From 6251d38059ae22304ede4f3748af9f795bdbf4fd Mon Sep 17 00:00:00 2001 From: Besar Wicaksono Date: Wed, 28 Sep 2022 19:28:34 -0500 Subject: ACPI: ARM Performance Monitoring Unit Table (APMT) initial support ARM Performance Monitoring Unit Table describes the properties of PMU support in ARM-based system. The APMT table contains a list of nodes, each represents a PMU in the system that conforms to ARM CoreSight PMU architecture. The properties of each node include information required to access the PMU (e.g. MMIO base address, interrupt number) and also identification. For more detailed information, please refer to the specification below: * APMT: https://developer.arm.com/documentation/den0117/latest * ARM Coresight PMU: https://developer.arm.com/documentation/ihi0091/latest The initial support adds the detection of APMT table and generic infrastructure to create platform devices for ARM CoreSight PMUs. Similar to IORT the root pointer of APMT is preserved during runtime and each PMU platform device is given a pointer to the corresponding APMT node. Signed-off-by: Besar Wicaksono Acked-by: Rafael J. Wysocki Reviewed-by: Sudeep Holla Link: https://lore.kernel.org/r/20220929002834.32664-1-bwicaksono@nvidia.com Signed-off-by: Will Deacon --- include/linux/acpi_apmt.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 include/linux/acpi_apmt.h (limited to 'include') diff --git a/include/linux/acpi_apmt.h b/include/linux/acpi_apmt.h new file mode 100644 index 000000000000..40bd634d082f --- /dev/null +++ b/include/linux/acpi_apmt.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * ARM CoreSight PMU driver. + * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. + * + */ + +#ifndef __ACPI_APMT_H__ +#define __ACPI_APMT_H__ + +#include + +#ifdef CONFIG_ACPI_APMT +void acpi_apmt_init(void); +#else +static inline void acpi_apmt_init(void) { } +#endif /* CONFIG_ACPI_APMT */ + +#endif /* __ACPI_APMT_H__ */ -- cgit v1.2.3 From fe40ffdb7656d1f9c42dd402740765ff8b418b17 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 30 Sep 2022 12:18:44 +0100 Subject: arm_pmu: rework ACPI probing The current ACPI PMU probing logic tries to associate PMUs with CPUs when the CPU is first brought online, in order to handle late hotplug, though PMUs are only registered during early boot, and so for late hotplugged CPUs this can only associate the CPU with an existing PMU. We tried to be clever and the have the arm_pmu_acpi_cpu_starting() callback allocate a struct arm_pmu when no matching instance is found, in order to avoid duplication of logic. However, as above this doesn't do anything useful for late hotplugged CPUs, and this requires us to allocate memory in an atomic context, which is especially problematic for PREEMPT_RT, as reported by Valentin and Pierre. This patch reworks the probing to detect PMUs for all online CPUs in the arm_pmu_acpi_probe() function, which is more aligned with how DT probing works. The arm_pmu_acpi_cpu_starting() callback only tries to associate CPUs with an existing arm_pmu instance, avoiding the problem of allocating in atomic context. Note that as we didn't previously register PMUs for late-hotplugged CPUs, this change doesn't result in a loss of existing functionality, though we will now warn when we cannot associate a CPU with a PMU. This change allows us to pull the hotplug callback registration into the arm_pmu_acpi_probe() function, as we no longer need the callbacks to be invoked shortly after probing the boot CPUs, and can register it without invoking the calls. For the moment the arm_pmu_acpi_init() initcall remains to register the SPE PMU, though in future this should probably be moved elsewhere (e.g. the arm64 ACPI init code), since this doesn't need to be tied to the regular CPU PMU code. Signed-off-by: Mark Rutland Reported-by: Valentin Schneider Link: https://lore.kernel.org/r/20210810134127.1394269-2-valentin.schneider@arm.com/ Reported-by: Pierre Gondois Link: https://lore.kernel.org/linux-arm-kernel/20220912155105.1443303-1-pierre.gondois@arm.com/ Cc: Pierre Gondois Cc: Valentin Schneider Cc: Will Deacon Reviewed-and-tested-by: Pierre Gondois Link: https://lore.kernel.org/r/20220930111844.1522365-4-mark.rutland@arm.com Signed-off-by: Will Deacon --- drivers/perf/arm_pmu.c | 17 ++------ drivers/perf/arm_pmu_acpi.c | 95 +++++++++++++++++++++++--------------------- include/linux/perf/arm_pmu.h | 1 - 3 files changed, 52 insertions(+), 61 deletions(-) (limited to 'include') diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 3f07df5a7e95..82a6d22e8ee2 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -861,16 +861,16 @@ static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu) &cpu_pmu->node); } -static struct arm_pmu *__armpmu_alloc(gfp_t flags) +struct arm_pmu *armpmu_alloc(void) { struct arm_pmu *pmu; int cpu; - pmu = kzalloc(sizeof(*pmu), flags); + pmu = kzalloc(sizeof(*pmu), GFP_KERNEL); if (!pmu) goto out; - pmu->hw_events = alloc_percpu_gfp(struct pmu_hw_events, flags); + pmu->hw_events = alloc_percpu_gfp(struct pmu_hw_events, GFP_KERNEL); if (!pmu->hw_events) { pr_info("failed to allocate per-cpu PMU data.\n"); goto out_free_pmu; @@ -916,17 +916,6 @@ out: return NULL; } -struct arm_pmu *armpmu_alloc(void) -{ - return __armpmu_alloc(GFP_KERNEL); -} - -struct arm_pmu *armpmu_alloc_atomic(void) -{ - return __armpmu_alloc(GFP_ATOMIC); -} - - void armpmu_free(struct arm_pmu *pmu) { free_percpu(pmu->hw_events); diff --git a/drivers/perf/arm_pmu_acpi.c b/drivers/perf/arm_pmu_acpi.c index 99abea3b2cc9..a085e45b509e 100644 --- a/drivers/perf/arm_pmu_acpi.c +++ b/drivers/perf/arm_pmu_acpi.c @@ -13,6 +13,7 @@ #include #include +#include #include static DEFINE_PER_CPU(struct arm_pmu *, probed_pmus); @@ -204,26 +205,6 @@ static struct arm_pmu *arm_pmu_acpi_find_pmu(void) return NULL; } -static struct arm_pmu *arm_pmu_acpi_find_alloc_pmu(void) -{ - struct arm_pmu *pmu; - - pmu = arm_pmu_acpi_find_pmu(); - if (pmu) - return pmu; - - pmu = armpmu_alloc_atomic(); - if (!pmu) { - pr_warn("Unable to allocate PMU for CPU%d\n", - smp_processor_id()); - return NULL; - } - - pmu->acpi_cpuid = read_cpuid_id(); - - return pmu; -} - /* * Check whether the new IRQ is compatible with those already associated with * the PMU (e.g. we don't have mismatched PPIs). @@ -286,26 +267,45 @@ static int arm_pmu_acpi_cpu_starting(unsigned int cpu) if (per_cpu(probed_pmus, cpu)) return 0; - pmu = arm_pmu_acpi_find_alloc_pmu(); - if (!pmu) - return -ENOMEM; + pmu = arm_pmu_acpi_find_pmu(); + if (!pmu) { + pr_warn_ratelimited("Unable to associate CPU%d with a PMU\n", + cpu); + return 0; + } arm_pmu_acpi_associate_pmu_cpu(pmu, cpu); - - /* - * Ideally, we'd probe the PMU here when we find the first matching - * CPU. We can't do that for several reasons; see the comment in - * arm_pmu_acpi_init(). - * - * So for the time being, we're done. - */ return 0; } +static void arm_pmu_acpi_probe_matching_cpus(struct arm_pmu *pmu, + unsigned long cpuid) +{ + int cpu; + + for_each_online_cpu(cpu) { + unsigned long cpu_cpuid = per_cpu(cpu_data, cpu).reg_midr; + + if (cpu_cpuid == cpuid) + arm_pmu_acpi_associate_pmu_cpu(pmu, cpu); + } +} + int arm_pmu_acpi_probe(armpmu_init_fn init_fn) { int pmu_idx = 0; - int cpu, ret; + unsigned int cpu; + int ret; + + ret = arm_pmu_acpi_parse_irqs(); + if (ret) + return ret; + + ret = cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_ACPI_STARTING, + "perf/arm/pmu_acpi:starting", + arm_pmu_acpi_cpu_starting, NULL); + if (ret) + return ret; /* * Initialise and register the set of PMUs which we know about right @@ -320,13 +320,26 @@ int arm_pmu_acpi_probe(armpmu_init_fn init_fn) * For the moment, as with the platform/DT case, we need at least one * of a PMU's CPUs to be online at probe time. */ - for_each_possible_cpu(cpu) { + for_each_online_cpu(cpu) { struct arm_pmu *pmu = per_cpu(probed_pmus, cpu); + unsigned long cpuid; char *base_name; - if (!pmu || pmu->name) + /* If we've already probed this CPU, we have nothing to do */ + if (pmu) continue; + pmu = armpmu_alloc(); + if (!pmu) { + pr_warn("Unable to allocate PMU for CPU%d\n", + cpu); + } + + cpuid = per_cpu(cpu_data, cpu).reg_midr; + pmu->acpi_cpuid = cpuid; + + arm_pmu_acpi_probe_matching_cpus(pmu, cpuid); + ret = init_fn(pmu); if (ret == -ENODEV) { /* PMU not handled by this driver, or not present */ @@ -351,26 +364,16 @@ int arm_pmu_acpi_probe(armpmu_init_fn init_fn) } } - return 0; + return ret; } static int arm_pmu_acpi_init(void) { - int ret; - if (acpi_disabled) return 0; arm_spe_acpi_register_device(); - ret = arm_pmu_acpi_parse_irqs(); - if (ret) - return ret; - - ret = cpuhp_setup_state(CPUHP_AP_PERF_ARM_ACPI_STARTING, - "perf/arm/pmu_acpi:starting", - arm_pmu_acpi_cpu_starting, NULL); - - return ret; + return 0; } subsys_initcall(arm_pmu_acpi_init) diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 0356cb6a215d..0c15c5b7f801 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -174,7 +174,6 @@ void kvm_host_pmu_init(struct arm_pmu *pmu); /* Internal functions only for core arm_pmu code */ struct arm_pmu *armpmu_alloc(void); -struct arm_pmu *armpmu_alloc_atomic(void); void armpmu_free(struct arm_pmu *pmu); int armpmu_register(struct arm_pmu *pmu); int armpmu_request_irq(int irq, int cpu); -- cgit v1.2.3 From 68c76ad4a9571a2b603665c85cf8229bcf04982a Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 27 Oct 2022 17:59:06 +0200 Subject: arm64: unwind: add asynchronous unwind tables to kernel and modules Enable asynchronous unwind table generation for both the core kernel as well as modules, and emit the resulting .eh_frame sections as init code so we