that nobody removed the request before we locked it */ if (head != folio->private) { + nfs_page_group_unlock(head); nfs_unlock_and_release_request(head); goto retry; } - ret = nfs_cancel_remove_inode(head, inode); - if (ret < 0) - goto out_unlock; - - ret = nfs_page_group_lock(head); - if (ret < 0) - goto out_unlock; + nfs_cancel_remove_inode(head, inode); /* lock each request in the page group */ for (subreq = head->wb_this_page; @@ -786,7 +775,8 @@ static void nfs_inode_remove_request(struct nfs_page *req) { struct nfs_inode *nfsi = NFS_I(nfs_page_to_inode(req)); - if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) { + nfs_page_group_lock(req); + if (nfs_page_group_sync_on_bit_locked(req, PG_REMOVE)) { struct folio *folio = nfs_page_to_folio(req->wb_head); struct address_space *mapping = folio->mapping; @@ -798,6 +788,7 @@ static void nfs_inode_remove_request(struct nfs_page *req) } spin_unlock(&mapping->i_private_lock); } + nfs_page_group_unlock(req); if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) { atomic_long_dec(&nfsi->nrequests); diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 169b4ae30ff4..9aed39abc94b 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -160,6 +160,7 @@ extern void nfs_join_page_group(struct nfs_page *head, extern int nfs_page_group_lock(struct nfs_page *); extern void nfs_page_group_unlock(struct nfs_page *); extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int); +extern bool nfs_page_group_sync_on_bit_locked(struct nfs_page *, unsigned int); extern int nfs_page_set_headlock(struct nfs_page *req); extern void nfs_page_clear_headlock(struct nfs_page *req); extern bool nfs_async_iocounter_wait(struct rpc_task *, struct nfs_lock_context *); -- cgit v1.2.3 From 808471ddb0fa785559c3e7aee59be20a13b46ef5 Mon Sep 17 00:00:00 2001 From: Dominique Martinet Date: Wed, 13 Aug 2025 15:04:55 +0900 Subject: iov_iter: iterate_folioq: fix handling of offset >= folio size It's apparently possible to get an iov advanced all the way up to the end of the current page we're looking at, e.g. (gdb) p *iter $24 = {iter_type = 4 '\004', nofault = false, data_source = false, iov_offset = 4096, {__ubuf_iovec = { iov_base = 0xffff88800f5bc000, iov_len = 655}, {{__iov = 0xffff88800f5bc000, kvec = 0xffff88800f5bc000, bvec = 0xffff88800f5bc000, folioq = 0xffff88800f5bc000, xarray = 0xffff88800f5bc000, ubuf = 0xffff88800f5bc000}, count = 655}}, {nr_segs = 2, folioq_slot = 2 '\002', xarray_start = 2}} Where iov_offset is 4k with 4k-sized folios This should have been fine because we're only in the 2nd slot and there's another one after this, but iterate_folioq should not try to map a folio that skips the whole size, and more importantly part here does not end up zero (because 'PAGE_SIZE - skip % PAGE_SIZE' ends up PAGE_SIZE and not zero..), so skip forward to the "advance to next folio" code Link: https://lkml.kernel.org/r/20250813-iot_iter_folio-v3-0-a0ffad2b665a@codewreck.org Link: https://lkml.kernel.org/r/20250813-iot_iter_folio-v3-1-a0ffad2b665a@codewreck.org Signed-off-by: Dominique Martinet Fixes: db0aa2e9566f ("mm: Define struct folio_queue and ITER_FOLIOQ to handle a sequence of folios") Reported-by: Maximilian Bosch Reported-by: Ryan Lahfa Reported-by: Christian Theune Reported-by: Arnout Engelen Link: https://lkml.kernel.org/r/D4LHHUNLG79Y.12PI0X6BEHRHW@mbosch.me/ Acked-by: David Howells Cc: Al Viro Cc: Christian Brauner Cc: Matthew Wilcox (Oracle) Cc: [6.12+] Signed-off-by: Andrew Morton --- include/linux/iov_iter.h | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iov_iter.h b/include/linux/iov_iter.h index c4aa58032faf..f9a17fbbd398 100644 --- a/include/linux/iov_iter.h +++ b/include/linux/iov_iter.h @@ -160,7 +160,7 @@ size_t iterate_folioq(struct iov_iter *iter, size_t len, void *priv, void *priv2 do { struct folio *folio = folioq_folio(folioq, slot); - size_t part, remain, consumed; + size_t part, remain = 0, consumed; size_t fsize; void *base; @@ -168,14 +168,16 @@ size_t iterate_folioq(struct iov_iter *iter, size_t len, void *priv, void *priv2 break; fsize = folioq_folio_size(folioq, slot); - base = kmap_local_folio(folio, skip); - part = umin(len, PAGE_SIZE - skip % PAGE_SIZE); - remain = step(base, progress, part, priv, priv2); - kunmap_local(base); - consumed = part - remain; - len -= consumed; - progress += consumed; - skip += consumed; + if (skip < fsize) { + base = kmap_local_folio(folio, skip); + part = umin(len, PAGE_SIZE - skip % PAGE_SIZE); + remain = step(base, progress, part, priv, priv2); + kunmap_local(base); + consumed = part - remain; + len -= consumed; + progress += consumed; + skip += consumed; + } if (skip >= fsize) { skip = 0; slot++; -- cgit v1.2.3 From 053c8ebe74f7e1f4c072e59428da80b9d78bc4b7 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Sun, 17 Aug 2025 23:17:59 +0800 Subject: mm/migrate: fix NULL movable_ops if CONFIG_ZSMALLOC=m After commit 84caf98838a3e5f4bdb34 ("mm: stop storing migration_ops in page->mapping") we get such an error message if CONFIG_ZSMALLOC=m: WARNING: CPU: 3 PID: 42 at mm/migrate.c:142 isolate_movable_ops_page+0xa8/0x1c0 CPU: 3 UID: 0 PID: 42 Comm: kcompactd0 Not tainted 6.16.0-rc5+ #2133 PREEMPT pc 9000000000540bd8 ra 9000000000540b84 tp 9000000100420000 sp 9000000100423a60 a0 9000000100193a80 a1 000000000000000c a2 000000000000001b a3 ffffffffffffffff a4 ffffffffffffffff a5 0000000000000267 a6 0000000000000000 a7 9000000100423ae0 t0 00000000000000f1 t1 00000000000000f6 t2 0000000000000000 t3 0000000000000001 t4 ffffff00010eb834 t5 0000000000000040 t6 900000010c89d380 t7 90000000023fcc70 t8 0000000000000018 u0 0000000000000000 s9 ffffff00010eb800 s0 ffffff00010eb800 s1 000000000000000c s2 0000000000043ae0 s3 0000800000000000 s4 900000000219cc40 s5 0000000000000000 s6 ffffff00010eb800 s7 0000000000000001 s8 90000000025b4000 ra: 9000000000540b84 isolate_movable_ops_page+0x54/0x1c0 ERA: 9000000000540bd8 isolate_movable_ops_page+0xa8/0x1c0 CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE) PRMD: 00000004 (PPLV0 +PIE -PWE) EUEN: 00000000 (-FPE -SXE -ASXE -BTE) ECFG: 00071c1d (LIE=0,2-4,10-12 VS=7) ESTAT: 000c0000 [BRK] (IS= ECode=12 EsubCode=0) PRID: 0014c010 (Loongson-64bit, Loongson-3A5000) CPU: 3 UID: 0 PID: 42 Comm: kcompactd0 Not tainted 6.16.0-rc5+ #2133 PREEMPT Stack : 90000000021fd000 0000000000000000 9000000000247720 9000000100420000 90000001004236a0 90000001004236a8 0000000000000000 90000001004237e8 90000001004237e0 90000001004237e0 9000000100423550 0000000000000001 0000000000000001 90000001004236a8 725a84864a19e2d9 90000000023fcc58 9000000100420000 90000000024c6848 9000000002416848 0000000000000001 0000000000000000 000000000000000a 0000000007fe0000 ffffff00010eb800 0000000000000000 90000000021fd000 0000000000000000 900000000205cf30 000000000000008e 0000000000000009 ffffff00010eb800 0000000000000001 90000000025b4000 0000000000000000 900000000024773c 00007ffff103d748 00000000000000b0 0000000000000004 0000000000000000 0000000000071c1d ... Call Trace: [<900000000024773c>] show_stack+0x5c/0x190 [<90000000002415e0>] dump_stack_lvl+0x70/0x9c [<90000000004abe6c>] isolate_migratepages_block+0x3bc/0x16e0 [<90000000004af408>] compact_zone+0x558/0x1000 [<90000000004b0068>] compact_node+0xa8/0x1e0 [<90000000004b0aa4>] kcompactd+0x394/0x410 [<90000000002b3c98>] kthread+0x128/0x140 [<9000000001779148>] ret_from_kernel_thread+0x28/0xc0 [<9000000000245528>] ret_from_kernel_thread_asm+0x10/0x88 The reason is that defined(CONFIG_ZSMALLOC) evaluates to 1 only when CONFIG_ZSMALLOC=y, we should use IS_ENABLED(CONFIG_ZSMALLOC) instead. But when I use IS_ENABLED(CONFIG_ZSMALLOC), page_movable_ops() cannot access zsmalloc_mops because zsmalloc_mops is in a module. To solve this problem, we define a set_movable_ops() interface to register and unregister offline_movable_ops / zsmalloc_movable_ops in mm/migrate.c, and call them at mm/balloon_compaction.c & mm/zsmalloc.c. Since offline_movable_ops / zsmalloc_movable_ops are always accessible, all #ifdef / #endif are removed in page_movable_ops(). Link: https://lkml.kernel.org/r/20250817151759.2525174-1-chenhuacai@loongson.cn Fixes: 84caf98838a3 ("mm: stop storing migration_ops in page->mapping") Signed-off-by: Huacai Chen Acked-by: Zi Yan Acked-by: David Hildenbrand Cc: Huacai Chen Cc: Huacai Chen Cc: Lorenzo Stoakes Cc: "Michael S. Tsirkin" Cc: Minchan Kim Cc: Sergey Senozhatsky Signed-off-by: Andrew Morton --- include/linux/migrate.h | 5 +++++ mm/balloon_compaction.c | 6 ++++++ mm/migrate.c | 38 ++++++++++++++++++++++++++++++-------- mm/zsmalloc.c | 10 ++++++++++ 4 files changed, 51 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index acadd41e0b5c..9009e27b5f44 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -79,6 +79,7 @@ void migration_entry_wait_on_locked(swp_entry_t entry, spinlock_t *ptl) void folio_migrate_flags(struct folio *newfolio, struct folio *folio); int folio_migrate_mapping(struct address_space *mapping, struct folio *newfolio, struct folio *folio, int