From 924fc22c282edbf93869b150d9e1b47e0b10485e Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 31 Jul 2024 09:44:57 +0200 Subject: firmware: qcom: qseecom: remove unused functions qseecom_scm_dev(), qseecom_dma_alloc() and qseecom_dma_free() are no longer used following the conversion to using tzmem. Remove them. Fixes: 6612103ec35a ("firmware: qcom: qseecom: convert to using the TZ allocator") Reviewed-by: Andrew Halaney Signed-off-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20240731-tzmem-efivars-fix-v2-2-f0e84071ec07@linaro.org Signed-off-by: Bjorn Andersson --- include/linux/firmware/qcom/qcom_qseecom.h | 45 ------------------------------ 1 file changed, 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/qcom/qcom_qseecom.h b/include/linux/firmware/qcom/qcom_qseecom.h index 1dc5b3b50aa9..3387897bf368 100644 --- a/include/linux/firmware/qcom/qcom_qseecom.h +++ b/include/linux/firmware/qcom/qcom_qseecom.h @@ -25,51 +25,6 @@ struct qseecom_client { u32 app_id; }; -/** - * qseecom_scm_dev() - Get the SCM device associated with the QSEECOM client. - * @client: The QSEECOM client device. - * - * Returns the SCM device under which the provided QSEECOM client device - * operates. This function is intended to be used for DMA allocations. - */ -static inline struct device *qseecom_scm_dev(struct qseecom_client *client) -{ - return client->aux_dev.dev.parent->parent; -} - -/** - * qseecom_dma_alloc() - Allocate DMA memory for a QSEECOM client. - * @client: The QSEECOM client to allocate the memory for. - * @size: The number of bytes to allocate. - * @dma_handle: Pointer to where the DMA address should be stored. - * @gfp: Allocation flags. - * - * Wrapper function for dma_alloc_coherent(), allocating DMA memory usable for - * TZ/QSEECOM communication. Refer to dma_alloc_coherent() for details. - */ -static inline void *qseecom_dma_alloc(struct qseecom_client *client, size_t size, - dma_addr_t *dma_handle, gfp_t gfp) -{ - return dma_alloc_coherent(qseecom_scm_dev(client), size, dma_handle, gfp); -} - -/** - * dma_free_coherent() - Free QSEECOM DMA memory. - * @client: The QSEECOM client for which the memory has been allocated. - * @size: The number of bytes allocated. - * @cpu_addr: Virtual memory address to free. - * @dma_handle: DMA memory address to free. - * - * Wrapper function for dma_free_coherent(), freeing memory previously - * allocated with qseecom_dma_alloc(). Refer to dma_free_coherent() for - * details. - */ -static inline void qseecom_dma_free(struct qseecom_client *client, size_t size, - void *cpu_addr, dma_addr_t dma_handle) -{ - return dma_free_coherent(qseecom_scm_dev(client), size, cpu_addr, dma_handle); -} - /** * qcom_qseecom_app_send() - Send to and receive data from a given QSEE app. * @client: The QSEECOM client associated with the target app. -- cgit v1.2.3 From ea72ce5da22806d5713f3ffb39a6d5ae73841f93 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Aug 2024 00:29:36 +0200 Subject: x86/kaslr: Expose and use the end of the physical memory address space iounmap() on x86 occasionally fails to unmap because the provided valid ioremap address is not below high_memory. It turned out that this happens due to KASLR. KASLR uses the full address space between PAGE_OFFSET and vaddr_end to randomize the starting points of the direct map, vmalloc and vmemmap regions. It thereby limits the size of the direct map by using the installed memory size plus an extra configurable margin for hot-plug memory. This limitation is done to gain more randomization space because otherwise only the holes between the direct map, vmalloc, vmemmap and vaddr_end would be usable for randomizing. The limited direct map size is not exposed to the rest of the kernel, so the memory hot-plug and resource management related code paths still operate under the assumption that the available address space can be determined with MAX_PHYSMEM_BITS. request_free_mem_region() allocates from (1 << MAX_PHYSMEM_BITS) - 1 downwards. That means the first allocation happens past the end of the direct map and if unlucky this address is in the vmalloc space, which causes high_memory to become greater than VMALLOC_START and consequently causes iounmap() to fail for valid ioremap addresses. MAX_PHYSMEM_BITS cannot be changed for that because the randomization does not align with address bit boundaries and there are other places which actually require to know the maximum number of address bits. All remaining usage sites of MAX_PHYSMEM_BITS have been analyzed and found to be correct. Cure this by exposing the end of the direct map via PHYSMEM_END and use that for the memory hot-plug and resource management related places instead of relying on MAX_PHYSMEM_BITS. In the KASLR case PHYSMEM_END maps to a variable which is initialized by the KASLR initialization and otherwise it is based on MAX_PHYSMEM_BITS as before. To prevent future hickups add a check into add_pages() to catch callers trying to add memory above PHYSMEM_END. Fixes: 0483e1fa6e09 ("x86/mm: Implement ASLR for kernel memory regions") Reported-by: Max Ramanouski Reported-by: Alistair Popple Signed-off-by: Thomas Gleixner Tested-By: Max Ramanouski Tested-by: Alistair Popple Reviewed-by: Dan Williams Reviewed-by: Alistair Popple Reviewed-by: Kees Cook Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/87ed6soy3z.ffs@tglx --- arch/x86/include/asm/page_64.h | 1 + arch/x86/include/asm/pgtable_64_types.h | 4 ++++ arch/x86/mm/init_64.c | 4 ++++ arch/x86/mm/kaslr.c | 32 ++++++++++++++++++++++++++------ include/linux/mm.h | 4 ++++ kernel/resource.c | 6 ++---- mm/memory_hotplug.c | 2 +- mm/sparse.c | 2 +- 8 files changed, 43 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index af4302d79b59..f3d257c45225 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -17,6 +17,7 @@ extern unsigned long phys_base; extern unsigned long page_offset_base; extern unsigned long vmalloc_base; extern unsigned long vmemmap_base; +extern unsigned long physmem_end; static __always_inline unsigned long __phys_addr_nodebug(unsigned long x) { diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 9053dfe9fa03..a98e53491a4e 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -140,6 +140,10 @@ extern unsigned int ptrs_per_p4d; # define VMEMMAP_START __VMEMMAP_BASE_L4 #endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */ +#ifdef CONFIG_RANDOMIZE_MEMORY +# define PHYSMEM_END physmem_end +#endif + /* * End of the region for which vmalloc page tables are pre-allocated. * For non-KMSAN builds, this is the same as VMALLOC_END. diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index d8dbeac8b206..ff253648706f 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -958,8 +958,12 @@ static void update_end_of_memory_vars(u64 start, u64 size) int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, struct mhp_params *params) { + unsigned long end = ((start_pfn + nr_pages) << PAGE_SHIFT) - 1; int ret; + if (WARN_ON_ONCE(end > PHYSMEM_END)) + return -ERANGE; + ret = __add_pages(nid, start_pfn, nr_pages, params); WARN_ON_ONCE(ret); diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 37db264866b6..230f1dee4f09 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -47,13 +47,24 @@ static const unsigned long vaddr_end = CPU_ENTRY_AREA_BASE; */ static __initdata struct kaslr_memory_region { unsigned long *base; + unsigned long *end; unsigned long size_tb; } kaslr_regions[] = { - { &page_offset_base, 0 }, - { &vmalloc_base, 0 }, - { &vmemmap_base, 0 }, + { + .base = &page_offset_base, + .end = &physmem_end, + }, + { + .base = &vmalloc_base, + }, + { + .base = &vmemmap_base, + }, }; +/* The end of the possible address space for physical memory */ +unsigned long physmem_end __ro_after_init; + /* Get size in bytes used by the memory region */ static inline unsigned long get_padding(struct kaslr_memory_region *region) { @@ -82,6 +93,8 @@ void __init kernel_randomize_memory(void) BUILD_BUG_ON(vaddr_end != CPU_ENTRY_AREA_BASE); BUILD_BUG_ON(vaddr_end > __START_KERNEL_map); + /* Preset the end of the possible address space for physical memory */ + physmem_end = ((1ULL << MAX_PHYSMEM_BITS) - 1); if (!kaslr_memory_enabled()) return; @@ -128,11 +141,18 @@ void __init kernel_randomize_memory(void) vaddr += entropy; *kaslr_regions[i].base = vaddr; + /* Calculate the end of the region */ + vaddr += get_padding(&kaslr_regions[i]); /* - * Jump the region and add a minimum padding based on - * randomization alignment. + * KASLR trims the maximum possible size of the + * direct-map. Update the physmem_end boundary. + * No rounding required as the region starts + * PUD aligned and size is in units of TB. */ - vaddr += get_padding(&kaslr_regions[i]); + if (kaslr_regions[i].end) + *kaslr_regions[i].end = __pa_nodebug(vaddr - 1); + + /* Add a minimum padding based on randomization alignment. */ vaddr = round_up(vaddr + 1, PUD_SIZE); remain_entropy -= entropy; } diff --git a/include/linux/mm.h b/include/linux/mm.h index c4b238a20b76..b3864156eaa4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -97,6 +97,10 @@ extern const int mmap_rnd_compat_bits_max; extern int mmap_rnd_compat_bits __read_mostly; #endif +#ifndef PHYSMEM_END +# define PHYSMEM_END ((1ULL << MAX_PHYSMEM_BITS) - 1) +#endif + #include #include diff --git a/kernel/resource.c b/kernel/resource.c index 14777afb0a99..a83040fde236 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1826,8 +1826,7 @@ static resource_size_t gfr_start(struct resource *base, resource_size_t size, if (flags & GFR_DESCENDING) { resource_size_t end; - end = min_t(resource_size_t, base->end, - (1ULL << MAX_PHYSMEM_BITS) - 1); + end = min_t(resource_size_t, base->end, PHYSMEM_END); return end - size + 1; } @@ -1844,8 +1843,7 @@ static bool gfr_continue(struct resource *base, resource_size_t addr, * @size did not wrap 0. */ return addr > addr - size && - addr <= min_t(resource_size_t, base->end, - (1ULL << MAX_PHYSMEM_BITS) - 1); + addr <= min_t(resource_size_t, base->end, PHYSMEM_END); } static resource_size_t gfr_next(resource_size_t addr, resource_size_t size, diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 66267c26ca1b..951878ab627a 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1681,7 +1681,7 @@ struct range __weak arch_get_mappable_range(void) struct range mhp_get_pluggable_range(bool need_mapping) { - const u64 max_phys = (1ULL << MAX_PHYSMEM_BITS) - 1; + const u64 max_phys = PHYSMEM_END; struct range mhp_range; if (need_mapping) { diff --git a/mm/sparse.c b/mm/sparse.c index e4b830091d13..0c3bff882033 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -129,7 +129,7 @@ static inline int sparse_early_nid(struct mem_section *section) static void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn, unsigned long *end_pfn) { - unsigned long max_sparsemem_pfn = 1UL << (MAX_PHYSMEM_BITS-PAGE_SHIFT); + unsigned long max_sparsemem_pfn = (PHYSMEM_END + 1) >> PAGE_SHIFT; /* * Sanity checks - do not allow an architecture to pass -- cgit v1.2.3 From 