can use the unwind directives for code patching at boot or module load time. This will be used by dynamic shadow call stack support, which will rely on code patching rather than compiler codegen to emit the shadow call stack push and pop instructions. Signed-off-by: Ard Biesheuvel Reviewed-by: Nick Desaulniers Reviewed-by: Sami Tolvanen Tested-by: Sami Tolvanen Link: https://lore.kernel.org/r/20221027155908.1940624-2-ardb@kernel.org Signed-off-by: Will Deacon --- arch/arm64/Kconfig | 3 +++ arch/arm64/Makefile | 5 +++++ arch/arm64/include/asm/module.lds.h | 8 ++++++++ arch/arm64/kernel/pi/Makefile | 1 + arch/arm64/kernel/vmlinux.lds.S | 13 +++++++++++++ arch/arm64/kvm/hyp/nvhe/Makefile | 1 + drivers/firmware/efi/libstub/Makefile | 1 + include/asm-generic/vmlinux.lds.h | 9 +++++++-- scripts/module.lds.S | 6 ++++++ 9 files changed, 45 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 505c8a1ccbe0..7e3a9cf2193d 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -370,6 +370,9 @@ config KASAN_SHADOW_OFFSET default 0xeffffff800000000 if ARM64_VA_BITS_36 && KASAN_SW_TAGS default 0xffffffffffffffff +config UNWIND_TABLES + bool + source "arch/arm64/Kconfig.platforms" menu "Kernel Features" diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 5e56d26a2239..7868a176993f 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -45,8 +45,13 @@ KBUILD_CFLAGS += $(call cc-option,-mabi=lp64) KBUILD_AFLAGS += $(call cc-option,-mabi=lp64) # Avoid generating .eh_frame* sections. +ifneq ($(CONFIG_UNWIND_TABLES),y) KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables KBUILD_AFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables +else +KBUILD_CFLAGS += -fasynchronous-unwind-tables +KBUILD_AFLAGS += -fasynchronous-unwind-tables +endif ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y) prepare: stack_protector_prepare diff --git a/arch/arm64/include/asm/module.lds.h b/arch/arm64/include/asm/module.lds.h index 094701ec5500..dbba4b7559aa 100644 --- a/arch/arm64/include/asm/module.lds.h +++ b/arch/arm64/include/asm/module.lds.h @@ -17,4 +17,12 @@ SECTIONS { */ .text.hot : { *(.text.hot) } #endif + +#ifdef CONFIG_UNWIND_TABLES + /* + * Currently, we only use unwind info at module load time, so we can + * put it into the .init allocation. + */ + .init.eh_frame : { *(.eh_frame) } +#endif } diff --git a/arch/arm64/kernel/pi/Makefile b/arch/arm64/kernel/pi/Makefile index 839291430cb3..4c0ea3cd4ea4 100644 --- a/arch/arm64/kernel/pi/Makefile +++ b/arch/arm64/kernel/pi/Makefile @@ -7,6 +7,7 @@ KBUILD_CFLAGS := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) -fpie \ -I$(srctree)/scripts/dtc/libfdt -fno-stack-protector \ -include $(srctree)/include/linux/hidden.h \ -D__DISABLE_EXPORTS -ffreestanding -D__NO_FORTIFY \ + -fno-asynchronous-unwind-tables -fno-unwind-tables \ $(call cc-option,-fno-addrsig) # remove SCS flags from all objects in this directory diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 45131e354e27..4c13dafc98b8 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -121,6 +121,17 @@ jiffies = jiffies_64; #define TRAMP_TEXT #endif +#ifdef CONFIG_UNWIND_TABLES +#define UNWIND_DATA_SECTIONS \ + .eh_frame : { \ + __eh_frame_start = .; \ + *(.eh_frame) \ + __eh_frame_end = .; \ + } +#else +#define UNWIND_DATA_SECTIONS +#endif + /* * The size of the PE/COFF section that covers the kernel image, which * runs from _stext to _edata, must be a round multiple of the PE/COFF @@ -231,6 +242,8 @@ SECTIONS __alt_instructions_end = .; } + UNWIND_DATA_SECTIONS + . = ALIGN(SEGMENT_ALIGN); __inittext_end = .; __initdata_begin = .; diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile index be0a2bc3e20d..530347cdebe3 100644 --- a/arch/arm64/kvm/hyp/nvhe/Makefile +++ b/arch/arm64/kvm/hyp/nvhe/Makefile @@ -96,6 +96,7 @@ KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) $(CC_FLAGS_CFI) # when profile optimization is applied. gen-hyprel does not support SHT_REL and # causes a build failure. Remove profile optimization flags. KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%, $(KBUILD_CFLAGS)) +KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables # KVM nVHE code is run at a different exception code with a different map, so # compiler instrumentation that inserts callbacks or checks into the code may diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index b1601aad7e1a..1016f0b5311d 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -20,6 +20,7 @@ cflags-$(CONFIG_X86) += -m$(BITS) -D__KERNEL__ \ # disable the stackleak plugin cflags-$(CONFIG_ARM64) := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \ -fpie $(DISABLE_STACKLEAK_PLUGIN) \ + -fno-unwind-tables -fno-asynchronous-unwind-tables \ $(call cc-option,-mbranch-protection=none) cflags-$(CONFIG_ARM) := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \ -fno-builtin -fpic \ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index d06ada2341cb..0cca179e5106 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -1027,14 +1027,19 @@ * keep any .init_array.* sections. * https://bugs.llvm.org/show_bug.cgi?id=46478 */ +#ifdef CONFIG_UNWIND_TABLES +#define DISCARD_EH_FRAME +#else +#define DISCARD_EH_FRAME *(.eh_frame) +#endif #if defined(CONFIG_GCOV_KERNEL) || defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KCSAN) # ifdef CONFIG_CONSTRUCTORS # define SANITIZER_DISCARDS \ - *(.eh_frame) + DISCARD_EH_FRAME # else # define SANITIZER_DISCARDS \ *(.init_array) *(.init_array.*) \ - *(.eh_frame) + DISCARD_EH_FRAME # endif #else # define SANITIZER_DISCARDS diff --git a/scripts/module.lds.S b/scripts/module.lds.S index da4bddd26171..bf5bcf2836d8 100644 --- a/scripts/module.lds.S +++ b/scripts/module.lds.S @@ -3,6 +3,12 @@ * Archs are free to supply their own linker scripts. ld will * combine them automatically. */ +#ifdef CONFIG_UNWIND_TABLES +#define DISCARD_EH_FRAME +#else +#define DISCARD_EH_FRAME *(.eh_frame) +#endif + SECTIONS { /DISCARD/ : { *(.discard) -- cgit v1.2.3 From 9beccca0984022a844850e32f0d7dd80d4a225de Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 27 Oct 2022 17:59:07 +0200 Subject: scs: add support for dynamic shadow call stacks In order to allow arches to use code patching to conditionally emit the shadow stack pushes and pops, rather than always taking the performance hit even on CPUs that implement alternatives such as stack pointer authentication on arm64, add a Kconfig symbol that can be set by the arch to omit the SCS codegen itself, without otherwise affecting how support code for SCS and compiler options (for register reservation, for instance) are emitted. Also, add a static key and some plumbing to omit the allocation of shadow call stack for dynamic SCS configurations if SCS is disabled at runtime. Signed-off-by: Ard Biesheuvel Reviewed-by: Nick Desaulniers Reviewed-by: Kees Cook Reviewed-by: Sami Tolvanen Tested-by: Sami Tolvanen Link: https://lore.kernel.org/r/20221027155908.1940624-3-ardb@kernel.org Signed-off-by: Will Deacon --- Makefile | 2 ++ arch/Kconfig | 7 +++++++ include/linux/scs.h | 18 ++++++++++++++++++ kernel/scs.c | 14 ++++++++++++-- 4 files changed, 39 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/Makefile b/Makefile index ac2ec990422d..69b40b629f3c 100644 --- a/Makefile +++ b/Makefile @@ -966,8 +966,10 @@ LDFLAGS_vmlinux += --gc-sections endif ifdef CONFIG_SHADOW_CALL_STACK +ifndef CONFIG_DYNAMIC_SCS CC_FLAGS_SCS := -fsanitize=shadow-call-stack KBUILD_CFLAGS += $(CC_FLAGS_SCS) +endif export CC_FLAGS_SCS endif diff --git a/arch/Kconfig b/arch/Kconfig index 8f138e580d1a..072a1b39e3af 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -651,6 +651,13 @@ config SHADOW_CALL_STACK reading and writing arbitrary memory may be able to locate them and hijack control flow by modifying the stacks. +config DYNAMIC_SCS + bool + help + Set by the arch code if it relies on code patching to insert the + shadow call stack push and pop instructions rather than on the + compiler. + config LTO bool help diff --git a/include/linux/scs.h b/include/linux/scs.h index 18122d9e17ff..4ab5bdc898cf 100644 --- a/include/linux/scs.h +++ b/include/linux/scs.h @@ -53,6 +53,22 @@ static inline bool task_scs_end_corrupted(struct task_struct *tsk) return sz >= SCS_SIZE - 1 || READ_ONCE_NOCHECK(*magic) != SCS_END_MAGIC; } +DECLARE_STATIC_KEY_FALSE(dynamic_scs_enabled); + +static inline bool scs_is_dynamic(void) +{ + if (!IS_ENABLED(CONFIG_DYNAMIC_SCS)) + return false; + return static_branch_likely(&dynamic_scs_enabled); +} + +static inline bool scs_is_enabled(void) +{ + if (!IS_ENABLED(CONFIG_DYNAMIC_SCS)) + return true; + return scs_is_dynamic(); +} + #else /* CONFIG_SHADOW_CALL_STACK */ static inline void *scs_alloc(int node) { return NULL; } @@ -62,6 +78,8 @@ static inline void scs_task_reset(struct task_struct *tsk) {} static inline int scs_prepare(struct task_struct *tsk, int node) { return 0; } static inline void scs_release(struct task_struct *tsk) {} static inline bool task_scs_end_corrupted(struct task_struct *tsk) { return false; } +static inline bool scs_is_enabled(void) { return false; } +static inline bool scs_is_dynamic(void) { return false; } #endif /* CONFIG_SHADOW_CALL_STACK */ diff --git a/kernel/scs.c b/kernel/scs.c index b7e1b096d906..d7809affe740 100644 --- a/kernel/scs.c +++ b/kernel/scs.c @@ -12,6 +12,10 @@ #include #include +#ifdef CONFIG_DYNAMIC_SCS +DEFINE_STATIC_KEY_FALSE(dynamic_scs_enabled); +#endif + static void __scs_account(void *s, int account) { struct page *scs_page = vmalloc_to_page(s); @@ -101,14 +105,20 @@ static int scs_cleanup(unsigned int cpu) void __init scs_init(void) { + if (!scs_is_enabled()) + return; cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "scs:scs_cache", NULL, scs_cleanup); } int scs_prepare(struct task_struct *tsk, int node) { - void *s = scs_alloc(node); + void *s; + if (!scs_is_enabled()) + return 0; + + s = scs_alloc(node); if (!s) return -ENOMEM; @@ -148,7 +158,7 @@ void scs_release(struct task_struct *tsk) { void *s = task_scs(tsk); - if (!s) + if (!scs_is_enabled() || !s) return; WARN(task_scs_end_corrupted(tsk), -- cgit v1.2.3 From 9705bc70960459ae09f4a5e77283973bb3a40f57 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 3 Nov 2022 17:05:17 +0000 Subject: ftrace: pass fregs to arch_ftrace_set_direct_caller() In subsequent patches we'll arrange for architectures to have an ftrace_regs which is entirely distinct from pt_regs. In preparation for this, we need to minimize the use of pt_regs to where strictly necessary in the core ftrace code. This patch changes the prototype of arch_ftrace_set_direct_caller() to take ftrace_regs rather than pt_regs, and moves the extraction of the pt_regs into arch_ftrace_set_direct_caller(). On x86, arch_ftrace_set_direct_caller() can be used even when CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS=n, and defines struct ftrace_regs. Due to this, it's necessary to define arch_ftrace_set_direct_caller() as a macro to avoid using an incomplete type. I've also moved the body of arch_ftrace_set_direct_caller() after the CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS=y defineidion of struct ftrace_regs. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Cc: Florent Revest Cc: Masami Hiramatsu Cc: Steven Rostedt Reviewed-by: Masami Hiramatsu (Google) Reviewed-by: Steven Rostedt (Google) Link: https://lore.kernel.org/r/20221103170520.931305-2-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/s390/include/asm/ftrace.h | 5 ++++- arch/x86/include/asm/ftrace.h | 31 ++++++++++++++++++------------- include/linux/ftrace.h | 9 ++++----- kernel/trace/ftrace.c | 3 +-- 4 files changed, 27 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index 6f80ec9c04be..85bc26ccdb87 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -60,6 +60,7 @@ static __always_inline void ftrace_instruction_pointer_set(struct ftrace_regs *f fregs->regs.psw.addr = ip; } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS /* * When an ftrace registered caller is tracing a function that is * also set by a register_ftrace_direct() call, it needs to be @@ -67,10 +68,12 @@ static __always_inline void ftrace_instruction_pointer_set(struct ftrace_regs *f * place the direct caller in the ORIG_GPR2 part of pt_regs. This * tells the ftrace_caller that there's a direct caller. */ -static inline void arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr) +static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, unsigned long addr) { + struct pt_regs *regs = &fregs->regs; regs->orig_gpr2 = addr; } +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ /* * Even though the system call numbers are identical for s390/s390x a diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 908d99b127d3..d2350a8351fa 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -34,19 +34,6 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) return addr; } -/* - * When a ftrace registered caller is tracing a function that is - * also set by a register_ftrace_direct() call, it needs to be - * differentiated in the ftrace_caller trampoline. To do this, we - * place the direct caller in the ORIG_AX part of pt_regs. This - * tells the ftrace_caller that there's a direct caller. - */ -static inline void arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr) -{ - /* Emulate a call */ - regs->orig_ax = addr; -} - #ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS struct ftrace_regs { struct pt_regs regs; @@ -72,6 +59,24 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, #define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR #endif +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +/* + * When a ftrace registered caller is tracing a function that is + * also set by a register_ftrace_direct() call, it needs to be + * differentiated in the ftrace_caller trampoline. To do this, we + * place the direct caller in the ORIG_AX part of pt_regs. This + * tells the ftrace_caller that there's a direct caller. + */ +static inline void +__arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr) +{ + /* Emulate a call */ + regs->orig_ax = addr; +} +#define arch_ftrace_set_direct_caller(fregs, addr) \ + __arch_ftrace_set_direct_caller(&(fregs)->regs, addr) +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ + #ifdef CONFIG_DYNAMIC_FTRACE struct dyn_arch_ftrace { diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 62557d4bffc2..f201fcbfffb0 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -37,9 +37,10 @@ extern void ftrace_boot_snapshot(void); static inline void ftrace_boot_snapshot(void) { } #endif -#ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops; struct ftrace_regs; + +#ifdef CONFIG_FUNCTION_TRACER /* * If the arch's mcount caller does not support all of ftrace's * features, then it must call an indirect function that @@ -427,9 +428,7 @@ static inline int modify_ftrace_direct_multi_nolock(struct ftrace_ops *ops, unsi { return -ENODEV; } -#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ -#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS /* * This must be implemented by the architecture. * It is the way the ftrace direct_ops helper, when called @@ -443,9 +442,9 @@ static inline int modify_ftrace_direct_multi_nolock(struct ftrace_ops *ops, unsi * the return from the trampoline jump to the direct caller * instead of going back to the function it just traced. */ -static inline void arch_ftrace_set_direct_caller(struct pt_regs *regs, +static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, unsigned long addr) { } -#endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ #ifdef CONFIG_STACK_TRACER diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 7dc023641bf1..9eb42120ac44 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2487,14 +2487,13 @@ ftrace_add_rec_direct(unsigned long ip, unsigned long addr, static void call_direct_funcs(unsigned long ip, unsigned long pip, struct ftrace_ops *ops, struct ftrace_regs *fregs) { - struct pt_regs *regs = ftrace_get_regs(fregs); unsigned long addr; addr = ftrace_find_rec_direct(ip); if (!addr) return; - arch_ftrace_set_direct_caller(regs, addr); + arch_ftrace_set_direct_caller(fregs, addr); } struct ftrace_ops direct_ops = { -- cgit v1.2.3 From 0ef86097f127d0d73e19aa4dcf86106105e7db09 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 3 Nov 2022 17:05:18 +0000 Subject: ftrace: rename ftrace_instruction_pointer_set() -> ftrace_regs_set_instruction_pointer() In subsequent patches we'll add a sew of ftrace_regs_{get,set}_*() helpers. In preparation, this patch renames ftrace_instruction_pointer_set() to ftrace_regs_set_instruction_pointer(). There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Cc: Florent Revest Cc: Masami Hiramatsu Cc: Steven Rostedt Reviewed-by: Masami Hiramatsu (Google) Reviewed-by: Steven Rostedt (Google) Link: https://lore.kernel.org/r/20221103170520.931305-3-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/powerpc/include/asm/ftrace.h | 5 +++-- arch/s390/include/asm/ftrace.h | 5 +++-- arch/x86/include/asm/ftrace.h | 2 +- include/linux/ftrace.h | 9 ++++----- kernel/livepatch/patch.c | 2 +- 5 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h index 3cee7115441b..c3eb48f67566 100644 --- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -37,8 +37,9 @@ static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs * return fregs->regs.msr ? &fregs->regs : NULL; } -static __always_inline void ftrace_instruction_pointer_set(struct ftrace_regs *fregs, - unsigned long ip) +static __always_inline void +ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, + unsigned long ip) { regs_set_return_ip(&fregs->regs, ip); } diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index 85bc26ccdb87..113d194acea0 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -54,8 +54,9 @@ static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs * return NULL; } -static __always_inline void ftrace_instruction_pointer_set(struct ftrace_regs *fregs, - unsigned long ip) +static __always_inline void +ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, + unsigned long ip) { fregs->regs.psw.addr = ip; } diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index d2350a8351fa..b2925d342c65 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -48,7 +48,7 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs) return &fregs->regs; } -#define ftrace_instruction_pointer_set(fregs, _ip) \ +#define ftrace_regs_set_instruction_pointer(fregs, _ip) \ do { (fregs)->regs.ip = (_ip); } while (0) struct ftrace_ops; diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index f201fcbfffb0..ec3657a60f85 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -111,12 +111,11 @@ struct ftrace_regs { #define arch_ftrace_get_regs(fregs) (&(fregs)->regs) /* - * ftrace_instruction_pointer_set() is to be defined by the architecture - * if to allow setting of the instruction pointer from the ftrace_regs - * when HAVE_DYNAMIC_FTRACE_WITH_ARGS is set and it supports - * live kernel patching. + * ftrace_regs_set_instruction_pointer() is to be defined by the architecture + * if to allow setting of the instruction pointer from the ftrace_regs when + * HAVE_DYNAMIC_FTRACE_WITH_ARGS is set and it supports live kernel patching. */ -#define ftrace_instruction_pointer_set(fregs, ip) do { } while (0) +#define ftrace_regs_set_instruction_pointer(fregs, ip) do { } while (0) #endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs) diff --git a/kernel/livepatch/patch.c b/kernel/livepatch/patch.c index 4c4f5a776d80..4152c71507e2 100644 --- a/kernel/livepatch/patch.c +++ b/kernel/livepatch/patch.c @@ -118,7 +118,7 @@ static void notrace klp_ftrace_handler(unsigned long ip, if (func->nop) goto unlock; - ftrace_instruction_pointer_set(fregs, (unsigned long)func->new_func); + ftrace_regs_set_instruction_pointer(fregs, (unsigned long)func->new_func); unlock: ftrace_test_recursion_unlock(bit); -- cgit v1.2.3 From 94d095ffa0e16bb7f161a2b73bbe5c2795d499a8 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 3 Nov 2022 17:05:19 +0000 Subject: ftrace: abstract DYNAMIC_FTRACE_WITH_ARGS accesses In subsequent patches we'll arrange for architectures to have an ftrace_regs which is entirely distinct from pt_regs. In preparation for this, we need to minimize the use of pt_regs to where strictly necessary in the core ftrace code. This patch adds new ftrace_regs_{get,set}_*() helpers which can be used to manipulate ftrace_regs. When CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS=y, these can always be used on any ftrace_regs, and when CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS=n these can be used when regs are available. A new ftrace_regs_has_args(fregs) helper is added which code can use to check when these are usable. Co-developed-by: Florent Revest Signed-off-by: Florent Revest Signed-off-by: Mark Rutland Cc: Masami Hiramatsu Cc: Steven Rostedt Reviewed-by: Masami Hiramatsu (Google) Reviewed-by: Steven Rostedt (Google) Link: https://lore.kernel.org/r/20221103170520.931305-4-mark.rutland@arm.com Signed-off-by: Will Deacon --- arch/powerpc/include/asm/ftrace.h | 19 +++++++++++++++++++ arch/s390/include/asm/ftrace.h | 19 +++++++++++++++++++ arch/x86/include/asm/ftrace.h | 16 ++++++++++++++++ include/linux/ftrace.h | 29 +++++++++++++++++++++++++++++ kernel/trace/Kconfig | 6 +++--- 5 files changed, 86 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h index c3eb48f67566..259b9dd5fe1c 100644 --- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -44,6 +44,25 @@ ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, regs_set_return_ip(&fregs->regs, ip); } +static __always_inline unsigned long +ftrace_regs_get_instruction_pointer(struct ftrace_regs *fregs) +{ + return instruction_pointer(&fregs->regs); +} + +#define ftrace_regs_get_argument(fregs, n) \ + regs_get_kernel_argument(&(fregs)->regs, n) +#define ftrace_regs_get_stack_pointer(fregs) \ + kernel_stack_pointer(&(fregs)->regs) +#define ftrace_regs_return_value(fregs) \ + regs_return_value(&(fregs)->regs) +#define ftrace_regs_set_return_value(fregs, ret) \ + regs_set_return_value(&(fregs)->regs, ret) +#define ftrace_override_function_with_return(fregs) \ + override_function_with_return(&(fregs)->regs) +#define ftrace_regs_query_register_offset(name) \ + regs_query_register_offset(name) + struct ftrace_ops; #define ftrace_graph_func ftrace_graph_func diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index 113d194acea0..e5c5cb1207e2 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -54,6 +54,12 @@ static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs * return NULL; } +static __always_inline unsigned long +ftrace_regs_get_instruction_pointer(const struct ftrace_regs *fregs) +{ + return fregs->regs.psw.addr; +} + static __always_inline void ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long ip) @@ -61,6 +67,19 @@ ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, fregs->regs.psw.addr = ip; } +#define ftrace_regs_get_argument(fregs, n) \ + regs_get_kernel_argument(&(fregs)->regs, n) +#define ftrace_regs_get_stack_pointer(fregs) \ + kernel_stack_pointer(&(fregs)->regs) +#define ftrace_regs_return_value(fregs) \ + regs_return_value(&(fregs)->regs) +#define ftrace_regs_set_return_value(fregs, ret) \ + regs_set_return_value(&(fregs)->regs, ret) +#define ftrace_override_function_with_return(fregs) \ + override_function_with_return(&(fregs)->regs) +#define ftrace_regs_query_register_offset(name) \ + regs_query_register_offset(name) + #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS /* * When an ftrace registered caller is tracing a function that is diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index b2925d342c65..5061ac98ffa1 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -51,6 +51,22 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs) #define ftrace_regs_set_instruction_pointer(fregs, _ip) \ do { (fregs)->regs.ip = (_ip); } while (0) +#define ftrace_regs_get_instruction_pointer(fregs) \ + ((fregs)->regs.ip) + +#define ftrace_regs_get_argument(fregs, n) \ + regs_get_kernel_argument(&(fregs)->regs, n) +#define ftrace_regs_get_stack_pointer(fregs) \ + kernel_stack_pointer(&(fregs)->regs) +#define ftrace_regs_return_value(fregs) \ + regs_return_value(&(fregs)->regs) +#define ftrace_regs_set_return_value(fregs, ret) \ + regs_set_return_value(&(fregs)->regs, ret) +#define ftrace_override_function_with_return(fregs) \ + override_function_with_return(&(fregs)->regs) +#define ftrace_regs_query_register_offset(name) \ + regs_query_register_offset(name) + struct ftrace_ops; #define ftrace_graph_func ftrace_graph_func void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index ec3657a60f85..99f1146614c0 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -126,6 +126,35 @@ static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs return arch_ftrace_get_regs(fregs); } +/* + * When true, the ftrace_regs_{get,set}_*() functions may be used on fregs. + * Note: this can be true even when ftrace_get_regs() cannot provide a pt_regs. + */ +static __always_inline bool ftrace_regs_has_args(struct ftrace_regs *fregs) +{ + if (IS_ENABLED(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS)) + return true; + + return ftrace_get_regs(fregs) != NULL; +} + +#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS +#define ftrace_regs_get_instruction_pointer(fregs) \ + instruction_pointer(ftrace_get_regs(fregs)) +#define ftrace_regs_get_argument(fregs, n) \ + regs_get_kernel_argument(ftrace_get_regs(fregs), n) +#define ftrace_regs_get_stack_pointer(fregs) \ + kernel_stack_pointer(ftrace_get_regs(fregs)) +#define ftrace_regs_return_value(fregs) \ + regs_return_value(ftrace_get_regs(fregs)) +#define ftrace_regs_set_return_value(fregs, ret) \ + regs_set_return_value(ftrace_get_regs(fregs), ret) +#define ftrace_override_function_with_return(fregs) \ + override_function_with_return(ftrace_get_regs(fregs)) +#define ftrace_regs_query_register_offset(name) \ + regs_query_register_offset(name) +#endif + typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index e9e95c790b8e..2c6611c13f99 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -46,10 +46,10 @@ config HAVE_DYNAMIC_FTRACE_WITH_ARGS bool help If this is set, then arguments and stack can be found from - the pt_regs passed into the function callback regs parameter + the ftrace_regs passed into the function callback regs parameter by default, even without setting the REGS flag in the ftrace_ops. - This allows for use of regs_get_kernel_argument() and - kernel_stack_pointer(). + This allows for use of ftrace_regs_get_argument() and + ftrace_regs_get_stack_pointer(). config HAVE_DYNAMIC_FTRACE_NO_PATCHABLE bool -- cgit v1.2.3 From 2016e2113d35ba06866961a39e9a9c822f2ffabd Mon Sep 17 00:00:00 2001 From: Jiucheng Xu Date: Mon, 21 Nov 2022 10:15:58 +0800 Subject: perf/amlogic: Add support for Amlogic meson G12 SoC DDR PMU driver Add support for Amlogic Meson G12 Series SOC - DDR bandwidth PMU driver framework and interfaces. The PMU can not only monitor the total DDR bandwidth, but also individual IP module bandwidth. Signed-off-by: Jiucheng Xu Tested-by: Chris Healy Link: https://lore.kernel.org/r/20221121021602.3306998-1-jiucheng.xu@amlogic.com Signed-off-by: Will Deacon --- MAINTAINERS | 8 + drivers/perf/Kconfig | 2 + drivers/perf/Makefile | 1 + drivers/perf/amlogic/Kconfig | 10 + drivers/perf/amlogic/Makefile | 5 + drivers/perf/amlogic/meson_ddr_pmu_core.c | 562 ++++++++++++++++++++++++++++++ drivers/perf/amlogic/meson_g12_ddr_pmu.c | 394 +++++++++++++++++++++ include/soc/amlogic/meson_ddr_pmu.h | 66 ++++ 8 files changed, 1048 insertions(+) create mode 100644 drivers/perf/amlogic/Kconfig create mode 100644 drivers/perf/amlogic/Makefile create mode 100644 drivers/perf/amlogic/meson_ddr_pmu_core.c create mode 100644 drivers/perf/amlogic/meson_g12_ddr_pmu.c create mode 100644 include/soc/amlogic/meson_ddr_pmu.