From ae7c18380495ac5c14a614fdb6c452c3bf9148ac Mon Sep 17 00:00:00 2001 From: Hanjun Guo Date: Tue, 7 Mar 2017 20:40:05 +0800 Subject: ACPI: platform-msi: retrieve devid from IORT For devices connecting to an ITS, the devices need to identify themself through a devid; this devid is represented in the IORT table in named component node [1] for platform devices, so this patch adds code that scans the IORT table to retrieve the devices devid. Add an IORT interface to collect ITS devices devid to carry out platform devices MSI mappings with IORT tables. [1]: https://static.docs.arm.com/den0049/b/DEN0049B_IO_Remapping_Table.pdf Signed-off-by: Hanjun Guo [lorenzo.pieralisi@arm.com: rewrote commit log/dropped ITS changes] Signed-off-by: Lorenzo Pieralisi Tested-by: Ming Lei Tested-by: Wei Xu Tested-by: Sinan Kaya Cc: Marc Zyngier Cc: Lorenzo Pieralisi Cc: Tomasz Nowicki Cc: Thomas Gleixner --- include/linux/acpi_iort.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 77e08099e554..fd8b9698e1d1 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -34,6 +34,7 @@ void acpi_iort_init(void); bool iort_node_match(u8 type); u32 iort_msi_map_rid(struct device *dev, u32 req_id); struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id); +int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id); /* IOMMU interface */ void iort_set_dma_mask(struct device *dev); const struct iommu_ops *iort_iommu_configure(struct device *dev); -- cgit v1.2.3 From d4f54a186667ffd19eac8e3f48c51d940a9b9784 Mon Sep 17 00:00:00 2001 From: Hanjun Guo Date: Tue, 7 Mar 2017 20:40:06 +0800 Subject: ACPI: platform: setup MSI domain for ACPI based platform device By allowing platform MSI domain to be created on ACPI platforms, a platform device MSI domain can be set-up when it is probed. In order to do that, the MSI domain the platform device connects to should be retrieved, so the iort_get_platform_device_domain() is introduced to retrieve the domain from the IORT kernel layer. With the domain retrieved, we need a proper way to set the domain to platform device. Given that some platform devices (irqchips) require the MSI irqdomain to be their interrupt parent domain, the MSI irqdomain should be determined before platform device is probed but after the platform device is allocated which means that the code setting up the MSI irqdomain, ie acpi_configure_pmsi_domain() should be called in acpi_platform_notify() (that is triggered after adding a device but before the respective driver is probed) for the platform MSI domain code set-up path to work properly. Acked-by: Rafael J. Wysocki [for glue.c] Signed-off-by: Hanjun Guo [lorenzo.pieralisi@arm.com: rewrote commit log] Signed-off-by: Lorenzo Pieralisi Tested-by: Ming Lei Tested-by: Wei Xu Tested-by: Sinan Kaya Cc: Marc Zyngier Cc: Lorenzo Pieralisi Cc: Tomasz Nowicki --- include/linux/acpi_iort.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index fd8b9698e1d1..26e25d85eb3e 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -34,6 +34,7 @@ void acpi_iort_init(void); bool iort_node_match(u8 type); u32 iort_msi_map_rid(struct device *dev, u32 req_id); struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id); +void acpi_configure_pmsi_domain(struct device *dev); int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id); /* IOMMU interface */ void iort_set_dma_mask(struct device *dev); @@ -46,6 +47,7 @@ static inline u32 iort_msi_map_rid(struct