extra_count); +int set_movable_ops(const struct movable_operations *ops, enum pagetype type); #else @@ -100,6 +101,10 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, { return -ENOSYS; } +static inline int set_movable_ops(const struct movable_operations *ops, enum pagetype type) +{ + return -ENOSYS; +} #endif /* CONFIG_MIGRATION */ diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c index 2a4a649805c1..03c5dbabb156 100644 --- a/mm/balloon_compaction.c +++ b/mm/balloon_compaction.c @@ -254,4 +254,10 @@ const struct movable_operations balloon_mops = { .putback_page = balloon_page_putback, }; +static int __init balloon_init(void) +{ + return set_movable_ops(&balloon_mops, PGTY_offline); +} +core_initcall(balloon_init); + #endif /* CONFIG_BALLOON_COMPACTION */ diff --git a/mm/migrate.c b/mm/migrate.c index 425401b2d4e1..9e5ef39ce73a 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -43,8 +43,6 @@ #include #include #include -#include -#include #include @@ -53,6 +51,33 @@ #include "internal.h" #include "swap.h" +static const struct movable_operations *offline_movable_ops; +static const struct movable_operations *zsmalloc_movable_ops; + +int set_movable_ops(const struct movable_operations *ops, enum pagetype type) +{ + /* + * We only allow for selected types and don't handle concurrent + * registration attempts yet. + */ + switch (type) { + case PGTY_offline: + if (offline_movable_ops && ops) + return -EBUSY; + offline_movable_ops = ops; + break; + case PGTY_zsmalloc: + if (zsmalloc_movable_ops && ops) + return -EBUSY; + zsmalloc_movable_ops = ops; + break; + default: + return -EINVAL; + } + return 0; +} +EXPORT_SYMBOL_GPL(set_movable_ops); + static const struct movable_operations *page_movable_ops(struct page *page) { VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(page), page); @@ -62,15 +87,12 @@ static const struct movable_operations *page_movable_ops(struct page *page) * it as movable, the page type must be sticky until the page gets freed * back to the buddy. */ -#ifdef CONFIG_BALLOON_COMPACTION if (PageOffline(page)) /* Only balloon compaction sets PageOffline pages movable. */ - return &balloon_mops; -#endif /* CONFIG_BALLOON_COMPACTION */ -#if defined(CONFIG_ZSMALLOC) && defined(CONFIG_COMPACTION) + return offline_movable_ops; if (PageZsmalloc(page)) - return &zsmalloc_mops; -#endif /* defined(CONFIG_ZSMALLOC) && defined(CONFIG_COMPACTION) */ + return zsmalloc_movable_ops; + return NULL; } diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 2c5e56a65354..805a10b41266 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -2246,8 +2246,15 @@ EXPORT_SYMBOL_GPL(zs_destroy_pool); static int __init zs_init(void) { + int rc __maybe_unused; + #ifdef CONFIG_ZPOOL zpool_register_driver(&zs_zpool_driver); +#endif +#ifdef CONFIG_COMPACTION + rc = set_movable_ops(&zsmalloc_mops, PGTY_zsmalloc); + if (rc) + return rc; #endif zs_stat_init(); return 0; @@ -2257,6 +2264,9 @@ static void __exit zs_exit(void) { #ifdef CONFIG_ZPOOL zpool_unregister_driver(&zs_zpool_driver); +#endif +#ifdef CONFIG_COMPACTION + set_movable_ops(NULL, PGTY_zsmalloc); #endif zs_stat_exit(); } -- cgit v1.2.3 From 8ef7f3132e4005a103b382e71abea7ad01fbeb86 Mon Sep 17 00:00:00 2001 From: Xianglai Li Date: Wed, 20 Aug 2025 22:23:44 +0800 Subject: LoongArch: Add cpuhotplug hooks to fix high cpu usage of vCPU threads When the CPU is offline, the timer of LoongArch is not correctly closed. This is harmless for real machines, but resulting in an excessively high cpu usage rate of the offline vCPU thread in the virtual machines. To correctly close the timer, we have made the following modifications: Register the cpu hotplug event (CPUHP_AP_LOONGARCH_ARCH_TIMER_STARTING) for LoongArch. This event's hooks will be called to close the timer when the CPU is offline. Clear the timer interrupt when the timer is turned off. Since before the timer is turned off, there may be a timer interrupt that has already been in the pending state due to the interruption of the disabled, which also affects the halt state of the offline vCPU. Signed-off-by: Xianglai Li Signed-off-by: Huacai Chen --- arch/loongarch/kernel/time.c | 22 ++++++++++++++++++++++ include/linux/cpuhotplug.h | 1 + 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c index 367906b10f81..f3092f2de8b5 100644 --- a/arch/loongarch/kernel/time.c +++ b/arch/loongarch/kernel/time.c @@ -5,6 +5,7 @@ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ #include +#include #include #include #include @@ -102,6 +103,23 @@ static int constant_timer_next_event(unsigned long delta, struct clock_event_dev return 0; } +static int arch_timer_starting(unsigned int cpu) +{ + set_csr_ecfg(ECFGF_TIMER); + + return 0; +} + +static int arch_timer_dying(unsigned int cpu) +{ + constant_set_state_shutdown(this_cpu_ptr(&constant_clockevent_device)); + + /* Clear Timer Interrupt */ + write_csr_tintclear(CSR_TINTCLR_TI); + + return 0; +} + static unsigned long get_loops_per_jiffy(void) { unsigned long lpj = (unsigned long)const_clock_freq; @@ -172,6 +190,10 @@ int constant_clockevent_init(void) lpj_fine = get_loops_per_jiffy(); pr_info("Constant clock event device register\n"); + cpuhp_setup_state(CPUHP_AP_LOONGARCH_ARCH_TIMER_STARTING, + "clockevents/loongarch/timer:starting", + arch_timer_starting, arch_timer_dying); + return 0; } diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index edfa61d80702..62cd7b35a29c 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -168,6 +168,7 @@ enum cpuhp_state { CPUHP_AP_QCOM_TIMER_STARTING, CPUHP_AP_TEGRA_TIMER_STARTING, CPUHP_AP_ARMADA_TIMER_STARTING, + CPUHP_AP_LOONGARCH_ARCH_TIMER_STARTING, CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_ARC_TIMER_STARTING, CPUHP_AP_REALTEK_TIMER_STARTING, -- cgit v1.2.3 From 370ac285f23aecae40600851fb4a1a9e75e50973 Mon Sep 17 00:00:00 2001 From: Nilay Shroff Date: Thu, 14 Aug 2025 13:54:59 +0530 Subject: block: avoid cpu_hotplug_lock depedency on freeze_lock A recent lockdep[1] splat observed while running blktest block/005 reveals a potential deadlock caused by the cpu_hotplug_lock dependency on ->freeze_lock. This dependency was introduced by commit 033b667a823e ("block: blk-rq-qos: guard rq-qos helpers by static key"). That change added a static key to avoid fetching q->rq_qos when neither blk-wbt nor blk-iolatency is configured. The static key dynamically patches kernel text to a NOP when disabled, eliminating overhead of fetching q->rq_qos in the I/O hot path. However, enabling a static key at runtime requires acquiring both cpu_hotplug_lock and jump_label_mutex. When this happens after the queue has already been frozen (i.e., while holding ->freeze_lock), it creates a locking dependency from cpu_hotplug_lock to ->freeze_lock, which leads to a potential deadlock reported by lockdep [1]. To resolve this, replace the static key mechanism with q->queue_flags: QUEUE_FLAG_QOS_ENABLED. This flag is evaluated in the fast path before accessing q->rq_qos. If the flag is set, we proceed to fetch q->rq_qos; otherwise, the access is skipped. Since q->queue_flags is commonly accessed in IO hotpath and resides in the first cacheline of struct request_queue, checking it imposes minimal overhead while eliminating the deadlock risk. This change avoids the lockdep splat without introducing performance regressions. [1] https://lore.kernel.org/linux-block/4fdm37so3o4xricdgfosgmohn63aa7wj3ua4e5vpihoamwg3ui@fq42f5q5t5ic/ Reported-by: Shinichiro Kawasaki Closes: https://lore.kernel.org/linux-block/4fdm37so3o4xricdgfosgmohn63aa7wj3ua4e5vpihoamwg3ui@fq42f5q5t5ic/ Fixes: 033b667a823e ("block: blk-rq-qos: guard rq-qos helpers by static key") Tested-by: Shin'ichiro Kawasaki Signed-off-by: Nilay Shroff Reviewed-by: Ming Lei Reviewed-by: Yu Kuai Link: https://lore.kernel.org/r/20250814082612.500845-4-nilay@linux.ibm.com Signed-off-by: Jens Axboe --- block/blk-mq-debugfs.c | 1 + block/blk-rq-qos.c | 9 ++++----- block/blk-rq-qos.h | 54 +++++++++++++++++++++++++++++--------------------- include/linux/blkdev.h | 1 + 4 files changed, 37 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 7ed3e71f2fc0..32c65efdda46 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -95,6 +95,7 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(SQ_SCHED), QUEUE_FLAG_NAME(DISABLE_WBT_DEF), QUEUE_FLAG_NAME(NO_ELV_SWITCH), + QUEUE_FLAG_NAME(QOS_ENABLED), }; #undef QUEUE_FLAG_NAME diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index b1e24bb85ad2..654478dfbc20 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -2,8 +2,6 @@ #include "blk-rq-qos.h" -__read_mostly DEFINE_STATIC_KEY_FALSE(block_rq_qos); - /* * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded, * false if 'v' + 1 would be bigger than 'below'. @@ -319,8 +317,8 @@ void rq_qos_exit(struct request_queue *q) struct rq_qos *rqos = q->rq_qos; q->rq_qos = rqos->next; rqos->ops->exit(rqos); - static_branch_dec(&block_rq_qos); } + blk_queue_flag_clear(QUEUE_FLAG_QOS_ENABLED, q); mutex_unlock(&q->rq_qos_mutex); } @@ -346,7 +344,7 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, goto ebusy; rqos->next = q->rq_qos; q->rq_qos = rqos; - static_branch_inc(&block_rq_qos); + blk_queue_flag_set(QUEUE_FLAG_QOS_ENABLED, q); blk_mq_unfreeze_queue(q, memflags); @@ -374,10 +372,11 @@ void rq_qos_del(struct rq_qos *rqos) for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) { if (*cur == rqos) { *cur = rqos->next; - static_branch_dec(&block_rq_qos); break; } } + if (!q->rq_qos) + blk_queue_flag_clear(QUEUE_FLAG_QOS_ENABLED, q); blk_mq_unfreeze_queue(q, memflags); mutex_lock(&q->debugfs_mutex); diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h index 28125fc49eff..1fe22000a379 100644 --- a/block/blk-rq-qos.h +++ b/block/blk-rq-qos.h @@ -12,7 +12,6 @@ #include "blk-mq-debugfs.h" struct blk_mq_debugfs_attr; -extern struct static_key_false block_rq_qos; enum rq_qos_id { RQ_QOS_WBT, @@ -113,49 +112,55 @@ void __rq_qos_queue_depth_changed(struct rq_qos *rqos); static inline void rq_qos_cleanup(struct request_queue *q, struct bio *bio) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) __rq_qos_cleanup(q->rq_qos, bio); } static inline void rq_qos_done(struct request_queue *q, struct request *rq) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos && - !blk_rq_is_passthrough(rq)) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos && !blk_rq_is_passthrough(rq)) __rq_qos_done(q->rq_qos, rq); } static inline void rq_qos_issue(struct request_queue *q, struct request *rq) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) __rq_qos_issue(q->rq_qos, rq); } static inline void rq_qos_requeue(struct request_queue *q, struct request *rq) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) __rq_qos_requeue(q->rq_qos, rq); } static inline void rq_qos_done_bio(struct bio *bio) { - if (static_branch_unlikely(&block_rq_qos) && - bio->bi_bdev && (bio_flagged(bio, BIO_QOS_THROTTLED) || - bio_flagged(bio, BIO_QOS_MERGED))) { - struct request_queue *q = bdev_get_queue(bio->bi_bdev); - - /* - * If a bio has BIO_QOS_xxx set, it implicitly implies that - * q->rq_qos is present. So, we skip re-checking q->rq_qos - * here as an extra optimization and directly call - * __rq_qos_done_bio(). - */ - __rq_qos_done_bio(q->rq_qos, bio); - } + struct request_queue *q; + + if (!bio->bi_bdev || (!bio_flagged(bio, BIO_QOS_THROTTLED) && + !bio_flagged(bio, BIO_QOS_MERGED))) + return; + + q = bdev_get_queue(bio->bi_bdev); + + /* + * If a bio has BIO_QOS_xxx set, it implicitly implies that + * q->rq_qos is present. So, we skip re-checking q->rq_qos + * here as an extra optimization and directly call + * __rq_qos_done_bio(). + */ + __rq_qos_done_bio(q->rq_qos, bio); } static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) { + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) { bio_set_flag(bio, BIO_QOS_THROTTLED); __rq_qos_throttle(q->rq_qos, bio); } @@ -164,14 +169,16 @@ static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio) static inline void rq_qos_track(struct request_queue *q, struct request *rq, struct bio *bio) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) __rq_qos_track(q->rq_qos, rq, bio); } static inline void rq_qos_merge(struct request_queue *q, struct request *rq, struct bio *bio) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) { + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) { bio_set_flag(bio, BIO_QOS_MERGED); __rq_qos_merge(q->rq_qos, rq, bio); } @@ -179,7 +186,8 @@ static inline void rq_qos_merge(struct request_queue *q, struct request *rq, static inline void rq_qos_queue_depth_changed(struct request_queue *q) { - if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) + if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) && + q->rq_qos) __rq_qos_queue_depth_changed(q->rq_qos); } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 95886b404b16..fe1797bbec42 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -656,6 +656,7 @@ enum { QUEUE_FLAG_SQ_SCHED, /* single queue style io dispatch */ QUEUE_FLAG_DISABLE_WBT_DEF, /* for sched to disable/enable wbt */ QUEUE_FLAG_NO_ELV_SWITCH, /* can't switch elevator any more */ + QUEUE_FLAG_QOS_ENABLED, /* qos is enabled */ QUEUE_FLAG_MAX }; -- cgit v1.2.3 From b08a784a5d1495c42ff9b0c70887d49211cddfe0 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 18 Aug 2025 19:03:54 +0100 Subject: net: Introduce skb_copy_datagram_from_iter_full() In a similar manner to copy_from_iter()/copy_from_iter_full(), introduce skb_copy_datagram_from_iter_full() which