3568affcddd68743e25aa3ec1647d9b82797757b Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 20 Aug 2024 13:29:30 -0700 Subject: soc: qcom: pmic_glink: Fix race during initialization As pointed out by Stephen Boyd it is possible that during initialization of the pmic_glink child drivers, the protection-domain notifiers fires, and the associated work is scheduled, before the client registration returns and as a result the local "client" pointer has been initialized. The outcome of this is a NULL pointer dereference as the "client" pointer is blindly dereferenced. Timeline provided by Stephen: CPU0 CPU1 ---- ---- ucsi->client = NULL; devm_pmic_glink_register_client() client->pdr_notify(client->priv, pg->client_state) pmic_glink_ucsi_pdr_notify() schedule_work(&ucsi->register_work) pmic_glink_ucsi_register() ucsi_register() pmic_glink_ucsi_read_version() pmic_glink_ucsi_read() pmic_glink_ucsi_read() pmic_glink_send(ucsi->client) ucsi->client = client // Too late! This code is identical across the altmode, battery manager and usci child drivers. Resolve this by splitting the allocation of the "client" object and the registration thereof into two operations. This only happens if the protection domain registry is populated at the time of registration, which by the introduction of commit '1ebcde047c54 ("soc: qcom: add pd-mapper implementation")' became much more likely. Reported-by: Amit Pundir Closes: https://lore.kernel.org/all/CAMi1Hd2_a7TjA7J9ShrAbNOd_CoZ3D87twmO5t+nZxC9sX18tA@mail.gmail.com/ Reported-by: Johan Hovold Closes: https://lore.kernel.org/all/ZqiyLvP0gkBnuekL@hovoldconsulting.com/ Reported-by: Stephen Boyd Closes: https://lore.kernel.org/all/CAE-0n52JgfCBWiFQyQWPji8cq_rCsviBpW-m72YitgNfdaEhQg@mail.gmail.com/ Fixes: 58ef4ece1e41 ("soc: qcom: pmic_glink: Introduce base PMIC GLINK driver") Cc: stable@vger.kernel.org Reviewed-by: Heikki Krogerus Reviewed-by: Neil Armstrong Tested-by: Amit Pundir Reviewed-by: Johan Hovold Acked-by: Sebastian Reichel Tested-by: Johan Hovold Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20240820-pmic-glink-v6-11-races-v3-1-eec53c750a04@quicinc.com Signed-off-by: Bjorn Andersson --- drivers/power/supply/qcom_battmgr.c | 16 ++++++++++------ drivers/soc/qcom/pmic_glink.c | 28 ++++++++++++++++++---------- drivers/soc/qcom/pmic_glink_altmode.c | 17 +++++++++++------ drivers/usb/typec/ucsi/ucsi_glink.c | 16 ++++++++++------ include/linux/soc/qcom/pmic_glink.h | 11 ++++++----- 5 files changed, 55 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/drivers/power/supply/qcom_battmgr.c b/drivers/power/supply/qcom_battmgr.c index 46f36dcb185c..7cf19a39d986 100644 --- a/drivers/power/supply/qcom_battmgr.c +++ b/drivers/power/supply/qcom_battmgr.c @@ -1385,12 +1385,16 @@ static int qcom_battmgr_probe(struct auxiliary_device *adev, "failed to register wireless charing power supply\n"); } - battmgr->client = devm_pmic_glink_register_client(dev, - PMIC_GLINK_OWNER_BATTMGR, - qcom_battmgr_callback, - qcom_battmgr_pdr_notify, - battmgr); - return PTR_ERR_OR_ZERO(battmgr->client); + battmgr->client = devm_pmic_glink_client_alloc(dev, PMIC_GLINK_OWNER_BATTMGR, + qcom_battmgr_callback, + qcom_battmgr_pdr_notify, + battmgr); + if (IS_ERR(battmgr->client)) + return PTR_ERR(battmgr->client); + + pmic_glink_client_register(battmgr->client); + + return 0; } static const struct auxiliary_device_id qcom_battmgr_id_table[] = { diff --git a/drivers/soc/qcom/pmic_glink.c b/drivers/soc/qcom/pmic_glink.c index 9ebc0ba35947..53b176d04fbd 100644 --- a/drivers/soc/qcom/pmic_glink.c +++ b/drivers/soc/qcom/pmic_glink.c @@ -66,15 +66,14 @@ static void _devm_pmic_glink_release_client(struct device *dev, void *res) spin_unlock_irqrestore(&pg->client_lock, flags); } -struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev, - unsigned int id, - void (*cb)(const void *, size_t, void *), - void (*pdr)(void *, int), - void *priv) +struct pmic_glink_client *devm_pmic_glink_client_alloc(struct device *dev, + unsigned int id, + void (*cb)(const void *, size_t, void *), + void (*pdr)(void *, int), + void *priv) { struct pmic_glink_client *client; struct pmic_glink *pg = dev_get_drvdata(dev->parent); - unsigned long flags; client = devres_alloc(_devm_pmic_glink_release_client, sizeof(*client), GFP_KERNEL); if (!client) @@ -85,6 +84,18 @@ struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev, client->cb = cb; client->pdr_notify = pdr; client->priv = priv; + INIT_LIST_HEAD(&client->node); + + devres_add(dev, client); + + return client; +} +EXPORT_SYMBOL_GPL(devm_pmic_glink_client_alloc); + +void pmic_glink_client_register(struct pmic_glink_client *client) +{ + struct pmic_glink *pg = client->pg; + unsigned long flags; mutex_lock(&pg->state_lock); spin_lock_irqsave(&pg->client_lock, flags); @@ -95,11 +106,8 @@ struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev, spin_unlock_irqrestore(&pg->client_lock, flags); mutex_unlock(&pg->state_lock); - devres_add(dev, client); - - return client; } -EXPORT_SYMBOL_GPL(devm_pmic_glink_register_client); +EXPORT_SYMBOL_GPL(pmic_glink_client_register); int pmic_glink_send(struct pmic_glink_client *client, void *data, size_t len) { diff --git a/drivers/soc/qcom/pmic_glink_altmode.c b/drivers/soc/qcom/pmic_glink_altmode.c index 1e0808b3cb93..463b1c528831 100644 --- a/drivers/soc/qcom/pmic_glink_altmode.c +++ b/drivers/soc/qcom/pmic_glink_altmode.c @@ -520,12 +520,17 @@ static int pmic_glink_altmode_probe(struct auxiliary_device *adev, return ret; } - altmode->client = devm_pmic_glink_register_client(dev, - altmode->owner_id, - pmic_glink_altmode_callback, - pmic_glink_altmode_pdr_notify, - altmode); - return PTR_ERR_OR_ZERO(altmode->client); + altmode->client = devm_pmic_glink_client_alloc(dev, + altmode->owner_id, + pmic_glink_altmode_callback, + pmic_glink_altmode_pdr_notify, + altmode); + if (IS_ERR(altmode->client)) + return PTR_ERR(altmode->client); + + pmic_glink_client_register(altmode->client); + + return 0; } static const struct auxiliary_device_id pmic_glink_altmode_id_table[] = { diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c index 16c328497e0b..f6f4fae40399 100644 --- a/drivers/usb/typec/ucsi/ucsi_glink.c +++ b/drivers/usb/typec/ucsi/ucsi_glink.c @@ -367,12 +367,16 @@ static int pmic_glink_ucsi_probe(struct auxiliary_device *adev, ucsi->port_orientation[port] = desc; } - ucsi->client = devm_pmic_glink_register_client(dev, - PMIC_GLINK_OWNER_USBC, - pmic_glink_ucsi_callback, - pmic_glink_ucsi_pdr_notify, - ucsi); - return PTR_ERR_OR_ZERO(ucsi->client); + ucsi->client = devm_pmic_glink_client_alloc(dev, PMIC_GLINK_OWNER_USBC, + pmic_glink_ucsi_callback, + pmic_glink_ucsi_pdr_notify, + ucsi); + if (IS_ERR(ucsi->client)) + return PTR_ERR(ucsi->client); + + pmic_glink_client_register(ucsi->client); + + return 0; } static void pmic_glink_ucsi_remove(struct auxiliary_device *adev) diff --git a/include/linux/soc/qcom/pmic_glink.h b/include/linux/soc/qcom/pmic_glink.h index fd124aa18c81..7cddf1027752 100644 --- a/include/linux/soc/qcom/pmic_glink.h +++ b/include/linux/soc/qcom/pmic_glink.h @@ -23,10 +23,11 @@ struct pmic_glink_hdr { int pmic_glink_send(struct pmic_glink_client *client, void *data, size_t len); -struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev, - unsigned int id, - void (*cb)(const void *, size_t, void *), - void (*pdr)(void *, int), - void *priv); +struct pmic_glink_client *devm_pmic_glink_client_alloc(struct device *dev, + unsigned int id, + void (*cb)(const void *, size_t, void *), + void (*pdr)(void *, int), + void *priv); +void pmic_glink_client_register(struct pmic_glink_client *client); #endif -- cgit v1.2.3 From b58b133e680b20d219940e0fdb6f6132c2b60f38 Mon Sep 17 00:00:00 2001 From: Pranjal Shrivastava Date: Fri, 16 Aug 2024 10:49:06 +0000 Subject: iommu: Handle iommu faults for a bad iopf setup The iommu_report_device_fault function was updated to return void while assuming that drivers only need to call iommu_report_device_fault() for reporting an iopf. This implementation causes following problems: 1. The drivers rely on the core code to call it's page_reponse, however, when a fault is received and no fault capable domain is attached / iopf_param is NULL, the ops->page_response is NOT called causing the device to stall in case the fault type was PAGE_REQ. 2. The arm_smmu_v3 driver relies on the returned value to log errors returning void from iommu_report_device_fault causes these events to be missed while logging. Modify the iommu_report_device_fault function to return -EINVAL for cases where no fault capable domain is attached or iopf_param was NULL and calls back to the driver (ops->page_response) in case the fault type was IOMMU_FAULT_PAGE_REQ. The returned value can be used by the drivers to log the fault/event as needed. Reported-by: Kunkun Jiang Closes: https://lore.kernel.org/all/6147caf0-b9a0-30ca-795e-a1aa502a5c51@huawei.com/ Fixes: 3dfa64aecbaf ("iommu: Make iommu_report_device_fault() return void") Signed-off-by: Jason Gunthorpe Signed-off-by: Pranjal Shrivastava Reviewed-by: Jason Gunthorpe Reviewed-by: Lu Baolu Link: https://lore.kernel.org/r/20240816104906.1010626-1-praan@google.com Signed-off-by: Joerg Roedel --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 2 +- drivers/iommu/io-pgfault.c | 121 +++++++++++++++++++--------- include/linux/iommu.h | 5 +- 3 files changed, 87 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index a31460f9f3d4..ed2b106e02dd 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -1777,7 +1777,7 @@ static int arm_smmu_handle_evt(struct arm_smmu_device *smmu, u64 *evt) goto out_unlock; } - iommu_report_device_fault(master->dev, &fault_evt); + ret = iommu_report_device_fault(master->dev, &fault_evt); out_unlock: mutex_unlock(&smmu->streams_mutex); return ret; diff --git a/drivers/iommu/io-pgfault.c b/drivers/iommu/io-pgfault.c index 81e9cc6e3164..4674e618797c 100644 --- a/drivers/iommu/io-pgfault.c +++ b/drivers/iommu/io-pgfault.c @@ -115,6 +115,59 @@ static struct iopf_group *iopf_group_alloc(struct iommu_fault_param *iopf_param, return group; } +static struct iommu_attach_handle *find_fault_handler(struct device *dev, + struct iopf_fault *evt) +{ + struct iommu_fault *fault = &evt->fault; + struct iommu_attach_handle *attach_handle; + + if (fault->prm.flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID) { + attach_handle = iommu_attach_handle_get(dev->iommu_group, + fault->prm.pasid, 0); + if (IS_ERR(attach_handle)) { + const struct iommu_ops *ops = dev_iommu_ops(dev); + + if (!ops->user_pasid_table) + return NULL; + /* + * The iommu driver for this device supports user- + * managed PASID table. Therefore page faults for + * any PASID should go through the NESTING domain + * attached to the device RID. + */ + attach_handle = iommu_attach_handle_get( + dev->iommu_group, IOMMU_NO_PASID, + IOMMU_DOMAIN_NESTED); + if (IS_ERR(attach_handle)) + return NULL; + } + } else { + attach_handle = iommu_attach_handle_get(dev->iommu_group, + IOMMU_NO_PASID, 