diff --git a/.clang-format b/.clang-format index 01a341ceec6c..c24b147cac01 100644 --- a/.clang-format +++ b/.clang-format @@ -109,6 +109,7 @@ ForEachMacros: - 'css_for_each_child' - 'css_for_each_descendant_post' - 'css_for_each_descendant_pre' + - 'cxl_for_each_cmd' - 'device_for_each_child_node' - 'dma_fence_chain_for_each' - 'do_for_each_ftrace_op' diff --git a/Documentation/ABI/testing/sysfs-bus-cxl b/Documentation/ABI/testing/sysfs-bus-cxl new file mode 100644 index 000000000000..2fe7490ad6a8 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-bus-cxl @@ -0,0 +1,26 @@ +What: /sys/bus/cxl/devices/memX/firmware_version +Date: December, 2020 +KernelVersion: v5.12 +Contact: linux-cxl@vger.kernel.org +Description: + (RO) "FW Revision" string as reported by the Identify + Memory Device Output Payload in the CXL-2.0 + specification. + +What: /sys/bus/cxl/devices/memX/ram/size +Date: December, 2020 +KernelVersion: v5.12 +Contact: linux-cxl@vger.kernel.org +Description: + (RO) "Volatile Only Capacity" as bytes. Represents the + identically named field in the Identify Memory Device Output + Payload in the CXL-2.0 specification. + +What: /sys/bus/cxl/devices/memX/pmem/size +Date: December, 2020 +KernelVersion: v5.12 +Contact: linux-cxl@vger.kernel.org +Description: + (RO) "Persistent Only Capacity" as bytes. Represents the + identically named field in the Identify Memory Device Output + Payload in the CXL-2.0 specification. diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst index 75cb757bbff0..e6d23f117308 100644 --- a/Documentation/core-api/dma-api.rst +++ b/Documentation/core-api/dma-api.rst @@ -526,46 +526,6 @@ for the kernel vs the device. If you don't understand how cache line coherency works between a processor and an I/O device, you should not be using this part of the API. -:: - - void * - dma_alloc_noncoherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, enum dma_data_direction dir, - gfp_t gfp) - -This routine allocates a region of bytes of consistent memory. It -returns a pointer to the allocated region (in the processor's virtual address -space) or NULL if the allocation failed. The returned memory may or may not -be in the kernel direct mapping. Drivers must not call virt_to_page on -the returned memory region. - -It also returns a which may be cast to an unsigned integer the -same width as the bus and given to the device as the DMA address base of -the region. - -The dir parameter specified if data is read and/or written by the device, -see dma_map_single() for details. - -The gfp parameter allows the caller to specify the ``GFP_`` flags (see -kmalloc()) for the allocation, but rejects flags used to specify a memory -zone such as GFP_DMA or GFP_HIGHMEM. - -Before giving the memory to the device, dma_sync_single_for_device() needs -to be called, and before reading memory written by the device, -dma_sync_single_for_cpu(), just like for streaming DMA mappings that are -reused. - -:: - - void - dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr, - dma_addr_t dma_handle, enum dma_data_direction dir) - -Free a region of memory previously allocated using dma_alloc_noncoherent(). -dev, size and dma_handle and dir must all be the same as those passed into -dma_alloc_noncoherent(). cpu_addr must be the virtual address returned by -dma_alloc_noncoherent(). - :: struct page * @@ -600,9 +560,29 @@ reused. dma_addr_t dma_handle, enum dma_data_direction dir) Free a region of memory previously allocated using dma_alloc_pages(). -dev, size and dma_handle and dir must all be the same as those passed into -dma_alloc_noncoherent(). page must be the pointer returned by -dma_alloc_pages(). +dev, size, dma_handle and dir must all be the same as those passed into +dma_alloc_pages(). page must be the pointer returned by dma_alloc_pages(). + +:: + + void * + dma_alloc_noncoherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, enum dma_data_direction dir, + gfp_t gfp) + +This routine is a convenient wrapper around dma_alloc_pages that returns the +kernel virtual address for the allocated memory instead of the page structure. + +:: + + void + dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t dma_handle, enum dma_data_direction dir) + +Free a region of memory previously allocated using dma_alloc_noncoherent(). +dev, size, dma_handle and dir must all be the same as those passed into +dma_alloc_noncoherent(). cpu_addr must be the virtual address returned by +dma_alloc_noncoherent(). :: diff --git a/Documentation/devicetree/bindings/mailbox/omap-mailbox.txt b/Documentation/devicetree/bindings/mailbox/omap-mailbox.txt index 5fe80c1c19fc..12371f5c6cd9 100644 --- a/Documentation/devicetree/bindings/mailbox/omap-mailbox.txt +++ b/Documentation/devicetree/bindings/mailbox/omap-mailbox.txt @@ -28,6 +28,9 @@ SoCs has each of these instances form a cluster and combine multiple clusters into a single IP block present within the Main NavSS. The interrupt lines from all these clusters are multiplexed and routed to different processor subsystems over a limited number of common interrupt output lines of an Interrupt Router. +The AM64x SoCS also uses a single IP block comprising of multiple clusters, +but the number of clusters are smaller, and the interrupt output lines are +connected directly to various processors. Mailbox Device Node: ==================== @@ -42,6 +45,7 @@ Required properties: "ti,omap4-mailbox" for OMAP44xx, OMAP54xx, AM33xx, AM43xx and DRA7xx SoCs "ti,am654-mailbox" for K3 AM65x and J721E SoCs + "ti,am64-mailbox" for K3 AM64x SoCs - reg: Contains the mailbox register address range (base address and length) - interrupts: Contains the interrupt information for the mailbox diff --git a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml index ffd09b664ff5..5dc1173d03fd 100644 --- a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml +++ b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml @@ -24,6 +24,7 @@ properties: - qcom,msm8998-apcs-hmss-global - qcom,qcs404-apcs-apps-global - qcom,sc7180-apss-shared + - qcom,sc8180x-apss-shared - qcom,sdm660-apcs-hmss-global - qcom,sdm845-apss-shared - qcom,sm8150-apss-shared @@ -33,9 +34,11 @@ properties: clocks: description: phandles to the parent clocks of the clock driver + minItems: 2 items: - description: primary pll parent of the clock driver - description: auxiliary parent + - description: reference clock '#mbox-cells': const: 1 @@ -44,9 +47,11 @@ properties: const: 0 clock-names: + minItems: 2 items: - const: pll - const: aux + - const: ref required: - compatible @@ -55,6 +60,35 @@ required: additionalProperties: false +allOf: + - if: + properties: + compatible: + enum: + - qcom,ipq6018-apcs-apps-global + - qcom,ipq8074-apcs-apps-global + - qcom,msm8916-apcs-kpss-global + - qcom,msm8994-apcs-kpss-global + - qcom,msm8996-apcs-hmss-global + - qcom,msm8998-apcs-hmss-global + - qcom,qcs404-apcs-apps-global + - qcom,sc7180-apss-shared + - qcom,sdm660-apcs-hmss-global + - qcom,sdm845-apss-shared + - qcom,sm8150-apss-shared + then: + properties: + clocks: + maxItems: 2 + - if: + properties: + compatible: + enum: + - qcom,sdx55-apcs-gcc + then: + properties: + clocks: + maxItems: 3 examples: # Example apcs with msm8996 diff --git a/Documentation/driver-api/cxl/index.rst b/Documentation/driver-api/cxl/index.rst new file mode 100644 index 000000000000..036e49553542 --- /dev/null +++ b/Documentation/driver-api/cxl/index.rst @@ -0,0 +1,12 @@ +.. SPDX-License-Identifier: GPL-2.0 + +==================== +Compute Express Link +==================== + +.. toctree:: + :maxdepth: 1 + + memory-devices + +.. only:: subproject and html diff --git a/Documentation/driver-api/cxl/memory-devices.rst b/Documentation/driver-api/cxl/memory-devices.rst new file mode 100644 index 000000000000..1bad466f9167 --- /dev/null +++ b/Documentation/driver-api/cxl/memory-devices.rst @@ -0,0 +1,46 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. include:: + +=================================== +Compute Express Link Memory Devices +=================================== + +A Compute Express Link Memory Device is a CXL component that implements the +CXL.mem protocol. It contains some amount of volatile memory, persistent memory, +or both. It is enumerated as a PCI device for configuration and passing +messages over an MMIO mailbox. Its contribution to the System Physical +Address space is handled via HDM (Host Managed Device Memory) decoders +that optionally define a device's contribution to an interleaved address +range across multiple devices underneath a host-bridge or interleaved +across host-bridges. + +Driver Infrastructure +===================== + +This section covers the driver infrastructure for a CXL memory device. + +CXL Memory Device +----------------- + +.. kernel-doc:: drivers/cxl/mem.c + :doc: cxl mem + +.. kernel-doc:: drivers/cxl/mem.c + :internal: + +CXL Bus +------- +.. kernel-doc:: drivers/cxl/bus.c + :doc: cxl bus + +External Interfaces +=================== + +CXL IOCTL Interface +------------------- + +.. kernel-doc:: include/uapi/linux/cxl_mem.h + :doc: UAPI + +.. kernel-doc:: include/uapi/linux/cxl_mem.h + :internal: diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst index 9d9af54d68c5..9ba74e86751b 100644 --- a/Documentation/driver-api/index.rst +++ b/Documentation/driver-api/index.rst @@ -35,6 +35,7 @@ available subsections can be seen below. usb/index firewire pci/index + cxl/index spi i2c ipmb diff --git a/Documentation/security/keys/core.rst b/Documentation/security/keys/core.rst index aa0081685ee1..b3ed5c581034 100644 --- a/Documentation/security/keys/core.rst +++ b/Documentation/security/keys/core.rst @@ -1040,8 +1040,8 @@ The keyctl syscall functions are: "key" is the ID of the key to be watched. - "queue_fd" is a file descriptor referring to an open "/dev/watch_queue" - which manages the buffer into which notifications will be delivered. + "queue_fd" is a file descriptor referring to an open pipe which + manages the buffer into which notifications will be delivered. "filter" is either NULL to remove a watch or a filter specification to indicate what events are required from the key. diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index d02ba2f67df8..2fe16fb8c3af 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -353,6 +353,7 @@ Code Seq# Include File Comments 0xCC 00-0F drivers/misc/ibmvmc.h pseries VMC driver 0xCD 01 linux/reiserfs_fs.h +0xCE 01-02 uapi/linux/cxl_mem.h Compute Express Link Memory Devices 0xCF 02 fs/cifs/ioctl.c 0xDB 00-0F drivers/char/mwave/mwavepub.h 0xDD 00-3F ZFCP device driver see drivers/s390/scsi/ diff --git a/MAINTAINERS b/MAINTAINERS index dcd0beb4c433..dccbf39ce02c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4434,6 +4434,17 @@ M: Miguel Ojeda S: Maintained F: include/linux/compiler_attributes.h +COMPUTE EXPRESS LINK (CXL) +M: Alison Schofield +M: Vishal Verma +M: Ira Weiny +M: Ben Widawsky +M: Dan Williams +L: linux-cxl@vger.kernel.org +S: Maintained +F: drivers/cxl/ +F: include/uapi/linux/cxl_mem.h + CONEXANT ACCESSRUNNER USB DRIVER L: accessrunner-general@lists.sourceforge.net S: Orphan diff --git a/Makefile b/Makefile index c628607bbceb..00878f99022e 100644 --- a/Makefile +++ b/Makefile @@ -863,6 +863,9 @@ ifdef CONFIG_FTRACE_MCOUNT_USE_CC endif endif endif +ifdef CONFIG_FTRACE_MCOUNT_USE_OBJTOOL + CC_FLAGS_USING += -DCC_USING_NOP_MCOUNT +endif ifdef CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT ifdef CONFIG_HAVE_C_RECORDMCOUNT BUILD_C_RECORDMCOUNT := y @@ -910,7 +913,8 @@ KBUILD_LDFLAGS += -mllvm -import-instr-limit=5 endif ifdef CONFIG_LTO -KBUILD_CFLAGS += $(CC_FLAGS_LTO) +KBUILD_CFLAGS += -fno-lto $(CC_FLAGS_LTO) +KBUILD_AFLAGS += -fno-lto export CC_FLAGS_LTO endif @@ -1281,6 +1285,10 @@ uapi-asm-generic: PHONY += prepare-objtool prepare-resolve_btfids prepare-objtool: $(objtool_target) ifeq ($(SKIP_STACK_VALIDATION),1) +ifdef CONFIG_FTRACE_MCOUNT_USE_OBJTOOL + @echo "error: Cannot generate __mcount_loc for CONFIG_DYNAMIC_FTRACE=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel" >&2 + @false +endif ifdef CONFIG_UNWINDER_ORC @echo "error: Cannot generate ORC metadata for CONFIG_UNWINDER_ORC=y, please install libelf-dev, libelf-devel or elfutils-libelf-devel" >&2 @false diff --git a/arch/nios2/kernel/entry.S b/arch/nios2/kernel/entry.S index da8442450e46..0794cd7803df 100644 --- a/arch/nios2/kernel/entry.S +++ b/arch/nios2/kernel/entry.S @@ -389,7 +389,10 @@ ENTRY(ret_from_interrupt) */ ENTRY(sys_clone) SAVE_SWITCH_STACK + subi sp, sp, 4 /* make space for tls pointer */ + stw r8, 0(sp) /* pass tls pointer (r8) via stack (5th argument) */ call nios2_clone + addi sp, sp, 4 RESTORE_SWITCH_STACK ret diff --git a/arch/nios2/kernel/setup.c b/arch/nios2/kernel/setup.c index 3c6e3c813a0b..d2f21957e99c 100644 --- a/arch/nios2/kernel/setup.c +++ b/arch/nios2/kernel/setup.c @@ -32,8 +32,6 @@ EXPORT_SYMBOL(memory_start); unsigned long memory_end; EXPORT_SYMBOL(memory_end); -unsigned long memory_size; - static struct pt_regs fake_regs = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0}; @@ -141,16 +139,22 @@ asmlinkage void __init nios2_boot_init(unsigned r4, unsigned r5, unsigned r6, parse_early_param(); } +static void __init find_limits(unsigned long *min, unsigned long *max_low, + unsigned long *max_high) +{ + *max_low = PFN_DOWN(memblock_get_current_limit()); + *min = PFN_UP(memblock_start_of_DRAM()); + *max_high = PFN_DOWN(memblock_end_of_DRAM()); +} + void __init setup_arch(char **cmdline_p) { int dram_start; console_verbose(); - dram_start = memblock_start_of_DRAM(); - memory_size = memblock_phys_mem_size(); - memory_start = PAGE_ALIGN((unsigned long)__pa(_end)); - memory_end = (unsigned long) CONFIG_NIOS2_MEM_BASE + memory_size; + memory_start = memblock_start_of_DRAM(); + memory_end = memblock_end_of_DRAM(); init_mm.start_code = (unsigned long) _stext; init_mm.end_code = (unsigned long) _etext; @@ -161,11 +165,10 @@ void __init setup_arch(char **cmdline_p) /* Keep a copy of command line */ *cmdline_p = boot_command_line; - min_low_pfn = PFN_UP(memory_start); - max_low_pfn = PFN_DOWN(memory_end); + find_limits(&min_low_pfn, &max_low_pfn, &max_pfn); max_mapnr = max_low_pfn; - memblock_reserve(dram_start, memory_start - dram_start); + memblock_reserve(__pa_symbol(_stext), _end - _stext); #ifdef CONFIG_BLK_DEV_INITRD if (initrd_start) { memblock_reserve(virt_to_phys((void *)initrd_start), diff --git a/arch/nios2/kernel/sys_nios2.c b/arch/nios2/kernel/sys_nios2.c index cd390ec4f88b..b1ca85699952 100644 --- a/arch/nios2/kernel/sys_nios2.c +++ b/arch/nios2/kernel/sys_nios2.c @@ -22,6 +22,7 @@ asmlinkage int sys_cacheflush(unsigned long addr, unsigned long len, unsigned int op) { struct vm_area_struct *vma; + struct mm_struct *mm = current->mm; if (len == 0) return 0; @@ -34,16 +35,22 @@ asmlinkage int sys_cacheflush(unsigned long addr, unsigned long len, if (addr + len < addr) return -EFAULT; + if (mmap_read_lock_killable(mm)) + return -EINTR; + /* * Verify that the specified address region actually belongs * to this process. */ - vma = find_vma(current->mm, addr); - if (vma == NULL || addr < vma->vm_start || addr + len > vma->vm_end) + vma = find_vma(mm, addr); + if (vma == NULL || addr < vma->vm_start || addr + len > vma->vm_end) { + mmap_read_unlock(mm); return -EFAULT; + } flush_cache_range(vma, addr, addr + len); + mmap_read_unlock(mm); return 0; } diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 2c1cee9eed73..5993eb544d35 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -175,7 +175,7 @@ config SMP Management" code will be disabled if you say Y here. See also and the SMP-HOWTO - available at . + available at . If you don't know what to do here, say N. diff --git a/arch/sparc/boot/piggyback.c b/arch/sparc/boot/piggyback.c index a7a38fb4ece0..6d74064add0a 100644 --- a/arch/sparc/boot/piggyback.c +++ b/arch/sparc/boot/piggyback.c @@ -154,6 +154,10 @@ static off_t get_hdrs_offset(int kernelfd, const char *filename) offset -= LOOKBACK; /* skip a.out header */ offset += AOUT_TEXT_OFFSET; + if (offset < 0) { + errno = -EINVAL; + die("Calculated a negative offset, probably elftoaout generated an invalid image. Did you use a recent elftoaout ?"); + } if (lseek(kernelfd, offset, SEEK_SET) < 0) die("lseek"); if (read(kernelfd, buffer, BUFSIZE) != BUFSIZE) diff --git a/arch/sparc/configs/sparc64_defconfig b/arch/sparc/configs/sparc64_defconfig index d91eb6a76dd1..148f44b33890 100644 --- a/arch/sparc/configs/sparc64_defconfig +++ b/arch/sparc/configs/sparc64_defconfig @@ -65,9 +65,8 @@ CONFIG_CDROM_PKTCDVD=m CONFIG_CDROM_PKTCDVD_WCACHE=y CONFIG_ATA_OVER_ETH=m CONFIG_SUNVDC=m -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=y -CONFIG_BLK_DEV_ALI15X3=y +CONFIG_ATA=y +CONFIG_PATA_ALI=y CONFIG_RAID_ATTRS=m CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y @@ -235,3 +234,9 @@ CONFIG_CRYPTO_TWOFISH=m CONFIG_CRC16=m CONFIG_LIBCRC32C=m CONFIG_VCC=m +CONFIG_ATA=y +CONFIG_PATA_CMD64X=y +CONFIG_HAPPYMEAL=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_DEVTMPFS=y diff --git a/arch/sparc/include/asm/backoff.h b/arch/sparc/include/asm/backoff.h index 8625946d8d00..597a22953bc5 100644 --- a/arch/sparc/include/asm/backoff.h +++ b/arch/sparc/include/asm/backoff.h @@ -18,7 +18,7 @@ * * When we spin, we try to use an operation that will cause the * current cpu strand to block, and therefore make the core fully - * available to any other other runnable strands. There are two + * available to any other runnable strands. There are two * options, based upon