reverts the iterator to its initial state when returning an error. A subsequent fix for a vsock regression will make use of this new function. Cc: Christian Brauner Cc: Alexander Viro Signed-off-by: Will Deacon Acked-by: Michael S. Tsirkin Reviewed-by: Stefan Hajnoczi Link: https://patch.msgid.link/20250818180355.29275-2-will@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 2 ++ net/core/datagram.c | 14 ++++++++++++++ 2 files changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 14b923ddb6df..fa633657e4c0 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4172,6 +4172,8 @@ int skb_copy_and_crc32c_datagram_iter(const struct sk_buff *skb, int offset, struct iov_iter *to, int len, u32 *crcp); int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset, struct iov_iter *from, int len); +int skb_copy_datagram_from_iter_full(struct sk_buff *skb, int offset, + struct iov_iter *from, int len); int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm); void skb_free_datagram(struct sock *sk, struct sk_buff *skb); int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); diff --git a/net/core/datagram.c b/net/core/datagram.c index 94cc4705e91d..f474b9b120f9 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -618,6 +618,20 @@ fault: } EXPORT_SYMBOL(skb_copy_datagram_from_iter); +int skb_copy_datagram_from_iter_full(struct sk_buff *skb, int offset, + struct iov_iter *from, int len) +{ + struct iov_iter_state state; + int ret; + + iov_iter_save_state(from, &state); + ret = skb_copy_datagram_from_iter(skb, offset, from, len); + if (ret) + iov_iter_restore(from, &state); + return ret; +} +EXPORT_SYMBOL(skb_copy_datagram_from_iter_full); + int zerocopy_fill_skb_from_iter(struct sk_buff *skb, struct iov_iter *from, size_t length) { -- cgit v1.2.3 From ec79003c5f9d2c7f9576fc69b8dbda80305cbe3a Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 21 Aug 2025 02:18:24 +0000 Subject: atm: atmtcp: Prevent arbitrary write in atmtcp_recv_control(). syzbot reported the splat below. [0] When atmtcp_v_open() or atmtcp_v_close() is called via connect() or close(), atmtcp_send_control() is called to send an in-kernel special message. The message has ATMTCP_HDR_MAGIC in atmtcp_control.hdr.length. Also, a pointer of struct atm_vcc is set to atmtcp_control.vcc. The notable thing is struct atmtcp_control is uAPI but has a space for an in-kernel pointer. struct atmtcp_control { struct atmtcp_hdr hdr; /* must be first */ ... atm_kptr_t vcc; /* both directions */ ... } __ATM_API_ALIGN; typedef struct { unsigned char _[8]; } __ATM_API_ALIGN atm_kptr_t; The special message is processed in atmtcp_recv_control() called from atmtcp_c_send(). atmtcp_c_send() is vcc->dev->ops->send() and called from 2 paths: 1. .ndo_start_xmit() (vcc->send() == atm_send_aal0()) 2. vcc_sendmsg() The problem is sendmsg() does not validate the message length and userspace can abuse atmtcp_recv_control() to overwrite any kptr by atmtcp_control. Let's add a new ->pre_send() hook to validate messages from sendmsg(). [0]: Oops: general protection fault, probably for non-canonical address 0xdffffc00200000ab: 0000 [#1] SMP KASAN PTI KASAN: probably user-memory-access in range [0x0000000100000558-0x000000010000055f] CPU: 0 UID: 0 PID: 5865 Comm: syz-executor331 Not tainted 6.17.0-rc1-syzkaller-00215-gbab3ce404553 #0 PREEMPT(full) Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/12/2025 RIP: 0010:atmtcp_recv_control drivers/atm/atmtcp.c:93 [inline] RIP: 0010:atmtcp_c_send+0x1da/0x950 drivers/atm/atmtcp.c:297 Code: 4d 8d 75 1a 4c 89 f0 48 c1 e8 03 42 0f b6 04 20 84 c0 0f 85 15 06 00 00 41 0f b7 1e 4d 8d b7 60 05 00 00 4c 89 f0 48 c1 e8 03 <42> 0f b6 04 20 84 c0 0f 85 13 06 00 00 66 41 89 1e 4d 8d 75 1c 4c RSP: 0018:ffffc90003f5f810 EFLAGS: 00010203 RAX: 00000000200000ab RBX: 0000000000000000 RCX: 0000000000000000 RDX: ffff88802a510000 RSI: 00000000ffffffff RDI: ffff888030a6068c RBP: ffff88802699fb40 R08: ffff888030a606eb R09: 1ffff1100614c0dd R10: dffffc0000000000 R11: ffffffff8718fc40 R12: dffffc0000000000 R13: ffff888030a60680 R14: 000000010000055f R15: 00000000ffffffff FS: 00007f8d7e9236c0(0000) GS:ffff888125c1c000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000045ad50 CR3: 0000000075bde000 CR4: 00000000003526f0 Call Trace: vcc_sendmsg+0xa10/0xc60 net/atm/common.c:645 sock_sendmsg_nosec net/socket.c:714 [inline] __sock_sendmsg+0x219/0x270 net/socket.c:729 ____sys_sendmsg+0x505/0x830 net/socket.c:2614 ___sys_sendmsg+0x21f/0x2a0 