0); + + if (IS_ERR(attach_handle)) + return NULL; + } + + if (!attach_handle->domain->iopf_handler) + return NULL; + + return attach_handle; +} + +static void iopf_error_response(struct device *dev, struct iopf_fault *evt) +{ + const struct iommu_ops *ops = dev_iommu_ops(dev); + struct iommu_fault *fault = &evt->fault; + struct iommu_page_response resp = { + .pasid = fault->prm.pasid, + .grpid = fault->prm.grpid, + .code = IOMMU_PAGE_RESP_INVALID + }; + + ops->page_response(dev, evt, &resp); +} + /** * iommu_report_device_fault() - Report fault event to device driver * @dev: the device @@ -153,24 +206,39 @@ static struct iopf_group *iopf_group_alloc(struct iommu_fault_param *iopf_param, * handling framework should guarantee that the iommu domain could only be * freed after the device has stopped generating page faults (or the iommu * hardware has been set to block the page faults) and the pending page faults - * have been flushed. + * have been flushed. In case no page fault handler is attached or no iopf params + * are setup, then the ops->page_response() is called to complete the evt. + * + * Returns 0 on success, or an error in case of a bad/failed iopf setup. */ -void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt) +int iommu_report_device_fault(struct device *dev, struct iopf_fault *evt) { + struct iommu_attach_handle *attach_handle; struct iommu_fault *fault = &evt->fault; struct iommu_fault_param *iopf_param; struct iopf_group abort_group = {}; struct iopf_group *group; + attach_handle = find_fault_handler(dev, evt); + if (!attach_handle) + goto err_bad_iopf; + + /* + * Something has gone wrong if a fault capable domain is attached but no + * iopf_param is setup + */ iopf_param = iopf_get_dev_fault_param(dev); if (WARN_ON(!iopf_param)) - return; + goto err_bad_iopf; if (!(fault->prm.flags & IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE)) { - report_partial_fault(iopf_param, fault); + int ret; + + ret = report_partial_fault(iopf_param, fault); iopf_put_dev_fault_param(iopf_param); /* A request that is not the last does not need to be ack'd */ - return; + + return ret; } /* @@ -185,38 +253,7 @@ void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt) if (group == &abort_group) goto err_abort; - if (fault->prm.flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID) { - group->attach_handle = iommu_attach_handle_get(dev->iommu_group, - fault->prm.pasid, - 0); - if (IS_ERR(group->attach_handle)) { - const struct iommu_ops *ops = dev_iommu_ops(dev); - - if (!ops->user_pasid_table) - goto err_abort; - - /* - * The iommu driver for this device supports user- - * managed PASID table. Therefore page faults for - * any PASID should go through the NESTING domain - * attached to the device RID. - */ - group->attach_handle = - iommu_attach_handle_get(dev->iommu_group, - IOMMU_NO_PASID, - IOMMU_DOMAIN_NESTED); - if (IS_ERR(group->attach_handle)) - goto err_abort; - } - } else { - group->attach_handle = - iommu_attach_handle_get(dev->iommu_group, IOMMU_NO_PASID, 0); - if (IS_ERR(group->attach_handle)) - goto err_abort; - } - - if (!group->attach_handle->domain->iopf_handler) - goto err_abort; + group->attach_handle = attach_handle; /* * On success iopf_handler must call iopf_group_response() and @@ -225,7 +262,7 @@ void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt) if (group->attach_handle->domain->iopf_handler(group)) goto err_abort; - return; + return 0; err_abort: dev_warn_ratelimited(dev, "iopf with pasid %d aborted\n", @@ -235,6 +272,14 @@ err_abort: __iopf_free_group(group); else iopf_free_group(group); + + return 0; + +err_bad_iopf: + if (fault->type == IOMMU_FAULT_PAGE_REQ) + iopf_error_response(dev, evt); + + return -EINVAL; } EXPORT_SYMBOL_GPL(iommu_report_device_fault); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 04cbdae0052e..bd722f473635 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -1563,7 +1563,7 @@ struct iopf_queue *iopf_queue_alloc(const char *name); void iopf_queue_free(struct iopf_queue *queue); int iopf_queue_discard_partial(struct iopf_queue *queue); void iopf_free_group(struct iopf_group *group); -void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt); +int iommu_report_device_fault(struct device *dev, struct iopf_fault *evt); void iopf_group_response(struct iopf_group *group, enum iommu_page_response_code status); #else @@ -1601,9 +1601,10 @@ static inline void iopf_free_group(struct iopf_group *group) { } -static inline void +static inline int iommu_report_device_fault(struct device *dev, struct iopf_fault *evt) { + return -ENODEV; } static inline void iopf_group_response(struct iopf_group *group, -- cgit v1.2.3 From b49420d6a1aeb399e5b107fc6eb8584d0860fbd7 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 21 Aug 2024 15:11:35 -0400 Subject: video/aperture: optionally match the device in sysfb_disable() In aperture_remove_conflicting_pci_devices(), we currently only call sysfb_disable() on vga class devices. This leads to the following problem when the pimary device is not VGA compatible: 1. A PCI device with a non-VGA class is the boot display 2. That device is probed first and it is not a VGA device so sysfb_disable() is not called, but the device resources are freed by aperture_detach_platform_device() 3. Non-primary GPU has a VGA class and it ends up calling sysfb_disable() 4. NULL pointer dereference via sysfb_disable() since the resources have already been freed by aperture_detach_platform_device() when it was