device *dev, u32 req_id) static inline struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id) { return NULL; } +static inline void acpi_configure_pmsi_domain(struct device *dev) { } /* IOMMU interface */ static inline void iort_set_dma_mask(struct device *dev) { } static inline -- cgit v1.2.3 From 7ed98e0168bd23d8ea3294e95254cc5b4000c948 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 10 Mar 2017 10:46:14 +0000 Subject: drivers/perf: arm_pmu: manage interrupts per-cpu When requesting or freeing interrupts, we use platform_get_irq() to find relevant irqs, backing this up with additional information in an optional irq_affinity table. This means that our irq request and free paths are tied to a platform_device, and our request path must jump through a number of hoops in order to determine the required affinity of each interrupt. Given that the affinity must be static, we can compute the affinity once up-front at probe time, simplifying the irq request and free paths. By recording interrupts in a per-cpu data structure, we simplify a few paths, and permit a subsequent rework of the request and free paths. Signed-off-by: Mark Rutland [will: rename local nr_irqs variable to avoid conflict with global] Signed-off-by: Will Deacon --- include/linux/perf/arm_pmu.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 8462da266089..05a3eb447fc8 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -75,6 +75,8 @@ struct pmu_hw_events { * already have to allocate this struct per cpu. */ struct arm_pmu *percpu_pmu; + + int irq; }; enum armpmu_attr_groups { @@ -88,7 +90,6 @@ struct arm_pmu { struct pmu pmu; cpumask_t active_irqs; cpumask_t supported_cpus; - int *irq_affinity; char *name; irqreturn_t (*handle_irq)(int irq_num, void *dev); void (*enable)(struct perf_event *event); -- cgit v1.2.3 From c09adab01e4aeecfa3dfae0946409844400c5901 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 10 Mar 2017 10:46:15 +0000 Subject: drivers/perf: arm_pmu: split irq request from enable For historical reasons, we lazily request and free interrupts in the arm pmu driver. This requires us to refcount use of the pmu (by way of counting the active events) in order to request/free interrupts at the correct times, which complicates the driver somewhat. The existing logic is flawed, as it only considers currently online CPUs when requesting, freeing, or managing the affinity of interrupts. Intervening hotplug events can result in erroneous IRQ affinity, online CPUs for which interrupts have not been requested, or offline CPUs whose interrupts are still requested. To fix this, this patch splits the requesting of interrupts from any per-cpu management (i.e. per-cpu enable/disable, and configuration of cpu affinity). We now request all interrupts up-front at probe time (and never free them, since we never unregister PMUs). The management of affinity, and per-cpu enable/disable now happens in our cpu hotplug callback, ensuring it occurs consistently. This means that we must now invoke the CPU hotplug callback at boot time in order to configure IRQs, and since the callback also resets the PMU hardware, we can remove the duplicate reset in the probe path. This rework renders our event refcounting unnecessary, so this is removed. Signed-off-by: Mark Rutland [will: make armpmu_get_cpu_irq static] Signed-off-by: Will Deacon --- include/linux/perf/arm_pmu.