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 35ce60f6b8ee..86d090ce3525 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1093,6 +1093,14 @@ S: Maintained F: Documentation/hid/amd-sfh* F: drivers/hid/amd-sfh-hid/ +AMLOGIC DDR PMU DRIVER +M: Jiucheng Xu +L: linux-amlogic@lists.infradead.org +S: Supported +W: http://www.amlogic.com +F: drivers/perf/amlogic/ +F: include/soc/amlogic/ + AMPHION VPU CODEC V4L2 DRIVER M: Ming Qian M: Shijie Qin diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig index fa87dedf8c92..77043bcdb33c 100644 --- a/drivers/perf/Kconfig +++ b/drivers/perf/Kconfig @@ -201,4 +201,6 @@ config MARVELL_CN10K_DDR_PMU source "drivers/perf/arm_cspmu/Kconfig" +source "drivers/perf/amlogic/Kconfig" + endmenu diff --git a/drivers/perf/Makefile b/drivers/perf/Makefile index 35bb0d979a70..13e45da61100 100644 --- a/drivers/perf/Makefile +++ b/drivers/perf/Makefile @@ -22,3 +22,4 @@ obj-$(CONFIG_MARVELL_CN10K_DDR_PMU) += marvell_cn10k_ddr_pmu.o obj-$(CONFIG_APPLE_M1_CPU_PMU) += apple_m1_cpu_pmu.o obj-$(CONFIG_ALIBABA_UNCORE_DRW_PMU) += alibaba_uncore_drw_pmu.o obj-$(CONFIG_ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU) += arm_cspmu/ +obj-$(CONFIG_MESON_DDR_PMU) += amlogic/ diff --git a/drivers/perf/amlogic/Kconfig b/drivers/perf/amlogic/Kconfig new file mode 100644 index 000000000000..f68db01a7f17 --- /dev/null +++ b/drivers/perf/amlogic/Kconfig @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0-only +config MESON_DDR_PMU + tristate "Amlogic DDR Bandwidth Performance Monitor" + depends on ARCH_MESON || COMPILE_TEST + help + Provides support for the DDR performance monitor + in Amlogic SoCs, which can give information about + memory throughput and other related events. It + supports multiple channels to monitor the memory + bandwidth simultaneously. diff --git a/drivers/perf/amlogic/Makefile b/drivers/perf/amlogic/Makefile new file mode 100644 index 000000000000..d3ab2ac5353b --- /dev/null +++ b/drivers/perf/amlogic/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0-only + +obj-$(CONFIG_MESON_DDR_PMU) += meson_ddr_pmu_g12.o + +meson_ddr_pmu_g12-y := meson_ddr_pmu_core.o meson_g12_ddr_pmu.o diff --git a/drivers/perf/amlogic/meson_ddr_pmu_core.c b/drivers/perf/amlogic/meson_ddr_pmu_core.c new file mode 100644 index 000000000000..0ff7c0449ac2 --- /dev/null +++ b/drivers/perf/amlogic/meson_ddr_pmu_core.c @@ -0,0 +1,562 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022 Amlogic, Inc. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +struct ddr_pmu { + struct pmu pmu; + struct dmc_info info; + struct dmc_counter counters; /* save counters from hw */ + bool pmu_enabled; + struct device *dev; + char *name; + struct hlist_node node; + enum cpuhp_state cpuhp_state; + int cpu; /* for cpu hotplug */ +}; + +#define DDR_PERF_DEV_NAME "meson_ddr_bw" +#define MAX_AXI_PORTS_OF_CHANNEL 4 /* A DMC channel can monitor max 4 axi ports */ + +#define to_ddr_pmu(p) container_of(p, struct ddr_pmu, pmu) +#define dmc_info_to_pmu(p) container_of(p, struct ddr_pmu, info) + +static void dmc_pmu_enable(struct ddr_pmu *pmu) +{ + if (!pmu->pmu_enabled) + pmu->info.hw_info->enable(&pmu->info); + + pmu->pmu_enabled = true; +} + +static void dmc_pmu_disable(struct ddr_pmu *pmu) +{ + if (pmu->pmu_enabled) + pmu->info.hw_info->disable(&pmu->info); + + pmu->pmu_enabled = false; +} + +static void meson_ddr_set_axi_filter(struct perf_event *event, u8 axi_id) +{ + struct ddr_pmu *pmu = to_ddr_pmu(event->pmu); + int chann; + + if (event->attr.config > ALL_CHAN_COUNTER_ID && + event->attr.config < COUNTER_MAX_ID) { + chann = event->attr.config - CHAN1_COUNTER_ID; + + pmu->info.hw_info->set_axi_filter(&pmu->info, axi_id, chann); + } +} + +static void ddr_cnt_addition(struct dmc_counter *sum, + struct dmc_counter *add1, + struct dmc_counter *add2, + int chann_nr) +{ + int i; + u64 cnt1, cnt2; + + sum->all_cnt = add1->all_cnt + add2->all_cnt; + sum->all_req = add1->all_req + add2->all_req; + for (i = 0; i < chann_nr; i++) { + cnt1 = add1->channel_cnt[i]; + cnt2 = add2->channel_cnt[i]; + + sum->channel_cnt[i] = cnt1 + cnt2; + } +} + +static void meson_ddr_perf_event_update(struct perf_event *event) +{ + struct ddr_pmu *pmu = to_ddr_pmu(event->pmu); + u64 new_raw_count = 0; + struct dmc_counter dc = {0}, sum_dc = {0}; + int idx; + int chann_nr = pmu->info.hw_info->chann_nr; + + /* get the remain counters in register. */ + pmu->info.hw_info->get_counters(&pmu->info, &dc); + + ddr_cnt_addition(&sum_dc, &pmu->counters, &dc, chann_nr); + + switch (event->attr.config) { + case ALL_CHAN_COUNTER_ID: + new_raw_count = sum_dc.all_cnt; + break; + case CHAN1_COUNTER_ID: + case CHAN2_COUNTER_ID: + case CHAN3_COUNTER_ID: + case CHAN4_COUNTER_ID: + case CHAN5_COUNTER_ID: + case CHAN6_COUNTER_ID: + case CHAN7_COUNTER_ID: + case CHAN8_COUNTER_ID: + idx = event->attr.config - CHAN1_COUNTER_ID; + new_raw_count = sum_dc.channel_cnt[idx]; + break; + } + + local64_set(&event->count, new_raw_count); +} + +static int meson_ddr_perf_event_init(struct perf_event *event) +{ + struct ddr_pmu *pmu = to_ddr_pmu(event->pmu); + u64 config1 = event->attr.config1; + u64 config2 = event->attr.config2; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK) + return -EOPNOTSUPP; + + if (event->cpu < 0) + return -EOPNOTSUPP; + + /* check if the number of parameters is too much */ + if (event->attr.config != ALL_CHAN_COUNTER_ID && + hweight64(config1) + hweight64(config2) > MAX_AXI_PORTS_OF_CHANNEL) + return -EOPNOTSUPP; + + event->cpu = pmu->cpu; + + return 0; +} + +static void meson_ddr_perf_event_start(struct perf_event *event, int flags) +{ + struct ddr_pmu *pmu = to_ddr_pmu(event->pmu); + + memset(&pmu->counters, 0, sizeof(pmu->counters)); + dmc_pmu_enable(pmu); +} + +static int meson_ddr_perf_event_add(struct perf_event *event, int flags) +{ + u64 config1 = event->attr.config1; + u64 config2 = event->attr.config2; + int i; + + for_each_set_bit(i, (const unsigned long *)&config1, sizeof(config1)) + meson_ddr_set_axi_filter(event, i); + + for_each_set_bit(i, (const unsigned long *)&config2, sizeof(config2)) + meson_ddr_set_axi_filter(event, i + 64); + + if (flags & PERF_EF_START) + meson_ddr_perf_event_start(event, flags); + + return 0; +} + +static void meson_ddr_perf_event_stop(struct perf_event *event, int flags) +{ + struct ddr_pmu *pmu = to_ddr_pmu(event->pmu); + + if (flags & PERF_EF_UPDATE) + meson_ddr_perf_event_update(event); + + dmc_pmu_disable(pmu); +} + +static void meson_ddr_perf_event_del(struct perf_event *event, int flags) +{ + meson_ddr_perf_event_stop(event, PERF_EF_UPDATE); +} + +static ssize_t meson_ddr_perf_cpumask_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct ddr_pmu *pmu = dev_get_drvdata(dev); + + return cpumap_print_to_pagebuf(true, buf, cpumask_of(pmu->cpu)); +} + +static struct device_attribute meson_ddr_perf_cpumask_attr = +__ATTR(cpumask, 0444, meson_ddr_perf_cpumask_show, NULL); + +static struct attribute *meson_ddr_perf_cpumask_attrs[] = { + &meson_ddr_perf_cpumask_attr.attr, + NULL, +}; + +static const struct attribute_group ddr_perf_cpumask_attr_group = { + .attrs = meson_ddr_perf_cpumask_attrs, +}; + +static ssize_t +pmu_event_show(struct device *dev, struct device_attribute *attr, + char *page) +{ + struct perf_pmu_events_attr *pmu_attr; + + pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr); + return sysfs_emit(page, "event=0x%02llx\n", pmu_attr->id); +} + +static ssize_t +event_show_unit(struct device *dev, struct device_attribute *attr, + char *page) +{ + return sysfs_emit(page, "MB\n"); +} + +static ssize_t +event_show_scale(struct device *dev, struct device_attribute *attr, + char *page) +{ + /* one count = 16byte = 1.52587890625e-05 MB */ + return sysfs_emit(page, "1.52587890625e-05\n"); +} + +#define AML_DDR_PMU_EVENT_ATTR(_name, _id) \ +{ \ + .attr = __ATTR(_name, 0444, pmu_event_show, NULL), \ + .id = _id, \ +} + +#define AML_DDR_PMU_EVENT_UNIT_ATTR(_name) \ + __ATTR(_name.unit, 0444, event_show_unit, NULL) + +#define AML_DDR_PMU_EVENT_SCALE_ATTR(_name) \ + __ATTR(_name.scale, 0444, event_show_scale, NULL) + +static struct device_attribute event_unit_attrs[] = { + AML_DDR_PMU_EVENT_UNIT_ATTR(total_rw_bytes), + AML_DDR_PMU_EVENT_UNIT_ATTR(chan_1_rw_bytes), + AML_DDR_PMU_EVENT_UNIT_ATTR(chan_2_rw_bytes), + AML_DDR_PMU_EVENT_UNIT_ATTR(chan_3_rw_bytes), + AML_DDR_PMU_EVENT_UNIT_ATTR(chan_4_rw_bytes), + AML_DDR_PMU_EVENT_UNIT_ATTR(chan_5_rw_bytes), + AML_DDR_PMU_EVENT_UNIT_ATTR(chan_6_rw_bytes), + AML_DDR_PMU_EVENT_UNIT_ATTR(chan_7_rw_bytes), + AML_DDR_PMU_EVENT_UNIT_ATTR(chan_8_rw_bytes), +}; + +static struct device_attribute event_scale_attrs[] = { + AML_DDR_PMU_EVENT_SCALE_ATTR(total_rw_bytes), + AML_DDR_PMU_EVENT_SCALE_ATTR(chan_1_rw_bytes), + AML_DDR_PMU_EVENT_SCALE_ATTR(chan_2_rw_bytes), + AML_DDR_PMU_EVENT_SCALE_ATTR(chan_3_rw_bytes), + AML_DDR_PMU_EVENT_SCALE_ATTR(chan_4_rw_bytes), + AML_DDR_PMU_EVENT_SCALE_ATTR(chan_5_rw_bytes), + AML_DDR_PMU_EVENT_SCALE_ATTR(chan_6_rw_bytes), + AML_DDR_PMU_EVENT_SCALE_ATTR(chan_7_rw_bytes), + AML_DDR_PMU_EVENT_SCALE_ATTR(chan_8_rw_bytes), +}; + +static struct perf_pmu_events_attr event_attrs[] = { + AML_DDR_PMU_EVENT_ATTR(total_rw_bytes, ALL_CHAN_COUNTER_ID), + AML_DDR_PMU_EVENT_ATTR(chan_1_rw_bytes, CHAN1_COUNTER_ID), + AML_DDR_PMU_EVENT_ATTR(chan_2_rw_bytes, CHAN2_COUNTER_ID), + AML_DDR_PMU_EVENT_ATTR(chan_3_rw_bytes, CHAN3_COUNTER_ID), + AML_DDR_PMU_EVENT_ATTR(chan_4_rw_bytes, CHAN4_COUNTER_ID), + AML_DDR_PMU_EVENT_ATTR(chan_5_rw_bytes, CHAN5_COUNTER_ID), + AML_DDR_PMU_EVENT_ATTR(chan_6_rw_bytes, CHAN6_COUNTER_ID), + AML_DDR_PMU_EVENT_ATTR(chan_7_rw_bytes, CHAN7_COUNTER_ID), + AML_DDR_PMU_EVENT_ATTR(chan_8_rw_bytes, CHAN8_COUNTER_ID), +}; + +/* three attrs are combined an event */ +static struct attribute *ddr_perf_events_attrs[COUNTER_MAX_ID * 3]; + +static struct attribute_group ddr_perf_events_attr_group = { + .name = "events", + .attrs = ddr_perf_events_attrs, +}; + +static umode_t meson_ddr_perf_format_attr_visible(struct kobject *kobj, + struct attribute *attr, + int n) +{ + struct pmu *pmu = dev_get_drvdata(kobj_to_dev(kobj)); + struct ddr_pmu *ddr_pmu = to_ddr_pmu(pmu); + const u64 *capability = ddr_pmu->info.hw_info->capability; + struct device_attribute *dev_attr; + int id; + char value[20]; // config1:xxx, 20 is enough + + dev_attr = container_of(attr, struct device_attribute, attr); + dev_attr->show(NULL, NULL, value); + + if (sscanf(value, "config1:%d", &id) == 1) + return capability[0] & (1ULL << id) ? attr->mode : 0; + + if (sscanf(value, "config2:%d", &id) == 1) + return capability[1] & (1ULL << id) ? attr->mode : 0; + + return attr->mode; +} + +static