From 53716a4d745f1dac7aff33f3d1494b701eb2f888 Mon Sep 17 00:00:00 2001 From: Seth Forshee Date: Tue, 2 Jun 2026 21:54:06 +0000 Subject: [PATCH 01/25] firmware: arm_ffa: Respect firmware advertised RX/TX buffer size limits FFA_FEATURES reports the minimum size and alignment boundary required for RXTX_MAP. In FF-A v1.2 and later it can also report a maximum buffer size, with zero meaning that no maximum is enforced. The driver only used the minimum value and then rounded it up to PAGE_SIZE before invoking RXTX_MAP after commit 83210251fd70 ("firmware: arm_ffa: Use the correct buffer size during RXTX_MAP"). On systems where PAGE_SIZE is larger than the advertised minimum, this can exceed a non-zero maximum reported by firmware. Older implementations do not advertise a maximum and may also reject the rounded-up size. Decode the maximum size and clamp the page-aligned minimum to it when it is present. If no maximum is advertised and RXTX_MAP rejects the rounded size with INVALID_PARAMETERS, retry with the advertised minimum size. Record drv_info->rxtx_bufsz only after RXTX_MAP succeeds so it reflects the size registered with firmware. While there, also update RXTX_MAP_MIN_BUFSZ() to use FIELD_GET() for consistency. Fixes: 83210251fd70 ("firmware: arm_ffa: Use the correct buffer size during RXTX_MAP") Suggested-by: Sudeep Holla Signed-off-by: Seth Forshee Link: https://patch.msgid.link/20260602-b4-ffa-rxtx-map-fixes-v2-1-7cb06508da84@nvidia.com (sudeep.holla: Minor rewording subject and commit message) Signed-off-by: Sudeep Holla --- drivers/firmware/arm_ffa/driver.c | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-) diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index 0f468362c288..bc2685331b27 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include #include @@ -59,7 +60,9 @@ (FIELD_PREP(SENDER_ID_MASK, (s)) | FIELD_PREP(RECEIVER_ID_MASK, (r))) #define RXTX_MAP_MIN_BUFSZ_MASK GENMASK(1, 0) -#define RXTX_MAP_MIN_BUFSZ(x) ((x) & RXTX_MAP_MIN_BUFSZ_MASK) +#define RXTX_MAP_MAX_BUFSZ_MASK GENMASK(31, 16) +#define RXTX_MAP_MIN_BUFSZ(x) (FIELD_GET(RXTX_MAP_MIN_BUFSZ_MASK, (x))) +#define RXTX_MAP_MAX_BUFSZ(x) (FIELD_GET(RXTX_MAP_MAX_BUFSZ_MASK, (x))) #define FFA_MAX_NOTIFICATIONS 64 @@ -2101,7 +2104,7 @@ static int ffa_probe(struct platform_device *pdev) { int ret; u32 buf_sz; - size_t rxtx_bufsz = SZ_4K; + size_t rxtx_min_bufsz = SZ_4K, rxtx_max_bufsz = 0, rxtx_bufsz; if (IS_BUILTIN(CONFIG_ARM_FFA_TRANSPORT) && is_protected_kvm_enabled() && !is_pkvm_initialized()) @@ -2132,15 +2135,18 @@ static int ffa_probe(struct platform_device *pdev) ret = ffa_features(FFA_FN_NATIVE(RXTX_MAP), 0, &buf_sz, NULL); if (!ret) { if (RXTX_MAP_MIN_BUFSZ(buf_sz) == 1) - rxtx_bufsz = SZ_64K; + rxtx_min_bufsz = SZ_64K; else if (RXTX_MAP_MIN_BUFSZ(buf_sz) == 2) - rxtx_bufsz = SZ_16K; + rxtx_min_bufsz = SZ_16K; else - rxtx_bufsz = SZ_4K; + rxtx_min_bufsz = SZ_4K; + + rxtx_max_bufsz = RXTX_MAP_MAX_BUFSZ(buf_sz) * SZ_4K; + if (rxtx_max_bufsz != 0 && rxtx_max_bufsz < rxtx_min_bufsz) + rxtx_max_bufsz = rxtx_min_bufsz; } - rxtx_bufsz = PAGE_ALIGN(rxtx_bufsz); - drv_info->rxtx_bufsz = rxtx_bufsz; + rxtx_bufsz = min_not_zero(PAGE_ALIGN(rxtx_min_bufsz), rxtx_max_bufsz); drv_info->rx_buffer = alloc_pages_exact(rxtx_bufsz, GFP_KERNEL); if (!drv_info->rx_buffer) { ret = -ENOMEM; @@ -2156,10 +2162,17 @@ static int ffa_probe(struct platform_device *pdev) ret = ffa_rxtx_map(virt_to_phys(drv_info->tx_buffer), virt_to_phys(drv_info->rx_buffer), rxtx_bufsz / FFA_PAGE_SIZE); + if (ret == -EINVAL && !rxtx_max_bufsz && rxtx_min_bufsz < rxtx_bufsz) { + rxtx_bufsz = rxtx_min_bufsz; + ret = ffa_rxtx_map(virt_to_phys(drv_info->tx_buffer), + virt_to_phys(drv_info->rx_buffer), + rxtx_bufsz / FFA_PAGE_SIZE); + } if (ret) { pr_err("failed to register FFA RxTx buffers\n"); goto free_pages; } + drv_info->rxtx_bufsz = rxtx_bufsz; mutex_init(&drv_info->rx_lock); mutex_init(&drv_info->tx_lock); From 8ae5f8e4836667fcaffdf2e3c6068b0a8b364dd8 Mon Sep 17 00:00:00 2001 From: Unnathi Chalicheemala Date: Wed, 17 Jun 2026 16:35:00 -0700 Subject: [PATCH 02/25] firmware: arm_ffa: Fix NULL dereference in ffa_partition_info_get() ffa_partition_info_get() passes uuid_str directly to uuid_parse() without a NULL check. When a caller passes NULL, uuid_parse() -> __uuid_parse() -> uuid_is_valid() dereferences the pointer, causing a kernel panic: | Unable to handle kernel NULL pointer dereference at virtual address | 0000000000000040 | pc : uuid_parse+0x40/0xac | lr : ffa_partition_info_get+0x1c/0x94 [arm_ffa] Add a NULL guard before uuid_parse() so a NULL argument returns -ENODEV instead of crashing. Callers are expected to always supply a valid partition UUID, so NULL is not a supported input. Fixes: d0c0bce83122 ("firmware: arm_ffa: Setup in-kernel users of FFA partitions") Signed-off-by: Unnathi Chalicheemala Link: https://patch.msgid.link/20260617-ffa_partition_nullptr_fix-v2-1-bc801b4ce34c@oss.qualcomm.com Signed-off-by: Sudeep Holla --- drivers/firmware/arm_ffa/driver.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index bc2685331b27..d475ff83132d 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -1142,7 +1142,7 @@ static int ffa_partition_info_get(const char *uuid_str, uuid_t uuid; struct ffa_partition_info *pbuf; - if (uuid_parse(uuid_str, &uuid)) { + if (!uuid_str || uuid_parse(uuid_str, &uuid)) { pr_err("invalid uuid (%s)\n", uuid_str); return -ENODEV; } From 05e5ffde9b666ee6d3ec225efeda9c038fa74ac8 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 3 Jun 2026 17:17:51 +0200 Subject: [PATCH 03/25] firmware: arm_scmi: Grammar s/may needed/may be needed/ Fix grammar in the help text for the ARM_SCMI_POWER_CONTROL symbol. Signed-off-by: Geert Uytterhoeven Link: https://patch.msgid.link/5180d04abfb8e3074a321e2eb73bacfdd61c30c5.1780499850.git.geert+renesas@glider.be Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/arm_scmi/Kconfig b/drivers/firmware/arm_scmi/Kconfig index e3fb36825978..783c24a20e29 100644 --- a/drivers/firmware/arm_scmi/Kconfig +++ b/drivers/firmware/arm_scmi/Kconfig @@ -96,7 +96,7 @@ config ARM_SCMI_POWER_CONTROL firmware. This driver can also be built as a module. If so, the module will be - called scmi_power_control. Note this may needed early in boot to catch - early shutdown/reboot SCMI requests. + called scmi_power_control. Note this may be needed early in boot to + catch early shutdown/reboot SCMI requests. endmenu From bf1deecccf210d1dd84e85cd4a45070888583984 Mon Sep 17 00:00:00 2001 From: Steve Dunnagan Date: Wed, 1 Jul 2026 15:59:20 -0400 Subject: [PATCH 04/25] firmware: arm_scmi: Use 64-bit division for clock rate rounding SCMI clock range descriptors report rates as 64-bit values. When handling a range clock, scmi_clock_determine_rate() rounds the requested rate up to the next supported step using the SCMI RATE_STEP value. The current code uses div64_ul() for this calculation. Since div64_ul() takes an unsigned long divisor, the 64-bit RATE_STEP value can be truncated on 32-bit builds. In the worst case, a non-zero 64-bit step can be narrowed to zero before the division. Store RATE_STEP in a u64, reject a malformed zero step, and use DIV64_U64_ROUND_UP() so the divisor is handled as a 64-bit value. This does not change behavior for valid firmware reporting a non-zero step that fits in unsigned long. Tested on Xunlong Orange Pi 5 Plus / RK3588 with SCMI over SMC. SCMI clocks probed successfully before and after the change. SCMI-backed CPU clocks were exercised through cpufreq-dt by switching each CPU policy between its lowest and highest available OPP. Fixes: ecde921eb460 ("firmware: arm_scmi: Add clock determine_rate operation") Signed-off-by: Steve Dunnagan Link: https://patch.msgid.link/20260701195923.444270-1-sdunnaga@redhat.com Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/clock.