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 05a3eb447fc8..44f43fcf2524 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -105,12 +105,8 @@ struct arm_pmu { void (*start)(struct arm_pmu *); void (*stop)(struct arm_pmu *); void (*reset)(void *); - int (*request_irq)(struct arm_pmu *, irq_handler_t handler); - void (*free_irq)(struct arm_pmu *); int (*map_event)(struct perf_event *event); int num_events; - atomic_t active_events; - struct mutex reserve_mutex; u64 max_period; bool secure_access; /* 32-bit ARM only */ #define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40 -- cgit v1.2.3 From 3071f13d75f627ed8648535815a0506d50cbc6ed Mon Sep 17 00:00:00 2001 From: Agustin Vega-Frias Date: Fri, 31 Mar 2017 14:13:43 -0400 Subject: perf: qcom: Add L3 cache PMU driver This adds a new dynamic PMU to the Perf Events framework to program and control the L3 cache PMUs in some Qualcomm Technologies SOCs. The driver supports a distributed cache architecture where the overall cache for a socket is comprised of multiple slices each with its own PMU. Access to each individual PMU is provided even though all CPUs share all the slices. User space needs to aggregate to individual counts to provide a global picture. The driver exports formatting and event information to sysfs so it can be used by the perf user space tools with the syntaxes: perf stat -a -e l3cache_0_0/read-miss/ perf stat -a -e l3cache_0_0/event=0x21/ Acked-by: Mark Rutland Signed-off-by: Agustin Vega-Frias [will: fixed sparse issues] Signed-off-by: Will Deacon --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 62d240e962f0..cfcfab37d9c4 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -137,6 +137,7 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_CCN_ONLINE, CPUHP_AP_PERF_ARM_L2X0_ONLINE, CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE, + CPUHP_AP_PERF_ARM_QCOM_L3_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_RCUTREE_ONLINE, CPUHP_AP_ONLINE_DYN, -- cgit v1.2.3 From 65c2e69b3ccaa359032cfc35c4dbb8d235f63e5b Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 23 Mar 2017 19:00:44 +0000 Subject: include: pe.h: allow for use in assembly Some of the definitions in include/linux/pe.h would be useful for the EFI stub headers, where values are currently open-coded. Unfortunately they cannot be used as some structures are also defined in pe.h without !__ASSEMBLY__ guards. This patch moves the structure definitions into an #ifdef __ASSEMBLY__ block, so that the common value definitions can be used from assembly. Signed-off-by: Mark Rutland Signed-off-by: Ard Biesheuvel Signed-off-by: Catalin Marinas --- include/linux/pe.h | 174 +++++++++++++++++++++++++++-------------------------- 1 file changed, 89 insertions(+), 85 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pe.h b/include/linux/pe.h index e170b95e763b..a8a594117df3 100644 --- a/include/linux/pe.h +++ b/include/linux/pe.h @@ -23,34 +23,6 @@ #define MZ_MAGIC 0x5a4d /* "MZ" */ -struct mz_hdr { - uint16_t magic; /* MZ_MAGIC */ - uint16_t lbsize; /* size of last used block */ - uint16_t blocks; /* pages in file, 0x3 */ - uint16_t relocs; /* relocations */ - uint16_t hdrsize; /* header size in "paragraphs" */ - uint16_t min_extra_pps; /* .bss */ - uint16_t max_extra_pps; /* runtime limit for the arena size */ - uint16_t ss; /* relative stack segment */ - uint16_t sp; /* initial %sp register */ - uint16_t checksum; /* word checksum */ - uint16_t ip; /* initial %ip