called by the other device. Fix this by passing a device pointer to sysfb_disable() and checking the device to determine if we should execute it or not. v2: Fix build when CONFIG_SCREEN_INFO is not set v3: Move device check into the mutex Drop primary variable in aperture_remove_conflicting_pci_devices() Drop __init on pci sysfb_pci_dev_is_enabled() Fixes: 5ae3716cfdcd ("video/aperture: Only remove sysfb on the default vga pci device") Cc: Javier Martinez Canillas Cc: Thomas Zimmermann Cc: Helge Deller Cc: Sam Ravnborg Cc: Daniel Vetter Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Reviewed-by: Javier Martinez Canillas Reviewed-by: Thomas Zimmermann Signed-off-by: Alex Deucher Link: https://patchwork.freedesktop.org/patch/msgid/20240821191135.829765-1-alexander.deucher@amd.com --- drivers/firmware/sysfb.c | 19 +++++++++++++------ drivers/of/platform.c | 2 +- drivers/video/aperture.c | 11 +++-------- include/linux/sysfb.h | 4 ++-- 4 files changed, 19 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c index 921f61507ae8..02a07d3d0d40 100644 --- a/drivers/firmware/sysfb.c +++ b/drivers/firmware/sysfb.c @@ -39,6 +39,8 @@ static struct platform_device *pd; static DEFINE_MUTEX(disable_lock); static bool disabled; +static struct device *sysfb_parent_dev(const struct screen_info *si); + static bool sysfb_unregister(void) { if (IS_ERR_OR_NULL(pd)) @@ -52,6 +54,7 @@ static bool sysfb_unregister(void) /** * sysfb_disable() - disable the Generic System Framebuffers support + * @dev: the device to check if non-NULL * * This disables the registration of system framebuffer devices that match the * generic drivers that make use of the system framebuffer set up by firmware. @@ -61,17 +64,21 @@ static bool sysfb_unregister(void) * Context: The function can sleep. A @disable_lock mutex is acquired to serialize * against sysfb_init(), that registers a system framebuffer device. */ -void sysfb_disable(void) +void sysfb_disable(struct device *dev) { + struct screen_info *si = &screen_info; + mutex_lock(&disable_lock); - sysfb_unregister(); - disabled = true; + if (!dev || dev == sysfb_parent_dev(si)) { + sysfb_unregister(); + disabled = true; + } mutex_unlock(&disable_lock); } EXPORT_SYMBOL_GPL(sysfb_disable); #if defined(CONFIG_PCI) -static __init bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev) +static bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev) { /* * TODO: Try to integrate this code into the PCI subsystem @@ -87,13 +94,13 @@ static __init bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev) return true; } #else -static __init bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev) +static bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev) { return false; } #endif -static __init struct device *sysfb_parent_dev(const struct screen_info *si) +static struct device *sysfb_parent_dev(const struct screen_info *si) { struct pci_dev *pdev; diff --git a/drivers/of/platform.c b/drivers/of/platform.c index 389d4ea6bfc1..ef622d41eb5b 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -592,7 +592,7 @@ static int __init of_platform_default_populate_init(void) * This can happen for example on DT systems that do EFI * booting and may provide a GOP handle to the EFI stub. */ - sysfb_disable(); + sysfb_disable(NULL); of_platform_device_create(node, NULL, NULL); of_node_put(node); } diff --git a/drivers/video/aperture.c b/drivers/video/aperture.c index 561be8feca96..2b5a1e666e9b 100644 --- a/drivers/video/aperture.c +++ b/drivers/video/aperture.c @@ -293,7 +293,7 @@ int aperture_remove_conflicting_devices(resource_size_t base, resource_size_t si * ask for this, so let's assume that a real driver for the display * was already probed and prevent sysfb to register devices later. */ - sysfb_disable(); + sysfb_disable(NULL); aperture_detach_devices(base, size); @@ -346,15 +346,10 @@ EXPORT_SYMBOL(__aperture_remove_legacy_vga_devices); */ int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *name) { - bool primary = false; resource_size_t base, size; int bar, ret = 0; - if (pdev == vga_default_device()) - primary = true; - - if (primary) - sysfb_disable(); + sysfb_disable(&pdev->dev); for (bar = 0; bar < PCI_STD_NUM_BARS; ++bar) { if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) @@ -370,7 +365,7 @@ int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *na * that consumes the VGA framebuffer I/O range. Remove this * device as well. */ - if (primary) + if (pdev == vga_default_device()) ret = __aperture_remove_legacy_vga_devices(pdev); return ret; diff --git a/include/linux/sysfb.h b/include/linux/sysfb.h index c9cb657dad08..bef5f06a91de 100644 --- a/include/linux/sysfb.h +++ b/include/linux/sysfb.h @@ -58,11 +58,11 @@ struct efifb_dmi_info { #ifdef CONFIG_SYSFB -void sysfb_disable(void); +void sysfb_disable(struct device *dev); #else /* CONFIG_SYSFB */ -static inline void sysfb_disable(void) +static inline void sysfb_disable(struct device *dev) { } -- cgit v1.2.3 From a547a5880cba6f287179135381f1b484b251be31 Mon Sep 17 00:00:00 2001 From: Peter Newman Date: Thu, 22 Aug 2024 12:02:11 -0700 Subject: x86/resctrl: Fix arch_mbm_* array overrun on SNC When using resctrl on systems with Sub-NUMA Clustering enabled, monitoring groups may be allocated RMID values which would overrun the arch_mbm_{local,total} arrays. This is due to inconsistencies in whether the SNC-adjusted num_rmid value or the unadjusted value in resctrl_arch_system_num_rmid_idx() is used. The num_rmid value for the L3 