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/firmware/arm_scmi/clock.c b/drivers/firmware/arm_scmi/clock.c index 42e666a628c7..0278705d809e 100644 --- a/drivers/firmware/arm_scmi/clock.c +++ b/drivers/firmware/arm_scmi/clock.c @@ -718,7 +718,7 @@ static int scmi_clock_rate_set(const struct scmi_protocol_handle *ph, static int scmi_clock_determine_rate(const struct scmi_protocol_handle *ph, u32 clk_id, unsigned long *rate) { - u64 fmin, fmax, ftmp; + u64 fmin, fmax, ftmp, step; struct scmi_clock_info *clk; struct scmi_clock_desc *clkd; struct clock_info *ci = ph->get_priv(ph); @@ -749,11 +749,14 @@ static int scmi_clock_determine_rate(const struct scmi_protocol_handle *ph, return 0; } - ftmp = *rate - fmin; - ftmp += clkd->r.rates[RATE_STEP] - 1; /* to round up */ - ftmp = div64_ul(ftmp, clkd->r.rates[RATE_STEP]); + step = clkd->r.rates[RATE_STEP]; + if (!step) + return -EINVAL; - *rate = ftmp * clkd->r.rates[RATE_STEP] + fmin; + ftmp = *rate - fmin; + ftmp = DIV64_U64_ROUND_UP(ftmp, step); + + *rate = ftmp * step + fmin; return 0; } From a4447c0693830d5ecadd6e755cb7fdc55d86aacc Mon Sep 17 00:00:00 2001 From: Pushpendra Singh Date: Wed, 8 Jul 2026 12:53:39 +0530 Subject: [PATCH 05/25] firmware: arm_scmi: Rate-limit queue-full warnings in IRQ context The scmi_notify() function is called from interrupt context to queue received notification events onto a per-protocol kfifo. When the kfifo is full, it logs a warning via dev_warn() for every dropped event. Under conditions where the platform sends a burst of SCMI notifications faster than the deferred worker can drain the queue, this results in a flood of dev_warn() calls from IRQ context. Each call acquires the console lock and may execute blocking console writes, causing the CPU to be held in interrupt context for an extended period and leading to observable system stalls. Fix this by switching to dev_warn_ratelimited() to limit the frequency of log messages when the notification queue is full. This reduces console overhead in interrupt context and prevents CPU stalls caused by excessive logging, while still preserving diagnostic visibility. Fixes: bd31b249692e ("firmware: arm_scmi: Add notification dispatch and delivery") Signed-off-by: Pushpendra Singh Link: https://patch.msgid.link/20260708072339.3021140-1-pushpendra.singh@oss.qualcomm.com Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/notify.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/firmware/arm_scmi/notify.c b/drivers/firmware/arm_scmi/notify.c index 40ec184eedae..0a192cf2deab 100644 --- a/drivers/firmware/arm_scmi/notify.c +++ b/drivers/firmware/arm_scmi/notify.c @@ -600,9 +600,9 @@ int scmi_notify(const struct scmi_handle *handle, u8 proto_id, u8 evt_id, return -EINVAL; } if (kfifo_avail(&r_evt->proto->equeue.kfifo) < sizeof(eh) + len) { - dev_warn(handle->dev, - "queue full, dropping proto_id:%d evt_id:%d ts:%lld\n", - proto_id, evt_id, ktime_to_ns(ts)); + dev_warn_ratelimited(handle->dev, + "queue full, dropping proto_id:%d evt_id:%d ts:%lld\n", + proto_id, evt_id, ktime_to_ns(ts)); return -ENOMEM; } From 9c62bb72a5d02795f767cf9f5e5dd781d8ccf70a Mon Sep 17 00:00:00 2001 From: Rosen Penev Date: Tue, 30 Jun 2026 13:47:19 -0700 Subject: [PATCH 06/25] firmware: arm_scmi: Simplify notification allocations Several SCMI notification data structures allocate a descriptor and then allocate a fixed-size array referenced by that descriptor. Use flexible array members for per-protocol registered events and per-event source refcounts so each descriptor and its array can be allocated together. Annotate the flexible arrays with __counted_by() and assign the count fields immediately after allocation, before any array access. The registered_protocols table has a fixed SCMI_MAX_PROTO size, so embed it directly in the notification instance instead of allocating it separately. Signed-off-by: Rosen Penev Link: https://patch.msgid.link/20260630204719.334211-1-rosenp@gmail.com (sudeep.holla: Updated title and improved change description) Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/notify.c | 43 ++++++++++++------------------ 1 file changed, 17 insertions(+), 26 deletions(-) diff --git a/drivers/firmware/arm_scmi/notify.c b/drivers/firmware/arm_scmi/notify.c index 0a192cf2deab..3cf706aacc11 100644 --- a/drivers/firmware/arm_scmi/notify.c +++ b/drivers/firmware/arm_scmi/notify.c @@ -209,11 +209,11 @@ struct scmi_registered_events_desc; * @init_work: A work item to perform final initializations of pending handlers * @notify_wq: A reference to the allocated Kernel cmwq * @pending_mtx: A mutex to protect @pending_events_handlers + * @pending_events_handlers: An hashtable containing all pending events' + * handlers descriptors * @registered_protocols: A statically allocated array containing pointers to * all the registered protocol-level specific information * related to events' handling - * @pending_events_handlers: An hashtable containing all pending events' - * handlers descriptors * * Each platform instance, represented by a handle, has its own instance of * the notification subsystem represented by this structure. @@ -225,8 +225,8 @@ struct scmi_notify_instance { struct workqueue_struct *notify_wq; /* lock to protect pending_events_handlers */ struct mutex pending_mtx; - struct scmi_registered_events_desc **registered_protocols; DECLARE_HASHTABLE(pending_events_handlers, SCMI_PENDING_HASH_SZ); + struct scmi_registered_events_desc *registered_protocols[SCMI_MAX_PROTO]; }; /** @@ -276,13 +276,13 @@ struct scmi_registered_event; * @eh_sz: Size of the pre-allocated buffer @eh * @in_flight: A reference to an in flight &struct scmi_registered_event * @num_events: Number of events in @registered_events - * @registered_events: A dynamically allocated array holding all the registered - * events' descriptors, whose fixed-size is determined at - * compile time. * @registered_mtx: A mutex to protect @registered_events_handlers * @ph: SCMI protocol handle reference * @registered_events_handlers: An hashtable containing all events' handlers * descriptors registered for this protocol + * @registered_events: A dynamically allocated array holding all the registered + * events' descriptors, whose fixed-size is determined at + * compile time. * * All protocols that register at least one event have their protocol-specific * information stored here, together with the embedded allocated events_queue. @@ -302,11 +302,11 @@ struct scmi_registered_events_desc { size_t eh_sz; void *in_flight; int num_events; - struct scmi_registered_event **registered_events; /* mutex to protect registered_events_handlers */ struct mutex registered_mtx; const struct scmi_protocol_handle *ph; DECLARE_HASHTABLE(registered_events_handlers, SCMI_REGISTERED_HASH_SZ); + struct scmi_registered_event *registered_events[] __counted_by(num_events); }; /** @@ -338,9 +338,9 @@ struct scmi_registered_event { void *report; u32 num_sources; bool not_supported_by_platform; - refcount_t *sources; /* locking to serialize the access to sources */ struct mutex sources_mtx; + refcount_t sources[] __counted_by(num_sources); }; /** @@ -706,9 +706,13 @@ scmi_allocate_registered_events_desc(struct scmi_notify_instance *ni, if (WARN_ON(ni->registered_protocols[proto_id])) return ERR_PTR(-EINVAL); - pd = devm_kzalloc(ni->handle->dev, sizeof(*pd), GFP_KERNEL); + pd = devm_kzalloc(ni->handle->dev, + struct_size(pd, registered_events, num_events), + GFP_KERNEL); if (!pd) return ERR_PTR(-ENOMEM); + + pd->num_events = num_events; pd->id = proto_id; pd->ops = ops; pd->ni = ni; @@ -722,12 +726,6 @@ scmi_allocate_registered_events_desc(struct scmi_notify_instance *ni, return ERR_PTR(-ENOMEM); pd->eh_sz = eh_sz; - pd->registered_events = devm_kcalloc(ni->handle->dev, num_events, - sizeof(char *), GFP_KERNEL); - if (!pd->registered_events) - return ERR_PTR(-ENOMEM); - pd->num_events = num_events; - /* Initialize per protocol handlers table */ mutex_init(&pd->registered_mtx); hash_init(pd->registered_events_handlers); @@ -796,18 +794,16 @@ int scmi_register_protocol_events(const struct scmi_handle *handle, u8 proto_id, int id; struct scmi_registered_event *r_evt; - r_evt = devm_kzalloc(ni->handle->dev, sizeof(*r_evt), + r_evt = devm_kzalloc(ni->handle->dev, + struct_size(r_evt, sources, num_sources), GFP_KERNEL); if (!r_evt) return -ENOMEM; + + r_evt->num_sources = num_sources; r_evt->proto = pd; r_evt->evt = evt; - r_evt->sources = devm_kcalloc(ni->handle->dev, num_sources, - sizeof(refcount_t), GFP_KERNEL); - if (!r_evt->sources) - return -ENOMEM; - r_evt->num_sources = num_sources; mutex_init(&r_evt->sources_mtx); r_evt->report = devm_kzalloc(ni->handle->dev, @@ -1673,11 +1669,6 @@ int scmi_notification_init(struct scmi_handle *handle) ni->gid = gid; ni->handle = handle; - ni->registered_protocols = devm_kcalloc(handle->dev, SCMI_MAX_PROTO, - sizeof(char *), GFP_KERNEL); - if (!ni->registered_protocols) - goto err; - ni->notify_wq = alloc_workqueue(dev_name(handle->dev), WQ_UNBOUND | WQ_FREEZABLE | WQ_SYSFS, 0); From 0314900dcdde044af0208fed212035dbfaa55843 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 14 Jul 2026 13:56:20 +0100 Subject: [PATCH 07/25] firmware: arm_scmi: Publish channel state before callbacks Transport setup can enable callbacks before the setup routine returns. mailbox_chan_setup() registers the mailbox client with