register */ - uint16_t cs; /* initial %cs relative to load segment */ - uint16_t reloc_table_offset; /* offset of the first relocation */ - uint16_t overlay_num; /* overlay number. set to 0. */ - uint16_t reserved0[4]; /* reserved */ - uint16_t oem_id; /* oem identifier */ - uint16_t oem_info; /* oem specific */ - uint16_t reserved1[10]; /* reserved */ - uint32_t peaddr; /* address of pe header */ - char message[64]; /* message to print */ -}; - -struct mz_reloc { - uint16_t offset; - uint16_t segment; -}; - #define PE_MAGIC 0x00004550 /* "PE\0\0" */ #define PE_OPT_MAGIC_PE32 0x010b #define PE_OPT_MAGIC_PE32_ROM 0x0107 @@ -98,17 +70,6 @@ struct mz_reloc { #define IMAGE_FILE_UP_SYSTEM_ONLY 0x4000 #define IMAGE_FILE_BYTES_REVERSED_HI 0x8000 -struct pe_hdr { - uint32_t magic; /* PE magic */ - uint16_t machine; /* machine type */ - uint16_t sections; /* number of sections */ - uint32_t timestamp; /* time_t */ - uint32_t symbol_table; /* symbol table offset */ - uint32_t symbols; /* number of symbols */ - uint16_t opt_hdr_size; /* size of optional header */ - uint16_t flags; /* flags */ -}; - #define IMAGE_FILE_OPT_ROM_MAGIC 0x107 #define IMAGE_FILE_OPT_PE32_MAGIC 0x10b #define IMAGE_FILE_OPT_PE32_PLUS_MAGIC 0x20b @@ -134,6 +95,93 @@ struct pe_hdr { #define IMAGE_DLLCHARACTERISTICS_WDM_DRIVER 0x2000 #define IMAGE_DLLCHARACTERISTICS_TERMINAL_SERVER_AWARE 0x8000 +/* they actually defined 0x00000000 as well, but I think we'll skip that one. */ +#define IMAGE_SCN_RESERVED_0 0x00000001 +#define IMAGE_SCN_RESERVED_1 0x00000002 +#define IMAGE_SCN_RESERVED_2 0x00000004 +#define IMAGE_SCN_TYPE_NO_PAD 0x00000008 /* don't pad - obsolete */ +#define IMAGE_SCN_RESERVED_3 0x00000010 +#define IMAGE_SCN_CNT_CODE 0x00000020 /* .text */ +#define IMAGE_SCN_CNT_INITIALIZED_DATA 0x00000040 /* .data */ +#define IMAGE_SCN_CNT_UNINITIALIZED_DATA 0x00000080 /* .bss */ +#define IMAGE_SCN_LNK_OTHER 0x00000100 /* reserved */ +#define IMAGE_SCN_LNK_INFO 0x00000200 /* .drectve comments */ +#define IMAGE_SCN_RESERVED_4 0x00000400 +#define IMAGE_SCN_LNK_REMOVE 0x00000800 /* .o only - scn to be rm'd*/ +#define IMAGE_SCN_LNK_COMDAT 0x00001000 /* .o only - COMDAT data */ +#define IMAGE_SCN_RESERVED_5 0x00002000 /* spec omits this */ +#define IMAGE_SCN_RESERVED_6 0x00004000 /* spec omits this */ +#define IMAGE_SCN_GPREL 0x00008000 /* global pointer referenced data */ +/* spec lists 0x20000 twice, I suspect they meant 0x10000 for one of them */ +#define IMAGE_SCN_MEM_PURGEABLE 0x00010000 /* reserved for "future" use */ +#define IMAGE_SCN_16BIT 0x00020000 /* reserved for "future" use */ +#define IMAGE_SCN_LOCKED 0x00040000 /* reserved for "future" use */ +#define IMAGE_SCN_PRELOAD 0x00080000 /* reserved for "future" use */ +/* and here they just stuck a 1-byte integer in the middle of a bitfield */ +#define IMAGE_SCN_ALIGN_1BYTES 0x00100000 /* it does what it says on the box */ +#define IMAGE_SCN_ALIGN_2BYTES 0x00200000 +#define IMAGE_SCN_ALIGN_4BYTES 0x00300000 +#define IMAGE_SCN_ALIGN_8BYTES 0x00400000 +#define IMAGE_SCN_ALIGN_16BYTES 0x00500000 +#define IMAGE_SCN_ALIGN_32BYTES 0x00600000 +#define IMAGE_SCN_ALIGN_64BYTES 0x00700000 +#define IMAGE_SCN_ALIGN_128BYTES 0x00800000 +#define IMAGE_SCN_ALIGN_256BYTES 0x00900000 +#define IMAGE_SCN_ALIGN_512BYTES 0x00a00000 +#define IMAGE_SCN_ALIGN_1024BYTES 0x00b00000 +#define IMAGE_SCN_ALIGN_2048BYTES 0x00c00000 +#define IMAGE_SCN_ALIGN_4096BYTES 0x00d00000 +#define