cpu capabilities. * * On all cpus prior to SPARC-T4 we do three dummy reads of the diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h index c73b5a3ab7b9..a53d744d4212 100644 --- a/arch/sparc/include/asm/cmpxchg_32.h +++ b/arch/sparc/include/asm/cmpxchg_32.h @@ -25,7 +25,7 @@ static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int return x; } -#define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr)))) +#define xchg(ptr,x) ({(__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr)));}) /* Emulate cmpxchg() the same way we emulate atomics, * by hashing the object address and indexing into an array diff --git a/arch/sparc/include/asm/mman.h b/arch/sparc/include/asm/mman.h index f94532f25db1..274217e7ed70 100644 --- a/arch/sparc/include/asm/mman.h +++ b/arch/sparc/include/asm/mman.h @@ -57,36 +57,40 @@ static inline int sparc_validate_prot(unsigned long prot, unsigned long addr) { if (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM | PROT_ADI)) return 0; - if (prot & PROT_ADI) { - if (!adi_capable()) - return 0; - - if (addr) { - struct vm_area_struct *vma; - - vma = find_vma(current->mm, addr); - if (vma) { - /* ADI can not be enabled on PFN - * mapped pages - */ - if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) - return 0; - - /* Mergeable pages can become unmergeable - * if ADI is enabled on them even if they - * have identical data on them. This can be - * because ADI enabled pages with identical - * data may still not have identical ADI - * tags on them. Disallow ADI on mergeable - * pages. - */ - if (vma->vm_flags & VM_MERGEABLE) - return 0; - } - } - } return 1; } + +#define arch_validate_flags(vm_flags) arch_validate_flags(vm_flags) +/* arch_validate_flags() - Ensure combination of flags is valid for a + * VMA. + */ +static inline bool arch_validate_flags(unsigned long vm_flags) +{ + /* If ADI is being enabled on this VMA, check for ADI + * capability on the platform and ensure VMA is suitable + * for ADI + */ + if (vm_flags & VM_SPARC_ADI) { + if (!adi_capable()) + return false; + + /* ADI can not be enabled on PFN mapped pages */ + if (vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) + return false; + + /* Mergeable pages can become unmergeable + * if ADI is enabled on them even if they + * have identical data on them. This can be + * because ADI enabled pages with identical + * data may still not have identical ADI + * tags on them. Disallow ADI on mergeable + * pages. + */ + if (vm_flags & VM_MERGEABLE) + return false; + } + return true; +} #endif /* CONFIG_SPARC64 */ #endif /* __ASSEMBLY__ */ diff --git a/arch/sparc/include/asm/pgtsrmmu.h b/arch/sparc/include/asm/pgtsrmmu.h index 7708d015712b..6067925972d9 100644 --- a/arch/sparc/include/asm/pgtsrmmu.h +++ b/arch/sparc/include/asm/pgtsrmmu.h @@ -113,7 +113,7 @@ extern unsigned long last_valid_pfn; extern void *srmmu_nocache_pool; #define __nocache_pa(VADDR) (((unsigned long)VADDR) - SRMMU_NOCACHE_VADDR + __pa((unsigned long)srmmu_nocache_pool)) #define __nocache_va(PADDR) (__va((unsigned long)PADDR) - (unsigned long)srmmu_nocache_pool + SRMMU_NOCACHE_VADDR) -#define __nocache_fix(VADDR) __va(__nocache_pa(VADDR)) +#define __nocache_fix(VADDR) ((__typeof__(VADDR))__va(__nocache_pa(VADDR))) /* Accessing the MMU control register. */ unsigned int srmmu_get_mmureg(void); diff --git a/arch/sparc/include/asm/signal.h b/arch/sparc/include/asm/signal.h index 827b73a97f8a..28f81081e37d 100644 --- a/arch/sparc/include/asm/signal.h +++ b/arch/sparc/include/asm/signal.h @@ -9,18 +9,6 @@ #include #ifndef __ASSEMBLY__ -/* - * DJHR - * SA_STATIC_ALLOC is used for the sparc32 system to indicate that this - * interrupt handler's irq structure should be statically allocated - * by the request_irq routine. - * The alternative is that arch/sparc/kernel/irq.c has carnal knowledge - * of interrupt usage and that sucks. Also without a flag like this - * it may be possible for the free_irq routine to attempt to free - * statically allocated data.. which is NOT GOOD. - * - */ -#define SA_STATIC_ALLOC 0x8000 #define __ARCH_HAS_KA_RESTORER #define __ARCH_HAS_SA_RESTORER diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S index d58940280f8d..a269ad2fe6df 100644 --- a/arch/sparc/kernel/entry.S +++ b/arch/sparc/kernel/entry.S @@ -994,7 +994,7 @@ do_syscall: andcc %l5, _TIF_SYSCALL_TRACE, %g0 mov %i4, %o4 bne linux_syscall_trace - mov %i0, %l5 + mov %i0, %l6 2: call %l7 mov %i5, %o5 @@ -1003,16 +1003,15 @@ do_syscall: st %o0, [%sp + STACKFRAME_SZ + PT_I0] ret_sys_call: - ld [%curptr + TI_FLAGS], %l6 + ld [%curptr + TI_FLAGS], %l5 cmp %o0, -ERESTART_RESTARTBLOCK ld [%sp + STACKFRAME_SZ + PT_PSR], %g3 set PSR_C, %g2 bgeu 1f - andcc %l6, _TIF_SYSCALL_TRACE, %g0 + andcc %l5, _TIF_SYSCALL_TRACE, %g0 /* System call success, clear Carry condition code. */ andn %g3, %g2, %g3 - clr %l6 st %g3, [%sp + STACKFRAME_SZ + PT_PSR] bne linux_syscall_trace2 ld [%sp + STACKFRAME_SZ + PT_NPC], %l1 /* pc = npc */ @@ -1027,7 +1026,6 @@ ret_sys_call: sub %g0, %o0, %o0 or %g3, %g2, %g3 st %o0, [%sp + STACKFRAME_SZ + PT_I0] - mov 1, %l6 st %g3, [%sp + STACKFRAME_SZ + PT_PSR] bne linux_syscall_trace2 ld [%sp + STACKFRAME_SZ + PT_NPC], %l1 /* pc = npc */ diff --git a/arch/sparc/kernel/led.c b/arch/sparc/kernel/led.c index bd48575172c3..3a66e62eb2a0 100644 --- a/arch/sparc/kernel/led.c +++ b/arch/sparc/kernel/led.c @@ -50,6 +50,7 @@ static void led_blink(struct timer_list *unused) add_timer(&led_blink_timer); } +#ifdef CONFIG_PROC_FS static int led_proc_show(struct seq_file *m, void *v) { if (get_auxio() & AUXIO_LED) @@ -111,6 +112,7 @@ static const struct proc_ops led_proc_ops = { .proc_release = single_release, .proc_write = led_proc_write, }; +#endif static struct proc_dir_entry *led; diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index 5d45b6d766d6..9c2b720bfd20 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -552,9 +552,8 @@ static void pci_of_scan_bus(struct pci_pbm_info *pbm, pci_info(bus, "scan_bus[%pOF] bus no %d\n", node, bus->number); - child = NULL; prev_devfn = -1; - while ((child = of_get_next_child(node, child)) != NULL) { + for_each_child_of_node(node, child) { if (ofpci_verbose) pci_info(bus, " * %pOF\n", child); reg = of_get_property(child, "reg", ®len); diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index a02363735915..7649b14d69f8 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -183,7 +183,7 @@ void exit_thread(struct task_struct *tsk) #ifndef CONFIG_SMP if (last_task_used_math == tsk) { #else - if (test_ti_thread_flag(task_thread_info(tsk), TIF_USEDFPU)) { + if (test_tsk_thread_flag(tsk, TIF_USEDFPU)) { #endif /* Keep process from leaving FPU in a bogon state. */ put_psr(get_psr() | PSR_EF); diff --git a/arch/sparc/kernel/rtrap_32.S b/arch/sparc/kernel/rtrap_32.S index dca8ed810046..8931fe266346 100644 --- a/arch/sparc/kernel/rtrap_32.S +++ b/arch/sparc/kernel/rtrap_32.S @@ -75,7 +75,7 @@ signal_p: ld [%sp + STACKFRAME_SZ + PT_PSR], %t_psr mov %g2, %o2 - mov %l5, %o1 + mov %l6, %o1 call do_notify_resume add %sp, STACKFRAME_SZ, %o0 ! pt_regs ptr diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index 11cf2281b581..02f3ad55dfe3 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -400,8 +400,8 @@ static int setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs, else { regs->u_regs[UREG_I7] = (unsigned long)(&(sf->insns[0]) - 2); - /* mov __NR_sigreturn, %g1 */ - err |= __put_user(0x821020d8, &sf->insns[0]); + /* mov __NR_rt_sigreturn, %g1 */ + err |= __put_user(0x82102065, &sf->insns[0]); /* t 0x10 */ err |= __put_user(0x91d02010, &sf->insns[1]); diff --git a/arch/sparc/kernel/viohs.c b/arch/sparc/kernel/viohs.c index 7db5aabe9708..e27afd233bf5 100644 --- a/arch/sparc/kernel/viohs.c +++ b/arch/sparc/kernel/viohs.c @@ -428,7 +428,7 @@ static int process_dreg_info(struct vio_driver_state *vio, struct vio_dring_register *pkt) { struct vio_dring_state *dr; - int i, len; + int i; viodbg(HS, "GOT DRING_REG INFO ident[%llx] " "ndesc[%u] dsz[%u] opt[0x%x] ncookies[%u]\n", @@ -482,9 +482,7 @@ static int process_dreg_info(struct vio_driver_state *vio, pkt->num_descr, pkt->descr_size, pkt->options, pkt->num_cookies); - len = (sizeof(*pkt) + - (dr->ncookies * sizeof(struct ldc_trans_cookie))); - if (send_ctrl(vio, &pkt->tag, len) < 0) + if (send_ctrl(vio, &pkt->tag, struct_size(pkt, cookies, dr->ncookies)) < 0) goto send_nack; vio->dr_state |= VIO_DR_STATE_RXREG; diff --git a/arch/sparc/lib/memset.S b/arch/sparc/lib/memset.S index b89d42b29e34..f427f34b8b79 100644 --- a/arch/sparc/lib/memset.S +++ b/arch/sparc/lib/memset.S @@ -142,6 +142,7 @@ __bzero: ZERO_LAST_BLOCKS(%o0, 0x48, %g2) ZERO_LAST_BLOCKS(%o0, 0x08, %g2) 13: + EXT(12b, 13b, 21f) be 8f andcc %o1, 4, %g0 diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index eb2946b1df8a..6139c5700ccc 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -197,6 +197,9 @@ unsigned long __init bootmem_init(unsigned long *pages_avail) size = memblock_phys_mem_size() - memblock_reserved_size(); *pages_avail = (size >> PAGE_SHIFT) - high_pages; + /* Only allow low memory to be allocated via memblock allocation */ + memblock_set_current_limit(max_low_pfn << PAGE_SHIFT); + return max_pfn; } diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index a03caa5f6628..a9aa6a92c7fe 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -351,7 +351,7 @@ pgtable_t pte_alloc_one(struct mm_struct *mm) pte_t *ptep; struct page *page; - if ((ptep = pte_alloc_one_kernel(mm)) == 0) + if (!(ptep = pte_alloc_one_kernel(mm))) return NULL; page = pfn_to_page(__nocache_pa((unsigned long)ptep) >> PAGE_SHIFT); spin_lock(&mm->page_table_lock); @@ -689,7 +689,7 @@ static void __init srmmu_early_allocate_ptable_skeleton(unsigned long start, pgdp = pgd_offset_k(start); p4dp = p4d_offset(pgdp, start); pudp = pud_offset(p4dp, start); - if (pud_none(*(pud_t *)__nocache_fix(pudp))) { + if (pud_none(*__nocache_fix(pudp))) { pmdp = __srmmu_get_nocache( SRMMU_PMD_TABLE_SIZE, SRMMU_PMD_TABLE_SIZE); if (pmdp == NULL) @@ -698,7 +698,7 @@ static void __init srmmu_early_allocate_ptable_skeleton(unsigned long start, pud_set(__nocache_fix(pudp), pmdp); } pmdp = pmd_offset(__nocache_fix(pudp), start); - if (srmmu_pmd_none(*(pmd_t *)__nocache_fix(pmdp))) { + if (srmmu_pmd_none(*__nocache_fix(pmdp))) { ptep = __srmmu_get_nocache(PTE_SIZE, PTE_SIZE); if (ptep == NULL) early_pgtable_allocfail("pte"); @@ -810,11 +810,11 @@ static void __init srmmu_inherit_prom_mappings(unsigned long start, p4dp = p4d_offset(pgdp, start); pudp = pud_offset(p4dp, start); if (what == 2) { - *(pgd_t *)__nocache_fix(pgdp) = __pgd(probed); + *__nocache_fix(pgdp) = __pgd(probed); start += PGDIR_SIZE; continue; } - if (pud_none(*(pud_t *)__nocache_fix(pudp))) { + if (pud_none(*__nocache_fix(pudp))) { pmdp = __srmmu_get_nocache(SRMMU_PMD_TABLE_SIZE, SRMMU_PMD_TABLE_SIZE); if (pmdp == NULL) @@ -822,13 +822,13 @@ static void __init srmmu_inherit_prom_mappings(unsigned long start, memset(__nocache_fix(pmdp), 0, SRMMU_PMD_TABLE_SIZE); pud_set(__nocache_fix(pudp), pmdp); } - pmdp = pmd_offset(__nocache_fix(pgdp), start); + pmdp = pmd_offset(__nocache_fix(pudp), start); if (what == 1) { *(pmd_t *)__nocache_fix(pmdp) = __pmd(probed); start += PMD_SIZE; continue; } - if (srmmu_pmd_none(*(pmd_t *)__nocache_fix(pmdp))) { + if (srmmu_pmd_none(*__nocache_fix(pmdp))) { ptep = __srmmu_get_nocache(PTE_SIZE, PTE_SIZE); if (ptep == NULL) early_pgtable_allocfail("pte"); @@ -836,7 +836,7 @@ static void __init srmmu_inherit_prom_mappings(unsigned long start, pmd_set(__nocache_fix(pmdp), ptep); } ptep = pte_offset_kernel(__nocache_fix(pmdp), start); - *(pte_t *)__nocache_fix(ptep) = __pte(probed); + *__nocache_fix(ptep) = __pte(probed); start += PAGE_SIZE; } } @@ -850,7 +850,7 @@ static void __init do_large_mapping(unsigned long vaddr, unsigned long phys_base unsigned long big_pte; big_pte = KERNEL_PTE(phys_base >> 4); - *(pgd_t *)__nocache_fix(pgdp) = __pgd(big_pte); + *__nocache_fix(pgdp) = __pgd(big_pte); } /* Map sp_bank entry SP_ENTRY, starting at virtual address VBASE. */ @@ -940,7 +940,7 @@ void __init srmmu_paging_init(void) srmmu_ctx_table_phys = (ctxd_t *)__nocache_pa(srmmu_context_table); for (i = 0; i < num_contexts; i++) - srmmu_ctxd_set((ctxd_t *)__nocache_fix(&srmmu_context_table[i]), srmmu_swapper_pg_dir); + srmmu_ctxd_set(__nocache_fix(&srmmu_context_table[i]), srmmu_swapper_pg_dir); flush_cache_all(); srmmu_set_ctable_ptr((unsigned long)srmmu_ctx_table_phys); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 595193bc2d31..792517c078c5 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -97,6 +97,8 @@ config X86 select ARCH_SUPPORTS_DEBUG_PAGEALLOC select ARCH_SUPPORTS_NUMA_BALANCING if X86_64 select ARCH_SUPPORTS_KMAP_LOCAL_FORCE_MAP if NR_CPUS <= 4096 + select ARCH_SUPPORTS_LTO_CLANG if X86_64 + select ARCH_SUPPORTS_LTO_CLANG_THIN if X86_64 select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS @@ -169,6 +171,7 @@ config X86 select HAVE_CONTEXT_TRACKING if X86_64 select HAVE_CONTEXT_TRACKING_OFFSTACK if HAVE_CONTEXT_TRACKING select HAVE_C_RECORDMCOUNT + select HAVE_OBJTOOL_MCOUNT if STACK_VALIDATION select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE diff --git a/arch/x86/Makefile b/arch/x86/Makefile index b797f1561943..2d6d5a28c3bf 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -169,6 +169,11 @@ ifeq ($(ACCUMULATE_OUTGOING_ARGS), 1) KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args,) endif +ifdef CONFIG_LTO_CLANG +KBUILD_LDFLAGS += -plugin-opt=-code-model=kernel \ + -plugin-opt=-stack-alignment=$(if $(CONFIG_X86_32),4,8) +endif + # Workaround for a gcc prelease that unfortunately was shipped in a suse release KBUILD_CFLAGS += -Wno-sign-compare # diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 02e3e42f380b..05c4abc2fdfd 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -91,7 +91,7 @@ ifneq ($(RETPOLINE_VDSO_CFLAGS),) endif endif -$(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL) +$(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL) # # vDSO code runs in userspace and -pg doesn't help with profiling anyway. @@ -150,6 +150,7 @@ KBUILD_CFLAGS_32 := $(filter-out -fno-pic,$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out -mfentry,$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS_32)) +KBUILD_CFLAGS_32 := $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic KBUILD_CFLAGS_32 += -fno-stack-protector KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls) diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile index 3ff80156f21a..379777572bc9 100644 --- a/arch/x86/power/Makefile +++ b/arch/x86/power/Makefile @@ -4,5 +4,9 @@ # itself be stack-protected CFLAGS_cpu.o := -fno-stack-protector +# Clang may incorrectly inline functions with stack protector enabled into +# __restore_processor_state(): https://bugs.llvm.org/show_bug.cgi?id=47479 +CFLAGS_REMOVE_cpu.o := $(CC_FLAGS_LTO) + obj-$(CONFIG_PM_SLEEP) += cpu.o obj-$(CONFIG_HIBERNATION) += hibernate_$(BITS).o hibernate_asm_$(BITS).o hibernate.o diff --git a/certs/blacklist.c b/certs/blacklist.c index 6514f9ebc943..bffe4c6f4a9e 100644 --- a/certs/blacklist.c +++ b/certs/blacklist.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include "blacklist.h" @@ -37,7 +38,7 @@ static int blacklist_vet_description(const char *desc) found_colon: desc++; for (; *desc; desc++) { - if (!isxdigit(*desc)) + if (!isxdigit(*desc) || isupper(*desc)) return -EINVAL; n++; } @@ -78,7 +79,7 @@ static struct key_type key_type_blacklist = { /** * mark_hash_blacklisted - Add a hash to the system blacklist - * @hash - The hash as a hex string with a type prefix (eg. "tbs:23aa429783") + * @hash: The hash as a hex string with a type prefix (eg. "tbs:23aa429783") */ int mark_hash_blacklisted(const char *hash) { @@ -156,13 +157,12 @@ static int __init blacklist_init(void) blacklist_keyring = keyring_alloc(".blacklist", - KUIDT_INIT(0), KGIDT_INIT(0), - current_cred(), + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, current_cred(), (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ | KEY_USR_SEARCH, KEY_ALLOC_NOT_IN_QUOTA | - KEY_FLAG_KEEP, + KEY_ALLOC_SET_KEEP, NULL, NULL); if (IS_ERR(blacklist_keyring)) panic("Can't allocate system blacklist keyring\n"); diff --git a/certs/system_keyring.c b/certs/system_keyring.c index 798291177186..4b693da488f1 100644 --- a/certs/system_keyring.c +++ b/certs/system_keyring.