mbox_request_channel(), and the mailbox controller startup path can enable interrupt delivery before SCMI mailbox channel state has been published. Similarly, smc_chan_setup() requests the optional A2P completion IRQ before the SMC transport has made its cinfo pointer visible. If a pending or spurious callback fires in those windows, the transport RX callback can dereference a NULL transport cinfo pointer. Publishing only the transport-private pointer is not sufficient either: an early callback can enter the SCMI core before scmi_chan_setup() has assigned cinfo->handle. The core derives scmi_info from cinfo->handle in the RX path, so a NULL handle can still fault even when the transport-private cinfo is valid. Assign cinfo->handle before invoking the transport setup callback. Publish the mailbox and SMC transport-private channel state before requesting the mailbox channels or IRQ, and clear the early-published pointers again on setup failure. Also unwind mailbox setup devres resources on failure so an optional RX setup error that is ignored by the core does not leave stale transport state behind. Fixes: 5c8a47a5a91d ("firmware: arm_scmi: Make scmi core independent of the transport type") Reported-by: Sashiko Link: https://patch.msgid.link/20260714-scmi_core_fixes-v6-1-3afe499d46e3@kernel.org Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/driver.c | 2 +- drivers/firmware/arm_scmi/transports/mailbox.c | 18 +++++++++++++----- drivers/firmware/arm_scmi/transports/smc.c | 15 +++++++++------ 3 files changed, 23 insertions(+), 12 deletions(-) diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 3e0d975ec94c..1d1f5d25d773 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -2782,6 +2782,7 @@ static int scmi_chan_setup(struct scmi_info *info, struct device_node *of_node, cinfo->id = prot_id; cinfo->dev = &tdev->dev; + cinfo->handle = &info->handle; ret = info->desc->ops->chan_setup(cinfo, info->dev, tx); if (ret) { of_node_put(of_node); @@ -2814,7 +2815,6 @@ static int scmi_chan_setup(struct scmi_info *info, struct device_node *of_node, return ret; } - cinfo->handle = &info->handle; return 0; } diff --git a/drivers/firmware/arm_scmi/transports/mailbox.c b/drivers/firmware/arm_scmi/transports/mailbox.c index ae0f67e6cc45..b6459fbb8151 100644 --- a/drivers/firmware/arm_scmi/transports/mailbox.c +++ b/drivers/firmware/arm_scmi/transports/mailbox.c @@ -211,13 +211,18 @@ static int mailbox_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, cl->tx_block = false; cl->knows_txdone = tx; + cinfo->transport_info = smbox; + smbox->cinfo = cinfo; + mutex_init(&smbox->chan_lock); + smbox->chan = mbox_request_channel(cl, tx ? 0 : p2a_chan); if (IS_ERR(smbox->chan)) { ret = PTR_ERR(smbox->chan); + smbox->chan = NULL; if (ret != -EPROBE_DEFER) dev_err(cdev, "failed to request SCMI %s mailbox\n", desc); - return ret; + goto err_clear_cinfo; } /* Additional unidirectional channel for TX if needed */ @@ -241,11 +246,14 @@ static int mailbox_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, } } - cinfo->transport_info = smbox; - smbox->cinfo = cinfo; - mutex_init(&smbox->chan_lock); - return 0; + +err_clear_cinfo: + cinfo->transport_info = NULL; + smbox->cinfo = NULL; + devm_iounmap(dev, smbox->shmem); + devm_kfree(dev, smbox); + return ret; } static int mailbox_chan_free(int id, void *p, void *data) diff --git a/drivers/firmware/arm_scmi/transports/smc.c b/drivers/firmware/arm_scmi/transports/smc.c index 21abb571e4f2..1fce3ccdeb7f 100644 --- a/drivers/firmware/arm_scmi/transports/smc.c +++ b/drivers/firmware/arm_scmi/transports/smc.c @@ -172,6 +172,13 @@ static int smc_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, scmi_info->param_page = SHMEM_PAGE(res.start); scmi_info->param_offset = SHMEM_OFFSET(res.start); } + + scmi_info->func_id = func_id; + scmi_info->cap_id = cap_id; + scmi_info->cinfo = cinfo; + smc_channel_lock_init(scmi_info); + cinfo->transport_info = scmi_info; + /* * If there is an interrupt named "a2p", then the service and * completion of a message is signaled by an interrupt rather than by @@ -183,18 +190,14 @@ static int smc_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, IRQF_NO_SUSPEND, dev_name(dev), scmi_info); if (ret) { dev_err(dev, "failed to setup SCMI smc irq\n"); + cinfo->transport_info = NULL; + scmi_info->cinfo = NULL; return ret; } } else { cinfo->no_completion_irq = true; } - scmi_info->func_id = func_id; - scmi_info->cap_id = cap_id; - scmi_info->cinfo = cinfo; - smc_channel_lock_init(scmi_info); - cinfo->transport_info = scmi_info; - return 0; } From 66a0bbf30cc14140fe13f63cd594a7c1ee352b75 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 14 Jul 2026 13:56:21 +0100 Subject: [PATCH 08/25] firmware: arm_scmi: Unregister device notifier before IDR teardown The requested-devices notifier looks up protocol fwnodes from the active_protocols IDR. During remove, unregister the notifier before releasing and destroying active_protocols so no notifier callback can race with the IDR teardown. Keep the bus notifier registered until after the protocol state is torn down, matching the existing remove ordering for SCMI bus users. Fixes: 53b8c25df708 ("firmware: arm_scmi: Add common notifier helpers") Reported-by: Sashiko Link: https://patch.msgid.link/20260714-scmi_core_fixes-v6-2-3afe499d46e3@kernel.org Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/driver.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 1d1f5d25d773..52aff3aded4c 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -3401,6 +3401,9 @@ static void scmi_remove(struct platform_device *pdev) list_del(&info->node); mutex_unlock(&scmi_list_mutex); + blocking_notifier_chain_unregister(&scmi_requested_devices_nh, + &info->dev_req_nb); + scmi_notification_exit(&info->handle); mutex_lock(&info->protocols_mtx); @@ -3411,8 +3414,6 @@ static void scmi_remove(struct platform_device *pdev) of_node_put(child); idr_destroy(&info->active_protocols); - blocking_notifier_chain_unregister(&scmi_requested_devices_nh, - &info->dev_req_nb); bus_unregister_notifier(&scmi_bus_type, &info->bus_nb); /* Safe to free channels since no more users */ From 8e49055d0d495c9c07575ad8e111d9eaf0efb13f Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 14 Jul 2026 13:56:22 +0100 Subject: [PATCH 09/25] firmware: arm_scmi: Quiesce notifications before teardown scmi_notification_exit() clears and releases the notification instance, but transport callbacks can still deliver incoming notifications until the TX/RX channels are freed. During remove, an RX interrupt in that window can enter scmi_notify() while notification state is being torn down and then dereference freed memory. The same ordering exists on the probe error path after notification initialization. The notification late-init worker has a separate lifetime issue: protocol event registration queues ni->init_work on the system workqueue, so destroying ni->notify_wq does not drain that work. If the devres group is released while init_work is still pending or running, the late-init worker can dereference the freed notification instance. Quiesce the notification core before TX/RX channels are torn down, then clean up the channels before releasing the notification core resources. Use disable_work_sync() so future late-init queueing is rejected and any already queued or running late-init work has completed before channel teardown starts. Fixes: 1e7cbfaa66d3 ("firmware: arm_scmi: Free mailbox channels if probe fails") Reported-by: Sashiko Link: https://patch.msgid.link/20260714-scmi_core_fixes-v6-3-3afe499d46e3@kernel.org Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/driver.c | 13 +++++++------ drivers/firmware/arm_scmi/notify.c | 21 +++++++++++++++++++++ drivers/firmware/arm_scmi/notify.h | 1 + 3 files changed, 29 insertions(+), 6 deletions(-) diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 52aff3aded4c..ec373595f955 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -3325,7 +3325,7 @@ static int scmi_probe(struct platform_device *pdev) dev_err(dev, "%s", err_str); return 0; } - goto notification_exit; + goto raw_mode_cleanup; } mutex_lock(&scmi_list_mutex); @@ -3367,17 +3367,18 @@ static int scmi_probe(struct platform_device *pdev) return 0; -notification_exit: +raw_mode_cleanup: if (IS_ENABLED(CONFIG_ARM_SCMI_RAW_MODE_SUPPORT)) scmi_raw_mode_cleanup(info->raw); - scmi_notification_exit(&info->handle); clear_dev_req_notifier: blocking_notifier_chain_unregister(&scmi_requested_devices_nh, &info->dev_req_nb); clear_bus_notifier: bus_unregister_notifier(&scmi_bus_type, &info->bus_nb); clear_txrx_setup: + scmi_notification_quiesce(&info->handle); scmi_cleanup_txrx_channels(info); + scmi_notification_exit(&info->handle); clear_ida: ida_free(&scmi_id, info->id); @@ -3404,6 +3405,9 @@ static void scmi_remove(struct platform_device *pdev) blocking_notifier_chain_unregister(&scmi_requested_devices_nh, &info->dev_req_nb); + /* Stop transport callbacks before tearing down notifications. */ + scmi_notification_quiesce(&info->handle); + scmi_cleanup_txrx_channels(info); scmi_notification_exit(&info->handle); mutex_lock(&info->protocols_mtx); @@ -3416,9 +3420,6 @@ static void scmi_remove(struct platform_device *pdev) bus_unregister_notifier(&scmi_bus_type, &info->bus_nb); - /* Safe to free channels since no more users */ - scmi_cleanup_txrx_channels(info); - ida_free(&scmi_id, info->id); } diff --git a/drivers/firmware/arm_scmi/notify.c b/drivers/firmware/arm_scmi/notify.c index 3cf706aacc11..fb60fb07c0ed 100644 --- a/drivers/firmware/arm_scmi/notify.c +++ b/drivers/firmware/arm_scmi/notify.c @@ -1697,6 +1697,25 @@ int scmi_notification_init(struct scmi_handle *handle) return -ENOMEM; } +/** + * scmi_notification_quiesce() - Stop notification late initialization + * @handle: The handle identifying the platform instance to quiesce + * + * Prevent new late-init work from being queued and wait for any already queued + * or running late-init work to complete before transport channels are torn + * down. + */ +void scmi_notification_quiesce(struct scmi_handle *handle) +{ + struct scmi_notify_instance *ni; + + ni = scmi_notification_instance_data_get(handle); + if (!ni) + return; + + disable_work_sync(&ni->init_work); +} + /** * scmi_notification_exit() - Shutdown and clean Notification core * @handle: The handle identifying the platform instance to shutdown @@ -1708,6 +1727,8 @@ void scmi_notification_exit(struct scmi_handle *handle) ni = scmi_notification_instance_data_get(handle); if (!ni) return; + + scmi_notification_quiesce(handle); scmi_notification_instance_data_set(handle, NULL); /* Destroy while letting pending work complete */ diff --git a/drivers/firmware/arm_scmi/notify.h b/drivers/firmware/arm_scmi/notify.h index 76758a736cf4..f18f98c5ab3b 100644 --- a/drivers/firmware/arm_scmi/notify.h +++ b/drivers/firmware/arm_scmi/notify.h @@ -82,6 +82,7 @@ struct scmi_protocol_events { }; int scmi_notification_init(struct scmi_handle *handle); +void scmi_notification_quiesce(struct scmi_handle *handle); void scmi_notification_exit(struct scmi_handle *handle); int scmi_register_protocol_events(const struct scmi_handle *handle, u8 proto_id, const struct scmi_protocol_handle *ph, From 687d67be3d87894ef12e8a164434612e0b53cfae Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 14 Jul 2026 13:56:23 +0100 Subject: [PATCH 10/25] firmware: arm_scmi: Clean up channels on setup failure scmi_channels_setup() can fail after the common BASE channel or earlier protocol channels have already been registered in the TX/RX IDRs. Route this failure through the existing channel cleanup label so the transport channels, transport devices and IDR state created before the failure are released before the probe error path frees the SCMI instance ID. Fixes: 05a2801d8b90 ("firmware: arm_scmi: Use dedicated devices to initialize channels") Reported-by: Sashiko Link: https://patch.msgid.link/20260714-scmi_core_fixes-v6-4-3afe499d46e3@kernel.org Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/driver.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index ec373595f955..d2af47d03b4b 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -3263,7 +3263,7 @@ static int scmi_probe(struct platform_device *pdev) ret = scmi_channels_setup(info); if (ret) { err_str = "failed to setup channels\n"; - goto clear_ida; + goto clear_txrx_setup; } ret = bus_register_notifier(&scmi_bus_type, &info->bus_nb); @@ -3379,7 +3379,6 @@ static int scmi_probe(struct platform_device *pdev) scmi_notification_quiesce(&info->handle); scmi_cleanup_txrx_channels(info); scmi_notification_exit(&info->handle); -clear_ida: ida_free(&scmi_id, info->id); out_err: From d72e7e5f24687c0490aabf317653caffe0447aeb Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 14 Jul 2026 13:56:24 +0100 Subject: [PATCH 11/25] firmware: arm_scmi: Free transport channel on IDR failure If transport channel setup succeeds but the following IDR insertion fails, the error path destroys the transport device and frees the channel info without invoking the transport cleanup callback. Call chan_free() before destroying the device so transport specific resources such as IRQs, mailbox channels and mapped shared memory are released consistently with the normal teardown path. Fixes: 05a2801d8b90 ("firmware: arm_scmi: Use dedicated devices to initialize channels") Reported-by: Sashiko Link: https://patch.msgid.link/20260714-scmi_core_fixes-v6-5-3afe499d46e3@kernel.org Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/driver.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index d2af47d03b4b..6ee2152f6b01 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -2808,6 +2808,7 @@ static int scmi_chan_setup(struct scmi_info *info, struct device_node *of_node, "unable to allocate SCMI idr slot err %d\n", ret); /* Destroy channel and device only if created by this call. */ if (tdev) { + info->desc->ops->chan_free(prot_id, cinfo, idr); of_node_put(of_node); scmi_device_destroy(info->dev, prot_id, name); devm_kfree(info->dev, cinfo); From c38b1e19485aaa820e52cfe162525a8af67563da Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 14 Jul 2026 13:56:25 +0100 Subject: [PATCH 12/25] firmware: arm_scmi: Avoid IDR updates while cleaning channels scmi_cleanup_channels() walks the TX/RX channel IDRs with idr_for_each() to free transport resources and destroy the dedicated transport devices before calling idr_destroy(). The destroy callback removed each entry from the same IDR being walked. That is not needed for this cleanup path, and it is unsafe because idr_for_each() has not advanced its radix-tree iterator while the callback is running. Removing the current entry from the callback can invalidate the iterator state. The callback also cannot be protected by rcu_read_lock(), because scmi_device_destroy() may sleep. Leave IDR teardown to the following idr_destroy() call and keep the callback limited to device destruction. Fixes: 05a2801d8b90 ("firmware: arm_scmi: Use dedicated devices to initialize channels") Reported-by: Sashiko Link: https://patch.msgid.link/20260714-scmi_core_fixes-v6-6-3afe499d46e3@kernel.org Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/driver.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 6ee2152f6b01..d17559c897a9 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -2885,7 +2885,7 @@ static int scmi_channels_setup(struct scmi_info *info) return 0; } -static int scmi_chan_destroy(int id, void *p, void *idr) +static int scmi_chan_destroy(int id, void *p, void *data) { struct scmi_chan_info *cinfo = p; @@ -2898,8 +2898,6 @@ static int scmi_chan_destroy(int id, void *p, void *idr) cinfo->dev = NULL; } - idr_remove(idr, id); - return 0; } From 59407ccb52130f2c81f4b3cbe4f14114afceb54f Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 14 Jul 2026 13:56:26 +0100 Subject: [PATCH 13/25] firmware: arm_scmi: Reject out of range DT protocol IDs SCMI protocol IDs carried in message headers are limited by MSG_PROTOCOL_ID_MASK. The DT parsing paths noticed protocol IDs outside that range, but only logged an error and then kept processing the invalid value. That lets a malformed 32-bit DT reg value reach helpers which take a u8 protocol ID, where it can be truncated and/or treated as a different protocol. For channel setup, two different out-of-range values can also be used as distinct IDR keys while aliasing the generated SCMI protocol identity. Skip DT protocol nodes whose reg value does not fit the SCMI protocol ID field before setting up channels or creating protocol devices. Fixes: 05a2801d8b90 ("firmware: arm_scmi: Use dedicated devices to initialize channels") Reported-by: Sashiko Link: https://patch.msgid.link/20260714-scmi_core_fixes-v6-7-3afe499d46e3@kernel.org Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/driver.