struct attribute_group ddr_perf_format_attr_group = { + .name = "format", + .is_visible = meson_ddr_perf_format_attr_visible, +}; + +static ssize_t meson_ddr_perf_identifier_show(struct device *dev, + struct device_attribute *attr, + char *page) +{ + struct ddr_pmu *pmu = dev_get_drvdata(dev); + + return sysfs_emit(page, "%s\n", pmu->name); +} + +static struct device_attribute meson_ddr_perf_identifier_attr = +__ATTR(identifier, 0444, meson_ddr_perf_identifier_show, NULL); + +static struct attribute *meson_ddr_perf_identifier_attrs[] = { + &meson_ddr_perf_identifier_attr.attr, + NULL, +}; + +static const struct attribute_group ddr_perf_identifier_attr_group = { + .attrs = meson_ddr_perf_identifier_attrs, +}; + +static const struct attribute_group *attr_groups[] = { + &ddr_perf_events_attr_group, + &ddr_perf_format_attr_group, + &ddr_perf_cpumask_attr_group, + &ddr_perf_identifier_attr_group, + NULL, +}; + +static irqreturn_t dmc_irq_handler(int irq, void *dev_id) +{ + struct dmc_info *info = dev_id; + struct ddr_pmu *pmu; + struct dmc_counter counters, *sum_cnter; + int i; + + pmu = dmc_info_to_pmu(info); + + if (info->hw_info->irq_handler(info, &counters) != 0) + goto out; + + sum_cnter = &pmu->counters; + sum_cnter->all_cnt += counters.all_cnt; + sum_cnter->all_req += counters.all_req; + + for (i = 0; i < pmu->info.hw_info->chann_nr; i++) + sum_cnter->channel_cnt[i] += counters.channel_cnt[i]; + + if (pmu->pmu_enabled) + /* + * the timer interrupt only supprt + * one shot mode, we have to re-enable + * it in ISR to support continue mode. + */ + info->hw_info->enable(info); + + dev_dbg(pmu->dev, "counts: %llu %llu %llu, %llu, %llu, %llu\t\t" + "sum: %llu %llu %llu, %llu, %llu, %llu\n", + counters.all_req, + counters.all_cnt, + counters.channel_cnt[0], + counters.channel_cnt[1], + counters.channel_cnt[2], + counters.channel_cnt[3], + + pmu->counters.all_req, + pmu->counters.all_cnt, + pmu->counters.channel_cnt[0], + pmu->counters.channel_cnt[1], + pmu->counters.channel_cnt[2], + pmu->counters.channel_cnt[3]); +out: + return IRQ_HANDLED; +} + +static int ddr_perf_offline_cpu(unsigned int cpu, struct hlist_node *node) +{ + struct ddr_pmu *pmu = hlist_entry_safe(node, struct ddr_pmu, node); + int target; + + if (cpu != pmu->cpu) + return 0; + + target = cpumask_any_but(cpu_online_mask, cpu); + if (target >= nr_cpu_ids) + return 0; + + perf_pmu_migrate_context(&pmu->pmu, cpu, target); + pmu->cpu = target; + + WARN_ON(irq_set_affinity(pmu->info.irq_num, cpumask_of(pmu->cpu))); + + return 0; +} + +static void fill_event_attr(struct ddr_pmu *pmu) +{ + int i, j, k; + struct attribute **dst = ddr_perf_events_attrs; + + j = 0; + k = 0; + + /* fill ALL_CHAN_COUNTER_ID event */ + dst[j++] = &event_attrs[k].attr.attr; + dst[j++] = &event_unit_attrs[k].attr; + dst[j++] = &event_scale_attrs[k].attr; + + k++; + + /* fill each channel event */ + for (i = 0; i < pmu->info.hw_info->chann_nr; i++, k++) { + dst[j++] = &event_attrs[k].attr.attr; + dst[j++] = &event_unit_attrs[k].attr; + dst[j++] = &event_scale_attrs[k].attr; + } + + dst[j] = NULL; /* mark end */ +} + +static void fmt_attr_fill(struct attribute **fmt_attr) +{ + ddr_perf_format_attr_group.attrs = fmt_attr; +} + +static int ddr_pmu_parse_dt(struct platform_device *pdev, + struct dmc_info *info) +{ + void __iomem *base; + int i, ret; + + info->hw_info = of_device_get_match_data(&pdev->dev); + + for (i = 0; i < info->hw_info->dmc_nr; i++) { + /* resource 0 for ddr register base */ + base = devm_platform_ioremap_resource(pdev, i); + if (IS_ERR(base)) + return PTR_ERR(base); + + info->ddr_reg[i] = base; + } + + /* resource i for pll register base */ + base = devm_platform_ioremap_resource(pdev, i); + if (IS_ERR(base)) + return PTR_ERR(base); + + info->pll_reg = base; + + ret = platform_get_irq(pdev, 0); + if (ret < 0) + return ret; + + info->irq_num = ret; + + ret = devm_request_irq(&pdev->dev, info->irq_num, dmc_irq_handler, + IRQF_NOBALANCING, dev_name(&pdev->dev), + (void *)info); + if (ret < 0) + return ret; + + return 0; +} + +int meson_ddr_pmu_create(struct platform_device *pdev) +{ + int ret; + char *name; + struct ddr_pmu *pmu; + + pmu = devm_kzalloc(&pdev->dev, sizeof(struct ddr_pmu), GFP_KERNEL); + if (!pmu) + return -ENOMEM; + + *pmu = (struct ddr_pmu) { + .pmu = { + .module = THIS_MODULE, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE, + .task_ctx_nr = perf_invalid_context, + .attr_groups = attr_groups, + .event_init = meson_ddr_perf_event_init, + .add = meson_ddr_perf_event_add, + .del = meson_ddr_perf_event_del, + .start = meson_ddr_perf_event_start, + .stop = meson_ddr_perf_event_stop, + .read = meson_ddr_perf_event_update, + }, + }; + + ret = ddr_pmu_parse_dt(pdev, &pmu->info); + if (ret < 0) + return ret; + + fmt_attr_fill(pmu->info.hw_info->fmt_attr); + + pmu->cpu = smp_processor_id(); + + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, DDR_PERF_DEV_NAME); + if (!name) + return -ENOMEM; + + ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, name, NULL, + ddr_perf_offline_cpu); + if (ret < 0) + return ret; + + pmu->cpuhp_state = ret; + + /* Register the pmu instance for cpu hotplug */ + ret = cpuhp_state_add_instance_nocalls(pmu->cpuhp_state, &pmu->node); + if (ret) + goto cpuhp_instance_err; + + fill_event_attr(pmu); + + ret = perf_pmu_register(&pmu->pmu, name, -1); + if (ret) + goto pmu_register_err; + + pmu->name = name; + pmu->dev = &pdev->dev; + pmu->pmu_enabled = false; + + platform_set_drvdata(pdev, pmu); + + return 0; + +pmu_register_err: + cpuhp_state_remove_instance_nocalls(pmu->cpuhp_state, &pmu->node); + +cpuhp_instance_err: + cpuhp_remove_state(pmu->cpuhp_state); + + return ret; +} + +int meson_ddr_pmu_remove(struct platform_device *pdev) +{ + struct ddr_pmu *pmu = platform_get_drvdata(pdev); + + perf_pmu_unregister(&pmu->pmu); + cpuhp_state_remove_instance_nocalls(pmu->cpuhp_state, &pmu->node); + cpuhp_remove_state(pmu->cpuhp_state); + + return 0; +} diff --git a/drivers/perf/amlogic/meson_g12_ddr_pmu.c b/drivers/perf/amlogic/meson_g12_ddr_pmu.c new file mode 100644 index 000000000000..c07c34f03cce --- /dev/null +++ b/drivers/perf/amlogic/meson_g12_ddr_pmu.c @@ -0,0 +1,394 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022 Amlogic, Inc. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#define PORT_MAJOR 32 +#define DEFAULT_XTAL_FREQ 24000000UL + +#define DMC_QOS_IRQ BIT(30) + +/* DMC bandwidth monitor register address offset */ +#define DMC_MON_G12_CTRL0 (0x20 << 2) +#define DMC_MON_G12_CTRL1 (0x21 << 2) +#define DMC_MON_G12_CTRL2 (0x22 << 2) +#define DMC_MON_G12_CTRL3 (0x23 << 2) +#define DMC_MON_G12_CTRL4 (0x24 << 2) +#define DMC_MON_G12_CTRL5 (0x25 << 2) +#define DMC_MON_G12_CTRL6 (0x26 << 2) +#define DMC_MON_G12_CTRL7 (0x27 << 2) +#define DMC_MON_G12_CTRL8 (0x28 << 2) + +#define DMC_MON_G12_ALL_REQ_CNT (0x29 << 2) +#define DMC_MON_G12_ALL_GRANT_CNT (0x2a << 2) +#define DMC_MON_G12_ONE_GRANT_CNT (0x2b << 2) +#define DMC_MON_G12_SEC_GRANT_CNT (0x2c << 2) +#define DMC_MON_G12_THD_GRANT_CNT (0x2d << 2) +#define DMC_MON_G12_FOR_GRANT_CNT (0x2e << 2) +#define DMC_MON_G12_TIMER (0x2f << 2) + +/* Each bit represent a axi line */ +PMU_FORMAT_ATTR(event, "config:0-7"); +PMU_FORMAT_ATTR(arm, "config1:0"); +PMU_FORMAT_ATTR(gpu, "config1:1"); +PMU_FORMAT_ATTR(pcie, "config1:2"); +PMU_FORMAT_ATTR(hdcp, "config1:3"); +PMU_FORMAT_ATTR(hevc_front, "config1:4"); +PMU_FORMAT_ATTR(usb3_0, "config1:6"); +PMU_FORMAT_ATTR(device, "config1:7"); +PMU_FORMAT_ATTR(hevc_back, "config1:8"); +PMU_FORMAT_ATTR(h265enc, "config1:9"); +PMU_FORMAT_ATTR(vpu_read1, "config1:16"); +PMU_FORMAT_ATTR(vpu_read2, "config1:17"); +PMU_FORMAT_ATTR(vpu_read3, "config1:18"); +PMU_FORMAT_ATTR(vpu_write1, "config1:19"); +PMU_FORMAT_ATTR(vpu_write2, "config1:20"); +PMU_FORMAT_ATTR(vdec, "config1:21"); +PMU_FORMAT_ATTR(hcodec, "config1:22"); +PMU_FORMAT_ATTR(ge2d, "config1:23"); + +PMU_FORMAT_ATTR(spicc1, "config1:32"); +PMU_FORMAT_ATTR(usb0, "config1:33"); +PMU_FORMAT_ATTR(dma, "config1:34"); +PMU_FORMAT_ATTR(arb0, "config1:35"); +PMU_FORMAT_ATTR(sd_emmc_b, "config1:36"); +PMU_FORMAT_ATTR(usb1, "config1:37"); +PMU_FORMAT_ATTR(audio, "config1:38"); +PMU_FORMAT_ATTR(aififo, "config1:39"); +PMU_FORMAT_ATTR(parser, "config1:41"); +PMU_FORMAT_ATTR(ao_cpu, "config1:42"); +PMU_FORMAT_ATTR(sd_emmc_c, "config1:43"); +PMU_FORMAT_ATTR(spicc2, "config1:44"); +PMU_FORMAT_ATTR(ethernet, "config1:45"); +PMU_FORMAT_ATTR(sana, "config1:46"); + +/* for sm1 and g12b */ +PMU_FORMAT_ATTR(nna, "config1:10"); + +/* for g12b only */ +PMU_FORMAT_ATTR(gdc, "config1:11"); +PMU_FORMAT_ATTR(mipi_isp, "config1:12"); +PMU_FORMAT_ATTR(arm1, "config1:13"); +PMU_FORMAT_ATTR(sd_emmc_a, "config1:40"); + +static struct attribute *g12_pmu_format_attrs[] = { + &format_attr_event.attr, + &format_attr_arm.attr, + &format_attr_gpu.attr, + &format_attr_nna.attr, + &format_attr_gdc.attr, + &format_attr_arm1.attr, + &format_attr_mipi_isp.attr, + &format_attr_sd_emmc_a.attr, + &format_attr_pcie.attr, + &format_attr_hdcp.attr, + &format_attr_hevc_front.attr, + &format_attr_usb3_0.attr, + &format_attr_device.attr, + &format_attr_hevc_back.attr, + &format_attr_h265enc.attr, + &format_attr_vpu_read1.attr, + &format_attr_vpu_read2.attr, + &format_attr_vpu_read3.attr, + &format_attr_vpu_write1.attr, + &format_attr_vpu_write2.attr, + &format_attr_vdec.attr, + &format_attr_hcodec.attr, + &format_attr_ge2d.attr, + &format_attr_spicc1.attr, + &format_attr_usb0.attr, + &format_attr_dma.attr, + &format_attr_arb0.attr, + &format_attr_sd_emmc_b.attr, + &format_attr_usb1.attr, + &format_attr_audio.attr, + &format_attr_aififo.attr, + &format_attr_parser.attr, + &format_attr_ao_cpu.attr, + &format_attr_sd_emmc_c.attr, + &format_attr_spicc2.attr, + &format_attr_ethernet.attr, + &format_attr_sana.attr, + NULL, +}; + +/* calculate ddr clock */ +static unsigned long dmc_g12_get_freq_quick(struct dmc_info *info) +{ + unsigned int val; + unsigned int n, m, od1; + unsigned int od_div = 0xfff; + unsigned long freq = 0; + + val = readl(info->pll_reg); + val = val & 0xfffff; + switch ((val >> 16) & 7) { + case 0: + od_div = 2; + break; + + case 1: + od_div = 3; + break; + + case 2: + od_div = 4; + break; + + case 3: + od_div = 6; + break; + + case 4: + od_div = 8; + break; + + default: + break; + } + + m = val & 0x1ff; + n = ((val >> 10) & 0x1f); + od1 = (((val >> 19) & 0x1)) == 1 ? 