net/socket.c:2668 __sys_sendmsg net/socket.c:2700 [inline] __do_sys_sendmsg net/socket.c:2705 [inline] __se_sys_sendmsg net/socket.c:2703 [inline] __x64_sys_sendmsg+0x19b/0x260 net/socket.c:2703 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f8d7e96a4a9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 51 18 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f8d7e923198 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f8d7e9f4308 RCX: 00007f8d7e96a4a9 RDX: 0000000000000000 RSI: 0000200000000240 RDI: 0000000000000005 RBP: 00007f8d7e9f4300 R08: 65732f636f72702f R09: 65732f636f72702f R10: 65732f636f72702f R11: 0000000000000246 R12: 00007f8d7e9c10ac R13: 00007f8d7e9231a0 R14: 0000200000000200 R15: 0000200000000250 Modules linked in: Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot+1741b56d54536f4ec349@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/68a6767c.050a0220.3d78fd.0011.GAE@google.com/ Tested-by: syzbot+1741b56d54536f4ec349@syzkaller.appspotmail.com Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20250821021901.2814721-1-kuniyu@google.com Signed-off-by: Jakub Kicinski --- drivers/atm/atmtcp.c | 17 ++++++++++++++--- include/linux/atmdev.h | 1 + net/atm/common.c | 15 ++++++++++++--- 3 files changed, 27 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/atm/atmtcp.c b/drivers/atm/atmtcp.c index eeae160c898d..fa3c76a2b49d 100644 --- a/drivers/atm/atmtcp.c +++ b/drivers/atm/atmtcp.c @@ -279,6 +279,19 @@ static struct atm_vcc *find_vcc(struct atm_dev *dev, short vpi, int vci) return NULL; } +static int atmtcp_c_pre_send(struct atm_vcc *vcc, struct sk_buff *skb) +{ + struct atmtcp_hdr *hdr; + + if (skb->len < sizeof(struct atmtcp_hdr)) + return -EINVAL; + + hdr = (struct atmtcp_hdr *)skb->data; + if (hdr->length == ATMTCP_HDR_MAGIC) + return -EINVAL; + + return 0; +} static int atmtcp_c_send(struct atm_vcc *vcc,struct sk_buff *skb) { @@ -288,9 +301,6 @@ static int atmtcp_c_send(struct atm_vcc *vcc,struct sk_buff *skb) struct sk_buff *new_skb; int result = 0; - if (skb->len < sizeof(struct atmtcp_hdr)) - goto done; - dev = vcc->dev_data; hdr = (struct atmtcp_hdr *) skb->data; if (hdr->length == ATMTCP_HDR_MAGIC) { @@ -347,6 +357,7 @@ static const struct atmdev_ops atmtcp_v_dev_ops = { static const struct atmdev_ops atmtcp_c_dev_ops = { .close = atmtcp_c_close, + .pre_send = atmtcp_c_pre_send, .send = atmtcp_c_send }; diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index 45f2f278b50a..70807c679f1a 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -185,6 +185,7 @@ struct atmdev_ops { /* only send is required */ int (*compat_ioctl)(struct atm_dev *dev,unsigned int cmd, void __user *arg); #endif + int (*pre_send)(struct atm_vcc *vcc, struct sk_buff *skb); int (*send)(struct atm_vcc *vcc,struct sk_buff *skb); int (*send_bh)(struct atm_vcc *vcc, struct sk_buff *skb); int (*send_oam)(struct atm_vcc *vcc,void *cell,int flags); diff --git a/net/atm/common.c b/net/atm/common.c index d7f7976ea13a..881c7f259dbd 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -635,18 +635,27 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size) skb->dev = NULL; /* for paths shared with net_device interfaces */ if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) { - atm_return_tx(vcc, skb); - kfree_skb(skb); error = -EFAULT; - goto out; + goto free_skb; } if (eff != size) memset(skb->data + size, 0, eff-size); + + if (vcc->dev->ops->pre_send) { + error = vcc->dev->ops->pre_send(vcc, skb); + if (error) + goto free_skb; + } + error = vcc->dev->ops->send(vcc, skb); error = error ? error : size; out: release_sock(sk); return error; +free_skb: + atm_return_tx(vcc, skb); + kfree_skb(skb); + goto out; } __poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait) -- cgit v1.2.3 From ced17ee32a9988b8a260628e7c31a100d7dc082e Mon Sep 17 00:00:00 2001 From: Igor Torrente Date: Thu, 7 Aug 2025 09:41:45 -0300 Subject: Revert "virtio: reject shm region if length is zero" The commit 206cc44588f7 ("virtio: reject shm region if length is zero") breaks the Virtio-gpu `host_visible` feature. As you can see in the snippet below, host_visible_region is zero because of the `kzalloc`. It's using the `vm_get_shm_region` (drivers/virtio/virtio_mmio.c:536) to read the `addr` and `len` from qemu/crosvm. ``` drivers/gpu/drm/virtio/virtgpu_kms.c 132 vgdev = drmm_kzalloc(dev, sizeof(struct virtio_gpu_device), GFP_KERNEL); [...] 