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index d17559c897a9..0735c6374269 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -2873,9 +2873,11 @@ static int scmi_channels_setup(struct scmi_info *info) if (of_property_read_u32(child, "reg", &prot_id)) continue; - if (!FIELD_FIT(MSG_PROTOCOL_ID_MASK, prot_id)) + if (!FIELD_FIT(MSG_PROTOCOL_ID_MASK, prot_id)) { dev_err(info->dev, "Out of range protocol %d\n", prot_id); + continue; + } ret = scmi_txrx_setup(info, child, prot_id); if (ret) @@ -3339,8 +3341,10 @@ static int scmi_probe(struct platform_device *pdev) if (of_property_read_u32(child, "reg", &prot_id)) continue; - if (!FIELD_FIT(MSG_PROTOCOL_ID_MASK, prot_id)) + if (!FIELD_FIT(MSG_PROTOCOL_ID_MASK, prot_id)) { dev_err(dev, "Out of range protocol %d\n", prot_id); + continue; + } if (!scmi_is_protocol_implemented(handle, prot_id)) { dev_err(dev, "SCMI protocol %d not implemented\n", From a71a3d4d8a6e9e399fd988c0e6da47a6ee21c99e Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 14 Jul 2026 13:56:27 +0100 Subject: [PATCH 14/25] firmware: arm_scmi: Use channel ID for transport teardown SCMI protocols can share the BASE transport channel when firmware does not describe a dedicated channel for the protocol. In that case multiple IDR entries can point at the same scmi_chan_info, whose owning transport device was created with cinfo->id. scmi_chan_destroy() used the IDR iterator key when destroying the transport device. If an alias entry is visited before the owning channel entry, the lookup can miss the device because the iterator key does not match the protocol ID used when the transport device was created. The code then clears cinfo->dev, so the later owning entry skips teardown and leaks the transport device. Destroy the transport device using cinfo->id, which is the protocol ID that owns the channel and was used when creating the transport device. Fixes: 05a2801d8b90 ("firmware: arm_scmi: Use dedicated devices to initialize channels") Reported-by: Sashiko Link: https://patch.msgid.link/20260714-scmi_core_fixes-v6-8-3afe499d46e3@kernel.org Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/driver.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 0735c6374269..f607557c04ad 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -2896,7 +2896,7 @@ static int scmi_chan_destroy(int id, void *p, void *data) struct scmi_device *sdev = to_scmi_dev(cinfo->dev); of_node_put(cinfo->dev->of_node); - scmi_device_destroy(info->dev, id, sdev->name); + scmi_device_destroy(info->dev, cinfo->id, sdev->name); cinfo->dev = NULL; } From e6a0e7a49d83e4fa4e1db68d74f99282eb97aa49 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 14 Jul 2026 13:56:28 +0100 Subject: [PATCH 15/25] firmware: arm_scmi: Protect device request lookup with RCU The SCMI device request notifier looks up protocol OF nodes from the active_protocols IDR. The IDR lookup can run concurrently with protocol activation while probe is still registering protocols and creating their SCMI devices. Wrap the lookup in an RCU read-side critical section as required by the IDR API for lockless readers. Fixes: 53b8c25df708 ("firmware: arm_scmi: Add common notifier helpers") Reported-by: Sashiko Link: https://patch.msgid.link/20260714-scmi_core_fixes-v6-9-3afe499d46e3@kernel.org Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/driver.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index f607557c04ad..a2871dca24dc 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include @@ -2958,7 +2959,9 @@ static int scmi_device_request_notifier(struct notifier_block *nb, struct scmi_device_id *id_table = data; struct scmi_info *info = req_nb_to_scmi_info(nb); + rcu_read_lock(); np = idr_find(&info->active_protocols, id_table->protocol_id); + rcu_read_unlock(); if (!np) return NOTIFY_DONE; From e3a5c30d233ca5d3e799a80da806554c703bda13 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 14 Jul 2026 13:56:29 +0100 Subject: [PATCH 16/25] firmware: arm_scmi: Drop handle on protocol bind failures The SCMI bus notifier acquires an SCMI handle when the driver core emits BUS_NOTIFY_BIND_DRIVER, before invoking the protocol driver probe callback. The protocol probe path only checks whether sdev->handle is set. If device_link_add() fails after the handle has been acquired, the protocol device can still bind with a valid handle but without the dependency link to the SCMI parent. A concurrent parent unbind can then miss the child and tear down the SCMI instance while the child still holds a handle into it. If the protocol driver probe later fails, for example with -EPROBE_DEFER, the driver core emits BUS_NOTIFY_DRIVER_NOT_BOUND rather than BUS_NOTIFY_UNBOUND_DRIVER. The SCMI notifier only released the handle on BUS_NOTIFY_UNBOUND_DRIVER, so each failed protocol-device bind leaked the SCMI instance users refcount and left sdev->handle set after the failed probe. Make the link helper report failure and drop the acquired handle if the link cannot be created. Also handle BUS_NOTIFY_DRIVER_NOT_BOUND in the same cleanup path used for unbind so failed probes balance the earlier BUS_NOTIFY_BIND_DRIVER acquisition. Fixes: 971fc0665f13 ("firmware: arm_scmi: Move handle get/set helpers") Reported-by: Sashiko Link: https://patch.msgid.link/20260714-scmi_core_fixes-v6-10-3afe499d46e3@kernel.org Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/driver.c | 31 ++++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 8 deletions(-) diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index a2871dca24dc..84d1294f269c 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -2629,21 +2629,31 @@ static int scmi_handle_put(const struct scmi_handle *handle) return 0; } -static void scmi_device_link_add(struct device *consumer, +static bool scmi_device_link_add(struct device *consumer, struct device *supplier) { struct device_link *link; link = device_link_add(consumer, supplier, DL_FLAG_AUTOREMOVE_CONSUMER); - WARN_ON(!link); + return !WARN_ON(!link); +} + +static void scmi_clear_handle(struct scmi_device *scmi_dev) +{ + if (!scmi_dev->handle) + return; + + scmi_handle_put(scmi_dev->handle); + scmi_dev->handle = NULL; } static void scmi_set_handle(struct scmi_device *scmi_dev) { scmi_dev->handle = scmi_handle_get(&scmi_dev->dev); - if (scmi_dev->handle) - scmi_device_link_add(&scmi_dev->dev, scmi_dev->handle->dev); + if (scmi_dev->handle && + !scmi_device_link_add(&scmi_dev->dev, scmi_dev->handle->dev)) + scmi_clear_handle(scmi_dev); } static int __scmi_xfer_info_init(struct scmi_info *sinfo, @@ -2927,6 +2937,7 @@ static int scmi_bus_notifier(struct notifier_block *nb, { struct scmi_info *info = bus_nb_to_scmi_info(nb); struct scmi_device *sdev = to_scmi_dev(data); + const char *status; /* Skip devices of different SCMI instances */ if (sdev->dev.parent != info->dev) @@ -2936,18 +2947,22 @@ static int scmi_bus_notifier(struct notifier_block *nb, case BUS_NOTIFY_BIND_DRIVER: /* setup handle now as the transport is ready */ scmi_set_handle(sdev); + status = "about to be BOUND."; + break; + case BUS_NOTIFY_DRIVER_NOT_BOUND: + scmi_clear_handle(sdev); + status = "NOT BOUND."; break; case BUS_NOTIFY_UNBOUND_DRIVER: - scmi_handle_put(sdev->handle); - sdev->handle = NULL; + scmi_clear_handle(sdev); + status = "UNBOUND."; break; default: return NOTIFY_DONE; } dev_dbg(info->dev, "Device %s (%s) is now %s\n", dev_name(&sdev->dev), - sdev->name, action == BUS_NOTIFY_BIND_DRIVER ? - "about to be BOUND." : "UNBOUND."); + sdev->name, status); return NOTIFY_OK; } From e4c16ae24ca027d7a72d645b42f976bb3e99b4b0 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 14 Jul 2026 13:56:30 +0100 Subject: [PATCH 17/25] firmware: arm_scmi: Clear SystemPower flag on create failure __scmi_device_create() reserves the singleton SystemPower protocol device before registering the SCMI device. If any later step fails, a stale reservation can make a later retry reject SystemPower device creation permanently, for example after probe deferral. A plain global boolean is not enough to track the reservation. A delayed final release of an older SystemPower device could clear the boolean after a newer device has already claimed it, breaking the singleton guarantee for the active device. Track the reservation with the scmi_device pointer itself. Claim it with cmpxchg(NULL, scmi_dev) after allocating the device object, and release it with cmpxchg(scmi_dev, NULL) from the common cleanup helper. This lets the create-failure, explicit destroy and final release paths clear only the reservation owned by the device being cleaned up. Fixes: 2c3e674465e7 ("firmware: arm_scmi: Refactor device create/destroy helpers") Reported-by: Sashiko Link: https://patch.msgid.link/20260714-scmi_core_fixes-v6-11-3afe499d46e3@kernel.org Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/bus.c | 61 ++++++++++++++++++--------------- 1 file changed, 33 insertions(+), 28 deletions(-) diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index 