2 : 1; + freq = DEFAULT_XTAL_FREQ / 1000; /* avoid overflow */ + if (n) + freq = ((((freq * m) / n) >> od1) / od_div) * 1000; + + return freq; +} + +#ifdef DEBUG +static void g12_dump_reg(struct dmc_info *db) +{ + int s = 0, i; + unsigned int r; + + for (i = 0; i < 9; i++) { + r = readl(db->ddr_reg[0] + (DMC_MON_G12_CTRL0 + (i << 2))); + pr_notice("DMC_MON_CTRL%d: %08x\n", i, r); + } + r = readl(db->ddr_reg[0] + DMC_MON_G12_ALL_REQ_CNT); + pr_notice("DMC_MON_ALL_REQ_CNT: %08x\n", r); + r = readl(db->ddr_reg[0] + DMC_MON_G12_ALL_GRANT_CNT); + pr_notice("DMC_MON_ALL_GRANT_CNT:%08x\n", r); + r = readl(db->ddr_reg[0] + DMC_MON_G12_ONE_GRANT_CNT); + pr_notice("DMC_MON_ONE_GRANT_CNT:%08x\n", r); + r = readl(db->ddr_reg[0] + DMC_MON_G12_SEC_GRANT_CNT); + pr_notice("DMC_MON_SEC_GRANT_CNT:%08x\n", r); + r = readl(db->ddr_reg[0] + DMC_MON_G12_THD_GRANT_CNT); + pr_notice("DMC_MON_THD_GRANT_CNT:%08x\n", r); + r = readl(db->ddr_reg[0] + DMC_MON_G12_FOR_GRANT_CNT); + pr_notice("DMC_MON_FOR_GRANT_CNT:%08x\n", r); + r = readl(db->ddr_reg[0] + DMC_MON_G12_TIMER); + pr_notice("DMC_MON_TIMER: %08x\n", r); +} +#endif + +static void dmc_g12_counter_enable(struct dmc_info *info) +{ + unsigned int val; + unsigned long clock_count = dmc_g12_get_freq_quick(info) / 10; /* 100ms */ + + writel(clock_count, info->ddr_reg[0] + DMC_MON_G12_TIMER); + + val = readl(info->ddr_reg[0] + DMC_MON_G12_CTRL0); + + /* enable all channel */ + val = BIT(31) | /* enable bit */ + BIT(20) | /* use timer */ + 0x0f; /* 4 channels */ + + writel(val, info->ddr_reg[0] + DMC_MON_G12_CTRL0); + +#ifdef DEBUG + g12_dump_reg(info); +#endif +} + +static void dmc_g12_config_fiter(struct dmc_info *info, + int port, int channel) +{ + u32 val; + u32 rp[MAX_CHANNEL_NUM] = {DMC_MON_G12_CTRL1, DMC_MON_G12_CTRL3, + DMC_MON_G12_CTRL5, DMC_MON_G12_CTRL7}; + u32 rs[MAX_CHANNEL_NUM] = {DMC_MON_G12_CTRL2, DMC_MON_G12_CTRL4, + DMC_MON_G12_CTRL6, DMC_MON_G12_CTRL8}; + int subport = -1; + + /* clear all port mask */ + if (port < 0) { + writel(0, info->ddr_reg[0] + rp[channel]); + writel(0, info->ddr_reg[0] + rs[channel]); + return; + } + + if (port >= PORT_MAJOR) + subport = port - PORT_MAJOR; + + if (subport < 0) { + val = readl(info->ddr_reg[0] + rp[channel]); + val |= (1 << port); + writel(val, info->ddr_reg[0] + rp[channel]); + val = 0xffff; + writel(val, info->ddr_reg[0] + rs[channel]); + } else { + val = BIT(23); /* select device */ + writel(val, info->ddr_reg[0] + rp[channel]); + val = readl(info->ddr_reg[0] + rs[channel]); + val |= (1 << subport); + writel(val, info->ddr_reg[0] + rs[channel]); + } +} + +static void dmc_g12_set_axi_filter(struct dmc_info *info, int axi_id, int channel) +{ + if (channel > info->hw_info->chann_nr) + return; + + dmc_g12_config_fiter(info, axi_id, channel); +} + +static void dmc_g12_counter_disable(struct dmc_info *info) +{ + int i; + + /* clear timer */ + writel(0, info->ddr_reg[0] + DMC_MON_G12_CTRL0); + writel(0, info->ddr_reg[0] + DMC_MON_G12_TIMER); + + writel(0, info->ddr_reg[0] + DMC_MON_G12_ALL_REQ_CNT); + writel(0, info->ddr_reg[0] + DMC_MON_G12_ALL_GRANT_CNT); + writel(0, info->ddr_reg[0] + DMC_MON_G12_ONE_GRANT_CNT); + writel(0, info->ddr_reg[0] + DMC_MON_G12_SEC_GRANT_CNT); + writel(0, info->ddr_reg[0] + DMC_MON_G12_THD_GRANT_CNT); + writel(0, info->ddr_reg[0] + DMC_MON_G12_FOR_GRANT_CNT); + + /* clear port channel mapping */ + for (i = 0; i < info->hw_info->chann_nr; i++) + dmc_g12_config_fiter(info, -1, i); +} + +static void dmc_g12_get_counters(struct dmc_info *info, + struct dmc_counter *counter) +{ + int i; + unsigned int reg; + + counter->all_cnt = readl(info->ddr_reg[0] + DMC_MON_G12_ALL_GRANT_CNT); + counter->all_req = readl(info->ddr_reg[0] + DMC_MON_G12_ALL_REQ_CNT); + + for (i = 0; i < info->hw_info->chann_nr; i++) { + reg = DMC_MON_G12_ONE_GRANT_CNT + (i << 2); + counter->channel_cnt[i] = readl(info->ddr_reg[0] + reg); + } +} + +static int dmc_g12_irq_handler(struct dmc_info *info, + struct dmc_counter *counter) +{ + unsigned int val; + int ret = -EINVAL; + + val = readl(info->ddr_reg[0] + DMC_MON_G12_CTRL0); + if (val & DMC_QOS_IRQ) { + dmc_g12_get_counters(info, counter); + /* clear irq flags */ + writel(val, info->ddr_reg[0] + DMC_MON_G12_CTRL0); + ret = 0; + } + return ret; +} + +static const struct dmc_hw_info g12a_dmc_info = { + .enable = dmc_g12_counter_enable, + .disable = dmc_g12_counter_disable, + .irq_handler = dmc_g12_irq_handler, + .get_counters = dmc_g12_get_counters, + .set_axi_filter = dmc_g12_set_axi_filter, + + .dmc_nr = 1, + .chann_nr = 4, + .capability = {0X7EFF00FF03DF, 0}, + .fmt_attr = g12_pmu_format_attrs, +}; + +static const struct dmc_hw_info g12b_dmc_info = { + .enable = dmc_g12_counter_enable, + .disable = dmc_g12_counter_disable, + .irq_handler = dmc_g12_irq_handler, + .get_counters = dmc_g12_get_counters, + .set_axi_filter = dmc_g12_set_axi_filter, + + .dmc_nr = 1, + .chann_nr = 4, + .capability = {0X7FFF00FF3FDF, 0}, + .fmt_attr = g12_pmu_format_attrs, +}; + +static const struct dmc_hw_info sm1_dmc_info = { + .enable = dmc_g12_counter_enable, + .disable = dmc_g12_counter_disable, + .irq_handler = dmc_g12_irq_handler, + .get_counters = dmc_g12_get_counters, + .set_axi_filter = dmc_g12_set_axi_filter, + + .dmc_nr = 1, + .chann_nr = 4, + .capability = {0X7EFF00FF07DF, 0}, + .fmt_attr = g12_pmu_format_attrs, +}; + +static int g12_ddr_pmu_probe(struct platform_device *pdev) +{ + return meson_ddr_pmu_create(pdev); +} + +static int g12_ddr_pmu_remove(struct platform_device *pdev) +{ + meson_ddr_pmu_remove(pdev); + + return 0; +} + +static const struct of_device_id meson_ddr_pmu_dt_match[] = { + { + .compatible = "amlogic,g12a-ddr-pmu", + .data = &g12a_dmc_info, + }, + { + .compatible = "amlogic,g12b-ddr-pmu", + .data = &g12b_dmc_info, + }, + { + .compatible = "amlogic,sm1-ddr-pmu", + .data = &sm1_dmc_info, + }, + {} +}; + +static struct platform_driver g12_ddr_pmu_driver = { + .probe = g12_ddr_pmu_probe, + .remove = g12_ddr_pmu_remove, + + .driver = { + .name = "meson-g12-ddr-pmu", + .of_match_table = meson_ddr_pmu_dt_match, + }, +}; + +module_platform_driver(g12_ddr_pmu_driver); +MODULE_AUTHOR("Jiucheng Xu"); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Amlogic G12 series SoC DDR PMU"); diff --git a/include/soc/amlogic/meson_ddr_pmu.h b/include/soc/amlogic/meson_ddr_pmu.h new file mode 100644 index 000000000000..4a33e4ab8ada --- /dev/null +++ b/include/soc/amlogic/meson_ddr_pmu.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022 Amlogic, Inc. All rights reserved. + */ + +#ifndef __MESON_DDR_PMU_H__ +#define __MESON_DDR_PMU_H__ + +#define MAX_CHANNEL_NUM 8 + +enum { + ALL_CHAN_COUNTER_ID, + CHAN1_COUNTER_ID, + CHAN2_COUNTER_ID, + CHAN3_COUNTER_ID, + CHAN4_COUNTER_ID, + CHAN5_COUNTER_ID, + CHAN6_COUNTER_ID, + CHAN7_COUNTER_ID, + CHAN8_COUNTER_ID, + COUNTER_MAX_ID, +}; + +struct dmc_info; + +struct dmc_counter { + u64 all_cnt; /* The count of all requests come in/out ddr controller */ + union { + u64 all_req; + struct { + u64 all_idle_cnt; + u64 all_16bit_cnt; + }; + }; + u64 channel_cnt[MAX_CHANNEL_NUM]; /* To save a DMC bandwidth-monitor channel counter */ +}; + +struct dmc_hw_info { + void (*enable)(struct dmc_info *info); + void (*disable)(struct dmc_info *info); + /* Bind an axi line to a bandwidth-monitor channel */ + void (*set_axi_filter)(struct dmc_info *info, int axi_id, int chann); + int (*irq_handler)(struct dmc_info *info, + struct dmc_counter *counter); + void (*get_counters)(struct dmc_info *info, + struct dmc_counter *counter); + + int dmc_nr; /* The number of dmc controller */ + int chann_nr; /* The number of dmc bandwidth monitor channels */ + struct attribute **fmt_attr; + const u64 capability[2]; +}; + +struct dmc_info { + const struct dmc_hw_info *hw_info; + + void __iomem *ddr_reg[4]; + unsigned long timer_value; /* Timer value in TIMER register */ + void __iomem *pll_reg; + int irq_num; /* irq vector number */ +}; + +int meson_ddr_pmu_create(struct platform_device *pdev); +int meson_ddr_pmu_remove(struct platform_device *pdev); + +#endif /* __MESON_DDR_PMU_H__ */ -- cgit v1.2.3 From 229d58e31678dece365060c50a39a99a2b1dc729 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 16 Nov 2022 17:03:24 +0000 Subject: firmware: arm_ffa: Move constants to header file FF-A function IDs and error codes will be needed in the hypervisor too, so move to them to the header file where they can be shared. Rename the version constants with an "FFA_" prefix so that they are less likely to clash with other code in the tree. Co-developed-by: Andrew Walbran Signed-off-by: Andrew Walbran Signed-off-by: Quentin Perret Reviewed-by: Sudeep Holla Link: https://lore.kernel.org/r/20221116170335.2341003-2-qperret@google.com Signed-off-by: Will Deacon --- drivers/firmware/arm_ffa/driver.c | 101 ++++---------------------------------- include/linux/arm_ffa.h | 83 +++++++++++++++++++++++++++++++ 2 files changed, 93 insertions(+), 