IMAGE_SCN_ALIGN_8192BYTES 0x00e00000 +#define IMAGE_SCN_LNK_NRELOC_OVFL 0x01000000 /* extended relocations */ +#define IMAGE_SCN_MEM_DISCARDABLE 0x02000000 /* scn can be discarded */ +#define IMAGE_SCN_MEM_NOT_CACHED 0x04000000 /* cannot be cached */ +#define IMAGE_SCN_MEM_NOT_PAGED 0x08000000 /* not pageable */ +#define IMAGE_SCN_MEM_SHARED 0x10000000 /* can be shared */ +#define IMAGE_SCN_MEM_EXECUTE 0x20000000 /* can be executed as code */ +#define IMAGE_SCN_MEM_READ 0x40000000 /* readable */ +#define IMAGE_SCN_MEM_WRITE 0x80000000 /* writeable */ + +#ifndef __ASSEMBLY__ + +struct mz_hdr { + uint16_t magic; /* MZ_MAGIC */ + uint16_t lbsize; /* size of last used block */ + uint16_t blocks; /* pages in file, 0x3 */ + uint16_t relocs; /* relocations */ + uint16_t hdrsize; /* header size in "paragraphs" */ + uint16_t min_extra_pps; /* .bss */ + uint16_t max_extra_pps; /* runtime limit for the arena size */ + uint16_t ss; /* relative stack segment */ + uint16_t sp; /* initial %sp register */ + uint16_t checksum; /* word checksum */ + uint16_t ip; /* initial %ip register */ + uint16_t cs; /* initial %cs relative to load segment */ + uint16_t reloc_table_offset; /* offset of the first relocation */ + uint16_t overlay_num; /* overlay number. set to 0. */ + uint16_t reserved0[4]; /* reserved */ + uint16_t oem_id; /* oem identifier */ + uint16_t oem_info; /* oem specific */ + uint16_t reserved1[10]; /* reserved */ + uint32_t peaddr; /* address of pe header */ + char message[64]; /* message to print */ +}; + +struct mz_reloc { + uint16_t offset; + uint16_t segment; +}; + +struct pe_hdr { + uint32_t magic; /* PE magic */ + uint16_t machine; /* machine type */ + uint16_t sections; /* number of sections */ + uint32_t timestamp; /* time_t */ + uint32_t symbol_table; /* symbol table offset */ + uint32_t symbols; /* number of symbols */ + uint16_t opt_hdr_size; /* size of optional header */ + uint16_t flags; /* flags */ +}; + /* the fact that pe32 isn't padded where pe32+ is 64-bit means union won't * work right. vomit. */ struct pe32_opt_hdr { @@ -243,52 +291,6 @@ struct section_header { uint32_t flags; }; -/* they actually defined 0x00000000 as well, but I think we'll skip that one. */ -#define IMAGE_SCN_RESERVED_0 0x00000001 -#define IMAGE_SCN_RESERVED_1 0x00000002 -#define IMAGE_SCN_RESERVED_2 0x00000004 -#define IMAGE_SCN_TYPE_NO_PAD 0x00000008 /* don't pad - obsolete */ -#define IMAGE_SCN_RESERVED_3 0x00000010 -#define IMAGE_SCN_CNT_CODE 0x00000020 /* .text */ -#define IMAGE_SCN_CNT_INITIALIZED_DATA 0x00000040 /* .data */ -#define IMAGE_SCN_CNT_UNINITIALIZED_DATA 0x00000080 /* .bss */ -#define IMAGE_SCN_LNK_OTHER 0x00000100 /* reserved */ -#define IMAGE_SCN_LNK_INFO 0x00000200 /* .drectve comments */ -#define IMAGE_SCN_RESERVED_4 0x00000400 -#define IMAGE_SCN_LNK_REMOVE 0x00000800 /* .o only - scn to be rm'd*/ -#define IMAGE_SCN_LNK_COMDAT 0x00001000 /* .o only - COMDAT data */ -#define IMAGE_SCN_RESERVED_5 0x00002000 /* spec omits this */ -#define IMAGE_SCN_RESERVED_6 0x00004000 /* spec omits this */ -#define IMAGE_SCN_GPREL 0x00008000 /* global pointer referenced data */ -/* spec lists 0x20000 twice, I suspect they meant 0x10000 for one of them */ -#define IMAGE_SCN_MEM_PURGEABLE 0x00010000 /* reserved for "future" use */ -#define IMAGE_SCN_16BIT 0x00020000 /* reserved for "future" use */ -#define IMAGE_SCN_LOCKED 0x00040000 /* reserved for "future" use */ -#define