793be9eabaed..dcaefc1aa892 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -7,7 +7,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include #include #include #include @@ -33,8 +32,8 @@ struct scmi_requested_dev { struct list_head node; }; -/* Track globally the creation of SCMI SystemPower related devices */ -static atomic_t scmi_syspower_registered = ATOMIC_INIT(0); +/* Track globally the SCMI SystemPower protocol device. */ +static struct scmi_device *scmi_syspower_registered; /** * scmi_protocol_device_request - Helper to request a device @@ -391,10 +390,17 @@ void scmi_driver_unregister(struct scmi_driver *driver) } EXPORT_SYMBOL_GPL(scmi_driver_unregister); +static void scmi_device_release_syspower(struct scmi_device *scmi_dev) +{ + if (scmi_dev->protocol_id == SCMI_PROTOCOL_SYSTEM) + cmpxchg(&scmi_syspower_registered, scmi_dev, NULL); +} + static void scmi_device_release(struct device *dev) { struct scmi_device *scmi_dev = to_scmi_dev(dev); + scmi_device_release_syspower(scmi_dev); kfree_const(scmi_dev->name); kfree(scmi_dev); } @@ -406,9 +412,7 @@ static void __scmi_device_destroy(struct scmi_device *scmi_dev) dev_name(&scmi_dev->dev), scmi_dev->protocol_id, scmi_dev->name); - if (scmi_dev->protocol_id == SCMI_PROTOCOL_SYSTEM) - atomic_set(&scmi_syspower_registered, 0); - + scmi_device_release_syspower(scmi_dev); ida_free(&scmi_bus_id, scmi_dev->id); device_unregister(&scmi_dev->dev); } @@ -419,6 +423,7 @@ __scmi_device_create(struct device_node *np, struct device *parent, { int id, retval; struct scmi_device *scmi_dev; + bool syspower = (protocol == SCMI_PROTOCOL_SYSTEM); /* * If the same protocol/name device already exist under the same parent @@ -431,39 +436,33 @@ __scmi_device_create(struct device_node *np, struct device *parent, if (scmi_dev) return scmi_dev; - /* - * Ignore any possible subsequent failures while creating the device - * since we are doomed anyway at that point; not using a mutex which - * spans across this whole function to keep things simple and to avoid - * to serialize all the __scmi_device_create calls across possibly - * different SCMI server instances (parent) - */ - if (protocol == SCMI_PROTOCOL_SYSTEM && - atomic_cmpxchg(&scmi_syspower_registered, 0, 1)) { - dev_warn(parent, - "SCMI SystemPower protocol device must be unique !\n"); - return NULL; - } - scmi_dev = kzalloc_obj(*scmi_dev); if (!scmi_dev) return NULL; - scmi_dev->name = kstrdup_const(name ?: "unknown", GFP_KERNEL); - if (!scmi_dev->name) { + scmi_dev->protocol_id = protocol; + + /* + * Reserve the singleton SystemPower protocol device using the device + * pointer itself, so delayed release of an older device cannot clear + * a reservation owned by a newer device. + */ + if (syspower && cmpxchg(&scmi_syspower_registered, NULL, scmi_dev)) { + dev_warn(parent, + "SCMI SystemPower protocol device must be unique !\n"); kfree(scmi_dev); return NULL; } + scmi_dev->name = kstrdup_const(name ?: "unknown", GFP_KERNEL); + if (!scmi_dev->name) + goto free_dev; + id = ida_alloc_min(&scmi_bus_id, 1, GFP_KERNEL); - if (id < 0) { - kfree_const(scmi_dev->name); - kfree(scmi_dev); - return NULL; - } + if (id < 0) + goto free_name; scmi_dev->id = id; - scmi_dev->protocol_id = protocol; scmi_dev->dev.parent = parent; device_set_node(&scmi_dev->dev, of_fwnode_handle(np)); scmi_dev->dev.bus = &scmi_bus_type; @@ -482,6 +481,12 @@ __scmi_device_create(struct device_node *np, struct device *parent, put_device(&scmi_dev->dev); ida_free(&scmi_bus_id, id); return NULL; +free_name: + kfree_const(scmi_dev->name); +free_dev: + scmi_device_release_syspower(scmi_dev); + kfree(scmi_dev); + return NULL; } static struct scmi_device * From 659705f5eb378cea462214b74bdc6240cdab53fc Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 14 Jul 2026 13:56:31 +0100 Subject: [PATCH 18/25] firmware: arm_scmi: Fix OF node reference handling SCMI devices store the DT node in dev.of_node through device_set_node(), but that helper only assigns the fwnode and of_node pointers without taking an OF node reference. Take a reference when assigning the node and release it from the SCMI device release path. With the device owning that reference, remove the separate channel-side get/put pair from the core driver. Fixes: 96da4a99ce50 ("firmware: arm_scmi: Set fwnode for the scmi_device") Link: https://patch.msgid.link/20260714-scmi_core_fixes-v6-12-3afe499d46e3@kernel.org Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/bus.c | 3 ++- drivers/firmware/arm_scmi/driver.c | 4 ---- 2 files changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index dcaefc1aa892..a14df82a9310 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -401,6 +401,7 @@ static void scmi_device_release(struct device *dev) struct scmi_device *scmi_dev = to_scmi_dev(dev); scmi_device_release_syspower(scmi_dev); + of_node_put(dev->of_node); kfree_const(scmi_dev->name); kfree(scmi_dev); } @@ -464,7 +465,7 @@ __scmi_device_create(struct device_node *np, struct device *parent, scmi_dev->id = id; scmi_dev->dev.parent = parent; - device_set_node(&scmi_dev->dev, of_fwnode_handle(np)); + device_set_node(&scmi_dev->dev, of_fwnode_handle(of_node_get(np))); scmi_dev->dev.bus = &scmi_bus_type; scmi_dev->dev.release = scmi_device_release; dev_set_name(&scmi_dev->dev, "scmi_dev.%d", id); diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 84d1294f269c..532f1f65b2ab 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -2789,14 +2789,12 @@ static int scmi_chan_setup(struct scmi_info *info, struct device_node *of_node, devm_kfree(info->dev, cinfo); return -EINVAL; } - of_node_get(of_node); cinfo->id = prot_id; cinfo->dev = &tdev->dev; cinfo->handle = &info->handle; ret = info->desc->ops->chan_setup(cinfo, info->dev, tx); if (ret) { - of_node_put(of_node); scmi_device_destroy(info->dev, prot_id, name); devm_kfree(info->dev, cinfo); return ret; @@ -2820,7 +2818,6 @@ static int scmi_chan_setup(struct scmi_info *info, struct device_node *of_node, /* Destroy channel and device only if created by this call. */ if (tdev) { info->desc->ops->chan_free(prot_id, cinfo, idr); - of_node_put(of_node); scmi_device_destroy(info->dev, prot_id, name); devm_kfree(info->dev, cinfo); } @@ -2906,7 +2903,6 @@ static int scmi_chan_destroy(int id, void *p, void *data) struct scmi_info *info = handle_to_scmi_info(cinfo->handle); struct scmi_device *sdev = to_scmi_dev(cinfo->dev); - of_node_put(cinfo->dev->of_node); scmi_device_destroy(info->dev, cinfo->id, sdev->name); cinfo->dev = NULL; } From 6f7c06744d53dc8e047725d411d7f915d9ec35ae Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 14 Jul 2026 13:56:32 +0100 Subject: [PATCH 19/25] firmware: arm_scmi: Unwind TX receiver mailbox setup failure mailbox_chan_setup() can request an additional unidirectional TX receiver channel after successfully acquiring the primary channel. If that second request fails, the function returns immediately and leaves the primary channel allocated. Unwind the primary mailbox channel before returning the error so probe deferral or other setup failures do not leave the channel busy for later probe attempts. Fixes: 9f68ff79ec2c ("firmware: arm_scmi: Add support for unidirectional mailbox channels") Reported-by: Sashiko Link: https://patch.msgid.link/20260714-scmi_core_fixes-v6-13-3afe499d46e3@kernel.org Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/transports/mailbox.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/firmware/arm_scmi/transports/mailbox.c b/drivers/firmware/arm_scmi/transports/mailbox.c index b6459fbb8151..37e3eab529ea 100644 --- a/drivers/firmware/arm_scmi/transports/mailbox.c +++ b/drivers/firmware/arm_scmi/transports/mailbox.c @@ -230,9 +230,10 @@ static int mailbox_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, smbox->chan_receiver = mbox_request_channel(cl, a2p_rx_chan); if (IS_ERR(smbox->chan_receiver)) { ret = PTR_ERR(smbox->chan_receiver); + smbox->chan_receiver = NULL; if (ret != -EPROBE_DEFER) dev_err(cdev, "failed to request SCMI Tx Receiver mailbox\n"); - return ret; + goto err_free_chan; } } @@ -248,6 +249,8 @@ static int mailbox_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, return 0; +err_free_chan: + mbox_free_channel(smbox->chan); err_clear_cinfo: cinfo->transport_info = NULL; smbox->cinfo = NULL; From f3e3773c4e5e96549d7540d8ddeb4fcd534f6f1d Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 14 Jul 2026 13:56:33 +0100 Subject: [PATCH 20/25] firmware: arm_scmi: Unwind P2A receiver mailbox setup failure mailbox_chan_setup() can request an additional P2A receiver channel after successfully acquiring the primary P2A channel. If that later request fails, the function returns immediately and leaves the primary channel allocated. Unwind the primary mailbox channel before returning the error so probe deferral or other setup failures do not leave the channel busy for later probe attempts. Fixes: fa8b28ba22d9 ("firmware: arm_scmi: Add support for platform to agent channel completion") Reported-by: Sashiko Link: https://patch.msgid.link/20260714-scmi_core_fixes-v6-14-3afe499d46e3@kernel.org Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/transports/mailbox.