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -98,7 +99,7 @@ static __init int system_trusted_keyring_init(void) builtin_trusted_keys = keyring_alloc(".builtin_trusted_keys", - KUIDT_INIT(0), KGIDT_INIT(0), current_cred(), + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, current_cred(), ((KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ | KEY_USR_SEARCH), KEY_ALLOC_NOT_IN_QUOTA, @@ -109,7 +110,7 @@ static __init int system_trusted_keyring_init(void) #ifdef CONFIG_SECONDARY_TRUSTED_KEYRING secondary_trusted_keys = keyring_alloc(".secondary_trusted_keys", - KUIDT_INIT(0), KGIDT_INIT(0), current_cred(), + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, current_cred(), ((KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ | KEY_USR_SEARCH | KEY_USR_WRITE), diff --git a/crypto/asymmetric_keys/asymmetric_type.c b/crypto/asymmetric_keys/asymmetric_type.c index 33e77d846caa..ad8af3d70ac0 100644 --- a/crypto/asymmetric_keys/asymmetric_type.c +++ b/crypto/asymmetric_keys/asymmetric_type.c @@ -152,7 +152,8 @@ EXPORT_SYMBOL_GPL(asymmetric_key_generate_id); /** * asymmetric_key_id_same - Return true if two asymmetric keys IDs are the same. - * @kid_1, @kid_2: The key IDs to compare + * @kid1: The key ID to compare + * @kid2: The key ID to compare */ bool asymmetric_key_id_same(const struct asymmetric_key_id *kid1, const struct asymmetric_key_id *kid2) @@ -168,7 +169,8 @@ EXPORT_SYMBOL_GPL(asymmetric_key_id_same); /** * asymmetric_key_id_partial - Return true if two asymmetric keys IDs * partially match - * @kid_1, @kid_2: The key IDs to compare + * @kid1: The key ID to compare + * @kid2: The key ID to compare */ bool asymmetric_key_id_partial(const struct asymmetric_key_id *kid1, const struct asymmetric_key_id *kid2) diff --git a/crypto/asymmetric_keys/pkcs7_parser.h b/crypto/asymmetric_keys/pkcs7_parser.h index 6565fdc2d4ca..e17f7ce4fb43 100644 --- a/crypto/asymmetric_keys/pkcs7_parser.h +++ b/crypto/asymmetric_keys/pkcs7_parser.h @@ -41,10 +41,9 @@ struct pkcs7_signed_info { * * This contains the generated digest of _either_ the Content Data or * the Authenticated Attributes [RFC2315 9.3]. If the latter, one of - * the attributes contains the digest of the the Content Data within - * it. + * the attributes contains the digest of the Content Data within it. * - * THis also contains the issuing cert serial number and issuer's name + * This also contains the issuing cert serial number and issuer's name * [PKCS#7 or CMS ver 1] or issuing cert's SKID [CMS ver 3]. */ struct public_key_signature *sig; diff --git a/crypto/asymmetric_keys/pkcs7_trust.c b/crypto/asymmetric_keys/pkcs7_trust.c index 61af3c4d82cc..b531df2013c4 100644 --- a/crypto/asymmetric_keys/pkcs7_trust.c +++ b/crypto/asymmetric_keys/pkcs7_trust.c @@ -16,7 +16,7 @@ #include #include "pkcs7_parser.h" -/** +/* * Check the trust on one PKCS#7 SignedInfo block. */ static int pkcs7_validate_trust_one(struct pkcs7_message *pkcs7, diff --git a/crypto/asymmetric_keys/pkcs7_verify.c b/crypto/asymmetric_keys/pkcs7_verify.c index ce49820caa97..0b4d07aa8811 100644 --- a/crypto/asymmetric_keys/pkcs7_verify.c +++ b/crypto/asymmetric_keys/pkcs7_verify.c @@ -141,11 +141,10 @@ int pkcs7_get_digest(struct pkcs7_message *pkcs7, const u8 **buf, u32 *len, *buf = sinfo->sig->digest; *len = sinfo->sig->digest_size; - for (i = 0; i < HASH_ALGO__LAST; i++) - if (!strcmp(hash_algo_name[i], sinfo->sig->hash_algo)) { - *hash_algo = i; - break; - } + i = match_string(hash_algo_name, HASH_ALGO__LAST, + sinfo->sig->hash_algo); + if (i >= 0) + *hash_algo = i; return 0; } diff --git a/drivers/Kconfig b/drivers/Kconfig index dcecc9f6e33f..62c753a73651 100644 --- a/drivers/Kconfig +++ b/drivers/Kconfig @@ -6,6 +6,7 @@ menu "Device Drivers" source "drivers/amba/Kconfig" source "drivers/eisa/Kconfig" source "drivers/pci/Kconfig" +source "drivers/cxl/Kconfig" source "drivers/pcmcia/Kconfig" source "drivers/rapidio/Kconfig" diff --git a/drivers/Makefile b/drivers/Makefile index fd11b9ac4cc3..678ea810410f 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -73,6 +73,7 @@ obj-$(CONFIG_NVM) += lightnvm/ obj-y += base/ block/ misc/ mfd/ nfc/ obj-$(CONFIG_LIBNVDIMM) += nvdimm/ obj-$(CONFIG_DAX) += dax/ +obj-$(CONFIG_CXL_BUS) += cxl/ obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/ obj-$(CONFIG_NUBUS) += nubus/ obj-y += macintosh/ diff --git a/drivers/cxl/Kconfig b/drivers/cxl/Kconfig new file mode 100644 index 000000000000..97dc4d751651 --- /dev/null +++ b/drivers/cxl/Kconfig @@ -0,0 +1,53 @@ +# SPDX-License-Identifier: GPL-2.0-only +menuconfig CXL_BUS + tristate "CXL (Compute Express Link) Devices Support" + depends on PCI + help + CXL is a bus that is electrically compatible with PCI Express, but + layers three protocols on that signalling (CXL.io, CXL.cache, and + CXL.mem). The CXL.cache protocol allows devices to hold cachelines + locally, the CXL.mem protocol allows devices to be fully coherent + memory targets, the CXL.io protocol is equivalent to PCI Express. + Say 'y' to enable support for the configuration and management of + devices supporting these protocols. + +if CXL_BUS + +config CXL_MEM + tristate "CXL.mem: Memory Devices" + help + The CXL.mem protocol allows a device to act as a provider of + "System RAM" and/or "Persistent Memory" that is fully coherent + as if the memory was attached to the typical CPU memory + controller. + + Say 'y/m' to enable a driver (named "cxl_mem.ko" when built as + a module) that will attach to CXL.mem devices for + configuration, provisioning, and health monitoring. This + driver is required for dynamic provisioning of CXL.mem + attached memory which is a prerequisite for persistent memory + support. Typically volatile memory is mapped by platform + firmware and included in the platform memory map, but in some + cases the OS is responsible for mapping that memory. See + Chapter 2.3 Type 3 CXL Device in the CXL 2.0 specification. + + If unsure say 'm'. + +config CXL_MEM_RAW_COMMANDS + bool "RAW Command Interface for Memory Devices" + depends on CXL_MEM + help + Enable CXL RAW command interface. + + The CXL driver ioctl interface may assign a kernel ioctl command + number for each specification defined opcode. At any given point in + time the number of opcodes that the specification defines and a device + may implement may exceed the kernel's set of associated ioctl function + numbers. The mismatch is either by omission, specification is too new, + or by design. When prototyping new hardware, or developing / debugging + the driver it is useful to be able to submit any possible command to + the hardware, even commands that may crash the kernel due to their + potential impact to memory currently in use by the kernel. + + If developing CXL hardware or the driver say Y, otherwise say N. +endif diff --git a/drivers/cxl/Makefile b/drivers/cxl/Makefile new file mode 100644 index 000000000000..a314a1891f4d --- /dev/null +++ b/drivers/cxl/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_CXL_BUS) += cxl_bus.o +obj-$(CONFIG_CXL_MEM) += cxl_mem.o + +ccflags-y += -DDEFAULT_SYMBOL_NAMESPACE=CXL +cxl_bus-y := bus.o +cxl_mem-y := mem.o diff --git a/drivers/cxl/bus.c b/drivers/cxl/bus.c new file mode 100644 index 000000000000..58f74796d525 --- /dev/null +++ b/drivers/cxl/bus.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2020 Intel Corporation. All rights reserved. */ +#include +#include + +/** + * DOC: cxl bus + * + * The CXL bus provides namespace for control devices and a rendezvous + * point for cross-device interleave coordination. + */ +struct bus_type cxl_bus_type = { + .name = "cxl", +}; +EXPORT_SYMBOL_GPL(cxl_bus_type); + +static __init int cxl_bus_init(void) +{ + return bus_register(&cxl_bus_type); +} + +static void cxl_bus_exit(void) +{ + bus_unregister(&cxl_bus_type); +} + +module_init(cxl_bus_init); +module_exit(cxl_bus_exit); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h new file mode 100644 index 000000000000..6f14838c2d25 --- /dev/null +++ b/drivers/cxl/cxl.h @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright(c) 2020 Intel Corporation. */ + +#ifndef __CXL_H__ +#define __CXL_H__ + +#include +#include +#include + +/* CXL 2.0 8.2.8.1 Device Capabilities Array Register */ +#define CXLDEV_CAP_ARRAY_OFFSET 0x0 +#define CXLDEV_CAP_ARRAY_CAP_ID 0 +#define CXLDEV_CAP_ARRAY_ID_MASK GENMASK_ULL(15, 0) +#define CXLDEV_CAP_ARRAY_COUNT_MASK GENMASK_ULL(47, 32) +/* CXL 2.0 8.2.8.2 CXL Device Capability Header Register */ +#define CXLDEV_CAP_HDR_CAP_ID_MASK GENMASK(15, 0) +/* CXL 2.0 8.2.8.2.1 CXL Device Capabilities */ +#define CXLDEV_CAP_CAP_ID_DEVICE_STATUS 0x1 +#define CXLDEV_CAP_CAP_ID_PRIMARY_MAILBOX 0x2 +#define CXLDEV_CAP_CAP_ID_SECONDARY_MAILBOX 0x3 +#define CXLDEV_CAP_CAP_ID_MEMDEV 0x4000 + +/* CXL 2.0 8.2.8.4 Mailbox Registers */ +#define CXLDEV_MBOX_CAPS_OFFSET 0x00 +#define CXLDEV_MBOX_CAP_PAYLOAD_SIZE_MASK GENMASK(4, 0) +#define CXLDEV_MBOX_CTRL_OFFSET 0x04 +#define CXLDEV_MBOX_CTRL_DOORBELL BIT(0) +#define CXLDEV_MBOX_CMD_OFFSET 0x08 +#define CXLDEV_MBOX_CMD_COMMAND_OPCODE_MASK GENMASK_ULL(15, 0) +#define CXLDEV_MBOX_CMD_PAYLOAD_LENGTH_MASK GENMASK_ULL(36, 16) +#define CXLDEV_MBOX_STATUS_OFFSET 0x10 +#define CXLDEV_MBOX_STATUS_RET_CODE_MASK GENMASK_ULL(47, 32) +#define CXLDEV_MBOX_BG_CMD_STATUS_OFFSET 0x18 +#define CXLDEV_MBOX_PAYLOAD_OFFSET 0x20 + +/* CXL 2.0 8.2.8.5.1.1 Memory Device Status Register */ +#define CXLMDEV_STATUS_OFFSET 0x0 +#define CXLMDEV_DEV_FATAL BIT(0) +#define CXLMDEV_FW_HALT BIT(1) +#define CXLMDEV_STATUS_MEDIA_STATUS_MASK GENMASK(3, 2) +#define CXLMDEV_MS_NOT_READY 0 +#define CXLMDEV_MS_READY 1 +#define CXLMDEV_MS_ERROR 2 +#define CXLMDEV_MS_DISABLED 3 +#define CXLMDEV_READY(status) \ + (FIELD_GET(CXLMDEV_STATUS_MEDIA_STATUS_MASK, status) == \ + CXLMDEV_MS_READY) +#define CXLMDEV_MBOX_IF_READY BIT(4) +#define CXLMDEV_RESET_NEEDED_MASK GENMASK(7, 5) +#define CXLMDEV_RESET_NEEDED_NOT 0 +#define CXLMDEV_RESET_NEEDED_COLD 1 +#define CXLMDEV_RESET_NEEDED_WARM 2 +#define CXLMDEV_RESET_NEEDED_HOT 3 +#define CXLMDEV_RESET_NEEDED_CXL 4 +#define CXLMDEV_RESET_NEEDED(status) \ + (FIELD_GET(CXLMDEV_RESET_NEEDED_MASK, status) != \ + CXLMDEV_RESET_NEEDED_NOT) + +struct cxl_memdev; +/** + * struct cxl_mem - A CXL memory device + * @pdev: The PCI device associated with this CXL device. + * @regs: IO mappings to the device's MMIO + * @status_regs: CXL 2.0 8.2.8.3 Device Status Registers + * @mbox_regs: CXL 2.0 8.2.8.4 Mailbox Registers + * @memdev_regs: CXL 2.0 8.2.8.5 Memory Device Registers + * @payload_size: Size of space for payload + * (CXL 2.0 8.2.8.4.3 Mailbox Capabilities Register) + * @mbox_mutex: Mutex to synchronize mailbox access. + * @firmware_version: Firmware version for the memory device. + * @enabled_commands: Hardware commands found enabled in CEL. + * @pmem_range: Persistent memory capacity information. + * @ram_range: Volatile memory capacity information. + */ +struct cxl_mem { + struct pci_dev *pdev; + void __iomem *regs; + struct cxl_memdev *cxlmd; + + void __iomem *status_regs; + void __iomem *mbox_regs; + void __iomem *memdev_regs; + + size_t payload_size; + struct mutex mbox_mutex; /* Protects device mailbox and firmware */ + char firmware_version[0x10]; + unsigned long *enabled_cmds; + + struct range pmem_range; + struct range ram_range; +}; + +extern struct bus_type cxl_bus_type; +#endif /* __CXL_H__ */ diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c new file mode 100644 index 000000000000..244cb7d89678 --- /dev/null +++ b/drivers/cxl/mem.c @@ -0,0 +1,1552 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2020 Intel Corporation. All rights reserved. */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "pci.h" +#include "cxl.h" + +/** + * DOC: cxl mem + * + * This implements a CXL memory device ("type-3") as it is defined by the + * Compute Express Link specification. + * + * The driver has several responsibilities, mainly: + * - Create the memX device and register on the CXL bus. + * - Enumerate device's register interface and map them. + * - Probe the device attributes to establish sysfs interface. + * - Provide an IOCTL interface to userspace to communicate with the device for + * things like firmware update. + * - Support management of interleave sets. + * - Handle and manage error conditions. + */ + +/* + * An entire PCI topology full of devices should be enough for any + * config + */ +#define CXL_MEM_MAX_DEVS 65536 + +#define cxl_doorbell_busy(cxlm) \ + (readl((cxlm)->mbox_regs + CXLDEV_MBOX_CTRL_OFFSET) & \ + CXLDEV_MBOX_CTRL_DOORBELL) + +/* CXL 2.0 - 8.2.8.4 */ +#define CXL_MAILBOX_TIMEOUT_MS (2 * HZ) + +enum opcode { + CXL_MBOX_OP_INVALID = 0x0000, + CXL_MBOX_OP_RAW = CXL_MBOX_OP_INVALID, + CXL_MBOX_OP_GET_FW_INFO = 0x0200, + CXL_MBOX_OP_ACTIVATE_FW = 0x0202, + CXL_MBOX_OP_GET_SUPPORTED_LOGS = 0x0400, + CXL_MBOX_OP_GET_LOG = 0x0401, + CXL_MBOX_OP_IDENTIFY = 0x4000, + CXL_MBOX_OP_GET_PARTITION_INFO = 0x4100, + CXL_MBOX_OP_SET_PARTITION_INFO = 0x4101, + CXL_MBOX_OP_GET_LSA = 0x4102, + CXL_MBOX_OP_SET_LSA = 0x4103, + CXL_MBOX_OP_GET_HEALTH_INFO = 0x4200, + CXL_MBOX_OP_SET_SHUTDOWN_STATE = 0x4204, + CXL_MBOX_OP_SCAN_MEDIA = 0x4304, + CXL_MBOX_OP_GET_SCAN_MEDIA = 0x4305, + CXL_MBOX_OP_MAX = 0x10000 +}; + +/** + * struct mbox_cmd - A command to be submitted to hardware. + * @opcode: (input) The command set and command submitted to hardware. + * @payload_in: (input) Pointer to the input payload. + * @payload_out: (output) Pointer to the output payload. Must be allocated by + * the caller. + * @size_in: (input) Number of bytes to load from @payload_in. + * @size_out: (input) Max number of bytes loaded into @payload_out. + * (output) Number of bytes generated by the device. For fixed size + * outputs commands this is always expected to be deterministic. For + * variable sized output commands, it tells the exact number of bytes + * written. + * @return_code: (output) Error code returned from hardware. + * + * This is the primary mechanism used to send commands to the hardware. + * All the fields except @payload_* correspond exactly to the fields described in + * Command Register section of the CXL 2.0 8.2.8.4.5. @payload_in and + * @payload_out are written to, and read from the Command Payload Registers + * defined in CXL 2.0 8.2.8.4.8. + */ +struct mbox_cmd { + u16 opcode; + void *payload_in; + void *payload_out; + size_t size_in; + size_t size_out; + u16 return_code; +#define CXL_MBOX_SUCCESS 0 +}; + +/** + * struct cxl_memdev - CXL bus object representing a Type-3 Memory Device + * @dev: driver core device object + * @cdev: char dev core object for ioctl operations + * @cxlm: pointer to the parent device driver data + * @ops_active: active user of @cxlm in ops handlers + * @ops_dead: completion when all @cxlm ops users have exited + * @id: id number of this memdev instance. + */ +struct cxl_memdev { + struct device dev; + struct cdev cdev; + struct cxl_mem *cxlm; + struct percpu_ref ops_active; + struct completion ops_dead; + int id; +}; + +static int cxl_mem_major; +static DEFINE_IDA(cxl_memdev_ida); +static struct dentry *cxl_debugfs; +static bool cxl_raw_allow_all; + +enum { + CEL_UUID, + VENDOR_DEBUG_UUID, +}; + +/* See CXL 2.0 Table 170. Get Log Input Payload */ +static const uuid_t log_uuid[] = { + [CEL_UUID] = UUID_INIT(0xda9c0b5, 0xbf41, 0x4b78, 0x8f, 0x79, 0x96, + 0xb1, 0x62, 0x3b, 0x3f, 0x17), + [VENDOR_DEBUG_UUID] = UUID_INIT(0xe1819d9, 0x11a9, 0x400c, 0x81, 0x1f, + 0xd6, 0x07, 0x19, 0x40, 0x3d, 0x86), +}; + +/** + * struct cxl_mem_command - Driver representation of a memory device command + * @info: Command information as it exists for the UAPI + * @opcode: The actual bits used for the mailbox protocol + * @flags: Set of flags effecting driver behavior. + * + * * %CXL_CMD_FLAG_FORCE_ENABLE: In cases of error, commands with this flag + * will be enabled by the driver regardless of what hardware may have + * advertised. + * + * The cxl_mem_command is the driver's internal representation of commands that + * are supported by the driver. Some of these commands may not be supported by + * the hardware. The driver will use @info to validate the fields passed in by + * the user then submit the @opcode to the hardware. + * + * See struct cxl_command_info. + */ +struct cxl_mem_command { + struct cxl_command_info info; + enum opcode opcode; + u32 flags; +#define CXL_CMD_FLAG_NONE 0 +#define CXL_CMD_FLAG_FORCE_ENABLE BIT(0) +}; + +#define CXL_CMD(_id, sin, sout, _flags) \ + [CXL_MEM_COMMAND_ID_##_id] = { \ + .info = { \ + .id = CXL_MEM_COMMAND_ID_##_id, \ + .size_in = sin, \ + .size_out = sout, \ + }, \ + .opcode = CXL_MBOX_OP_##_id, \ + .flags = _flags, \ + } + +/* + * This table defines the supported mailbox commands for the driver. This table + * is made up of a UAPI structure. Non-negative values as parameters in the + * table will be validated against the user's input. For example, if size_in is + * 0, and the user passed in 1, it is an error. + */ +static struct cxl_mem_command mem_commands[] = { + CXL_CMD(IDENTIFY, 0, 0x43, CXL_CMD_FLAG_FORCE_ENABLE), +#ifdef CONFIG_CXL_MEM_RAW_COMMANDS + CXL_CMD(RAW, ~0, ~0, 0), +#endif + CXL_CMD(GET_SUPPORTED_LOGS, 0, ~0, CXL_CMD_FLAG_FORCE_ENABLE), + CXL_CMD(GET_FW_INFO, 0, 0x50, 0), + CXL_CMD(GET_PARTITION_INFO, 0, 0x20, 0), + CXL_CMD(GET_LSA, 0x8, ~0, 0), + CXL_CMD(GET_HEALTH_INFO, 0, 0x12, 0), + CXL_CMD(GET_LOG, 0x18, ~0, CXL_CMD_FLAG_FORCE_ENABLE), +}; + +/* + * Commands that RAW doesn't permit. The rationale for each: + * + * CXL_MBOX_OP_ACTIVATE_FW: Firmware activation requires adjustment / + * coordination of transaction timeout values at the root bridge level. + * + * CXL_MBOX_OP_SET_PARTITION_INFO: The device memory map may change live + * and needs to be coordinated with HDM updates. + * + * CXL_MBOX_OP_SET_LSA: The label storage area may be cached by the + * driver and any writes from userspace invalidates those contents. + * + * CXL_MBOX_OP_SET_SHUTDOWN_STATE: Set shutdown state assumes no writes + * to the device after it is marked clean, userspace can not make that + * assertion. + * + * CXL_MBOX_OP_[GET_]SCAN_MEDIA: The kernel provides a native error list that + * is kept up to date with patrol notifications and error management. + */ +static u16 cxl_disabled_raw_commands[] = { + CXL_MBOX_OP_ACTIVATE_FW, + CXL_MBOX_OP_SET_PARTITION_INFO, + CXL_MBOX_OP_SET_LSA, + CXL_MBOX_OP_SET_SHUTDOWN_STATE, + CXL_MBOX_OP_SCAN_MEDIA, + CXL_MBOX_OP_GET_SCAN_MEDIA, +}; + +/* + * Command sets that RAW doesn't permit. All opcodes in this set are + * disabled because they pass plain text security payloads over the + * user/kernel boundary. This functionality is intended to be wrapped + * behind the keys ABI which allows for encrypted payloads in the UAPI + */ +static u8 security_command_sets[] = { + 0x44, /* Sanitize */ + 0x45, /* Persistent Memory Data-at-rest Security */ + 0x46, /* Security Passthrough */ +}; + +#define cxl_for_each_cmd(cmd) \ + for ((cmd) = &mem_commands[0]; \ + ((cmd) - mem_commands) < ARRAY_SIZE(mem_commands); (cmd)++) + +#define cxl_cmd_count ARRAY_SIZE(mem_commands) + +static int cxl_mem_wait_for_doorbell(struct cxl_mem *cxlm) +{ + const unsigned long start = jiffies; + unsigned long end = start; + + while (cxl_doorbell_busy(cxlm)) { + end = jiffies; + + if (time_after(end, start + CXL_MAILBOX_TIMEOUT_MS)) { + /* Check again in case preempted before timeout test */ + if (!cxl_doorbell_busy(cxlm)) + break; + return -ETIMEDOUT; + } + cpu_relax(); + } + + dev_dbg(&cxlm->pdev->dev, "Doorbell wait took %dms", + jiffies_to_msecs(end) - jiffies_to_msecs(start)); + return 0; +} + +static bool cxl_is_security_command(u16 opcode) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(security_command_sets); i++) + if (security_command_sets[i] == (opcode >> 8)) + return true; + return false; +} + +static void cxl_mem_mbox_timeout(struct cxl_mem *cxlm, + struct mbox_cmd *mbox_cmd) +{ + struct device *dev = &cxlm->pdev->dev; + + dev_dbg(dev, "Mailbox command (opcode: %#x size: %zub) timed out\n", + mbox_cmd->opcode, mbox_cmd->size_in); +} + +/** + * __cxl_mem_mbox_send_cmd() - Execute a mailbox command + * @cxlm: The CXL memory device to communicate with. + * @mbox_cmd: Command to send to the memory device. + * + * Context: Any context. Expects mbox_mutex to be held. + * Return: -ETIMEDOUT if timeout occurred waiting for completion. 