177 if (virtio_get_shm_region(vgdev->vdev, &vgdev->host_visible_region, 178 VIRTIO_GPU_SHM_ID_HOST_VISIBLE)) { ``` Now it always fails. To fix, revert the offending commit. Fixes: 206cc44588f7 ("virtio: reject shm region if length is zero") Signed-off-by: Igor Torrente Message-Id: <20250807124145.81816-1-igor.torrente@collabora.com> Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 918cf25cd3c6..8bf156dde554 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -328,8 +328,6 @@ static inline bool virtio_get_shm_region(struct virtio_device *vdev, struct virtio_shm_region *region, u8 id) { - if (!region->len) - return false; if (!vdev->config->get_shm_region) return false; return vdev->config->get_shm_region(vdev, region, id); -- cgit v1.2.3 From b3dcc9d1d806fb1e175f85978713eef868531da4 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" Date: Tue, 26 Aug 2025 10:19:46 +0300 Subject: memblock: fix kernel-doc for MEMBLOCK_RSRV_NOINIT The kernel-doc description of MEMBLOCK_RSRV_NOINIT and memblock_reserved_mark_noinit() do not accurately describe their functionality. Expand their kernel doc to make it clear that the user of MEMBLOCK_RSRV_NOINIT is responsible to properly initialize the struct pages for such regions and add more details about effects of using this flag. Reviewed-by: David Hildenbrand Link: https://lore.kernel.org/r/f8140a17-c4ec-489b-b314-d45abe48bf36@redhat.com Link: https://lore.kernel.org/r/20250826071947.1949725-1-rppt@kernel.org Signed-off-by: Mike Rapoport (Microsoft) --- include/linux/memblock.h | 5 +++-- mm/memblock.c | 15 +++++++++++---- 2 files changed, 14 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index b96746376e17..fcda8481de9a 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -40,8 +40,9 @@ extern unsigned long long max_possible_pfn; * via a driver, and never indicated in the firmware-provided memory map as * system RAM. This corresponds to IORESOURCE_SYSRAM_DRIVER_MANAGED in the * kernel resource tree. - * @MEMBLOCK_RSRV_NOINIT: memory region for which struct pages are - * not initialized (only for reserved regions). + * @MEMBLOCK_RSRV_NOINIT: reserved memory region for which struct pages are not + * fully initialized. Users of this flag are responsible to properly initialize + * struct pages of this region * @MEMBLOCK_RSRV_KERN: memory region that is reserved for kernel use, * either explictitly with memblock_reserve_kern() or via memblock * allocation APIs. All memblock allocations set this flag. diff --git a/mm/memblock.c b/mm/memblock.c index 8a0ed3074af4..117d963e677c 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1091,13 +1091,20 @@ int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size) /** * memblock_reserved_mark_noinit - Mark a reserved memory region with flag - * MEMBLOCK_RSRV_NOINIT which results in the struct pages not being initialized - * for this region. + * MEMBLOCK_RSRV_NOINIT + * * @base: the base phys addr of the region * @size: the size of the region * - * struct pages will not be initialized for reserved memory regions marked with - * %MEMBLOCK_RSRV_NOINIT. + * The struct pages for the reserved regions marked %MEMBLOCK_RSRV_NOINIT will + * not be fully initialized to allow the caller optimize their initialization. + * + * When %CONFIG_DEFERRED_STRUCT_PAGE_INIT is enabled, setting this flag + * completely bypasses the initialization of struct pages for such region. + * + * When %CONFIG_DEFERRED_STRUCT_PAGE_INIT is disabled, struct pages in this + * region will be initialized with default values but won't be marked as + * reserved. * * Return: 0 on success, -errno on failure. */ -- cgit v1.2.3 From d1dd75c6500c74b91c5286fd3277710371d3e3ca Mon Sep 17 00:00:00 2001 From: Rahul Rameshbabu Date: Sat, 13 Sep 2025 16:12:54 +0000 Subject: HID: core: Change hid_driver to use a const char* for name name is never mutated by the core HID stack. Making name a const char* simplifies passing the string from Rust to C. Otherwise, it becomes difficult to pass a 'static lifetime CStr from Rust to a char*, rather than a const char*, due to lack of guarantee that the underlying data of the CStr will not be mutated by the C code. Signed-off-by: Rahul Rameshbabu Signed-off-by: Benjamin Tissoires --- include/linux/hid.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 2cc4f1e4ea96..426b22ed42b4 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -816,7 +816,7 @@ struct hid_usage_id { * zero from them. */ struct hid_driver { - char *name; + const char *name; const struct hid_device_id *id_table; struct list_head dyn_list; -- cgit v1.2.3