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/firmware/arm_scmi/transports/mailbox.c b/drivers/firmware/arm_scmi/transports/mailbox.c index 37e3eab529ea..308736c3ead9 100644 --- a/drivers/firmware/arm_scmi/transports/mailbox.c +++ b/drivers/firmware/arm_scmi/transports/mailbox.c @@ -241,9 +241,10 @@ static int mailbox_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, smbox->chan_platform_receiver = mbox_request_channel(cl, p2a_rx_chan); if (IS_ERR(smbox->chan_platform_receiver)) { ret = PTR_ERR(smbox->chan_platform_receiver); + smbox->chan_platform_receiver = NULL; if (ret != -EPROBE_DEFER) dev_err(cdev, "failed to request SCMI P2A Receiver mailbox\n"); - return ret; + goto err_free_chan; } } From 6abe8fe36b29ff51d1a42c2f338972883f4751a5 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 14 Jul 2026 13:56:34 +0100 Subject: [PATCH 21/25] firmware: arm_scmi: Fix SCMI device destroy lifetimes scmi_child_dev_find() drops the reference returned by device_find_child() before returning the scmi_device pointer. A concurrent unregister can then release the device while the destroy path is still using the returned pointer. Make the lookup helper return the device_find_child() reference and keep it until scmi_device_destroy() has finished unregistering the child. Also split device_unregister() in __scmi_device_destroy() so the SCMI bus ID is not made reusable until after device_del() has removed the old scmi_dev.N name from sysfs. This avoids a new SCMI device reusing the same ID while the old device is still registered. The final device release callback is also a possible cleanup path when SCMI children are deleted by driver core recursion rather than __scmi_device_destroy(). Release the SCMI bus ID from a common helper used by destroy, register-failure and final-release paths, and clear scmi_dev->id after freeing it so the final release cannot free the same ID again. Fixes: 9ca67840c0dd ("firmware: arm_scmi: Balance device refcount when destroying devices") Reported-by: Sashiko Link: https://patch.msgid.link/20260714-scmi_core_fixes-v6-15-3afe499d46e3@kernel.org Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/bus.c | 39 +++++++++++++++++++-------------- 1 file changed, 23 insertions(+), 16 deletions(-) diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index a14df82a9310..e1f66c08c81d 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -237,8 +237,9 @@ static int scmi_match_by_id_table(struct device *dev, const void *data) return scmi_dev_match_by_id_table(scmi_dev, id_table); } -static struct scmi_device *scmi_child_dev_find(struct device *parent, - int prot_id, const char *name) +/* Returns a device_find_child() reference which must be dropped by caller. */ +static struct scmi_device * +scmi_child_dev_find_get(struct device *parent, int prot_id, const char *name) { struct scmi_device_id id_table[2] = { 0 }; struct device *dev; @@ -250,9 +251,6 @@ static struct scmi_device *scmi_child_dev_find(struct device *parent, if (!dev) return NULL; - /* Drop the refcnt bumped implicitly by device_find_child */ - put_device(dev); - return to_scmi_dev(dev); } @@ -390,17 +388,22 @@ void scmi_driver_unregister(struct scmi_driver *driver) } EXPORT_SYMBOL_GPL(scmi_driver_unregister); -static void scmi_device_release_syspower(struct scmi_device *scmi_dev) +static void scmi_device_release_resources(struct scmi_device *scmi_dev) { if (scmi_dev->protocol_id == SCMI_PROTOCOL_SYSTEM) cmpxchg(&scmi_syspower_registered, scmi_dev, NULL); + + if (scmi_dev->id) { + ida_free(&scmi_bus_id, scmi_dev->id); + scmi_dev->id = 0; + } } static void scmi_device_release(struct device *dev) { struct scmi_device *scmi_dev = to_scmi_dev(dev); - scmi_device_release_syspower(scmi_dev); + scmi_device_release_resources(scmi_dev); of_node_put(dev->of_node); kfree_const(scmi_dev->name); kfree(scmi_dev); @@ -413,9 +416,9 @@ static void __scmi_device_destroy(struct scmi_device *scmi_dev) dev_name(&scmi_dev->dev), scmi_dev->protocol_id, scmi_dev->name); - scmi_device_release_syspower(scmi_dev); - ida_free(&scmi_bus_id, scmi_dev->id); - device_unregister(&scmi_dev->dev); + device_del(&scmi_dev->dev); + scmi_device_release_resources(scmi_dev); + put_device(&scmi_dev->dev); } static struct scmi_device * @@ -433,9 +436,11 @@ __scmi_device_create(struct device_node *np, struct device *parent, * each DT defined protocol at probe time, and the concurrent * registration of SCMI drivers. */ - scmi_dev = scmi_child_dev_find(parent, protocol, name); - if (scmi_dev) + scmi_dev = scmi_child_dev_find_get(parent, protocol, name); + if (scmi_dev) { + put_device(&scmi_dev->dev); return scmi_dev; + } scmi_dev = kzalloc_obj(*scmi_dev); if (!scmi_dev) @@ -479,13 +484,13 @@ __scmi_device_create(struct device_node *np, struct device *parent, return scmi_dev; put_dev: + scmi_device_release_resources(scmi_dev); put_device(&scmi_dev->dev); - ida_free(&scmi_bus_id, id); return NULL; free_name: kfree_const(scmi_dev->name); free_dev: - scmi_device_release_syspower(scmi_dev); + scmi_device_release_resources(scmi_dev); kfree(scmi_dev); return NULL; } @@ -567,9 +572,11 @@ void scmi_device_destroy(struct device *parent, int protocol, const char *name) { struct scmi_device *scmi_dev; - scmi_dev = scmi_child_dev_find(parent, protocol, name); - if (scmi_dev) + scmi_dev = scmi_child_dev_find_get(parent, protocol, name); + if (scmi_dev) { __scmi_device_destroy(scmi_dev); + put_device(&scmi_dev->dev); + } } EXPORT_SYMBOL_GPL(scmi_device_destroy); From a14dd8fe0a95db638c550ed984cfe2a7428c783d Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 14 Jul 2026 13:56:35 +0100 Subject: [PATCH 22/25] firmware: arm_scmi: Fix transport device teardown lookup SCMI transport devices are deliberately excluded from normal SCMI bus matching so protocol drivers cannot bind to the internal transport children. However, scmi_device_destroy() uses the same protocol/name lookup to find devices that must be unregistered during channel teardown. Split the match helper so driver matching still skips transport devices, while explicit child lookup can find them for teardown. Use a shared transport-device name prefix macro for both matching and name generation. Since transport-device names are derived from direction and protocol ID, reject duplicate protocol channel setup before creating or finding a transport device. This prevents malformed firmware with duplicate protocol child nodes from reusing an existing transport device and then destroying it when the duplicate IDR insertion fails. Fixes: 9593804c44c2 ("firmware: arm_scmi: Exclude transport devices from bus matching") Reported-by: Sashiko Link: https://patch.msgid.link/20260714-scmi_core_fixes-v6-16-3afe499d46e3@kernel.org Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/bus.c | 22 +++++++++++++++++----- drivers/firmware/arm_scmi/common.h | 2 ++ drivers/firmware/arm_scmi/driver.c | 5 ++++- 3 files changed, 23 insertions(+), 6 deletions(-) diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index e1f66c08c81d..7f06d56e4905 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -200,21 +200,33 @@ scmi_protocol_table_unregister(const struct scmi_device_id *id_table) scmi_protocol_device_unrequest(entry); } -static int scmi_dev_match_by_id_table(struct scmi_device *scmi_dev, - const struct scmi_device_id *id_table) +static bool scmi_device_is_transport(const struct scmi_device *scmi_dev) +{ + return !strncmp(scmi_dev->name, SCMI_TRANSPORT_DEVNAME_PREFIX, + strlen(SCMI_TRANSPORT_DEVNAME_PREFIX)); +} + +static int __scmi_dev_match_by_id_table(struct scmi_device *scmi_dev, + const struct scmi_device_id *id_table, + bool skip_transport) { if (!id_table || !id_table->name) return 0; - /* Always skip transport devices from matching */ for (; id_table->protocol_id && id_table->name; id_table++) if (id_table->protocol_id == scmi_dev->protocol_id && - strncmp(scmi_dev->name, "__scmi_transport_device", 23) && + !