0 on success. + * Caller should check the return code in @mbox_cmd to make sure it + * succeeded. + * + * This is a generic form of the CXL mailbox send command thus only using the + * registers defined by the mailbox capability ID - CXL 2.0 8.2.8.4. Memory + * devices, and perhaps other types of CXL devices may have further information + * available upon error conditions. Driver facilities wishing to send mailbox + * commands should use the wrapper command. + * + * The CXL spec allows for up to two mailboxes. The intention is for the primary + * mailbox to be OS controlled and the secondary mailbox to be used by system + * firmware. This allows the OS and firmware to communicate with the device and + * not need to coordinate with each other. The driver only uses the primary + * mailbox. + */ +static int __cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, + struct mbox_cmd *mbox_cmd) +{ + void __iomem *payload = cxlm->mbox_regs + CXLDEV_MBOX_PAYLOAD_OFFSET; + u64 cmd_reg, status_reg; + size_t out_len; + int rc; + + lockdep_assert_held(&cxlm->mbox_mutex); + + /* + * Here are the steps from 8.2.8.4 of the CXL 2.0 spec. + * 1. Caller reads MB Control Register to verify doorbell is clear + * 2. Caller writes Command Register + * 3. Caller writes Command Payload Registers if input payload is non-empty + * 4. Caller writes MB Control Register to set doorbell + * 5. Caller either polls for doorbell to be clear or waits for interrupt if configured + * 6. Caller reads MB Status Register to fetch Return code + * 7. If command successful, Caller reads Command Register to get Payload Length + * 8. If output payload is non-empty, host reads Command Payload Registers + * + * Hardware is free to do whatever it wants before the doorbell is rung, + * and isn't allowed to change anything after it clears the doorbell. As + * such, steps 2 and 3 can happen in any order, and steps 6, 7, 8 can + * also happen in any order (though some orders might not make sense). + */ + + /* #1 */ + if (cxl_doorbell_busy(cxlm)) { + dev_err_ratelimited(&cxlm->pdev->dev, + "Mailbox re-busy after acquiring\n"); + return -EBUSY; + } + + cmd_reg = FIELD_PREP(CXLDEV_MBOX_CMD_COMMAND_OPCODE_MASK, + mbox_cmd->opcode); + if (mbox_cmd->size_in) { + if (WARN_ON(!mbox_cmd->payload_in)) + return -EINVAL; + + cmd_reg |= FIELD_PREP(CXLDEV_MBOX_CMD_PAYLOAD_LENGTH_MASK, + mbox_cmd->size_in); + memcpy_toio(payload, mbox_cmd->payload_in, mbox_cmd->size_in); + } + + /* #2, #3 */ + writeq(cmd_reg, cxlm->mbox_regs + CXLDEV_MBOX_CMD_OFFSET); + + /* #4 */ + dev_dbg(&cxlm->pdev->dev, "Sending command\n"); + writel(CXLDEV_MBOX_CTRL_DOORBELL, + cxlm->mbox_regs + CXLDEV_MBOX_CTRL_OFFSET); + + /* #5 */ + rc = cxl_mem_wait_for_doorbell(cxlm); + if (rc == -ETIMEDOUT) { + cxl_mem_mbox_timeout(cxlm, mbox_cmd); + return rc; + } + + /* #6 */ + status_reg = readq(cxlm->mbox_regs + CXLDEV_MBOX_STATUS_OFFSET); + mbox_cmd->return_code = + FIELD_GET(CXLDEV_MBOX_STATUS_RET_CODE_MASK, status_reg); + + if (mbox_cmd->return_code != 0) { + dev_dbg(&cxlm->pdev->dev, "Mailbox operation had an error\n"); + return 0; + } + + /* #7 */ + cmd_reg = readq(cxlm->mbox_regs + CXLDEV_MBOX_CMD_OFFSET); + out_len = FIELD_GET(CXLDEV_MBOX_CMD_PAYLOAD_LENGTH_MASK, cmd_reg); + + /* #8 */ + if (out_len && mbox_cmd->payload_out) { + /* + * Sanitize the copy. If hardware misbehaves, out_len per the + * spec can actually be greater than the max allowed size (21 + * bits available but spec defined 1M max). The caller also may + * have requested less data than the hardware supplied even + * within spec. + */ + size_t n = min3(mbox_cmd->size_out, cxlm->payload_size, out_len); + + memcpy_fromio(mbox_cmd->payload_out, payload, n); + mbox_cmd->size_out = n; + } else { + mbox_cmd->size_out = 0; + } + + return 0; +} + +/** + * cxl_mem_mbox_get() - Acquire exclusive access to the mailbox. + * @cxlm: The memory device to gain access to. + * + * Context: Any context. Takes the mbox_mutex. + * Return: 0 if exclusive access was acquired. + */ +static int cxl_mem_mbox_get(struct cxl_mem *cxlm) +{ + struct device *dev = &cxlm->pdev->dev; + u64 md_status; + int rc; + + mutex_lock_io(&cxlm->mbox_mutex); + + /* + * XXX: There is some amount of ambiguity in the 2.0 version of the spec + * around the mailbox interface ready (8.2.8.5.1.1). The purpose of the + * bit is to allow firmware running on the device to notify the driver + * that it's ready to receive commands. It is unclear if the bit needs + * to be read for each transaction mailbox, ie. the firmware can switch + * it on and off as needed. Second, there is no defined timeout for + * mailbox ready, like there is for the doorbell interface. + * + * Assumptions: + * 1. The firmware might toggle the Mailbox Interface Ready bit, check + * it for every command. + * + * 2. If the doorbell is clear, the firmware should have first set the + * Mailbox Interface Ready bit. Therefore, waiting for the doorbell + * to be ready is sufficient. + */ + rc = cxl_mem_wait_for_doorbell(cxlm); + if (rc) { + dev_warn(dev, "Mailbox interface not ready\n"); + goto out; + } + + md_status = readq(cxlm->memdev_regs + CXLMDEV_STATUS_OFFSET); + if (!(md_status & CXLMDEV_MBOX_IF_READY && CXLMDEV_READY(md_status))) { + dev_err(dev, "mbox: reported doorbell ready, but not mbox ready\n"); + rc = -EBUSY; + goto out; + } + + /* + * Hardware shouldn't allow a ready status but also have failure bits + * set. Spit out an error, this should be a bug report + */ + rc = -EFAULT; + if (md_status & CXLMDEV_DEV_FATAL) { + dev_err(dev, "mbox: reported ready, but fatal\n"); + goto out; + } + if (md_status & CXLMDEV_FW_HALT) { + dev_err(dev, "mbox: reported ready, but halted\n"); + goto out; + } + if (CXLMDEV_RESET_NEEDED(md_status)) { + dev_err(dev, "mbox: reported ready, but reset needed\n"); + goto out; + } + + /* with lock held */ + return 0; + +out: + mutex_unlock(&cxlm->mbox_mutex); + return rc; +} + +/** + * cxl_mem_mbox_put() - Release exclusive access to the mailbox. + * @cxlm: The CXL memory device to communicate with. + * + * Context: Any context. Expects mbox_mutex to be held. + */ +static void cxl_mem_mbox_put(struct cxl_mem *cxlm) +{ + mutex_unlock(&cxlm->mbox_mutex); +} + +/** + * handle_mailbox_cmd_from_user() - Dispatch a mailbox command for userspace. + * @cxlm: The CXL memory device to communicate with. + * @cmd: The validated command. + * @in_payload: Pointer to userspace's input payload. + * @out_payload: Pointer to userspace's output payload. + * @size_out: (Input) Max payload size to copy out. + * (Output) Payload size hardware generated. + * @retval: Hardware generated return code from the operation. + * + * Return: + * * %0 - Mailbox transaction succeeded. This implies the mailbox + * protocol completed successfully not that the operation itself + * was successful. + * * %-ENOMEM - Couldn't allocate a bounce buffer. + * * %-EFAULT - Something happened with copy_to/from_user. + * * %-EINTR - Mailbox acquisition interrupted. + * * %-EXXX - Transaction level failures. + * + * Creates the appropriate mailbox command and dispatches it on behalf of a + * userspace request. The input and output payloads are copied between + * userspace. + * + * See cxl_send_cmd(). + */ +static int handle_mailbox_cmd_from_user(struct cxl_mem *cxlm, + const struct cxl_mem_command *cmd, + u64 in_payload, u64 out_payload, + s32 *size_out, u32 *retval) +{ + struct device *dev = &cxlm->pdev->dev; + struct mbox_cmd mbox_cmd = { + .opcode = cmd->opcode, + .size_in = cmd->info.size_in, + .size_out = cmd->info.size_out, + }; + int rc; + + if (cmd->info.size_out) { + mbox_cmd.payload_out = kvzalloc(cmd->info.size_out, GFP_KERNEL); + if (!mbox_cmd.payload_out) + return -ENOMEM; + } + + if (cmd->info.size_in) { + mbox_cmd.payload_in = vmemdup_user(u64_to_user_ptr(in_payload), + cmd->info.size_in); + if (IS_ERR(mbox_cmd.payload_in)) { + kvfree(mbox_cmd.payload_out); + return PTR_ERR(mbox_cmd.payload_in); + } + } + + rc = cxl_mem_mbox_get(cxlm); + if (rc) + goto out; + + dev_dbg(dev, + "Submitting %s command for user\n" + "\topcode: %x\n" + "\tsize: %ub\n", + cxl_command_names[cmd->info.id].name, mbox_cmd.opcode, + cmd->info.size_in); + + dev_WARN_ONCE(dev, cmd->info.id == CXL_MEM_COMMAND_ID_RAW, + "raw command path used\n"); + + rc = __cxl_mem_mbox_send_cmd(cxlm, &mbox_cmd); + cxl_mem_mbox_put(cxlm); + if (rc) + goto out; + + /* + * @size_out contains the max size that's allowed to be written back out + * to userspace. While the payload may have written more output than + * this it will have to be ignored. + */ + if (mbox_cmd.size_out) { + dev_WARN_ONCE(dev, mbox_cmd.size_out > *size_out, + "Invalid return size\n"); + if (copy_to_user(u64_to_user_ptr(out_payload), + mbox_cmd.payload_out, mbox_cmd.size_out)) { + rc = -EFAULT; + goto out; + } + } + + *size_out = mbox_cmd.size_out; + *retval = mbox_cmd.return_code; + +out: + kvfree(mbox_cmd.payload_in); + kvfree(mbox_cmd.payload_out); + return rc; +} + +static bool cxl_mem_raw_command_allowed(u16 opcode) +{ + int i; + + if (!IS_ENABLED(CONFIG_CXL_MEM_RAW_COMMANDS)) + return false; + + if (security_locked_down(LOCKDOWN_NONE)) + return false; + + if (cxl_raw_allow_all) + return true; + + if (cxl_is_security_command(opcode)) + return false; + + for (i = 0; i < ARRAY_SIZE(cxl_disabled_raw_commands); i++) + if (cxl_disabled_raw_commands[i] == opcode) + return false; + + return true; +} + +/** + * cxl_validate_cmd_from_user() - Check fields for CXL_MEM_SEND_COMMAND. + * @cxlm: &struct cxl_mem device whose mailbox will be used. + * @send_cmd: &struct cxl_send_command copied in from userspace. + * @out_cmd: Sanitized and populated &struct cxl_mem_command. + * + * Return: + * * %0 - @out_cmd is ready to send. + * * %-ENOTTY - Invalid command specified. + * * %-EINVAL - Reserved fields or invalid values were used. + * * %-ENOMEM - Input or output buffer wasn't sized properly. + * * %-EPERM - Attempted to use a protected command. + * + * The result of this command is a fully validated command in @out_cmd that is + * safe to send to the hardware. + * + * See handle_mailbox_cmd_from_user() + */ +static int cxl_validate_cmd_from_user(struct cxl_mem *cxlm, + const struct cxl_send_command *send_cmd, + struct cxl_mem_command *out_cmd) +{ + const struct cxl_command_info *info; + struct cxl_mem_command *c; + + if (send_cmd->id == 0 || send_cmd->id >= CXL_MEM_COMMAND_ID_MAX) + return -ENOTTY; + + /* + * The user can never specify an input payload larger than what hardware + * supports, but output can be arbitrarily large (simply write out as + * much data as the hardware provides). + */ + if (send_cmd->in.size > cxlm->payload_size) + return -EINVAL; + + /* + * Checks are bypassed for raw commands but a WARN/taint will occur + * later in the callchain + */ + if (send_cmd->id == CXL_MEM_COMMAND_ID_RAW) { + const struct cxl_mem_command temp = { + .info = { + .id = CXL_MEM_COMMAND_ID_RAW, + .flags = 0, + .size_in = send_cmd->in.size, + .size_out = send_cmd->out.size, + }, + .opcode = send_cmd->raw.opcode + }; + + if (send_cmd->raw.rsvd) + return -EINVAL; + + /* + * Unlike supported commands, the output size of RAW commands + * gets passed along without further checking, so it must be + * validated here. + */ + if (send_cmd->out.size > cxlm->payload_size) + return -EINVAL; + + if (!cxl_mem_raw_command_allowed(send_cmd->raw.opcode)) + return -EPERM; + + memcpy(out_cmd, &temp, sizeof(temp)); + + return 0; + } + + if (send_cmd->flags & ~CXL_MEM_COMMAND_FLAG_MASK) + return -EINVAL; + + if (send_cmd->rsvd) + return -EINVAL; + + if (send_cmd->in.rsvd || send_cmd->out.rsvd) + return -EINVAL; + + /* Convert user's command into the internal representation */ + c = &mem_commands[send_cmd->id]; + info = &c->info; + + /* Check that the command is enabled for hardware */ + if (!test_bit(info->id, cxlm->enabled_cmds)) + return -ENOTTY; + + /* Check the input buffer is the expected size */ + if (info->size_in >= 0 && info->size_in != send_cmd->in.size) + return -ENOMEM; + + /* Check the output buffer is at least large enough */ + if (info->size_out >= 0 && send_cmd->out.size < info->size_out) + return -ENOMEM; + + memcpy(out_cmd, c, sizeof(*c)); + out_cmd->info.size_in = send_cmd->in.size; + /* + * XXX: out_cmd->info.size_out will be controlled by the driver, and the + * specified number of bytes @send_cmd->out.size will be copied back out + * to userspace. + */ + + return 0; +} + +static int cxl_query_cmd(struct cxl_memdev *cxlmd, + struct cxl_mem_query_commands __user *q) +{ + struct device *dev = &cxlmd->dev; + struct cxl_mem_command *cmd; + u32 n_commands; + int j = 0; + + dev_dbg(dev, "Query IOCTL\n"); + + if (get_user(n_commands, &q->n_commands)) + return -EFAULT; + + /* returns the total number if 0 elements are requested. */ + if (n_commands == 0) + return put_user(cxl_cmd_count, &q->n_commands); + + /* + * otherwise, return max(n_commands, total commands) cxl_command_info + * structures. + */ + cxl_for_each_cmd(cmd) { + const struct cxl_command_info *info = &cmd->info; + + if (copy_to_user(&q->commands[j++], info, sizeof(*info))) + return -EFAULT; + + if (j == n_commands) + break; + } + + return 0; +} + +static int cxl_send_cmd(struct cxl_memdev *cxlmd, + struct cxl_send_command __user *s) +{ + struct cxl_mem *cxlm = cxlmd->cxlm; + struct device *dev = &cxlmd->dev; + struct cxl_send_command send; + struct cxl_mem_command c; + int rc; + + dev_dbg(dev, "Send IOCTL\n"); + + if (copy_from_user(&send, s, sizeof(send))) + return -EFAULT; + + rc = cxl_validate_cmd_from_user(cxlmd->cxlm, &send, &c); + if (rc) + return rc; + + /* Prepare to handle a full payload for variable sized output */ + if (c.info.size_out < 0) + c.info.size_out = cxlm->payload_size; + + rc = handle_mailbox_cmd_from_user(cxlm, &c, send.in.payload, + send.out.payload, &send.out.size, + &send.retval); + if (rc) + return rc; + + if (copy_to_user(s, &send, sizeof(send))) + return -EFAULT; + + return 0; +} + +static long __cxl_memdev_ioctl(struct cxl_memdev *cxlmd, unsigned int cmd, + unsigned long arg) +{ + switch (cmd) { + case CXL_MEM_QUERY_COMMANDS: + return cxl_query_cmd(cxlmd, (void __user *)arg); + case CXL_MEM_SEND_COMMAND: + return cxl_send_cmd(cxlmd, (void __user *)arg); + default: + return -ENOTTY; + } +} + +static long cxl_memdev_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct cxl_memdev *cxlmd; + struct inode *inode; + int rc = -ENOTTY; + + inode = file_inode(file); + cxlmd = container_of(inode->i_cdev, typeof(*cxlmd), cdev); + + if (!percpu_ref_tryget_live(&cxlmd->ops_active)) + return -ENXIO; + + rc = __cxl_memdev_ioctl(cxlmd, cmd, arg); + + percpu_ref_put(&cxlmd->ops_active); + + return rc; +} + +static const struct file_operations cxl_memdev_fops = { + .owner = THIS_MODULE, + .unlocked_ioctl = cxl_memdev_ioctl, + .compat_ioctl = compat_ptr_ioctl, + .llseek = noop_llseek, +}; + +static inline struct cxl_mem_command *cxl_mem_find_command(u16 opcode) +{ + struct cxl_mem_command *c; + + cxl_for_each_cmd(c) + if (c->opcode == opcode) + return c; + + return NULL; +} + +/** + * cxl_mem_mbox_send_cmd() - Send a mailbox command to a memory device. + * @cxlm: The CXL memory device to communicate with. + * @opcode: Opcode for the mailbox command. + * @in: The input payload for the mailbox command. + * @in_size: The length of the input payload + * @out: Caller allocated buffer for the output. + * @out_size: Expected size of output. + * + * Context: Any context. Will acquire and release mbox_mutex. + * Return: + * * %>=0 - Number of bytes returned in @out. + * * %-E2BIG - Payload is too large for hardware. + * * %-EBUSY - Couldn't acquire exclusive mailbox access. + * * %-EFAULT - Hardware error occurred. + * * %-ENXIO - Command completed, but device reported an error. + * * %-EIO - Unexpected output size. + * + * Mailbox commands may execute successfully yet the device