resource is currently: resctrl_arch_system_num_rmid_idx() / snc_nodes_per_l3_cache As a simple fix, make resctrl_arch_system_num_rmid_idx() return the SNC-adjusted, L3 num_rmid value on x86. Fixes: e13db55b5a0d ("x86/resctrl: Introduce snc_nodes_per_l3_cache") Signed-off-by: Peter Newman Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Link: https://lore.kernel.org/r/20240822190212.1848788-1-peternewman@google.com --- arch/x86/include/asm/resctrl.h | 6 ------ arch/x86/kernel/cpu/resctrl/core.c | 8 ++++++++ include/linux/resctrl.h | 1 + 3 files changed, 9 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index 12dbd2588ca7..8b1b6ce1e51b 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -156,12 +156,6 @@ static inline void resctrl_sched_in(struct task_struct *tsk) __resctrl_sched_in(tsk); } -static inline u32 resctrl_arch_system_num_rmid_idx(void) -{ - /* RMID are independent numbers for x86. num_rmid_idx == num_rmid */ - return boot_cpu_data.x86_cache_max_rmid + 1; -} - static inline void resctrl_arch_rmid_idx_decode(u32 idx, u32 *closid, u32 *rmid) { *rmid = idx; diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 1930fce9dfe9..8591d53c144b 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -119,6 +119,14 @@ struct rdt_hw_resource rdt_resources_all[] = { }, }; +u32 resctrl_arch_system_num_rmid_idx(void) +{ + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + + /* RMID are independent numbers for x86. num_rmid_idx == num_rmid */ + return r->num_rmid; +} + /* * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs * as they do not have CPUID enumeration support for Cache allocation. diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index b0875b99e811..d94abba1c716 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -248,6 +248,7 @@ struct resctrl_schema { /* The number of closid supported by this resource regardless of CDP */ u32 resctrl_arch_get_num_closid(struct rdt_resource *r); +u32 resctrl_arch_system_num_rmid_idx(void); int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid); /* -- cgit v1.2.3 From 1da29f2c39b67b846b74205c81bf0ccd96d34727 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 22 Aug 2024 23:06:49 +0100 Subject: netfs, cifs: Fix handling of short DIO read Short DIO reads, particularly in relation to cifs, are not being handled correctly by cifs and netfslib. This can be tested by doing a DIO read of a file where the size of read is larger than the size of the file. When it crosses the EOF, it gets a short read and this gets retried, and in the case of cifs, the retry read fails, with the failure being translated to ENODATA. Fix this by the following means: (1) Add a flag, NETFS_SREQ_HIT_EOF, for the filesystem to set when it detects that the read did hit the EOF. (2) Make the netfslib read assessment stop processing subrequests when it encounters one with that flag set. (3) Return rreq->transferred, the accumulated contiguous amount read to that point, to userspace for a DIO read. (4) Make cifs set the flag and clear the error if the read RPC returned ENODATA. (5) Make cifs set the flag and clear the error if a short read occurred without error and the read-to file position is now at the remote inode size. Fixes: 69c3c023af25 ("cifs: Implement netfslib hooks") Signed-off-by: David Howells cc: Steve French cc: Paulo Alcantara cc: Jeff Layton cc: linux-cifs@vger.kernel.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Steve French --- fs/netfs/io.c | 17 +++++++++++------ fs/smb/client/smb2pdu.c | 13 +++++++++---- include/linux/netfs.h | 1 + 3 files changed, 21 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/netfs/io.c b/fs/netfs/io.c index 3303b515b536..943128507af5 100644 --- a/fs/netfs/io.c +++ b/fs/netfs/io.c @@ -368,7 +368,8 @@ static void netfs_rreq_assess_dio(struct netfs_io_request *rreq) if (subreq->error || subreq->transferred == 0) break; transferred += subreq->transferred; - if (subreq->transferred < subreq->len) + if (subreq->transferred < subreq->len || + test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags)) break; } @@ -503,7 +504,8 @@ void netfs_subreq_terminated(struct netfs_io_subrequest *subreq, subreq->error = 0; subreq->transferred += transferred_or_error; - if (subreq->transferred < subreq->len) + if (subreq->transferred < subreq->len && + !test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags)) goto incomplete; complete: @@ -782,10 +784,13 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync) TASK_UNINTERRUPTIBLE); ret = rreq->error; - if (ret == 0 && rreq->submitted < rreq->len && - rreq->origin != NETFS_DIO_READ) { - trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); - ret = -EIO; + if (ret == 0) { + if (rreq->origin == NETFS_DIO_READ) { + ret = rreq->transferred; + } else if (rreq->submitted < rreq->len) { + trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); + ret = -EIO; + } } } else { /* If we decrement nr_outstanding to 0, the ref belongs to us. */ diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index be7a1a9c691d..88dc49d67037 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4507,6 +4507,7 @@ static void smb2_readv_callback(struct mid_q_entry *mid) { struct cifs_io_subrequest *rdata = mid->callback_data; + struct netfs_inode *ictx = netfs_inode(rdata->rreq->inode); struct cifs_tcon *tcon = tlink_tcon(rdata->req->cfile->tlink); struct TCP_Server_Info *server = rdata->server; struct smb2_hdr *shdr = @@ -4599,11 +4600,15 @@ smb2_readv_callback(struct mid_q_entry *mid) rdata->got_bytes); if (rdata->result == -ENODATA) { - /* We may have got an EOF error because fallocate - * failed to enlarge the file. - */ - if (rdata->subreq.start < rdata->subreq.rreq->i_size) + __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); + rdata->result = 0; + } else { + if (rdata->got_bytes < rdata->actual_len && + rdata->subreq.start + rdata->subreq.transferred + rdata->got_bytes == + ictx->remote_i_size) { + __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; + } } trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, rdata->credits.value, server->credits, server->in_flight, diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 983816608f15..c47443e7a97e 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -198,6 +198,7 @@ struct netfs_io_subrequest { #define NETFS_SREQ_NEED_RETRY 9 /* Set if the filesystem requests a retry */ #define NETFS_SREQ_RETRYING 10 /* Set if we're retrying */ #define NETFS_SREQ_FAILED 11 /* Set if the subreq failed unretryably */ +#define NETFS_SREQ_HIT_EOF 12 /* Set if we hit the EOF */ }; enum netfs_io_origin { -- cgit v1.2.3 From 1a5caec7f80ca2e659c03f45378ee26915f4eda2 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Fri, 30 Aug 2024 07:35:12 -0700 Subject: regulator: core: Stub devm_regulator_bulk_get_const() if !CONFIG_REGULATOR When adding devm_regulator_bulk_get_const() I missed adding a stub for when CONFIG_REGULATOR is not enabled. Under certain conditions (like randconfig testing) this can cause the compiler to reports errors like: error: implicit declaration of function 'devm_regulator_bulk_get_const'; did you mean 'devm_regulator_bulk_get_enable'? Add the stub. Fixes: 1de452a0edda ("regulator: core: Allow drivers to define their init data as const") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202408301813.TesFuSbh-lkp@intel.com/ Cc: Neil Armstrong Signed-off-by: Douglas Anderson Link: https://patch.msgid.link/20240830073511.1.Ib733229a8a19fad8179213c05e1af01b51e42328@changeid Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index d986ec13092e..b9ce521910a0 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -452,6 +452,14 @@ static inline int of_regulator_bulk_get_all(struct device *dev, struct device_no return 0; } +static inline int devm_regulator_bulk_get_const( + struct device *dev, int num_consumers, + const struct regulator_bulk_data *in_consumers, + struct regulator_bulk_data **out_consumers) +{ + return 0; +} + static inline int regulator_bulk_enable(int num_consumers, struct regulator_bulk_data *consumers) { -- cgit v1.2.3 From 33f339a1ba54e56bba57ee9a77c71e385ab4825c Mon Sep 17 00:00:00 2001 From: Tze-nan Wu Date: Fri, 30 Aug 2024 16:25:17 +0800 Subject: bpf, net: Fix a potential race in do_sock_getsockopt() There's a potential race when `cgroup_bpf_enabled(CGROUP_GETSOCKOPT)` is false during the execution of `BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN`, but becomes true when `BPF_CGROUP_RUN_PROG_GETSOCKOPT` is called. This inconsistency can lead to `BPF_CGROUP_RUN_PROG_GETSOCKOPT` receiving an "-EFAULT" from `__cgroup_bpf_run_filter_getsockopt(max_optlen=0)`. Scenario shown as below: `process A` `process B` ----------- ------------ BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN enable CGROUP_GETSOCKOPT BPF_CGROUP_RUN_PROG_GETSOCKOPT (-EFAULT) To resolve this, remove the `BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN` macro and directly uses `copy_from_sockptr` to ensure that `max_optlen` is always set before `BPF_CGROUP_RUN_PROG_GETSOCKOPT` is invoked. Fixes: 0d01da6afc54 ("bpf: implement getsockopt and setsockopt hooks") Co-developed-by: Yanghui Li Signed-off-by: Yanghui Li Co-developed-by: Cheng-Jui Wang Signed-off-by: Cheng-Jui Wang Signed-off-by: Tze-nan Wu Acked-by: Stanislav Fomichev Acked-by: Alexei Starovoitov Link: https://patch.msgid.link/20240830082518.23243-1-Tze-nan.Wu@mediatek.com Signed-off-by: Jakub Kicinski --- include/linux/bpf-cgroup.h | 9 --------- net/socket.c | 4 ++-- 2 files changed, 2 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index fb3c3e7181e6..ce91d9b2acb9 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -390,14 +390,6 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, __ret; \ }) -#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) \ -({ \ - int __ret = 0; \ - if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT)) \ - copy_from_sockptr(&__ret, optlen, sizeof(int)); \ - __ret; \ -}) - #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, optlen, \ max_optlen, retval) \ ({ \ @@ -518,7 +510,6 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; }) -#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \ optlen, max_optlen, retval) ({ retval; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \ diff --git a/net/socket.c b/net/socket.c index fcbdd5bc47ac..0a2bd22ec105 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2362,7 +2362,7 @@ INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level, int do_sock_getsockopt(struct socket *sock, bool compat, int level, int optname, sockptr_t optval, sockptr_t optlen) { - int max_optlen __maybe_unused; + int max_optlen __maybe_unused = 0; const struct proto_ops *ops; int err; @@ -2371,7 +2371,7 @@ int do_sock_getsockopt(struct socket *sock, bool compat, int level, return err; if (!compat) - max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen); + copy_from_sockptr(&max_optlen, optlen, sizeof(int)); ops = READ_ONCE(sock->ops); if (level == SOL_SOCKET) { -- cgit v1.2.3