(skip_transport && scmi_device_is_transport(scmi_dev)) && !strcmp(id_table->name, scmi_dev->name)) return 1; return 0; } +static int scmi_dev_match_by_id_table(struct scmi_device *scmi_dev, + const struct scmi_device_id *id_table) +{ + return __scmi_dev_match_by_id_table(scmi_dev, id_table, true); +} + static int scmi_dev_match_id(struct scmi_device *scmi_dev, const struct scmi_driver *scmi_drv) { @@ -234,7 +246,7 @@ static int scmi_match_by_id_table(struct device *dev, const void *data) struct scmi_device *scmi_dev = to_scmi_dev(dev); const struct scmi_device_id *id_table = data; - return scmi_dev_match_by_id_table(scmi_dev, id_table); + return __scmi_dev_match_by_id_table(scmi_dev, id_table, false); } /* Returns a device_find_child() reference which must be dropped by caller. */ diff --git a/drivers/firmware/arm_scmi/common.h b/drivers/firmware/arm_scmi/common.h index b9723c105fc1..fe8c22cfb9f7 100644 --- a/drivers/firmware/arm_scmi/common.h +++ b/drivers/firmware/arm_scmi/common.h @@ -34,6 +34,8 @@ #define SCMI_SHMEM_MAX_PAYLOAD_SIZE 104 +#define SCMI_TRANSPORT_DEVNAME_PREFIX "__scmi_transport_device" + enum scmi_error_codes { SCMI_SUCCESS = 0, /* Success */ SCMI_ERR_SUPPORT = -1, /* Not supported */ diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 532f1f65b2ab..ef29fd223287 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -2762,6 +2762,9 @@ static int scmi_chan_setup(struct scmi_info *info, struct device_node *of_node, idx = tx ? 0 : 1; idr = tx ? &info->tx_idr : &info->rx_idr; + if (idr_find(idr, prot_id)) + return -EEXIST; + if (!info->desc->ops->chan_available(of_node, idx)) { cinfo = idr_find(idr, SCMI_PROTOCOL_BASE); if (unlikely(!cinfo)) /* Possible only if platform has no Rx */ @@ -2779,7 +2782,7 @@ static int scmi_chan_setup(struct scmi_info *info, struct device_node *of_node, cinfo->no_completion_irq = info->desc->no_completion_irq; /* Create a unique name for this transport device */ - snprintf(name, 32, "__scmi_transport_device_%s_%02X", + snprintf(name, sizeof(name), SCMI_TRANSPORT_DEVNAME_PREFIX "_%s_%02X", idx ? "rx" : "tx", prot_id); /* Create a uniquely named, dedicated transport device for this chan */ tdev = scmi_device_create(of_node, info->dev, prot_id, name); From 2c4097e6c4aed276c5e9ec2ab331ab397ea780bf Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Wed, 22 Jul 2026 10:52:50 +0100 Subject: [PATCH 23/25] firmware: arm_scmi: Fix requested device removal race scmi_protocol_device_unrequest() drops scmi_requested_devices_mtx while notifying listeners but continues to retain the per-protocol list head. When two SCMI drivers for the same protocol unregister concurrently, one thread can remove the final request and free the list head while the other is running its notifier. The latter then dereferences the freed list head after reacquiring the mutex and can free it a second time. Complete the list and IDR updates, including freeing an empty list head, before dropping the mutex. Keep the blocking notifier outside the critical section and retain only the detached request across the callback. Fixes: d3cd7c525fd2 ("firmware: arm_scmi: Refactor protocol device creation") Reported-by: Sashiko Link: https://patch.msgid.link/20260722095250.2011630-1-sudeep.holla@kernel.org Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/bus.c | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index 7f06d56e4905..cdaea09d9611 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -158,6 +158,7 @@ static int scmi_protocol_table_register(const struct scmi_device_id *id_table) */ static void scmi_protocol_device_unrequest(const struct scmi_device_id *id_table) { + struct scmi_requested_dev *rdev, *victim = NULL; struct list_head *phead; pr_debug("Unrequesting SCMI device (%s) for protocol %x\n", @@ -166,29 +167,28 @@ static void scmi_protocol_device_unrequest(const struct scmi_device_id *id_table mutex_lock(&scmi_requested_devices_mtx); phead = idr_find(&scmi_requested_devices, id_table->protocol_id); if (phead) { - struct scmi_requested_dev *victim, *tmp; - - list_for_each_entry_safe(victim, tmp, phead, node) { - if (!strcmp(victim->id_table->name, id_table->name)) { - list_del(&victim->node); - - mutex_unlock(&scmi_requested_devices_mtx); - blocking_notifier_call_chain(&scmi_requested_devices_nh, - SCMI_BUS_NOTIFY_DEVICE_UNREQUEST, - (void *)victim->id_table); - kfree(victim); - mutex_lock(&scmi_requested_devices_mtx); + list_for_each_entry(rdev, phead, node) { + if (!strcmp(rdev->id_table->name, id_table->name)) { + victim = rdev; + list_del(&rdev->node); break; } } - if (list_empty(phead)) { + if (victim && list_empty(phead)) { idr_remove(&scmi_requested_devices, id_table->protocol_id); kfree(phead); } } mutex_unlock(&scmi_requested_devices_mtx); + + if (victim) { + blocking_notifier_call_chain(&scmi_requested_devices_nh, + SCMI_BUS_NOTIFY_DEVICE_UNREQUEST, + (void *)victim->id_table); + kfree(victim); + } } static void From 2224b622260ba590ab56ea1585d6bf7610be25b2 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Wed, 22 Jul 2026 18:35:20 +0100 Subject: [PATCH 24/25] firmware: arm_scmi: Roll back partial protocol table registration scmi_protocol_table_register() can leave earlier requests registered when a later entry in the same ID table fails. Each request retains a pointer to the driver's ID table, so a failed module load can leave a dangling pointer after the module storage is released. Unrequest only the successfully registered prefix, in reverse order, before returning the failure. Leave the failed entry and the remaining entries untouched because matching requests can be owned by another driver. Fixes: 2858f6e5f064 ("firmware: arm_scmi: Add multiple protocols registration support") Reported-by: Sashiko Link: https://patch.msgid.link/20260722173521.2184378-1-sudeep.holla@kernel.org Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/bus.c | 31 ++++++++++++++++++++----------- 1 file changed, 20 insertions(+), 11 deletions(-) diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index cdaea09d9611..d520910eb251 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -135,17 +135,6 @@ static int scmi_protocol_device_request(const struct scmi_device_id *id_table) return ret; } -static int scmi_protocol_table_register(const struct scmi_device_id *id_table) -{ - int ret = 0; - const struct scmi_device_id *entry; - - for (entry = id_table; entry->name && ret == 0; entry++) - ret = scmi_protocol_device_request(entry); - - return ret; -} - /** * scmi_protocol_device_unrequest - Helper to unrequest a device * @@ -191,6 +180,26 @@ static void scmi_protocol_device_unrequest(const struct scmi_device_id *id_table } } +static int scmi_protocol_table_register(const struct scmi_device_id *id_table) +{ + const struct scmi_device_id *entry; + int ret; + + for (entry = id_table; entry->name; entry++) { + ret = scmi_protocol_device_request(entry); + if (ret) + goto err_unrequest; + } + + return 0; + +err_unrequest: + while (entry != id_table) + scmi_protocol_device_unrequest(--entry); + + return ret; +} + static void scmi_protocol_table_unregister(const struct scmi_device_id *id_table) { From 9f7cd6a62aa754ed6b48cbd5d50de40add1bcc86 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Wed, 22 Jul 2026 18:35:21 +0100 Subject: [PATCH 25/25] firmware: arm_scmi: Unrequest devices if driver registration fails scmi_driver_register() requests protocol devices before registering the driver. If driver_register() fails, those requests remain in the global IDR and retain pointers to the module's ID table. Once the failed module load releases that storage, later request matching or SCMI device creation can dereference the stale pointers. Unrequest the complete protocol table before returning the registration failure. At this point table registration succeeded, so every entry is owned by the current registration attempt. Fixes: d3cd7c525fd2 ("firmware: arm_scmi: Refactor protocol device creation") Reported-by: Sashiko Link: https://patch.msgid.link/20260722173521.2184378-2-sudeep.holla@kernel.org Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/bus.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index d520910eb251..e060edbe7e83 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -395,10 +395,14 @@ int scmi_driver_register(struct scmi_driver *driver, struct module *owner, driver->driver.mod_name = mod_name; retval = driver_register(&driver->driver); - if (!retval) - pr_debug("Registered new scmi driver %s\n", driver->name); + if (retval) { + scmi_protocol_table_unregister(driver->id_table); + return retval; + } - return retval; + pr_debug("Registered new scmi driver %s\n", driver->name); + + return 0; } EXPORT_SYMBOL_GPL(scmi_driver_register);