itself reported an + * error. While this distinction can be useful for commands from userspace, the + * kernel will only be able to use results when both are successful. + * + * See __cxl_mem_mbox_send_cmd() + */ +static int cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, u16 opcode, + void *in, size_t in_size, + void *out, size_t out_size) +{ + const struct cxl_mem_command *cmd = cxl_mem_find_command(opcode); + struct mbox_cmd mbox_cmd = { + .opcode = opcode, + .payload_in = in, + .size_in = in_size, + .size_out = out_size, + .payload_out = out, + }; + int rc; + + if (out_size > cxlm->payload_size) + return -E2BIG; + + rc = cxl_mem_mbox_get(cxlm); + if (rc) + return rc; + + rc = __cxl_mem_mbox_send_cmd(cxlm, &mbox_cmd); + cxl_mem_mbox_put(cxlm); + if (rc) + return rc; + + /* TODO: Map return code to proper kernel style errno */ + if (mbox_cmd.return_code != CXL_MBOX_SUCCESS) + return -ENXIO; + + /* + * Variable sized commands can't be validated and so it's up to the + * caller to do that if they wish. + */ + if (cmd->info.size_out >= 0 && mbox_cmd.size_out != out_size) + return -EIO; + + return 0; +} + +/** + * cxl_mem_setup_regs() - Setup necessary MMIO. + * @cxlm: The CXL memory device to communicate with. + * + * Return: 0 if all necessary registers mapped. + * + * A memory device is required by spec to implement a certain set of MMIO + * regions. The purpose of this function is to enumerate and map those + * registers. + */ +static int cxl_mem_setup_regs(struct cxl_mem *cxlm) +{ + struct device *dev = &cxlm->pdev->dev; + int cap, cap_count; + u64 cap_array; + + cap_array = readq(cxlm->regs + CXLDEV_CAP_ARRAY_OFFSET); + if (FIELD_GET(CXLDEV_CAP_ARRAY_ID_MASK, cap_array) != + CXLDEV_CAP_ARRAY_CAP_ID) + return -ENODEV; + + cap_count = FIELD_GET(CXLDEV_CAP_ARRAY_COUNT_MASK, cap_array); + + for (cap = 1; cap <= cap_count; cap++) { + void __iomem *register_block; + u32 offset; + u16 cap_id; + + cap_id = FIELD_GET(CXLDEV_CAP_HDR_CAP_ID_MASK, + readl(cxlm->regs + cap * 0x10)); + offset = readl(cxlm->regs + cap * 0x10 + 0x4); + register_block = cxlm->regs + offset; + + switch (cap_id) { + case CXLDEV_CAP_CAP_ID_DEVICE_STATUS: + dev_dbg(dev, "found Status capability (0x%x)\n", offset); + cxlm->status_regs = register_block; + break; + case CXLDEV_CAP_CAP_ID_PRIMARY_MAILBOX: + dev_dbg(dev, "found Mailbox capability (0x%x)\n", offset); + cxlm->mbox_regs = register_block; + break; + case CXLDEV_CAP_CAP_ID_SECONDARY_MAILBOX: + dev_dbg(dev, "found Secondary Mailbox capability (0x%x)\n", offset); + break; + case CXLDEV_CAP_CAP_ID_MEMDEV: + dev_dbg(dev, "found Memory Device capability (0x%x)\n", offset); + cxlm->memdev_regs = register_block; + break; + default: + dev_dbg(dev, "Unknown cap ID: %d (0x%x)\n", cap_id, offset); + break; + } + } + + if (!cxlm->status_regs || !cxlm->mbox_regs || !cxlm->memdev_regs) { + dev_err(dev, "registers not found: %s%s%s\n", + !cxlm->status_regs ? "status " : "", + !cxlm->mbox_regs ? "mbox " : "", + !cxlm->memdev_regs ? "memdev" : ""); + return -ENXIO; + } + + return 0; +} + +static int cxl_mem_setup_mailbox(struct cxl_mem *cxlm) +{ + const int cap = readl(cxlm->mbox_regs + CXLDEV_MBOX_CAPS_OFFSET); + + cxlm->payload_size = + 1 << FIELD_GET(CXLDEV_MBOX_CAP_PAYLOAD_SIZE_MASK, cap); + + /* + * CXL 2.0 8.2.8.4.3 Mailbox Capabilities Register + * + * If the size is too small, mandatory commands will not work and so + * there's no point in going forward. If the size is too large, there's + * no harm is soft limiting it. + */ + cxlm->payload_size = min_t(size_t, cxlm->payload_size, SZ_1M); + if (cxlm->payload_size < 256) { + dev_err(&cxlm->pdev->dev, "Mailbox is too small (%zub)", + cxlm->payload_size); + return -ENXIO; + } + + dev_dbg(&cxlm->pdev->dev, "Mailbox payload sized %zu", + cxlm->payload_size); + + return 0; +} + +static struct cxl_mem *cxl_mem_create(struct pci_dev *pdev, u32 reg_lo, + u32 reg_hi) +{ + struct device *dev = &pdev->dev; + struct cxl_mem *cxlm; + void __iomem *regs; + u64 offset; + u8 bar; + int rc; + + cxlm = devm_kzalloc(&pdev->dev, sizeof(*cxlm), GFP_KERNEL); + if (!cxlm) { + dev_err(dev, "No memory available\n"); + return NULL; + } + + offset = ((u64)reg_hi << 32) | FIELD_GET(CXL_REGLOC_ADDR_MASK, reg_lo); + bar = FIELD_GET(CXL_REGLOC_BIR_MASK, reg_lo); + + /* Basic sanity check that BAR is big enough */ + if (pci_resource_len(pdev, bar) < offset) { + dev_err(dev, "BAR%d: %pr: too small (offset: %#llx)\n", bar, + &pdev->resource[bar], (unsigned long long)offset); + return NULL; + } + + rc = pcim_iomap_regions(pdev, BIT(bar), pci_name(pdev)); + if (rc) { + dev_err(dev, "failed to map registers\n"); + return NULL; + } + regs = pcim_iomap_table(pdev)[bar]; + + mutex_init(&cxlm->mbox_mutex); + cxlm->pdev = pdev; + cxlm->regs = regs + offset; + cxlm->enabled_cmds = + devm_kmalloc_array(dev, BITS_TO_LONGS(cxl_cmd_count), + sizeof(unsigned long), + GFP_KERNEL | __GFP_ZERO); + if (!cxlm->enabled_cmds) { + dev_err(dev, "No memory available for bitmap\n"); + return NULL; + } + + dev_dbg(dev, "Mapped CXL Memory Device resource\n"); + return cxlm; +} + +static int cxl_mem_dvsec(struct pci_dev *pdev, int dvsec) +{ + int pos; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DVSEC); + if (!pos) + return 0; + + while (pos) { + u16 vendor, id; + + pci_read_config_word(pdev, pos + PCI_DVSEC_HEADER1, &vendor); + pci_read_config_word(pdev, pos + PCI_DVSEC_HEADER2, &id); + if (vendor == PCI_DVSEC_VENDOR_ID_CXL && dvsec == id) + return pos; + + pos = pci_find_next_ext_capability(pdev, pos, + PCI_EXT_CAP_ID_DVSEC); + } + + return 0; +} + +static struct cxl_memdev *to_cxl_memdev(struct device *dev) +{ + return container_of(dev, struct cxl_memdev, dev); +} + +static void cxl_memdev_release(struct device *dev) +{ + struct cxl_memdev *cxlmd = to_cxl_memdev(dev); + + percpu_ref_exit(&cxlmd->ops_active); + ida_free(&cxl_memdev_ida, cxlmd->id); + kfree(cxlmd); +} + +static char *cxl_memdev_devnode(struct device *dev, umode_t *mode, kuid_t *uid, + kgid_t *gid) +{ + return kasprintf(GFP_KERNEL, "cxl/%s", dev_name(dev)); +} + +static ssize_t firmware_version_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct cxl_memdev *cxlmd = to_cxl_memdev(dev); + struct cxl_mem *cxlm = cxlmd->cxlm; + + return sprintf(buf, "%.16s\n", cxlm->firmware_version); +} +static DEVICE_ATTR_RO(firmware_version); + +static ssize_t payload_max_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct cxl_memdev *cxlmd = to_cxl_memdev(dev); + struct cxl_mem *cxlm = cxlmd->cxlm; + + return sprintf(buf, "%zu\n", cxlm->payload_size); +} +static DEVICE_ATTR_RO(payload_max); + +static ssize_t ram_size_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct cxl_memdev *cxlmd = to_cxl_memdev(dev); + struct cxl_mem *cxlm = cxlmd->cxlm; + unsigned long long len = range_len(&cxlm->ram_range); + + return sprintf(buf, "%#llx\n", len); +} + +static struct device_attribute dev_attr_ram_size = + __ATTR(size, 0444, ram_size_show, NULL); + +static ssize_t pmem_size_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct cxl_memdev *cxlmd = to_cxl_memdev(dev); + struct cxl_mem *cxlm = cxlmd->cxlm; + unsigned long long len = range_len(&cxlm->pmem_range); + + return sprintf(buf, "%#llx\n", len); +} + +static struct device_attribute dev_attr_pmem_size = + __ATTR(size, 0444, pmem_size_show, NULL); + +static struct attribute *cxl_memdev_attributes[] = { + &dev_attr_firmware_version.attr, + &dev_attr_payload_max.attr, + NULL, +}; + +static struct attribute *cxl_memdev_pmem_attributes[] = { + &dev_attr_pmem_size.attr, + NULL, +}; + +static struct attribute *cxl_memdev_ram_attributes[] = { + &dev_attr_ram_size.attr, + NULL, +}; + +static struct attribute_group cxl_memdev_attribute_group = { + .attrs = cxl_memdev_attributes, +}; + +static struct attribute_group cxl_memdev_ram_attribute_group = { + .name = "ram", + .attrs = cxl_memdev_ram_attributes, +}; + +static struct attribute_group cxl_memdev_pmem_attribute_group = { + .name = "pmem", + .attrs = cxl_memdev_pmem_attributes, +}; + +static const struct attribute_group *cxl_memdev_attribute_groups[] = { + &cxl_memdev_attribute_group, + &cxl_memdev_ram_attribute_group, + &cxl_memdev_pmem_attribute_group, + NULL, +}; + +static const struct device_type cxl_memdev_type = { + .name = "cxl_memdev", + .release = cxl_memdev_release, + .devnode = cxl_memdev_devnode, + .groups = cxl_memdev_attribute_groups, +}; + +static void cxlmdev_unregister(void *_cxlmd) +{ + struct cxl_memdev *cxlmd = _cxlmd; + struct device *dev = &cxlmd->dev; + + percpu_ref_kill(&cxlmd->ops_active); + cdev_device_del(&cxlmd->cdev, dev); + wait_for_completion(&cxlmd->ops_dead); + cxlmd->cxlm = NULL; + put_device(dev); +} + +static void cxlmdev_ops_active_release(struct percpu_ref *ref) +{ + struct cxl_memdev *cxlmd = + container_of(ref, typeof(*cxlmd), ops_active); + + complete(&cxlmd->ops_dead); +} + +static int cxl_mem_add_memdev(struct cxl_mem *cxlm) +{ + struct pci_dev *pdev = cxlm->pdev; + struct cxl_memdev *cxlmd; + struct device *dev; + struct cdev *cdev; + int rc; + + cxlmd = kzalloc(sizeof(*cxlmd), GFP_KERNEL); + if (!cxlmd) + return -ENOMEM; + init_completion(&cxlmd->ops_dead); + + /* + * @cxlm is deallocated when the driver unbinds so operations + * that are using it need to hold a live reference. + */ + cxlmd->cxlm = cxlm; + rc = percpu_ref_init(&cxlmd->ops_active, cxlmdev_ops_active_release, 0, + GFP_KERNEL); + if (rc) + goto err_ref; + + rc = ida_alloc_range(&cxl_memdev_ida, 0, CXL_MEM_MAX_DEVS, GFP_KERNEL); + if (rc < 0) + goto err_id; + cxlmd->id = rc; + + dev = &cxlmd->dev; + device_initialize(dev); + dev->parent = &pdev->dev; + dev->bus = &cxl_bus_type; + dev->devt = MKDEV(cxl_mem_major, cxlmd->id); + dev->type = &cxl_memdev_type; + dev_set_name(dev, "mem%d", cxlmd->id); + + cdev = &cxlmd->cdev; + cdev_init(cdev, &cxl_memdev_fops); + + rc = cdev_device_add(cdev, dev); + if (rc) + goto err_add; + + return devm_add_action_or_reset(dev->parent, cxlmdev_unregister, cxlmd); + +err_add: + ida_free(&cxl_memdev_ida, cxlmd->id); +err_id: + /* + * Theoretically userspace could have already entered the fops, + * so flush ops_active. + */ + percpu_ref_kill(&cxlmd->ops_active); + wait_for_completion(&cxlmd->ops_dead); + percpu_ref_exit(&cxlmd->ops_active); +err_ref: + kfree(cxlmd); + + return rc; +} + +static int cxl_xfer_log(struct cxl_mem *cxlm, uuid_t *uuid, u32 size, u8 *out) +{ + u32 remaining = size; + u32 offset = 0; + + while (remaining) { + u32 xfer_size = min_t(u32, remaining, cxlm->payload_size); + struct cxl_mbox_get_log { + uuid_t uuid; + __le32 offset; + __le32 length; + } __packed log = { + .uuid = *uuid, + .offset = cpu_to_le32(offset), + .length = cpu_to_le32(xfer_size) + }; + int rc; + + rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_GET_LOG, &log, + sizeof(log), out, xfer_size); + if (rc < 0) + return rc; + + out += xfer_size; + remaining -= xfer_size; + offset += xfer_size; + } + + return 0; +} + +/** + * cxl_walk_cel() - Walk through the Command Effects Log. + * @cxlm: Device. + * @size: Length of the Command Effects Log. + * @cel: CEL + * + * Iterate over each entry in the CEL and determine if the driver supports the + * command. If so, the command is enabled for the device and can be used later. + */ +static void cxl_walk_cel(struct cxl_mem *cxlm, size_t size, u8 *cel) +{ + struct cel_entry { + __le16 opcode; + __le16 effect; + } __packed * cel_entry; + const int cel_entries = size / sizeof(*cel_entry); + int i; + + cel_entry = (struct cel_entry *)cel; + + for (i = 0; i < cel_entries; i++) { + u16 opcode = le16_to_cpu(cel_entry[i].opcode); + struct cxl_mem_command *cmd = cxl_mem_find_command(opcode); + + if (!cmd) { + dev_dbg(&cxlm->pdev->dev, + "Opcode 0x%04x unsupported by driver", opcode); + continue; + } + + set_bit(cmd->info.id, cxlm->enabled_cmds); + } +} + +struct cxl_mbox_get_supported_logs { + __le16 entries; + u8 rsvd[6]; + struct gsl_entry { + uuid_t uuid; + __le32 size; + } __packed entry[]; +} __packed; + +static struct cxl_mbox_get_supported_logs *cxl_get_gsl(struct cxl_mem *cxlm) +{ + struct cxl_mbox_get_supported_logs *ret; + int rc; + + ret = kvmalloc(cxlm->payload_size, GFP_KERNEL); + if (!ret) + return ERR_PTR(-ENOMEM); + + rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_GET_SUPPORTED_LOGS, NULL, + 0, ret, cxlm->payload_size); + if (rc < 0) { + kvfree(ret); + return ERR_PTR(rc); + } + + return ret; +} + +/** + * cxl_mem_enumerate_cmds() - Enumerate commands for a device. + * @cxlm: The device. + * + * Returns 0 if enumerate completed successfully. + * + * CXL devices have optional support for certain commands. This function will + * determine the set of supported commands for the hardware and update the + * enabled_cmds bitmap in the @cxlm. + */ +static int cxl_mem_enumerate_cmds(struct cxl_mem *cxlm) +{ + struct cxl_mbox_get_supported_logs *gsl; + struct device *dev = &cxlm->pdev->dev; + struct cxl_mem_command *cmd; + int i, rc; + + gsl = cxl_get_gsl(cxlm); + if (IS_ERR(gsl)) + return PTR_ERR(gsl); + + rc = -ENOENT; + for (i = 0; i < le16_to_cpu(gsl->entries); i++) { + u32 size = le32_to_cpu(gsl->entry[i].size); + uuid_t uuid = gsl->entry[i].uuid; + u8 *log; + + dev_dbg(dev, "Found LOG type %pU of size %d", &uuid, size); + + if (!uuid_equal(&uuid, &log_uuid[CEL_UUID])) + continue; + + log = kvmalloc(size, GFP_KERNEL); + if (!log) { + rc = -ENOMEM; + goto out; + } + + rc = cxl_xfer_log(cxlm, &uuid, size, log); + if (rc) { + kvfree(log); + goto out; + } + + cxl_walk_cel(cxlm, size, log); + kvfree(log); + + /* In case CEL was bogus, enable some default commands. */ + cxl_for_each_cmd(cmd) + if (cmd->flags & CXL_CMD_FLAG_FORCE_ENABLE) + set_bit(cmd->info.id, cxlm->enabled_cmds); + + /* Found the required CEL */ + rc = 0; + } + +out: + kvfree(gsl); + return rc; +} + +/** + * cxl_mem_identify() - Send the IDENTIFY command to the device. + * @cxlm: The device to identify. + * + * Return: 0 if identify was executed successfully. + * + * This will dispatch the identify command to the device and on success populate + * structures to be exported to sysfs. + */ +static int cxl_mem_identify(struct cxl_mem *cxlm) +{ + struct cxl_mbox_identify { + char fw_revision[0x10]; + __le64 total_capacity; + __le64 volatile_capacity; + __le64 persistent_capacity; + __le64 partition_align; + __le16 info_event_log_size; + __le16 warning_event_log_size; + __le16 failure_event_log_size; + __le16 fatal_event_log_size; + __le32 lsa_size; + u8 poison_list_max_mer[3]; + __le16 inject_poison_limit; + u8 poison_caps; + u8 qos_telemetry_caps; + } __packed id; + int rc; + + rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_IDENTIFY, NULL, 0, &id, + sizeof(id)); + if (rc < 0) + return rc; + + /* + * TODO: enumerate DPA map, as 'ram' and 'pmem' do not alias. + * For now, only the capacity is exported in sysfs + */ + cxlm->ram_range.start = 0; + cxlm->ram_range.end = le64_to_cpu(id.volatile_capacity) - 1; + + cxlm->pmem_range.start = 0; + cxlm->pmem_range.end = le64_to_cpu(id.persistent_capacity) - 1; + + memcpy(cxlm->firmware_version, id.fw_revision, sizeof(id.fw_revision)); + + return 0; +} + +static int cxl_mem_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct device *dev = &pdev->dev; + struct cxl_mem *cxlm = NULL; + u32 regloc_size, regblocks; + int rc, regloc, i; + + rc = pcim_enable_device(pdev); + if (rc) + return rc; + + regloc = cxl_mem_dvsec(pdev, PCI_DVSEC_ID_CXL_REGLOC_OFFSET); + if (!regloc) { + dev_err(dev, "register location dvsec not found\n"); + return -ENXIO; + } + + /* Get the size of the Register Locator DVSEC */ + pci_read_config_dword(pdev, regloc + PCI_DVSEC_HEADER1, ®loc_size); + regloc_size = FIELD_GET(PCI_DVSEC_HEADER1_LENGTH_MASK, regloc_size); + + regloc += PCI_DVSEC_ID_CXL_REGLOC_BLOCK1_OFFSET; + regblocks = (regloc_size - PCI_DVSEC_ID_CXL_REGLOC_BLOCK1_OFFSET) / 8; + + for (i = 0; i < regblocks; i++, regloc += 8) { + u32 reg_lo, reg_hi; + u8 reg_type; + + /* "register low and high" contain other bits */ + pci_read_config_dword(pdev, regloc, ®_lo); + pci_read_config_dword(pdev, regloc + 4, ®_hi); + + reg_type = FIELD_GET(CXL_REGLOC_RBI_MASK, reg_lo); + + if (reg_type == CXL_REGLOC_RBI_MEMDEV) { + cxlm = cxl_mem_create(pdev, reg_lo, reg_hi); + break; + } + } + + if (!cxlm) + return -ENODEV; + + rc = cxl_mem_setup_regs(cxlm); + if (rc) + return rc; + + rc = cxl_mem_setup_mailbox(cxlm); + if (rc) + return rc; + + rc = cxl_mem_enumerate_cmds(cxlm); + if (rc) + return rc; + + rc = cxl_mem_identify(cxlm); + if (rc) + return rc; + + return cxl_mem_add_memdev(cxlm); +} + +static const struct pci_device_id cxl_mem_pci_tbl[] = { + /* PCI class code for CXL.mem Type-3 Devices */ + { PCI_DEVICE_CLASS((PCI_CLASS_MEMORY_CXL << 8 | CXL_MEMORY_PROGIF), ~0)}, + { /* terminate list */ }, +}; +MODULE_DEVICE_TABLE(pci, cxl_mem_pci_tbl); + +static struct pci_driver cxl_mem_driver = { + .name = KBUILD_MODNAME, + .id_table = cxl_mem_pci_tbl, + .probe = cxl_mem_probe, + .driver = { + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, +}; + +static __init int cxl_mem_init(void) +{ + struct dentry *mbox_debugfs; + dev_t devt; + int rc; + + rc = alloc_chrdev_region(&devt, 0, CXL_MEM_MAX_DEVS, "cxl"); + if (rc) + return rc; + + cxl_mem_major = MAJOR(devt); + + rc = pci_register_driver(&cxl_mem_driver); + if (rc) { + unregister_chrdev_region(MKDEV(cxl_mem_major, 0), + CXL_MEM_MAX_DEVS); + return rc; + } + + cxl_debugfs = debugfs_create_dir("cxl", NULL); + mbox_debugfs = debugfs_create_dir("mbox", cxl_debugfs); + debugfs_create_bool("raw_allow_all", 0600, mbox_debugfs, + &cxl_raw_allow_all); + + return 0; +} + +static __exit void cxl_mem_exit(void) +{ + debugfs_remove_recursive(cxl_debugfs); + pci_unregister_driver(&cxl_mem_driver); + unregister_chrdev_region(MKDEV(cxl_mem_major, 0), CXL_MEM_MAX_DEVS); +} + +MODULE_LICENSE("GPL v2"); +module_init(cxl_mem_init); +module_exit(cxl_mem_exit); +MODULE_IMPORT_NS(CXL); diff --git a/drivers/cxl/pci.h b/drivers/cxl/pci.h new file mode 100644 index 000000000000..af3ec078cf6c --- /dev/null +++ b/drivers/cxl/pci.