IMAGE_SCN_PRELOAD 0x00080000 /* reserved for "future" use */ -/* and here they just stuck a 1-byte integer in the middle of a bitfield */ -#define IMAGE_SCN_ALIGN_1BYTES 0x00100000 /* it does what it says on the box */ -#define IMAGE_SCN_ALIGN_2BYTES 0x00200000 -#define IMAGE_SCN_ALIGN_4BYTES 0x00300000 -#define IMAGE_SCN_ALIGN_8BYTES 0x00400000 -#define IMAGE_SCN_ALIGN_16BYTES 0x00500000 -#define IMAGE_SCN_ALIGN_32BYTES 0x00600000 -#define IMAGE_SCN_ALIGN_64BYTES 0x00700000 -#define IMAGE_SCN_ALIGN_128BYTES 0x00800000 -#define IMAGE_SCN_ALIGN_256BYTES 0x00900000 -#define IMAGE_SCN_ALIGN_512BYTES 0x00a00000 -#define IMAGE_SCN_ALIGN_1024BYTES 0x00b00000 -#define IMAGE_SCN_ALIGN_2048BYTES 0x00c00000 -#define IMAGE_SCN_ALIGN_4096BYTES 0x00d00000 -#define IMAGE_SCN_ALIGN_8192BYTES 0x00e00000 -#define IMAGE_SCN_LNK_NRELOC_OVFL 0x01000000 /* extended relocations */ -#define IMAGE_SCN_MEM_DISCARDABLE 0x02000000 /* scn can be discarded */ -#define IMAGE_SCN_MEM_NOT_CACHED 0x04000000 /* cannot be cached */ -#define IMAGE_SCN_MEM_NOT_PAGED 0x08000000 /* not pageable */ -#define IMAGE_SCN_MEM_SHARED 0x10000000 /* can be shared */ -#define IMAGE_SCN_MEM_EXECUTE 0x20000000 /* can be executed as code */ -#define IMAGE_SCN_MEM_READ 0x40000000 /* readable */ -#define IMAGE_SCN_MEM_WRITE 0x80000000 /* writeable */ - enum x64_coff_reloc_type { IMAGE_REL_AMD64_ABSOLUTE = 0, IMAGE_REL_AMD64_ADDR64, @@ -445,4 +447,6 @@ struct win_certificate { uint16_t cert_type; }; +#endif /* !__ASSEMBLY__ */ + #endif /* __LINUX_PE_H */ -- cgit v1.2.3 From 6f5541ba0eed842445a99b411d0f34103bcbbea1 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 23 Mar 2017 19:00:45 +0000 Subject: include: pe.h: add some missing definitions Add the missing IMAGE_FILE_MACHINE_ARM64 and IMAGE_DEBUG_TYPE_CODEVIEW definitions. We'll need them for the arm64 EFI stub... Signed-off-by: Mark Rutland [ardb: add IMAGE_DEBUG_TYPE_CODEVIEW as well] Signed-off-by: Ard Biesheuvel Signed-off-by: Catalin Marinas --- include/linux/pe.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pe.h b/include/linux/pe.h index a8a594117df3..143ce75be5f0 100644 --- a/include/linux/pe.h +++ b/include/linux/pe.h @@ -34,6 +34,7 @@ #define IMAGE_FILE_MACHINE_AMD64 0x8664 #define IMAGE_FILE_MACHINE_ARM 0x01c0 #define IMAGE_FILE_MACHINE_ARMV7 0x01c4 +#define IMAGE_FILE_MACHINE_ARM64 0xaa64 #define IMAGE_FILE_MACHINE_EBC 0x0ebc #define IMAGE_FILE_MACHINE_I386 0x014c #define IMAGE_FILE_MACHINE_IA64 0x0200 @@ -141,6 +142,8 @@ #define IMAGE_SCN_MEM_READ 0x40000000 /* readable */ #define IMAGE_SCN_MEM_WRITE 0x80000000 /* writeable */ +#define IMAGE_DEBUG_TYPE_CODEVIEW 2 + #ifndef __ASSEMBLY__ struct mz_hdr { -- cgit v1.2.3 From 4c546b8a34690ca858e50f2017b8bb6e358365d1 Mon Sep 17 00:00:00 2001 From: AKASHI Takahiro Date: Mon, 3 Apr 2017 11:23:54 +0900 Subject: memblock: add memblock_clear_nomap() This function, with a combination of memblock_mark_nomap(), will be used in a later kdump patch for arm64 when it temporarily isolates some range of memory from the other memory blocks in order to create a specific kernel mapping at boot time. Signed-off-by: AKASHI Takahiro Reviewed-by: Ard Biesheuvel Signed-off-by: Catalin Marinas --- include/linux/memblock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index bdfc65af4152..e82daffcfc44 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -93,6 +93,7 @@ int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size); int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size); int memblock_mark_mirror(phys_addr_t base, phys_addr_t size); int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); +int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); ulong choose_memblock_flags(void); /* Low level functions */ -- cgit v1.2.3 From c9ca9b4e2198a4dbeb83739460d4a7ff9ffed24f Mon Sep 17 00:00:00 2001 From: AKASHI Takahiro Date: Mon, 3 Apr 2017 11:23:55 +0900 Subject: memblock: add memblock_cap_memory_range() Add memblock_cap_memory_range() which will remove all the memblock regions except the memory range specified in the arguments. In addition, rework is done on memblock_mem_limit_remove_map() to re-implement it using memblock_cap_memory_range(). This function, like memblock_mem_limit_remove_map(), will not remove memblocks with MEMMAP_NOMAP attribute as they may be mapped and accessed later as "device memory." See the commit a571d4eb55d8 ("mm/memblock.c: add new infrastructure to address the mem limit issue"). This function is used, in a succeeding patch in the series of arm64 kdump suuport, to limit the range of usable memory, or System RAM, on crash dump kernel. (Please note that "mem=" parameter is of little use for this purpose.) Signed-off-by: AKASHI Takahiro Reviewed-by: Will Deacon Acked-by: Catalin Marinas Acked-by: Dennis Chen Cc: linux-mm@kvack.org Cc: Andrew Morton Reviewed-by: Ard Biesheuvel Signed-off-by: Catalin Marinas --- include/linux/memblock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index e82daffcfc44..4ce24a376262 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -336,6 +336,7 @@ phys_addr_t memblock_mem_size(unsigned long limit_pfn); phys_addr_t memblock_start_of_DRAM(void); phys_addr_t memblock_end_of_DRAM(void); void memblock_enforce_memory_limit(phys_addr_t memory_limit); +void memblock_cap_memory_range(phys_addr_t base, phys_addr_t size); void memblock_mem_limit_remove_map(phys_addr_t limit); bool memblock_is_memory(phys_addr_t addr); int memblock_is_map_memory(phys_addr_t addr); -- cgit v1.2.3 From 083c52144a19c69b7956aa53c913ba621f7c5ae2 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 11 Apr 2017 09:39:45 +0100 Subject: drivers/perf: arm_pmu: define armpmu_init_fn We expect an ARM PMU's init function to have a particular prototype, which we open-code in a few places. This is less than ideal, considering that we cast a void value to this type in one location, and a mismatch could easily be missed. Add a typedef so that we can ensure this is consistent. Signed-off-by: Mark Rutland Tested-by: Jeremy Linton Cc: Will Deacon Signed-off-by: Will Deacon --- include/linux/perf/arm_pmu.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 44f43fcf2524..4249914315a4 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -132,10 +132,12 @@ int armpmu_map_event(struct perf_event *event, [PERF_COUNT_HW_CACHE_RESULT_MAX], u32 raw_event_mask); +typedef int (*armpmu_init_fn)(struct arm_pmu *); + struct pmu_probe_info { unsigned int cpuid; unsigned int mask; - int (*init)(struct arm_pmu *); + armpmu_init_fn init; }; #define PMU_PROBE(_cpuid, _mask, _fn) \ -- cgit v1.2.3 From 18bfcfe51b8f60b69ab012888dea8061a9cd3381 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 11 Apr 2017 09:39:53 +0100 Subject: drivers/perf: arm_pmu: split out platform device probe logic Now that we've split the pdev and DT probing logic from the runtime management, let's move the former into its own file. We gain a few lines due to the copyright header and includes, but this should keep the logic clearly separated, and paves the way for adding ACPI support in a similar fashion. Signed-off-by: Mark Rutland Tested-by: Jeremy Linton [will: rename nr_irqs to avoid conflict with global variable] Signed-off-by: Will Deacon --- include/linux/perf/arm_pmu.