91 deletions(-) (limited to 'include') diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index d5e86ef40b89..fa85c64d3ded 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -36,81 +36,6 @@ #include "common.h" #define FFA_DRIVER_VERSION FFA_VERSION_1_0 - -#define FFA_SMC(calling_convention, func_num) \ - ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, (calling_convention), \ - ARM_SMCCC_OWNER_STANDARD, (func_num)) - -#define FFA_SMC_32(func_num) FFA_SMC(ARM_SMCCC_SMC_32, (func_num)) -#define FFA_SMC_64(func_num) FFA_SMC(ARM_SMCCC_SMC_64, (func_num)) - -#define FFA_ERROR FFA_SMC_32(0x60) -#define FFA_SUCCESS FFA_SMC_32(0x61) -#define FFA_INTERRUPT FFA_SMC_32(0x62) -#define FFA_VERSION FFA_SMC_32(0x63) -#define FFA_FEATURES FFA_SMC_32(0x64) -#define FFA_RX_RELEASE FFA_SMC_32(0x65) -#define FFA_RXTX_MAP FFA_SMC_32(0x66) -#define FFA_FN64_RXTX_MAP FFA_SMC_64(0x66) -#define FFA_RXTX_UNMAP FFA_SMC_32(0x67) -#define FFA_PARTITION_INFO_GET FFA_SMC_32(0x68) -#define FFA_ID_GET FFA_SMC_32(0x69) -#define FFA_MSG_POLL FFA_SMC_32(0x6A) -#define FFA_MSG_WAIT FFA_SMC_32(0x6B) -#define FFA_YIELD FFA_SMC_32(0x6C) -#define FFA_RUN FFA_SMC_32(0x6D) -#define FFA_MSG_SEND FFA_SMC_32(0x6E) -#define FFA_MSG_SEND_DIRECT_REQ FFA_SMC_32(0x6F) -#define FFA_FN64_MSG_SEND_DIRECT_REQ FFA_SMC_64(0x6F) -#define FFA_MSG_SEND_DIRECT_RESP FFA_SMC_32(0x70) -#define FFA_FN64_MSG_SEND_DIRECT_RESP FFA_SMC_64(0x70) -#define FFA_MEM_DONATE FFA_SMC_32(0x71) -#define FFA_FN64_MEM_DONATE FFA_SMC_64(0x71) -#define FFA_MEM_LEND FFA_SMC_32(0x72) -#define FFA_FN64_MEM_LEND FFA_SMC_64(0x72) -#define FFA_MEM_SHARE FFA_SMC_32(0x73) -#define FFA_FN64_MEM_SHARE FFA_SMC_64(0x73) -#define FFA_MEM_RETRIEVE_REQ FFA_SMC_32(0x74) -#define FFA_FN64_MEM_RETRIEVE_REQ FFA_SMC_64(0x74) -#define FFA_MEM_RETRIEVE_RESP FFA_SMC_32(0x75) -#define FFA_MEM_RELINQUISH FFA_SMC_32(0x76) -#define FFA_MEM_RECLAIM FFA_SMC_32(0x77) -#define FFA_MEM_OP_PAUSE FFA_SMC_32(0x78) -#define FFA_MEM_OP_RESUME FFA_SMC_32(0x79) -#define FFA_MEM_FRAG_RX FFA_SMC_32(0x7A) -#define FFA_MEM_FRAG_TX FFA_SMC_32(0x7B) -#define FFA_NORMAL_WORLD_RESUME FFA_SMC_32(0x7C) - -/* - * For some calls it is necessary to use SMC64 to pass or return 64-bit values. - * For such calls FFA_FN_NATIVE(name) will choose the appropriate - * (native-width) function ID. - */ -#ifdef CONFIG_64BIT -#define FFA_FN_NATIVE(name) FFA_FN64_##name -#else -#define FFA_FN_NATIVE(name) FFA_##name -#endif - -/* FFA error codes. */ -#define FFA_RET_SUCCESS (0) -#define FFA_RET_NOT_SUPPORTED (-1) -#define FFA_RET_INVALID_PARAMETERS (-2) -#define FFA_RET_NO_MEMORY (-3) -#define FFA_RET_BUSY (-4) -#define FFA_RET_INTERRUPTED (-5) -#define FFA_RET_DENIED (-6) -#define FFA_RET_RETRY (-7) -#define FFA_RET_ABORTED (-8) - -#define MAJOR_VERSION_MASK GENMASK(30, 16) -#define MINOR_VERSION_MASK GENMASK(15, 0) -#define MAJOR_VERSION(x) ((u16)(FIELD_GET(MAJOR_VERSION_MASK, (x)))) -#define MINOR_VERSION(x) ((u16)(FIELD_GET(MINOR_VERSION_MASK, (x)))) -#define PACK_VERSION_INFO(major, minor) \ - (FIELD_PREP(MAJOR_VERSION_MASK, (major)) | \ - FIELD_PREP(MINOR_VERSION_MASK, (minor))) -#define FFA_VERSION_1_0 PACK_VERSION_INFO(1, 0) #define FFA_MIN_VERSION FFA_VERSION_1_0 #define SENDER_ID_MASK GENMASK(31, 16) @@ -120,12 +45,6 @@ #define PACK_TARGET_INFO(s, r) \ (FIELD_PREP(SENDER_ID_MASK, (s)) | FIELD_PREP(RECEIVER_ID_MASK, (r))) -/* - * FF-A specification mentions explicitly about '4K pages'. This should - * not be confused with the kernel PAGE_SIZE, which is the translation - * granule kernel is configured and may be one among 4K, 16K and 64K. - */ -#define FFA_PAGE_SIZE SZ_4K /* * Keeping RX TX buffer size as 4K for now * 64K may be preferred to keep it min a page in 64K PAGE_SIZE config @@ -178,9 +97,9 @@ static struct ffa_drv_info *drv_info; */ static u32 ffa_compatible_version_find(u32 version) { - u16 major = MAJOR_VERSION(version), minor = MINOR_VERSION(version); - u16 drv_major = MAJOR_VERSION(FFA_DRIVER_VERSION); - u16 drv_minor = MINOR_VERSION(FFA_DRIVER_VERSION); + u16 major = FFA_MAJOR_VERSION(version), minor = FFA_MINOR_VERSION(version); + u16 drv_major = FFA_MAJOR_VERSION(FFA_DRIVER_VERSION); + u16 drv_minor = FFA_MINOR_VERSION(FFA_DRIVER_VERSION); if ((major < drv_major) || (major == drv_major && minor <= drv_minor)) return version; @@ -204,16 +123,16 @@ static int ffa_version_check(u32 *version) if (ver.a0 < FFA_MIN_VERSION) { pr_err("Incompatible v%d.%d! Earliest supported v%d.%d\n", - MAJOR_VERSION(ver.a0), MINOR_VERSION(ver.a0), - MAJOR_VERSION(FFA_MIN_VERSION), - MINOR_VERSION(FFA_MIN_VERSION)); + FFA_MAJOR_VERSION(ver.a0), FFA_MINOR_VERSION(ver.a0), + FFA_MAJOR_VERSION(FFA_MIN_VERSION), + FFA_MINOR_VERSION(FFA_MIN_VERSION)); return -EINVAL; } - pr_info("Driver version %d.%d\n", MAJOR_VERSION(FFA_DRIVER_VERSION), - MINOR_VERSION(FFA_DRIVER_VERSION)); - pr_info("Firmware version %d.%d found\n", MAJOR_VERSION(ver.a0), - MINOR_VERSION(ver.a0)); + pr_info("Driver version %d.%d\n", FFA_MAJOR_VERSION(FFA_DRIVER_VERSION), + FFA_MINOR_VERSION(FFA_DRIVER_VERSION)); + pr_info("Firmware version %d.%d found\n", FFA_MAJOR_VERSION(ver.a0), + FFA_MINOR_VERSION(ver.a0)); *version = ffa_compatible_version_find(ver.a0); return 0; diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index 5f02d2e6b9d9..daff44d777fa 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -11,6 +11,89 @@ #include #include +#define FFA_SMC(calling_convention, func_num) \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, (calling_convention), \ + ARM_SMCCC_OWNER_STANDARD, (func_num)) + +#define FFA_SMC_32(func_num) FFA_SMC(ARM_SMCCC_SMC_32, (func_num)) +#define FFA_SMC_64(func_num) FFA_SMC(ARM_SMCCC_SMC_64, (func_num)) + +#define FFA_ERROR FFA_SMC_32(0x60) +#define FFA_SUCCESS FFA_SMC_32(0x61) +#define FFA_INTERRUPT FFA_SMC_32(0x62) +#define FFA_VERSION FFA_SMC_32(0x63) +#define FFA_FEATURES FFA_SMC_32(0x64) +#define FFA_RX_RELEASE FFA_SMC_32(0x65) +#define FFA_RXTX_MAP FFA_SMC_32(0x66) +#define FFA_FN64_RXTX_MAP FFA_SMC_64(0x66) +#define FFA_RXTX_UNMAP FFA_SMC_32(0x67) +#define FFA_PARTITION_INFO_GET FFA_SMC_32(0x68) +#define FFA_ID_GET FFA_SMC_32(0x69) +#define FFA_MSG_POLL FFA_SMC_32(0x6A) +#define FFA_MSG_WAIT FFA_SMC_32(0x6B) +#define FFA_YIELD FFA_SMC_32(0x6C) +#define FFA_RUN FFA_SMC_32(0x6D) +#define FFA_MSG_SEND FFA_SMC_32(0x6E) +#define FFA_MSG_SEND_DIRECT_REQ FFA_SMC_32(0x6F) +#define FFA_FN64_MSG_SEND_DIRECT_REQ FFA_SMC_64(0x6F) +#define FFA_MSG_SEND_DIRECT_RESP FFA_SMC_32(0x70) +#define FFA_FN64_MSG_SEND_DIRECT_RESP FFA_SMC_64(0x70) +#define FFA_MEM_DONATE FFA_SMC_32(0x71) +#define FFA_FN64_MEM_DONATE FFA_SMC_64(0x71) +#define FFA_MEM_LEND FFA_SMC_32(0x72) +#define FFA_FN64_MEM_LEND FFA_SMC_64(0x72) +#define FFA_MEM_SHARE FFA_SMC_32(0x73) +#define FFA_FN64_MEM_SHARE FFA_SMC_64(0x73) +#define FFA_MEM_RETRIEVE_REQ FFA_SMC_32(0x74) +#define FFA_FN64_MEM_RETRIEVE_REQ FFA_SMC_64(0x74) +#define FFA_MEM_RETRIEVE_RESP FFA_SMC_32(0x75) +#define FFA_MEM_RELINQUISH FFA_SMC_32(0x76) +#define FFA_MEM_RECLAIM FFA_SMC_32(0x77) +#define FFA_MEM_OP_PAUSE FFA_SMC_32(0x78) +#define FFA_MEM_OP_RESUME FFA_SMC_32(0x79) +#define FFA_MEM_FRAG_RX FFA_SMC_32(0x7A) +#define FFA_MEM_FRAG_TX FFA_SMC_32(0x7B) +#define FFA_NORMAL_WORLD_RESUME FFA_SMC_32(0x7C) + +/* + * For some calls it is necessary to use SMC64 to pass or return 64-bit values. + * For such calls FFA_FN_NATIVE(name) will choose the appropriate + * (native-width) function ID. + */ +#ifdef CONFIG_64BIT +#define FFA_FN_NATIVE(name) FFA_FN64_##name +#else +#define FFA_FN_NATIVE(name) FFA_##name +#endif + +/* FFA error codes. */ +#define FFA_RET_SUCCESS (0) +#define FFA_RET_NOT_SUPPORTED (-1) +#define FFA_RET_INVALID_PARAMETERS (-2) +#define FFA_RET_NO_MEMORY (-3) +#define FFA_RET_BUSY (-4) +#define FFA_RET_INTERRUPTED (-5) +#define FFA_RET_DENIED (-6) +#define FFA_RET_RETRY (-7) +#define FFA_RET_ABORTED (-8) + +/* FFA version encoding */ +#define FFA_MAJOR_VERSION_MASK GENMASK(30, 16) +#define FFA_MINOR_VERSION_MASK GENMASK(15, 0) +#define FFA_MAJOR_VERSION(x) ((u16)(FIELD_GET(FFA_MAJOR_VERSION_MASK, (x)))) +#define FFA_MINOR_VERSION(x) ((u16)(FIELD_GET(FFA_MINOR_VERSION_MASK, (x)))) +#define FFA_PACK_VERSION_INFO(major, minor) \ + (FIELD_PREP(FFA_MAJOR_VERSION_MASK, (major)) | \ + FIELD_PREP(FFA_MINOR_VERSION_MASK, (minor))) +#define FFA_VERSION_1_0 FFA_PACK_VERSION_INFO(1, 0) + +/** + * FF-A specification mentions explicitly about '4K pages'. This should + * not be confused with the kernel PAGE_SIZE, which is the translation + * granule kernel is configured and may be one among 4K, 16K and 64K. + */ +#define FFA_PAGE_SIZE SZ_4K + /* FFA Bus/Device/Driver related */ struct ffa_device { int vm_id; -- cgit v1.2.3 From c8e320b00a2a720862b9c028153c681b1a50aa61 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 16 Nov 2022 17:03:25 +0000 Subject: firmware: arm_ffa: Move comment before the field it is documenting This is consistent with the other comments in the struct. Co-developed-by: Andrew Walbran Signed-off-by: Andrew Walbran Signed-off-by: Quentin Perret Reviewed-by: Sudeep Holla Link: https://lore.kernel.org/r/20221116170335.2341003-3-qperret@google.com Signed-off-by: Will Deacon --- include/linux/arm_ffa.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index daff44d777fa..c87aeecaa9b2 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -244,11 +244,11 @@ struct ffa_mem_region_attributes { */ #define FFA_MEM_RETRIEVE_SELF_BORROWER BIT(0) u8 flag; - u32 composite_off; /* * Offset in bytes from the start of the outer `ffa_memory_region` to * an `struct ffa_mem_region_addr_range`. */ + u32 composite_off; u64 reserved; }; -- cgit v1.2.3