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright(c) 2020 Intel Corporation. All rights reserved. */ +#ifndef __CXL_PCI_H__ +#define __CXL_PCI_H__ + +#define CXL_MEMORY_PROGIF 0x10 + +/* + * See section 8.1 Configuration Space Registers in the CXL 2.0 + * Specification + */ +#define PCI_DVSEC_HEADER1_LENGTH_MASK GENMASK(31, 20) +#define PCI_DVSEC_VENDOR_ID_CXL 0x1E98 +#define PCI_DVSEC_ID_CXL 0x0 + +#define PCI_DVSEC_ID_CXL_REGLOC_OFFSET 0x8 +#define PCI_DVSEC_ID_CXL_REGLOC_BLOCK1_OFFSET 0xC + +/* BAR Indicator Register (BIR) */ +#define CXL_REGLOC_BIR_MASK GENMASK(2, 0) + +/* Register Block Identifier (RBI) */ +#define CXL_REGLOC_RBI_MASK GENMASK(15, 8) +#define CXL_REGLOC_RBI_EMPTY 0 +#define CXL_REGLOC_RBI_COMPONENT 1 +#define CXL_REGLOC_RBI_VIRT 2 +#define CXL_REGLOC_RBI_MEMDEV 3 + +#define CXL_REGLOC_ADDR_MASK GENMASK(31, 16) + +#endif /* __CXL_PCI_H__ */ diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index 737b207c9e30..452e85ae87a8 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -179,7 +179,10 @@ static int dax_bus_remove(struct device *dev) struct dax_device_driver *dax_drv = to_dax_drv(dev->driver); struct dev_dax *dev_dax = to_dev_dax(dev); - return dax_drv->remove(dev_dax); + if (dax_drv->remove) + dax_drv->remove(dev_dax); + + return 0; } static struct bus_type dax_bus_type = { @@ -1038,7 +1041,7 @@ static ssize_t range_parse(const char *opt, size_t len, struct range *range) { unsigned long long addr = 0; char *start, *end, *str; - ssize_t rc = EINVAL; + ssize_t rc = -EINVAL; str = kstrdup(opt, GFP_KERNEL); if (!str) @@ -1392,6 +1395,13 @@ int __dax_driver_register(struct dax_device_driver *dax_drv, struct device_driver *drv = &dax_drv->drv; int rc = 0; + /* + * dax_bus_probe() calls dax_drv->probe() unconditionally. + * So better be safe than sorry and ensure it is provided. + */ + if (!dax_drv->probe) + return -EINVAL; + INIT_LIST_HEAD(&dax_drv->ids); drv->owner = module; drv->name = mod_name; @@ -1409,7 +1419,15 @@ int __dax_driver_register(struct dax_device_driver *dax_drv, mutex_unlock(&dax_bus_lock); if (rc) return rc; - return driver_register(drv); + + rc = driver_register(drv); + if (rc && dax_drv->match_always) { + mutex_lock(&dax_bus_lock); + match_always_count -= dax_drv->match_always; + mutex_unlock(&dax_bus_lock); + } + + return rc; } EXPORT_SYMBOL_GPL(__dax_driver_register); diff --git a/drivers/dax/bus.h b/drivers/dax/bus.h index 72b92f95509f..1e946ad7780a 100644 --- a/drivers/dax/bus.h +++ b/drivers/dax/bus.h @@ -39,7 +39,7 @@ struct dax_device_driver { struct list_head ids; int match_always; int (*probe)(struct dev_dax *dev); - int (*remove)(struct dev_dax *dev); + void (*remove)(struct dev_dax *dev); }; int __dax_driver_register(struct dax_device_driver *dax_drv, diff --git a/drivers/dax/device.c b/drivers/dax/device.c index 5da2980bb16b..db92573c94e8 100644 --- a/drivers/dax/device.c +++ b/drivers/dax/device.c @@ -452,15 +452,9 @@ int dev_dax_probe(struct dev_dax *dev_dax) } EXPORT_SYMBOL_GPL(dev_dax_probe); -static int dev_dax_remove(struct dev_dax *dev_dax) -{ - /* all probe actions are unwound by devm */ - return 0; -} - static struct dax_device_driver device_dax_driver = { .probe = dev_dax_probe, - .remove = dev_dax_remove, + /* all probe actions are unwound by devm, so .remove isn't necessary */ .match_always = 1, }; diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c index 403ec42472d1..ac231cc36359 100644 --- a/drivers/dax/kmem.c +++ b/drivers/dax/kmem.c @@ -136,7 +136,7 @@ err_res_name: } #ifdef CONFIG_MEMORY_HOTREMOVE -static int dev_dax_kmem_remove(struct dev_dax *dev_dax) +static void dev_dax_kmem_remove(struct dev_dax *dev_dax) { int i, success = 0; struct device *dev = &dev_dax->dev; @@ -176,11 +176,9 @@ static int dev_dax_kmem_remove(struct dev_dax *dev_dax) kfree(data); dev_set_drvdata(dev, NULL); } - - return 0; } #else -static int dev_dax_kmem_remove(struct dev_dax *dev_dax) +static void dev_dax_kmem_remove(struct dev_dax *dev_dax) { /* * Without hotremove purposely leak the request_mem_region() for the @@ -190,7 +188,6 @@ static int dev_dax_kmem_remove(struct dev_dax *dev_dax) * request_mem_region(). */ any_hotremove_failed = true; - return 0; } #endif /* CONFIG_MEMORY_HOTREMOVE */ diff --git a/drivers/dax/pmem/compat.c b/drivers/dax/pmem/compat.c index 863c114fd88c..d81dc35fd65d 100644 --- a/drivers/dax/pmem/compat.c +++ b/drivers/dax/pmem/compat.c @@ -41,10 +41,9 @@ static int dax_pmem_compat_release(struct device *dev, void *data) return 0; } -static int dax_pmem_compat_remove(struct device *dev) +static void dax_pmem_compat_remove(struct device *dev) { device_for_each_child(dev, NULL, dax_pmem_compat_release); - return 0; } static struct nd_device_driver dax_pmem_compat_driver = { diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index f659395e7959..9ab6ee22c110 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -1187,34 +1187,6 @@ static void *iommu_dma_alloc(struct device *dev, size_t size, return cpu_addr; } -#ifdef CONFIG_DMA_REMAP -static void *iommu_dma_alloc_noncoherent(struct device *dev, size_t size, - dma_addr_t *handle, enum dma_data_direction dir, gfp_t gfp) -{ - if (!gfpflags_allow_blocking(gfp)) { - struct page *page; - - page = dma_common_alloc_pages(dev, size, handle, dir, gfp); - if (!page) - return NULL; - return page_address(page); - } - - return iommu_dma_alloc_remap(dev, size, handle, gfp | __GFP_ZERO, - PAGE_KERNEL, 0); -} - -static void iommu_dma_free_noncoherent(struct device *dev, size_t size, - void *cpu_addr, dma_addr_t handle, enum dma_data_direction dir) -{ - __iommu_dma_unmap(dev, handle, size); - __iommu_dma_free(dev, size, cpu_addr); -} -#else -#define iommu_dma_alloc_noncoherent NULL -#define iommu_dma_free_noncoherent NULL -#endif /* CONFIG_DMA_REMAP */ - static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) @@ -1285,8 +1257,6 @@ static const struct dma_map_ops iommu_dma_ops = { .free = iommu_dma_free, .alloc_pages = dma_common_alloc_pages, .free_pages = dma_common_free_pages, - .alloc_noncoherent = iommu_dma_alloc_noncoherent, - .free_noncoherent = iommu_dma_free_noncoherent, .mmap = iommu_dma_mmap, .get_sgtable = iommu_dma_get_sgtable, .map_page = iommu_dma_map_page, diff --git a/drivers/mailbox/arm_mhuv2.c b/drivers/mailbox/arm_mhuv2.c index 6cf1991a5c9c..d997f8ebfa98 100644 --- a/drivers/mailbox/arm_mhuv2.c +++ b/drivers/mailbox/arm_mhuv2.c @@ -238,19 +238,19 @@ struct mhuv2_mbox_chan_priv { }; /* Macro for reading a bitfield within a physically mapped packed struct */ -#define readl_relaxed_bitfield(_regptr, _field) \ +#define readl_relaxed_bitfield(_regptr, _type, _field) \ ({ \ u32 _regval; \ _regval = readl_relaxed((_regptr)); \ - (*(typeof((_regptr)))(&_regval))._field; \ + (*(_type *)(&_regval))._field; \ }) /* Macro for writing a bitfield within a physically mapped packed struct */ -#define writel_relaxed_bitfield(_value, _regptr, _field) \ +#define writel_relaxed_bitfield(_value, _regptr, _type, _field) \ ({ \ u32 _regval; \ _regval = readl_relaxed(_regptr); \ - (*(typeof(_regptr))(&_regval))._field = _value; \ + (*(_type *)(&_regval))._field = _value; \ writel_relaxed(_regval, _regptr); \ }) @@ -496,7 +496,7 @@ static const struct mhuv2_protocol_ops mhuv2_data_transfer_ops = { /* Interrupt handlers */ -static struct mbox_chan *get_irq_chan_comb(struct mhuv2 *mhu, u32 *reg) +static struct mbox_chan *get_irq_chan_comb(struct mhuv2 *mhu, u32 __iomem *reg) { struct mbox_chan *chans = mhu->mbox.chans; int channel = 0, i, offset = 0, windows, protocol, ch_wn; @@ -699,7 +699,9 @@ static irqreturn_t mhuv2_receiver_interrupt(int irq, void *arg) ret = IRQ_HANDLED; } - kfree(data); + if (!IS_ERR(data)) + kfree(data); + return ret; } @@ -969,8 +971,8 @@ static int mhuv2_tx_init(struct amba_device *adev, struct mhuv2 *mhu, mhu->mbox.ops = &mhuv2_sender_ops; mhu->send = reg; - mhu->windows = readl_relaxed_bitfield(&mhu->send->mhu_cfg, num_ch); - mhu->minor = readl_relaxed_bitfield(&mhu->send->aidr, arch_minor_rev); + mhu->windows = readl_relaxed_bitfield(&mhu->send->mhu_cfg, struct mhu_cfg_t, num_ch); + mhu->minor = readl_relaxed_bitfield(&mhu->send->aidr, struct aidr_t, arch_minor_rev); spin_lock_init(&mhu->doorbell_pending_lock); @@ -990,7 +992,7 @@ static int mhuv2_tx_init(struct amba_device *adev, struct mhuv2 *mhu, mhu->mbox.txdone_poll = false; mhu->irq = adev->irq[0]; - writel_relaxed_bitfield(1, &mhu->send->int_en, chcomb); + writel_relaxed_bitfield(1, &mhu->send->int_en, struct int_en_t, chcomb); /* Disable all channel interrupts */ for (i = 0; i < mhu->windows; i++) @@ -1023,8 +1025,8 @@ static int mhuv2_rx_init(struct amba_device *adev, struct mhuv2 *mhu, mhu->mbox.ops = &mhuv2_receiver_ops; mhu->recv = reg; - mhu->windows = readl_relaxed_bitfield(&mhu->recv->mhu_cfg, num_ch); - mhu->minor = readl_relaxed_bitfield(&mhu->recv->aidr, arch_minor_rev); + mhu->windows = readl_relaxed_bitfield(&mhu->recv->mhu_cfg, struct mhu_cfg_t, num_ch); + mhu->minor = readl_relaxed_bitfield(&mhu->recv->aidr, struct aidr_t, arch_minor_rev); mhu->irq = adev->irq[0]; if (!mhu->irq) { @@ -1045,7 +1047,7 @@ static int mhuv2_rx_init(struct amba_device *adev, struct mhuv2 *mhu, writel_relaxed(0xFFFFFFFF, &mhu->recv->ch_wn[i].mask_set); if (mhu->minor) - writel_relaxed_bitfield(1, &mhu->recv->int_en, chcomb); + writel_relaxed_bitfield(1, &mhu->recv->int_en, struct int_en_t, chcomb); return 0; } diff --git a/drivers/mailbox/omap-mailbox.c b/drivers/mailbox/omap-mailbox.c index 93fe08aef3ca..7295e3835e30 100644 --- a/drivers/mailbox/omap-mailbox.c +++ b/drivers/mailbox/omap-mailbox.c @@ -3,7 +3,7 @@ * OMAP mailbox driver * * Copyright (C) 2006-2009 Nokia Corporation. All rights reserved. - * Copyright (C) 2013-2019 Texas Instruments Incorporated - https://www.ti.com + * Copyright (C) 2013-2021 Texas Instruments Incorporated - https://www.ti.com * * Contact: Hiroshi DOYU * Suman Anna @@ -663,6 +663,10 @@ static const struct of_device_id omap_mailbox_of_match[] = { .compatible = "ti,am654-mailbox", .data = &omap4_data, }, + { + .compatible = "ti,am64-mailbox", + .data = &omap4_data, + }, { /* end */ }, diff --git a/drivers/mailbox/qcom-apcs-ipc-mailbox.c b/drivers/mailbox/qcom-apcs-ipc-mailbox.c index 077e5c6a9ef7..f25324d03842 100644 --- a/drivers/mailbox/qcom-apcs-ipc-mailbox.c +++ b/drivers/mailbox/qcom-apcs-ipc-mailbox.c @@ -61,11 +61,15 @@ static const struct qcom_apcs_ipc_data apps_shared_apcs_data = { .offset = 12, .clk_name = NULL }; +static const struct qcom_apcs_ipc_data sdx55_apcs_data = { + .offset = 0x1008, .clk_name = "qcom-sdx55-acps-clk" +}; + static const struct regmap_config apcs_regmap_config = { .reg_bits = 32, .reg_stride = 4, .val_bits = 32, - .max_register = 0xFFC, + .max_register = 0x1008, .fast_io = true, }; @@ -159,9 +163,11 @@ static const struct of_device_id qcom_apcs_ipc_of_match[] = { { .compatible = "qcom,msm8998-apcs-hmss-global", .data = &msm8998_apcs_data }, { .compatible = "qcom,qcs404-apcs-apps-global", .data = &msm8916_apcs_data }, { .compatible = "qcom,sc7180-apss-shared", .data = &apps_shared_apcs_data }, + { .compatible = "qcom,sc8180x-apss-shared", .data = &apps_shared_apcs_data }, { .compatible = "qcom,sdm660-apcs-hmss-global", .data = &sdm660_apcs_data }, { .compatible = "qcom,sdm845-apss-shared", .data = &apps_shared_apcs_data }, { .compatible = "qcom,sm8150-apss-shared", .data = &apps_shared_apcs_data }, + { .compatible = "qcom,sdx55-apcs-gcc", .data = &sdx55_apcs_data }, {} }; MODULE_DEVICE_TABLE(of, qcom_apcs_ipc_of_match); diff --git a/drivers/mailbox/sprd-mailbox.c b/drivers/mailbox/sprd-mailbox.c index f6fab24ae8a9..4c325301a2fe 100644 --- a/drivers/mailbox/sprd-mailbox.c +++ b/drivers/mailbox/sprd-mailbox.c @@ -35,7 +35,7 @@ #define SPRD_MBOX_IRQ_CLR BIT(0) /* Bit and mask definiation for outbox's SPRD_MBOX_FIFO_STS register */ -#define SPRD_OUTBOX_FIFO_FULL BIT(0) +#define SPRD_OUTBOX_FIFO_FULL BIT(2) #define SPRD_OUTBOX_FIFO_WR_SHIFT 16 #define SPRD_OUTBOX_FIFO_RD_SHIFT 24 #define SPRD_OUTBOX_FIFO_POS_MASK GENMASK(7, 0) diff --git a/drivers/mailbox/tegra-hsp.c b/drivers/mailbox/tegra-hsp.c index e07091d71986..acd0675da681 100644 --- a/drivers/mailbox/tegra-hsp.c +++ b/drivers/mailbox/tegra-hsp.c @@ -98,7 +98,9 @@ struct tegra_hsp { unsigned int num_ss; unsigned int num_db; unsigned int num_si; + spinlock_t lock; + struct lock_class_key lock_key; struct list_head doorbells; struct tegra_hsp_mailbox *mailboxes; @@ -775,6 +777,18 @@ static int tegra_hsp_probe(struct platform_device *pdev) return err; } + lockdep_register_key(&hsp->lock_key); + lockdep_set_class(&hsp->lock, &hsp->lock_key); + + return 0; +} + +static int tegra_hsp_remove(struct platform_device *pdev) +{ + struct tegra_hsp *hsp = platform_get_drvdata(pdev); + + lockdep_unregister_key(&hsp->lock_key); + return 0; } @@ -834,6 +848,7 @@ static struct platform_driver tegra_hsp_driver = { .pm = &tegra_hsp_pm_ops, }, .probe = tegra_hsp_probe, + .remove = tegra_hsp_remove, }; static int __init tegra_hsp_init(void) diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c index e03a1f38d750..7b9556291eb1 100644 --- a/drivers/nvdimm/blk.c +++ b/drivers/nvdimm/blk.c @@ -310,11 +310,10 @@ static int nd_blk_probe(struct device *dev) return nsblk_attach_disk(nsblk); } -static int nd_blk_remove(struct device *dev) +static void nd_blk_remove(struct device *dev) { if (is_nd_btt(dev)) nvdimm_namespace_detach_btt(to_nd_btt(dev)); - return 0; } static struct nd_device_driver nd_blk_driver = { diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 2304c6183822..48f0985ca8a0 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -113,18 +113,17 @@ static int nvdimm_bus_remove(struct device *dev) struct nd_device_driver *nd_drv = to_nd_device_driver(dev->driver); struct module *provider = to_bus_provider(dev); struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); - int rc = 0; if (nd_drv->remove) { debug_nvdimm_lock(dev); - rc = nd_drv->remove(dev); + nd_drv->remove(dev); debug_nvdimm_unlock(dev); } - dev_dbg(&nvdimm_bus->dev, "%s.remove(%s) = %d\n", dev->driver->name, - dev_name(dev), rc); + dev_dbg(&nvdimm_bus->dev, "%s.remove(%s)\n", dev->driver->name, + dev_name(dev)); module_put(provider); - return rc; + return 0; } static void nvdimm_bus_shutdown(struct device *dev) @@ -427,7 +426,7 @@ static void free_badrange_list(struct list_head *badrange_list) list_del_init(badrange_list); } -static int nd_bus_remove(struct device *dev) +static void nd_bus_remove(struct device *dev) { struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev); @@ -446,8 +445,6 @@ static int nd_bus_remove(struct device *dev) spin_unlock(&nvdimm_bus->badrange.lock); nvdimm_bus_destroy_ndctl(nvdimm_bus); - - return 0; } static int nd_bus_probe(struct device *dev) diff --git a/drivers/nvdimm/dimm.c b/drivers/nvdimm/dimm.c index 7d4ddc4d9322..91d9163ee303 100644 --- a/drivers/nvdimm/dimm.c +++ b/drivers/nvdimm/dimm.c @@ -113,19 +113,14 @@ static int nvdimm_probe(struct device *dev) return rc; } -static int nvdimm_remove(struct device *dev) +static void nvdimm_remove(struct device *dev) { struct nvdimm_drvdata *ndd = dev_get_drvdata(dev); - if (!ndd) - return 0; - nvdimm_bus_lock(dev); dev_set_drvdata(dev, NULL); nvdimm_bus_unlock(dev); put_ndd(ndd); - - return 0; } static struct nd_device_driver nvdimm_driver = { diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 281fedb4dc4d..b8a85bfb2e95 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -563,7 +563,7 @@ static int nd_pmem_probe(struct device *dev) return pmem_attach_disk(dev, ndns); } -static int nd_pmem_remove(struct device *dev) +static void nd_pmem_remove(struct device *dev) { struct pmem_device *pmem = dev_get_drvdata(dev); @@ -578,8 +578,6 @@ static int nd_pmem_remove(struct device *dev) pmem->bb_state = NULL; } nvdimm_flush(to_nd_region(dev->parent), NULL); - - return 0; } static void nd_pmem_shutdown(struct device *dev) diff --git a/drivers/nvdimm/region.c b/drivers/nvdimm/region.c index bfce87ed72ab..e0c34120df37 100644 --- a/drivers/nvdimm/region.c +++ b/drivers/nvdimm/region.c @@ -87,7 +87,7 @@ static int child_unregister(struct device *dev, void *data) return 0; } -static int nd_region_remove(struct device *dev) +static void nd_region_remove(struct device *dev) { struct nd_region *nd_region = to_nd_region(dev); @@ -108,8 +108,6 @@ static int nd_region_remove(struct device *dev) */ sysfs_put(nd_region->bb_state); nd_region->bb_state = NULL; - - return 0; } static int child_notify(struct device *dev, void *data) diff --git a/drivers/sbus/char/display7seg.c b/drivers/sbus/char/display7seg.c index fad936eb845f..00e72b97d0b6 100644 --- a/drivers/sbus/char/display7seg.c +++ b/drivers/sbus/char/display7seg.c @@ -186,7 +186,7 @@ static int d7s_probe(struct platform_device *op) p->regs = of_ioremap(&op->resource[0], 0, sizeof(u8), "d7s"); if (!p->regs) { printk(KERN_ERR PFX "Cannot map chip registers\n"); - goto out_free; + goto out; } err = misc_register(&d7s_miscdev); @@ -228,8 +228,6 @@ out: out_iounmap: of_iounmap(&op->resource[0], p->regs, sizeof(u8)); - -out_free: goto out; } diff --git a/include/crypto/public_key.h b/include/crypto/public_key.h index 948c5203ca9c..47accec68cb0 100644 --- a/include/crypto/public_key.h +++ b/include/crypto/public_key.h @@ -12,7 +12,6 @@ #include #include -#include /* * Cryptographic data for the public-key subtype of the asymmetric key type. diff --git a/include/keys/encrypted-type.h b/include/keys/encrypted-type.h index 38afb341c3f2..abfcbe02001a 100644 --- a/include/keys/encrypted-type.h +++ b/include/keys/encrypted-type.h @@ -2,7 +2,7 @@ /* * Copyright (C) 2010 IBM Corporation * Copyright (C) 2010 Politecnico di Torino, Italy - * TORSEC group -- http://security.polito.it + * TORSEC group -- https://security.polito.it * * Authors: * Mimi Zohar diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 1e98b8c1e055..51872e736e7b 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -22,11 +22,6 @@ struct dma_map_ops { gfp_t gfp); void (*free_pages)(struct device *dev, size_t size, struct page *vaddr, dma_addr_t dma_handle, enum dma_data_direction dir); - void *(*alloc_noncoherent)(struct device *dev, size_t size, - dma_addr_t *dma_handle, enum dma_data_direction dir, - gfp_t gfp); - void (*free_noncoherent)(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, enum dma_data_direction dir); int (*mmap)(struct device *, struct vm_area_struct *, void *, dma_addr_t, size_t, unsigned long attrs); diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 2e49996a8f39..fbfa3f5abd94 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -263,10 +263,19 @@ struct page *dma_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp); void dma_free_pages(struct device *dev, size_t size, struct page *page, dma_addr_t dma_handle, enum dma_data_direction dir); -void *dma_alloc_noncoherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp); -void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, enum dma_data_direction dir); + +static inline void *dma_alloc_noncoherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp) +{ + struct page *page = dma_alloc_pages(dev, size, dma_handle, dir, gfp); + return page ? page_address(page) : NULL; +} + +static inline void dma_free_noncoherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_handle, enum dma_data_direction dir) +{ + dma_free_pages(dev, size, virt_to_page(vaddr), dma_handle, dir); +} static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr, size_t size, enum dma_data_direction dir, unsigned long attrs) diff --git a/include/linux/key.h b/include/linux/key.h index 0f2e24f13c2b..7febc4881363 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -289,6 +289,7 @@ extern struct key *key_alloc(struct key_type *type, #define KEY_ALLOC_BUILT_IN 0x0004 /* Key is built into kernel */ #define KEY_ALLOC_BYPASS_RESTRICTION 0x0008 /* Override the check on restricted keyrings */ #define KEY_ALLOC_UID_KEYRING 0x0010 /* allocating a user or user session keyring */ +#define KEY_ALLOC_SET_KEEP 0x0020 /* Set the KEEP flag on the key/keyring */ extern void key_revoke(struct key *key); extern void key_invalidate(struct key *key); @@ -360,7 +361,7 @@ static inline struct key *request_key(struct key_type *type, * completion of keys undergoing construction with a non-interruptible wait. */ #define request_key_net(type, description, net, callout_info) \ - request_key_tag(type, description, net->key_domain, callout_info); + request_key_tag(type, description, net->key_domain, callout_info) /** * request_key_net_rcu - Request a key for a net namespace under RCU conditions @@ -372,7 +373,7 @@ static inline struct key *request_key(struct key_type *type, * network namespace are used. */ #define request_key_net_rcu(type, description, net) \ - request_key_rcu(type, description, net->key_domain); + request_key_rcu(type, description, net->key_domain) #endif /* CONFIG_NET */ extern int wait_for_key_construction(struct key *key, bool intr); diff --git a/include/linux/nd.h b/include/linux/nd.h index 55c735997805..cec526c8043d 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -26,7 +26,7 @@ struct nd_device_driver { struct device_driver drv; unsigned long type; int (*probe)(struct device *dev); - int (*remove)(struct device *dev); + void (*remove)(struct device *dev); void (*shutdown)(struct device *dev); void (*notify)(struct device *dev, enum nvdimm_event event); }; diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 693a41efca85..6de389d9aada 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -51,6 +51,7 @@ #define PCI_BASE_CLASS_MEMORY 0x05 #define PCI_CLASS_MEMORY_RAM 0x0500 #define PCI_CLASS_MEMORY_FLASH 0x0501 +#define PCI_CLASS_MEMORY_CXL 0x0502 #define PCI_CLASS_MEMORY_OTHER 0x0580 #define PCI_BASE_CLASS_BRIDGE 0x06 diff --git a/include/linux/verification.h b/include/linux/verification.h index 911ab7c2b1ab..a655923335ae 100644 --- a/include/linux/verification.h +++ b/include/linux/verification.h @@ -8,6 +8,8 @@ #ifndef _LINUX_VERIFICATION_H #define _LINUX_VERIFICATION_H +#include + /* * Indicate that both builtin trusted keys and secondary trusted keys * should be used. diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h new file mode 100644 index 000000000000..3155382dfc9b --- /dev/null +++ b/include/uapi/linux/cxl_mem.h @@ -0,0 +1,172 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * CXL IOCTLs for Memory Devices + */ + +#ifndef _UAPI_CXL_MEM_H_ +#define _UAPI_CXL_MEM_H_ + +#include + +/** + * DOC: UAPI + * + * Not all of all commands that the driver supports are always available for use + * by userspace. Userspace must check the results from the QUERY command in + * order to determine the live set of commands. + */ + +#define CXL_MEM_QUERY_COMMANDS _IOR(0xCE, 1, struct cxl_mem_query_commands) +#define CXL_MEM_SEND_COMMAND _IOWR(0xCE, 2, struct cxl_send_command) + +#define CXL_CMDS \ + ___C(INVALID, "Invalid Command"), \ + ___C(IDENTIFY, "Identify Command"), \ + ___C(RAW, "Raw device command"), \ + ___C(GET_SUPPORTED_LOGS, "Get Supported Logs"), \ + ___C(GET_FW_INFO, "Get FW Info"), \ + ___C(GET_PARTITION_INFO, "Get Partition Information"), \ + ___C(GET_LSA, "Get Label Storage Area"), \ + ___C(GET_HEALTH_INFO, "Get Health Info"), \ + ___C(GET_LOG, "Get Log"), \ + ___C(MAX, "invalid / last command") + +#define ___C(a, b) CXL_MEM_COMMAND_ID_##a +enum { CXL_CMDS }; + +#undef ___C +#define ___C(a, b) { b } +static const struct { + const char *name; +} cxl_command_names[] = { CXL_CMDS }; + +/* + * Here's how this actually breaks out: + * cxl_command_names[] = { + * [CXL_MEM_COMMAND_ID_INVALID] = { "Invalid Command" }, + * [CXL_MEM_COMMAND_ID_IDENTIFY] = { "Identify Command" }, + * ... + * [CXL_MEM_COMMAND_ID_MAX] = { "invalid / last command" }, + * }; + */ + +#undef ___C + +/** + * struct cxl_command_info - Command information returned from a query. + * @id: ID number for the command. + * @flags: Flags that specify command behavior. + * @size_in: Expected input size, or -1 if variable length. + * @size_out: Expected output size, or -1 if variable length. + * + * Represents a single command that is supported by both the driver and the + * hardware. This is returned as part of an array from the query ioctl. The + * following would be a command that takes a variable length input and returns 0 + * bytes of output. + * + * - @id = 10 + * - @flags = 0 + * - @size_in = -1 + * - @size_out = 0 + * + * See struct cxl_mem_query_commands. + */ +struct cxl_command_info { + __u32 id; + + __u32 flags; +#define CXL_MEM_COMMAND_FLAG_MASK GENMASK(0, 0) + + __s32 size_in; + __s32 size_out; +}; + +/** + * struct cxl_mem_query_commands - Query supported commands. + * @n_commands: In/out parameter. When @n_commands is > 0, the driver will + * return min(num_support_commands, n_commands). When @n_commands + * is 0, driver will return the number of total supported commands. + * @rsvd: Reserved for future use. + * @commands: Output array of supported commands. This array must be allocated + * by userspace to be at least min(num_support_commands, @n_commands) + * + * Allow userspace to query the available commands supported by both the driver, + * and the hardware. Commands that aren't supported by either the driver, or the + * hardware are not returned in the query. + * + * Examples: + * + * - { .n_commands = 0 } // Get number of supported commands + * - { .n_commands = 15, .commands = buf } // Return first 15 (or less) + * supported commands + * + * See struct cxl_command_info. + */ +struct cxl_mem_query_commands { + /* + * Input: Number of commands to return (space allocated by user) + * Output: Number of commands supported by the driver/hardware + * + * If n_commands is 0, kernel will only return number of commands and + * not try to populate commands[], thus allowing userspace to know how + * much space to allocate + */ + __u32 n_commands; + __u32 rsvd; + + struct cxl_command_info __user commands[]; /* out: supported commands */ +}; + +/** + * struct cxl_send_command - Send a command to a memory device. + * @id: The command to send to the memory device. This must be one of the + * commands returned by the query command. + * @flags: Flags for the command (input). + * @raw: Special fields for raw commands + * @raw.opcode: Opcode passed to hardware when using the RAW command. + * @raw.rsvd: Must be zero. + * @rsvd: Must be zero. + * @retval: Return value from the memory device (output). + * @in: Parameters associated with input payload. + * @in.size: Size of the payload to provide to the device (input). + * @in.rsvd: Must be zero. + * @in.payload: Pointer to memory for payload input, payload is little endian. + * @out: Parameters associated with output payload. + * @out.size: Size of the payload received from the device (input/output). This + * field is filled in by userspace to let the driver know how much + * space was allocated for output. It is populated by the driver to + * let userspace know how large the output payload actually was. + * @out.rsvd: Must be zero. + * @out.payload: Pointer to memory for payload output, payload is little endian. + * + * Mechanism for userspace to send a command to the hardware for processing. The + * driver will do basic validation on the command sizes. In some cases even the + * payload may be introspected. Userspace is required to allocate large enough + * buffers for size_out which can be variable length in certain situations. + */ +struct cxl_send_command { + __u32 id; + __u32 flags; + union { + struct { + __u16 opcode; + __u16 rsvd; + } raw; + __u32 rsvd; + }; + __u32 retval; + + struct { + __s32 size; + __u32 rsvd; + __u64 payload; + } in; + + struct { + __s32 size; + __u32 rsvd; + __u64 payload; + } out; +}; + +#endif diff --git a/init/Kconfig b/init/Kconfig index 060476c102c5..f5ec194d7212 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -2313,8 +2313,8 @@ config MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS If unsure, say N. config TRIM_UNUSED_KSYMS - bool "Trim unused exported kernel symbols" - depends on BROKEN + bool "Trim unused exported kernel symbols" if EXPERT + depends on !COMPILE_TEST help The kernel and some modules make many symbols available for other modules to use via EXPORT_SYMBOL() and variants. Depending diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c index da95df381483..e0e64f8b0739 100644 --- a/kernel/dma/map_benchmark.c +++ b/kernel/dma/map_benchmark.c @@ -21,6 +21,7 @@ #define DMA_MAP_BENCHMARK _IOWR('d', 1, struct map_benchmark) #define DMA_MAP_MAX_THREADS 1024 #define DMA_MAP_MAX_SECONDS 300 +#define DMA_MAP_MAX_TRANS_DELAY (10 * NSEC_PER_MSEC) #define DMA_MAP_BIDIRECTIONAL 0 #define DMA_MAP_TO_DEVICE 1 @@ -36,7 +37,8 @@ struct map_benchmark { __s32 node; /* which numa node this benchmark will run on */ __u32 dma_bits; /* DMA addressing capability */ __u32 dma_dir; /* DMA data direction */ - __u8 expansion[84]; /* For future use */ + __u32 dma_trans_ns; /* time for DMA transmission in ns */ + __u8 expansion[80]; /* For future use */ }; struct map_benchmark_data { @@ -87,6 +89,9 @@ static int map_benchmark_thread(void *data) map_etime = ktime_get(); map_delta = ktime_sub(map_etime, map_stime); + /* Pretend DMA is transmitting */ + ndelay(map->bparam.dma_trans_ns); + unmap_stime = ktime_get(); dma_unmap_single(map->dev, dma_addr, PAGE_SIZE, map->dir); unmap_etime = ktime_get(); @@ -218,6 +223,11 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd, return -EINVAL; } + if (map->bparam.dma_trans_ns > DMA_MAP_MAX_TRANS_DELAY) { + pr_err("invalid transmission delay\n"); + return -EINVAL; + } + if (map->bparam.node != NUMA_NO_NODE && !node_possible(map->bparam.node)) { pr_err("invalid numa node\n"); diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 84de6b1c5fab..b6a633679933 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -517,46 +517,6 @@ void dma_free_pages(struct device *dev, size_t size, struct page *page, } EXPORT_SYMBOL_GPL(dma_free_pages); -void *dma_alloc_noncoherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - void *vaddr; - - if (!ops || !ops->alloc_noncoherent) { - struct page *page; - - page = dma_alloc_pages(dev, size, dma_handle, dir, gfp); - if (!page) - return NULL; - return page_address(page); - } - - size = PAGE_ALIGN(size); - vaddr = ops->alloc_noncoherent(dev, size, dma_handle, dir, gfp); - if (vaddr) - debug_dma_map_page(dev, virt_to_page(vaddr), 0, size, dir, - *dma_handle); - return vaddr; -} -EXPORT_SYMBOL_GPL(dma_alloc_noncoherent); - -void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, enum dma_data_direction dir) -{ - const struct dma_map_ops *ops = get_dma_ops(dev); - - if (!ops || !ops->free_noncoherent) { - dma_free_pages(dev, size, virt_to_page(vaddr), dma_handle, dir); - return; - } - - size = PAGE_ALIGN(size); - debug_dma_unmap_page(dev, dma_handle, size, dir); - ops->free_noncoherent(dev, size, vaddr, dma_handle, dir); -} -EXPORT_SYMBOL_GPL(dma_free_noncoherent); - int dma_supported(struct device *dev, u64 mask) { const struct dma_map_ops *ops = get_dma_ops(dev); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 61cefb157b59..9c266b93cbc0 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -60,6 +60,11 @@ config HAVE_NOP_MCOUNT help Arch supports the gcc options -pg with -mrecord-mcount and -nop-mcount +config HAVE_OBJTOOL_MCOUNT + bool + help + Arch supports objtool --mcount + config HAVE_C_RECORDMCOUNT bool help @@ -612,10 +617,18 @@ config FTRACE_MCOUNT_USE_CC depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY depends on FTRACE_MCOUNT_RECORD +config FTRACE_MCOUNT_USE_OBJTOOL + def_bool y + depends on HAVE_OBJTOOL_MCOUNT + depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY + depends on !FTRACE_MCOUNT_USE_CC + depends on FTRACE_MCOUNT_RECORD + config FTRACE_MCOUNT_USE_RECORDMCOUNT def_bool y depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY depends on !FTRACE_MCOUNT_USE_CC + depends on !FTRACE_MCOUNT_USE_OBJTOOL depends on FTRACE_MCOUNT_RECORD config TRACING_MAP diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index 0ef8f65bd2d7..9c9eb20dd2c5 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -413,7 +413,7 @@ static void put_watch(struct watch *watch) } /** - * init_watch_queue - Initialise a watch + * init_watch - Initialise a watch * @watch: The watch to initialise. * @wqueue: The queue to assign. * diff --git a/samples/Kconfig b/samples/Kconfig index 0ed6e4d71d87..e76cdfc50e25 100644 --- a/samples/Kconfig +++ b/samples/Kconfig @@ -210,7 +210,7 @@ config SAMPLE_WATCHDOG depends on CC_CAN_LINK config SAMPLE_WATCH_QUEUE - bool "Build example /dev/watch_queue notification consumer" + bool "Build example watch_queue notification API consumer" depends on CC_CAN_LINK && HEADERS_INSTALL help Build example userspace program to use the new mount_notify(), diff --git a/samples/watch_queue/watch_test.c b/samples/watch_queue/watch_test.c index 46e618a897fe..8c6cb57d5cfc 100644 --- a/samples/watch_queue/watch_test.c +++ b/samples/watch_queue/watch_test.