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 4249914315a4..25556ebb1c7b 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -159,6 +159,13 @@ int arm_pmu_device_probe(struct platform_device *pdev, const struct of_device_id *of_table, const struct pmu_probe_info *probe_table); +/* Internal functions only for core arm_pmu code */ +struct arm_pmu *armpmu_alloc(void); +void armpmu_free(struct arm_pmu *pmu); +int armpmu_register(struct arm_pmu *pmu); +int armpmu_request_irqs(struct arm_pmu *armpmu); +void armpmu_free_irqs(struct arm_pmu *armpmu); + #define ARMV8_PMU_PDEV_NAME "armv8-pmu" #endif /* CONFIG_ARM_PMU */ -- cgit v1.2.3 From 45736a72fb79b204c1fbdb08a1e1a2aa52c7281a Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 11 Apr 2017 09:39:55 +0100 Subject: drivers/perf: arm_pmu: add ACPI framework This patch adds framework code to handle parsing PMU data out of the MADT, sanity checking this, and managing the association of CPUs (and their interrupts) with appropriate logical PMUs. For the time being, we expect that only one PMU driver (PMUv3) will make use of this, and we simply pass in a single probe function. This is based on an earlier patch from Jeremy Linton. Signed-off-by: Mark Rutland Tested-by: Jeremy Linton Cc: Will Deacon Signed-off-by: Will Deacon --- include/linux/cpuhotplug.h | 1 + include/linux/perf/arm_pmu.h | 11 +++++++++++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index cfcfab37d9c4..0f2a80377520 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -94,6 +94,7 @@ enum cpuhp_state { CPUHP_AP_ARM_VFP_STARTING, CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING, CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING, + CPUHP_AP_PERF_ARM_ACPI_STARTING, CPUHP_AP_PERF_ARM_STARTING, CPUHP_AP_ARM_L2X0_STARTING, CPUHP_AP_ARM_ARCH_TIMER_STARTING, diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 25556ebb1c7b..1360dd6d5e61 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -117,6 +117,9 @@ struct arm_pmu { struct notifier_block cpu_pm_nb; /* the attr_groups array must be NULL-terminated */ const struct attribute_group *attr_groups[ARMPMU_NR_ATTR_GROUPS + 1]; + + /* Only to be used by ACPI probing code */ + unsigned long acpi_cpuid; }; #define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu)) @@ -159,12 +162,20 @@ int arm_pmu_device_probe(struct platform_device *pdev, const struct of_device_id *of_table, const struct pmu_probe_info *probe_table); +#ifdef CONFIG_ACPI +int arm_pmu_acpi_probe(armpmu_init_fn init_fn); +#else +static inline int arm_pmu_acpi_probe(armpmu_init_fn init_fn) { return 0; } +#endif + /* Internal functions only for core arm_pmu code */ struct arm_pmu *armpmu_alloc(void); void armpmu_free(struct arm_pmu *pmu); int armpmu_register(struct arm_pmu *pmu); int armpmu_request_irqs(struct arm_pmu *armpmu); void armpmu_free_irqs(struct arm_pmu *armpmu); +int armpmu_request_irq(struct arm_pmu *armpmu, int cpu); +void armpmu_free_irq(struct arm_pmu *armpmu, int cpu); #define ARMV8_PMU_PDEV_NAME "armv8-pmu" -- cgit v1.2.3