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Use /dev/watch_queue to watch for notifications. +/* Use watch_queue API to watch for notifications. * * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index d94fc9ab819d..3f6bf0ea7c0e 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -218,27 +218,11 @@ cmd_record_mcount = $(if $(findstring $(strip $(CC_FLAGS_FTRACE)),$(_c_flags)), endif # CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT ifdef CONFIG_STACK_VALIDATION +ifndef CONFIG_LTO_CLANG ifneq ($(SKIP_STACK_VALIDATION),1) __objtool_obj := $(objtree)/tools/objtool/objtool -objtool_args = $(if $(CONFIG_UNWINDER_ORC),orc generate,check) - -objtool_args += $(if $(part-of-module), --module,) - -ifndef CONFIG_FRAME_POINTER -objtool_args += --no-fp -endif -ifdef CONFIG_GCOV_KERNEL -objtool_args += --no-unreachable -endif -ifdef CONFIG_RETPOLINE - objtool_args += --retpoline -endif -ifdef CONFIG_X86_SMAP - objtool_args += --uaccess -endif - # 'OBJECT_FILES_NON_STANDARD := y': skip objtool checking for a directory # 'OBJECT_FILES_NON_STANDARD_foo.o := 'y': skip objtool checking for a file # 'OBJECT_FILES_NON_STANDARD_foo.o := 'n': override directory skip for a file @@ -250,6 +234,7 @@ objtool_obj = $(if $(patsubst y%,, \ $(__objtool_obj)) endif # SKIP_STACK_VALIDATION +endif # CONFIG_LTO_CLANG endif # CONFIG_STACK_VALIDATION # Rebuild all objects when objtool changes, or is enabled/disabled. diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 7048aaafcf89..29e8a816d9ab 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -222,6 +222,18 @@ dtc_cpp_flags = -Wp,-MMD,$(depfile).pre.tmp -nostdinc \ $(addprefix -I,$(DTC_INCLUDE)) \ -undef -D__DTS__ +# Objtool arguments are also needed for modfinal with LTO, so we define +# then here to avoid duplication. +objtool_args = \ + $(if $(CONFIG_UNWINDER_ORC),orc generate,check) \ + $(if $(part-of-module), --module,) \ + $(if $(CONFIG_FRAME_POINTER),, --no-fp) \ + $(if $(or $(CONFIG_GCOV_KERNEL),$(CONFIG_LTO_CLANG)), \ + --no-unreachable,) \ + $(if $(CONFIG_RETPOLINE), --retpoline,) \ + $(if $(CONFIG_X86_SMAP), --uaccess,) \ + $(if $(CONFIG_FTRACE_MCOUNT_USE_OBJTOOL), --mcount,) + # Useful for describing the dependency of composite objects # Usage: # $(call multi_depend, multi_used_targets, suffix_to_remove, suffix_to_add) diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal index 6de2c35b64e8..735e11e9041b 100644 --- a/scripts/Makefile.modfinal +++ b/scripts/Makefile.modfinal @@ -9,7 +9,7 @@ __modfinal: include include/config/auto.conf include $(srctree)/scripts/Kbuild.include -# for c_flags +# for c_flags and objtool_args include $(srctree)/scripts/Makefile.lib # find all modules listed in modules.order @@ -34,10 +34,23 @@ ifdef CONFIG_LTO_CLANG # With CONFIG_LTO_CLANG, reuse the object file we compiled for modpost to # avoid a second slow LTO link prelink-ext := .lto -endif + +# ELF processing was skipped earlier because we didn't have native code, +# so let's now process the prelinked binary before we link the module. + +ifdef CONFIG_STACK_VALIDATION +ifneq ($(SKIP_STACK_VALIDATION),1) +cmd_ld_ko_o += \ + $(objtree)/tools/objtool/objtool $(objtool_args) \ + $(@:.ko=$(prelink-ext).o); + +endif # SKIP_STACK_VALIDATION +endif # CONFIG_STACK_VALIDATION + +endif # CONFIG_LTO_CLANG quiet_cmd_ld_ko_o = LD [M] $@ - cmd_ld_ko_o = \ + cmd_ld_ko_o += \ $(LD) -r $(KBUILD_LDFLAGS) \ $(KBUILD_LDFLAGS_MODULE) $(LDFLAGS_MODULE) \ -T scripts/module.lds -o $@ $(filter %.o, $^); \ diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index c5919d5a0b4f..3b261b0f74f0 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -103,14 +103,36 @@ modpost_link() objtool_link() { + local objtoolcmd; local objtoolopt; + if [ "${CONFIG_LTO_CLANG} ${CONFIG_STACK_VALIDATION}" = "y y" ]; then + # Don't perform vmlinux validation unless explicitly requested, + # but run objtool on vmlinux.o now that we have an object file. + if [ -n "${CONFIG_UNWINDER_ORC}" ]; then + objtoolcmd="orc generate" + fi + + objtoolopt="${objtoolopt} --duplicate" + + if [ -n "${CONFIG_FTRACE_MCOUNT_USE_OBJTOOL}" ]; then + objtoolopt="${objtoolopt} --mcount" + fi + fi + if [ -n "${CONFIG_VMLINUX_VALIDATION}" ]; then - objtoolopt="check" + objtoolopt="${objtoolopt} --noinstr" + fi + + if [ -n "${objtoolopt}" ]; then + if [ -z "${objtoolcmd}" ]; then + objtoolcmd="check" + fi + objtoolopt="${objtoolopt} --vmlinux" if [ -z "${CONFIG_FRAME_POINTER}" ]; then objtoolopt="${objtoolopt} --no-fp" fi - if [ -n "${CONFIG_GCOV_KERNEL}" ]; then + if [ -n "${CONFIG_GCOV_KERNEL}" ] || [ -n "${CONFIG_LTO_CLANG}" ]; then objtoolopt="${objtoolopt} --no-unreachable" fi if [ -n "${CONFIG_RETPOLINE}" ]; then @@ -120,7 +142,7 @@ objtool_link() objtoolopt="${objtoolopt} --uaccess" fi info OBJTOOL ${1} - tools/objtool/objtool ${objtoolopt} ${1} + tools/objtool/objtool ${objtoolcmd} ${objtoolopt} ${1} fi } diff --git a/security/integrity/ima/ima_mok.c b/security/integrity/ima/ima_mok.c index 36cadadbfba4..1e5c01916173 100644 --- a/security/integrity/ima/ima_mok.c +++ b/security/integrity/ima/ima_mok.c @@ -38,13 +38,12 @@ __init int ima_mok_init(void) (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ | KEY_USR_WRITE | KEY_USR_SEARCH, - KEY_ALLOC_NOT_IN_QUOTA, + KEY_ALLOC_NOT_IN_QUOTA | + KEY_ALLOC_SET_KEEP, restriction, NULL); if (IS_ERR(ima_blacklist_keyring)) panic("Can't allocate IMA blacklist keyring."); - - set_bit(KEY_FLAG_KEEP, &ima_blacklist_keyring->flags); return 0; } device_initcall(ima_mok_init); diff --git a/security/keys/Kconfig b/security/keys/Kconfig index 83bc23409164..c161642a8484 100644 --- a/security/keys/Kconfig +++ b/security/keys/Kconfig @@ -119,7 +119,7 @@ config KEY_NOTIFICATIONS bool "Provide key/keyring change notifications" depends on KEYS && WATCH_QUEUE help - This option provides support for getting change notifications on keys - and keyrings on which the caller has View permission. This makes use - of the /dev/watch_queue misc device to handle the notification - buffer and provides KEYCTL_WATCH_KEY to enable/disable watches. + This option provides support for getting change notifications + on keys and keyrings on which the caller has View permission. + This makes use of pipes to handle the notification buffer and + provides KEYCTL_WATCH_KEY to enable/disable watches. diff --git a/security/keys/big_key.c b/security/keys/big_key.c index 691347dea3c1..d17e5f09eeb8 100644 --- a/security/keys/big_key.c +++ b/security/keys/big_key.c @@ -121,8 +121,7 @@ int big_key_preparse(struct key_preparsed_payload *prep) *path = file->f_path; path_get(path); fput(file); - memzero_explicit(buf, enclen); - kvfree(buf); + kvfree_sensitive(buf, enclen); } else { /* Just store the data in a buffer */ void *data = kmalloc(datalen, GFP_KERNEL); @@ -140,8 +139,7 @@ err_fput: err_enckey: kfree_sensitive(enckey); error: - memzero_explicit(buf, enclen); - kvfree(buf); + kvfree_sensitive(buf, enclen); return ret; } @@ -273,8 +271,7 @@ long big_key_read(const struct key *key, char *buffer, size_t buflen) err_fput: fput(file); error: - memzero_explicit(buf, enclen); - kvfree(buf); + kvfree_sensitive(buf, enclen); } else { ret = datalen; memcpy(buffer, key->payload.data[big_key_data], datalen); diff --git a/security/keys/key.c b/security/keys/key.c index ebe752b137aa..c45afdd1dfbb 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -303,6 +303,8 @@ struct key *key_alloc(struct key_type *type, const char *desc, key->flags |= 1 << KEY_FLAG_BUILTIN; if (flags & KEY_ALLOC_UID_KEYRING) key->flags |= 1 << KEY_FLAG_UID_KEYRING; + if (flags & KEY_ALLOC_SET_KEEP) + key->flags |= 1 << KEY_FLAG_KEEP; #ifdef KEY_DEBUGGING key->magic = KEY_DEBUG_MAGIC; diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index 61a614c21b9b..96a92a645216 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -506,7 +506,7 @@ error: * keyring, otherwise replace the link to the matching key with a link to the * new key. * - * The key must grant the caller Link permission and the the keyring must grant + * The key must grant the caller Link permission and the keyring must grant * the caller Write permission. Furthermore, if an additional link is created, * the keyring's quota will be extended. * diff --git a/security/keys/keyctl_pkey.c b/security/keys/keyctl_pkey.c index 931d8dfb4a7f..5de0d599a274 100644 --- a/security/keys/keyctl_pkey.c +++ b/security/keys/keyctl_pkey.c @@ -166,8 +166,6 @@ long keyctl_pkey_query(key_serial_t id, struct kernel_pkey_query res; long ret; - memset(¶ms, 0, sizeof(params)); - ret = keyctl_pkey_params_get(id, _info, ¶ms); if (ret < 0) goto error; diff --git a/security/keys/keyring.c b/security/keys/keyring.c index 14abfe765b7e..5e6a90760753 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -452,7 +452,7 @@ static void keyring_describe(const struct key *keyring, struct seq_file *m) struct keyring_read_iterator_context { size_t buflen; size_t count; - key_serial_t __user *buffer; + key_serial_t *buffer; }; static int keyring_read_iterator(const void *object, void *data) @@ -479,7 +479,7 @@ static int keyring_read_iterator(const void *object, void *data) * times. */ static long keyring_read(const struct key *keyring, - char __user *buffer, size_t buflen) + char *buffer, size_t buflen) { struct keyring_read_iterator_context ctx; long ret; @@ -491,7 +491,7 @@ static long keyring_read(const struct key *keyring, /* Copy as many key IDs as fit into the buffer */ if (buffer && buflen) { - ctx.buffer = (key_serial_t __user *)buffer; + ctx.buffer = (key_serial_t *)buffer; ctx.buflen = buflen; ctx.count = 0; ret = assoc_array_iterate(&keyring->keys, @@ -881,7 +881,7 @@ found: * * Keys are matched to the type provided and are then filtered by the match * function, which is given the description to use in any way it sees fit. The - * match function may use any attributes of a key that it wishes to to + * match function may use any attributes of a key that it wishes to * determine the match. Normally the match function from the key type would be * used. * @@ -1204,7 +1204,7 @@ static int keyring_detect_cycle_iterator(const void *object, } /* - * See if a cycle will will be created by inserting acyclic tree B in acyclic + * See if a cycle will be created by inserting acyclic tree B in acyclic * tree A at the topmost level (ie: as a direct child of A). * * Since we are adding B to A at the top level, checking for cycles should just diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c index 1fe8b934f656..e3d79a7b6db6 100644 --- a/security/keys/process_keys.c +++ b/security/keys/process_keys.c @@ -783,6 +783,7 @@ try_again: if (need_perm != KEY_AUTHTOKEN_OVERRIDE && need_perm != KEY_DEFER_PERM_CHECK) goto invalid_key; + break; case 0: break; } diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index f47951e19c9d..c3a85d8f6c5c 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -18,7 +18,7 @@ #include #include -bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats, validate_dup, vmlinux; +bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats, validate_dup, vmlinux, mcount, noinstr; static const char * const check_usage[] = { "objtool check [] file.o", @@ -34,13 +34,15 @@ const struct option check_options[] = { OPT_BOOLEAN('a', "uaccess", &uaccess, "enable uaccess checking"), OPT_BOOLEAN('s', "stats", &stats, "print statistics"), OPT_BOOLEAN('d', "duplicate", &validate_dup, "duplicate validation for vmlinux.o"), + OPT_BOOLEAN('n', "noinstr", &noinstr, "noinstr validation for vmlinux.o"), OPT_BOOLEAN('l', "vmlinux", &vmlinux, "vmlinux.o validation"), + OPT_BOOLEAN('M', "mcount", &mcount, "generate __mcount_loc"), OPT_END(), }; int cmd_check(int argc, const char **argv) { - const char *objname, *s; + const char *objname; struct objtool_file *file; int ret; @@ -51,10 +53,6 @@ int cmd_check(int argc, const char **argv) objname = argv[0]; - s = strstr(objname, "vmlinux.o"); - if (s && !s[9]) - vmlinux = true; - file = objtool_open_read(objname); if (!file) return 1; diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 331a763d8775..080a3d6cbd75 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -249,7 +249,7 @@ static void init_insn_state(struct insn_state *state, struct section *sec) * not correctly determine insn->call_dest->sec (external symbols do * not have a section). */ - if (vmlinux && sec) + if (vmlinux && noinstr && sec) state->noinstr = sec->noinstr; } @@ -548,6 +548,78 @@ static int create_static_call_sections(struct objtool_file *file) return 0; } +static int create_mcount_loc_sections(struct objtool_file *file) +{ + struct section *sec, *reloc_sec; + struct reloc *reloc; + unsigned long *loc; + struct instruction *insn; + int idx; + + sec = find_section_by_name(file->elf, "__mcount_loc"); + if (sec) { + INIT_LIST_HEAD(&file->mcount_loc_list); + WARN("file already has __mcount_loc section, skipping"); + return 0; + } + + if (list_empty(&file->mcount_loc_list)) + return 0; + + idx = 0; + list_for_each_entry(insn, &file->mcount_loc_list, mcount_loc_node) + idx++; + + sec = elf_create_section(file->elf, "__mcount_loc", 0, sizeof(unsigned long), idx); + if (!sec) + return -1; + + reloc_sec = elf_create_reloc_section(file->elf, sec, SHT_RELA); + if (!reloc_sec) + return -1; + + idx = 0; + list_for_each_entry(insn, &file->mcount_loc_list, mcount_loc_node) { + + loc = (unsigned long *)sec->data->d_buf + idx; + memset(loc, 0, sizeof(unsigned long)); + + reloc = malloc(sizeof(*reloc)); + if (!reloc) { + perror("malloc"); + return -1; + } + memset(reloc, 0, sizeof(*reloc)); + + if (insn->sec->sym) { + reloc->sym = insn->sec->sym; + reloc->addend = insn->offset; + } else { + reloc->sym = find_symbol_containing(insn->sec, insn->offset); + + if (!reloc->sym) { + WARN("missing symbol for insn at offset 0x%lx\n", + insn->offset); + return -1; + } + + reloc->addend = insn->offset - reloc->sym->offset; + } + + reloc->type = R_X86_64_64; + reloc->offset = idx * sizeof(unsigned long); + reloc->sec = reloc_sec; + elf_add_reloc(file->elf, reloc); + + idx++; + } + + if (elf_rebuild_reloc_section(file->elf, reloc_sec)) + return -1; + + return 0; +} + /* * Warnings shouldn't be reported for ignored functions. */ @@ -975,6 +1047,22 @@ static int add_call_destinations(struct objtool_file *file) insn->type = INSN_NOP; } + if (mcount && !strcmp(insn->call_dest->name, "__fentry__")) { + if (reloc) { + reloc->type = R_NONE; + elf_write_reloc(file->elf, reloc); + } + + elf_write_insn(file->elf, insn->sec, + insn->offset, insn->len, + arch_nop_insn(insn->len)); + + insn->type = INSN_NOP; + + list_add_tail(&insn->mcount_loc_node, + &file->mcount_loc_list); + } + /* * Whatever stack impact regular CALLs have, should be undone * by the RETURN of the called function. @@ -3048,6 +3136,13 @@ int check(struct objtool_file *file) goto out; warnings += ret; + if (mcount) { + ret = create_mcount_loc_sections(file); + if (ret < 0) + goto out; + warnings += ret; + } + out: /* * For now, don't fail the kernel build on fatal warnings. These diff --git a/tools/objtool/include/objtool/builtin.h b/tools/objtool/include/objtool/builtin.h index 85c979caa367..2502bb27de17 100644 --- a/tools/objtool/include/objtool/builtin.h +++ b/tools/objtool/include/objtool/builtin.h @@ -8,7 +8,7 @@ #include extern const struct option check_options[]; -extern bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats, validate_dup, vmlinux; +extern bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats, validate_dup, vmlinux, mcount, noinstr; extern int cmd_check(int argc, const char **argv); extern int cmd_orc(int argc, const char **argv); diff --git a/tools/objtool/include/objtool/check.h b/tools/objtool/include/objtool/check.h index 4891ead0e85f..f5be798107bc 100644 --- a/tools/objtool/include/objtool/check.h +++ b/tools/objtool/include/objtool/check.h @@ -40,6 +40,7 @@ struct instruction { struct list_head list; struct hlist_node hash; struct list_head static_call_node; + struct list_head mcount_loc_node; struct section *sec; unsigned long offset; unsigned int len; diff --git a/tools/objtool/include/objtool/objtool.h b/tools/objtool/include/objtool/objtool.h index e114642efb65..e68e37476c15 100644 --- a/tools/objtool/include/objtool/objtool.h +++ b/tools/objtool/include/objtool/objtool.h @@ -19,6 +19,7 @@ struct objtool_file { struct list_head insn_list; DECLARE_HASHTABLE(insn_hash, 20); struct list_head static_call_list; + struct list_head mcount_loc_list; bool ignore_unreachables, c_file, hints, rodata; }; diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c index e848feb0a5fc..7b97ce499405 100644 --- a/tools/objtool/objtool.c +++ b/tools/objtool/objtool.c @@ -62,6 +62,7 @@ struct objtool_file *objtool_open_read(const char *_objname) INIT_LIST_HEAD(&file.insn_list); hash_init(file.insn_hash); INIT_LIST_HEAD(&file.static_call_list); + INIT_LIST_HEAD(&file.mcount_loc_list); file.c_file = !vmlinux && find_section_by_name(file.elf, ".comment"); file.ignore_unreachables = no_unreachable; file.hints = false; diff --git a/tools/testing/selftests/dma/dma_map_benchmark.c b/tools/testing/selftests/dma/dma_map_benchmark.c index 537d65968c48..fb23ce9617ea 100644 --- a/tools/testing/selftests/dma/dma_map_benchmark.c +++ b/tools/testing/selftests/dma/dma_map_benchmark.c @@ -12,9 +12,12 @@ #include #include +#define NSEC_PER_MSEC 1000000L + #define DMA_MAP_BENCHMARK _IOWR('d', 1, struct map_benchmark) #define DMA_MAP_MAX_THREADS 1024 #define DMA_MAP_MAX_SECONDS 300 +#define DMA_MAP_MAX_TRANS_DELAY (10 * NSEC_PER_MSEC) #define DMA_MAP_BIDIRECTIONAL 0 #define DMA_MAP_TO_DEVICE 1 @@ -36,7 +39,8 @@ struct map_benchmark { __s32 node; /* which numa node this benchmark will run on */ __u32 dma_bits; /* DMA addressing capability */ __u32 dma_dir; /* DMA data direction */ - __u8 expansion[84]; /* For future use */ + __u32 dma_trans_ns; /* time for DMA transmission in ns */ + __u8 expansion[80]; /* For future use */ }; int main(int argc, char **argv) @@ -46,12 +50,12 @@ int main(int argc, char **argv) /* default single thread, run 20 seconds on NUMA_NO_NODE */ int threads = 1, seconds = 20, node = -1; /* default dma mask 32bit, bidirectional DMA */ - int bits = 32, dir = DMA_MAP_BIDIRECTIONAL; + int bits = 32, xdelay = 0, dir = DMA_MAP_BIDIRECTIONAL; int cmd = DMA_MAP_BENCHMARK; char *p; - while ((opt = getopt(argc, argv, "t:s:n:b:d:")) != -1) { + while ((opt = getopt(argc, argv, "t:s:n:b:d:x:")) != -1) { switch (opt) { case 't': threads = atoi(optarg); @@ -68,6 +72,9 @@ int main(int argc, char **argv) case 'd': dir = atoi(optarg); break; + case 'x': + xdelay = atoi(optarg); + break; default: return -1; } @@ -85,6 +92,12 @@ int main(int argc, char **argv) exit(1); } + if (xdelay < 0 || xdelay > DMA_MAP_MAX_TRANS_DELAY) { + fprintf(stderr, "invalid transmit delay, must be in 0-%ld\n", + DMA_MAP_MAX_TRANS_DELAY); + exit(1); + } + /* suppose the mininum DMA zone is 1MB in the world */ if (bits < 20 || bits > 64) { fprintf(stderr, "invalid dma mask bit, must be in 20-64\n"); @@ -109,6 +122,8 @@ int main(int argc, char **argv) map.node = node; map.dma_bits = bits; map.dma_dir = dir; + map.dma_trans_ns = xdelay; + if (ioctl(fd, cmd, &map)) { perror("ioctl"); exit(1);